{ "segments": [ { "id": 1, "seek": 2870, "start": 0.0, "end": 5.62, "text": " I just want to double check this.", "tokens": [ 50414, 286, 445, 528, 281, 3834, 1520, 341, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.29736327938735485, "compression_ratio": 1.6506550218340612, "no_speech_prob": 0.038970947265625, "words": [ { "start": 0.0, "end": 0.08, "word": " I", "probability": 0.313720703125 }, { "start": 0.08, "end": 0.32, "word": " just", "probability": 0.75 }, { "start": 0.32, "end": 0.58, "word": " want", "probability": 0.5400390625 }, { "start": 0.58, "end": 1.04, "word": " to", "probability": 0.9033203125 }, { "start": 1.04, "end": 2.72, "word": " double", "probability": 0.8564453125 }, { "start": 2.72, "end": 3.58, "word": " check", "probability": 0.71826171875 }, { "start": 3.58, "end": 5.06, "word": " this", "probability": 0.77587890625 }, { "start": 5.06, "end": 5.62, "word": ".", "probability": 0.9072265625 } ] }, { "id": 2, "seek": 2870, "start": 6.28, "end": 10.84, "text": " Alright, cool. I have all my stuff muted and we are good to go.", "tokens": [ 50664, 2798, 11, 1627, 13, 286, 362, 439, 452, 1507, 32808, 293, 321, 366, 665, 281, 352, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.29736327938735485, "compression_ratio": 1.6506550218340612, "no_speech_prob": 0.038970947265625, "words": [ { "start": 6.28, "end": 6.74, "word": " Alright", "probability": 0.1846923828125 }, { "start": 6.74, "end": 6.96, "word": ",", "probability": 0.759765625 }, { "start": 6.96, "end": 7.16, "word": " cool", "probability": 0.85302734375 }, { "start": 7.16, "end": 7.42, "word": ".", "probability": 0.78125 }, { "start": 7.42, "end": 7.52, "word": " I", "probability": 0.8154296875 }, { "start": 7.52, "end": 7.7, "word": " have", "probability": 0.875 }, { "start": 7.7, "end": 7.88, "word": " all", "probability": 0.89306640625 }, { "start": 7.88, "end": 8.04, "word": " my", "probability": 0.90869140625 }, { "start": 8.04, "end": 8.28, "word": " stuff", "probability": 0.8076171875 }, { "start": 8.28, "end": 8.58, "word": " muted", "probability": 0.78271484375 }, { "start": 8.58, "end": 9.0, "word": " and", "probability": 0.6796875 }, { "start": 9.0, "end": 9.24, "word": " we", "probability": 0.90576171875 }, { "start": 9.24, "end": 9.4, "word": " are", "probability": 0.87744140625 }, { "start": 9.4, "end": 9.66, "word": " good", "probability": 0.87744140625 }, { "start": 9.66, "end": 9.9, "word": " to", "probability": 0.90966796875 }, { "start": 9.9, "end": 10.28, "word": " go", "probability": 0.90966796875 }, { "start": 10.28, "end": 10.84, "word": ".", "probability": 0.9560546875 } ] }, { "id": 3, "seek": 2870, "start": 10.96, "end": 15.02, "text": " Hello and welcome to Machine Learning for Security Analysts.", "tokens": [ 50914, 2425, 293, 2928, 281, 22155, 15205, 337, 11164, 1107, 19530, 82, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.29736327938735485, "compression_ratio": 1.6506550218340612, "no_speech_prob": 0.038970947265625, "words": [ { "start": 10.96, "end": 11.44, "word": " Hello", "probability": 0.640625 }, { "start": 11.44, "end": 12.08, "word": " and", "probability": 0.78125 }, { "start": 12.08, "end": 12.56, "word": " welcome", "probability": 0.7646484375 }, { "start": 12.56, "end": 13.08, "word": " to", "probability": 0.8984375 }, { "start": 13.08, "end": 13.56, "word": " Machine", "probability": 0.50439453125 }, { "start": 13.56, "end": 13.86, "word": " Learning", "probability": 0.8466796875 }, { "start": 13.86, "end": 14.04, "word": " for", "probability": 0.87939453125 }, { "start": 14.04, "end": 14.38, "word": " Security", "probability": 0.82373046875 }, { "start": 14.38, "end": 15.02, "word": " Analysts", "probability": 0.8131510416666666 }, { "start": 15.02, "end": 15.02, "word": ".", "probability": 0.93359375 } ] }, { "id": 4, "seek": 2870, "start": 15.02, "end": 18.64, "text": " This is going to be our final workshop for the AI village.", "tokens": [ 51114, 639, 307, 516, 281, 312, 527, 2572, 13541, 337, 264, 7318, 7288, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.29736327938735485, "compression_ratio": 1.6506550218340612, "no_speech_prob": 0.038970947265625, "words": [ { "start": 15.02, "end": 15.2, "word": " This", "probability": 0.81396484375 }, { "start": 15.2, "end": 15.36, "word": " is", "probability": 0.908203125 }, { "start": 15.36, "end": 15.58, "word": " going", "probability": 0.86328125 }, { "start": 15.58, "end": 15.8, "word": " to", "probability": 0.90087890625 }, { "start": 15.8, "end": 16.02, "word": " be", "probability": 0.90380859375 }, { "start": 16.02, "end": 16.42, "word": " our", "probability": 0.82568359375 }, { "start": 16.42, "end": 16.76, "word": " final", "probability": 0.8955078125 }, { "start": 16.76, "end": 17.06, "word": " workshop", "probability": 0.716796875 }, { "start": 17.06, "end": 17.38, "word": " for", "probability": 0.89501953125 }, { "start": 17.38, "end": 17.5, "word": " the", "probability": 0.80126953125 }, { "start": 17.5, "end": 17.72, "word": " AI", "probability": 0.89892578125 }, { "start": 17.72, "end": 18.08, "word": " village", "probability": 0.50390625 }, { "start": 18.08, "end": 18.64, "word": ".", "probability": 0.7744140625 } ] }, { "id": 5, "seek": 2870, "start": 19.02, "end": 21.76, "text": " This is going to be a beginner and interactive workshop", "tokens": [ 51314, 639, 307, 516, 281, 312, 257, 22080, 293, 15141, 13541, 51464 ], "temperature": 0.0, "avg_logprob": -0.29736327938735485, "compression_ratio": 1.6506550218340612, "no_speech_prob": 0.038970947265625, "words": [ { "start": 19.02, "end": 19.18, "word": " This", "probability": 0.5107421875 }, { "start": 19.18, "end": 19.32, "word": " is", "probability": 0.90673828125 }, { "start": 19.32, "end": 19.42, "word": " going", "probability": 0.78515625 }, { "start": 19.42, "end": 19.48, "word": " to", "probability": 0.90283203125 }, { "start": 19.48, "end": 19.6, "word": " be", "probability": 0.8955078125 }, { "start": 19.96, "end": 20.24, "word": " a beginner", "probability": 0.693359375 }, { "start": 20.24, "end": 20.76, "word": " and", "probability": 0.88525390625 }, { "start": 20.76, "end": 21.26, "word": " interactive", "probability": 0.70703125 }, { "start": 21.26, "end": 21.76, "word": " workshop", "probability": 0.69677734375 } ] }, { "id": 6, "seek": 2870, "start": 21.76, "end": 25.26, "text": " for all those who are interested in machine learning and security", "tokens": [ 51514, 337, 439, 729, 567, 366, 3102, 294, 3479, 2539, 293, 3825, 51614 ], "temperature": 0.0, "avg_logprob": -0.29736327938735485, "compression_ratio": 1.6506550218340612, "no_speech_prob": 0.038970947265625, "words": [ { "start": 21.76, "end": 22.78, "word": " for", "probability": 0.845703125 }, { "start": 22.78, "end": 22.96, "word": " all", "probability": 0.90185546875 }, { "start": 22.96, "end": 23.36, "word": " those", "probability": 0.6025390625 }, { "start": 23.36, "end": 23.6, "word": " who", "probability": 0.81787109375 }, { "start": 23.6, "end": 23.82, "word": " are", "probability": 0.89501953125 }, { "start": 23.82, "end": 24.16, "word": " interested", "probability": 0.66064453125 }, { "start": 24.16, "end": 24.32, "word": " in", "probability": 0.89990234375 }, { "start": 24.32, "end": 24.52, "word": " machine", "probability": 0.67919921875 }, { "start": 24.52, "end": 24.76, "word": " learning", "probability": 0.84814453125 }, { "start": 24.76, "end": 24.9, "word": " and", "probability": 0.89599609375 }, { "start": 24.9, "end": 25.26, "word": " security", "probability": 0.927734375 } ] }, { "id": 7, "seek": 2870, "start": 25.26, "end": 28.7, "text": " and what this whole crazy AI thing is.", "tokens": [ 51664, 293, 437, 341, 1379, 3219, 7318, 551, 307, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.29736327938735485, "compression_ratio": 1.6506550218340612, "no_speech_prob": 0.038970947265625, "words": [ { "start": 25.26, "end": 25.92, "word": " and", "probability": 0.689453125 }, { "start": 25.92, "end": 26.14, "word": " what", "probability": 0.8837890625 }, { "start": 26.14, "end": 26.34, "word": " this", "probability": 0.8828125 }, { "start": 26.34, "end": 26.54, "word": " whole", "probability": 0.82177734375 }, { "start": 26.54, "end": 27.04, "word": " crazy", "probability": 0.82958984375 }, { "start": 27.04, "end": 27.48, "word": " AI", "probability": 0.91064453125 }, { "start": 27.48, "end": 27.86, "word": " thing", "probability": 0.81640625 }, { "start": 27.86, "end": 28.14, "word": " is", "probability": 0.90625 }, { "start": 28.14, "end": 28.7, "word": ".", "probability": 0.99658203125 } ] }, { "id": 8, "seek": 5870, "start": 28.7, "end": 31.98, "text": " So really, the major motivation for this workshop", "tokens": [ 50364, 407, 534, 11, 264, 2563, 12335, 337, 341, 13541, 50514 ], "temperature": 0.0, "avg_logprob": -0.28919954728661923, "compression_ratio": 1.5450980392156863, "no_speech_prob": 0.0222625732421875, "words": [ { "start": 28.7, "end": 29.54, "word": " So", "probability": 0.70751953125 }, { "start": 29.54, "end": 29.92, "word": " really", "probability": 0.65576171875 }, { "start": 29.92, "end": 30.14, "word": ",", "probability": 0.310546875 }, { "start": 30.14, "end": 30.4, "word": " the", "probability": 0.8115234375 }, { "start": 30.4, "end": 30.82, "word": " major", "probability": 0.71875 }, { "start": 30.82, "end": 31.24, "word": " motivation", "probability": 0.87158203125 }, { "start": 31.24, "end": 31.5, "word": " for", "probability": 0.89697265625 }, { "start": 31.5, "end": 31.66, "word": " this", "probability": 0.8896484375 }, { "start": 31.66, "end": 31.98, "word": " workshop", "probability": 0.6865234375 } ] }, { "id": 9, "seek": 5870, "start": 31.98, "end": 35.8, "text": " was that we're seeing a lot of buzz in the security community", "tokens": [ 50564, 390, 300, 321, 434, 2577, 257, 688, 295, 13036, 294, 264, 3825, 1768, 50664 ], "temperature": 0.0, "avg_logprob": -0.28919954728661923, "compression_ratio": 1.5450980392156863, "no_speech_prob": 0.0222625732421875, "words": [ { "start": 31.98, "end": 32.56, "word": " was", "probability": 0.8837890625 }, { "start": 32.56, "end": 33.06, "word": " that", "probability": 0.876953125 }, { "start": 33.06, "end": 34.04, "word": " we're", "probability": 0.892578125 }, { "start": 34.04, "end": 34.22, "word": " seeing", "probability": 0.78857421875 }, { "start": 34.34, "end": 34.4, "word": " a lot", "probability": 0.892578125 }, { "start": 34.4, "end": 34.52, "word": " of", "probability": 0.9033203125 }, { "start": 34.52, "end": 34.76, "word": " buzz", "probability": 0.74560546875 }, { "start": 34.76, "end": 34.94, "word": " in", "probability": 0.9013671875 }, { "start": 34.94, "end": 35.06, "word": " the", "probability": 0.810546875 }, { "start": 35.06, "end": 35.32, "word": " security", "probability": 0.93408203125 }, { "start": 35.32, "end": 35.8, "word": " community", "probability": 0.81689453125 } ] }, { "id": 10, "seek": 5870, "start": 35.8, "end": 38.36, "text": " around AI and machine learning.", "tokens": [ 50714, 926, 7318, 293, 3479, 2539, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.28919954728661923, "compression_ratio": 1.5450980392156863, "no_speech_prob": 0.0222625732421875, "words": [ { "start": 35.8, "end": 36.32, "word": " around", "probability": 0.85205078125 }, { "start": 36.32, "end": 36.66, "word": " AI", "probability": 0.9111328125 }, { "start": 36.66, "end": 37.12, "word": " and", "probability": 0.892578125 }, { "start": 37.12, "end": 37.4, "word": " machine", "probability": 0.6904296875 }, { "start": 37.4, "end": 37.8, "word": " learning", "probability": 0.85302734375 }, { "start": 37.8, "end": 38.36, "word": ".", "probability": 0.4345703125 } ] }, { "id": 11, "seek": 5870, "start": 38.36, "end": 42.64, "text": " But for many of us, it's not really clear what that is.", "tokens": [ 50864, 583, 337, 867, 295, 505, 11, 309, 311, 406, 534, 1850, 437, 300, 307, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.28919954728661923, "compression_ratio": 1.5450980392156863, "no_speech_prob": 0.0222625732421875, "words": [ { "start": 38.36, "end": 38.38, "word": " But", "probability": 0.88525390625 }, { "start": 38.38, "end": 38.8, "word": " for", "probability": 0.87353515625 }, { "start": 38.8, "end": 39.2, "word": " many", "probability": 0.8115234375 }, { "start": 39.2, "end": 39.36, "word": " of", "probability": 0.90380859375 }, { "start": 39.36, "end": 39.56, "word": " us", "probability": 0.90673828125 }, { "start": 39.56, "end": 39.6, "word": ",", "probability": 0.9384765625 }, { "start": 39.6, "end": 39.86, "word": " it's", "probability": 0.950927734375 }, { "start": 39.86, "end": 40.02, "word": " not", "probability": 0.89892578125 }, { "start": 40.02, "end": 40.22, "word": " really", "probability": 0.77880859375 }, { "start": 40.22, "end": 40.58, "word": " clear", "probability": 0.80810546875 }, { "start": 40.58, "end": 41.04, "word": " what", "probability": 0.8828125 }, { "start": 41.04, "end": 41.42, "word": " that", "probability": 0.87841796875 }, { "start": 41.42, "end": 42.0, "word": " is", "probability": 0.90380859375 }, { "start": 42.0, "end": 42.64, "word": ".", "probability": 0.90869140625 } ] }, { "id": 12, "seek": 5870, "start": 43.46, "end": 46.62, "text": " So... oh, sorry.", "tokens": [ 51064, 407, 485, 1954, 11, 2597, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.28919954728661923, "compression_ratio": 1.5450980392156863, "no_speech_prob": 0.0222625732421875, "words": [ { "start": 43.46, "end": 44.1, "word": " So...", "probability": 0.4075927734375 }, { "start": 44.1, "end": 44.22, "word": " oh", "probability": 0.013336181640625 }, { "start": 44.22, "end": 44.96, "word": ",", "probability": 0.260498046875 }, { "start": 44.96, "end": 46.0, "word": " sorry", "probability": 0.70361328125 }, { "start": 46.0, "end": 46.62, "word": ".", "probability": 0.814453125 } ] }, { "id": 13, "seek": 5870, "start": 46.62, "end": 49.02, "text": " If you want to participate and ask questions,", "tokens": [ 51264, 759, 291, 528, 281, 8197, 293, 1029, 1651, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.28919954728661923, "compression_ratio": 1.5450980392156863, "no_speech_prob": 0.0222625732421875, "words": [ { "start": 46.62, "end": 46.88, "word": " If", "probability": 0.9072265625 }, { "start": 46.88, "end": 47.0, "word": " you", "probability": 0.896484375 }, { "start": 47.0, "end": 47.16, "word": " want", "probability": 0.7060546875 }, { "start": 47.16, "end": 47.28, "word": " to", "probability": 0.9072265625 }, { "start": 47.28, "end": 47.7, "word": " participate", "probability": 0.82763671875 }, { "start": 47.7, "end": 48.06, "word": " and", "probability": 0.88330078125 }, { "start": 48.06, "end": 48.28, "word": " ask", "probability": 0.81298828125 }, { "start": 48.28, "end": 48.82, "word": " questions", "probability": 0.91455078125 }, { "start": 48.82, "end": 49.02, "word": ",", "probability": 0.88525390625 } ] }, { "id": 14, "seek": 5870, "start": 49.02, "end": 52.1, "text": " head over to the DevSchool channel and join the", "tokens": [ 51414, 1378, 670, 281, 264, 9096, 50, 21856, 2269, 293, 3917, 264, 51514 ], "temperature": 0.0, "avg_logprob": -0.28919954728661923, "compression_ratio": 1.5450980392156863, "no_speech_prob": 0.0222625732421875, "words": [ { "start": 49.02, "end": 49.18, "word": " head", "probability": 0.88916015625 }, { "start": 49.18, "end": 49.36, "word": " over", "probability": 0.88134765625 }, { "start": 49.36, "end": 49.54, "word": " to", "probability": 0.896484375 }, { "start": 49.54, "end": 49.7, "word": " the", "probability": 0.7939453125 }, { "start": 49.7, "end": 50.02, "word": " DevSchool", "probability": 0.44677734375 }, { "start": 50.02, "end": 50.52, "word": " channel", "probability": 0.77734375 }, { "start": 50.52, "end": 51.26, "word": " and", "probability": 0.71826171875 }, { "start": 51.26, "end": 51.84, "word": " join", "probability": 0.215576171875 }, { "start": 51.84, "end": 52.1, "word": " the", "probability": 0.80712890625 } ] }, { "id": 15, "seek": 5870, "start": 52.1, "end": 55.78, "text": " AIVillage-General-Voice, AIV-General-Voice.", "tokens": [ 51564, 7318, 53, 373, 609, 12, 46302, 12, 13339, 11, 7318, 53, 12, 46302, 12, 13339, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.28919954728661923, "compression_ratio": 1.5450980392156863, "no_speech_prob": 0.0222625732421875, "words": [ { "start": 52.1, "end": 52.56, "word": " AIVillage", "probability": 0.662109375 }, { "start": 52.56, "end": 53.04, "word": "-General", "probability": 0.7099609375 }, { "start": 53.04, "end": 53.96, "word": "-Voice", "probability": 0.783203125 }, { "start": 53.96, "end": 54.12, "word": ",", "probability": 0.50732421875 }, { "start": 54.12, "end": 54.46, "word": " AIV", "probability": 0.8134765625 }, { "start": 54.46, "end": 54.94, "word": "-General", "probability": 0.88427734375 }, { "start": 54.94, "end": 55.48, "word": "-Voice", "probability": 0.873291015625 }, { "start": 55.48, "end": 55.78, "word": ".", "probability": 0.364501953125 } ] }, { "id": 16, "seek": 5870, "start": 55.96, "end": 58.68, "text": " And you'll be able to ask us questions.", "tokens": [ 51714, 400, 291, 603, 312, 1075, 281, 1029, 505, 1651, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.28919954728661923, "compression_ratio": 1.5450980392156863, "no_speech_prob": 0.0222625732421875, "words": [ { "start": 55.96, "end": 56.6, "word": " And", "probability": 0.82958984375 }, { "start": 56.6, "end": 56.78, "word": " you'll", "probability": 0.92041015625 }, { "start": 56.78, "end": 56.88, "word": " be", "probability": 0.88525390625 }, { "start": 56.88, "end": 56.96, "word": " able", "probability": 0.8125 }, { "start": 56.96, "end": 57.04, "word": " to", "probability": 0.90185546875 }, { "start": 57.04, "end": 57.26, "word": " ask", "probability": 0.8173828125 }, { "start": 57.26, "end": 57.5, "word": " us", "probability": 0.908203125 }, { "start": 57.5, "end": 58.22, "word": " questions", "probability": 0.9169921875 }, { "start": 58.22, "end": 58.68, "word": ".", "probability": 0.75634765625 } ] }, { "id": 17, "seek": 8870, "start": 59.28, "end": 62.8, "text": " If there's too many people joining and it gets unorganized,", "tokens": [ 50364, 759, 456, 311, 886, 867, 561, 5549, 293, 309, 2170, 517, 12372, 1602, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.20586832220317752, "compression_ratio": 1.611683848797251, "no_speech_prob": 0.006378173828125, "words": [ { "start": 59.28, "end": 59.76, "word": " If", "probability": 0.583984375 }, { "start": 59.76, "end": 60.04, "word": " there's", "probability": 0.8525390625 }, { "start": 60.04, "end": 60.16, "word": " too", "probability": 0.81005859375 }, { "start": 60.16, "end": 60.3, "word": " many", "probability": 0.8056640625 }, { "start": 60.3, "end": 60.54, "word": " people", "probability": 0.9208984375 }, { "start": 60.54, "end": 60.86, "word": " joining", "probability": 0.25 }, { "start": 60.86, "end": 61.38, "word": " and", "probability": 0.6845703125 }, { "start": 61.38, "end": 61.78, "word": " it", "probability": 0.5615234375 }, { "start": 61.78, "end": 62.06, "word": " gets", "probability": 0.78759765625 }, { "start": 62.06, "end": 62.74, "word": " unorganized", "probability": 0.91064453125 }, { "start": 62.74, "end": 62.8, "word": ",", "probability": 0.787109375 } ] }, { "id": 18, "seek": 8870, "start": 62.8, "end": 63.9, "text": " we're going to switch to Zoom.", "tokens": [ 50564, 321, 434, 516, 281, 3679, 281, 13453, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.20586832220317752, "compression_ratio": 1.611683848797251, "no_speech_prob": 0.006378173828125, "words": [ { "start": 62.8, "end": 62.94, "word": " we're", "probability": 0.91357421875 }, { "start": 62.94, "end": 63.0, "word": " going", "probability": 0.65869140625 }, { "start": 63.0, "end": 63.06, "word": " to", "probability": 0.90234375 }, { "start": 63.06, "end": 63.24, "word": " switch", "probability": 0.9365234375 }, { "start": 63.24, "end": 63.4, "word": " to", "probability": 0.90283203125 }, { "start": 63.4, "end": 63.62, "word": " Zoom", "probability": 0.72802734375 }, { "start": 63.62, "end": 63.9, "word": ".", "probability": 0.52392578125 } ] }, { "id": 19, "seek": 8870, "start": 63.9, "end": 68.14, "text": " But it's sort of more open than it was before.", "tokens": [ 50664, 583, 309, 311, 1333, 295, 544, 1269, 813, 309, 390, 949, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.20586832220317752, "compression_ratio": 1.611683848797251, "no_speech_prob": 0.006378173828125, "words": [ { "start": 63.9, "end": 64.04, "word": " But", "probability": 0.81884765625 }, { "start": 64.04, "end": 65.52, "word": " it's", "probability": 0.832275390625 }, { "start": 65.52, "end": 65.7, "word": " sort", "probability": 0.69091796875 }, { "start": 65.7, "end": 65.82, "word": " of", "probability": 0.90283203125 }, { "start": 65.82, "end": 66.2, "word": " more", "probability": 0.875 }, { "start": 66.2, "end": 66.52, "word": " open", "probability": 0.81298828125 }, { "start": 66.52, "end": 66.8, "word": " than", "probability": 0.87060546875 }, { "start": 66.8, "end": 67.1, "word": " it", "probability": 0.89794921875 }, { "start": 67.1, "end": 67.34, "word": " was", "probability": 0.89697265625 }, { "start": 67.34, "end": 67.66, "word": " before", "probability": 0.80419921875 }, { "start": 67.66, "end": 68.14, "word": ".", "probability": 0.9921875 } ] }, { "id": 20, "seek": 8870, "start": 69.0, "end": 71.92, "text": " Sorry, Gavin. Just needed to say that.", "tokens": [ 50864, 4919, 11, 24020, 13, 1449, 2978, 281, 584, 300, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.20586832220317752, "compression_ratio": 1.611683848797251, "no_speech_prob": 0.006378173828125, "words": [ { "start": 69.0, "end": 69.48, "word": " Sorry", "probability": 0.7568359375 }, { "start": 69.48, "end": 69.62, "word": ",", "probability": 0.94970703125 }, { "start": 69.62, "end": 69.78, "word": " Gavin", "probability": 0.72900390625 }, { "start": 69.78, "end": 70.16, "word": ".", "probability": 0.56689453125 }, { "start": 70.16, "end": 70.54, "word": " Just", "probability": 0.345947265625 }, { "start": 70.54, "end": 70.88, "word": " needed", "probability": 0.73876953125 }, { "start": 70.88, "end": 71.06, "word": " to", "probability": 0.8984375 }, { "start": 71.06, "end": 71.22, "word": " say", "probability": 0.90087890625 }, { "start": 71.22, "end": 71.44, "word": " that", "probability": 0.8779296875 }, { "start": 71.44, "end": 71.92, "word": ".", "probability": 0.98681640625 } ] }, { "id": 21, "seek": 8870, "start": 72.26, "end": 74.5, "text": " No worries. Last line of this statement is", "tokens": [ 51014, 883, 16340, 13, 5264, 1622, 295, 341, 5629, 307, 51114 ], "temperature": 0.0, "avg_logprob": -0.20586832220317752, "compression_ratio": 1.611683848797251, "no_speech_prob": 0.006378173828125, "words": [ { "start": 72.26, "end": 72.34, "word": " No", "probability": 0.76318359375 }, { "start": 72.34, "end": 72.64, "word": " worries", "probability": 0.798828125 }, { "start": 72.64, "end": 72.92, "word": ".", "probability": 0.966796875 }, { "start": 72.92, "end": 73.4, "word": " Last", "probability": 0.79541015625 }, { "start": 73.4, "end": 73.54, "word": " line", "probability": 0.477294921875 }, { "start": 73.54, "end": 73.66, "word": " of", "probability": 0.52734375 }, { "start": 73.66, "end": 73.76, "word": " this", "probability": 0.379150390625 }, { "start": 73.76, "end": 74.02, "word": " statement", "probability": 0.859375 }, { "start": 74.02, "end": 74.5, "word": " is", "probability": 0.89697265625 } ] }, { "id": 22, "seek": 8870, "start": 74.5, "end": 76.6, "text": " I wanted to take, for the security community,", "tokens": [ 51164, 286, 1415, 281, 747, 11, 337, 264, 3825, 1768, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.20586832220317752, "compression_ratio": 1.611683848797251, "no_speech_prob": 0.006378173828125, "words": [ { "start": 74.5, "end": 74.62, "word": " I", "probability": 0.399658203125 }, { "start": 74.62, "end": 74.8, "word": " wanted", "probability": 0.78369140625 }, { "start": 74.8, "end": 74.96, "word": " to", "probability": 0.90283203125 }, { "start": 74.96, "end": 75.28, "word": " take", "probability": 0.80419921875 }, { "start": 75.28, "end": 75.44, "word": ",", "probability": 0.3095703125 }, { "start": 75.44, "end": 75.48, "word": " for", "probability": 0.89404296875 }, { "start": 75.48, "end": 75.64, "word": " the", "probability": 0.81298828125 }, { "start": 75.64, "end": 75.88, "word": " security", "probability": 0.931640625 }, { "start": 75.88, "end": 76.28, "word": " community", "probability": 0.80712890625 }, { "start": 76.28, "end": 76.6, "word": ",", "probability": 0.9833984375 } ] }, { "id": 23, "seek": 8870, "start": 76.6, "end": 79.4, "text": " the idea of machine learning and AI out of the buzzword", "tokens": [ 51264, 264, 1558, 295, 3479, 2539, 293, 7318, 484, 295, 264, 13036, 7462, 51364 ], "temperature": 0.0, "avg_logprob": -0.20586832220317752, "compression_ratio": 1.611683848797251, "no_speech_prob": 0.006378173828125, "words": [ { "start": 76.6, "end": 76.72, "word": " the", "probability": 0.80908203125 }, { "start": 76.72, "end": 76.96, "word": " idea", "probability": 0.7861328125 }, { "start": 76.96, "end": 77.12, "word": " of", "probability": 0.90380859375 }, { "start": 77.12, "end": 77.38, "word": " machine", "probability": 0.70703125 }, { "start": 77.38, "end": 77.68, "word": " learning", "probability": 0.8427734375 }, { "start": 77.68, "end": 77.86, "word": " and", "probability": 0.86962890625 }, { "start": 77.86, "end": 78.28, "word": " AI", "probability": 0.79248046875 }, { "start": 78.28, "end": 78.82, "word": " out", "probability": 0.8046875 }, { "start": 78.82, "end": 78.88, "word": " of", "probability": 0.90283203125 }, { "start": 78.88, "end": 78.98, "word": " the", "probability": 0.8056640625 }, { "start": 78.98, "end": 79.4, "word": " buzzword", "probability": 0.872802734375 } ] }, { "id": 24, "seek": 8870, "start": 79.4, "end": 80.72, "text": " and into the mainstream.", "tokens": [ 51414, 293, 666, 264, 15960, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.20586832220317752, "compression_ratio": 1.611683848797251, "no_speech_prob": 0.006378173828125, "words": [ { "start": 79.4, "end": 79.66, "word": " and", "probability": 0.89013671875 }, { "start": 79.66, "end": 79.84, "word": " into", "probability": 0.72412109375 }, { "start": 79.84, "end": 79.96, "word": " the", "probability": 0.74560546875 }, { "start": 79.96, "end": 80.24, "word": " mainstream", "probability": 0.869140625 }, { "start": 80.24, "end": 80.72, "word": ".", "probability": 0.99560546875 } ] }, { "id": 25, "seek": 8870, "start": 82.04, "end": 85.52, "text": " So, my name is Gavin. I go by the pseudonym GT Klondike.", "tokens": [ 51514, 407, 11, 452, 1315, 307, 24020, 13, 286, 352, 538, 264, 25505, 532, 12732, 17530, 16053, 684, 1123, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.20586832220317752, "compression_ratio": 1.611683848797251, "no_speech_prob": 0.006378173828125, "words": [ { "start": 82.04, "end": 82.48, "word": " So", "probability": 0.830078125 }, { "start": 82.48, "end": 82.64, "word": ",", "probability": 0.2003173828125 }, { "start": 82.64, "end": 82.86, "word": " my", "probability": 0.89892578125 }, { "start": 82.86, "end": 82.96, "word": " name", "probability": 0.81591796875 }, { "start": 82.96, "end": 83.1, "word": " is", "probability": 0.9091796875 }, { "start": 83.1, "end": 83.3, "word": " Gavin", "probability": 0.87646484375 }, { "start": 83.3, "end": 83.48, "word": ".", "probability": 0.80908203125 }, { "start": 83.48, "end": 83.62, "word": " I", "probability": 0.9990234375 }, { "start": 83.62, "end": 83.74, "word": " go", "probability": 0.89697265625 }, { "start": 83.74, "end": 83.94, "word": " by", "probability": 0.90380859375 }, { "start": 83.94, "end": 84.22, "word": " the", "probability": 0.81494140625 }, { "start": 84.22, "end": 84.56, "word": " pseudonym", "probability": 0.9560546875 }, { "start": 84.56, "end": 84.9, "word": " GT", "probability": 0.587890625 }, { "start": 84.9, "end": 85.36, "word": " Klondike", "probability": 0.8076171875 }, { "start": 85.36, "end": 85.52, "word": ".", "probability": 0.94775390625 } ] }, { "id": 26, "seek": 8870, "start": 85.52, "end": 88.68, "text": " I'm an independent security researcher and a security consultant.", "tokens": [ 51714, 286, 478, 364, 6695, 3825, 21751, 293, 257, 3825, 24676, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.20586832220317752, "compression_ratio": 1.611683848797251, "no_speech_prob": 0.006378173828125, "words": [ { "start": 85.52, "end": 85.64, "word": " I'm", "probability": 0.994384765625 }, { "start": 85.64, "end": 85.86, "word": " an", "probability": 0.89990234375 }, { "start": 85.86, "end": 86.14, "word": " independent", "probability": 0.775390625 }, { "start": 86.14, "end": 86.5, "word": " security", "probability": 0.89306640625 }, { "start": 86.5, "end": 86.94, "word": " researcher", "probability": 0.75927734375 }, { "start": 86.94, "end": 87.5, "word": " and", "probability": 0.89111328125 }, { "start": 87.76, "end": 88.0, "word": " a security", "probability": 0.92333984375 }, { "start": 88.0, "end": 88.42, "word": " consultant", "probability": 0.8388671875 }, { "start": 88.42, "end": 88.68, "word": ".", "probability": 0.916015625 } ] }, { "id": 27, "seek": 11768, "start": 88.7, "end": 92.72, "text": " I'm very passionate about network attack and defense.", "tokens": [ 50364, 286, 478, 588, 11410, 466, 3209, 2690, 293, 7654, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.19002015744486161, "compression_ratio": 1.5973154362416107, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 88.7, "end": 89.46, "word": " I'm", "probability": 0.755615234375 }, { "start": 89.46, "end": 89.64, "word": " very", "probability": 0.69677734375 }, { "start": 89.64, "end": 90.06, "word": " passionate", "probability": 0.771484375 }, { "start": 90.06, "end": 90.64, "word": " about", "probability": 0.82421875 }, { "start": 90.64, "end": 91.0, "word": " network", "probability": 0.8271484375 }, { "start": 91.0, "end": 91.38, "word": " attack", "probability": 0.822265625 }, { "start": 91.38, "end": 91.72, "word": " and", "probability": 0.88818359375 }, { "start": 91.72, "end": 92.22, "word": " defense", "probability": 0.80810546875 }, { "start": 92.22, "end": 92.72, "word": ".", "probability": 0.357666015625 } ] }, { "id": 28, "seek": 11768, "start": 92.72, "end": 95.4, "text": " And through that passion, I run a project called NetSecExplain,", "tokens": [ 50564, 400, 807, 300, 5418, 11, 286, 1190, 257, 1716, 1219, 6188, 29511, 11149, 34821, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.19002015744486161, "compression_ratio": 1.5973154362416107, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 92.72, "end": 92.72, "word": " And", "probability": 0.60791015625 }, { "start": 92.72, "end": 92.94, "word": " through", "probability": 0.76806640625 }, { "start": 92.94, "end": 93.12, "word": " that", "probability": 0.880859375 }, { "start": 93.12, "end": 93.48, "word": " passion", "probability": 0.83447265625 }, { "start": 93.48, "end": 93.68, "word": ",", "probability": 0.74462890625 }, { "start": 93.68, "end": 93.68, "word": " I", "probability": 0.99755859375 }, { "start": 93.68, "end": 93.8, "word": " run", "probability": 0.85595703125 }, { "start": 93.88, "end": 94.18, "word": " a project", "probability": 0.83447265625 }, { "start": 94.18, "end": 94.42, "word": " called", "probability": 0.78125 }, { "start": 94.42, "end": 95.16, "word": " NetSecExplain", "probability": 0.60943603515625 }, { "start": 95.16, "end": 95.4, "word": ",", "probability": 0.7880859375 } ] }, { "id": 29, "seek": 11768, "start": 95.4, "end": 97.34, "text": " which is a blog and a YouTube channel,", "tokens": [ 50714, 597, 307, 257, 6968, 293, 257, 3088, 2269, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.19002015744486161, "compression_ratio": 1.5973154362416107, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 95.4, "end": 95.56, "word": " which", "probability": 0.912109375 }, { "start": 95.56, "end": 95.68, "word": " is", "probability": 0.90478515625 }, { "start": 95.78, "end": 96.14, "word": " a blog", "probability": 0.8125 }, { "start": 96.14, "end": 96.3, "word": " and", "probability": 0.88671875 }, { "start": 96.42, "end": 96.62, "word": " a YouTube", "probability": 0.79150390625 }, { "start": 96.62, "end": 97.14, "word": " channel", "probability": 0.7978515625 }, { "start": 97.14, "end": 97.34, "word": ",", "probability": 0.31884765625 } ] }, { "id": 30, "seek": 11768, "start": 97.34, "end": 99.9, "text": " where I explain intermediate and advanced level", "tokens": [ 50814, 689, 286, 2903, 19376, 293, 7339, 1496, 50914 ], "temperature": 0.0, "avg_logprob": -0.19002015744486161, "compression_ratio": 1.5973154362416107, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 97.34, "end": 97.8, "word": " where", "probability": 0.9033203125 }, { "start": 97.8, "end": 98.02, "word": " I", "probability": 0.99853515625 }, { "start": 98.02, "end": 98.46, "word": " explain", "probability": 0.818359375 }, { "start": 98.46, "end": 98.94, "word": " intermediate", "probability": 0.76806640625 }, { "start": 98.94, "end": 99.14, "word": " and", "probability": 0.87353515625 }, { "start": 99.14, "end": 99.52, "word": " advanced", "probability": 0.84716796875 }, { "start": 99.52, "end": 99.9, "word": " level", "probability": 0.7353515625 } ] }, { "id": 31, "seek": 11768, "start": 99.9, "end": 103.18, "text": " computer networking concepts and security concepts", "tokens": [ 50964, 3820, 17985, 10392, 293, 3825, 10392, 51064 ], "temperature": 0.0, "avg_logprob": -0.19002015744486161, "compression_ratio": 1.5973154362416107, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 99.9, "end": 100.42, "word": " computer", "probability": 0.61474609375 }, { "start": 100.42, "end": 100.76, "word": " networking", "probability": 0.67529296875 }, { "start": 100.76, "end": 101.48, "word": " concepts", "probability": 0.77685546875 }, { "start": 101.48, "end": 102.44, "word": " and", "probability": 0.71923828125 }, { "start": 102.44, "end": 102.72, "word": " security", "probability": 0.9208984375 }, { "start": 102.72, "end": 103.18, "word": " concepts", "probability": 0.70263671875 } ] }, { "id": 32, "seek": 11768, "start": 103.55, "end": 105.8, "text": " in an easy-to-understand way.", "tokens": [ 51114, 294, 364, 1858, 12, 1353, 12, 6617, 1115, 636, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.19002015744486161, "compression_ratio": 1.5973154362416107, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 103.55, "end": 103.8, "word": " in", "probability": 0.8896484375 }, { "start": 103.8, "end": 104.08, "word": " an", "probability": 0.90625 }, { "start": 104.08, "end": 104.32, "word": " easy", "probability": 0.80810546875 }, { "start": 104.32, "end": 104.48, "word": "-to", "probability": 0.60345458984375 }, { "start": 104.48, "end": 104.94, "word": "-understand", "probability": 0.9020182291666666 }, { "start": 104.94, "end": 105.3, "word": " way", "probability": 0.89794921875 }, { "start": 105.3, "end": 105.8, "word": ".", "probability": 0.99755859375 } ] }, { "id": 33, "seek": 11768, "start": 107.42, "end": 109.92, "text": " So, before I get started, usually in person,", "tokens": [ 51264, 407, 11, 949, 286, 483, 1409, 11, 2673, 294, 954, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.19002015744486161, "compression_ratio": 1.5973154362416107, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 107.42, "end": 107.84, "word": " So", "probability": 0.77197265625 }, { "start": 107.84, "end": 107.98, "word": ",", "probability": 0.251708984375 }, { "start": 107.98, "end": 108.2, "word": " before", "probability": 0.8037109375 }, { "start": 108.2, "end": 108.32, "word": " I", "probability": 0.89208984375 }, { "start": 108.32, "end": 108.42, "word": " get", "probability": 0.90478515625 }, { "start": 108.42, "end": 108.7, "word": " started", "probability": 0.80322265625 }, { "start": 108.7, "end": 108.98, "word": ",", "probability": 0.96240234375 }, { "start": 108.98, "end": 109.36, "word": " usually", "probability": 0.7646484375 }, { "start": 109.36, "end": 109.56, "word": " in", "probability": 0.8779296875 }, { "start": 109.56, "end": 109.82, "word": " person", "probability": 0.7568359375 }, { "start": 109.82, "end": 109.92, "word": ",", "probability": 0.7548828125 } ] }, { "id": 34, "seek": 11768, "start": 109.92, "end": 111.36, "text": " this is where I ask people,", "tokens": [ 51414, 341, 307, 689, 286, 1029, 561, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.19002015744486161, "compression_ratio": 1.5973154362416107, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 109.92, "end": 110.06, "word": " this", "probability": 0.8818359375 }, { "start": 110.06, "end": 110.16, "word": " is", "probability": 0.9013671875 }, { "start": 110.16, "end": 110.3, "word": " where", "probability": 0.90478515625 }, { "start": 110.3, "end": 110.42, "word": " I", "probability": 0.99853515625 }, { "start": 110.42, "end": 110.66, "word": " ask", "probability": 0.8125 }, { "start": 110.66, "end": 111.02, "word": " people", "probability": 0.921875 }, { "start": 111.02, "end": 111.36, "word": ",", "probability": 0.84326171875 } ] }, { "id": 35, "seek": 11768, "start": 111.36, "end": 113.28, "text": " what are your thoughts when you hear the word", "tokens": [ 51514, 437, 366, 428, 4598, 562, 291, 1568, 264, 1349, 51564 ], "temperature": 0.0, "avg_logprob": -0.19002015744486161, "compression_ratio": 1.5973154362416107, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 111.36, "end": 111.84, "word": " what", "probability": 0.383544921875 }, { "start": 111.84, "end": 111.92, "word": " are", "probability": 0.88720703125 }, { "start": 111.92, "end": 112.04, "word": " your", "probability": 0.80712890625 }, { "start": 112.04, "end": 112.28, "word": " thoughts", "probability": 0.80419921875 }, { "start": 112.28, "end": 112.44, "word": " when", "probability": 0.86865234375 }, { "start": 112.44, "end": 112.56, "word": " you", "probability": 0.8935546875 }, { "start": 112.56, "end": 112.8, "word": " hear", "probability": 0.88818359375 }, { "start": 112.8, "end": 113.04, "word": " the", "probability": 0.80810546875 }, { "start": 113.04, "end": 113.28, "word": " word", "probability": 0.80029296875 } ] }, { "id": 36, "seek": 11768, "start": 113.28, "end": 115.38, "text": " machine learning? Right?", "tokens": [ 51614, 3479, 2539, 30, 1779, 30, 51664 ], "temperature": 0.0, "avg_logprob": -0.19002015744486161, "compression_ratio": 1.5973154362416107, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 113.28, "end": 113.8, "word": " machine", "probability": 0.36669921875 }, { "start": 113.8, "end": 114.16, "word": " learning", "probability": 0.8251953125 }, { "start": 114.16, "end": 114.66, "word": "?", "probability": 0.708984375 }, { "start": 114.76, "end": 114.9, "word": " Right", "probability": 0.1943359375 }, { "start": 114.9, "end": 115.38, "word": "?", "probability": 0.7177734375 } ] }, { "id": 37, "seek": 11768, "start": 115.38, "end": 117.68, "text": " And I've gotten a range of answers in the past", "tokens": [ 51714, 400, 286, 600, 5768, 257, 3613, 295, 6338, 294, 264, 1791, 51764 ], "temperature": 0.0, "avg_logprob": -0.19002015744486161, "compression_ratio": 1.5973154362416107, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 115.38, "end": 115.82, "word": " And", "probability": 0.84423828125 }, { "start": 115.82, "end": 115.92, "word": " I've", "probability": 0.97265625 }, { "start": 115.92, "end": 116.08, "word": " gotten", "probability": 0.8173828125 }, { "start": 116.24, "end": 116.54, "word": " a range", "probability": 0.77294921875 }, { "start": 116.54, "end": 116.66, "word": " of", "probability": 0.90966796875 }, { "start": 116.66, "end": 116.94, "word": " answers", "probability": 0.830078125 }, { "start": 116.94, "end": 117.1, "word": " in", "probability": 0.9052734375 }, { "start": 117.1, "end": 117.2, "word": " the", "probability": 0.8115234375 }, { "start": 117.2, "end": 117.68, "word": " past", "probability": 0.80810546875 } ] }, { "id": 38, "seek": 14768, "start": 117.68, "end": 121.48, "text": " that range from, oh, Skynet's going to take over the world,", "tokens": [ 50364, 300, 3613, 490, 11, 1954, 11, 7324, 2534, 302, 311, 516, 281, 747, 670, 264, 1002, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.19887743239263886, "compression_ratio": 1.5515873015873016, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 117.68, "end": 118.1, "word": " that", "probability": 0.1285400390625 }, { "start": 118.1, "end": 118.54, "word": " range", "probability": 0.71826171875 }, { "start": 118.54, "end": 119.12, "word": " from", "probability": 0.806640625 }, { "start": 119.12, "end": 119.28, "word": ",", "probability": 0.529296875 }, { "start": 119.28, "end": 119.42, "word": " oh", "probability": 0.475830078125 }, { "start": 119.42, "end": 119.6, "word": ",", "probability": 0.6865234375 }, { "start": 119.6, "end": 120.06, "word": " Skynet's", "probability": 0.880859375 }, { "start": 120.06, "end": 120.16, "word": " going", "probability": 0.289794921875 }, { "start": 120.16, "end": 120.24, "word": " to", "probability": 0.90478515625 }, { "start": 120.24, "end": 120.42, "word": " take", "probability": 0.80712890625 }, { "start": 120.42, "end": 120.56, "word": " over", "probability": 0.87255859375 }, { "start": 120.56, "end": 120.7, "word": " the", "probability": 0.8125 }, { "start": 120.7, "end": 121.14, "word": " world", "probability": 0.888671875 }, { "start": 121.14, "end": 121.48, "word": ",", "probability": 0.45849609375 } ] }, { "id": 39, "seek": 14768, "start": 121.48, "end": 124.76, "text": " to you need a PhD in multivariable calculus", "tokens": [ 50564, 281, 291, 643, 257, 14476, 294, 2120, 592, 3504, 712, 33400, 50714 ], "temperature": 0.0, "avg_logprob": -0.19887743239263886, "compression_ratio": 1.5515873015873016, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 121.48, "end": 121.74, "word": " to", "probability": 0.89697265625 }, { "start": 121.74, "end": 122.38, "word": " you", "probability": 0.76611328125 }, { "start": 122.38, "end": 122.6, "word": " need", "probability": 0.81201171875 }, { "start": 122.88, "end": 123.32, "word": " a PhD", "probability": 0.72119140625 }, { "start": 123.32, "end": 123.72, "word": " in", "probability": 0.89306640625 }, { "start": 123.72, "end": 124.3, "word": " multivariable", "probability": 0.8970947265625 }, { "start": 124.3, "end": 124.76, "word": " calculus", "probability": 0.77978515625 } ] }, { "id": 40, "seek": 14768, "start": 124.76, "end": 126.62, "text": " and linear algebra.", "tokens": [ 50764, 293, 8213, 21989, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.19887743239263886, "compression_ratio": 1.5515873015873016, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 124.76, "end": 125.34, "word": " and", "probability": 0.83642578125 }, { "start": 125.34, "end": 125.6, "word": " linear", "probability": 0.796875 }, { "start": 125.6, "end": 126.02, "word": " algebra", "probability": 0.72314453125 }, { "start": 126.02, "end": 126.62, "word": ".", "probability": 0.81005859375 } ] }, { "id": 41, "seek": 14768, "start": 127.7, "end": 131.64, "text": " And while there is a mild amount of truth", "tokens": [ 50864, 400, 1339, 456, 307, 257, 15154, 2372, 295, 3494, 51014 ], "temperature": 0.0, "avg_logprob": -0.19887743239263886, "compression_ratio": 1.5515873015873016, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 127.7, "end": 127.98, "word": " And", "probability": 0.8037109375 }, { "start": 127.98, "end": 128.4, "word": " while", "probability": 0.88916015625 }, { "start": 128.4, "end": 128.74, "word": " there", "probability": 0.8564453125 }, { "start": 128.74, "end": 129.04, "word": " is", "probability": 0.90576171875 }, { "start": 130.48, "end": 131.0, "word": " a mild", "probability": 0.76416015625 }, { "start": 131.0, "end": 131.24, "word": " amount", "probability": 0.8603515625 }, { "start": 131.24, "end": 131.38, "word": " of", "probability": 0.90625 }, { "start": 131.38, "end": 131.64, "word": " truth", "probability": 0.85693359375 } ] }, { "id": 42, "seek": 14768, "start": 131.64, "end": 134.12, "text": " to the math background that you should have,", "tokens": [ 51064, 281, 264, 5221, 3678, 300, 291, 820, 362, 11, 51164 ], "temperature": 0.0, "avg_logprob": -0.19887743239263886, "compression_ratio": 1.5515873015873016, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 131.64, "end": 131.84, "word": " to", "probability": 0.8984375 }, { "start": 131.84, "end": 132.12, "word": " the", "probability": 0.810546875 }, { "start": 132.12, "end": 132.5, "word": " math", "probability": 0.88720703125 }, { "start": 132.5, "end": 132.94, "word": " background", "probability": 0.76806640625 }, { "start": 132.94, "end": 133.1, "word": " that", "probability": 0.8681640625 }, { "start": 133.1, "end": 133.2, "word": " you", "probability": 0.89599609375 }, { "start": 133.2, "end": 133.34, "word": " should", "probability": 0.9287109375 }, { "start": 133.34, "end": 133.78, "word": " have", "probability": 0.8837890625 }, { "start": 133.78, "end": 134.12, "word": ",", "probability": 0.97021484375 } ] }, { "id": 43, "seek": 14768, "start": 134.6, "end": 136.52, "text": " neither of those are really true.", "tokens": [ 51214, 9662, 295, 729, 366, 534, 2074, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.19887743239263886, "compression_ratio": 1.5515873015873016, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 134.6, "end": 134.9, "word": " neither", "probability": 0.87060546875 }, { "start": 134.9, "end": 135.1, "word": " of", "probability": 0.904296875 }, { "start": 135.1, "end": 135.26, "word": " those", "probability": 0.8447265625 }, { "start": 135.26, "end": 135.36, "word": " are", "probability": 0.890625 }, { "start": 135.36, "end": 135.56, "word": " really", "probability": 0.779296875 }, { "start": 135.56, "end": 135.92, "word": " true", "probability": 0.90576171875 }, { "start": 135.92, "end": 136.52, "word": ".", "probability": 0.994140625 } ] }, { "id": 44, "seek": 14768, "start": 137.92, "end": 141.22, "text": " Instead, machine learning is really a form of pattern matching.", "tokens": [ 51364, 7156, 11, 3479, 2539, 307, 534, 257, 1254, 295, 5102, 14324, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.19887743239263886, "compression_ratio": 1.5515873015873016, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 137.92, "end": 138.52, "word": " Instead", "probability": 0.92529296875 }, { "start": 138.52, "end": 138.74, "word": ",", "probability": 0.888671875 }, { "start": 138.74, "end": 138.92, "word": " machine", "probability": 0.6962890625 }, { "start": 138.92, "end": 139.14, "word": " learning", "probability": 0.8447265625 }, { "start": 139.14, "end": 139.32, "word": " is", "probability": 0.89990234375 }, { "start": 139.32, "end": 139.64, "word": " really", "probability": 0.763671875 }, { "start": 140.2, "end": 140.4, "word": " a form", "probability": 0.79150390625 }, { "start": 140.4, "end": 140.54, "word": " of", "probability": 0.90283203125 }, { "start": 140.54, "end": 140.8, "word": " pattern", "probability": 0.7490234375 }, { "start": 140.8, "end": 141.1, "word": " matching", "probability": 0.68212890625 }, { "start": 141.1, "end": 141.22, "word": ".", "probability": 0.59521484375 } ] }, { "id": 45, "seek": 14768, "start": 141.22, "end": 142.74, "text": " It's applied statistics.", "tokens": [ 51564, 467, 311, 6456, 12523, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.19887743239263886, "compression_ratio": 1.5515873015873016, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 141.22, "end": 141.28, "word": " It's", "probability": 0.948974609375 }, { "start": 141.28, "end": 141.6, "word": " applied", "probability": 0.67529296875 }, { "start": 141.6, "end": 142.38, "word": " statistics", "probability": 0.8798828125 }, { "start": 142.38, "end": 142.74, "word": ".", "probability": 0.499755859375 } ] }, { "id": 46, "seek": 14768, "start": 142.74, "end": 147.38, "text": " And with the increase in power behind the computer memory", "tokens": [ 51664, 400, 365, 264, 3488, 294, 1347, 2261, 264, 3820, 4675, 51814 ], "temperature": 0.0, "avg_logprob": -0.19887743239263886, "compression_ratio": 1.5515873015873016, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 142.74, "end": 142.8, "word": " And", "probability": 0.88330078125 }, { "start": 142.8, "end": 143.02, "word": " with", "probability": 0.8134765625 }, { "start": 143.02, "end": 143.36, "word": " the", "probability": 0.8115234375 }, { "start": 143.36, "end": 143.88, "word": " increase", "probability": 0.765625 }, { "start": 143.88, "end": 144.08, "word": " in", "probability": 0.90625 }, { "start": 144.08, "end": 144.6, "word": " power", "probability": 0.80126953125 }, { "start": 144.6, "end": 145.66, "word": " behind", "probability": 0.8515625 }, { "start": 145.66, "end": 146.34, "word": " the", "probability": 0.81005859375 }, { "start": 146.34, "end": 146.92, "word": " computer", "probability": 0.6357421875 }, { "start": 146.92, "end": 147.38, "word": " memory", "probability": 0.75537109375 } ] }, { "id": 47, "seek": 17336, "start": 147.68, "end": 148.52, "text": " and behind the CPU,", "tokens": [ 50364, 293, 2261, 264, 13199, 11, 50414 ], "temperature": 0.0, "avg_logprob": -0.19531249455534494, "compression_ratio": 1.6398305084745763, "no_speech_prob": 3.594160079956055e-05, "words": [ { "start": 147.68, "end": 148.16, "word": " and", "probability": 0.028411865234375 }, { "start": 148.16, "end": 148.16, "word": " behind", "probability": 0.00011008977890014648 }, { "start": 148.16, "end": 148.16, "word": " the", "probability": 0.49462890625 }, { "start": 148.16, "end": 148.16, "word": " CPU", "probability": 0.2890625 }, { "start": 148.16, "end": 148.52, "word": ",", "probability": 0.52099609375 } ] }, { "id": 48, "seek": 17336, "start": 148.52, "end": 150.2, "text": " we're able to use these statistics", "tokens": [ 50464, 321, 434, 1075, 281, 764, 613, 12523, 50514 ], "temperature": 0.0, "avg_logprob": -0.19531249455534494, "compression_ratio": 1.6398305084745763, "no_speech_prob": 3.594160079956055e-05, "words": [ { "start": 148.52, "end": 148.82, "word": " we're", "probability": 0.7978515625 }, { "start": 148.82, "end": 149.06, "word": " able", "probability": 0.8671875 }, { "start": 149.06, "end": 149.22, "word": " to", "probability": 0.90576171875 }, { "start": 149.22, "end": 149.52, "word": " use", "probability": 0.8154296875 }, { "start": 149.52, "end": 149.7, "word": " these", "probability": 0.67919921875 }, { "start": 149.7, "end": 150.2, "word": " statistics", "probability": 0.8720703125 } ] }, { "id": 49, "seek": 17336, "start": 150.2, "end": 154.38, "text": " in a much quicker, more processed way.", "tokens": [ 50564, 294, 257, 709, 16255, 11, 544, 18846, 636, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.19531249455534494, "compression_ratio": 1.6398305084745763, "no_speech_prob": 3.594160079956055e-05, "words": [ { "start": 150.2, "end": 150.46, "word": " in", "probability": 0.884765625 }, { "start": 150.82, "end": 151.38, "word": " a much", "probability": 0.80810546875 }, { "start": 151.38, "end": 152.16, "word": " quicker", "probability": 0.79296875 }, { "start": 152.16, "end": 152.48, "word": ",", "probability": 0.86962890625 }, { "start": 152.48, "end": 152.84, "word": " more", "probability": 0.88427734375 }, { "start": 152.84, "end": 153.42, "word": " processed", "probability": 0.767578125 }, { "start": 153.42, "end": 153.78, "word": " way", "probability": 0.8984375 }, { "start": 153.78, "end": 154.38, "word": ".", "probability": 0.98974609375 } ] }, { "id": 50, "seek": 17336, "start": 155.98, "end": 157.62, "text": " So, first I want to kind of cover", "tokens": [ 50764, 407, 11, 700, 286, 528, 281, 733, 295, 2060, 50864 ], "temperature": 0.0, "avg_logprob": -0.19531249455534494, "compression_ratio": 1.6398305084745763, "no_speech_prob": 3.594160079956055e-05, "words": [ { "start": 155.98, "end": 156.58, "word": " So", "probability": 0.73095703125 }, { "start": 156.58, "end": 156.64, "word": ",", "probability": 0.10760498046875 }, { "start": 156.64, "end": 156.8, "word": " first", "probability": 0.8115234375 }, { "start": 156.8, "end": 156.9, "word": " I", "probability": 0.72216796875 }, { "start": 156.9, "end": 157.0, "word": " want", "probability": 0.56494140625 }, { "start": 157.0, "end": 157.08, "word": " to", "probability": 0.90087890625 }, { "start": 157.08, "end": 157.22, "word": " kind", "probability": 0.6123046875 }, { "start": 157.22, "end": 157.3, "word": " of", "probability": 0.91064453125 }, { "start": 157.3, "end": 157.62, "word": " cover", "probability": 0.85791015625 } ] }, { "id": 51, "seek": 17336, "start": 157.62, "end": 159.9, "text": " this idea of machine learning,", "tokens": [ 50914, 341, 1558, 295, 3479, 2539, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.19531249455534494, "compression_ratio": 1.6398305084745763, "no_speech_prob": 3.594160079956055e-05, "words": [ { "start": 157.62, "end": 158.24, "word": " this", "probability": 0.8671875 }, { "start": 158.24, "end": 158.56, "word": " idea", "probability": 0.7705078125 }, { "start": 158.56, "end": 159.0, "word": " of", "probability": 0.8994140625 }, { "start": 159.0, "end": 159.32, "word": " machine", "probability": 0.68603515625 }, { "start": 159.32, "end": 159.7, "word": " learning", "probability": 0.84033203125 }, { "start": 159.7, "end": 159.9, "word": ",", "probability": 0.96826171875 } ] }, { "id": 52, "seek": 17336, "start": 159.9, "end": 161.92, "text": " artificial intelligence, and deep learning.", "tokens": [ 51014, 11677, 7599, 11, 293, 2452, 2539, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.19531249455534494, "compression_ratio": 1.6398305084745763, "no_speech_prob": 3.594160079956055e-05, "words": [ { "start": 159.9, "end": 160.12, "word": " artificial", "probability": 0.806640625 }, { "start": 160.12, "end": 160.72, "word": " intelligence", "probability": 0.68798828125 }, { "start": 160.72, "end": 160.86, "word": ",", "probability": 0.6669921875 }, { "start": 160.86, "end": 160.98, "word": " and", "probability": 0.89013671875 }, { "start": 160.98, "end": 161.2, "word": " deep", "probability": 0.9150390625 }, { "start": 161.2, "end": 161.52, "word": " learning", "probability": 0.83203125 }, { "start": 161.52, "end": 161.92, "word": ".", "probability": 0.97265625 } ] }, { "id": 53, "seek": 17336, "start": 161.92, "end": 165.12, "text": " In a lot of areas, it's being used interchangeably,", "tokens": [ 51114, 682, 257, 688, 295, 3179, 11, 309, 311, 885, 1143, 30358, 1188, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.19531249455534494, "compression_ratio": 1.6398305084745763, "no_speech_prob": 3.594160079956055e-05, "words": [ { "start": 161.92, "end": 162.44, "word": " In", "probability": 0.88916015625 }, { "start": 162.72, "end": 162.84, "word": " a lot", "probability": 0.888671875 }, { "start": 162.84, "end": 162.94, "word": " of", "probability": 0.9033203125 }, { "start": 162.94, "end": 163.32, "word": " areas", "probability": 0.86767578125 }, { "start": 163.32, "end": 163.54, "word": ",", "probability": 0.6611328125 }, { "start": 163.54, "end": 163.78, "word": " it's", "probability": 0.94580078125 }, { "start": 163.78, "end": 163.98, "word": " being", "probability": 0.890625 }, { "start": 163.98, "end": 164.22, "word": " used", "probability": 0.82080078125 }, { "start": 164.22, "end": 164.96, "word": " interchangeably", "probability": 0.91650390625 }, { "start": 164.96, "end": 165.12, "word": ",", "probability": 0.66259765625 } ] }, { "id": 54, "seek": 17336, "start": 165.12, "end": 166.96, "text": " and that's not really correct.", "tokens": [ 51264, 293, 300, 311, 406, 534, 3006, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.19531249455534494, "compression_ratio": 1.6398305084745763, "no_speech_prob": 3.594160079956055e-05, "words": [ { "start": 165.12, "end": 165.44, "word": " and", "probability": 0.89453125 }, { "start": 165.44, "end": 165.62, "word": " that's", "probability": 0.9423828125 }, { "start": 165.62, "end": 165.74, "word": " not", "probability": 0.8935546875 }, { "start": 165.74, "end": 165.94, "word": " really", "probability": 0.78466796875 }, { "start": 165.94, "end": 166.36, "word": " correct", "probability": 0.87060546875 }, { "start": 166.36, "end": 166.96, "word": ".", "probability": 0.998046875 } ] }, { "id": 55, "seek": 17336, "start": 167.24, "end": 169.44, "text": " First, what we have is this large umbrella", "tokens": [ 51364, 2386, 11, 437, 321, 362, 307, 341, 2416, 21925, 51464 ], "temperature": 0.0, "avg_logprob": -0.19531249455534494, "compression_ratio": 1.6398305084745763, "no_speech_prob": 3.594160079956055e-05, "words": [ { "start": 167.24, "end": 167.64, "word": " First", "probability": 0.88818359375 }, { "start": 167.64, "end": 167.72, "word": ",", "probability": 0.89501953125 }, { "start": 167.72, "end": 167.8, "word": " what", "probability": 0.87890625 }, { "start": 167.8, "end": 167.92, "word": " we", "probability": 0.90673828125 }, { "start": 167.92, "end": 168.12, "word": " have", "probability": 0.876953125 }, { "start": 168.12, "end": 168.28, "word": " is", "probability": 0.89794921875 }, { "start": 168.28, "end": 168.5, "word": " this", "probability": 0.88427734375 }, { "start": 168.5, "end": 168.92, "word": " large", "probability": 0.92626953125 }, { "start": 168.92, "end": 169.44, "word": " umbrella", "probability": 0.748046875 } ] }, { "id": 56, "seek": 17336, "start": 169.44, "end": 171.62, "text": " of artificial intelligence.", "tokens": [ 51514, 295, 11677, 7599, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.19531249455534494, "compression_ratio": 1.6398305084745763, "no_speech_prob": 3.594160079956055e-05, "words": [ { "start": 169.44, "end": 170.34, "word": " of", "probability": 0.8974609375 }, { "start": 170.34, "end": 170.86, "word": " artificial", "probability": 0.81982421875 }, { "start": 170.86, "end": 171.48, "word": " intelligence", "probability": 0.689453125 }, { "start": 171.48, "end": 171.62, "word": ".", "probability": 0.40576171875 } ] }, { "id": 57, "seek": 17336, "start": 171.62, "end": 173.36, "text": " And artificial intelligence is", "tokens": [ 51614, 400, 11677, 7599, 307, 51714 ], "temperature": 0.0, "avg_logprob": -0.19531249455534494, "compression_ratio": 1.6398305084745763, "no_speech_prob": 3.594160079956055e-05, "words": [ { "start": 171.62, "end": 171.7, "word": " And", "probability": 0.74169921875 }, { "start": 171.7, "end": 172.02, "word": " artificial", "probability": 0.7822265625 }, { "start": 172.02, "end": 172.58, "word": " intelligence", "probability": 0.70458984375 }, { "start": 172.58, "end": 173.36, "word": " is", "probability": 0.90478515625 } ] }, { "id": 58, "seek": 20202, "start": 174.22, "end": 178.34, "text": " kind of a philosophy, in my opinion.", "tokens": [ 50414, 733, 295, 257, 10675, 11, 294, 452, 4800, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.19531250059604643, "compression_ratio": 1.858974358974359, "no_speech_prob": 0.00016605854034423828, "words": [ { "start": 174.22, "end": 174.54, "word": " kind", "probability": 0.06982421875 }, { "start": 174.54, "end": 176.18, "word": " of", "probability": 0.9052734375 }, { "start": 176.34, "end": 176.84, "word": " a philosophy", "probability": 0.6806640625 }, { "start": 176.84, "end": 177.2, "word": ",", "probability": 0.379638671875 }, { "start": 177.2, "end": 177.28, "word": " in", "probability": 0.88623046875 }, { "start": 177.28, "end": 177.46, "word": " my", "probability": 0.90380859375 }, { "start": 177.46, "end": 177.82, "word": " opinion", "probability": 0.8271484375 }, { "start": 177.82, "end": 178.34, "word": ".", "probability": 0.828125 } ] }, { "id": 59, "seek": 20202, "start": 178.34, "end": 180.32, "text": " Artificial intelligence used to be,", "tokens": [ 50614, 5735, 10371, 7599, 1143, 281, 312, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.19531250059604643, "compression_ratio": 1.858974358974359, "no_speech_prob": 0.00016605854034423828, "words": [ { "start": 178.34, "end": 178.84, "word": " Artificial", "probability": 0.89013671875 }, { "start": 178.84, "end": 179.4, "word": " intelligence", "probability": 0.626953125 }, { "start": 179.4, "end": 179.76, "word": " used", "probability": 0.55712890625 }, { "start": 179.76, "end": 179.92, "word": " to", "probability": 0.90625 }, { "start": 179.92, "end": 180.14, "word": " be", "probability": 0.90478515625 }, { "start": 180.14, "end": 180.32, "word": ",", "probability": 0.399658203125 } ] }, { "id": 60, "seek": 20202, "start": 180.32, "end": 183.4, "text": " when the first digital calculators came out,", "tokens": [ 50714, 562, 264, 700, 4562, 4322, 3391, 1361, 484, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.19531250059604643, "compression_ratio": 1.858974358974359, "no_speech_prob": 0.00016605854034423828, "words": [ { "start": 180.32, "end": 180.4, "word": " when", "probability": 0.85595703125 }, { "start": 180.4, "end": 180.6, "word": " the", "probability": 0.81640625 }, { "start": 180.6, "end": 180.88, "word": " first", "probability": 0.7998046875 }, { "start": 180.88, "end": 181.56, "word": " digital", "probability": 0.82666015625 }, { "start": 181.56, "end": 182.18, "word": " calculators", "probability": 0.932373046875 }, { "start": 182.18, "end": 182.48, "word": " came", "probability": 0.81494140625 }, { "start": 182.48, "end": 182.82, "word": " out", "probability": 0.82421875 }, { "start": 182.82, "end": 183.4, "word": ",", "probability": 0.85595703125 } ] }, { "id": 61, "seek": 20202, "start": 183.4, "end": 185.54, "text": " that was considered artificial intelligence.", "tokens": [ 50864, 300, 390, 4888, 11677, 7599, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.19531250059604643, "compression_ratio": 1.858974358974359, "no_speech_prob": 0.00016605854034423828, "words": [ { "start": 183.4, "end": 183.76, "word": " that", "probability": 0.86279296875 }, { "start": 183.76, "end": 183.92, "word": " was", "probability": 0.8896484375 }, { "start": 183.92, "end": 184.32, "word": " considered", "probability": 0.61669921875 }, { "start": 184.32, "end": 184.68, "word": " artificial", "probability": 0.791015625 }, { "start": 184.68, "end": 185.36, "word": " intelligence", "probability": 0.71044921875 }, { "start": 185.36, "end": 185.54, "word": ".", "probability": 0.55810546875 } ] }, { "id": 62, "seek": 20202, "start": 185.54, "end": 187.38, "text": " A computer can do math.", "tokens": [ 50964, 316, 3820, 393, 360, 5221, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.19531250059604643, "compression_ratio": 1.858974358974359, "no_speech_prob": 0.00016605854034423828, "words": [ { "start": 185.54, "end": 185.66, "word": " A", "probability": 0.763671875 }, { "start": 185.66, "end": 185.96, "word": " computer", "probability": 0.6298828125 }, { "start": 185.96, "end": 186.18, "word": " can", "probability": 0.87255859375 }, { "start": 186.18, "end": 186.36, "word": " do", "probability": 0.9091796875 }, { "start": 186.36, "end": 186.74, "word": " math", "probability": 0.88134765625 }, { "start": 186.74, "end": 187.38, "word": ".", "probability": 0.9697265625 } ] }, { "id": 63, "seek": 20202, "start": 187.4, "end": 189.82, "text": " As things became more advanced,", "tokens": [ 51064, 1018, 721, 3062, 544, 7339, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.19531250059604643, "compression_ratio": 1.858974358974359, "no_speech_prob": 0.00016605854034423828, "words": [ { "start": 187.4, "end": 187.86, "word": " As", "probability": 0.896484375 }, { "start": 187.86, "end": 188.06, "word": " things", "probability": 0.73095703125 }, { "start": 188.06, "end": 188.36, "word": " became", "probability": 0.78271484375 }, { "start": 188.36, "end": 188.62, "word": " more", "probability": 0.884765625 }, { "start": 188.62, "end": 189.22, "word": " advanced", "probability": 0.83349609375 }, { "start": 189.22, "end": 189.82, "word": ",", "probability": 0.9052734375 } ] }, { "id": 64, "seek": 20202, "start": 189.82, "end": 193.04, "text": " different concepts were considered artificial intelligence.", "tokens": [ 51164, 819, 10392, 645, 4888, 11677, 7599, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.19531250059604643, "compression_ratio": 1.858974358974359, "no_speech_prob": 0.00016605854034423828, "words": [ { "start": 189.82, "end": 190.5, "word": " different", "probability": 0.6787109375 }, { "start": 190.5, "end": 191.3, "word": " concepts", "probability": 0.70458984375 }, { "start": 191.3, "end": 191.52, "word": " were", "probability": 0.876953125 }, { "start": 191.52, "end": 191.84, "word": " considered", "probability": 0.6328125 }, { "start": 191.84, "end": 192.22, "word": " artificial", "probability": 0.810546875 }, { "start": 192.22, "end": 192.84, "word": " intelligence", "probability": 0.73193359375 }, { "start": 192.84, "end": 193.04, "word": ".", "probability": 0.95849609375 } ] }, { "id": 65, "seek": 20202, "start": 193.04, "end": 195.0, "text": " There's video game artificial intelligence,", "tokens": [ 51364, 821, 311, 960, 1216, 11677, 7599, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.19531250059604643, "compression_ratio": 1.858974358974359, "no_speech_prob": 0.00016605854034423828, "words": [ { "start": 193.04, "end": 193.2, "word": " There's", "probability": 0.841064453125 }, { "start": 193.2, "end": 193.5, "word": " video", "probability": 0.73876953125 }, { "start": 193.5, "end": 193.76, "word": " game", "probability": 0.7880859375 }, { "start": 193.76, "end": 194.1, "word": " artificial", "probability": 0.7900390625 }, { "start": 194.1, "end": 194.78, "word": " intelligence", "probability": 0.697265625 }, { "start": 194.78, "end": 195.0, "word": ",", "probability": 0.9365234375 } ] }, { "id": 66, "seek": 20202, "start": 195.0, "end": 196.82, "text": " rule-based artificial intelligence,", "tokens": [ 51464, 4978, 12, 6032, 11677, 7599, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.19531250059604643, "compression_ratio": 1.858974358974359, "no_speech_prob": 0.00016605854034423828, "words": [ { "start": 195.0, "end": 195.3, "word": " rule", "probability": 0.7998046875 }, { "start": 195.3, "end": 195.56, "word": "-based", "probability": 0.8115234375 }, { "start": 195.56, "end": 195.98, "word": " artificial", "probability": 0.8427734375 }, { "start": 195.98, "end": 196.52, "word": " intelligence", "probability": 0.68505859375 }, { "start": 196.52, "end": 196.82, "word": ",", "probability": 0.9775390625 } ] }, { "id": 67, "seek": 20202, "start": 196.82, "end": 198.76, "text": " classical image recognition.", "tokens": [ 51564, 13735, 3256, 11150, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.19531250059604643, "compression_ratio": 1.858974358974359, "no_speech_prob": 0.00016605854034423828, "words": [ { "start": 196.82, "end": 197.2, "word": " classical", "probability": 0.8837890625 }, { "start": 197.2, "end": 197.56, "word": " image", "probability": 0.84130859375 }, { "start": 197.56, "end": 198.12, "word": " recognition", "probability": 0.849609375 }, { "start": 198.12, "end": 198.76, "word": ".", "probability": 0.8447265625 } ] }, { "id": 68, "seek": 20202, "start": 200.2, "end": 202.02, "text": " But today we're talking about machine learning,", "tokens": [ 51664, 583, 965, 321, 434, 1417, 466, 3479, 2539, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.19531250059604643, "compression_ratio": 1.858974358974359, "no_speech_prob": 0.00016605854034423828, "words": [ { "start": 200.2, "end": 200.54, "word": " But", "probability": 0.85400390625 }, { "start": 200.54, "end": 200.76, "word": " today", "probability": 0.7734375 }, { "start": 200.76, "end": 200.9, "word": " we're", "probability": 0.817626953125 }, { "start": 200.9, "end": 201.14, "word": " talking", "probability": 0.7666015625 }, { "start": 201.14, "end": 201.38, "word": " about", "probability": 0.81689453125 }, { "start": 201.38, "end": 201.64, "word": " machine", "probability": 0.6904296875 }, { "start": 201.64, "end": 201.92, "word": " learning", "probability": 0.84521484375 }, { "start": 201.92, "end": 202.02, "word": ",", "probability": 0.83642578125 } ] }, { "id": 69, "seek": 23020, "start": 202.02, "end": 204.84, "text": " which is a subset of artificial intelligence.", "tokens": [ 50364, 597, 307, 257, 25993, 295, 11677, 7599, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.7404255319148936, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 202.02, "end": 202.14, "word": " which", "probability": 0.60302734375 }, { "start": 202.14, "end": 202.24, "word": " is", "probability": 0.90087890625 }, { "start": 202.52, "end": 203.02, "word": " a subset", "probability": 0.7314453125 }, { "start": 203.02, "end": 203.38, "word": " of", "probability": 0.8974609375 }, { "start": 203.38, "end": 203.76, "word": " artificial", "probability": 0.7216796875 }, { "start": 203.76, "end": 204.4, "word": " intelligence", "probability": 0.70263671875 }, { "start": 204.4, "end": 204.84, "word": ".", "probability": 0.56201171875 } ] }, { "id": 70, "seek": 23020, "start": 204.84, "end": 207.48, "text": " And it's focused a lot more on", "tokens": [ 50514, 400, 309, 311, 5178, 257, 688, 544, 322, 50614 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.7404255319148936, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 204.84, "end": 204.94, "word": " And", "probability": 0.494384765625 }, { "start": 204.94, "end": 205.4, "word": " it's", "probability": 0.93017578125 }, { "start": 205.4, "end": 206.0, "word": " focused", "probability": 0.75732421875 }, { "start": 206.22, "end": 206.42, "word": " a lot", "probability": 0.8935546875 }, { "start": 206.42, "end": 206.8, "word": " more", "probability": 0.88671875 }, { "start": 206.8, "end": 207.48, "word": " on", "probability": 0.9013671875 } ] }, { "id": 71, "seek": 23020, "start": 208.02, "end": 209.68, "text": " grabbing inferences from data", "tokens": [ 50664, 23771, 13596, 2667, 490, 1412, 50714 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.7404255319148936, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 208.02, "end": 208.62, "word": " grabbing", "probability": 0.74267578125 }, { "start": 208.62, "end": 209.04, "word": " inferences", "probability": 0.869873046875 }, { "start": 209.04, "end": 209.32, "word": " from", "probability": 0.8173828125 }, { "start": 209.32, "end": 209.68, "word": " data", "probability": 0.8037109375 } ] }, { "id": 72, "seek": 23020, "start": 209.68, "end": 212.32, "text": " and making statistical patterns.", "tokens": [ 50764, 293, 1455, 22820, 8294, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.7404255319148936, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 209.68, "end": 210.26, "word": " and", "probability": 0.8427734375 }, { "start": 210.26, "end": 210.56, "word": " making", "probability": 0.80029296875 }, { "start": 210.56, "end": 211.08, "word": " statistical", "probability": 0.76708984375 }, { "start": 211.08, "end": 211.68, "word": " patterns", "probability": 0.74755859375 }, { "start": 211.68, "end": 212.32, "word": ".", "probability": 0.982421875 } ] }, { "id": 73, "seek": 23020, "start": 213.68, "end": 215.72, "text": " And then inside of machine learning,", "tokens": [ 50914, 400, 550, 1854, 295, 3479, 2539, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.7404255319148936, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 213.68, "end": 214.32, "word": " And", "probability": 0.85302734375 }, { "start": 214.32, "end": 214.46, "word": " then", "probability": 0.7255859375 }, { "start": 214.46, "end": 214.84, "word": " inside", "probability": 0.8291015625 }, { "start": 214.84, "end": 214.98, "word": " of", "probability": 0.8916015625 }, { "start": 214.98, "end": 215.22, "word": " machine", "probability": 0.67236328125 }, { "start": 215.22, "end": 215.52, "word": " learning", "probability": 0.8408203125 }, { "start": 215.52, "end": 215.72, "word": ",", "probability": 0.728515625 } ] }, { "id": 74, "seek": 23020, "start": 215.72, "end": 218.02, "text": " we have a concept called deep learning.", "tokens": [ 51064, 321, 362, 257, 3410, 1219, 2452, 2539, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.7404255319148936, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 215.72, "end": 215.82, "word": " we", "probability": 0.89990234375 }, { "start": 215.82, "end": 216.16, "word": " have", "probability": 0.8798828125 }, { "start": 216.38, "end": 216.7, "word": " a concept", "probability": 0.79296875 }, { "start": 216.7, "end": 217.22, "word": " called", "probability": 0.8115234375 }, { "start": 217.22, "end": 217.54, "word": " deep", "probability": 0.74462890625 }, { "start": 217.54, "end": 217.84, "word": " learning", "probability": 0.83203125 }, { "start": 217.84, "end": 218.02, "word": ".", "probability": 0.958984375 } ] }, { "id": 75, "seek": 23020, "start": 218.02, "end": 221.52, "text": " Deep learning is specifically deep neural networks.", "tokens": [ 51164, 14895, 2539, 307, 4682, 2452, 18161, 9590, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.7404255319148936, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 218.02, "end": 218.18, "word": " Deep", "probability": 0.92578125 }, { "start": 218.18, "end": 218.46, "word": " learning", "probability": 0.82958984375 }, { "start": 218.46, "end": 218.96, "word": " is", "probability": 0.90234375 }, { "start": 218.96, "end": 219.52, "word": " specifically", "probability": 0.72900390625 }, { "start": 219.52, "end": 220.0, "word": " deep", "probability": 0.9052734375 }, { "start": 220.0, "end": 220.34, "word": " neural", "probability": 0.876953125 }, { "start": 220.34, "end": 220.88, "word": " networks", "probability": 0.66455078125 }, { "start": 220.88, "end": 221.52, "word": ".", "probability": 0.93212890625 } ] }, { "id": 76, "seek": 23020, "start": 221.96, "end": 224.68, "text": " And so neural networks is a machine learning algorithm", "tokens": [ 51314, 400, 370, 18161, 9590, 307, 257, 3479, 2539, 9284, 51464 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.7404255319148936, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 221.96, "end": 222.06, "word": " And", "probability": 0.84033203125 }, { "start": 222.06, "end": 222.26, "word": " so", "probability": 0.9013671875 }, { "start": 222.26, "end": 222.5, "word": " neural", "probability": 0.8681640625 }, { "start": 222.5, "end": 222.84, "word": " networks", "probability": 0.6728515625 }, { "start": 222.84, "end": 223.02, "word": " is", "probability": 0.87939453125 }, { "start": 223.42, "end": 223.92, "word": " a machine", "probability": 0.72314453125 }, { "start": 223.92, "end": 224.16, "word": " learning", "probability": 0.8154296875 }, { "start": 224.16, "end": 224.68, "word": " algorithm", "probability": 0.7822265625 } ] }, { "id": 77, "seek": 23020, "start": 225.42, "end": 227.18, "text": " that's pretty popular.", "tokens": [ 51514, 300, 311, 1238, 3743, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.7404255319148936, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 225.42, "end": 226.06, "word": " that's", "probability": 0.87646484375 }, { "start": 226.06, "end": 226.5, "word": " pretty", "probability": 0.8779296875 }, { "start": 226.5, "end": 226.92, "word": " popular", "probability": 0.91650390625 }, { "start": 226.92, "end": 227.18, "word": ".", "probability": 0.325927734375 } ] }, { "id": 78, "seek": 23020, "start": 227.18, "end": 228.5, "text": " But deep learning allows us", "tokens": [ 51614, 583, 2452, 2539, 4045, 505, 51664 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.7404255319148936, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 227.18, "end": 227.34, "word": " But", "probability": 0.89453125 }, { "start": 227.34, "end": 227.62, "word": " deep", "probability": 0.92724609375 }, { "start": 227.62, "end": 227.94, "word": " learning", "probability": 0.8408203125 }, { "start": 227.94, "end": 228.32, "word": " allows", "probability": 0.802734375 }, { "start": 228.32, "end": 228.5, "word": " us", "probability": 0.900390625 } ] }, { "id": 79, "seek": 23020, "start": 228.5, "end": 230.2, "text": " to take that a little bit further.", "tokens": [ 51714, 281, 747, 300, 257, 707, 857, 3052, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.7404255319148936, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 228.5, "end": 228.62, "word": " to", "probability": 0.9033203125 }, { "start": 228.62, "end": 228.82, "word": " take", "probability": 0.8125 }, { "start": 228.82, "end": 228.94, "word": " that", "probability": 0.8837890625 }, { "start": 229.06, "end": 229.16, "word": " a little", "probability": 0.80712890625 }, { "start": 229.16, "end": 229.36, "word": " bit", "probability": 0.8984375 }, { "start": 229.36, "end": 229.72, "word": " further", "probability": 0.8623046875 }, { "start": 229.72, "end": 230.2, "word": ".", "probability": 0.96826171875 } ] }, { "id": 80, "seek": 25632, "start": 230.2, "end": 232.02, "text": " And so usually we see this in the form", "tokens": [ 50364, 400, 370, 2673, 321, 536, 341, 294, 264, 1254, 50414 ], "temperature": 0.0, "avg_logprob": -0.17961309410276868, "compression_ratio": 1.7468354430379747, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 230.2, "end": 230.32, "word": " And", "probability": 0.541015625 }, { "start": 230.32, "end": 230.6, "word": " so", "probability": 0.8994140625 }, { "start": 230.6, "end": 230.96, "word": " usually", "probability": 0.6796875 }, { "start": 230.96, "end": 231.16, "word": " we", "probability": 0.84521484375 }, { "start": 231.16, "end": 231.32, "word": " see", "probability": 0.818359375 }, { "start": 231.32, "end": 231.5, "word": " this", "probability": 0.8759765625 }, { "start": 231.5, "end": 231.58, "word": " in", "probability": 0.900390625 }, { "start": 231.58, "end": 231.72, "word": " the", "probability": 0.81689453125 }, { "start": 231.72, "end": 232.02, "word": " form", "probability": 0.81396484375 } ] }, { "id": 81, "seek": 25632, "start": 232.02, "end": 233.8, "text": " of convolutional neural networks,", "tokens": [ 50464, 295, 45216, 304, 18161, 9590, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.17961309410276868, "compression_ratio": 1.7468354430379747, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 232.02, "end": 232.44, "word": " of", "probability": 0.90576171875 }, { "start": 232.44, "end": 233.14, "word": " convolutional", "probability": 0.861572265625 }, { "start": 233.14, "end": 233.3, "word": " neural", "probability": 0.8916015625 }, { "start": 233.3, "end": 233.72, "word": " networks", "probability": 0.67578125 }, { "start": 233.72, "end": 233.8, "word": ",", "probability": 0.69921875 } ] }, { "id": 82, "seek": 25632, "start": 233.8, "end": 236.68, "text": " which are primarily used for image recognition,", "tokens": [ 50564, 597, 366, 10029, 1143, 337, 3256, 11150, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.17961309410276868, "compression_ratio": 1.7468354430379747, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 233.8, "end": 233.96, "word": " which", "probability": 0.9130859375 }, { "start": 233.96, "end": 234.1, "word": " are", "probability": 0.89697265625 }, { "start": 234.1, "end": 234.48, "word": " primarily", "probability": 0.7998046875 }, { "start": 234.48, "end": 234.94, "word": " used", "probability": 0.806640625 }, { "start": 234.94, "end": 235.38, "word": " for", "probability": 0.88916015625 }, { "start": 235.38, "end": 235.74, "word": " image", "probability": 0.82177734375 }, { "start": 235.74, "end": 236.3, "word": " recognition", "probability": 0.8603515625 }, { "start": 236.3, "end": 236.68, "word": ",", "probability": 0.43505859375 } ] }, { "id": 83, "seek": 25632, "start": 236.68, "end": 238.38, "text": " or recurrent neural networks,", "tokens": [ 50714, 420, 18680, 1753, 18161, 9590, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.17961309410276868, "compression_ratio": 1.7468354430379747, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 236.68, "end": 237.2, "word": " or", "probability": 0.90625 }, { "start": 237.2, "end": 237.74, "word": " recurrent", "probability": 0.925048828125 }, { "start": 237.74, "end": 237.92, "word": " neural", "probability": 0.919921875 }, { "start": 237.92, "end": 238.32, "word": " networks", "probability": 0.69140625 }, { "start": 238.32, "end": 238.38, "word": ",", "probability": 0.76025390625 } ] }, { "id": 84, "seek": 25632, "start": 238.38, "end": 241.4, "text": " which are used for cyclical pattern recognition.", "tokens": [ 50814, 597, 366, 1143, 337, 19474, 804, 5102, 11150, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.17961309410276868, "compression_ratio": 1.7468354430379747, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 238.38, "end": 238.58, "word": " which", "probability": 0.91796875 }, { "start": 238.58, "end": 238.78, "word": " are", "probability": 0.89794921875 }, { "start": 238.78, "end": 239.14, "word": " used", "probability": 0.81494140625 }, { "start": 239.14, "end": 239.5, "word": " for", "probability": 0.89599609375 }, { "start": 239.5, "end": 240.06, "word": " cyclical", "probability": 0.83349609375 }, { "start": 240.06, "end": 240.46, "word": " pattern", "probability": 0.77197265625 }, { "start": 240.46, "end": 241.0, "word": " recognition", "probability": 0.86572265625 }, { "start": 241.0, "end": 241.4, "word": ".", "probability": 0.9912109375 } ] }, { "id": 85, "seek": 25632, "start": 241.4, "end": 245.88, "text": " So think of things such as a heartbeat monitor,", "tokens": [ 50914, 407, 519, 295, 721, 1270, 382, 257, 34851, 6002, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.17961309410276868, "compression_ratio": 1.7468354430379747, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 241.4, "end": 241.56, "word": " So", "probability": 0.87255859375 }, { "start": 241.56, "end": 242.18, "word": " think", "probability": 0.705078125 }, { "start": 242.18, "end": 242.3, "word": " of", "probability": 0.9111328125 }, { "start": 242.3, "end": 242.64, "word": " things", "probability": 0.74072265625 }, { "start": 242.64, "end": 242.94, "word": " such", "probability": 0.86572265625 }, { "start": 242.94, "end": 243.62, "word": " as", "probability": 0.908203125 }, { "start": 243.98, "end": 245.14, "word": " a heartbeat", "probability": 0.9052734375 }, { "start": 245.14, "end": 245.64, "word": " monitor", "probability": 0.8662109375 }, { "start": 245.64, "end": 245.88, "word": ",", "probability": 0.88916015625 } ] }, { "id": 86, "seek": 25632, "start": 245.88, "end": 247.4, "text": " where there's a pattern involved", "tokens": [ 51164, 689, 456, 311, 257, 5102, 3288, 51214 ], "temperature": 0.0, "avg_logprob": -0.17961309410276868, "compression_ratio": 1.7468354430379747, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 245.88, "end": 246.24, "word": " where", "probability": 0.1888427734375 }, { "start": 246.24, "end": 246.52, "word": " there's", "probability": 0.91259765625 }, { "start": 246.66, "end": 247.08, "word": " a pattern", "probability": 0.77490234375 }, { "start": 247.08, "end": 247.4, "word": " involved", "probability": 0.77587890625 } ] }, { "id": 87, "seek": 25632, "start": 248.18, "end": 250.02, "text": " that you kind of need to match up.", "tokens": [ 51264, 300, 291, 733, 295, 643, 281, 2995, 493, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.17961309410276868, "compression_ratio": 1.7468354430379747, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 248.18, "end": 248.82, "word": " that", "probability": 0.8125 }, { "start": 248.82, "end": 248.94, "word": " you", "probability": 0.90087890625 }, { "start": 248.94, "end": 249.1, "word": " kind", "probability": 0.442138671875 }, { "start": 249.1, "end": 249.18, "word": " of", "probability": 0.904296875 }, { "start": 249.18, "end": 249.32, "word": " need", "probability": 0.81005859375 }, { "start": 249.32, "end": 249.46, "word": " to", "probability": 0.90576171875 }, { "start": 249.46, "end": 249.72, "word": " match", "probability": 0.806640625 }, { "start": 249.72, "end": 249.98, "word": " up", "probability": 0.90478515625 }, { "start": 249.98, "end": 250.02, "word": ".", "probability": 0.6787109375 } ] }, { "id": 88, "seek": 25632, "start": 250.02, "end": 252.44, "text": " And if there's any sort of heart irregularities,", "tokens": [ 51364, 400, 498, 456, 311, 604, 1333, 295, 1917, 29349, 1088, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.17961309410276868, "compression_ratio": 1.7468354430379747, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 250.02, "end": 250.1, "word": " And", "probability": 0.89697265625 }, { "start": 250.1, "end": 250.2, "word": " if", "probability": 0.90283203125 }, { "start": 250.2, "end": 250.36, "word": " there's", "probability": 0.92333984375 }, { "start": 250.36, "end": 250.52, "word": " any", "probability": 0.81591796875 }, { "start": 250.52, "end": 250.68, "word": " sort", "probability": 0.81005859375 }, { "start": 250.68, "end": 250.8, "word": " of", "probability": 0.90625 }, { "start": 250.8, "end": 251.04, "word": " heart", "probability": 0.85302734375 }, { "start": 251.04, "end": 252.04, "word": " irregularities", "probability": 0.91357421875 }, { "start": 252.04, "end": 252.44, "word": ",", "probability": 0.9580078125 } ] }, { "id": 89, "seek": 25632, "start": 252.44, "end": 256.32, "text": " the pattern will diverge from predicted patterns.", "tokens": [ 51464, 264, 5102, 486, 18558, 432, 490, 19147, 8294, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.17961309410276868, "compression_ratio": 1.7468354430379747, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 252.44, "end": 252.92, "word": " the", "probability": 0.81103515625 }, { "start": 252.92, "end": 253.36, "word": " pattern", "probability": 0.7978515625 }, { "start": 253.36, "end": 253.64, "word": " will", "probability": 0.8232421875 }, { "start": 253.64, "end": 254.24, "word": " diverge", "probability": 0.908935546875 }, { "start": 254.24, "end": 254.58, "word": " from", "probability": 0.8212890625 }, { "start": 254.58, "end": 255.18, "word": " predicted", "probability": 0.7255859375 }, { "start": 255.18, "end": 255.68, "word": " patterns", "probability": 0.77490234375 }, { "start": 255.68, "end": 256.32, "word": ".", "probability": 0.99853515625 } ] }, { "id": 90, "seek": 28458, "start": 257.96, "end": 262.02, "text": " So if we wanted to formally define machine learning,", "tokens": [ 50414, 407, 498, 321, 1415, 281, 25983, 6964, 3479, 2539, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.18229166455943174, "compression_ratio": 1.642570281124498, "no_speech_prob": 0.0009107589721679688, "words": [ { "start": 257.96, "end": 258.56, "word": " So", "probability": 0.148681640625 }, { "start": 258.56, "end": 259.16, "word": " if", "probability": 0.513671875 }, { "start": 259.16, "end": 259.26, "word": " we", "probability": 0.8896484375 }, { "start": 259.26, "end": 259.42, "word": " wanted", "probability": 0.7607421875 }, { "start": 259.42, "end": 259.56, "word": " to", "probability": 0.90869140625 }, { "start": 259.56, "end": 259.94, "word": " formally", "probability": 0.859375 }, { "start": 259.94, "end": 261.0, "word": " define", "probability": 0.8681640625 }, { "start": 261.0, "end": 261.48, "word": " machine", "probability": 0.69482421875 }, { "start": 261.48, "end": 261.82, "word": " learning", "probability": 0.84375 }, { "start": 261.82, "end": 262.02, "word": ",", "probability": 0.80908203125 } ] }, { "id": 91, "seek": 28458, "start": 262.02, "end": 264.14, "text": " I would say that it's a set of statistical techniques", "tokens": [ 50664, 286, 576, 584, 300, 309, 311, 257, 992, 295, 22820, 7512, 50714 ], "temperature": 0.0, "avg_logprob": -0.18229166455943174, "compression_ratio": 1.642570281124498, "no_speech_prob": 0.0009107589721679688, "words": [ { "start": 262.02, "end": 262.08, "word": " I", "probability": 0.98291015625 }, { "start": 262.08, "end": 262.2, "word": " would", "probability": 0.8525390625 }, { "start": 262.2, "end": 262.34, "word": " say", "probability": 0.89599609375 }, { "start": 262.34, "end": 262.46, "word": " that", "probability": 0.83984375 }, { "start": 262.46, "end": 262.62, "word": " it's", "probability": 0.93212890625 }, { "start": 262.68, "end": 262.9, "word": " a set", "probability": 0.8798828125 }, { "start": 262.9, "end": 263.16, "word": " of", "probability": 0.900390625 }, { "start": 263.16, "end": 263.62, "word": " statistical", "probability": 0.80517578125 }, { "start": 263.62, "end": 264.14, "word": " techniques", "probability": 0.833984375 } ] }, { "id": 92, "seek": 28458, "start": 264.14, "end": 266.6, "text": " that enable the process of information mining,", "tokens": [ 50764, 300, 9528, 264, 1399, 295, 1589, 15512, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.18229166455943174, "compression_ratio": 1.642570281124498, "no_speech_prob": 0.0009107589721679688, "words": [ { "start": 264.14, "end": 264.34, "word": " that", "probability": 0.8740234375 }, { "start": 264.34, "end": 264.58, "word": " enable", "probability": 0.8896484375 }, { "start": 264.58, "end": 264.76, "word": " the", "probability": 0.80908203125 }, { "start": 264.76, "end": 265.24, "word": " process", "probability": 0.86962890625 }, { "start": 265.24, "end": 265.56, "word": " of", "probability": 0.89794921875 }, { "start": 265.56, "end": 266.0, "word": " information", "probability": 0.74462890625 }, { "start": 266.0, "end": 266.42, "word": " mining", "probability": 0.88232421875 }, { "start": 266.42, "end": 266.6, "word": ",", "probability": 0.9287109375 } ] }, { "id": 93, "seek": 28458, "start": 266.6, "end": 269.48, "text": " pattern discovery, and drawing inferences from data.", "tokens": [ 50864, 5102, 12114, 11, 293, 6316, 13596, 2667, 490, 1412, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.18229166455943174, "compression_ratio": 1.642570281124498, "no_speech_prob": 0.0009107589721679688, "words": [ { "start": 266.6, "end": 266.84, "word": " pattern", "probability": 0.77099609375 }, { "start": 266.84, "end": 267.28, "word": " discovery", "probability": 0.76416015625 }, { "start": 267.28, "end": 267.48, "word": ",", "probability": 0.701171875 }, { "start": 267.48, "end": 267.58, "word": " and", "probability": 0.88916015625 }, { "start": 267.58, "end": 267.84, "word": " drawing", "probability": 0.6064453125 }, { "start": 267.84, "end": 268.3, "word": " inferences", "probability": 0.882080078125 }, { "start": 268.3, "end": 268.56, "word": " from", "probability": 0.81884765625 }, { "start": 268.56, "end": 268.88, "word": " data", "probability": 0.81591796875 }, { "start": 268.88, "end": 269.48, "word": ".", "probability": 0.98046875 } ] }, { "id": 94, "seek": 28458, "start": 269.54, "end": 272.58, "text": " So the idea is that the algorithms learn", "tokens": [ 51014, 407, 264, 1558, 307, 300, 264, 14642, 1466, 51114 ], "temperature": 0.0, "avg_logprob": -0.18229166455943174, "compression_ratio": 1.642570281124498, "no_speech_prob": 0.0009107589721679688, "words": [ { "start": 269.54, "end": 269.88, "word": " So", "probability": 0.8251953125 }, { "start": 269.88, "end": 270.04, "word": " the", "probability": 0.80908203125 }, { "start": 270.04, "end": 270.34, "word": " idea", "probability": 0.78564453125 }, { "start": 270.34, "end": 270.7, "word": " is", "probability": 0.90673828125 }, { "start": 270.7, "end": 270.9, "word": " that", "probability": 0.87109375 }, { "start": 270.9, "end": 271.38, "word": " the", "probability": 0.796875 }, { "start": 271.38, "end": 271.92, "word": " algorithms", "probability": 0.86767578125 }, { "start": 271.92, "end": 272.58, "word": " learn", "probability": 0.87548828125 } ] }, { "id": 95, "seek": 28458, "start": 272.58, "end": 274.82, "text": " from past data to predict future outcomes,", "tokens": [ 51164, 490, 1791, 1412, 281, 6069, 2027, 10070, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.18229166455943174, "compression_ratio": 1.642570281124498, "no_speech_prob": 0.0009107589721679688, "words": [ { "start": 272.58, "end": 272.86, "word": " from", "probability": 0.814453125 }, { "start": 272.86, "end": 273.26, "word": " past", "probability": 0.8125 }, { "start": 273.26, "end": 273.52, "word": " data", "probability": 0.8115234375 }, { "start": 273.52, "end": 273.7, "word": " to", "probability": 0.9013671875 }, { "start": 273.7, "end": 273.92, "word": " predict", "probability": 0.81005859375 }, { "start": 273.92, "end": 274.26, "word": " future", "probability": 0.93017578125 }, { "start": 274.26, "end": 274.8, "word": " outcomes", "probability": 0.76513671875 }, { "start": 274.8, "end": 274.82, "word": ",", "probability": 0.41796875 } ] }, { "id": 96, "seek": 28458, "start": 274.82, "end": 277.74, "text": " instead of creating a different algorithm", "tokens": [ 51314, 2602, 295, 4084, 257, 819, 9284, 51414 ], "temperature": 0.0, "avg_logprob": -0.18229166455943174, "compression_ratio": 1.642570281124498, "no_speech_prob": 0.0009107589721679688, "words": [ { "start": 274.82, "end": 275.68, "word": " instead", "probability": 0.84130859375 }, { "start": 275.68, "end": 276.14, "word": " of", "probability": 0.90087890625 }, { "start": 276.14, "end": 276.8, "word": " creating", "probability": 0.8017578125 }, { "start": 276.96, "end": 277.22, "word": " a different", "probability": 0.69580078125 }, { "start": 277.22, "end": 277.74, "word": " algorithm", "probability": 0.8359375 } ] }, { "id": 97, "seek": 28458, "start": 277.74, "end": 280.08, "text": " for a different scenario.", "tokens": [ 51464, 337, 257, 819, 9005, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.18229166455943174, "compression_ratio": 1.642570281124498, "no_speech_prob": 0.0009107589721679688, "words": [ { "start": 277.74, "end": 278.14, "word": " for", "probability": 0.89599609375 }, { "start": 278.28, "end": 278.58, "word": " a different", "probability": 0.6806640625 }, { "start": 278.58, "end": 279.48, "word": " scenario", "probability": 0.7666015625 }, { "start": 279.48, "end": 280.08, "word": ".", "probability": 0.72265625 } ] }, { "id": 98, "seek": 28458, "start": 280.4, "end": 284.58, "text": " And we'll see that as we go through the workbooks,", "tokens": [ 51564, 400, 321, 603, 536, 300, 382, 321, 352, 807, 264, 589, 15170, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.18229166455943174, "compression_ratio": 1.642570281124498, "no_speech_prob": 0.0009107589721679688, "words": [ { "start": 280.4, "end": 281.0, "word": " And", "probability": 0.60205078125 }, { "start": 281.0, "end": 281.2, "word": " we'll", "probability": 0.9296875 }, { "start": 281.2, "end": 281.46, "word": " see", "probability": 0.82080078125 }, { "start": 281.46, "end": 281.76, "word": " that", "probability": 0.880859375 }, { "start": 281.76, "end": 281.98, "word": " as", "probability": 0.88232421875 }, { "start": 281.98, "end": 282.28, "word": " we", "probability": 0.90087890625 }, { "start": 282.28, "end": 282.98, "word": " go", "probability": 0.4775390625 }, { "start": 282.98, "end": 283.26, "word": " through", "probability": 0.79052734375 }, { "start": 283.26, "end": 283.44, "word": " the", "probability": 0.81298828125 }, { "start": 283.44, "end": 283.98, "word": " workbooks", "probability": 0.87158203125 }, { "start": 283.98, "end": 284.58, "word": ",", "probability": 0.7470703125 } ] }, { "id": 99, "seek": 31284, "start": 284.58, "end": 287.14, "text": " how we're able to create multiple different types", "tokens": [ 50364, 577, 321, 434, 1075, 281, 1884, 3866, 819, 3467, 50464 ], "temperature": 0.0, "avg_logprob": -0.16364397720566817, "compression_ratio": 1.779591836734694, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 284.58, "end": 285.12, "word": " how", "probability": 0.7275390625 }, { "start": 285.12, "end": 285.28, "word": " we're", "probability": 0.90380859375 }, { "start": 285.28, "end": 285.48, "word": " able", "probability": 0.888671875 }, { "start": 285.48, "end": 285.68, "word": " to", "probability": 0.90673828125 }, { "start": 285.68, "end": 286.04, "word": " create", "probability": 0.82763671875 }, { "start": 286.04, "end": 286.4, "word": " multiple", "probability": 0.77685546875 }, { "start": 286.4, "end": 286.8, "word": " different", "probability": 0.67578125 }, { "start": 286.8, "end": 287.14, "word": " types", "probability": 0.75146484375 } ] }, { "id": 100, "seek": 31284, "start": 287.14, "end": 290.42, "text": " of algorithms around the same set of data,", "tokens": [ 50514, 295, 14642, 926, 264, 912, 992, 295, 1412, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.16364397720566817, "compression_ratio": 1.779591836734694, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 287.14, "end": 287.32, "word": " of", "probability": 0.90283203125 }, { "start": 287.32, "end": 287.88, "word": " algorithms", "probability": 0.87744140625 }, { "start": 287.88, "end": 289.34, "word": " around", "probability": 0.82177734375 }, { "start": 289.34, "end": 289.6, "word": " the", "probability": 0.8046875 }, { "start": 289.6, "end": 289.8, "word": " same", "probability": 0.81201171875 }, { "start": 289.8, "end": 290.0, "word": " set", "probability": 0.88330078125 }, { "start": 290.0, "end": 290.12, "word": " of", "probability": 0.90625 }, { "start": 290.12, "end": 290.38, "word": " data", "probability": 0.8076171875 }, { "start": 290.38, "end": 290.42, "word": ",", "probability": 0.4345703125 } ] }, { "id": 101, "seek": 31284, "start": 290.42, "end": 291.86, "text": " or how we can use the same algorithms", "tokens": [ 50664, 420, 577, 321, 393, 764, 264, 912, 14642, 50714 ], "temperature": 0.0, "avg_logprob": -0.16364397720566817, "compression_ratio": 1.779591836734694, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 290.42, "end": 290.58, "word": " or", "probability": 0.8984375 }, { "start": 290.58, "end": 290.7, "word": " how", "probability": 0.90380859375 }, { "start": 290.7, "end": 290.8, "word": " we", "probability": 0.90478515625 }, { "start": 290.8, "end": 290.92, "word": " can", "probability": 0.896484375 }, { "start": 290.92, "end": 291.08, "word": " use", "probability": 0.83251953125 }, { "start": 291.08, "end": 291.24, "word": " the", "probability": 0.806640625 }, { "start": 291.24, "end": 291.4, "word": " same", "probability": 0.81884765625 }, { "start": 291.4, "end": 291.86, "word": " algorithms", "probability": 0.87353515625 } ] }, { "id": 102, "seek": 31284, "start": 291.86, "end": 293.64, "text": " with different types of data.", "tokens": [ 50764, 365, 819, 3467, 295, 1412, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.16364397720566817, "compression_ratio": 1.779591836734694, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 291.86, "end": 292.14, "word": " with", "probability": 0.8037109375 }, { "start": 292.14, "end": 292.4, "word": " different", "probability": 0.69580078125 }, { "start": 292.4, "end": 292.64, "word": " types", "probability": 0.7470703125 }, { "start": 292.64, "end": 292.78, "word": " of", "probability": 0.90673828125 }, { "start": 292.78, "end": 293.0, "word": " data", "probability": 0.8125 }, { "start": 293.0, "end": 293.64, "word": ".", "probability": 0.98193359375 } ] }, { "id": 103, "seek": 31284, "start": 294.44, "end": 296.12, "text": " So some key examples,", "tokens": [ 50864, 407, 512, 2141, 5110, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.16364397720566817, "compression_ratio": 1.779591836734694, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 294.44, "end": 295.0, "word": " So", "probability": 0.81640625 }, { "start": 295.0, "end": 295.22, "word": " some", "probability": 0.6279296875 }, { "start": 295.22, "end": 295.52, "word": " key", "probability": 0.8251953125 }, { "start": 295.52, "end": 295.94, "word": " examples", "probability": 0.78271484375 }, { "start": 295.94, "end": 296.12, "word": ",", "probability": 0.8955078125 } ] }, { "id": 104, "seek": 31284, "start": 296.12, "end": 297.54, "text": " especially in the security sphere,", "tokens": [ 50964, 2318, 294, 264, 3825, 16687, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.16364397720566817, "compression_ratio": 1.779591836734694, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 296.12, "end": 296.28, "word": " especially", "probability": 0.71923828125 }, { "start": 296.28, "end": 296.44, "word": " in", "probability": 0.900390625 }, { "start": 296.44, "end": 296.54, "word": " the", "probability": 0.81298828125 }, { "start": 296.54, "end": 296.86, "word": " security", "probability": 0.880859375 }, { "start": 296.86, "end": 297.28, "word": " sphere", "probability": 0.78564453125 }, { "start": 297.28, "end": 297.54, "word": ",", "probability": 0.779296875 } ] }, { "id": 105, "seek": 31284, "start": 297.54, "end": 299.92, "text": " is domain generation algorithms.", "tokens": [ 51064, 307, 9274, 5125, 14642, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.16364397720566817, "compression_ratio": 1.779591836734694, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 297.54, "end": 297.92, "word": " is", "probability": 0.87841796875 }, { "start": 297.92, "end": 298.76, "word": " domain", "probability": 0.85546875 }, { "start": 298.76, "end": 299.22, "word": " generation", "probability": 0.77978515625 }, { "start": 299.22, "end": 299.78, "word": " algorithms", "probability": 0.87939453125 }, { "start": 299.78, "end": 299.92, "word": ".", "probability": 0.9267578125 } ] }, { "id": 106, "seek": 31284, "start": 299.92, "end": 302.06, "text": " Domain generation algorithms are heavily used", "tokens": [ 51164, 16674, 491, 5125, 14642, 366, 10950, 1143, 51214 ], "temperature": 0.0, "avg_logprob": -0.16364397720566817, "compression_ratio": 1.779591836734694, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 299.92, "end": 300.1, "word": " Domain", "probability": 0.92431640625 }, { "start": 300.1, "end": 300.5, "word": " generation", "probability": 0.794921875 }, { "start": 300.5, "end": 300.9, "word": " algorithms", "probability": 0.87890625 }, { "start": 300.9, "end": 301.36, "word": " are", "probability": 0.89453125 }, { "start": 301.36, "end": 301.72, "word": " heavily", "probability": 0.8515625 }, { "start": 301.72, "end": 302.06, "word": " used", "probability": 0.8076171875 } ] }, { "id": 107, "seek": 31284, "start": 302.06, "end": 304.12, "text": " by botnets so that the bot herder", "tokens": [ 51264, 538, 10592, 77, 1385, 370, 300, 264, 10592, 720, 1068, 51314 ], "temperature": 0.0, "avg_logprob": -0.16364397720566817, "compression_ratio": 1.779591836734694, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 302.06, "end": 302.4, "word": " by", "probability": 0.91650390625 }, { "start": 302.4, "end": 302.98, "word": " botnets", "probability": 0.91064453125 }, { "start": 302.98, "end": 303.3, "word": " so", "probability": 0.58349609375 }, { "start": 303.3, "end": 303.48, "word": " that", "probability": 0.87353515625 }, { "start": 303.48, "end": 303.6, "word": " the", "probability": 0.814453125 }, { "start": 303.6, "end": 303.78, "word": " bot", "probability": 0.82080078125 }, { "start": 303.78, "end": 304.12, "word": " herder", "probability": 0.842529296875 } ] }, { "id": 108, "seek": 31284, "start": 304.12, "end": 307.76, "text": " can stay in contact with the botnet itself,", "tokens": [ 51364, 393, 1754, 294, 3385, 365, 264, 10592, 7129, 2564, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.16364397720566817, "compression_ratio": 1.779591836734694, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 304.12, "end": 304.4, "word": " can", "probability": 0.90283203125 }, { "start": 304.4, "end": 304.62, "word": " stay", "probability": 0.91845703125 }, { "start": 304.62, "end": 304.8, "word": " in", "probability": 0.9140625 }, { "start": 304.8, "end": 305.16, "word": " contact", "probability": 0.853515625 }, { "start": 305.16, "end": 305.52, "word": " with", "probability": 0.81982421875 }, { "start": 305.52, "end": 306.28, "word": " the", "probability": 0.8134765625 }, { "start": 306.28, "end": 306.74, "word": " botnet", "probability": 0.905517578125 }, { "start": 306.74, "end": 307.26, "word": " itself", "probability": 0.77001953125 }, { "start": 307.26, "end": 307.76, "word": ",", "probability": 0.311767578125 } ] }, { "id": 109, "seek": 31284, "start": 307.76, "end": 311.0, "text": " while government agencies or ISPs", "tokens": [ 51514, 1339, 2463, 9504, 420, 6205, 23043, 51664 ], "temperature": 0.0, "avg_logprob": -0.16364397720566817, "compression_ratio": 1.779591836734694, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 307.76, "end": 308.18, "word": " while", "probability": 0.90771484375 }, { "start": 308.18, "end": 309.04, "word": " government", "probability": 0.8349609375 }, { "start": 309.04, "end": 309.5, "word": " agencies", "probability": 0.625 }, { "start": 309.5, "end": 310.28, "word": " or", "probability": 0.85546875 }, { "start": 310.28, "end": 311.0, "word": " ISPs", "probability": 0.9189453125 } ] }, { "id": 110, "seek": 31284, "start": 311.0, "end": 312.84, "text": " are taking down the domains", "tokens": [ 51714, 366, 1940, 760, 264, 25514, 51764 ], "temperature": 0.0, "avg_logprob": -0.16364397720566817, "compression_ratio": 1.779591836734694, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 311.0, "end": 311.28, "word": " are", "probability": 0.890625 }, { "start": 311.28, "end": 311.58, "word": " taking", "probability": 0.81103515625 }, { "start": 311.58, "end": 312.06, "word": " down", "probability": 0.81298828125 }, { "start": 312.06, "end": 312.5, "word": " the", "probability": 0.818359375 }, { "start": 312.5, "end": 312.84, "word": " domains", "probability": 0.7861328125 } ] }, { "id": 111, "seek": 34284, "start": 312.84, "end": 314.58, "text": " that they use to communicate.", "tokens": [ 50364, 300, 436, 764, 281, 7890, 13, 50414 ], "temperature": 0.0, "avg_logprob": -0.1922487679357622, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.0001823902130126953, "words": [ { "start": 312.84, "end": 313.02, "word": " that", "probability": 0.72705078125 }, { "start": 313.02, "end": 313.16, "word": " they", "probability": 0.740234375 }, { "start": 313.16, "end": 313.42, "word": " use", "probability": 0.8046875 }, { "start": 313.42, "end": 313.56, "word": " to", "probability": 0.9072265625 }, { "start": 313.56, "end": 314.0, "word": " communicate", "probability": 0.7392578125 }, { "start": 314.0, "end": 314.58, "word": ".", "probability": 0.9716796875 } ] }, { "id": 112, "seek": 34284, "start": 314.94, "end": 317.68, "text": " We also see this with web application firewalls.", "tokens": [ 50464, 492, 611, 536, 341, 365, 3670, 3861, 36109, 82, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.1922487679357622, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.0001823902130126953, "words": [ { "start": 314.94, "end": 315.4, "word": " We", "probability": 0.89501953125 }, { "start": 315.4, "end": 315.58, "word": " also", "probability": 0.814453125 }, { "start": 315.58, "end": 315.78, "word": " see", "probability": 0.82177734375 }, { "start": 315.78, "end": 315.94, "word": " this", "probability": 0.7724609375 }, { "start": 315.94, "end": 316.12, "word": " with", "probability": 0.08056640625 }, { "start": 316.12, "end": 316.46, "word": " web", "probability": 0.79296875 }, { "start": 316.46, "end": 316.92, "word": " application", "probability": 0.765625 }, { "start": 316.92, "end": 317.62, "word": " firewalls", "probability": 0.85302734375 }, { "start": 317.62, "end": 317.68, "word": ".", "probability": 0.53173828125 } ] }, { "id": 113, "seek": 34284, "start": 317.68, "end": 319.24, "text": " We can perform anomaly detection", "tokens": [ 50614, 492, 393, 2042, 42737, 17784, 50664 ], "temperature": 0.0, "avg_logprob": -0.1922487679357622, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.0001823902130126953, "words": [ { "start": 317.68, "end": 317.72, "word": " We", "probability": 0.8984375 }, { "start": 317.72, "end": 317.84, "word": " can", "probability": 0.8974609375 }, { "start": 317.84, "end": 318.22, "word": " perform", "probability": 0.7158203125 }, { "start": 318.22, "end": 318.6, "word": " anomaly", "probability": 0.732421875 }, { "start": 318.6, "end": 319.24, "word": " detection", "probability": 0.77099609375 } ] }, { "id": 114, "seek": 34284, "start": 319.24, "end": 325.1, "text": " to identify normal web traffic,", "tokens": [ 50714, 281, 5876, 2710, 3670, 6419, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.1922487679357622, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.0001823902130126953, "words": [ { "start": 319.24, "end": 319.8, "word": " to", "probability": 0.328857421875 }, { "start": 319.8, "end": 322.06, "word": " identify", "probability": 0.88134765625 }, { "start": 322.06, "end": 323.92, "word": " normal", "probability": 0.8134765625 }, { "start": 323.92, "end": 324.44, "word": " web", "probability": 0.74169921875 }, { "start": 324.44, "end": 324.94, "word": " traffic", "probability": 0.82421875 }, { "start": 324.94, "end": 325.1, "word": ",", "probability": 0.869140625 } ] }, { "id": 115, "seek": 34284, "start": 325.1, "end": 327.88, "text": " normal parameters that are sent by a web client,", "tokens": [ 50964, 2710, 9834, 300, 366, 2279, 538, 257, 3670, 6423, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.1922487679357622, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.0001823902130126953, "words": [ { "start": 325.1, "end": 325.36, "word": " normal", "probability": 0.80419921875 }, { "start": 325.36, "end": 325.86, "word": " parameters", "probability": 0.87939453125 }, { "start": 325.86, "end": 326.12, "word": " that", "probability": 0.8642578125 }, { "start": 326.12, "end": 326.22, "word": " are", "probability": 0.9033203125 }, { "start": 326.22, "end": 326.52, "word": " sent", "probability": 0.8125 }, { "start": 326.52, "end": 327.1, "word": " by", "probability": 0.85400390625 }, { "start": 327.24, "end": 327.38, "word": " a web", "probability": 0.8056640625 }, { "start": 327.38, "end": 327.82, "word": " client", "probability": 0.8984375 }, { "start": 327.82, "end": 327.88, "word": ",", "probability": 0.1661376953125 } ] }, { "id": 116, "seek": 34284, "start": 327.88, "end": 330.26, "text": " versus potentially malicious parameters.", "tokens": [ 51114, 5717, 7263, 33496, 9834, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.1922487679357622, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.0001823902130126953, "words": [ { "start": 327.88, "end": 328.22, "word": " versus", "probability": 0.79541015625 }, { "start": 328.22, "end": 329.0, "word": " potentially", "probability": 0.640625 }, { "start": 329.0, "end": 329.4, "word": " malicious", "probability": 0.8173828125 }, { "start": 329.4, "end": 329.98, "word": " parameters", "probability": 0.8740234375 }, { "start": 329.98, "end": 330.26, "word": ".", "probability": 0.9658203125 } ] }, { "id": 117, "seek": 34284, "start": 330.26, "end": 331.78, "text": " In this example here,", "tokens": [ 51214, 682, 341, 1365, 510, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.1922487679357622, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.0001823902130126953, "words": [ { "start": 330.26, "end": 330.36, "word": " In", "probability": 0.9072265625 }, { "start": 330.36, "end": 330.6, "word": " this", "probability": 0.880859375 }, { "start": 330.6, "end": 331.32, "word": " example", "probability": 0.92431640625 }, { "start": 331.32, "end": 331.72, "word": " here", "probability": 0.767578125 }, { "start": 331.72, "end": 331.78, "word": ",", "probability": 0.8193359375 } ] }, { "id": 118, "seek": 34284, "start": 331.78, "end": 335.18, "text": " it's showing a possible SQL injection,", "tokens": [ 51314, 309, 311, 4099, 257, 1944, 19200, 22873, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.1922487679357622, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.0001823902130126953, "words": [ { "start": 331.78, "end": 332.06, "word": " it's", "probability": 0.94970703125 }, { "start": 332.06, "end": 332.34, "word": " showing", "probability": 0.78515625 }, { "start": 332.7, "end": 333.1, "word": " a possible", "probability": 0.8466796875 }, { "start": 333.1, "end": 333.68, "word": " SQL", "probability": 0.90478515625 }, { "start": 333.68, "end": 334.22, "word": " injection", "probability": 0.71337890625 }, { "start": 334.22, "end": 335.18, "word": ",", "probability": 0.51025390625 } ] }, { "id": 119, "seek": 34284, "start": 335.18, "end": 336.94, "text": " and it's calling that out.", "tokens": [ 51464, 293, 309, 311, 5141, 300, 484, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.1922487679357622, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.0001823902130126953, "words": [ { "start": 335.18, "end": 335.46, "word": " and", "probability": 0.89599609375 }, { "start": 335.46, "end": 335.6, "word": " it's", "probability": 0.95068359375 }, { "start": 335.6, "end": 335.84, "word": " calling", "probability": 0.67236328125 }, { "start": 335.84, "end": 336.08, "word": " that", "probability": 0.8818359375 }, { "start": 336.08, "end": 336.36, "word": " out", "probability": 0.8212890625 }, { "start": 336.36, "end": 336.94, "word": ".", "probability": 0.95166015625 } ] }, { "id": 120, "seek": 34284, "start": 337.22, "end": 339.32, "text": " And then, of course, network anomaly detection,", "tokens": [ 51564, 400, 550, 11, 295, 1164, 11, 3209, 42737, 17784, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.1922487679357622, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.0001823902130126953, "words": [ { "start": 337.22, "end": 337.52, "word": " And", "probability": 0.78076171875 }, { "start": 337.52, "end": 337.6, "word": " then", "probability": 0.7255859375 }, { "start": 337.6, "end": 337.68, "word": ",", "probability": 0.42919921875 }, { "start": 337.68, "end": 337.74, "word": " of", "probability": 0.9091796875 }, { "start": 337.74, "end": 337.88, "word": " course", "probability": 0.8681640625 }, { "start": 337.88, "end": 337.92, "word": ",", "probability": 0.99267578125 }, { "start": 337.92, "end": 338.18, "word": " network", "probability": 0.7978515625 }, { "start": 338.18, "end": 338.5, "word": " anomaly", "probability": 0.794921875 }, { "start": 338.5, "end": 339.0, "word": " detection", "probability": 0.75634765625 }, { "start": 339.0, "end": 339.32, "word": ",", "probability": 0.7578125 } ] }, { "id": 121, "seek": 34284, "start": 339.32, "end": 341.84, "text": " where what we can do is predict", "tokens": [ 51714, 689, 437, 321, 393, 360, 307, 6069, 51814 ], "temperature": 0.0, "avg_logprob": -0.1922487679357622, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.0001823902130126953, "words": [ { "start": 339.32, "end": 339.7, "word": " where", "probability": 0.91064453125 }, { "start": 339.7, "end": 340.02, "word": " what", "probability": 0.87890625 }, { "start": 340.02, "end": 340.14, "word": " we", "probability": 0.904296875 }, { "start": 340.14, "end": 340.3, "word": " can", "probability": 0.89453125 }, { "start": 340.3, "end": 340.58, "word": " do", "probability": 0.9072265625 }, { "start": 340.58, "end": 341.06, "word": " is", "probability": 0.9052734375 }, { "start": 341.06, "end": 341.84, "word": " predict", "probability": 0.83203125 } ] }, { "id": 122, "seek": 37284, "start": 343.3, "end": 346.88, "text": " how the network will operate over a period of time,", "tokens": [ 50364, 577, 264, 3209, 486, 9651, 670, 257, 2896, 295, 565, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.18434873724184117, "compression_ratio": 1.7121771217712176, "no_speech_prob": 0.0002415180206298828, "words": [ { "start": 343.3, "end": 343.78, "word": " how", "probability": 0.294921875 }, { "start": 343.78, "end": 344.0, "word": " the", "probability": 0.8095703125 }, { "start": 344.0, "end": 344.34, "word": " network", "probability": 0.83203125 }, { "start": 344.34, "end": 344.58, "word": " will", "probability": 0.81201171875 }, { "start": 344.58, "end": 345.28, "word": " operate", "probability": 0.78271484375 }, { "start": 345.28, "end": 345.6, "word": " over", "probability": 0.8818359375 }, { "start": 345.8, "end": 346.02, "word": " a period", "probability": 0.91455078125 }, { "start": 346.02, "end": 346.18, "word": " of", "probability": 0.90234375 }, { "start": 346.18, "end": 346.64, "word": " time", "probability": 0.79931640625 }, { "start": 346.64, "end": 346.88, "word": ",", "probability": 0.3125 } ] }, { "id": 123, "seek": 37284, "start": 346.88, "end": 350.78, "text": " and then keep track of how it is actually operating.", "tokens": [ 50564, 293, 550, 1066, 2837, 295, 577, 309, 307, 767, 7447, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.18434873724184117, "compression_ratio": 1.7121771217712176, "no_speech_prob": 0.0002415180206298828, "words": [ { "start": 346.88, "end": 346.94, "word": " and", "probability": 0.861328125 }, { "start": 346.94, "end": 347.24, "word": " then", "probability": 0.7177734375 }, { "start": 347.24, "end": 348.5, "word": " keep", "probability": 0.32861328125 }, { "start": 348.5, "end": 348.92, "word": " track", "probability": 0.8427734375 }, { "start": 348.92, "end": 349.1, "word": " of", "probability": 0.8994140625 }, { "start": 349.1, "end": 349.28, "word": " how", "probability": 0.90087890625 }, { "start": 349.28, "end": 349.42, "word": " it", "probability": 0.90380859375 }, { "start": 349.42, "end": 349.58, "word": " is", "probability": 0.88134765625 }, { "start": 349.58, "end": 349.96, "word": " actually", "probability": 0.7783203125 }, { "start": 349.96, "end": 350.46, "word": " operating", "probability": 0.88427734375 }, { "start": 350.46, "end": 350.78, "word": ".", "probability": 0.433349609375 } ] }, { "id": 124, "seek": 37284, "start": 350.78, "end": 353.36, "text": " And if it's beyond a certain delta or a difference,", "tokens": [ 50764, 400, 498, 309, 311, 4399, 257, 1629, 8289, 420, 257, 2649, 11, 50864 ], "temperature": 0.0, "avg_logprob": -0.18434873724184117, "compression_ratio": 1.7121771217712176, "no_speech_prob": 0.0002415180206298828, "words": [ { "start": 350.78, "end": 350.8, "word": " And", "probability": 0.67431640625 }, { "start": 350.8, "end": 350.92, "word": " if", "probability": 0.89013671875 }, { "start": 350.92, "end": 351.08, "word": " it's", "probability": 0.937255859375 }, { "start": 351.08, "end": 351.38, "word": " beyond", "probability": 0.72509765625 }, { "start": 351.58, "end": 351.8, "word": " a certain", "probability": 0.78662109375 }, { "start": 351.8, "end": 352.26, "word": " delta", "probability": 0.623046875 }, { "start": 352.26, "end": 352.52, "word": " or", "probability": 0.7724609375 }, { "start": 352.68, "end": 353.18, "word": " a difference", "probability": 0.69970703125 }, { "start": 353.18, "end": 353.36, "word": ",", "probability": 0.88525390625 } ] }, { "id": 125, "seek": 37284, "start": 353.36, "end": 355.24, "text": " then we can flag that and send it off", "tokens": [ 50914, 550, 321, 393, 7166, 300, 293, 2845, 309, 766, 50964 ], "temperature": 0.0, "avg_logprob": -0.18434873724184117, "compression_ratio": 1.7121771217712176, "no_speech_prob": 0.0002415180206298828, "words": [ { "start": 353.36, "end": 353.88, "word": " then", "probability": 0.73095703125 }, { "start": 353.88, "end": 354.0, "word": " we", "probability": 0.90625 }, { "start": 354.0, "end": 354.16, "word": " can", "probability": 0.8916015625 }, { "start": 354.16, "end": 354.48, "word": " flag", "probability": 0.859375 }, { "start": 354.48, "end": 354.72, "word": " that", "probability": 0.87109375 }, { "start": 354.72, "end": 354.88, "word": " and", "probability": 0.87353515625 }, { "start": 354.88, "end": 355.0, "word": " send", "probability": 0.81982421875 }, { "start": 355.0, "end": 355.1, "word": " it", "probability": 0.89892578125 }, { "start": 355.1, "end": 355.24, "word": " off", "probability": 0.8115234375 } ] }, { "id": 126, "seek": 37284, "start": 355.24, "end": 356.74, "text": " to a security analyst.", "tokens": [ 51014, 281, 257, 3825, 19085, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.18434873724184117, "compression_ratio": 1.7121771217712176, "no_speech_prob": 0.0002415180206298828, "words": [ { "start": 355.24, "end": 355.38, "word": " to", "probability": 0.90380859375 }, { "start": 355.5, "end": 355.8, "word": " a security", "probability": 0.912109375 }, { "start": 355.8, "end": 356.26, "word": " analyst", "probability": 0.61962890625 }, { "start": 356.26, "end": 356.74, "word": ".", "probability": 0.994140625 } ] }, { "id": 127, "seek": 37284, "start": 358.04, "end": 360.3, "text": " So why is this important for security analysts,", "tokens": [ 51114, 407, 983, 307, 341, 1021, 337, 3825, 31388, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.18434873724184117, "compression_ratio": 1.7121771217712176, "no_speech_prob": 0.0002415180206298828, "words": [ { "start": 358.04, "end": 358.52, "word": " So", "probability": 0.7841796875 }, { "start": 358.52, "end": 358.7, "word": " why", "probability": 0.73876953125 }, { "start": 358.7, "end": 358.82, "word": " is", "probability": 0.9052734375 }, { "start": 358.82, "end": 358.94, "word": " this", "probability": 0.8740234375 }, { "start": 358.94, "end": 359.24, "word": " important", "probability": 0.78759765625 }, { "start": 359.24, "end": 359.4, "word": " for", "probability": 0.900390625 }, { "start": 359.4, "end": 359.74, "word": " security", "probability": 0.9189453125 }, { "start": 359.74, "end": 360.06, "word": " analysts", "probability": 0.67529296875 }, { "start": 360.06, "end": 360.3, "word": ",", "probability": 0.169677734375 } ] }, { "id": 128, "seek": 37284, "start": 360.3, "end": 362.2, "text": " and also important for hackers?", "tokens": [ 51264, 293, 611, 1021, 337, 39766, 30, 51314 ], "temperature": 0.0, "avg_logprob": -0.18434873724184117, "compression_ratio": 1.7121771217712176, "no_speech_prob": 0.0002415180206298828, "words": [ { "start": 360.3, "end": 360.54, "word": " and", "probability": 0.8935546875 }, { "start": 360.54, "end": 360.82, "word": " also", "probability": 0.81884765625 }, { "start": 360.82, "end": 361.2, "word": " important", "probability": 0.7822265625 }, { "start": 361.2, "end": 361.4, "word": " for", "probability": 0.90478515625 }, { "start": 361.4, "end": 361.72, "word": " hackers", "probability": 0.71826171875 }, { "start": 361.72, "end": 362.2, "word": "?", "probability": 0.59619140625 } ] }, { "id": 129, "seek": 37284, "start": 362.7, "end": 365.46, "text": " Well, today, over a quarter of security products", "tokens": [ 51364, 1042, 11, 965, 11, 670, 257, 6555, 295, 3825, 3383, 51464 ], "temperature": 0.0, "avg_logprob": -0.18434873724184117, "compression_ratio": 1.7121771217712176, "no_speech_prob": 0.0002415180206298828, "words": [ { "start": 362.7, "end": 363.0, "word": " Well", "probability": 0.6279296875 }, { "start": 363.0, "end": 363.1, "word": ",", "probability": 0.53076171875 }, { "start": 363.1, "end": 363.4, "word": " today", "probability": 0.7705078125 }, { "start": 363.4, "end": 363.58, "word": ",", "probability": 0.46923828125 }, { "start": 363.58, "end": 363.78, "word": " over", "probability": 0.8759765625 }, { "start": 363.94, "end": 364.14, "word": " a quarter", "probability": 0.82421875 }, { "start": 364.14, "end": 364.28, "word": " of", "probability": 0.8544921875 }, { "start": 364.28, "end": 365.02, "word": " security", "probability": 0.62841796875 }, { "start": 365.02, "end": 365.46, "word": " products", "probability": 0.7470703125 } ] }, { "id": 130, "seek": 37284, "start": 365.46, "end": 368.64, "text": " for detection have some form of machine learning.", "tokens": [ 51514, 337, 17784, 362, 512, 1254, 295, 3479, 2539, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.18434873724184117, "compression_ratio": 1.7121771217712176, "no_speech_prob": 0.0002415180206298828, "words": [ { "start": 365.46, "end": 365.92, "word": " for", "probability": 0.88623046875 }, { "start": 365.92, "end": 366.42, "word": " detection", "probability": 0.7490234375 }, { "start": 366.42, "end": 366.82, "word": " have", "probability": 0.86279296875 }, { "start": 366.82, "end": 367.06, "word": " some", "probability": 0.81884765625 }, { "start": 367.06, "end": 367.36, "word": " form", "probability": 0.79736328125 }, { "start": 367.36, "end": 367.52, "word": " of", "probability": 0.9013671875 }, { "start": 367.52, "end": 367.82, "word": " machine", "probability": 0.68408203125 }, { "start": 367.82, "end": 368.16, "word": " learning", "probability": 0.84375 }, { "start": 368.16, "end": 368.64, "word": ".", "probability": 0.9833984375 } ] }, { "id": 131, "seek": 37284, "start": 368.8, "end": 370.26, "text": " So from an analyst's perspective,", "tokens": [ 51664, 407, 490, 364, 19085, 311, 4585, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.18434873724184117, "compression_ratio": 1.7121771217712176, "no_speech_prob": 0.0002415180206298828, "words": [ { "start": 368.8, "end": 368.94, "word": " So", "probability": 0.853515625 }, { "start": 368.94, "end": 369.1, "word": " from", "probability": 0.76220703125 }, { "start": 369.1, "end": 369.26, "word": " an", "probability": 0.9091796875 }, { "start": 369.26, "end": 369.66, "word": " analyst's", "probability": 0.4649658203125 }, { "start": 369.66, "end": 370.08, "word": " perspective", "probability": 0.806640625 }, { "start": 370.08, "end": 370.26, "word": ",", "probability": 0.97119140625 } ] }, { "id": 132, "seek": 37284, "start": 370.26, "end": 371.6, "text": " what you want to do is understand", "tokens": [ 51764, 437, 291, 528, 281, 360, 307, 1223, 51814 ], "temperature": 0.0, "avg_logprob": -0.18434873724184117, "compression_ratio": 1.7121771217712176, "no_speech_prob": 0.0002415180206298828, "words": [ { "start": 370.26, "end": 370.38, "word": " what", "probability": 0.8828125 }, { "start": 370.38, "end": 370.5, "word": " you", "probability": 0.892578125 }, { "start": 370.5, "end": 370.64, "word": " want", "probability": 0.71533203125 }, { "start": 370.64, "end": 370.74, "word": " to", "probability": 0.90673828125 }, { "start": 370.74, "end": 370.86, "word": " do", "probability": 0.89990234375 }, { "start": 370.86, "end": 370.98, "word": " is", "probability": 0.89990234375 }, { "start": 370.98, "end": 371.6, "word": " understand", "probability": 0.734375 } ] }, { "id": 133, "seek": 40284, "start": 372.84, "end": 373.22, "text": " how these machines work,", "tokens": [ 50364, 577, 613, 8379, 589, 11, 50414 ], "temperature": 0.0, "avg_logprob": -0.21272322152342116, "compression_ratio": 1.7378640776699028, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 372.84, "end": 372.84, "word": " how", "probability": 0.0019321441650390625 }, { "start": 372.84, "end": 372.84, "word": " these", "probability": 0.028717041015625 }, { "start": 372.84, "end": 372.84, "word": " machines", "probability": 0.062469482421875 }, { "start": 372.84, "end": 372.92, "word": " work", "probability": 0.54248046875 }, { "start": 372.92, "end": 373.22, "word": ",", "probability": 0.345947265625 } ] }, { "id": 134, "seek": 40284, "start": 373.22, "end": 375.44, "text": " so that you can ensure that they operate efficiently", "tokens": [ 50464, 370, 300, 291, 393, 5586, 300, 436, 9651, 19621, 50564 ], "temperature": 0.0, "avg_logprob": -0.21272322152342116, "compression_ratio": 1.7378640776699028, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 373.22, "end": 373.4, "word": " so", "probability": 0.80224609375 }, { "start": 373.4, "end": 373.52, "word": " that", "probability": 0.6123046875 }, { "start": 373.52, "end": 373.6, "word": " you", "probability": 0.8447265625 }, { "start": 373.6, "end": 373.74, "word": " can", "probability": 0.89013671875 }, { "start": 373.74, "end": 374.02, "word": " ensure", "probability": 0.6884765625 }, { "start": 374.02, "end": 374.18, "word": " that", "probability": 0.75146484375 }, { "start": 374.18, "end": 374.3, "word": " they", "probability": 0.71875 }, { "start": 374.3, "end": 374.74, "word": " operate", "probability": 0.74072265625 }, { "start": 374.74, "end": 375.44, "word": " efficiently", "probability": 0.798828125 } ] }, { "id": 135, "seek": 40284, "start": 376.58, "end": 378.28, "text": " and are working effectively.", "tokens": [ 50614, 293, 366, 1364, 8659, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.21272322152342116, "compression_ratio": 1.7378640776699028, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 376.58, "end": 376.96, "word": " and", "probability": 0.66259765625 }, { "start": 376.96, "end": 377.06, "word": " are", "probability": 0.841796875 }, { "start": 377.06, "end": 377.28, "word": " working", "probability": 0.7431640625 }, { "start": 377.28, "end": 377.9, "word": " effectively", "probability": 0.767578125 }, { "start": 377.9, "end": 378.28, "word": ".", "probability": 0.865234375 } ] }, { "id": 136, "seek": 40284, "start": 379.1, "end": 381.36, "text": " Machine learning isn't this magical black box", "tokens": [ 50714, 22155, 2539, 1943, 380, 341, 12066, 2211, 2424, 50814 ], "temperature": 0.0, "avg_logprob": -0.21272322152342116, "compression_ratio": 1.7378640776699028, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 379.1, "end": 379.48, "word": " Machine", "probability": 0.6005859375 }, { "start": 379.48, "end": 379.72, "word": " learning", "probability": 0.72509765625 }, { "start": 379.72, "end": 380.06, "word": " isn't", "probability": 0.8994140625 }, { "start": 380.06, "end": 380.24, "word": " this", "probability": 0.841796875 }, { "start": 380.24, "end": 380.64, "word": " magical", "probability": 0.83203125 }, { "start": 380.64, "end": 381.02, "word": " black", "probability": 0.8447265625 }, { "start": 381.02, "end": 381.36, "word": " box", "probability": 0.79931640625 } ] }, { "id": 137, "seek": 40284, "start": 381.36, "end": 383.18, "text": " that just solves all of our problems.", "tokens": [ 50864, 300, 445, 39890, 439, 295, 527, 2740, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.21272322152342116, "compression_ratio": 1.7378640776699028, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 381.36, "end": 381.54, "word": " that", "probability": 0.80712890625 }, { "start": 381.54, "end": 381.72, "word": " just", "probability": 0.6748046875 }, { "start": 381.72, "end": 381.98, "word": " solves", "probability": 0.82275390625 }, { "start": 381.98, "end": 382.16, "word": " all", "probability": 0.8994140625 }, { "start": 382.16, "end": 382.26, "word": " of", "probability": 0.876953125 }, { "start": 382.26, "end": 382.36, "word": " our", "probability": 0.82177734375 }, { "start": 382.36, "end": 382.8, "word": " problems", "probability": 0.69580078125 }, { "start": 382.8, "end": 383.18, "word": ".", "probability": 0.96142578125 } ] }, { "id": 138, "seek": 40284, "start": 383.92, "end": 385.48, "text": " And I want to share a story with you,", "tokens": [ 50964, 400, 286, 528, 281, 2073, 257, 1657, 365, 291, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.21272322152342116, "compression_ratio": 1.7378640776699028, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 383.92, "end": 384.26, "word": " And", "probability": 0.41357421875 }, { "start": 384.26, "end": 384.32, "word": " I", "probability": 0.97314453125 }, { "start": 384.32, "end": 384.42, "word": " want", "probability": 0.7216796875 }, { "start": 384.42, "end": 384.5, "word": " to", "probability": 0.90380859375 }, { "start": 384.5, "end": 384.64, "word": " share", "probability": 0.7822265625 }, { "start": 384.78, "end": 384.94, "word": " a story", "probability": 0.8779296875 }, { "start": 384.94, "end": 385.16, "word": " with", "probability": 0.814453125 }, { "start": 385.16, "end": 385.34, "word": " you", "probability": 0.89111328125 }, { "start": 385.34, "end": 385.48, "word": ",", "probability": 0.436279296875 } ] }, { "id": 139, "seek": 40284, "start": 385.48, "end": 388.24, "text": " and this is what really made the idea of machine learning", "tokens": [ 51064, 293, 341, 307, 437, 534, 1027, 264, 1558, 295, 3479, 2539, 51164 ], "temperature": 0.0, "avg_logprob": -0.21272322152342116, "compression_ratio": 1.7378640776699028, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 385.48, "end": 385.56, "word": " and", "probability": 0.771484375 }, { "start": 385.56, "end": 385.7, "word": " this", "probability": 0.8798828125 }, { "start": 385.7, "end": 385.82, "word": " is", "probability": 0.89013671875 }, { "start": 385.82, "end": 385.96, "word": " what", "probability": 0.87451171875 }, { "start": 385.96, "end": 386.24, "word": " really", "probability": 0.6884765625 }, { "start": 386.24, "end": 386.72, "word": " made", "probability": 0.81298828125 }, { "start": 386.72, "end": 386.92, "word": " the", "probability": 0.8056640625 }, { "start": 386.92, "end": 387.32, "word": " idea", "probability": 0.76953125 }, { "start": 387.32, "end": 387.64, "word": " of", "probability": 0.9013671875 }, { "start": 387.64, "end": 387.96, "word": " machine", "probability": 0.7021484375 }, { "start": 387.96, "end": 388.24, "word": " learning", "probability": 0.837890625 } ] }, { "id": 140, "seek": 40284, "start": 388.24, "end": 391.02, "text": " and the value of machine learning really stick out to me.", "tokens": [ 51214, 293, 264, 2158, 295, 3479, 2539, 534, 2897, 484, 281, 385, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.21272322152342116, "compression_ratio": 1.7378640776699028, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 388.24, "end": 388.4, "word": " and", "probability": 0.74853515625 }, { "start": 388.4, "end": 388.58, "word": " the", "probability": 0.81494140625 }, { "start": 388.58, "end": 388.92, "word": " value", "probability": 0.92529296875 }, { "start": 388.92, "end": 389.08, "word": " of", "probability": 0.89892578125 }, { "start": 389.08, "end": 389.36, "word": " machine", "probability": 0.71484375 }, { "start": 389.36, "end": 389.64, "word": " learning", "probability": 0.8525390625 }, { "start": 389.64, "end": 389.86, "word": " really", "probability": 0.744140625 }, { "start": 389.86, "end": 390.14, "word": " stick", "probability": 0.8984375 }, { "start": 390.14, "end": 390.3, "word": " out", "probability": 0.81982421875 }, { "start": 390.3, "end": 390.44, "word": " to", "probability": 0.90087890625 }, { "start": 390.44, "end": 390.64, "word": " me", "probability": 0.904296875 }, { "start": 390.64, "end": 391.02, "word": ".", "probability": 0.9921875 } ] }, { "id": 141, "seek": 40284, "start": 391.48, "end": 392.52, "text": " So a number of years ago,", "tokens": [ 51364, 407, 257, 1230, 295, 924, 2057, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.21272322152342116, "compression_ratio": 1.7378640776699028, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 391.48, "end": 391.6, "word": " So", "probability": 0.68408203125 }, { "start": 391.7, "end": 391.82, "word": " a number", "probability": 0.86865234375 }, { "start": 391.82, "end": 391.98, "word": " of", "probability": 0.90576171875 }, { "start": 391.98, "end": 392.14, "word": " years", "probability": 0.88037109375 }, { "start": 392.14, "end": 392.4, "word": " ago", "probability": 0.81298828125 }, { "start": 392.4, "end": 392.52, "word": ",", "probability": 0.82080078125 } ] }, { "id": 142, "seek": 40284, "start": 392.62, "end": 395.42, "text": " a friend of mine was approached by a non-profit.", "tokens": [ 51464, 257, 1277, 295, 3892, 390, 17247, 538, 257, 2107, 12, 14583, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.21272322152342116, "compression_ratio": 1.7378640776699028, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 392.62, "end": 392.8, "word": " a friend", "probability": 0.634765625 }, { "start": 392.8, "end": 392.96, "word": " of", "probability": 0.90625 }, { "start": 392.96, "end": 393.28, "word": " mine", "probability": 0.85400390625 }, { "start": 393.28, "end": 393.9, "word": " was", "probability": 0.8828125 }, { "start": 393.9, "end": 394.22, "word": " approached", "probability": 0.61962890625 }, { "start": 394.22, "end": 394.4, "word": " by", "probability": 0.90673828125 }, { "start": 394.58, "end": 394.78, "word": " a non", "probability": 0.61083984375 }, { "start": 394.78, "end": 395.12, "word": "-profit", "probability": 0.77734375 }, { "start": 395.12, "end": 395.42, "word": ".", "probability": 0.40576171875 } ] }, { "id": 143, "seek": 40284, "start": 395.42, "end": 397.2, "text": " And what this non-profit did was track", "tokens": [ 51564, 400, 437, 341, 2107, 12, 14583, 630, 390, 2837, 51614 ], "temperature": 0.0, "avg_logprob": -0.21272322152342116, "compression_ratio": 1.7378640776699028, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 395.42, "end": 395.5, "word": " And", "probability": 0.8291015625 }, { "start": 395.5, "end": 395.64, "word": " what", "probability": 0.8759765625 }, { "start": 395.64, "end": 395.78, "word": " this", "probability": 0.8828125 }, { "start": 395.78, "end": 396.0, "word": " non", "probability": 0.84033203125 }, { "start": 396.0, "end": 396.2, "word": "-profit", "probability": 0.905517578125 }, { "start": 396.2, "end": 396.58, "word": " did", "probability": 0.89111328125 }, { "start": 396.58, "end": 396.78, "word": " was", "probability": 0.8466796875 }, { "start": 396.78, "end": 397.2, "word": " track", "probability": 0.73291015625 } ] }, { "id": 144, "seek": 40284, "start": 397.2, "end": 399.18, "text": " cheetah population out in Africa.", "tokens": [ 51664, 947, 47947, 4415, 484, 294, 7349, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.21272322152342116, "compression_ratio": 1.7378640776699028, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 397.2, "end": 397.52, "word": " cheetah", "probability": 0.8466796875 }, { "start": 397.52, "end": 398.18, "word": " population", "probability": 0.81640625 }, { "start": 398.18, "end": 398.5, "word": " out", "probability": 0.76806640625 }, { "start": 398.5, "end": 398.58, "word": " in", "probability": 0.9052734375 }, { "start": 398.58, "end": 398.92, "word": " Africa", "probability": 0.72314453125 }, { "start": 398.92, "end": 399.18, "word": ".", "probability": 0.89453125 } ] }, { "id": 145, "seek": 40284, "start": 399.18, "end": 401.36, "text": " So they set up a bunch of different cameras,", "tokens": [ 51764, 407, 436, 992, 493, 257, 3840, 295, 819, 8622, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.21272322152342116, "compression_ratio": 1.7378640776699028, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 399.18, "end": 399.36, "word": " So", "probability": 0.8388671875 }, { "start": 399.36, "end": 399.52, "word": " they", "probability": 0.72412109375 }, { "start": 399.52, "end": 399.66, "word": " set", "probability": 0.88427734375 }, { "start": 399.66, "end": 399.78, "word": " up", "probability": 0.9033203125 }, { "start": 399.88, "end": 400.04, "word": " a bunch", "probability": 0.80712890625 }, { "start": 400.04, "end": 400.14, "word": " of", "probability": 0.90380859375 }, { "start": 400.14, "end": 400.42, "word": " different", "probability": 0.66357421875 }, { "start": 400.42, "end": 400.76, "word": " cameras", "probability": 0.8232421875 }, { "start": 400.76, "end": 401.36, "word": ",", "probability": 0.65087890625 } ] }, { "id": 146, "seek": 42986, "start": 402.84, "end": 404.96, "text": " and they would take a picture at different intervals,", "tokens": [ 50364, 293, 436, 576, 747, 257, 3036, 412, 819, 26651, 11, 50464 ], "temperature": 0.0, "avg_logprob": -0.18050698675475754, "compression_ratio": 1.7124183006535947, "no_speech_prob": 0.00029587745666503906, "words": [ { "start": 402.84, "end": 402.84, "word": " and", "probability": 0.024444580078125 }, { "start": 402.84, "end": 402.84, "word": " they", "probability": 0.041839599609375 }, { "start": 402.84, "end": 402.84, "word": " would", "probability": 0.61474609375 }, { "start": 402.84, "end": 402.9, "word": " take", "probability": 0.5947265625 }, { "start": 403.04, "end": 403.28, "word": " a picture", "probability": 0.7900390625 }, { "start": 403.28, "end": 403.64, "word": " at", "probability": 0.87255859375 }, { "start": 403.64, "end": 404.04, "word": " different", "probability": 0.6630859375 }, { "start": 404.04, "end": 404.48, "word": " intervals", "probability": 0.72412109375 }, { "start": 404.48, "end": 404.96, "word": ",", "probability": 0.3310546875 } ] }, { "id": 147, "seek": 42986, "start": 404.96, "end": 406.62, "text": " and it would be sent off to a human analyst", "tokens": [ 50514, 293, 309, 576, 312, 2279, 766, 281, 257, 1952, 19085, 50564 ], "temperature": 0.0, "avg_logprob": -0.18050698675475754, "compression_ratio": 1.7124183006535947, "no_speech_prob": 0.00029587745666503906, "words": [ { "start": 404.96, "end": 405.06, "word": " and", "probability": 0.880859375 }, { "start": 405.06, "end": 405.18, "word": " it", "probability": 0.87451171875 }, { "start": 405.18, "end": 405.26, "word": " would", "probability": 0.84375 }, { "start": 405.26, "end": 405.4, "word": " be", "probability": 0.89794921875 }, { "start": 405.4, "end": 405.56, "word": " sent", "probability": 0.7724609375 }, { "start": 405.56, "end": 405.72, "word": " off", "probability": 0.79248046875 }, { "start": 405.72, "end": 405.82, "word": " to", "probability": 0.89990234375 }, { "start": 405.94, "end": 406.14, "word": " a human", "probability": 0.82373046875 }, { "start": 406.14, "end": 406.62, "word": " analyst", "probability": 0.55712890625 } ] }, { "id": 148, "seek": 42986, "start": 406.62, "end": 409.9, "text": " to identify whether or not there's a cheetah in the picture.", "tokens": [ 50614, 281, 5876, 1968, 420, 406, 456, 311, 257, 947, 47947, 294, 264, 3036, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.18050698675475754, "compression_ratio": 1.7124183006535947, "no_speech_prob": 0.00029587745666503906, "words": [ { "start": 406.62, "end": 406.84, "word": " to", "probability": 0.76318359375 }, { "start": 406.84, "end": 407.5, "word": " identify", "probability": 0.89990234375 }, { "start": 407.5, "end": 408.22, "word": " whether", "probability": 0.82763671875 }, { "start": 408.22, "end": 408.4, "word": " or", "probability": 0.8994140625 }, { "start": 408.4, "end": 408.56, "word": " not", "probability": 0.890625 }, { "start": 408.56, "end": 408.78, "word": " there's", "probability": 0.85888671875 }, { "start": 408.9, "end": 409.06, "word": " a cheetah", "probability": 0.905517578125 }, { "start": 409.06, "end": 409.16, "word": " in", "probability": 0.8974609375 }, { "start": 409.16, "end": 409.24, "word": " the", "probability": 0.810546875 }, { "start": 409.24, "end": 409.54, "word": " picture", "probability": 0.78173828125 }, { "start": 409.54, "end": 409.9, "word": ".", "probability": 0.96142578125 } ] }, { "id": 149, "seek": 42986, "start": 410.42, "end": 412.02, "text": " Not a job I would want to do,", "tokens": [ 50764, 1726, 257, 1691, 286, 576, 528, 281, 360, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.18050698675475754, "compression_ratio": 1.7124183006535947, "no_speech_prob": 0.00029587745666503906, "words": [ { "start": 410.42, "end": 410.78, "word": " Not", "probability": 0.880859375 }, { "start": 410.88, "end": 411.02, "word": " a job", "probability": 0.89697265625 }, { "start": 411.02, "end": 411.16, "word": " I", "probability": 0.9853515625 }, { "start": 411.16, "end": 411.28, "word": " would", "probability": 0.8154296875 }, { "start": 411.28, "end": 411.46, "word": " want", "probability": 0.62451171875 }, { "start": 411.46, "end": 411.6, "word": " to", "probability": 0.90087890625 }, { "start": 411.6, "end": 411.8, "word": " do", "probability": 0.90625 }, { "start": 411.8, "end": 412.02, "word": ",", "probability": 0.884765625 } ] }, { "id": 150, "seek": 42986, "start": 412.02, "end": 414.88, "text": " but it needs done, and it's really important.", "tokens": [ 50864, 457, 309, 2203, 1096, 11, 293, 309, 311, 534, 1021, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.18050698675475754, "compression_ratio": 1.7124183006535947, "no_speech_prob": 0.00029587745666503906, "words": [ { "start": 412.02, "end": 412.26, "word": " but", "probability": 0.90283203125 }, { "start": 412.26, "end": 412.56, "word": " it", "probability": 0.8974609375 }, { "start": 412.56, "end": 413.16, "word": " needs", "probability": 0.7236328125 }, { "start": 413.16, "end": 413.46, "word": " done", "probability": 0.796875 }, { "start": 413.46, "end": 413.7, "word": ",", "probability": 0.5595703125 }, { "start": 413.7, "end": 413.76, "word": " and", "probability": 0.89697265625 }, { "start": 413.76, "end": 413.9, "word": " it's", "probability": 0.94921875 }, { "start": 413.9, "end": 414.1, "word": " really", "probability": 0.78369140625 }, { "start": 414.1, "end": 414.52, "word": " important", "probability": 0.7763671875 }, { "start": 414.52, "end": 414.88, "word": ".", "probability": 0.96728515625 } ] }, { "id": 151, "seek": 42986, "start": 416.1, "end": 417.22, "text": " So they approached my friend,", "tokens": [ 51014, 407, 436, 17247, 452, 1277, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.18050698675475754, "compression_ratio": 1.7124183006535947, "no_speech_prob": 0.00029587745666503906, "words": [ { "start": 416.1, "end": 416.46, "word": " So", "probability": 0.81884765625 }, { "start": 416.46, "end": 416.6, "word": " they", "probability": 0.66162109375 }, { "start": 416.6, "end": 416.8, "word": " approached", "probability": 0.6279296875 }, { "start": 416.8, "end": 416.96, "word": " my", "probability": 0.90478515625 }, { "start": 416.96, "end": 417.16, "word": " friend", "probability": 0.65283203125 }, { "start": 417.16, "end": 417.22, "word": ",", "probability": 0.415283203125 } ] }, { "id": 152, "seek": 42986, "start": 417.22, "end": 418.4, "text": " and they were saying, hey, is there a way", "tokens": [ 51114, 293, 436, 645, 1566, 11, 4177, 11, 307, 456, 257, 636, 51164 ], "temperature": 0.0, "avg_logprob": -0.18050698675475754, "compression_ratio": 1.7124183006535947, "no_speech_prob": 0.00029587745666503906, "words": [ { "start": 417.22, "end": 417.28, "word": " and", "probability": 0.88720703125 }, { "start": 417.28, "end": 417.34, "word": " they", "probability": 0.7333984375 }, { "start": 417.34, "end": 417.44, "word": " were", "probability": 0.85986328125 }, { "start": 417.44, "end": 417.64, "word": " saying", "probability": 0.80517578125 }, { "start": 417.64, "end": 417.76, "word": ",", "probability": 0.88427734375 }, { "start": 417.76, "end": 417.9, "word": " hey", "probability": 0.1826171875 }, { "start": 417.9, "end": 417.98, "word": ",", "probability": 0.91162109375 }, { "start": 417.98, "end": 418.12, "word": " is", "probability": 0.90283203125 }, { "start": 418.12, "end": 418.22, "word": " there", "probability": 0.8544921875 }, { "start": 418.3, "end": 418.4, "word": " a way", "probability": 0.900390625 } ] }, { "id": 153, "seek": 42986, "start": 418.4, "end": 420.26, "text": " that we can increase our efficiency?", "tokens": [ 51214, 300, 321, 393, 3488, 527, 10493, 30, 51264 ], "temperature": 0.0, "avg_logprob": -0.18050698675475754, "compression_ratio": 1.7124183006535947, "no_speech_prob": 0.00029587745666503906, "words": [ { "start": 418.4, "end": 418.52, "word": " that", "probability": 0.81103515625 }, { "start": 418.52, "end": 418.64, "word": " we", "probability": 0.90380859375 }, { "start": 418.64, "end": 418.8, "word": " can", "probability": 0.8828125 }, { "start": 418.8, "end": 419.28, "word": " increase", "probability": 0.7646484375 }, { "start": 419.28, "end": 419.62, "word": " our", "probability": 0.8095703125 }, { "start": 419.62, "end": 420.06, "word": " efficiency", "probability": 0.85302734375 }, { "start": 420.06, "end": 420.26, "word": "?", "probability": 0.41845703125 } ] }, { "id": 154, "seek": 42986, "start": 420.26, "end": 422.68, "text": " Something that we can use to kind of automate", "tokens": [ 51314, 6595, 300, 321, 393, 764, 281, 733, 295, 31605, 51364 ], "temperature": 0.0, "avg_logprob": -0.18050698675475754, "compression_ratio": 1.7124183006535947, "no_speech_prob": 0.00029587745666503906, "words": [ { "start": 420.26, "end": 420.42, "word": " Something", "probability": 0.7734375 }, { "start": 420.42, "end": 420.86, "word": " that", "probability": 0.87109375 }, { "start": 420.86, "end": 421.28, "word": " we", "probability": 0.896484375 }, { "start": 421.28, "end": 421.44, "word": " can", "probability": 0.88427734375 }, { "start": 421.44, "end": 421.8, "word": " use", "probability": 0.8193359375 }, { "start": 421.8, "end": 422.06, "word": " to", "probability": 0.90234375 }, { "start": 422.06, "end": 422.28, "word": " kind", "probability": 0.53857421875 }, { "start": 422.28, "end": 422.34, "word": " of", "probability": 0.900390625 }, { "start": 422.34, "end": 422.68, "word": " automate", "probability": 0.875 } ] }, { "id": 155, "seek": 42986, "start": 422.68, "end": 424.78, "text": " some of the manual labor that we're doing.", "tokens": [ 51414, 512, 295, 264, 9688, 5938, 300, 321, 434, 884, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.18050698675475754, "compression_ratio": 1.7124183006535947, "no_speech_prob": 0.00029587745666503906, "words": [ { "start": 422.68, "end": 422.9, "word": " some", "probability": 0.8115234375 }, { "start": 422.9, "end": 422.98, "word": " of", "probability": 0.90185546875 }, { "start": 422.98, "end": 423.2, "word": " the", "probability": 0.81982421875 }, { "start": 423.2, "end": 423.58, "word": " manual", "probability": 0.93212890625 }, { "start": 423.58, "end": 423.88, "word": " labor", "probability": 0.79541015625 }, { "start": 423.88, "end": 424.04, "word": " that", "probability": 0.87841796875 }, { "start": 424.04, "end": 424.16, "word": " we're", "probability": 0.925048828125 }, { "start": 424.16, "end": 424.42, "word": " doing", "probability": 0.9130859375 }, { "start": 424.42, "end": 424.78, "word": ".", "probability": 0.7119140625 } ] }, { "id": 156, "seek": 42986, "start": 425.18, "end": 426.84, "text": " And so what he did was spend about a week,", "tokens": [ 51514, 400, 370, 437, 415, 630, 390, 3496, 466, 257, 1243, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.18050698675475754, "compression_ratio": 1.7124183006535947, "no_speech_prob": 0.00029587745666503906, "words": [ { "start": 425.18, "end": 425.42, "word": " And", "probability": 0.8544921875 }, { "start": 425.42, "end": 425.54, "word": " so", "probability": 0.89111328125 }, { "start": 425.54, "end": 425.68, "word": " what", "probability": 0.84033203125 }, { "start": 425.68, "end": 425.84, "word": " he", "probability": 0.90869140625 }, { "start": 425.84, "end": 425.98, "word": " did", "probability": 0.8857421875 }, { "start": 425.98, "end": 426.12, "word": " was", "probability": 0.8681640625 }, { "start": 426.12, "end": 426.3, "word": " spend", "probability": 0.79541015625 }, { "start": 426.3, "end": 426.46, "word": " about", "probability": 0.81591796875 }, { "start": 426.6, "end": 426.78, "word": " a week", "probability": 0.81787109375 }, { "start": 426.78, "end": 426.84, "word": ",", "probability": 0.7861328125 } ] }, { "id": 157, "seek": 42986, "start": 426.84, "end": 429.86, "text": " and he used a very simple machine learning model", "tokens": [ 51614, 293, 415, 1143, 257, 588, 2199, 3479, 2539, 2316, 51714 ], "temperature": 0.0, "avg_logprob": -0.18050698675475754, "compression_ratio": 1.7124183006535947, "no_speech_prob": 0.00029587745666503906, "words": [ { "start": 426.84, "end": 426.94, "word": " and", "probability": 0.89404296875 }, { "start": 426.94, "end": 427.06, "word": " he", "probability": 0.89990234375 }, { "start": 427.06, "end": 427.28, "word": " used", "probability": 0.8076171875 }, { "start": 427.6, "end": 427.84, "word": " a very", "probability": 0.73095703125 }, { "start": 427.84, "end": 428.34, "word": " simple", "probability": 0.9130859375 }, { "start": 428.34, "end": 429.12, "word": " machine", "probability": 0.7041015625 }, { "start": 429.12, "end": 429.42, "word": " learning", "probability": 0.71142578125 }, { "start": 429.42, "end": 429.86, "word": " model", "probability": 0.8046875 } ] }, { "id": 158, "seek": 45986, "start": 431.3, "end": 433.14, "text": " to identify images.", "tokens": [ 50364, 281, 5876, 5267, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.13752386201429004, "compression_ratio": 1.624031007751938, "no_speech_prob": 0.00028252601623535156, "words": [ { "start": 431.3, "end": 431.74, "word": " to", "probability": 0.4580078125 }, { "start": 431.74, "end": 432.18, "word": " identify", "probability": 0.85205078125 }, { "start": 432.18, "end": 432.7, "word": " images", "probability": 0.845703125 }, { "start": 432.7, "end": 433.14, "word": ".", "probability": 0.51123046875 } ] }, { "id": 159, "seek": 45986, "start": 433.2, "end": 435.84, "text": " And what he told this model was,", "tokens": [ 50514, 400, 437, 415, 1907, 341, 2316, 390, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.13752386201429004, "compression_ratio": 1.624031007751938, "no_speech_prob": 0.00028252601623535156, "words": [ { "start": 433.2, "end": 433.42, "word": " And", "probability": 0.765625 }, { "start": 433.42, "end": 433.84, "word": " what", "probability": 0.85888671875 }, { "start": 433.84, "end": 433.96, "word": " he", "probability": 0.90283203125 }, { "start": 433.96, "end": 434.14, "word": " told", "probability": 0.90771484375 }, { "start": 434.14, "end": 434.32, "word": " this", "probability": 0.826171875 }, { "start": 434.32, "end": 434.58, "word": " model", "probability": 0.80908203125 }, { "start": 434.58, "end": 435.2, "word": " was", "probability": 0.880859375 }, { "start": 435.2, "end": 435.84, "word": ",", "probability": 0.837890625 } ] }, { "id": 160, "seek": 45986, "start": 435.84, "end": 437.44, "text": " hey, if you see an image,", "tokens": [ 50614, 4177, 11, 498, 291, 536, 364, 3256, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.13752386201429004, "compression_ratio": 1.624031007751938, "no_speech_prob": 0.00028252601623535156, "words": [ { "start": 435.84, "end": 436.0, "word": " hey", "probability": 0.268798828125 }, { "start": 436.0, "end": 436.12, "word": ",", "probability": 0.888671875 }, { "start": 436.12, "end": 436.3, "word": " if", "probability": 0.8994140625 }, { "start": 436.3, "end": 436.56, "word": " you", "probability": 0.89990234375 }, { "start": 436.56, "end": 436.86, "word": " see", "probability": 0.8134765625 }, { "start": 436.86, "end": 437.0, "word": " an", "probability": 0.89794921875 }, { "start": 437.0, "end": 437.3, "word": " image", "probability": 0.83984375 }, { "start": 437.3, "end": 437.44, "word": ",", "probability": 0.2042236328125 } ] }, { "id": 161, "seek": 45986, "start": 437.44, "end": 439.94, "text": " and you are at least 5% confident", "tokens": [ 50714, 293, 291, 366, 412, 1935, 1025, 4, 6679, 50814 ], "temperature": 0.0, "avg_logprob": -0.13752386201429004, "compression_ratio": 1.624031007751938, "no_speech_prob": 0.00028252601623535156, "words": [ { "start": 437.44, "end": 437.62, "word": " and", "probability": 0.8935546875 }, { "start": 437.62, "end": 437.78, "word": " you", "probability": 0.89501953125 }, { "start": 437.78, "end": 438.04, "word": " are", "probability": 0.87841796875 }, { "start": 438.04, "end": 438.54, "word": " at", "probability": 0.89306640625 }, { "start": 438.54, "end": 438.74, "word": " least", "probability": 0.8564453125 }, { "start": 438.74, "end": 439.22, "word": " 5", "probability": 0.822265625 }, { "start": 439.22, "end": 439.44, "word": "%", "probability": 0.96728515625 }, { "start": 439.44, "end": 439.94, "word": " confident", "probability": 0.92236328125 } ] }, { "id": 162, "seek": 45986, "start": 439.94, "end": 442.08, "text": " that there's a cheetah in the picture,", "tokens": [ 50864, 300, 456, 311, 257, 947, 47947, 294, 264, 3036, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.13752386201429004, "compression_ratio": 1.624031007751938, "no_speech_prob": 0.00028252601623535156, "words": [ { "start": 439.94, "end": 440.62, "word": " that", "probability": 0.84521484375 }, { "start": 440.62, "end": 440.86, "word": " there's", "probability": 0.785400390625 }, { "start": 440.98, "end": 441.18, "word": " a cheetah", "probability": 0.927978515625 }, { "start": 441.18, "end": 441.32, "word": " in", "probability": 0.90283203125 }, { "start": 441.32, "end": 441.42, "word": " the", "probability": 0.81396484375 }, { "start": 441.42, "end": 441.76, "word": " picture", "probability": 0.7666015625 }, { "start": 441.76, "end": 442.08, "word": ",", "probability": 0.966796875 } ] }, { "id": 163, "seek": 45986, "start": 442.08, "end": 443.74, "text": " send it off to an analyst.", "tokens": [ 50964, 2845, 309, 766, 281, 364, 19085, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.13752386201429004, "compression_ratio": 1.624031007751938, "no_speech_prob": 0.00028252601623535156, "words": [ { "start": 442.08, "end": 442.4, "word": " send", "probability": 0.8251953125 }, { "start": 442.4, "end": 442.52, "word": " it", "probability": 0.90283203125 }, { "start": 442.52, "end": 442.7, "word": " off", "probability": 0.80224609375 }, { "start": 442.7, "end": 442.84, "word": " to", "probability": 0.90380859375 }, { "start": 442.84, "end": 442.98, "word": " an", "probability": 0.9033203125 }, { "start": 442.98, "end": 443.4, "word": " analyst", "probability": 0.60888671875 }, { "start": 443.4, "end": 443.74, "word": ".", "probability": 0.96240234375 } ] }, { "id": 164, "seek": 45986, "start": 443.74, "end": 445.68, "text": " If you're less than 5% confident,", "tokens": [ 51064, 759, 291, 434, 1570, 813, 1025, 4, 6679, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.13752386201429004, "compression_ratio": 1.624031007751938, "no_speech_prob": 0.00028252601623535156, "words": [ { "start": 443.74, "end": 444.1, "word": " If", "probability": 0.8955078125 }, { "start": 444.1, "end": 444.24, "word": " you're", "probability": 0.915283203125 }, { "start": 444.24, "end": 444.46, "word": " less", "probability": 0.88916015625 }, { "start": 444.46, "end": 444.62, "word": " than", "probability": 0.875 }, { "start": 444.62, "end": 444.88, "word": " 5", "probability": 0.99658203125 }, { "start": 444.88, "end": 445.1, "word": "%", "probability": 0.98779296875 }, { "start": 445.1, "end": 445.54, "word": " confident", "probability": 0.92578125 }, { "start": 445.54, "end": 445.68, "word": ",", "probability": 0.94580078125 } ] }, { "id": 165, "seek": 45986, "start": 445.68, "end": 446.92, "text": " just throw it away.", "tokens": [ 51164, 445, 3507, 309, 1314, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.13752386201429004, "compression_ratio": 1.624031007751938, "no_speech_prob": 0.00028252601623535156, "words": [ { "start": 445.68, "end": 445.82, "word": " just", "probability": 0.884765625 }, { "start": 445.82, "end": 446.08, "word": " throw", "probability": 0.79248046875 }, { "start": 446.08, "end": 446.22, "word": " it", "probability": 0.9013671875 }, { "start": 446.22, "end": 446.48, "word": " away", "probability": 0.8154296875 }, { "start": 446.48, "end": 446.92, "word": ".", "probability": 0.9921875 } ] }, { "id": 166, "seek": 45986, "start": 447.64, "end": 449.64, "text": " Now 5%, that doesn't really sound like a lot,", "tokens": [ 51264, 823, 1025, 8923, 300, 1177, 380, 534, 1626, 411, 257, 688, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.13752386201429004, "compression_ratio": 1.624031007751938, "no_speech_prob": 0.00028252601623535156, "words": [ { "start": 447.64, "end": 447.82, "word": " Now", "probability": 0.89208984375 }, { "start": 447.82, "end": 448.24, "word": " 5%,", "probability": 0.6048583984375 }, { "start": 448.24, "end": 448.4, "word": " that", "probability": 0.88623046875 }, { "start": 448.4, "end": 448.56, "word": " doesn't", "probability": 0.929931640625 }, { "start": 448.56, "end": 448.76, "word": " really", "probability": 0.7646484375 }, { "start": 448.76, "end": 449.04, "word": " sound", "probability": 0.794921875 }, { "start": 449.04, "end": 449.22, "word": " like", "probability": 0.876953125 }, { "start": 449.34, "end": 449.56, "word": " a lot", "probability": 0.88916015625 }, { "start": 449.56, "end": 449.64, "word": ",", "probability": 0.5166015625 } ] }, { "id": 167, "seek": 45986, "start": 449.64, "end": 451.16, "text": " and to be honest, it's not.", "tokens": [ 51364, 293, 281, 312, 3245, 11, 309, 311, 406, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.13752386201429004, "compression_ratio": 1.624031007751938, "no_speech_prob": 0.00028252601623535156, "words": [ { "start": 449.64, "end": 449.76, "word": " and", "probability": 0.89794921875 }, { "start": 449.76, "end": 449.86, "word": " to", "probability": 0.8876953125 }, { "start": 449.86, "end": 449.94, "word": " be", "probability": 0.904296875 }, { "start": 449.94, "end": 450.18, "word": " honest", "probability": 0.853515625 }, { "start": 450.18, "end": 450.28, "word": ",", "probability": 0.91650390625 }, { "start": 450.28, "end": 450.46, "word": " it's", "probability": 0.952880859375 }, { "start": 450.46, "end": 450.72, "word": " not", "probability": 0.89697265625 }, { "start": 450.72, "end": 451.16, "word": ".", "probability": 0.90380859375 } ] }, { "id": 168, "seek": 45986, "start": 451.32, "end": 453.74, "text": " But what this non-profit was able to do", "tokens": [ 51464, 583, 437, 341, 2107, 12, 14583, 390, 1075, 281, 360, 51514 ], "temperature": 0.0, "avg_logprob": -0.13752386201429004, "compression_ratio": 1.624031007751938, "no_speech_prob": 0.00028252601623535156, "words": [ { "start": 451.32, "end": 451.66, "word": " But", "probability": 0.892578125 }, { "start": 451.66, "end": 452.32, "word": " what", "probability": 0.8154296875 }, { "start": 452.32, "end": 452.48, "word": " this", "probability": 0.884765625 }, { "start": 452.48, "end": 452.68, "word": " non", "probability": 0.43994140625 }, { "start": 452.68, "end": 452.88, "word": "-profit", "probability": 0.660400390625 }, { "start": 452.88, "end": 453.08, "word": " was", "probability": 0.89501953125 }, { "start": 453.08, "end": 453.22, "word": " able", "probability": 0.888671875 }, { "start": 453.22, "end": 453.4, "word": " to", "probability": 0.90673828125 }, { "start": 453.4, "end": 453.74, "word": " do", "probability": 0.90087890625 } ] }, { "id": 169, "seek": 45986, "start": 453.74, "end": 455.86, "text": " with this simple model was", "tokens": [ 51564, 365, 341, 2199, 2316, 390, 51664 ], "temperature": 0.0, "avg_logprob": -0.13752386201429004, "compression_ratio": 1.624031007751938, "no_speech_prob": 0.00028252601623535156, "words": [ { "start": 453.74, "end": 454.06, "word": " with", "probability": 0.7392578125 }, { "start": 454.06, "end": 454.32, "word": " this", "probability": 0.88525390625 }, { "start": 454.32, "end": 454.62, "word": " simple", "probability": 0.9189453125 }, { "start": 454.62, "end": 455.08, "word": " model", "probability": 0.7998046875 }, { "start": 455.08, "end": 455.86, "word": " was", "probability": 0.685546875 } ] }, { "id": 170, "seek": 45986, "start": 457.24, "end": 459.68, "text": " what would normally take them a year of labor", "tokens": [ 51714, 437, 576, 5646, 747, 552, 257, 1064, 295, 5938, 51814 ], "temperature": 0.0, "avg_logprob": -0.13752386201429004, "compression_ratio": 1.624031007751938, "no_speech_prob": 0.00028252601623535156, "words": [ { "start": 457.24, "end": 457.68, "word": " what", "probability": 0.759765625 }, { "start": 457.68, "end": 457.8, "word": " would", "probability": 0.83447265625 }, { "start": 457.8, "end": 458.1, "word": " normally", "probability": 0.86865234375 }, { "start": 458.1, "end": 458.4, "word": " take", "probability": 0.81640625 }, { "start": 458.4, "end": 458.6, "word": " them", "probability": 0.7314453125 }, { "start": 458.82, "end": 459.18, "word": " a year", "probability": 0.873046875 }, { "start": 459.18, "end": 459.38, "word": " of", "probability": 0.90380859375 }, { "start": 459.38, "end": 459.68, "word": " labor", "probability": 0.7509765625 } ] }, { "id": 171, "seek": 48788, "start": 459.86, "end": 461.98, "text": " they were able to complete in one month.", "tokens": [ 50364, 436, 645, 1075, 281, 3566, 294, 472, 1618, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.17432851239669422, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.00019109249114990234, "words": [ { "start": 459.86, "end": 460.22, "word": " they", "probability": 0.2457275390625 }, { "start": 460.22, "end": 460.32, "word": " were", "probability": 0.83251953125 }, { "start": 460.32, "end": 460.5, "word": " able", "probability": 0.88623046875 }, { "start": 460.5, "end": 460.64, "word": " to", "probability": 0.908203125 }, { "start": 460.64, "end": 460.94, "word": " complete", "probability": 0.6650390625 }, { "start": 460.94, "end": 461.08, "word": " in", "probability": 0.87451171875 }, { "start": 461.08, "end": 461.26, "word": " one", "probability": 0.75146484375 }, { "start": 461.26, "end": 461.54, "word": " month", "probability": 0.83154296875 }, { "start": 461.54, "end": 461.98, "word": ".", "probability": 0.927734375 } ] }, { "id": 172, "seek": 48788, "start": 462.62, "end": 465.5, "text": " That is a 1200% increase in productivity", "tokens": [ 50514, 663, 307, 257, 29139, 4, 3488, 294, 15604, 50614 ], "temperature": 0.0, "avg_logprob": -0.17432851239669422, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.00019109249114990234, "words": [ { "start": 462.62, "end": 462.86, "word": " That", "probability": 0.7431640625 }, { "start": 462.86, "end": 462.96, "word": " is", "probability": 0.87841796875 }, { "start": 463.14, "end": 463.8, "word": " a 1200", "probability": 0.501953125 }, { "start": 463.8, "end": 464.36, "word": "%", "probability": 0.91748046875 }, { "start": 464.36, "end": 464.92, "word": " increase", "probability": 0.7373046875 }, { "start": 464.92, "end": 465.1, "word": " in", "probability": 0.8935546875 }, { "start": 465.1, "end": 465.5, "word": " productivity", "probability": 0.91259765625 } ] }, { "id": 173, "seek": 48788, "start": 465.5, "end": 467.72, "text": " by just implementing a little bit of machine learning", "tokens": [ 50664, 538, 445, 18114, 257, 707, 857, 295, 3479, 2539, 50764 ], "temperature": 0.0, "avg_logprob": -0.17432851239669422, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.00019109249114990234, "words": [ { "start": 465.5, "end": 465.84, "word": " by", "probability": 0.80029296875 }, { "start": 465.84, "end": 466.06, "word": " just", "probability": 0.77685546875 }, { "start": 466.06, "end": 466.46, "word": " implementing", "probability": 0.69775390625 }, { "start": 466.64, "end": 466.78, "word": " a little", "probability": 0.798828125 }, { "start": 466.78, "end": 466.92, "word": " bit", "probability": 0.90283203125 }, { "start": 466.92, "end": 467.0, "word": " of", "probability": 0.8974609375 }, { "start": 467.0, "end": 467.3, "word": " machine", "probability": 0.63818359375 }, { "start": 467.3, "end": 467.72, "word": " learning", "probability": 0.8369140625 } ] }, { "id": 174, "seek": 48788, "start": 467.72, "end": 470.64, "text": " and that fuzzy logic into their process", "tokens": [ 50814, 293, 300, 34710, 9952, 666, 641, 1399, 50864 ], "temperature": 0.0, "avg_logprob": -0.17432851239669422, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.00019109249114990234, "words": [ { "start": 467.72, "end": 468.58, "word": " and", "probability": 0.78125 }, { "start": 468.58, "end": 469.12, "word": " that", "probability": 0.77099609375 }, { "start": 469.12, "end": 469.42, "word": " fuzzy", "probability": 0.89892578125 }, { "start": 469.42, "end": 469.8, "word": " logic", "probability": 0.767578125 }, { "start": 469.8, "end": 470.08, "word": " into", "probability": 0.73486328125 }, { "start": 470.08, "end": 470.22, "word": " their", "probability": 0.89306640625 }, { "start": 470.22, "end": 470.64, "word": " process", "probability": 0.8642578125 } ] }, { "id": 175, "seek": 48788, "start": 470.64, "end": 472.32, "text": " to kind of help automate it.", "tokens": [ 50914, 281, 733, 295, 854, 31605, 309, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.17432851239669422, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.00019109249114990234, "words": [ { "start": 470.64, "end": 470.86, "word": " to", "probability": 0.8388671875 }, { "start": 470.86, "end": 471.0, "word": " kind", "probability": 0.4638671875 }, { "start": 471.0, "end": 471.08, "word": " of", "probability": 0.9033203125 }, { "start": 471.08, "end": 471.26, "word": " help", "probability": 0.83154296875 }, { "start": 471.26, "end": 471.66, "word": " automate", "probability": 0.83154296875 }, { "start": 471.66, "end": 471.88, "word": " it", "probability": 0.89599609375 }, { "start": 471.88, "end": 472.32, "word": ".", "probability": 0.98486328125 } ] }, { "id": 176, "seek": 48788, "start": 472.86, "end": 474.16, "text": " So this is what I want to do", "tokens": [ 51014, 407, 341, 307, 437, 286, 528, 281, 360, 51064 ], "temperature": 0.0, "avg_logprob": -0.17432851239669422, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.00019109249114990234, "words": [ { "start": 472.86, "end": 473.3, "word": " So", "probability": 0.77294921875 }, { "start": 473.3, "end": 473.48, "word": " this", "probability": 0.79833984375 }, { "start": 473.48, "end": 473.6, "word": " is", "probability": 0.90380859375 }, { "start": 473.6, "end": 473.74, "word": " what", "probability": 0.88671875 }, { "start": 473.74, "end": 473.84, "word": " I", "probability": 0.99072265625 }, { "start": 473.84, "end": 473.96, "word": " want", "probability": 0.7158203125 }, { "start": 473.96, "end": 474.06, "word": " to", "probability": 0.90380859375 }, { "start": 474.06, "end": 474.16, "word": " do", "probability": 0.9052734375 } ] }, { "id": 177, "seek": 48788, "start": 474.16, "end": 476.52, "text": " to kind of push for the security analysts", "tokens": [ 51114, 281, 733, 295, 2944, 337, 264, 3825, 31388, 51164 ], "temperature": 0.0, "avg_logprob": -0.17432851239669422, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.00019109249114990234, "words": [ { "start": 474.16, "end": 474.3, "word": " to", "probability": 0.89306640625 }, { "start": 474.3, "end": 474.46, "word": " kind", "probability": 0.70703125 }, { "start": 474.46, "end": 474.58, "word": " of", "probability": 0.90380859375 }, { "start": 474.58, "end": 474.98, "word": " push", "probability": 0.81494140625 }, { "start": 474.98, "end": 475.44, "word": " for", "probability": 0.89208984375 }, { "start": 475.44, "end": 475.8, "word": " the", "probability": 0.79443359375 }, { "start": 475.8, "end": 476.1, "word": " security", "probability": 0.90869140625 }, { "start": 476.1, "end": 476.52, "word": " analysts", "probability": 0.5673828125 } ] }, { "id": 178, "seek": 48788, "start": 476.52, "end": 477.6, "text": " and for the hacker community", "tokens": [ 51214, 293, 337, 264, 38155, 1768, 51264 ], "temperature": 0.0, "avg_logprob": -0.17432851239669422, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.00019109249114990234, "words": [ { "start": 476.52, "end": 476.7, "word": " and", "probability": 0.84814453125 }, { "start": 476.7, "end": 476.8, "word": " for", "probability": 0.8466796875 }, { "start": 476.8, "end": 476.94, "word": " the", "probability": 0.80615234375 }, { "start": 476.94, "end": 477.14, "word": " hacker", "probability": 0.71728515625 }, { "start": 477.14, "end": 477.6, "word": " community", "probability": 0.79296875 } ] }, { "id": 179, "seek": 48788, "start": 478.1, "end": 479.5, "text": " to get a little bit more involved", "tokens": [ 51314, 281, 483, 257, 707, 857, 544, 3288, 51364 ], "temperature": 0.0, "avg_logprob": -0.17432851239669422, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.00019109249114990234, "words": [ { "start": 478.1, "end": 478.54, "word": " to", "probability": 0.83251953125 }, { "start": 478.54, "end": 478.66, "word": " get", "probability": 0.89599609375 }, { "start": 478.74, "end": 478.82, "word": " a little", "probability": 0.80712890625 }, { "start": 478.82, "end": 478.96, "word": " bit", "probability": 0.88671875 }, { "start": 478.96, "end": 479.12, "word": " more", "probability": 0.88134765625 }, { "start": 479.12, "end": 479.5, "word": " involved", "probability": 0.7900390625 } ] }, { "id": 180, "seek": 48788, "start": 479.5, "end": 480.74, "text": " in AI and machine learning", "tokens": [ 51414, 294, 7318, 293, 3479, 2539, 51464 ], "temperature": 0.0, "avg_logprob": -0.17432851239669422, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.00019109249114990234, "words": [ { "start": 479.5, "end": 479.66, "word": " in", "probability": 0.90478515625 }, { "start": 479.66, "end": 479.92, "word": " AI", "probability": 0.8837890625 }, { "start": 479.92, "end": 480.06, "word": " and", "probability": 0.841796875 }, { "start": 480.06, "end": 480.32, "word": " machine", "probability": 0.7041015625 }, { "start": 480.32, "end": 480.74, "word": " learning", "probability": 0.84521484375 } ] }, { "id": 181, "seek": 48788, "start": 480.74, "end": 483.94, "text": " so that we can see and identify ways", "tokens": [ 51514, 370, 300, 321, 393, 536, 293, 5876, 2098, 51564 ], "temperature": 0.0, "avg_logprob": -0.17432851239669422, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.00019109249114990234, "words": [ { "start": 480.74, "end": 481.28, "word": " so", "probability": 0.669921875 }, { "start": 481.28, "end": 481.44, "word": " that", "probability": 0.87646484375 }, { "start": 481.44, "end": 481.58, "word": " we", "probability": 0.904296875 }, { "start": 481.58, "end": 481.84, "word": " can", "probability": 0.8994140625 }, { "start": 481.84, "end": 482.74, "word": " see", "probability": 0.80712890625 }, { "start": 482.74, "end": 483.04, "word": " and", "probability": 0.89111328125 }, { "start": 483.04, "end": 483.46, "word": " identify", "probability": 0.88671875 }, { "start": 483.46, "end": 483.94, "word": " ways", "probability": 0.8115234375 } ] }, { "id": 182, "seek": 48788, "start": 483.94, "end": 485.86, "text": " that we can improve our own processes,", "tokens": [ 51614, 300, 321, 393, 3470, 527, 1065, 7555, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.17432851239669422, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.00019109249114990234, "words": [ { "start": 483.94, "end": 484.08, "word": " that", "probability": 0.8720703125 }, { "start": 484.08, "end": 484.18, "word": " we", "probability": 0.90673828125 }, { "start": 484.18, "end": 484.3, "word": " can", "probability": 0.8935546875 }, { "start": 484.3, "end": 484.64, "word": " improve", "probability": 0.73828125 }, { "start": 484.64, "end": 484.82, "word": " our", "probability": 0.81298828125 }, { "start": 484.82, "end": 485.04, "word": " own", "probability": 0.82373046875 }, { "start": 485.04, "end": 485.52, "word": " processes", "probability": 0.794921875 }, { "start": 485.52, "end": 485.86, "word": ",", "probability": 0.6552734375 } ] }, { "id": 183, "seek": 48788, "start": 486.66, "end": 487.88, "text": " especially ones that require", "tokens": [ 51714, 2318, 2306, 300, 3651, 51764 ], "temperature": 0.0, "avg_logprob": -0.17432851239669422, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.00019109249114990234, "words": [ { "start": 486.66, "end": 487.1, "word": " especially", "probability": 0.7119140625 }, { "start": 487.1, "end": 487.42, "word": " ones", "probability": 0.837890625 }, { "start": 487.42, "end": 487.56, "word": " that", "probability": 0.88232421875 }, { "start": 487.56, "end": 487.88, "word": " require", "probability": 0.82470703125 } ] }, { "id": 184, "seek": 51788, "start": 487.96, "end": 489.06, "text": " a little bit of fuzzy logic,", "tokens": [ 50364, 257, 707, 857, 295, 34710, 9952, 11, 50414 ], "temperature": 0.0, "avg_logprob": -0.19460227679122577, "compression_ratio": 1.6638297872340426, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 487.96, "end": 488.08, "word": " a little", "probability": 0.6279296875 }, { "start": 488.08, "end": 488.22, "word": " bit", "probability": 0.75732421875 }, { "start": 488.22, "end": 488.32, "word": " of", "probability": 0.88232421875 }, { "start": 488.32, "end": 488.54, "word": " fuzzy", "probability": 0.93310546875 }, { "start": 488.54, "end": 488.92, "word": " logic", "probability": 0.75341796875 }, { "start": 488.92, "end": 489.06, "word": ",", "probability": 0.4716796875 } ] }, { "id": 185, "seek": 51788, "start": 489.06, "end": 490.48, "text": " things that traditional signatures", "tokens": [ 50464, 721, 300, 5164, 32322, 50514 ], "temperature": 0.0, "avg_logprob": -0.19460227679122577, "compression_ratio": 1.6638297872340426, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 489.06, "end": 489.2, "word": " things", "probability": 0.7373046875 }, { "start": 489.2, "end": 489.54, "word": " that", "probability": 0.8701171875 }, { "start": 489.54, "end": 490.0, "word": " traditional", "probability": 0.74267578125 }, { "start": 490.0, "end": 490.48, "word": " signatures", "probability": 0.81494140625 } ] }, { "id": 186, "seek": 51788, "start": 490.48, "end": 494.16, "text": " or scripting aren't sufficient in.", "tokens": [ 50564, 420, 5755, 278, 3212, 380, 11563, 294, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.19460227679122577, "compression_ratio": 1.6638297872340426, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 490.48, "end": 490.94, "word": " or", "probability": 0.88916015625 }, { "start": 490.94, "end": 491.72, "word": " scripting", "probability": 0.784912109375 }, { "start": 491.72, "end": 492.96, "word": " aren't", "probability": 0.866455078125 }, { "start": 492.96, "end": 493.38, "word": " sufficient", "probability": 0.7890625 }, { "start": 493.38, "end": 493.64, "word": " in", "probability": 0.84912109375 }, { "start": 493.64, "end": 494.16, "word": ".", "probability": 0.96875 } ] }, { "id": 187, "seek": 51788, "start": 496.38, "end": 498.6, "text": " So the 7-step machine learning process", "tokens": [ 50714, 407, 264, 1614, 12, 16792, 3479, 2539, 1399, 50864 ], "temperature": 0.0, "avg_logprob": -0.19460227679122577, "compression_ratio": 1.6638297872340426, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 496.38, "end": 496.9, "word": " So", "probability": 0.55908203125 }, { "start": 496.9, "end": 497.26, "word": " the", "probability": 0.59423828125 }, { "start": 497.26, "end": 497.46, "word": " 7", "probability": 0.400634765625 }, { "start": 497.46, "end": 497.64, "word": "-step", "probability": 0.771728515625 }, { "start": 497.64, "end": 497.92, "word": " machine", "probability": 0.6591796875 }, { "start": 497.92, "end": 498.18, "word": " learning", "probability": 0.82568359375 }, { "start": 498.18, "end": 498.6, "word": " process", "probability": 0.845703125 } ] }, { "id": 188, "seek": 51788, "start": 498.6, "end": 500.5, "text": " generally looks like this.", "tokens": [ 50914, 5101, 1542, 411, 341, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.19460227679122577, "compression_ratio": 1.6638297872340426, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 498.6, "end": 499.1, "word": " generally", "probability": 0.837890625 }, { "start": 499.1, "end": 499.42, "word": " looks", "probability": 0.79541015625 }, { "start": 499.42, "end": 499.6, "word": " like", "probability": 0.88525390625 }, { "start": 499.6, "end": 499.98, "word": " this", "probability": 0.8837890625 }, { "start": 499.98, "end": 500.5, "word": ".", "probability": 0.693359375 } ] }, { "id": 189, "seek": 51788, "start": 500.66, "end": 502.72, "text": " And this isn't a list", "tokens": [ 51014, 400, 341, 1943, 380, 257, 1329, 51064 ], "temperature": 0.0, "avg_logprob": -0.19460227679122577, "compression_ratio": 1.6638297872340426, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 500.66, "end": 500.88, "word": " And", "probability": 0.58837890625 }, { "start": 500.88, "end": 501.1, "word": " this", "probability": 0.87841796875 }, { "start": 501.1, "end": 501.7, "word": " isn't", "probability": 0.9287109375 }, { "start": 502.42, "end": 502.72, "word": " a list", "probability": 0.89990234375 } ] }, { "id": 190, "seek": 51788, "start": 502.72, "end": 505.56, "text": " so much as a cycle, right?", "tokens": [ 51114, 370, 709, 382, 257, 6586, 11, 558, 30, 51214 ], "temperature": 0.0, "avg_logprob": -0.19460227679122577, "compression_ratio": 1.6638297872340426, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 502.72, "end": 503.08, "word": " so", "probability": 0.7705078125 }, { "start": 503.08, "end": 503.3, "word": " much", "probability": 0.80615234375 }, { "start": 503.3, "end": 503.5, "word": " as", "probability": 0.89990234375 }, { "start": 503.96, "end": 504.42, "word": " a cycle", "probability": 0.89697265625 }, { "start": 504.42, "end": 504.74, "word": ",", "probability": 0.448974609375 }, { "start": 504.74, "end": 505.04, "word": " right", "probability": 0.85107421875 }, { "start": 505.04, "end": 505.56, "word": "?", "probability": 0.806640625 } ] }, { "id": 191, "seek": 51788, "start": 506.56, "end": 508.08, "text": " So first we're going to start", "tokens": [ 51264, 407, 700, 321, 434, 516, 281, 722, 51314 ], "temperature": 0.0, "avg_logprob": -0.19460227679122577, "compression_ratio": 1.6638297872340426, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 506.56, "end": 507.08, "word": " So", "probability": 0.85302734375 }, { "start": 507.08, "end": 507.6, "word": " first", "probability": 0.71240234375 }, { "start": 507.6, "end": 507.82, "word": " we're", "probability": 0.757568359375 }, { "start": 507.82, "end": 507.9, "word": " going", "probability": 0.6884765625 }, { "start": 507.9, "end": 507.94, "word": " to", "probability": 0.9052734375 }, { "start": 507.94, "end": 508.08, "word": " start", "probability": 0.876953125 } ] }, { "id": 192, "seek": 51788, "start": 508.08, "end": 508.98, "text": " with gathering the data.", "tokens": [ 51364, 365, 13519, 264, 1412, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.19460227679122577, "compression_ratio": 1.6638297872340426, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 508.08, "end": 508.22, "word": " with", "probability": 0.81787109375 }, { "start": 508.22, "end": 508.52, "word": " gathering", "probability": 0.755859375 }, { "start": 508.52, "end": 508.72, "word": " the", "probability": 0.80712890625 }, { "start": 508.72, "end": 508.88, "word": " data", "probability": 0.81884765625 }, { "start": 508.88, "end": 508.98, "word": ".", "probability": 0.82861328125 } ] }, { "id": 193, "seek": 51788, "start": 508.98, "end": 512.24, "text": " We want to identify what it is", "tokens": [ 51464, 492, 528, 281, 5876, 437, 309, 307, 51514 ], "temperature": 0.0, "avg_logprob": -0.19460227679122577, "compression_ratio": 1.6638297872340426, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 508.98, "end": 509.04, "word": " We", "probability": 0.8955078125 }, { "start": 509.04, "end": 509.18, "word": " want", "probability": 0.81201171875 }, { "start": 509.18, "end": 509.26, "word": " to", "probability": 0.90185546875 }, { "start": 509.26, "end": 509.9, "word": " identify", "probability": 0.90283203125 }, { "start": 509.9, "end": 510.92, "word": " what", "probability": 0.87939453125 }, { "start": 510.92, "end": 511.04, "word": " it", "probability": 0.88232421875 }, { "start": 511.04, "end": 512.24, "word": " is", "probability": 0.552734375 } ] }, { "id": 194, "seek": 51788, "start": 512.24, "end": 513.84, "text": " we want our machine learning algorithm", "tokens": [ 51564, 321, 528, 527, 3479, 2539, 9284, 51614 ], "temperature": 0.0, "avg_logprob": -0.19460227679122577, "compression_ratio": 1.6638297872340426, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 512.24, "end": 512.4, "word": " we", "probability": 0.87841796875 }, { "start": 512.4, "end": 512.62, "word": " want", "probability": 0.80615234375 }, { "start": 512.62, "end": 512.82, "word": " our", "probability": 0.8173828125 }, { "start": 512.82, "end": 513.1, "word": " machine", "probability": 0.72119140625 }, { "start": 513.1, "end": 513.36, "word": " learning", "probability": 0.80859375 }, { "start": 513.36, "end": 513.84, "word": " algorithm", "probability": 0.8076171875 } ] }, { "id": 195, "seek": 51788, "start": 513.84, "end": 515.66, "text": " to classify.", "tokens": [ 51664, 281, 33872, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.19460227679122577, "compression_ratio": 1.6638297872340426, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 513.84, "end": 514.66, "word": " to", "probability": 0.9033203125 }, { "start": 514.66, "end": 515.14, "word": " classify", "probability": 0.9482421875 }, { "start": 515.14, "end": 515.66, "word": ".", "probability": 0.98291015625 } ] }, { "id": 196, "seek": 51788, "start": 515.96, "end": 517.52, "text": " So first we're going to gather the data", "tokens": [ 51764, 407, 700, 321, 434, 516, 281, 5448, 264, 1412, 51814 ], "temperature": 0.0, "avg_logprob": -0.19460227679122577, "compression_ratio": 1.6638297872340426, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 515.96, "end": 516.4, "word": " So", "probability": 0.8740234375 }, { "start": 516.4, "end": 516.62, "word": " first", "probability": 0.81201171875 }, { "start": 516.62, "end": 516.76, "word": " we're", "probability": 0.89111328125 }, { "start": 516.76, "end": 516.84, "word": " going", "probability": 0.83056640625 }, { "start": 516.84, "end": 516.92, "word": " to", "probability": 0.90576171875 }, { "start": 516.92, "end": 517.1, "word": " gather", "probability": 0.7802734375 }, { "start": 517.1, "end": 517.28, "word": " the", "probability": 0.81884765625 }, { "start": 517.28, "end": 517.52, "word": " data", "probability": 0.828125 } ] }, { "id": 197, "seek": 54788, "start": 517.88, "end": 518.72, "text": " and then we're going to prepare the data", "tokens": [ 50364, 293, 550, 321, 434, 516, 281, 5940, 264, 1412, 50414 ], "temperature": 0.0, "avg_logprob": -0.19831731477817455, "compression_ratio": 1.7567567567567568, "no_speech_prob": 6.502866744995117e-05, "words": [ { "start": 517.88, "end": 517.88, "word": " and", "probability": 0.035888671875 }, { "start": 517.88, "end": 517.88, "word": " then", "probability": 0.0404052734375 }, { "start": 517.88, "end": 517.88, "word": " we're", "probability": 0.5133056640625 }, { "start": 517.88, "end": 517.96, "word": " going", "probability": 0.5712890625 }, { "start": 517.96, "end": 518.02, "word": " to", "probability": 0.90380859375 }, { "start": 518.02, "end": 518.28, "word": " prepare", "probability": 0.7548828125 }, { "start": 518.28, "end": 518.48, "word": " the", "probability": 0.78857421875 }, { "start": 518.48, "end": 518.72, "word": " data", "probability": 0.826171875 } ] }, { "id": 198, "seek": 54788, "start": 518.72, "end": 520.66, "text": " in such a way that is easy", "tokens": [ 50464, 294, 1270, 257, 636, 300, 307, 1858, 50514 ], "temperature": 0.0, "avg_logprob": -0.19831731477817455, "compression_ratio": 1.7567567567567568, "no_speech_prob": 6.502866744995117e-05, "words": [ { "start": 518.72, "end": 518.98, "word": " in", "probability": 0.88671875 }, { "start": 518.98, "end": 519.2, "word": " such", "probability": 0.8251953125 }, { "start": 519.34, "end": 519.62, "word": " a way", "probability": 0.89306640625 }, { "start": 519.62, "end": 520.12, "word": " that", "probability": 0.85888671875 }, { "start": 520.12, "end": 520.38, "word": " is", "probability": 0.5625 }, { "start": 520.38, "end": 520.66, "word": " easy", "probability": 0.80078125 } ] }, { "id": 199, "seek": 54788, "start": 520.66, "end": 523.1, "text": " for machine learning models to understand.", "tokens": [ 50564, 337, 3479, 2539, 5245, 281, 1223, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.19831731477817455, "compression_ratio": 1.7567567567567568, "no_speech_prob": 6.502866744995117e-05, "words": [ { "start": 520.66, "end": 520.88, "word": " for", "probability": 0.89013671875 }, { "start": 520.88, "end": 521.16, "word": " machine", "probability": 0.65771484375 }, { "start": 521.16, "end": 521.42, "word": " learning", "probability": 0.7802734375 }, { "start": 521.42, "end": 521.84, "word": " models", "probability": 0.79345703125 }, { "start": 521.84, "end": 522.06, "word": " to", "probability": 0.904296875 }, { "start": 522.06, "end": 522.66, "word": " understand", "probability": 0.7451171875 }, { "start": 522.66, "end": 523.1, "word": ".", "probability": 0.74853515625 } ] }, { "id": 200, "seek": 54788, "start": 523.3, "end": 524.64, "text": " And in this case, it's usually turning it", "tokens": [ 50664, 400, 294, 341, 1389, 11, 309, 311, 2673, 6246, 309, 50714 ], "temperature": 0.0, "avg_logprob": -0.19831731477817455, "compression_ratio": 1.7567567567567568, "no_speech_prob": 6.502866744995117e-05, "words": [ { "start": 523.3, "end": 523.32, "word": " And", "probability": 0.32470703125 }, { "start": 523.32, "end": 523.42, "word": " in", "probability": 0.8828125 }, { "start": 523.42, "end": 523.56, "word": " this", "probability": 0.8779296875 }, { "start": 523.56, "end": 523.76, "word": " case", "probability": 0.8037109375 }, { "start": 523.76, "end": 523.82, "word": ",", "probability": 0.705078125 }, { "start": 523.82, "end": 523.96, "word": " it's", "probability": 0.94140625 }, { "start": 523.96, "end": 524.2, "word": " usually", "probability": 0.77294921875 }, { "start": 524.2, "end": 524.48, "word": " turning", "probability": 0.7880859375 }, { "start": 524.48, "end": 524.64, "word": " it", "probability": 0.8671875 } ] }, { "id": 201, "seek": 54788, "start": 524.64, "end": 525.74, "text": " into some form of number", "tokens": [ 50764, 666, 512, 1254, 295, 1230, 50814 ], "temperature": 0.0, "avg_logprob": -0.19831731477817455, "compression_ratio": 1.7567567567567568, "no_speech_prob": 6.502866744995117e-05, "words": [ { "start": 524.64, "end": 524.8, "word": " into", "probability": 0.73681640625 }, { "start": 524.8, "end": 525.0, "word": " some", "probability": 0.8134765625 }, { "start": 525.0, "end": 525.26, "word": " form", "probability": 0.81494140625 }, { "start": 525.26, "end": 525.38, "word": " of", "probability": 0.90673828125 }, { "start": 525.38, "end": 525.74, "word": " number", "probability": 0.85009765625 } ] }, { "id": 202, "seek": 54788, "start": 525.74, "end": 527.44, "text": " or some form of signal.", "tokens": [ 50864, 420, 512, 1254, 295, 6358, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.19831731477817455, "compression_ratio": 1.7567567567567568, "no_speech_prob": 6.502866744995117e-05, "words": [ { "start": 525.74, "end": 526.04, "word": " or", "probability": 0.81005859375 }, { "start": 526.04, "end": 526.22, "word": " some", "probability": 0.7783203125 }, { "start": 526.22, "end": 526.46, "word": " form", "probability": 0.806640625 }, { "start": 526.46, "end": 526.62, "word": " of", "probability": 0.9052734375 }, { "start": 526.62, "end": 527.0, "word": " signal", "probability": 0.76904296875 }, { "start": 527.0, "end": 527.44, "word": ".", "probability": 0.9892578125 } ] }, { "id": 203, "seek": 54788, "start": 528.78, "end": 530.84, "text": " Most of our time is spent gathering the data", "tokens": [ 50964, 4534, 295, 527, 565, 307, 4418, 13519, 264, 1412, 51014 ], "temperature": 0.0, "avg_logprob": -0.19831731477817455, "compression_ratio": 1.7567567567567568, "no_speech_prob": 6.502866744995117e-05, "words": [ { "start": 528.78, "end": 529.22, "word": " Most", "probability": 0.83056640625 }, { "start": 529.22, "end": 529.34, "word": " of", "probability": 0.90380859375 }, { "start": 529.34, "end": 529.44, "word": " our", "probability": 0.81494140625 }, { "start": 529.44, "end": 529.7, "word": " time", "probability": 0.8046875 }, { "start": 529.7, "end": 529.84, "word": " is", "probability": 0.890625 }, { "start": 529.84, "end": 530.08, "word": " spent", "probability": 0.80029296875 }, { "start": 530.08, "end": 530.44, "word": " gathering", "probability": 0.78369140625 }, { "start": 530.44, "end": 530.66, "word": " the", "probability": 0.80322265625 }, { "start": 530.66, "end": 530.84, "word": " data", "probability": 0.82177734375 } ] }, { "id": 204, "seek": 54788, "start": 530.84, "end": 531.86, "text": " and preparing the data.", "tokens": [ 51064, 293, 10075, 264, 1412, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.19831731477817455, "compression_ratio": 1.7567567567567568, "no_speech_prob": 6.502866744995117e-05, "words": [ { "start": 530.84, "end": 530.96, "word": " and", "probability": 0.87158203125 }, { "start": 530.96, "end": 531.26, "word": " preparing", "probability": 0.81689453125 }, { "start": 531.26, "end": 531.48, "word": " the", "probability": 0.80859375 }, { "start": 531.48, "end": 531.68, "word": " data", "probability": 0.81787109375 }, { "start": 531.68, "end": 531.86, "word": ".", "probability": 0.85693359375 } ] }, { "id": 205, "seek": 54788, "start": 531.86, "end": 534.28, "text": " The rest of this tends to be a little bit quicker.", "tokens": [ 51164, 440, 1472, 295, 341, 12258, 281, 312, 257, 707, 857, 16255, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.19831731477817455, "compression_ratio": 1.7567567567567568, "no_speech_prob": 6.502866744995117e-05, "words": [ { "start": 531.86, "end": 531.96, "word": " The", "probability": 0.81103515625 }, { "start": 531.96, "end": 532.2, "word": " rest", "probability": 0.80224609375 }, { "start": 532.2, "end": 532.32, "word": " of", "probability": 0.90283203125 }, { "start": 532.32, "end": 532.5, "word": " this", "probability": 0.8681640625 }, { "start": 532.5, "end": 532.82, "word": " tends", "probability": 0.72314453125 }, { "start": 532.82, "end": 532.96, "word": " to", "probability": 0.904296875 }, { "start": 532.96, "end": 533.08, "word": " be", "probability": 0.90673828125 }, { "start": 533.22, "end": 533.34, "word": " a little", "probability": 0.81103515625 }, { "start": 533.34, "end": 533.54, "word": " bit", "probability": 0.88232421875 }, { "start": 533.54, "end": 533.84, "word": " quicker", "probability": 0.81103515625 }, { "start": 533.84, "end": 534.28, "word": ".", "probability": 0.95703125 } ] }, { "id": 206, "seek": 54788, "start": 535.16, "end": 536.86, "text": " So first, based on the data that we have", "tokens": [ 51264, 407, 700, 11, 2361, 322, 264, 1412, 300, 321, 362, 51314 ], "temperature": 0.0, "avg_logprob": -0.19831731477817455, "compression_ratio": 1.7567567567567568, "no_speech_prob": 6.502866744995117e-05, "words": [ { "start": 535.16, "end": 535.26, "word": " So", "probability": 0.58642578125 }, { "start": 535.26, "end": 535.52, "word": " first", "probability": 0.74755859375 }, { "start": 535.52, "end": 535.7, "word": ",", "probability": 0.859375 }, { "start": 535.7, "end": 535.9, "word": " based", "probability": 0.80078125 }, { "start": 535.9, "end": 536.04, "word": " on", "probability": 0.90673828125 }, { "start": 536.04, "end": 536.16, "word": " the", "probability": 0.8125 }, { "start": 536.16, "end": 536.32, "word": " data", "probability": 0.82958984375 }, { "start": 536.32, "end": 536.48, "word": " that", "probability": 0.8544921875 }, { "start": 536.48, "end": 536.58, "word": " we", "probability": 0.90966796875 }, { "start": 536.58, "end": 536.86, "word": " have", "probability": 0.87939453125 } ] }, { "id": 207, "seek": 54788, "start": 536.86, "end": 538.84, "text": " and the problem set that were presented,", "tokens": [ 51364, 293, 264, 1154, 992, 300, 645, 8212, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.19831731477817455, "compression_ratio": 1.7567567567567568, "no_speech_prob": 6.502866744995117e-05, "words": [ { "start": 536.86, "end": 536.94, "word": " and", "probability": 0.7119140625 }, { "start": 536.94, "end": 537.06, "word": " the", "probability": 0.81396484375 }, { "start": 537.06, "end": 537.32, "word": " problem", "probability": 0.73388671875 }, { "start": 537.32, "end": 537.56, "word": " set", "probability": 0.857421875 }, { "start": 537.56, "end": 537.7, "word": " that", "probability": 0.8759765625 }, { "start": 537.7, "end": 537.82, "word": " were", "probability": 0.373046875 }, { "start": 537.82, "end": 538.16, "word": " presented", "probability": 0.71923828125 }, { "start": 538.16, "end": 538.84, "word": ",", "probability": 0.89453125 } ] }, { "id": 208, "seek": 54788, "start": 538.84, "end": 540.26, "text": " we choose a model.", "tokens": [ 51464, 321, 2826, 257, 2316, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.19831731477817455, "compression_ratio": 1.7567567567567568, "no_speech_prob": 6.502866744995117e-05, "words": [ { "start": 538.84, "end": 539.3, "word": " we", "probability": 0.888671875 }, { "start": 539.3, "end": 539.52, "word": " choose", "probability": 0.806640625 }, { "start": 539.68, "end": 539.9, "word": " a model", "probability": 0.81201171875 }, { "start": 539.9, "end": 540.26, "word": ".", "probability": 0.94580078125 } ] }, { "id": 209, "seek": 54788, "start": 540.26, "end": 542.24, "text": " So some models perform better than others", "tokens": [ 51564, 407, 512, 5245, 2042, 1101, 813, 2357, 51614 ], "temperature": 0.0, "avg_logprob": -0.19831731477817455, "compression_ratio": 1.7567567567567568, "no_speech_prob": 6.502866744995117e-05, "words": [ { "start": 540.26, "end": 540.46, "word": " So", "probability": 0.62353515625 }, { "start": 540.46, "end": 540.94, "word": " some", "probability": 0.61279296875 }, { "start": 540.94, "end": 541.22, "word": " models", "probability": 0.794921875 }, { "start": 541.22, "end": 541.52, "word": " perform", "probability": 0.701171875 }, { "start": 541.52, "end": 541.74, "word": " better", "probability": 0.82861328125 }, { "start": 541.74, "end": 541.9, "word": " than", "probability": 0.8818359375 }, { "start": 541.9, "end": 542.24, "word": " others", "probability": 0.76806640625 } ] }, { "id": 210, "seek": 54788, "start": 542.24, "end": 543.42, "text": " in certain tasks.", "tokens": [ 51664, 294, 1629, 9608, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.19831731477817455, "compression_ratio": 1.7567567567567568, "no_speech_prob": 6.502866744995117e-05, "words": [ { "start": 542.24, "end": 542.44, "word": " in", "probability": 0.6650390625 }, { "start": 542.44, "end": 542.68, "word": " certain", "probability": 0.8037109375 }, { "start": 542.68, "end": 543.2, "word": " tasks", "probability": 0.869140625 }, { "start": 543.2, "end": 543.42, "word": ".", "probability": 0.33740234375 } ] }, { "id": 211, "seek": 54788, "start": 543.42, "end": 544.72, "text": " And sometimes you just got to kind of", "tokens": [ 51764, 400, 2171, 291, 445, 658, 281, 733, 295, 51814 ], "temperature": 0.0, "avg_logprob": -0.19831731477817455, "compression_ratio": 1.7567567567567568, "no_speech_prob": 6.502866744995117e-05, "words": [ { "start": 543.42, "end": 543.5, "word": " And", "probability": 0.76806640625 }, { "start": 543.5, "end": 543.82, "word": " sometimes", "probability": 0.88623046875 }, { "start": 543.82, "end": 544.04, "word": " you", "probability": 0.830078125 }, { "start": 544.04, "end": 544.18, "word": " just", "probability": 0.80126953125 }, { "start": 544.18, "end": 544.34, "word": " got", "probability": 0.6767578125 }, { "start": 544.34, "end": 544.46, "word": " to", "probability": 0.888671875 }, { "start": 544.46, "end": 544.66, "word": " kind", "probability": 0.6923828125 }, { "start": 544.66, "end": 544.72, "word": " of", "probability": 0.91015625 } ] }, { "id": 212, "seek": 57788, "start": 547.88, "end": 548.78, "text": " figure out maybe neural nets isn't", "tokens": [ 50364, 2573, 484, 1310, 18161, 36170, 1943, 380, 50414 ], "temperature": 0.0, "avg_logprob": -0.20872043586663297, "compression_ratio": 1.7473309608540926, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 547.88, "end": 548.02, "word": " figure", "probability": 1.2099742889404297e-05 }, { "start": 548.02, "end": 548.02, "word": " out", "probability": 0.673828125 }, { "start": 548.02, "end": 548.02, "word": " maybe", "probability": 0.1466064453125 }, { "start": 548.02, "end": 548.22, "word": " neural", "probability": 0.6220703125 }, { "start": 548.22, "end": 548.46, "word": " nets", "probability": 0.79150390625 }, { "start": 548.46, "end": 548.78, "word": " isn't", "probability": 0.903076171875 } ] }, { "id": 213, "seek": 57788, "start": 548.78, "end": 550.12, "text": " the best model for you.", "tokens": [ 50464, 264, 1151, 2316, 337, 291, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.20872043586663297, "compression_ratio": 1.7473309608540926, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 548.78, "end": 548.92, "word": " the", "probability": 0.80908203125 }, { "start": 548.92, "end": 549.16, "word": " best", "probability": 0.79638671875 }, { "start": 549.16, "end": 549.42, "word": " model", "probability": 0.8095703125 }, { "start": 549.42, "end": 549.68, "word": " for", "probability": 0.8857421875 }, { "start": 549.68, "end": 549.9, "word": " you", "probability": 0.88623046875 }, { "start": 549.9, "end": 550.12, "word": ".", "probability": 0.3916015625 } ] }, { "id": 214, "seek": 57788, "start": 550.12, "end": 552.62, "text": " Maybe logistic regression or SVM", "tokens": [ 50564, 2704, 3565, 3142, 24590, 420, 31910, 44, 50614 ], "temperature": 0.0, "avg_logprob": -0.20872043586663297, "compression_ratio": 1.7473309608540926, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 550.12, "end": 550.34, "word": " Maybe", "probability": 0.8798828125 }, { "start": 550.34, "end": 551.12, "word": " logistic", "probability": 0.911865234375 }, { "start": 551.12, "end": 551.56, "word": " regression", "probability": 0.88037109375 }, { "start": 551.56, "end": 551.94, "word": " or", "probability": 0.66015625 }, { "start": 551.94, "end": 552.62, "word": " SVM", "probability": 0.94677734375 } ] }, { "id": 215, "seek": 57788, "start": 552.62, "end": 555.22, "text": " or random forest classifier is better for you.", "tokens": [ 50664, 420, 4974, 6719, 1508, 9902, 307, 1101, 337, 291, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.20872043586663297, "compression_ratio": 1.7473309608540926, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 552.62, "end": 552.76, "word": " or", "probability": 0.8212890625 }, { "start": 552.76, "end": 553.04, "word": " random", "probability": 0.5791015625 }, { "start": 553.04, "end": 553.42, "word": " forest", "probability": 0.609375 }, { "start": 553.42, "end": 554.06, "word": " classifier", "probability": 0.90185546875 }, { "start": 554.06, "end": 554.18, "word": " is", "probability": 0.8779296875 }, { "start": 554.18, "end": 554.36, "word": " better", "probability": 0.81982421875 }, { "start": 554.36, "end": 554.58, "word": " for", "probability": 0.89892578125 }, { "start": 554.58, "end": 554.78, "word": " you", "probability": 0.8935546875 }, { "start": 554.78, "end": 555.22, "word": ".", "probability": 0.939453125 } ] }, { "id": 216, "seek": 57788, "start": 555.68, "end": 557.14, "text": " But once we've identified the model", "tokens": [ 50764, 583, 1564, 321, 600, 9234, 264, 2316, 50814 ], "temperature": 0.0, "avg_logprob": -0.20872043586663297, "compression_ratio": 1.7473309608540926, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 555.68, "end": 555.92, "word": " But", "probability": 0.71826171875 }, { "start": 555.92, "end": 556.08, "word": " once", "probability": 0.79736328125 }, { "start": 556.08, "end": 556.24, "word": " we've", "probability": 0.903564453125 }, { "start": 556.24, "end": 556.6, "word": " identified", "probability": 0.88818359375 }, { "start": 556.6, "end": 556.82, "word": " the", "probability": 0.8115234375 }, { "start": 556.82, "end": 557.14, "word": " model", "probability": 0.78662109375 } ] }, { "id": 217, "seek": 57788, "start": 557.14, "end": 559.56, "text": " or models, then we go ahead and train it.", "tokens": [ 50864, 420, 5245, 11, 550, 321, 352, 2286, 293, 3847, 309, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.20872043586663297, "compression_ratio": 1.7473309608540926, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 557.14, "end": 557.4, "word": " or", "probability": 0.84814453125 }, { "start": 557.4, "end": 557.86, "word": " models", "probability": 0.8115234375 }, { "start": 557.86, "end": 558.1, "word": ",", "probability": 0.79345703125 }, { "start": 558.1, "end": 558.5, "word": " then", "probability": 0.7216796875 }, { "start": 558.5, "end": 558.6, "word": " we", "probability": 0.9052734375 }, { "start": 558.6, "end": 558.72, "word": " go", "probability": 0.8974609375 }, { "start": 558.72, "end": 558.88, "word": " ahead", "probability": 0.85595703125 }, { "start": 558.88, "end": 559.02, "word": " and", "probability": 0.89404296875 }, { "start": 559.02, "end": 559.3, "word": " train", "probability": 0.81591796875 }, { "start": 559.3, "end": 559.42, "word": " it", "probability": 0.8515625 }, { "start": 559.42, "end": 559.56, "word": ".", "probability": 0.86474609375 } ] }, { "id": 218, "seek": 57788, "start": 559.56, "end": 561.54, "text": " And so what we'll usually do is perform", "tokens": [ 50964, 400, 370, 437, 321, 603, 2673, 360, 307, 2042, 51014 ], "temperature": 0.0, "avg_logprob": -0.20872043586663297, "compression_ratio": 1.7473309608540926, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 559.56, "end": 559.56, "word": " And", "probability": 0.475341796875 }, { "start": 559.56, "end": 559.78, "word": " so", "probability": 0.89013671875 }, { "start": 559.78, "end": 560.5, "word": " what", "probability": 0.7236328125 }, { "start": 560.5, "end": 560.64, "word": " we'll", "probability": 0.8818359375 }, { "start": 560.64, "end": 560.88, "word": " usually", "probability": 0.80810546875 }, { "start": 560.88, "end": 561.12, "word": " do", "probability": 0.90576171875 }, { "start": 561.12, "end": 561.24, "word": " is", "probability": 0.8994140625 }, { "start": 561.24, "end": 561.54, "word": " perform", "probability": 0.76513671875 } ] }, { "id": 219, "seek": 57788, "start": 561.54, "end": 563.6, "text": " what's called a training testing split.", "tokens": [ 51064, 437, 311, 1219, 257, 3097, 4997, 7472, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.20872043586663297, "compression_ratio": 1.7473309608540926, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 561.54, "end": 561.74, "word": " what's", "probability": 0.927490234375 }, { "start": 561.74, "end": 561.84, "word": " called", "probability": 0.8134765625 }, { "start": 561.96, "end": 562.24, "word": " a training", "probability": 0.77197265625 }, { "start": 562.24, "end": 562.72, "word": " testing", "probability": 0.4794921875 }, { "start": 562.72, "end": 563.16, "word": " split", "probability": 0.8671875 }, { "start": 563.16, "end": 563.6, "word": ".", "probability": 0.951171875 } ] }, { "id": 220, "seek": 57788, "start": 563.6, "end": 565.76, "text": " And in this case, we have a series", "tokens": [ 51164, 400, 294, 341, 1389, 11, 321, 362, 257, 2638, 51214 ], "temperature": 0.0, "avg_logprob": -0.20872043586663297, "compression_ratio": 1.7473309608540926, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 563.6, "end": 563.72, "word": " And", "probability": 0.8896484375 }, { "start": 563.72, "end": 563.82, "word": " in", "probability": 0.90283203125 }, { "start": 563.82, "end": 563.98, "word": " this", "probability": 0.87841796875 }, { "start": 563.98, "end": 564.2, "word": " case", "probability": 0.81201171875 }, { "start": 564.2, "end": 564.22, "word": ",", "probability": 0.72802734375 }, { "start": 564.22, "end": 564.36, "word": " we", "probability": 0.9013671875 }, { "start": 564.36, "end": 564.72, "word": " have", "probability": 0.87939453125 }, { "start": 565.18, "end": 565.76, "word": " a series", "probability": 0.822265625 } ] }, { "id": 221, "seek": 57788, "start": 565.76, "end": 569.32, "text": " or a lot of clean labeled data.", "tokens": [ 51264, 420, 257, 688, 295, 2541, 21335, 1412, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.20872043586663297, "compression_ratio": 1.7473309608540926, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 565.76, "end": 566.16, "word": " or", "probability": 0.8388671875 }, { "start": 566.38, "end": 566.7, "word": " a lot", "probability": 0.88427734375 }, { "start": 566.7, "end": 567.22, "word": " of", "probability": 0.90576171875 }, { "start": 567.22, "end": 568.12, "word": " clean", "probability": 0.80615234375 }, { "start": 568.12, "end": 568.52, "word": " labeled", "probability": 0.4619140625 }, { "start": 568.52, "end": 569.0, "word": " data", "probability": 0.81494140625 }, { "start": 569.0, "end": 569.32, "word": ".", "probability": 0.734375 } ] }, { "id": 222, "seek": 57788, "start": 569.48, "end": 570.9, "text": " And we take that data,", "tokens": [ 51464, 400, 321, 747, 300, 1412, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.20872043586663297, "compression_ratio": 1.7473309608540926, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 569.48, "end": 569.92, "word": " And", "probability": 0.869140625 }, { "start": 569.92, "end": 570.02, "word": " we", "probability": 0.88330078125 }, { "start": 570.02, "end": 570.2, "word": " take", "probability": 0.80908203125 }, { "start": 570.2, "end": 570.38, "word": " that", "probability": 0.88232421875 }, { "start": 570.38, "end": 570.66, "word": " data", "probability": 0.8193359375 }, { "start": 570.66, "end": 570.9, "word": ",", "probability": 0.7822265625 } ] }, { "id": 223, "seek": 57788, "start": 570.9, "end": 573.44, "text": " we separate 80% of it and 20% of it.", "tokens": [ 51564, 321, 4994, 4688, 4, 295, 309, 293, 945, 4, 295, 309, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.20872043586663297, "compression_ratio": 1.7473309608540926, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 570.9, "end": 571.04, "word": " we", "probability": 0.89794921875 }, { "start": 571.04, "end": 571.46, "word": " separate", "probability": 0.8623046875 }, { "start": 571.46, "end": 572.06, "word": " 80", "probability": 0.90771484375 }, { "start": 572.06, "end": 572.32, "word": "%", "probability": 0.9443359375 }, { "start": 572.32, "end": 572.5, "word": " of", "probability": 0.90380859375 }, { "start": 572.5, "end": 572.6, "word": " it", "probability": 0.90673828125 }, { "start": 572.6, "end": 572.72, "word": " and", "probability": 0.837890625 }, { "start": 572.72, "end": 572.96, "word": " 20", "probability": 0.90576171875 }, { "start": 572.96, "end": 573.2, "word": "%", "probability": 0.81396484375 }, { "start": 573.2, "end": 573.32, "word": " of", "probability": 0.8916015625 }, { "start": 573.32, "end": 573.42, "word": " it", "probability": 0.830078125 }, { "start": 573.42, "end": 573.44, "word": ".", "probability": 0.837890625 } ] }, { "id": 224, "seek": 57788, "start": 573.44, "end": 575.88, "text": " 80% of it is what we use to train the model.", "tokens": [ 51664, 4688, 4, 295, 309, 307, 437, 321, 764, 281, 3847, 264, 2316, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.20872043586663297, "compression_ratio": 1.7473309608540926, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 573.44, "end": 573.64, "word": " 80", "probability": 0.88623046875 }, { "start": 573.64, "end": 573.88, "word": "%", "probability": 0.99755859375 }, { "start": 573.88, "end": 574.04, "word": " of", "probability": 0.88916015625 }, { "start": 574.04, "end": 574.14, "word": " it", "probability": 0.8994140625 }, { "start": 574.14, "end": 574.3, "word": " is", "probability": 0.90283203125 }, { "start": 574.3, "end": 574.46, "word": " what", "probability": 0.8828125 }, { "start": 574.46, "end": 574.6, "word": " we", "probability": 0.9013671875 }, { "start": 574.6, "end": 574.8, "word": " use", "probability": 0.75634765625 }, { "start": 574.8, "end": 574.94, "word": " to", "probability": 0.90478515625 }, { "start": 574.94, "end": 575.3, "word": " train", "probability": 0.81640625 }, { "start": 575.3, "end": 575.46, "word": " the", "probability": 0.8115234375 }, { "start": 575.46, "end": 575.74, "word": " model", "probability": 0.81689453125 }, { "start": 575.74, "end": 575.88, "word": ".", "probability": 0.58984375 } ] }, { "id": 225, "seek": 57788, "start": 575.88, "end": 577.0, "text": " And then the other 20%", "tokens": [ 51764, 400, 550, 264, 661, 945, 4, 51814 ], "temperature": 0.0, "avg_logprob": -0.20872043586663297, "compression_ratio": 1.7473309608540926, "no_speech_prob": 0.0002269744873046875, "words": [ { "start": 575.88, "end": 575.96, "word": " And", "probability": 0.89501953125 }, { "start": 575.96, "end": 576.06, "word": " then", "probability": 0.7080078125 }, { "start": 576.06, "end": 576.18, "word": " the", "probability": 0.81396484375 }, { "start": 576.18, "end": 576.32, "word": " other", "probability": 0.76806640625 }, { "start": 576.32, "end": 576.72, "word": " 20", "probability": 0.916015625 }, { "start": 576.72, "end": 577.0, "word": "%", "probability": 0.94580078125 } ] }, { "id": 226, "seek": 60480, "start": 577.88, "end": 580.0, "text": " is what is used to evaluate the model", "tokens": [ 50364, 307, 437, 307, 1143, 281, 13059, 264, 2316, 50414 ], "temperature": 0.0, "avg_logprob": -0.1929624029775945, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 577.88, "end": 578.0, "word": " is", "probability": 0.061187744140625 }, { "start": 578.0, "end": 578.06, "word": " what", "probability": 0.62548828125 }, { "start": 578.06, "end": 578.26, "word": " is", "probability": 0.90576171875 }, { "start": 578.26, "end": 578.54, "word": " used", "probability": 0.80615234375 }, { "start": 578.54, "end": 578.92, "word": " to", "probability": 0.9033203125 }, { "start": 578.92, "end": 579.54, "word": " evaluate", "probability": 0.7705078125 }, { "start": 579.54, "end": 579.8, "word": " the", "probability": 0.8095703125 }, { "start": 579.8, "end": 580.0, "word": " model", "probability": 0.8193359375 } ] }, { "id": 227, "seek": 60480, "start": 580.0, "end": 581.94, "text": " to see how well the model is performing.", "tokens": [ 50464, 281, 536, 577, 731, 264, 2316, 307, 10205, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.1929624029775945, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 580.0, "end": 580.14, "word": " to", "probability": 0.31103515625 }, { "start": 580.14, "end": 580.28, "word": " see", "probability": 0.80810546875 }, { "start": 580.28, "end": 580.46, "word": " how", "probability": 0.900390625 }, { "start": 580.46, "end": 580.68, "word": " well", "probability": 0.87109375 }, { "start": 580.68, "end": 580.82, "word": " the", "probability": 0.81298828125 }, { "start": 580.82, "end": 581.0, "word": " model", "probability": 0.66015625 }, { "start": 581.0, "end": 581.12, "word": " is", "probability": 0.505859375 }, { "start": 581.12, "end": 581.54, "word": " performing", "probability": 0.70166015625 }, { "start": 581.54, "end": 581.94, "word": ".", "probability": 0.92333984375 } ] }, { "id": 228, "seek": 60480, "start": 582.84, "end": 585.22, "text": " And so it's kind of like how we teach", "tokens": [ 50564, 400, 370, 309, 311, 733, 295, 411, 577, 321, 2924, 50714 ], "temperature": 0.0, "avg_logprob": -0.1929624029775945, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 582.84, "end": 583.2, "word": " And", "probability": 0.6650390625 }, { "start": 583.2, "end": 583.52, "word": " so", "probability": 0.89306640625 }, { "start": 583.52, "end": 584.32, "word": " it's", "probability": 0.87255859375 }, { "start": 584.32, "end": 584.46, "word": " kind", "probability": 0.7802734375 }, { "start": 584.46, "end": 584.54, "word": " of", "probability": 0.904296875 }, { "start": 584.54, "end": 584.68, "word": " like", "probability": 0.8623046875 }, { "start": 584.68, "end": 584.82, "word": " how", "probability": 0.90087890625 }, { "start": 584.82, "end": 584.96, "word": " we", "probability": 0.90869140625 }, { "start": 584.96, "end": 585.22, "word": " teach", "probability": 0.85595703125 } ] }, { "id": 229, "seek": 60480, "start": 585.22, "end": 587.16, "text": " students in elementary school, right?", "tokens": [ 50764, 1731, 294, 16429, 1395, 11, 558, 30, 50814 ], "temperature": 0.0, "avg_logprob": -0.1929624029775945, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 585.22, "end": 585.68, "word": " students", "probability": 0.90869140625 }, { "start": 585.68, "end": 586.04, "word": " in", "probability": 0.90087890625 }, { "start": 586.04, "end": 586.44, "word": " elementary", "probability": 0.859375 }, { "start": 586.44, "end": 586.76, "word": " school", "probability": 0.896484375 }, { "start": 586.76, "end": 586.92, "word": ",", "probability": 0.70361328125 }, { "start": 586.92, "end": 587.12, "word": " right", "probability": 0.8515625 }, { "start": 587.12, "end": 587.16, "word": "?", "probability": 0.85693359375 } ] }, { "id": 230, "seek": 60480, "start": 587.16, "end": 589.5, "text": " We train them on the bulk of information", "tokens": [ 50864, 492, 3847, 552, 322, 264, 16139, 295, 1589, 50914 ], "temperature": 0.0, "avg_logprob": -0.1929624029775945, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 587.16, "end": 587.38, "word": " We", "probability": 0.8984375 }, { "start": 587.38, "end": 587.94, "word": " train", "probability": 0.6943359375 }, { "start": 587.94, "end": 588.16, "word": " them", "probability": 0.75048828125 }, { "start": 588.16, "end": 588.36, "word": " on", "probability": 0.90869140625 }, { "start": 588.36, "end": 588.48, "word": " the", "probability": 0.81591796875 }, { "start": 588.48, "end": 588.72, "word": " bulk", "probability": 0.81201171875 }, { "start": 588.72, "end": 588.94, "word": " of", "probability": 0.90234375 }, { "start": 588.94, "end": 589.5, "word": " information", "probability": 0.71484375 } ] }, { "id": 231, "seek": 60480, "start": 589.5, "end": 591.38, "text": " and then we test them to see how well", "tokens": [ 50964, 293, 550, 321, 1500, 552, 281, 536, 577, 731, 51014 ], "temperature": 0.0, "avg_logprob": -0.1929624029775945, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 589.5, "end": 589.78, "word": " and", "probability": 0.607421875 }, { "start": 589.78, "end": 589.88, "word": " then", "probability": 0.732421875 }, { "start": 589.88, "end": 590.0, "word": " we", "probability": 0.90771484375 }, { "start": 590.0, "end": 590.32, "word": " test", "probability": 0.8095703125 }, { "start": 590.32, "end": 590.48, "word": " them", "probability": 0.74462890625 }, { "start": 590.48, "end": 590.62, "word": " to", "probability": 0.904296875 }, { "start": 590.62, "end": 590.78, "word": " see", "probability": 0.80419921875 }, { "start": 590.78, "end": 591.06, "word": " how", "probability": 0.89990234375 }, { "start": 591.06, "end": 591.38, "word": " well", "probability": 0.87841796875 } ] }, { "id": 232, "seek": 60480, "start": 591.38, "end": 593.14, "text": " they're understanding the material.", "tokens": [ 51064, 436, 434, 3701, 264, 2527, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.1929624029775945, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 591.38, "end": 591.58, "word": " they're", "probability": 0.81005859375 }, { "start": 591.58, "end": 592.1, "word": " understanding", "probability": 0.693359375 }, { "start": 592.1, "end": 592.28, "word": " the", "probability": 0.8125 }, { "start": 592.28, "end": 592.74, "word": " material", "probability": 0.81005859375 }, { "start": 592.74, "end": 593.14, "word": ".", "probability": 0.93701171875 } ] }, { "id": 233, "seek": 60480, "start": 594.04, "end": 595.88, "text": " And so some of our models", "tokens": [ 51164, 400, 370, 512, 295, 527, 5245, 51264 ], "temperature": 0.0, "avg_logprob": -0.1929624029775945, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 594.04, "end": 594.16, "word": " And", "probability": 0.86572265625 }, { "start": 594.16, "end": 594.46, "word": " so", "probability": 0.88623046875 }, { "start": 594.46, "end": 595.12, "word": " some", "probability": 0.75537109375 }, { "start": 595.12, "end": 595.22, "word": " of", "probability": 0.8857421875 }, { "start": 595.22, "end": 595.36, "word": " our", "probability": 0.654296875 }, { "start": 595.36, "end": 595.88, "word": " models", "probability": 0.82568359375 } ] }, { "id": 234, "seek": 60480, "start": 596.68, "end": 597.74, "text": " will perform very well.", "tokens": [ 51314, 486, 2042, 588, 731, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.1929624029775945, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 596.68, "end": 596.88, "word": " will", "probability": 0.69189453125 }, { "start": 596.88, "end": 597.22, "word": " perform", "probability": 0.78515625 }, { "start": 597.22, "end": 597.44, "word": " very", "probability": 0.72900390625 }, { "start": 597.44, "end": 597.66, "word": " well", "probability": 0.88037109375 }, { "start": 597.66, "end": 597.74, "word": ".", "probability": 0.31884765625 } ] }, { "id": 235, "seek": 60480, "start": 597.74, "end": 600.64, "text": " Some of our models may not.", "tokens": [ 51414, 2188, 295, 527, 5245, 815, 406, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.1929624029775945, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 597.74, "end": 597.86, "word": " Some", "probability": 0.89404296875 }, { "start": 597.86, "end": 598.0, "word": " of", "probability": 0.900390625 }, { "start": 598.0, "end": 598.16, "word": " our", "probability": 0.81640625 }, { "start": 598.16, "end": 598.54, "word": " models", "probability": 0.8046875 }, { "start": 598.54, "end": 599.96, "word": " may", "probability": 0.89501953125 }, { "start": 599.96, "end": 600.24, "word": " not", "probability": 0.89697265625 }, { "start": 600.24, "end": 600.64, "word": ".", "probability": 0.919921875 } ] }, { "id": 236, "seek": 60480, "start": 600.64, "end": 602.0, "text": " And so if we have a model", "tokens": [ 51514, 400, 370, 498, 321, 362, 257, 2316, 51564 ], "temperature": 0.0, "avg_logprob": -0.1929624029775945, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 600.64, "end": 600.8, "word": " And", "probability": 0.89404296875 }, { "start": 600.8, "end": 601.12, "word": " so", "probability": 0.8984375 }, { "start": 601.12, "end": 601.4, "word": " if", "probability": 0.89013671875 }, { "start": 601.4, "end": 601.54, "word": " we", "probability": 0.90380859375 }, { "start": 601.54, "end": 601.68, "word": " have", "probability": 0.88037109375 }, { "start": 601.82, "end": 602.0, "word": " a model", "probability": 0.826171875 } ] }, { "id": 237, "seek": 60480, "start": 602.0, "end": 603.64, "text": " that performs fairly well,", "tokens": [ 51614, 300, 26213, 6457, 731, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.1929624029775945, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 602.0, "end": 602.22, "word": " that", "probability": 0.8798828125 }, { "start": 602.22, "end": 602.7, "word": " performs", "probability": 0.736328125 }, { "start": 602.7, "end": 603.4, "word": " fairly", "probability": 0.85498046875 }, { "start": 603.4, "end": 603.64, "word": " well", "probability": 0.8740234375 }, { "start": 603.64, "end": 603.64, "word": ",", "probability": 0.50341796875 } ] }, { "id": 238, "seek": 60480, "start": 603.64, "end": 604.8, "text": " but we think it could do better,", "tokens": [ 51714, 457, 321, 519, 309, 727, 360, 1101, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.1929624029775945, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 603.64, "end": 603.78, "word": " but", "probability": 0.90087890625 }, { "start": 603.78, "end": 603.9, "word": " we", "probability": 0.90966796875 }, { "start": 603.9, "end": 604.06, "word": " think", "probability": 0.81298828125 }, { "start": 604.06, "end": 604.16, "word": " it", "probability": 0.90087890625 }, { "start": 604.16, "end": 604.26, "word": " could", "probability": 0.79638671875 }, { "start": 604.26, "end": 604.4, "word": " do", "probability": 0.9111328125 }, { "start": 604.4, "end": 604.68, "word": " better", "probability": 0.83056640625 }, { "start": 604.68, "end": 604.8, "word": ",", "probability": 0.525390625 } ] }, { "id": 239, "seek": 63480, "start": 604.8, "end": 606.5, "text": " then we hop into what is called", "tokens": [ 50364, 550, 321, 3818, 666, 437, 307, 1219, 50414 ], "temperature": 0.0, "avg_logprob": -0.15237069294370453, "compression_ratio": 1.7220216606498195, "no_speech_prob": 0.0005612373352050781, "words": [ { "start": 604.8, "end": 604.9, "word": " then", "probability": 0.266357421875 }, { "start": 604.9, "end": 605.12, "word": " we", "probability": 0.91064453125 }, { "start": 605.12, "end": 605.48, "word": " hop", "probability": 0.83447265625 }, { "start": 605.48, "end": 605.88, "word": " into", "probability": 0.71142578125 }, { "start": 605.88, "end": 606.18, "word": " what", "probability": 0.86669921875 }, { "start": 606.18, "end": 606.3, "word": " is", "probability": 0.900390625 }, { "start": 606.3, "end": 606.5, "word": " called", "probability": 0.77880859375 } ] }, { "id": 240, "seek": 63480, "start": 607.1, "end": 608.26, "text": " hyperparameter tuning.", "tokens": [ 50464, 9848, 2181, 335, 2398, 15164, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.15237069294370453, "compression_ratio": 1.7220216606498195, "no_speech_prob": 0.0005612373352050781, "words": [ { "start": 607.1, "end": 607.5, "word": " hyperparameter", "probability": 0.8331298828125 }, { "start": 607.5, "end": 607.86, "word": " tuning", "probability": 0.78125 }, { "start": 607.86, "end": 608.26, "word": ".", "probability": 0.748046875 } ] }, { "id": 241, "seek": 63480, "start": 608.5, "end": 609.9, "text": " And we're going to see what a hyperparameter", "tokens": [ 50564, 400, 321, 434, 516, 281, 536, 437, 257, 9848, 2181, 335, 2398, 50614 ], "temperature": 0.0, "avg_logprob": -0.15237069294370453, "compression_ratio": 1.7220216606498195, "no_speech_prob": 0.0005612373352050781, "words": [ { "start": 608.5, "end": 608.64, "word": " And", "probability": 0.69970703125 }, { "start": 608.64, "end": 608.78, "word": " we're", "probability": 0.921630859375 }, { "start": 608.78, "end": 608.86, "word": " going", "probability": 0.406005859375 }, { "start": 608.86, "end": 608.94, "word": " to", "probability": 0.90576171875 }, { "start": 608.94, "end": 609.12, "word": " see", "probability": 0.81591796875 }, { "start": 609.12, "end": 609.28, "word": " what", "probability": 0.88916015625 }, { "start": 609.36, "end": 609.9, "word": " a hyperparameter", "probability": 0.9744873046875 } ] }, { "id": 242, "seek": 63480, "start": 609.9, "end": 611.6, "text": " looks like in a little bit.", "tokens": [ 50664, 1542, 411, 294, 257, 707, 857, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.15237069294370453, "compression_ratio": 1.7220216606498195, "no_speech_prob": 0.0005612373352050781, "words": [ { "start": 609.9, "end": 610.18, "word": " looks", "probability": 0.80517578125 }, { "start": 610.18, "end": 610.46, "word": " like", "probability": 0.87646484375 }, { "start": 610.46, "end": 610.64, "word": " in", "probability": 0.8994140625 }, { "start": 610.78, "end": 610.92, "word": " a little", "probability": 0.80224609375 }, { "start": 610.92, "end": 611.2, "word": " bit", "probability": 0.90576171875 }, { "start": 611.2, "end": 611.6, "word": ".", "probability": 0.638671875 } ] }, { "id": 243, "seek": 63480, "start": 611.88, "end": 613.6, "text": " But hyperparameter tuning,", "tokens": [ 50764, 583, 9848, 2181, 335, 2398, 15164, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.15237069294370453, "compression_ratio": 1.7220216606498195, "no_speech_prob": 0.0005612373352050781, "words": [ { "start": 611.88, "end": 611.98, "word": " But", "probability": 0.85546875 }, { "start": 611.98, "end": 613.04, "word": " hyperparameter", "probability": 0.9488525390625 }, { "start": 613.04, "end": 613.42, "word": " tuning", "probability": 0.78857421875 }, { "start": 613.42, "end": 613.6, "word": ",", "probability": 0.8125 } ] }, { "id": 244, "seek": 63480, "start": 613.6, "end": 616.18, "text": " think of it as little knobs and levers", "tokens": [ 50864, 519, 295, 309, 382, 707, 46999, 293, 45571, 50914 ], "temperature": 0.0, "avg_logprob": -0.15237069294370453, "compression_ratio": 1.7220216606498195, "no_speech_prob": 0.0005612373352050781, "words": [ { "start": 613.6, "end": 613.74, "word": " think", "probability": 0.7880859375 }, { "start": 613.74, "end": 613.82, "word": " of", "probability": 0.90673828125 }, { "start": 613.82, "end": 613.9, "word": " it", "probability": 0.90576171875 }, { "start": 613.9, "end": 614.02, "word": " as", "probability": 0.908203125 }, { "start": 614.02, "end": 614.4, "word": " little", "probability": 0.77880859375 }, { "start": 614.4, "end": 615.68, "word": " knobs", "probability": 0.85693359375 }, { "start": 615.68, "end": 615.88, "word": " and", "probability": 0.82666015625 }, { "start": 615.88, "end": 616.18, "word": " levers", "probability": 0.70361328125 } ] }, { "id": 245, "seek": 63480, "start": 616.18, "end": 617.54, "text": " and switches that we can use", "tokens": [ 50964, 293, 19458, 300, 321, 393, 764, 51014 ], "temperature": 0.0, "avg_logprob": -0.15237069294370453, "compression_ratio": 1.7220216606498195, "no_speech_prob": 0.0005612373352050781, "words": [ { "start": 616.18, "end": 616.38, "word": " and", "probability": 0.88916015625 }, { "start": 616.38, "end": 616.66, "word": " switches", "probability": 0.873046875 }, { "start": 616.66, "end": 616.98, "word": " that", "probability": 0.87451171875 }, { "start": 616.98, "end": 617.08, "word": " we", "probability": 0.9072265625 }, { "start": 617.08, "end": 617.26, "word": " can", "probability": 0.89404296875 }, { "start": 617.26, "end": 617.54, "word": " use", "probability": 0.8310546875 } ] }, { "id": 246, "seek": 63480, "start": 617.54, "end": 618.76, "text": " to kind of tweak our model", "tokens": [ 51064, 281, 733, 295, 29879, 527, 2316, 51114 ], "temperature": 0.0, "avg_logprob": -0.15237069294370453, "compression_ratio": 1.7220216606498195, "no_speech_prob": 0.0005612373352050781, "words": [ { "start": 617.54, "end": 617.7, "word": " to", "probability": 0.9013671875 }, { "start": 617.7, "end": 617.9, "word": " kind", "probability": 0.658203125 }, { "start": 617.9, "end": 618.02, "word": " of", "probability": 0.8984375 }, { "start": 618.02, "end": 618.28, "word": " tweak", "probability": 0.87890625 }, { "start": 618.28, "end": 618.48, "word": " our", "probability": 0.81982421875 }, { "start": 618.48, "end": 618.76, "word": " model", "probability": 0.81689453125 } ] }, { "id": 247, "seek": 63480, "start": 618.76, "end": 620.16, "text": " and tune it in such a way", "tokens": [ 51164, 293, 10864, 309, 294, 1270, 257, 636, 51214 ], "temperature": 0.0, "avg_logprob": -0.15237069294370453, "compression_ratio": 1.7220216606498195, "no_speech_prob": 0.0005612373352050781, "words": [ { "start": 618.76, "end": 619.0, "word": " and", "probability": 0.87646484375 }, { "start": 619.0, "end": 619.24, "word": " tune", "probability": 0.830078125 }, { "start": 619.24, "end": 619.4, "word": " it", "probability": 0.90576171875 }, { "start": 619.4, "end": 619.54, "word": " in", "probability": 0.90771484375 }, { "start": 619.54, "end": 619.74, "word": " such", "probability": 0.8818359375 }, { "start": 619.88, "end": 620.16, "word": " a way", "probability": 0.89599609375 } ] }, { "id": 248, "seek": 63480, "start": 620.16, "end": 624.16, "text": " that it is better at a certain type of problem.", "tokens": [ 51264, 300, 309, 307, 1101, 412, 257, 1629, 2010, 295, 1154, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.15237069294370453, "compression_ratio": 1.7220216606498195, "no_speech_prob": 0.0005612373352050781, "words": [ { "start": 620.16, "end": 620.86, "word": " that", "probability": 0.87109375 }, { "start": 620.86, "end": 621.06, "word": " it", "probability": 0.88330078125 }, { "start": 621.06, "end": 621.22, "word": " is", "probability": 0.8955078125 }, { "start": 621.22, "end": 621.86, "word": " better", "probability": 0.8212890625 }, { "start": 621.86, "end": 622.58, "word": " at", "probability": 0.8857421875 }, { "start": 622.78, "end": 622.96, "word": " a certain", "probability": 0.802734375 }, { "start": 622.96, "end": 623.24, "word": " type", "probability": 0.923828125 }, { "start": 623.24, "end": 623.38, "word": " of", "probability": 0.90673828125 }, { "start": 623.38, "end": 623.76, "word": " problem", "probability": 0.76318359375 }, { "start": 623.76, "end": 624.16, "word": ".", "probability": 0.9970703125 } ] }, { "id": 249, "seek": 63480, "start": 624.98, "end": 626.44, "text": " And then once we've completed all this,", "tokens": [ 51364, 400, 550, 1564, 321, 600, 7365, 439, 341, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.15237069294370453, "compression_ratio": 1.7220216606498195, "no_speech_prob": 0.0005612373352050781, "words": [ { "start": 624.98, "end": 625.14, "word": " And", "probability": 0.880859375 }, { "start": 625.14, "end": 625.26, "word": " then", "probability": 0.732421875 }, { "start": 625.26, "end": 625.4, "word": " once", "probability": 0.79931640625 }, { "start": 625.4, "end": 625.6, "word": " we've", "probability": 0.927734375 }, { "start": 625.6, "end": 625.9, "word": " completed", "probability": 0.59033203125 }, { "start": 625.9, "end": 626.12, "word": " all", "probability": 0.89404296875 }, { "start": 626.12, "end": 626.38, "word": " this", "probability": 0.34228515625 }, { "start": 626.38, "end": 626.44, "word": ",", "probability": 0.87841796875 } ] }, { "id": 250, "seek": 63480, "start": 626.44, "end": 627.68, "text": " we're ready to deploy.", "tokens": [ 51464, 321, 434, 1919, 281, 7274, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.15237069294370453, "compression_ratio": 1.7220216606498195, "no_speech_prob": 0.0005612373352050781, "words": [ { "start": 626.44, "end": 626.58, "word": " we're", "probability": 0.926513671875 }, { "start": 626.58, "end": 626.8, "word": " ready", "probability": 0.80517578125 }, { "start": 626.8, "end": 626.96, "word": " to", "probability": 0.904296875 }, { "start": 626.96, "end": 627.28, "word": " deploy", "probability": 0.7568359375 }, { "start": 627.28, "end": 627.68, "word": ".", "probability": 0.98486328125 } ] }, { "id": 251, "seek": 63480, "start": 628.0, "end": 630.04, "text": " Now the reason why this is cyclical, right?", "tokens": [ 51564, 823, 264, 1778, 983, 341, 307, 19474, 804, 11, 558, 30, 51614 ], "temperature": 0.0, "avg_logprob": -0.15237069294370453, "compression_ratio": 1.7220216606498195, "no_speech_prob": 0.0005612373352050781, "words": [ { "start": 628.0, "end": 628.4, "word": " Now", "probability": 0.88916015625 }, { "start": 628.4, "end": 628.5, "word": " the", "probability": 0.353515625 }, { "start": 628.5, "end": 628.7, "word": " reason", "probability": 0.91162109375 }, { "start": 628.7, "end": 628.86, "word": " why", "probability": 0.82080078125 }, { "start": 628.86, "end": 629.04, "word": " this", "probability": 0.88427734375 }, { "start": 629.04, "end": 629.2, "word": " is", "probability": 0.9169921875 }, { "start": 629.2, "end": 629.68, "word": " cyclical", "probability": 0.8291015625 }, { "start": 629.68, "end": 629.9, "word": ",", "probability": 0.92919921875 }, { "start": 629.9, "end": 630.04, "word": " right", "probability": 0.595703125 }, { "start": 630.04, "end": 630.04, "word": "?", "probability": 0.46484375 } ] }, { "id": 252, "seek": 63480, "start": 630.04, "end": 631.3, "text": " We want to gather more data,", "tokens": [ 51664, 492, 528, 281, 5448, 544, 1412, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.15237069294370453, "compression_ratio": 1.7220216606498195, "no_speech_prob": 0.0005612373352050781, "words": [ { "start": 630.04, "end": 630.16, "word": " We", "probability": 0.90087890625 }, { "start": 630.16, "end": 630.32, "word": " want", "probability": 0.77880859375 }, { "start": 630.32, "end": 630.4, "word": " to", "probability": 0.9072265625 }, { "start": 630.4, "end": 630.56, "word": " gather", "probability": 0.7978515625 }, { "start": 630.56, "end": 630.88, "word": " more", "probability": 0.884765625 }, { "start": 630.88, "end": 631.16, "word": " data", "probability": 0.81689453125 }, { "start": 631.16, "end": 631.3, "word": ",", "probability": 0.974609375 } ] }, { "id": 253, "seek": 63480, "start": 631.3, "end": 632.9, "text": " prepare the data,", "tokens": [ 51764, 5940, 264, 1412, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.15237069294370453, "compression_ratio": 1.7220216606498195, "no_speech_prob": 0.0005612373352050781, "words": [ { "start": 631.3, "end": 631.58, "word": " prepare", "probability": 0.8330078125 }, { "start": 631.58, "end": 631.8, "word": " the", "probability": 0.81787109375 }, { "start": 631.8, "end": 632.14, "word": " data", "probability": 0.818359375 }, { "start": 632.14, "end": 632.9, "word": ",", "probability": 0.94091796875 } ] }, { "id": 254, "seek": 66142, "start": 634.8, "end": 636.0, "text": " and use the same model", "tokens": [ 50364, 293, 764, 264, 912, 2316, 50414 ], "temperature": 0.0, "avg_logprob": -0.18419716028663202, "compression_ratio": 1.7297297297297298, "no_speech_prob": 0.01049041748046875, "words": [ { "start": 634.8, "end": 635.26, "word": " and", "probability": 0.0201263427734375 }, { "start": 635.26, "end": 635.34, "word": " use", "probability": 0.238037109375 }, { "start": 635.34, "end": 635.5, "word": " the", "probability": 0.73583984375 }, { "start": 635.5, "end": 635.72, "word": " same", "probability": 0.798828125 }, { "start": 635.72, "end": 636.0, "word": " model", "probability": 0.81201171875 } ] }, { "id": 255, "seek": 66142, "start": 636.0, "end": 638.5, "text": " that we're already using after deploy", "tokens": [ 50464, 300, 321, 434, 1217, 1228, 934, 7274, 50514 ], "temperature": 0.0, "avg_logprob": -0.18419716028663202, "compression_ratio": 1.7297297297297298, "no_speech_prob": 0.01049041748046875, "words": [ { "start": 636.0, "end": 636.16, "word": " that", "probability": 0.5166015625 }, { "start": 636.16, "end": 636.3, "word": " we're", "probability": 0.8330078125 }, { "start": 636.3, "end": 636.56, "word": " already", "probability": 0.7470703125 }, { "start": 636.56, "end": 636.94, "word": " using", "probability": 0.82666015625 }, { "start": 636.94, "end": 637.84, "word": " after", "probability": 0.56103515625 }, { "start": 637.84, "end": 638.5, "word": " deploy", "probability": 0.7001953125 } ] }, { "id": 256, "seek": 66142, "start": 638.5, "end": 640.04, "text": " is because machine learning", "tokens": [ 50564, 307, 570, 3479, 2539, 50614 ], "temperature": 0.0, "avg_logprob": -0.18419716028663202, "compression_ratio": 1.7297297297297298, "no_speech_prob": 0.01049041748046875, "words": [ { "start": 638.5, "end": 638.98, "word": " is", "probability": 0.5478515625 }, { "start": 638.98, "end": 639.28, "word": " because", "probability": 0.81982421875 }, { "start": 639.28, "end": 639.62, "word": " machine", "probability": 0.67431640625 }, { "start": 639.62, "end": 640.04, "word": " learning", "probability": 0.84716796875 } ] }, { "id": 257, "seek": 66142, "start": 640.58, "end": 642.86, "text": " stops learning as soon as it's trained.", "tokens": [ 50664, 10094, 2539, 382, 2321, 382, 309, 311, 8895, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.18419716028663202, "compression_ratio": 1.7297297297297298, "no_speech_prob": 0.01049041748046875, "words": [ { "start": 640.58, "end": 640.82, "word": " stops", "probability": 0.7490234375 }, { "start": 640.82, "end": 641.24, "word": " learning", "probability": 0.8515625 }, { "start": 641.24, "end": 641.58, "word": " as", "probability": 0.8896484375 }, { "start": 641.58, "end": 641.74, "word": " soon", "probability": 0.8759765625 }, { "start": 641.74, "end": 641.88, "word": " as", "probability": 0.90185546875 }, { "start": 641.88, "end": 642.04, "word": " it's", "probability": 0.91845703125 }, { "start": 642.04, "end": 642.38, "word": " trained", "probability": 0.81494140625 }, { "start": 642.38, "end": 642.86, "word": ".", "probability": 0.9091796875 } ] }, { "id": 258, "seek": 66142, "start": 643.3, "end": 644.84, "text": " So to kind of give you an idea,", "tokens": [ 50764, 407, 281, 733, 295, 976, 291, 364, 1558, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.18419716028663202, "compression_ratio": 1.7297297297297298, "no_speech_prob": 0.01049041748046875, "words": [ { "start": 643.3, "end": 643.62, "word": " So", "probability": 0.469970703125 }, { "start": 643.62, "end": 643.76, "word": " to", "probability": 0.53662109375 }, { "start": 643.76, "end": 643.96, "word": " kind", "probability": 0.60986328125 }, { "start": 643.96, "end": 643.98, "word": " of", "probability": 0.908203125 }, { "start": 643.98, "end": 644.12, "word": " give", "probability": 0.82177734375 }, { "start": 644.12, "end": 644.22, "word": " you", "probability": 0.89599609375 }, { "start": 644.22, "end": 644.32, "word": " an", "probability": 0.90283203125 }, { "start": 644.32, "end": 644.6, "word": " idea", "probability": 0.77001953125 }, { "start": 644.6, "end": 644.84, "word": ",", "probability": 0.84716796875 } ] }, { "id": 259, "seek": 66142, "start": 644.84, "end": 646.82, "text": " I know that certain spam filters", "tokens": [ 50864, 286, 458, 300, 1629, 24028, 15995, 50914 ], "temperature": 0.0, "avg_logprob": -0.18419716028663202, "compression_ratio": 1.7297297297297298, "no_speech_prob": 0.01049041748046875, "words": [ { "start": 644.84, "end": 644.88, "word": " I", "probability": 0.98779296875 }, { "start": 644.88, "end": 645.1, "word": " know", "probability": 0.81005859375 }, { "start": 645.1, "end": 645.58, "word": " that", "probability": 0.88134765625 }, { "start": 645.58, "end": 646.16, "word": " certain", "probability": 0.82177734375 }, { "start": 646.16, "end": 646.44, "word": " spam", "probability": 0.919921875 }, { "start": 646.44, "end": 646.82, "word": " filters", "probability": 0.81982421875 } ] }, { "id": 260, "seek": 66142, "start": 646.82, "end": 648.66, "text": " like Facebook's Facebook spam filter,", "tokens": [ 50964, 411, 4384, 311, 4384, 24028, 6608, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.18419716028663202, "compression_ratio": 1.7297297297297298, "no_speech_prob": 0.01049041748046875, "words": [ { "start": 646.82, "end": 647.1, "word": " like", "probability": 0.6669921875 }, { "start": 647.1, "end": 647.62, "word": " Facebook's", "probability": 0.71630859375 }, { "start": 647.62, "end": 647.88, "word": " Facebook", "probability": 0.6640625 }, { "start": 647.88, "end": 648.16, "word": " spam", "probability": 0.8603515625 }, { "start": 648.16, "end": 648.5, "word": " filter", "probability": 0.90869140625 }, { "start": 648.5, "end": 648.66, "word": ",", "probability": 0.85205078125 } ] }, { "id": 261, "seek": 66142, "start": 648.66, "end": 650.26, "text": " they retrain it and rebuild it", "tokens": [ 51064, 436, 1533, 7146, 309, 293, 16877, 309, 51114 ], "temperature": 0.0, "avg_logprob": -0.18419716028663202, "compression_ratio": 1.7297297297297298, "no_speech_prob": 0.01049041748046875, "words": [ { "start": 648.66, "end": 648.76, "word": " they", "probability": 0.73828125 }, { "start": 648.76, "end": 649.42, "word": " retrain", "probability": 0.835205078125 }, { "start": 649.42, "end": 649.56, "word": " it", "probability": 0.8251953125 }, { "start": 649.56, "end": 649.68, "word": " and", "probability": 0.87890625 }, { "start": 649.68, "end": 650.06, "word": " rebuild", "probability": 0.72119140625 }, { "start": 650.06, "end": 650.26, "word": " it", "probability": 0.88818359375 } ] }, { "id": 262, "seek": 66142, "start": 650.26, "end": 651.38, "text": " every one to three days", "tokens": [ 51164, 633, 472, 281, 1045, 1708, 51214 ], "temperature": 0.0, "avg_logprob": -0.18419716028663202, "compression_ratio": 1.7297297297297298, "no_speech_prob": 0.01049041748046875, "words": [ { "start": 650.26, "end": 650.5, "word": " every", "probability": 0.7578125 }, { "start": 650.5, "end": 650.72, "word": " one", "probability": 0.76513671875 }, { "start": 650.72, "end": 650.84, "word": " to", "probability": 0.9052734375 }, { "start": 650.84, "end": 651.04, "word": " three", "probability": 0.84326171875 }, { "start": 651.04, "end": 651.38, "word": " days", "probability": 0.79541015625 } ] }, { "id": 263, "seek": 66142, "start": 651.38, "end": 653.96, "text": " because that's how quickly spam", "tokens": [ 51264, 570, 300, 311, 577, 2661, 24028, 51314 ], "temperature": 0.0, "avg_logprob": -0.18419716028663202, "compression_ratio": 1.7297297297297298, "no_speech_prob": 0.01049041748046875, "words": [ { "start": 651.38, "end": 651.64, "word": " because", "probability": 0.5869140625 }, { "start": 651.64, "end": 651.92, "word": " that's", "probability": 0.9404296875 }, { "start": 651.92, "end": 652.3, "word": " how", "probability": 0.90673828125 }, { "start": 652.3, "end": 653.44, "word": " quickly", "probability": 0.8896484375 }, { "start": 653.44, "end": 653.96, "word": " spam", "probability": 0.9296875 } ] }, { "id": 264, "seek": 66142, "start": 653.96, "end": 656.46, "text": " is being processed through their pipelines", "tokens": [ 51364, 307, 885, 18846, 807, 641, 40168, 51414 ], "temperature": 0.0, "avg_logprob": -0.18419716028663202, "compression_ratio": 1.7297297297297298, "no_speech_prob": 0.01049041748046875, "words": [ { "start": 653.96, "end": 654.14, "word": " is", "probability": 0.9033203125 }, { "start": 654.14, "end": 654.36, "word": " being", "probability": 0.89208984375 }, { "start": 654.36, "end": 654.98, "word": " processed", "probability": 0.76904296875 }, { "start": 654.98, "end": 655.44, "word": " through", "probability": 0.79736328125 }, { "start": 655.44, "end": 655.82, "word": " their", "probability": 0.90283203125 }, { "start": 655.82, "end": 656.46, "word": " pipelines", "probability": 0.88916015625 } ] }, { "id": 265, "seek": 66142, "start": 656.46, "end": 658.26, "text": " and through their networks.", "tokens": [ 51464, 293, 807, 641, 9590, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.18419716028663202, "compression_ratio": 1.7297297297297298, "no_speech_prob": 0.01049041748046875, "words": [ { "start": 656.46, "end": 657.06, "word": " and", "probability": 0.8701171875 }, { "start": 657.06, "end": 657.22, "word": " through", "probability": 0.79052734375 }, { "start": 657.22, "end": 657.38, "word": " their", "probability": 0.90576171875 }, { "start": 657.38, "end": 657.78, "word": " networks", "probability": 0.65966796875 }, { "start": 657.78, "end": 658.26, "word": ".", "probability": 0.8330078125 } ] }, { "id": 266, "seek": 66142, "start": 658.32, "end": 659.58, "text": " And so it's a way for them", "tokens": [ 51564, 400, 370, 309, 311, 257, 636, 337, 552, 51614 ], "temperature": 0.0, "avg_logprob": -0.18419716028663202, "compression_ratio": 1.7297297297297298, "no_speech_prob": 0.01049041748046875, "words": [ { "start": 658.32, "end": 658.56, "word": " And", "probability": 0.84765625 }, { "start": 658.56, "end": 658.78, "word": " so", "probability": 0.90283203125 }, { "start": 658.78, "end": 659.02, "word": " it's", "probability": 0.922119140625 }, { "start": 659.12, "end": 659.28, "word": " a way", "probability": 0.90283203125 }, { "start": 659.28, "end": 659.4, "word": " for", "probability": 0.8916015625 }, { "start": 659.4, "end": 659.58, "word": " them", "probability": 0.74365234375 } ] }, { "id": 267, "seek": 66142, "start": 659.58, "end": 661.42, "text": " to kind of stay on top of that.", "tokens": [ 51664, 281, 733, 295, 1754, 322, 1192, 295, 300, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.18419716028663202, "compression_ratio": 1.7297297297297298, "no_speech_prob": 0.01049041748046875, "words": [ { "start": 659.58, "end": 659.7, "word": " to", "probability": 0.904296875 }, { "start": 659.7, "end": 659.88, "word": " kind", "probability": 0.81982421875 }, { "start": 659.88, "end": 659.96, "word": " of", "probability": 0.91162109375 }, { "start": 659.96, "end": 660.2, "word": " stay", "probability": 0.921875 }, { "start": 660.2, "end": 660.38, "word": " on", "probability": 0.9013671875 }, { "start": 660.38, "end": 660.62, "word": " top", "probability": 0.82177734375 }, { "start": 660.62, "end": 660.76, "word": " of", "probability": 0.90380859375 }, { "start": 660.76, "end": 660.94, "word": " that", "probability": 0.88623046875 }, { "start": 660.94, "end": 661.42, "word": ".", "probability": 0.9990234375 } ] }, { "id": 268, "seek": 68970, "start": 664.28, "end": 666.04, "text": " So we're going to hop into", "tokens": [ 50414, 407, 321, 434, 516, 281, 3818, 666, 50564 ], "temperature": 0.0, "avg_logprob": -0.16330198482074568, "compression_ratio": 1.6983471074380165, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 664.28, "end": 664.8, "word": " So", "probability": 0.61083984375 }, { "start": 664.8, "end": 665.32, "word": " we're", "probability": 0.77294921875 }, { "start": 665.32, "end": 665.4, "word": " going", "probability": 0.466796875 }, { "start": 665.4, "end": 665.48, "word": " to", "probability": 0.908203125 }, { "start": 665.48, "end": 665.68, "word": " hop", "probability": 0.8623046875 }, { "start": 665.68, "end": 666.04, "word": " into", "probability": 0.70361328125 } ] }, { "id": 269, "seek": 68970, "start": 666.9, "end": 668.88, "text": " understanding how machine learning works,", "tokens": [ 50614, 3701, 577, 3479, 2539, 1985, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.16330198482074568, "compression_ratio": 1.6983471074380165, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 666.9, "end": 667.42, "word": " understanding", "probability": 0.70068359375 }, { "start": 667.42, "end": 667.94, "word": " how", "probability": 0.89892578125 }, { "start": 667.94, "end": 668.26, "word": " machine", "probability": 0.69384765625 }, { "start": 668.26, "end": 668.48, "word": " learning", "probability": 0.849609375 }, { "start": 668.48, "end": 668.84, "word": " works", "probability": 0.73681640625 }, { "start": 668.84, "end": 668.88, "word": ",", "probability": 0.8623046875 } ] }, { "id": 270, "seek": 68970, "start": 668.88, "end": 670.24, "text": " especially in the security space.", "tokens": [ 50714, 2318, 294, 264, 3825, 1901, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.16330198482074568, "compression_ratio": 1.6983471074380165, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 668.88, "end": 669.16, "word": " especially", "probability": 0.7265625 }, { "start": 669.16, "end": 669.34, "word": " in", "probability": 0.90087890625 }, { "start": 669.34, "end": 669.44, "word": " the", "probability": 0.8125 }, { "start": 669.44, "end": 669.72, "word": " security", "probability": 0.921875 }, { "start": 669.72, "end": 670.12, "word": " space", "probability": 0.81005859375 }, { "start": 670.12, "end": 670.24, "word": ".", "probability": 0.6591796875 } ] }, { "id": 271, "seek": 68970, "start": 670.24, "end": 672.24, "text": " And the easiest example, in my opinion,", "tokens": [ 50814, 400, 264, 12889, 1365, 11, 294, 452, 4800, 11, 50864 ], "temperature": 0.0, "avg_logprob": -0.16330198482074568, "compression_ratio": 1.6983471074380165, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 670.24, "end": 670.28, "word": " And", "probability": 0.76806640625 }, { "start": 670.28, "end": 670.4, "word": " the", "probability": 0.81103515625 }, { "start": 670.4, "end": 670.64, "word": " easiest", "probability": 0.85693359375 }, { "start": 670.64, "end": 671.18, "word": " example", "probability": 0.9326171875 }, { "start": 671.18, "end": 671.46, "word": ",", "probability": 0.75634765625 }, { "start": 671.46, "end": 671.5, "word": " in", "probability": 0.9033203125 }, { "start": 671.5, "end": 671.72, "word": " my", "probability": 0.904296875 }, { "start": 671.72, "end": 672.08, "word": " opinion", "probability": 0.8271484375 }, { "start": 672.08, "end": 672.24, "word": ",", "probability": 0.9443359375 } ] }, { "id": 272, "seek": 68970, "start": 672.24, "end": 674.04, "text": " is building a spam filter.", "tokens": [ 50914, 307, 2390, 257, 24028, 6608, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.16330198482074568, "compression_ratio": 1.6983471074380165, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 672.24, "end": 672.56, "word": " is", "probability": 0.90087890625 }, { "start": 672.56, "end": 672.84, "word": " building", "probability": 0.806640625 }, { "start": 673.0, "end": 673.2, "word": " a spam", "probability": 0.72998046875 }, { "start": 673.2, "end": 673.52, "word": " filter", "probability": 0.91748046875 }, { "start": 673.52, "end": 674.04, "word": ".", "probability": 0.984375 } ] }, { "id": 273, "seek": 68970, "start": 674.6, "end": 675.52, "text": " Now spam filters,", "tokens": [ 51014, 823, 24028, 15995, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.16330198482074568, "compression_ratio": 1.6983471074380165, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 674.6, "end": 674.78, "word": " Now", "probability": 0.86669921875 }, { "start": 674.78, "end": 675.06, "word": " spam", "probability": 0.373779296875 }, { "start": 675.06, "end": 675.36, "word": " filters", "probability": 0.810546875 }, { "start": 675.36, "end": 675.52, "word": ",", "probability": 0.84912109375 } ] }, { "id": 274, "seek": 68970, "start": 675.52, "end": 677.9, "text": " we already know how they operate conceptually.", "tokens": [ 51114, 321, 1217, 458, 577, 436, 9651, 3410, 671, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.16330198482074568, "compression_ratio": 1.6983471074380165, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 675.52, "end": 675.56, "word": " we", "probability": 0.8994140625 }, { "start": 675.56, "end": 675.8, "word": " already", "probability": 0.8359375 }, { "start": 675.8, "end": 675.98, "word": " know", "probability": 0.81103515625 }, { "start": 675.98, "end": 676.12, "word": " how", "probability": 0.908203125 }, { "start": 676.12, "end": 676.26, "word": " they", "probability": 0.73291015625 }, { "start": 676.26, "end": 676.72, "word": " operate", "probability": 0.78173828125 }, { "start": 676.72, "end": 677.38, "word": " conceptually", "probability": 0.837158203125 }, { "start": 677.38, "end": 677.9, "word": ".", "probability": 0.78369140625 } ] }, { "id": 275, "seek": 68970, "start": 678.18, "end": 680.66, "text": " So it's a lower barrier of entry.", "tokens": [ 51214, 407, 309, 311, 257, 3126, 13357, 295, 8729, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.16330198482074568, "compression_ratio": 1.6983471074380165, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 678.18, "end": 678.7, "word": " So", "probability": 0.8828125 }, { "start": 678.7, "end": 679.22, "word": " it's", "probability": 0.93798828125 }, { "start": 679.56, "end": 679.8, "word": " a lower", "probability": 0.78857421875 }, { "start": 679.8, "end": 680.1, "word": " barrier", "probability": 0.8671875 }, { "start": 680.1, "end": 680.26, "word": " of", "probability": 0.896484375 }, { "start": 680.26, "end": 680.52, "word": " entry", "probability": 0.75146484375 }, { "start": 680.52, "end": 680.66, "word": ".", "probability": 0.80712890625 } ] }, { "id": 276, "seek": 68970, "start": 680.66, "end": 682.52, "text": " We're going to see specifically", "tokens": [ 51314, 492, 434, 516, 281, 536, 4682, 51364 ], "temperature": 0.0, "avg_logprob": -0.16330198482074568, "compression_ratio": 1.6983471074380165, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 680.66, "end": 680.78, "word": " We're", "probability": 0.926513671875 }, { "start": 680.78, "end": 680.98, "word": " going", "probability": 0.85205078125 }, { "start": 680.98, "end": 681.14, "word": " to", "probability": 0.9091796875 }, { "start": 681.14, "end": 681.44, "word": " see", "probability": 0.8251953125 }, { "start": 681.44, "end": 682.52, "word": " specifically", "probability": 0.71337890625 } ] }, { "id": 277, "seek": 68970, "start": 682.52, "end": 684.58, "text": " how the machine learning fits in.", "tokens": [ 51414, 577, 264, 3479, 2539, 9001, 294, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.16330198482074568, "compression_ratio": 1.6983471074380165, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 682.52, "end": 682.86, "word": " how", "probability": 0.8974609375 }, { "start": 682.86, "end": 683.0, "word": " the", "probability": 0.81201171875 }, { "start": 683.0, "end": 683.26, "word": " machine", "probability": 0.73828125 }, { "start": 683.26, "end": 683.52, "word": " learning", "probability": 0.8515625 }, { "start": 683.52, "end": 683.84, "word": " fits", "probability": 0.8837890625 }, { "start": 683.84, "end": 684.06, "word": " in", "probability": 0.89990234375 }, { "start": 684.06, "end": 684.58, "word": ".", "probability": 0.9560546875 } ] }, { "id": 278, "seek": 68970, "start": 684.76, "end": 686.12, "text": " But before I hop into that,", "tokens": [ 51514, 583, 949, 286, 3818, 666, 300, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.16330198482074568, "compression_ratio": 1.6983471074380165, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 684.76, "end": 685.0, "word": " But", "probability": 0.88671875 }, { "start": 685.0, "end": 685.26, "word": " before", "probability": 0.80224609375 }, { "start": 685.26, "end": 685.4, "word": " I", "probability": 0.95263671875 }, { "start": 685.4, "end": 685.58, "word": " hop", "probability": 0.85546875 }, { "start": 685.58, "end": 685.74, "word": " into", "probability": 0.7392578125 }, { "start": 685.74, "end": 686.02, "word": " that", "probability": 0.8828125 }, { "start": 686.02, "end": 686.12, "word": ",", "probability": 0.9755859375 } ] }, { "id": 279, "seek": 68970, "start": 686.12, "end": 687.34, "text": " are there any questions", "tokens": [ 51614, 366, 456, 604, 1651, 51664 ], "temperature": 0.0, "avg_logprob": -0.16330198482074568, "compression_ratio": 1.6983471074380165, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 686.12, "end": 686.22, "word": " are", "probability": 0.88623046875 }, { "start": 686.22, "end": 686.38, "word": " there", "probability": 0.85302734375 }, { "start": 686.38, "end": 686.72, "word": " any", "probability": 0.81640625 }, { "start": 686.72, "end": 687.34, "word": " questions", "probability": 0.90966796875 } ] }, { "id": 280, "seek": 68970, "start": 687.34, "end": 689.7, "text": " on how machine learning,", "tokens": [ 51714, 322, 577, 3479, 2539, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.16330198482074568, "compression_ratio": 1.6983471074380165, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 687.34, "end": 687.88, "word": " on", "probability": 0.9072265625 }, { "start": 687.88, "end": 688.34, "word": " how", "probability": 0.8984375 }, { "start": 688.34, "end": 688.86, "word": " machine", "probability": 0.7216796875 }, { "start": 688.86, "end": 689.32, "word": " learning", "probability": 0.84326171875 }, { "start": 689.32, "end": 689.7, "word": ",", "probability": 0.69482421875 } ] }, { "id": 281, "seek": 71570, "start": 689.7, "end": 691.38, "text": " AI, and deep learning", "tokens": [ 50364, 7318, 11, 293, 2452, 2539, 50414 ], "temperature": 0.0, "avg_logprob": -0.2011904761904762, "compression_ratio": 1.8372093023255813, "no_speech_prob": 0.00154876708984375, "words": [ { "start": 689.7, "end": 690.28, "word": " AI", "probability": 0.28271484375 }, { "start": 690.28, "end": 690.72, "word": ",", "probability": 0.043548583984375 }, { "start": 690.72, "end": 690.82, "word": " and", "probability": 0.8818359375 }, { "start": 690.82, "end": 691.04, "word": " deep", "probability": 0.84716796875 }, { "start": 691.04, "end": 691.38, "word": " learning", "probability": 0.8330078125 } ] }, { "id": 282, "seek": 71570, "start": 691.38, "end": 692.3, "text": " kind of intermingle", "tokens": [ 50464, 733, 295, 728, 2810, 306, 50514 ], "temperature": 0.0, "avg_logprob": -0.2011904761904762, "compression_ratio": 1.8372093023255813, "no_speech_prob": 0.00154876708984375, "words": [ { "start": 691.38, "end": 691.64, "word": " kind", "probability": 0.74658203125 }, { "start": 691.64, "end": 691.74, "word": " of", "probability": 0.9111328125 }, { "start": 691.74, "end": 692.3, "word": " intermingle", "probability": 0.9256184895833334 } ] }, { "id": 283, "seek": 71570, "start": 692.3, "end": 693.6, "text": " and why it's important", "tokens": [ 50564, 293, 983, 309, 311, 1021, 50614 ], "temperature": 0.0, "avg_logprob": -0.2011904761904762, "compression_ratio": 1.8372093023255813, "no_speech_prob": 0.00154876708984375, "words": [ { "start": 692.3, "end": 692.56, "word": " and", "probability": 0.59814453125 }, { "start": 692.56, "end": 693.06, "word": " why", "probability": 0.8203125 }, { "start": 693.06, "end": 693.24, "word": " it's", "probability": 0.94970703125 }, { "start": 693.24, "end": 693.6, "word": " important", "probability": 0.77392578125 } ] }, { "id": 284, "seek": 71570, "start": 693.6, "end": 695.4, "text": " to understand machine learning", "tokens": [ 50664, 281, 1223, 3479, 2539, 50714 ], "temperature": 0.0, "avg_logprob": -0.2011904761904762, "compression_ratio": 1.8372093023255813, "no_speech_prob": 0.00154876708984375, "words": [ { "start": 693.6, "end": 693.82, "word": " to", "probability": 0.9111328125 }, { "start": 693.82, "end": 694.48, "word": " understand", "probability": 0.75830078125 }, { "start": 694.48, "end": 695.08, "word": " machine", "probability": 0.65673828125 }, { "start": 695.08, "end": 695.4, "word": " learning", "probability": 0.84765625 } ] }, { "id": 285, "seek": 71570, "start": 695.4, "end": 696.58, "text": " from a security standpoint", "tokens": [ 50764, 490, 257, 3825, 15827, 50814 ], "temperature": 0.0, "avg_logprob": -0.2011904761904762, "compression_ratio": 1.8372093023255813, "no_speech_prob": 0.00154876708984375, "words": [ { "start": 695.4, "end": 695.64, "word": " from", "probability": 0.814453125 }, { "start": 695.76, "end": 696.14, "word": " a security", "probability": 0.92333984375 }, { "start": 696.14, "end": 696.58, "word": " standpoint", "probability": 0.78955078125 } ] }, { "id": 286, "seek": 71570, "start": 696.58, "end": 699.22, "text": " or in the hacking community?", "tokens": [ 50864, 420, 294, 264, 31422, 1768, 30, 50914 ], "temperature": 0.0, "avg_logprob": -0.2011904761904762, "compression_ratio": 1.8372093023255813, "no_speech_prob": 0.00154876708984375, "words": [ { "start": 696.58, "end": 697.2, "word": " or", "probability": 0.65625 }, { "start": 697.2, "end": 697.68, "word": " in", "probability": 0.900390625 }, { "start": 697.68, "end": 697.78, "word": " the", "probability": 0.810546875 }, { "start": 697.78, "end": 698.0, "word": " hacking", "probability": 0.66357421875 }, { "start": 698.0, "end": 698.56, "word": " community", "probability": 0.79541015625 }, { "start": 698.56, "end": 699.22, "word": "?", "probability": 0.019073486328125 } ] }, { "id": 287, "seek": 71570, "start": 706.49, "end": 708.33, "text": " I see on the Twitch chat,", "tokens": [ 50964, 286, 536, 322, 264, 22222, 5081, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.2011904761904762, "compression_ratio": 1.8372093023255813, "no_speech_prob": 0.00154876708984375, "words": [ { "start": 706.49, "end": 707.15, "word": " I", "probability": 0.68896484375 }, { "start": 707.15, "end": 707.27, "word": " see", "probability": 0.7626953125 }, { "start": 707.27, "end": 707.39, "word": " on", "probability": 0.8544921875 }, { "start": 707.39, "end": 707.53, "word": " the", "probability": 0.81396484375 }, { "start": 707.53, "end": 707.79, "word": " Twitch", "probability": 0.720703125 }, { "start": 707.79, "end": 708.17, "word": " chat", "probability": 0.7900390625 }, { "start": 708.17, "end": 708.33, "word": ",", "probability": 0.350830078125 } ] }, { "id": 288, "seek": 71570, "start": 708.33, "end": 709.25, "text": " reinforcement learning,", "tokens": [ 51064, 29280, 2539, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.2011904761904762, "compression_ratio": 1.8372093023255813, "no_speech_prob": 0.00154876708984375, "words": [ { "start": 708.33, "end": 708.69, "word": " reinforcement", "probability": 0.638671875 }, { "start": 708.69, "end": 709.09, "word": " learning", "probability": 0.8232421875 }, { "start": 709.09, "end": 709.25, "word": ",", "probability": 0.86328125 } ] }, { "id": 289, "seek": 71570, "start": 709.25, "end": 710.67, "text": " reinforcement learning, self-learning,", "tokens": [ 51164, 29280, 2539, 11, 2698, 12, 47204, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.2011904761904762, "compression_ratio": 1.8372093023255813, "no_speech_prob": 0.00154876708984375, "words": [ { "start": 709.25, "end": 709.51, "word": " reinforcement", "probability": 0.86962890625 }, { "start": 709.51, "end": 709.89, "word": " learning", "probability": 0.81689453125 }, { "start": 709.89, "end": 709.99, "word": ",", "probability": 0.8984375 }, { "start": 709.99, "end": 710.17, "word": " self", "probability": 0.81982421875 }, { "start": 710.17, "end": 710.45, "word": "-learning", "probability": 0.743408203125 }, { "start": 710.45, "end": 710.67, "word": ",", "probability": 0.8447265625 } ] }, { "id": 290, "seek": 71570, "start": 710.67, "end": 712.29, "text": " contextual regret minimization,", "tokens": [ 51264, 35526, 10879, 4464, 2144, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.2011904761904762, "compression_ratio": 1.8372093023255813, "no_speech_prob": 0.00154876708984375, "words": [ { "start": 710.67, "end": 710.97, "word": " contextual", "probability": 0.86474609375 }, { "start": 710.97, "end": 711.49, "word": " regret", "probability": 0.673828125 }, { "start": 711.49, "end": 712.09, "word": " minimization", "probability": 0.8046875 }, { "start": 712.09, "end": 712.29, "word": ",", "probability": 0.59423828125 } ] }, { "id": 291, "seek": 71570, "start": 712.29, "end": 714.11, "text": " what differences between them?", "tokens": [ 51364, 437, 7300, 1296, 552, 30, 51414 ], "temperature": 0.0, "avg_logprob": -0.2011904761904762, "compression_ratio": 1.8372093023255813, "no_speech_prob": 0.00154876708984375, "words": [ { "start": 712.29, "end": 712.39, "word": " what", "probability": 0.80810546875 }, { "start": 712.39, "end": 712.73, "word": " differences", "probability": 0.58349609375 }, { "start": 712.73, "end": 713.21, "word": " between", "probability": 0.75341796875 }, { "start": 713.21, "end": 713.45, "word": " them", "probability": 0.67041015625 }, { "start": 713.45, "end": 714.11, "word": "?", "probability": 0.80810546875 } ] }, { "id": 292, "seek": 71570, "start": 714.41, "end": 717.21, "text": " I'm not familiar with counterfactual,", "tokens": [ 51464, 286, 478, 406, 4963, 365, 5682, 44919, 901, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.2011904761904762, "compression_ratio": 1.8372093023255813, "no_speech_prob": 0.00154876708984375, "words": [ { "start": 714.41, "end": 714.63, "word": " I'm", "probability": 0.990234375 }, { "start": 714.63, "end": 714.83, "word": " not", "probability": 0.89013671875 }, { "start": 714.83, "end": 715.23, "word": " familiar", "probability": 0.82177734375 }, { "start": 715.23, "end": 715.93, "word": " with", "probability": 0.798828125 }, { "start": 715.93, "end": 717.17, "word": " counterfactual", "probability": 0.7294921875 }, { "start": 717.17, "end": 717.21, "word": ",", "probability": 0.58984375 } ] }, { "id": 293, "seek": 71570, "start": 717.21, "end": 718.85, "text": " not familiar with counterfactual", "tokens": [ 51564, 406, 4963, 365, 5682, 44919, 901, 51614 ], "temperature": 0.0, "avg_logprob": -0.2011904761904762, "compression_ratio": 1.8372093023255813, "no_speech_prob": 0.00154876708984375, "words": [ { "start": 717.21, "end": 717.65, "word": " not", "probability": 0.736328125 }, { "start": 717.65, "end": 717.89, "word": " familiar", "probability": 0.84228515625 }, { "start": 717.89, "end": 718.07, "word": " with", "probability": 0.8017578125 }, { "start": 718.07, "end": 718.85, "word": " counterfactual", "probability": 0.90771484375 } ] }, { "id": 294, "seek": 71570, "start": 718.85, "end": 720.81, "text": " regret minimization,", "tokens": [ 51664, 10879, 4464, 2144, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.2011904761904762, "compression_ratio": 1.8372093023255813, "no_speech_prob": 0.00154876708984375, "words": [ { "start": 718.85, "end": 719.37, "word": " regret", "probability": 0.84326171875 }, { "start": 719.37, "end": 720.01, "word": " minimization", "probability": 0.956787109375 }, { "start": 720.01, "end": 720.81, "word": ",", "probability": 0.765625 } ] }, { "id": 295, "seek": 74406, "start": 720.81, "end": 724.91, "text": " but typically you'll see", "tokens": [ 50364, 457, 5850, 291, 603, 536, 50614 ], "temperature": 0.0, "avg_logprob": -0.17264093064209995, "compression_ratio": 1.8450704225352113, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 720.81, "end": 721.05, "word": " but", "probability": 0.2763671875 }, { "start": 721.05, "end": 723.71, "word": " typically", "probability": 0.79736328125 }, { "start": 723.71, "end": 724.37, "word": " you'll", "probability": 0.825927734375 }, { "start": 724.37, "end": 724.91, "word": " see", "probability": 0.81103515625 } ] }, { "id": 296, "seek": 74406, "start": 726.43, "end": 727.97, "text": " three types of machine learning.", "tokens": [ 50664, 1045, 3467, 295, 3479, 2539, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.17264093064209995, "compression_ratio": 1.8450704225352113, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 726.43, "end": 726.95, "word": " three", "probability": 0.8095703125 }, { "start": 726.95, "end": 727.21, "word": " types", "probability": 0.75048828125 }, { "start": 727.21, "end": 727.35, "word": " of", "probability": 0.90625 }, { "start": 727.35, "end": 727.59, "word": " machine", "probability": 0.7060546875 }, { "start": 727.59, "end": 727.83, "word": " learning", "probability": 0.84228515625 }, { "start": 727.83, "end": 727.97, "word": ".", "probability": 0.78125 } ] }, { "id": 297, "seek": 74406, "start": 727.97, "end": 729.45, "text": " You'll see classification", "tokens": [ 50764, 509, 603, 536, 21538, 50814 ], "temperature": 0.0, "avg_logprob": -0.17264093064209995, "compression_ratio": 1.8450704225352113, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 727.97, "end": 728.01, "word": " You'll", "probability": 0.923095703125 }, { "start": 728.01, "end": 728.37, "word": " see", "probability": 0.82470703125 }, { "start": 728.37, "end": 729.45, "word": " classification", "probability": 0.80859375 } ] }, { "id": 298, "seek": 74406, "start": 729.45, "end": 730.91, "text": " or supervised learning,", "tokens": [ 50864, 420, 46533, 2539, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.17264093064209995, "compression_ratio": 1.8450704225352113, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 729.45, "end": 729.83, "word": " or", "probability": 0.84765625 }, { "start": 729.83, "end": 730.21, "word": " supervised", "probability": 0.7431640625 }, { "start": 730.21, "end": 730.77, "word": " learning", "probability": 0.84912109375 }, { "start": 730.77, "end": 730.91, "word": ",", "probability": 0.75390625 } ] }, { "id": 299, "seek": 74406, "start": 730.91, "end": 732.49, "text": " which is what we're going to be covering.", "tokens": [ 50964, 597, 307, 437, 321, 434, 516, 281, 312, 10322, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.17264093064209995, "compression_ratio": 1.8450704225352113, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 730.91, "end": 731.29, "word": " which", "probability": 0.9140625 }, { "start": 731.29, "end": 731.41, "word": " is", "probability": 0.90673828125 }, { "start": 731.41, "end": 731.53, "word": " what", "probability": 0.88671875 }, { "start": 731.53, "end": 731.71, "word": " we're", "probability": 0.928466796875 }, { "start": 731.71, "end": 731.79, "word": " going", "probability": 0.332275390625 }, { "start": 731.79, "end": 731.83, "word": " to", "probability": 0.9033203125 }, { "start": 731.83, "end": 731.97, "word": " be", "probability": 0.90625 }, { "start": 731.97, "end": 732.25, "word": " covering", "probability": 0.81982421875 }, { "start": 732.25, "end": 732.49, "word": ".", "probability": 0.93603515625 } ] }, { "id": 300, "seek": 74406, "start": 732.49, "end": 734.35, "text": " You'll see unsupervised learning,", "tokens": [ 51064, 509, 603, 536, 2693, 12879, 24420, 2539, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.17264093064209995, "compression_ratio": 1.8450704225352113, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 732.49, "end": 732.69, "word": " You'll", "probability": 0.918701171875 }, { "start": 732.69, "end": 732.93, "word": " see", "probability": 0.82666015625 }, { "start": 732.93, "end": 733.69, "word": " unsupervised", "probability": 0.9041341145833334 }, { "start": 733.69, "end": 734.11, "word": " learning", "probability": 0.837890625 }, { "start": 734.11, "end": 734.35, "word": ",", "probability": 0.90185546875 } ] }, { "id": 301, "seek": 74406, "start": 734.35, "end": 737.43, "text": " which is very good for data exploration.", "tokens": [ 51164, 597, 307, 588, 665, 337, 1412, 16197, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.17264093064209995, "compression_ratio": 1.8450704225352113, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 734.35, "end": 734.77, "word": " which", "probability": 0.90966796875 }, { "start": 734.77, "end": 735.03, "word": " is", "probability": 0.90673828125 }, { "start": 735.03, "end": 735.45, "word": " very", "probability": 0.623046875 }, { "start": 735.45, "end": 735.63, "word": " good", "probability": 0.8828125 }, { "start": 735.63, "end": 735.85, "word": " for", "probability": 0.89208984375 }, { "start": 735.85, "end": 736.27, "word": " data", "probability": 0.2342529296875 }, { "start": 736.27, "end": 736.91, "word": " exploration", "probability": 0.779296875 }, { "start": 736.91, "end": 737.43, "word": ".", "probability": 0.60888671875 } ] }, { "id": 302, "seek": 74406, "start": 738.87, "end": 740.17, "text": " And unsupervised learning", "tokens": [ 51264, 400, 2693, 12879, 24420, 2539, 51314 ], "temperature": 0.0, "avg_logprob": -0.17264093064209995, "compression_ratio": 1.8450704225352113, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 738.87, "end": 739.39, "word": " And", "probability": 0.73095703125 }, { "start": 739.39, "end": 739.91, "word": " unsupervised", "probability": 0.9033203125 }, { "start": 739.91, "end": 740.17, "word": " learning", "probability": 0.83251953125 } ] }, { "id": 303, "seek": 74406, "start": 740.17, "end": 741.99, "text": " uses a whole different set of algorithms.", "tokens": [ 51364, 4960, 257, 1379, 819, 992, 295, 14642, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.17264093064209995, "compression_ratio": 1.8450704225352113, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 740.17, "end": 740.37, "word": " uses", "probability": 0.81591796875 }, { "start": 740.57, "end": 740.71, "word": " a whole", "probability": 0.81396484375 }, { "start": 740.71, "end": 740.97, "word": " different", "probability": 0.6806640625 }, { "start": 740.97, "end": 741.19, "word": " set", "probability": 0.8876953125 }, { "start": 741.19, "end": 741.31, "word": " of", "probability": 0.90380859375 }, { "start": 741.31, "end": 741.71, "word": " algorithms", "probability": 0.8818359375 }, { "start": 741.71, "end": 741.99, "word": ".", "probability": 0.70458984375 } ] }, { "id": 304, "seek": 74406, "start": 741.99, "end": 743.55, "text": " And then there's reinforcement learning,", "tokens": [ 51464, 400, 550, 456, 311, 29280, 2539, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.17264093064209995, "compression_ratio": 1.8450704225352113, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 741.99, "end": 742.05, "word": " And", "probability": 0.8798828125 }, { "start": 742.05, "end": 742.17, "word": " then", "probability": 0.7333984375 }, { "start": 742.17, "end": 742.33, "word": " there's", "probability": 0.921630859375 }, { "start": 742.33, "end": 742.85, "word": " reinforcement", "probability": 0.76513671875 }, { "start": 742.85, "end": 743.39, "word": " learning", "probability": 0.84521484375 }, { "start": 743.39, "end": 743.55, "word": ",", "probability": 0.51171875 } ] }, { "id": 305, "seek": 74406, "start": 743.55, "end": 746.87, "text": " where we embed in a model", "tokens": [ 51564, 689, 321, 12240, 294, 257, 2316, 51664 ], "temperature": 0.0, "avg_logprob": -0.17264093064209995, "compression_ratio": 1.8450704225352113, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 743.55, "end": 744.17, "word": " where", "probability": 0.90478515625 }, { "start": 744.17, "end": 744.81, "word": " we", "probability": 0.9013671875 }, { "start": 744.81, "end": 745.99, "word": " embed", "probability": 0.751953125 }, { "start": 745.99, "end": 746.35, "word": " in", "probability": 0.88818359375 }, { "start": 746.51, "end": 746.87, "word": " a model", "probability": 0.81201171875 } ] }, { "id": 306, "seek": 74406, "start": 746.87, "end": 749.17, "text": " different rewards and punishments", "tokens": [ 51714, 819, 17203, 293, 9842, 1117, 51764 ], "temperature": 0.0, "avg_logprob": -0.17264093064209995, "compression_ratio": 1.8450704225352113, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 746.87, "end": 747.69, "word": " different", "probability": 0.496826171875 }, { "start": 747.69, "end": 748.29, "word": " rewards", "probability": 0.697265625 }, { "start": 748.29, "end": 748.51, "word": " and", "probability": 0.8974609375 }, { "start": 748.51, "end": 749.17, "word": " punishments", "probability": 0.933837890625 } ] }, { "id": 307, "seek": 77222, "start": 749.17, "end": 752.41, "text": " based on how it's performing.", "tokens": [ 50364, 2361, 322, 577, 309, 311, 10205, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.20433858789286566, "compression_ratio": 1.508849557522124, "no_speech_prob": 0.00044417381286621094, "words": [ { "start": 749.17, "end": 749.79, "word": " based", "probability": 0.1431884765625 }, { "start": 749.79, "end": 750.11, "word": " on", "probability": 0.908203125 }, { "start": 750.11, "end": 750.33, "word": " how", "probability": 0.90673828125 }, { "start": 750.33, "end": 750.75, "word": " it's", "probability": 0.907470703125 }, { "start": 750.75, "end": 751.97, "word": " performing", "probability": 0.56591796875 }, { "start": 751.97, "end": 752.41, "word": ".", "probability": 0.775390625 } ] }, { "id": 308, "seek": 77222, "start": 752.69, "end": 753.77, "text": " And so these are all different ways", "tokens": [ 50514, 400, 370, 613, 366, 439, 819, 2098, 50564 ], "temperature": 0.0, "avg_logprob": -0.20433858789286566, "compression_ratio": 1.508849557522124, "no_speech_prob": 0.00044417381286621094, "words": [ { "start": 752.69, "end": 752.71, "word": " And", "probability": 0.42431640625 }, { "start": 752.71, "end": 752.83, "word": " so", "probability": 0.8857421875 }, { "start": 752.83, "end": 752.99, "word": " these", "probability": 0.62890625 }, { "start": 752.99, "end": 753.09, "word": " are", "probability": 0.88818359375 }, { "start": 753.09, "end": 753.19, "word": " all", "probability": 0.888671875 }, { "start": 753.19, "end": 753.43, "word": " different", "probability": 0.69775390625 }, { "start": 753.43, "end": 753.77, "word": " ways", "probability": 0.8134765625 } ] }, { "id": 309, "seek": 77222, "start": 753.77, "end": 754.87, "text": " of training the model,", "tokens": [ 50614, 295, 3097, 264, 2316, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.20433858789286566, "compression_ratio": 1.508849557522124, "no_speech_prob": 0.00044417381286621094, "words": [ { "start": 753.77, "end": 753.99, "word": " of", "probability": 0.8984375 }, { "start": 753.99, "end": 754.31, "word": " training", "probability": 0.79296875 }, { "start": 754.31, "end": 754.53, "word": " the", "probability": 0.81201171875 }, { "start": 754.53, "end": 754.75, "word": " model", "probability": 0.80908203125 }, { "start": 754.75, "end": 754.87, "word": ",", "probability": 0.31591796875 } ] }, { "id": 310, "seek": 77222, "start": 754.87, "end": 757.59, "text": " and then we can make decisions off of those.", "tokens": [ 50714, 293, 550, 321, 393, 652, 5327, 766, 295, 729, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.20433858789286566, "compression_ratio": 1.508849557522124, "no_speech_prob": 0.00044417381286621094, "words": [ { "start": 754.87, "end": 754.91, "word": " and", "probability": 0.87548828125 }, { "start": 754.91, "end": 755.01, "word": " then", "probability": 0.712890625 }, { "start": 755.01, "end": 755.11, "word": " we", "probability": 0.8974609375 }, { "start": 755.11, "end": 755.21, "word": " can", "probability": 0.79296875 }, { "start": 755.21, "end": 755.33, "word": " make", "probability": 0.8759765625 }, { "start": 755.33, "end": 755.83, "word": " decisions", "probability": 0.84765625 }, { "start": 755.83, "end": 756.59, "word": " off", "probability": 0.80712890625 }, { "start": 756.59, "end": 756.73, "word": " of", "probability": 0.900390625 }, { "start": 756.73, "end": 757.15, "word": " those", "probability": 0.8525390625 }, { "start": 757.15, "end": 757.59, "word": ".", "probability": 0.98876953125 } ] }, { "id": 311, "seek": 77222, "start": 759.83, "end": 762.49, "text": " Hey, Sven, are there any questions", "tokens": [ 50864, 1911, 11, 49787, 11, 366, 456, 604, 1651, 51014 ], "temperature": 0.0, "avg_logprob": -0.20433858789286566, "compression_ratio": 1.508849557522124, "no_speech_prob": 0.00044417381286621094, "words": [ { "start": 759.83, "end": 760.19, "word": " Hey", "probability": 0.5859375 }, { "start": 760.19, "end": 760.57, "word": ",", "probability": 0.482177734375 }, { "start": 760.57, "end": 761.43, "word": " Sven", "probability": 0.88623046875 }, { "start": 761.43, "end": 761.57, "word": ",", "probability": 0.904296875 }, { "start": 761.57, "end": 761.67, "word": " are", "probability": 0.87451171875 }, { "start": 761.67, "end": 761.81, "word": " there", "probability": 0.85205078125 }, { "start": 761.81, "end": 762.03, "word": " any", "probability": 0.8232421875 }, { "start": 762.03, "end": 762.49, "word": " questions", "probability": 0.90576171875 } ] }, { "id": 312, "seek": 77222, "start": 762.49, "end": 765.07, "text": " in the Discord chat before I move on?", "tokens": [ 51064, 294, 264, 32623, 5081, 949, 286, 1286, 322, 30, 51164 ], "temperature": 0.0, "avg_logprob": -0.20433858789286566, "compression_ratio": 1.508849557522124, "no_speech_prob": 0.00044417381286621094, "words": [ { "start": 762.49, "end": 762.91, "word": " in", "probability": 0.9072265625 }, { "start": 762.91, "end": 763.09, "word": " the", "probability": 0.8134765625 }, { "start": 763.09, "end": 763.43, "word": " Discord", "probability": 0.66259765625 }, { "start": 763.43, "end": 763.83, "word": " chat", "probability": 0.76904296875 }, { "start": 763.83, "end": 764.17, "word": " before", "probability": 0.60302734375 }, { "start": 764.17, "end": 764.33, "word": " I", "probability": 0.97998046875 }, { "start": 764.33, "end": 764.45, "word": " move", "probability": 0.87353515625 }, { "start": 764.45, "end": 764.63, "word": " on", "probability": 0.90869140625 }, { "start": 764.63, "end": 765.07, "word": "?", "probability": 0.9765625 } ] }, { "id": 313, "seek": 77222, "start": 775.84, "end": 777.78, "text": " Okay, I'm going to assume not.", "tokens": [ 51214, 1033, 11, 286, 478, 516, 281, 6552, 406, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.20433858789286566, "compression_ratio": 1.508849557522124, "no_speech_prob": 0.00044417381286621094, "words": [ { "start": 775.84, "end": 776.26, "word": " Okay", "probability": 0.65185546875 }, { "start": 776.26, "end": 776.44, "word": ",", "probability": 0.78662109375 }, { "start": 776.44, "end": 776.68, "word": " I'm", "probability": 0.998046875 }, { "start": 776.68, "end": 776.76, "word": " going", "probability": 0.380126953125 }, { "start": 776.76, "end": 776.84, "word": " to", "probability": 0.91162109375 }, { "start": 776.84, "end": 777.1, "word": " assume", "probability": 0.82763671875 }, { "start": 777.1, "end": 777.34, "word": " not", "probability": 0.8154296875 }, { "start": 777.34, "end": 777.78, "word": ".", "probability": 0.9951171875 } ] }, { "id": 314, "seek": 77222, "start": 779.48, "end": 782.62, "text": " So before we look at a full spam filter,", "tokens": [ 51414, 407, 949, 321, 574, 412, 257, 1577, 24028, 6608, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.20433858789286566, "compression_ratio": 1.508849557522124, "no_speech_prob": 0.00044417381286621094, "words": [ { "start": 779.48, "end": 779.92, "word": " So", "probability": 0.873046875 }, { "start": 779.92, "end": 780.1, "word": " before", "probability": 0.7373046875 }, { "start": 780.1, "end": 780.28, "word": " we", "probability": 0.90087890625 }, { "start": 780.28, "end": 780.46, "word": " look", "probability": 0.91162109375 }, { "start": 780.46, "end": 780.76, "word": " at", "probability": 0.90283203125 }, { "start": 781.28, "end": 781.64, "word": " a full", "probability": 0.82373046875 }, { "start": 781.64, "end": 782.18, "word": " spam", "probability": 0.88623046875 }, { "start": 782.18, "end": 782.52, "word": " filter", "probability": 0.91748046875 }, { "start": 782.52, "end": 782.62, "word": ",", "probability": 0.9580078125 } ] }, { "id": 315, "seek": 77222, "start": 782.62, "end": 784.74, "text": " we want to kind of look at a smaller example.", "tokens": [ 51614, 321, 528, 281, 733, 295, 574, 412, 257, 4356, 1365, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.20433858789286566, "compression_ratio": 1.508849557522124, "no_speech_prob": 0.00044417381286621094, "words": [ { "start": 782.62, "end": 782.72, "word": " we", "probability": 0.90087890625 }, { "start": 782.72, "end": 782.84, "word": " want", "probability": 0.79443359375 }, { "start": 782.84, "end": 782.92, "word": " to", "probability": 0.9033203125 }, { "start": 782.92, "end": 783.08, "word": " kind", "probability": 0.66455078125 }, { "start": 783.08, "end": 783.18, "word": " of", "probability": 0.90673828125 }, { "start": 783.18, "end": 783.42, "word": " look", "probability": 0.9150390625 }, { "start": 783.42, "end": 783.5, "word": " at", "probability": 0.90673828125 }, { "start": 783.62, "end": 783.88, "word": " a smaller", "probability": 0.73193359375 }, { "start": 783.88, "end": 784.3, "word": " example", "probability": 0.923828125 }, { "start": 784.3, "end": 784.74, "word": ".", "probability": 0.99609375 } ] }, { "id": 316, "seek": 77222, "start": 784.88, "end": 786.0, "text": " So in this case,", "tokens": [ 51714, 407, 294, 341, 1389, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.20433858789286566, "compression_ratio": 1.508849557522124, "no_speech_prob": 0.00044417381286621094, "words": [ { "start": 784.88, "end": 785.24, "word": " So", "probability": 0.87744140625 }, { "start": 785.24, "end": 785.48, "word": " in", "probability": 0.84228515625 }, { "start": 785.48, "end": 785.68, "word": " this", "probability": 0.87646484375 }, { "start": 785.68, "end": 785.96, "word": " case", "probability": 0.8095703125 }, { "start": 785.96, "end": 786.0, "word": ",", "probability": 0.841796875 } ] }, { "id": 317, "seek": 79800, "start": 786.0, "end": 787.2, "text": " we have a series of sentences", "tokens": [ 50364, 321, 362, 257, 2638, 295, 16579, 50414 ], "temperature": 0.0, "avg_logprob": -0.20542278915059334, "compression_ratio": 1.5485436893203883, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 786.0, "end": 786.14, "word": " we", "probability": 0.52587890625 }, { "start": 786.14, "end": 786.44, "word": " have", "probability": 0.87841796875 }, { "start": 786.58, "end": 786.74, "word": " a series", "probability": 0.82763671875 }, { "start": 786.74, "end": 786.9, "word": " of", "probability": 0.90478515625 }, { "start": 786.9, "end": 787.2, "word": " sentences", "probability": 0.869140625 } ] }, { "id": 318, "seek": 79800, "start": 787.2, "end": 790.02, "text": " talking about sports or not sports,", "tokens": [ 50464, 1417, 466, 6573, 420, 406, 6573, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.20542278915059334, "compression_ratio": 1.5485436893203883, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 787.2, "end": 787.54, "word": " talking", "probability": 0.7421875 }, { "start": 787.54, "end": 787.8, "word": " about", "probability": 0.8193359375 }, { "start": 787.8, "end": 788.3, "word": " sports", "probability": 0.7607421875 }, { "start": 788.3, "end": 788.76, "word": " or", "probability": 0.8271484375 }, { "start": 788.76, "end": 789.32, "word": " not", "probability": 0.87353515625 }, { "start": 789.32, "end": 789.8, "word": " sports", "probability": 0.779296875 }, { "start": 789.8, "end": 790.02, "word": ",", "probability": 0.78857421875 } ] }, { "id": 319, "seek": 79800, "start": 790.02, "end": 791.8, "text": " which are really elections.", "tokens": [ 50564, 597, 366, 534, 12870, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.20542278915059334, "compression_ratio": 1.5485436893203883, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 790.02, "end": 790.22, "word": " which", "probability": 0.92431640625 }, { "start": 790.22, "end": 790.38, "word": " are", "probability": 0.89794921875 }, { "start": 790.38, "end": 790.9, "word": " really", "probability": 0.7646484375 }, { "start": 790.9, "end": 791.36, "word": " elections", "probability": 0.81396484375 }, { "start": 791.36, "end": 791.8, "word": ".", "probability": 0.978515625 } ] }, { "id": 320, "seek": 79800, "start": 792.26, "end": 793.98, "text": " So here we have a couple sentences.", "tokens": [ 50664, 407, 510, 321, 362, 257, 1916, 16579, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.20542278915059334, "compression_ratio": 1.5485436893203883, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 792.26, "end": 792.56, "word": " So", "probability": 0.81884765625 }, { "start": 792.56, "end": 792.7, "word": " here", "probability": 0.76025390625 }, { "start": 792.7, "end": 792.82, "word": " we", "probability": 0.8583984375 }, { "start": 792.82, "end": 792.98, "word": " have", "probability": 0.87939453125 }, { "start": 793.14, "end": 793.32, "word": " a couple", "probability": 0.79443359375 }, { "start": 793.32, "end": 793.74, "word": " sentences", "probability": 0.5869140625 }, { "start": 793.74, "end": 793.98, "word": ".", "probability": 0.374267578125 } ] }, { "id": 321, "seek": 79800, "start": 793.98, "end": 794.92, "text": " A, great games.", "tokens": [ 50764, 316, 11, 869, 2813, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.20542278915059334, "compression_ratio": 1.5485436893203883, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 793.98, "end": 794.04, "word": " A", "probability": 0.6416015625 }, { "start": 794.04, "end": 794.12, "word": ",", "probability": 0.330810546875 }, { "start": 794.12, "end": 794.3, "word": " great", "probability": 0.72119140625 }, { "start": 794.3, "end": 794.72, "word": " games", "probability": 0.71240234375 }, { "start": 794.72, "end": 794.92, "word": ".", "probability": 0.4873046875 } ] }, { "id": 322, "seek": 79800, "start": 795.1, "end": 796.76, "text": " Sorry. Yes.", "tokens": [ 50864, 4919, 13, 1079, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.20542278915059334, "compression_ratio": 1.5485436893203883, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 795.1, "end": 795.54, "word": " Sorry", "probability": 0.330078125 }, { "start": 795.54, "end": 795.98, "word": ".", "probability": 0.82958984375 }, { "start": 796.06, "end": 796.32, "word": " Yes", "probability": 0.8720703125 }, { "start": 796.32, "end": 796.76, "word": ".", "probability": 0.8427734375 } ] }, { "id": 323, "seek": 79800, "start": 798.26, "end": 800.42, "text": " Well, I think you got this one.", "tokens": [ 50964, 1042, 11, 286, 519, 291, 658, 341, 472, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.20542278915059334, "compression_ratio": 1.5485436893203883, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 798.26, "end": 798.7, "word": " Well", "probability": 0.6171875 }, { "start": 798.7, "end": 798.74, "word": ",", "probability": 0.92919921875 }, { "start": 798.74, "end": 798.84, "word": " I", "probability": 0.9990234375 }, { "start": 798.84, "end": 799.0, "word": " think", "probability": 0.810546875 }, { "start": 799.0, "end": 799.12, "word": " you", "probability": 0.89599609375 }, { "start": 799.12, "end": 799.3, "word": " got", "probability": 0.82080078125 }, { "start": 799.3, "end": 799.48, "word": " this", "probability": 0.88037109375 }, { "start": 799.48, "end": 799.98, "word": " one", "probability": 0.82666015625 }, { "start": 799.98, "end": 800.42, "word": ".", "probability": 0.75439453125 } ] }, { "id": 324, "seek": 79800, "start": 801.34, "end": 803.2, "text": " But there was a question from Norwin.", "tokens": [ 51114, 583, 456, 390, 257, 1168, 490, 6966, 9136, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.20542278915059334, "compression_ratio": 1.5485436893203883, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 801.34, "end": 801.78, "word": " But", "probability": 0.81103515625 }, { "start": 801.78, "end": 801.98, "word": " there", "probability": 0.72998046875 }, { "start": 801.98, "end": 802.1, "word": " was", "probability": 0.8974609375 }, { "start": 802.22, "end": 802.56, "word": " a question", "probability": 0.64111328125 }, { "start": 802.56, "end": 802.8, "word": " from", "probability": 0.81884765625 }, { "start": 802.8, "end": 803.1, "word": " Norwin", "probability": 0.4615478515625 }, { "start": 803.1, "end": 803.2, "word": ".", "probability": 0.8173828125 } ] }, { "id": 325, "seek": 79800, "start": 803.2, "end": 804.68, "text": " I fell asleep on the job.", "tokens": [ 51264, 286, 5696, 11039, 322, 264, 1691, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.20542278915059334, "compression_ratio": 1.5485436893203883, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 803.2, "end": 803.38, "word": " I", "probability": 0.953125 }, { "start": 803.38, "end": 803.54, "word": " fell", "probability": 0.81396484375 }, { "start": 803.54, "end": 803.76, "word": " asleep", "probability": 0.791015625 }, { "start": 803.76, "end": 803.88, "word": " on", "probability": 0.8857421875 }, { "start": 803.88, "end": 804.0, "word": " the", "probability": 0.81396484375 }, { "start": 804.0, "end": 804.24, "word": " job", "probability": 0.85791015625 }, { "start": 804.24, "end": 804.68, "word": ".", "probability": 0.98681640625 } ] }, { "id": 326, "seek": 79800, "start": 806.34, "end": 807.66, "text": " No worries.", "tokens": [ 51364, 883, 16340, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.20542278915059334, "compression_ratio": 1.5485436893203883, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 806.34, "end": 806.78, "word": " No", "probability": 0.83349609375 }, { "start": 806.78, "end": 807.22, "word": " worries", "probability": 0.8701171875 }, { "start": 807.22, "end": 807.66, "word": ".", "probability": 0.9052734375 } ] }, { "id": 327, "seek": 79800, "start": 807.78, "end": 809.28, "text": " It has been a long weekend.", "tokens": [ 51464, 467, 575, 668, 257, 938, 6711, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.20542278915059334, "compression_ratio": 1.5485436893203883, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 807.78, "end": 807.96, "word": " It", "probability": 0.904296875 }, { "start": 807.96, "end": 808.08, "word": " has", "probability": 0.8681640625 }, { "start": 808.08, "end": 808.18, "word": " been", "probability": 0.818359375 }, { "start": 808.34, "end": 808.5, "word": " a long", "probability": 0.89697265625 }, { "start": 808.5, "end": 808.84, "word": " weekend", "probability": 0.81298828125 }, { "start": 808.84, "end": 809.28, "word": ".", "probability": 0.99609375 } ] }, { "id": 328, "seek": 79800, "start": 810.26, "end": 811.78, "text": " So what was the question?", "tokens": [ 51564, 407, 437, 390, 264, 1168, 30, 51614 ], "temperature": 0.0, "avg_logprob": -0.20542278915059334, "compression_ratio": 1.5485436893203883, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 810.26, "end": 810.7, "word": " So", "probability": 0.9013671875 }, { "start": 810.7, "end": 810.84, "word": " what", "probability": 0.8798828125 }, { "start": 810.84, "end": 810.94, "word": " was", "probability": 0.8994140625 }, { "start": 810.94, "end": 811.04, "word": " the", "probability": 0.8056640625 }, { "start": 811.04, "end": 811.34, "word": " question", "probability": 0.8046875 }, { "start": 811.34, "end": 811.78, "word": "?", "probability": 0.955078125 } ] }, { "id": 329, "seek": 82800, "start": 814.34, "end": 818.68, "text": " Norwin kindly repeated Glucorio's question.", "tokens": [ 50414, 6966, 9136, 29736, 10477, 5209, 1311, 284, 1004, 311, 1168, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.187650247118794, "compression_ratio": 1.7192118226600985, "no_speech_prob": 0.0084381103515625, "words": [ { "start": 814.34, "end": 814.86, "word": " Norwin", "probability": 0.06111627817153931 }, { "start": 814.86, "end": 815.14, "word": " kindly", "probability": 0.0809326171875 }, { "start": 815.14, "end": 816.5, "word": " repeated", "probability": 0.791015625 }, { "start": 816.5, "end": 817.78, "word": " Glucorio's", "probability": 0.78330078125 }, { "start": 817.78, "end": 818.16, "word": " question", "probability": 0.80078125 }, { "start": 818.16, "end": 818.68, "word": ".", "probability": 0.42529296875 } ] }, { "id": 330, "seek": 82800, "start": 820.2, "end": 822.06, "text": " So you already answered it.", "tokens": [ 50714, 407, 291, 1217, 10103, 309, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.187650247118794, "compression_ratio": 1.7192118226600985, "no_speech_prob": 0.0084381103515625, "words": [ { "start": 820.2, "end": 820.72, "word": " So", "probability": 0.68115234375 }, { "start": 820.72, "end": 820.92, "word": " you", "probability": 0.71044921875 }, { "start": 820.92, "end": 821.12, "word": " already", "probability": 0.79638671875 }, { "start": 821.12, "end": 821.42, "word": " answered", "probability": 0.681640625 }, { "start": 821.42, "end": 821.64, "word": " it", "probability": 0.89306640625 }, { "start": 821.64, "end": 822.06, "word": ".", "probability": 0.9482421875 } ] }, { "id": 331, "seek": 82800, "start": 822.06, "end": 823.32, "text": " Okay, okay.", "tokens": [ 50864, 1033, 11, 1392, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.187650247118794, "compression_ratio": 1.7192118226600985, "no_speech_prob": 0.0084381103515625, "words": [ { "start": 822.06, "end": 822.32, "word": " Okay", "probability": 0.435791015625 }, { "start": 822.32, "end": 822.48, "word": ",", "probability": 0.486572265625 }, { "start": 822.48, "end": 822.8, "word": " okay", "probability": 0.72998046875 }, { "start": 822.8, "end": 823.32, "word": ".", "probability": 0.89111328125 } ] }, { "id": 332, "seek": 82800, "start": 825.0, "end": 826.3, "text": " So kind of going back,", "tokens": [ 50964, 407, 733, 295, 516, 646, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.187650247118794, "compression_ratio": 1.7192118226600985, "no_speech_prob": 0.0084381103515625, "words": [ { "start": 825.0, "end": 825.52, "word": " So", "probability": 0.7705078125 }, { "start": 825.52, "end": 825.68, "word": " kind", "probability": 0.51904296875 }, { "start": 825.68, "end": 825.72, "word": " of", "probability": 0.90576171875 }, { "start": 825.72, "end": 825.9, "word": " going", "probability": 0.8525390625 }, { "start": 825.9, "end": 826.14, "word": " back", "probability": 0.814453125 }, { "start": 826.14, "end": 826.3, "word": ",", "probability": 0.642578125 } ] }, { "id": 333, "seek": 82800, "start": 826.3, "end": 827.82, "text": " we have a great game,", "tokens": [ 51064, 321, 362, 257, 869, 1216, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.187650247118794, "compression_ratio": 1.7192118226600985, "no_speech_prob": 0.0084381103515625, "words": [ { "start": 826.3, "end": 826.4, "word": " we", "probability": 0.888671875 }, { "start": 826.4, "end": 826.82, "word": " have", "probability": 0.8037109375 }, { "start": 827.06, "end": 827.32, "word": " a great", "probability": 0.239990234375 }, { "start": 827.32, "end": 827.68, "word": " game", "probability": 0.84375 }, { "start": 827.68, "end": 827.82, "word": ",", "probability": 0.53662109375 } ] }, { "id": 334, "seek": 82800, "start": 827.82, "end": 829.26, "text": " which is talking about sports.", "tokens": [ 51164, 597, 307, 1417, 466, 6573, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.187650247118794, "compression_ratio": 1.7192118226600985, "no_speech_prob": 0.0084381103515625, "words": [ { "start": 827.82, "end": 827.98, "word": " which", "probability": 0.91552734375 }, { "start": 827.98, "end": 828.08, "word": " is", "probability": 0.896484375 }, { "start": 828.08, "end": 828.32, "word": " talking", "probability": 0.76904296875 }, { "start": 828.32, "end": 828.52, "word": " about", "probability": 0.81005859375 }, { "start": 828.52, "end": 828.94, "word": " sports", "probability": 0.7705078125 }, { "start": 828.94, "end": 829.26, "word": ".", "probability": 0.75244140625 } ] }, { "id": 335, "seek": 82800, "start": 829.26, "end": 830.8, "text": " We have the election was over,", "tokens": [ 51264, 492, 362, 264, 6618, 390, 670, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.187650247118794, "compression_ratio": 1.7192118226600985, "no_speech_prob": 0.0084381103515625, "words": [ { "start": 829.26, "end": 829.6, "word": " We", "probability": 0.89208984375 }, { "start": 829.6, "end": 829.82, "word": " have", "probability": 0.880859375 }, { "start": 829.82, "end": 829.92, "word": " the", "probability": 0.4375 }, { "start": 829.92, "end": 830.18, "word": " election", "probability": 0.85498046875 }, { "start": 830.18, "end": 830.4, "word": " was", "probability": 0.8828125 }, { "start": 830.4, "end": 830.66, "word": " over", "probability": 0.8828125 }, { "start": 830.66, "end": 830.8, "word": ",", "probability": 0.8974609375 } ] }, { "id": 336, "seek": 82800, "start": 830.8, "end": 833.2, "text": " which is talking about not sports.", "tokens": [ 51364, 597, 307, 1417, 466, 406, 6573, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.187650247118794, "compression_ratio": 1.7192118226600985, "no_speech_prob": 0.0084381103515625, "words": [ { "start": 830.8, "end": 830.92, "word": " which", "probability": 0.916015625 }, { "start": 830.92, "end": 831.06, "word": " is", "probability": 0.890625 }, { "start": 831.06, "end": 831.28, "word": " talking", "probability": 0.76416015625 }, { "start": 831.28, "end": 831.66, "word": " about", "probability": 0.830078125 }, { "start": 831.66, "end": 832.2, "word": " not", "probability": 0.2841796875 }, { "start": 832.2, "end": 832.68, "word": " sports", "probability": 0.7685546875 }, { "start": 832.68, "end": 833.2, "word": ".", "probability": 0.771484375 } ] }, { "id": 337, "seek": 82800, "start": 833.24, "end": 835.68, "text": " Very clean match, talking about sports.", "tokens": [ 51464, 4372, 2541, 2995, 11, 1417, 466, 6573, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.187650247118794, "compression_ratio": 1.7192118226600985, "no_speech_prob": 0.0084381103515625, "words": [ { "start": 833.24, "end": 833.52, "word": " Very", "probability": 0.79248046875 }, { "start": 833.52, "end": 833.78, "word": " clean", "probability": 0.79638671875 }, { "start": 833.78, "end": 834.18, "word": " match", "probability": 0.7841796875 }, { "start": 834.18, "end": 834.36, "word": ",", "probability": 0.68359375 }, { "start": 834.36, "end": 834.6, "word": " talking", "probability": 0.75048828125 }, { "start": 834.6, "end": 834.8, "word": " about", "probability": 0.8125 }, { "start": 834.8, "end": 835.28, "word": " sports", "probability": 0.77734375 }, { "start": 835.28, "end": 835.68, "word": ".", "probability": 0.7978515625 } ] }, { "id": 338, "seek": 82800, "start": 835.68, "end": 837.14, "text": " Clean but forgettable game,", "tokens": [ 51564, 18463, 457, 2870, 23811, 1216, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.187650247118794, "compression_ratio": 1.7192118226600985, "no_speech_prob": 0.0084381103515625, "words": [ { "start": 835.68, "end": 835.92, "word": " Clean", "probability": 0.80908203125 }, { "start": 835.92, "end": 836.06, "word": " but", "probability": 0.72802734375 }, { "start": 836.06, "end": 836.48, "word": " forgettable", "probability": 0.839599609375 }, { "start": 836.48, "end": 836.86, "word": " game", "probability": 0.81103515625 }, { "start": 836.86, "end": 837.14, "word": ",", "probability": 0.90673828125 } ] }, { "id": 339, "seek": 82800, "start": 837.14, "end": 838.4, "text": " talking about sports.", "tokens": [ 51664, 1417, 466, 6573, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.187650247118794, "compression_ratio": 1.7192118226600985, "no_speech_prob": 0.0084381103515625, "words": [ { "start": 837.14, "end": 837.44, "word": " talking", "probability": 0.75830078125 }, { "start": 837.44, "end": 837.62, "word": " about", "probability": 0.8173828125 }, { "start": 837.62, "end": 837.98, "word": " sports", "probability": 0.75634765625 }, { "start": 837.98, "end": 838.4, "word": ".", "probability": 0.99560546875 } ] }, { "id": 340, "seek": 82800, "start": 838.4, "end": 840.58, "text": " So if we wanted to take this idea", "tokens": [ 51764, 407, 498, 321, 1415, 281, 747, 341, 1558, 51814 ], "temperature": 0.0, "avg_logprob": -0.187650247118794, "compression_ratio": 1.7192118226600985, "no_speech_prob": 0.0084381103515625, "words": [ { "start": 838.4, "end": 838.76, "word": " So", "probability": 0.8916015625 }, { "start": 838.76, "end": 838.96, "word": " if", "probability": 0.86572265625 }, { "start": 838.96, "end": 839.04, "word": " we", "probability": 0.8994140625 }, { "start": 839.04, "end": 839.24, "word": " wanted", "probability": 0.7568359375 }, { "start": 839.24, "end": 839.7, "word": " to", "probability": 0.90185546875 }, { "start": 839.7, "end": 840.1, "word": " take", "probability": 0.80615234375 }, { "start": 840.1, "end": 840.26, "word": " this", "probability": 0.88232421875 }, { "start": 840.26, "end": 840.58, "word": " idea", "probability": 0.77490234375 } ] }, { "id": 341, "seek": 85526, "start": 841.78, "end": 842.3, "text": " and specify a sentence", "tokens": [ 50364, 293, 16500, 257, 8174, 50414 ], "temperature": 0.0, "avg_logprob": -0.15073528810709463, "compression_ratio": 1.8169642857142858, "no_speech_prob": 0.0013456344604492188, "words": [ { "start": 841.78, "end": 841.9, "word": " and", "probability": 0.013153076171875 }, { "start": 841.9, "end": 841.9, "word": " specify", "probability": 0.07733154296875 }, { "start": 842.12, "end": 842.3, "word": " a sentence", "probability": 0.8310546875 } ] }, { "id": 342, "seek": 85526, "start": 842.3, "end": 843.64, "text": " that we've never seen before", "tokens": [ 50464, 300, 321, 600, 1128, 1612, 949, 50514 ], "temperature": 0.0, "avg_logprob": -0.15073528810709463, "compression_ratio": 1.8169642857142858, "no_speech_prob": 0.0013456344604492188, "words": [ { "start": 842.3, "end": 842.44, "word": " that", "probability": 0.71630859375 }, { "start": 842.44, "end": 842.62, "word": " we've", "probability": 0.878173828125 }, { "start": 842.62, "end": 842.94, "word": " never", "probability": 0.85205078125 }, { "start": 842.94, "end": 843.24, "word": " seen", "probability": 0.88427734375 }, { "start": 843.24, "end": 843.64, "word": " before", "probability": 0.8037109375 } ] }, { "id": 343, "seek": 85526, "start": 843.64, "end": 846.5, "text": " about sports and not sports,", "tokens": [ 50564, 466, 6573, 293, 406, 6573, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.15073528810709463, "compression_ratio": 1.8169642857142858, "no_speech_prob": 0.0013456344604492188, "words": [ { "start": 843.64, "end": 844.36, "word": " about", "probability": 0.6689453125 }, { "start": 844.36, "end": 844.9, "word": " sports", "probability": 0.716796875 }, { "start": 844.9, "end": 845.14, "word": " and", "probability": 0.84765625 }, { "start": 845.14, "end": 845.36, "word": " not", "probability": 0.810546875 }, { "start": 845.36, "end": 845.88, "word": " sports", "probability": 0.73046875 }, { "start": 845.88, "end": 846.5, "word": ",", "probability": 0.54833984375 } ] }, { "id": 344, "seek": 85526, "start": 846.5, "end": 848.5, "text": " how would we do this?", "tokens": [ 50664, 577, 576, 321, 360, 341, 30, 50714 ], "temperature": 0.0, "avg_logprob": -0.15073528810709463, "compression_ratio": 1.8169642857142858, "no_speech_prob": 0.0013456344604492188, "words": [ { "start": 846.5, "end": 846.76, "word": " how", "probability": 0.86083984375 }, { "start": 846.76, "end": 847.46, "word": " would", "probability": 0.80859375 }, { "start": 847.46, "end": 847.58, "word": " we", "probability": 0.90283203125 }, { "start": 847.58, "end": 847.7, "word": " do", "probability": 0.90087890625 }, { "start": 847.7, "end": 847.98, "word": " this", "probability": 0.87890625 }, { "start": 847.98, "end": 848.5, "word": "?", "probability": 0.98828125 } ] }, { "id": 345, "seek": 85526, "start": 848.7, "end": 851.64, "text": " We would want to look at keywords.", "tokens": [ 50764, 492, 576, 528, 281, 574, 412, 21009, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.15073528810709463, "compression_ratio": 1.8169642857142858, "no_speech_prob": 0.0013456344604492188, "words": [ { "start": 848.7, "end": 849.22, "word": " We", "probability": 0.875 }, { "start": 849.22, "end": 849.38, "word": " would", "probability": 0.84716796875 }, { "start": 849.38, "end": 849.66, "word": " want", "probability": 0.833984375 }, { "start": 849.66, "end": 849.84, "word": " to", "probability": 0.90625 }, { "start": 849.84, "end": 850.1, "word": " look", "probability": 0.91455078125 }, { "start": 850.1, "end": 850.4, "word": " at", "probability": 0.89990234375 }, { "start": 850.4, "end": 851.12, "word": " keywords", "probability": 0.56201171875 }, { "start": 851.12, "end": 851.64, "word": ".", "probability": 0.9111328125 } ] }, { "id": 346, "seek": 85526, "start": 851.9, "end": 853.9, "text": " So in this case,", "tokens": [ 50914, 407, 294, 341, 1389, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.15073528810709463, "compression_ratio": 1.8169642857142858, "no_speech_prob": 0.0013456344604492188, "words": [ { "start": 851.9, "end": 851.96, "word": " So", "probability": 0.55517578125 }, { "start": 851.96, "end": 852.08, "word": " in", "probability": 0.79052734375 }, { "start": 852.08, "end": 852.22, "word": " this", "probability": 0.873046875 }, { "start": 852.22, "end": 853.76, "word": " case", "probability": 0.73974609375 }, { "start": 853.76, "end": 853.9, "word": ",", "probability": 0.701171875 } ] }, { "id": 347, "seek": 85526, "start": 853.9, "end": 856.38, "text": " we can see that it's talking about games.", "tokens": [ 51014, 321, 393, 536, 300, 309, 311, 1417, 466, 2813, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.15073528810709463, "compression_ratio": 1.8169642857142858, "no_speech_prob": 0.0013456344604492188, "words": [ { "start": 853.9, "end": 854.04, "word": " we", "probability": 0.89306640625 }, { "start": 854.04, "end": 854.18, "word": " can", "probability": 0.896484375 }, { "start": 854.18, "end": 854.46, "word": " see", "probability": 0.81689453125 }, { "start": 854.46, "end": 854.9, "word": " that", "probability": 0.8681640625 }, { "start": 854.9, "end": 855.22, "word": " it's", "probability": 0.94873046875 }, { "start": 855.22, "end": 855.44, "word": " talking", "probability": 0.76806640625 }, { "start": 855.44, "end": 855.7, "word": " about", "probability": 0.8154296875 }, { "start": 855.7, "end": 856.14, "word": " games", "probability": 0.80322265625 }, { "start": 856.14, "end": 856.38, "word": ".", "probability": 0.57861328125 } ] }, { "id": 348, "seek": 85526, "start": 856.38, "end": 858.06, "text": " We know it's probably about sports.", "tokens": [ 51164, 492, 458, 309, 311, 1391, 466, 6573, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.15073528810709463, "compression_ratio": 1.8169642857142858, "no_speech_prob": 0.0013456344604492188, "words": [ { "start": 856.38, "end": 856.68, "word": " We", "probability": 0.8837890625 }, { "start": 856.68, "end": 856.82, "word": " know", "probability": 0.8154296875 }, { "start": 856.82, "end": 856.98, "word": " it's", "probability": 0.947021484375 }, { "start": 856.98, "end": 857.32, "word": " probably", "probability": 0.91259765625 }, { "start": 857.32, "end": 857.62, "word": " about", "probability": 0.822265625 }, { "start": 857.62, "end": 858.02, "word": " sports", "probability": 0.77880859375 }, { "start": 858.02, "end": 858.06, "word": ".", "probability": 0.94921875 } ] }, { "id": 349, "seek": 85526, "start": 858.06, "end": 859.26, "text": " If it's talking about elections,", "tokens": [ 51264, 759, 309, 311, 1417, 466, 12870, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.15073528810709463, "compression_ratio": 1.8169642857142858, "no_speech_prob": 0.0013456344604492188, "words": [ { "start": 858.06, "end": 858.2, "word": " If", "probability": 0.87548828125 }, { "start": 858.2, "end": 858.34, "word": " it's", "probability": 0.953369140625 }, { "start": 858.34, "end": 858.54, "word": " talking", "probability": 0.76318359375 }, { "start": 858.54, "end": 858.74, "word": " about", "probability": 0.83056640625 }, { "start": 858.74, "end": 859.14, "word": " elections", "probability": 0.775390625 }, { "start": 859.14, "end": 859.26, "word": ",", "probability": 0.9501953125 } ] }, { "id": 350, "seek": 85526, "start": 859.26, "end": 861.72, "text": " it's probably not talking about sports.", "tokens": [ 51364, 309, 311, 1391, 406, 1417, 466, 6573, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.15073528810709463, "compression_ratio": 1.8169642857142858, "no_speech_prob": 0.0013456344604492188, "words": [ { "start": 859.26, "end": 859.52, "word": " it's", "probability": 0.94921875 }, { "start": 859.52, "end": 859.88, "word": " probably", "probability": 0.9189453125 }, { "start": 859.88, "end": 860.22, "word": " not", "probability": 0.90087890625 }, { "start": 860.22, "end": 860.54, "word": " talking", "probability": 0.7744140625 }, { "start": 860.54, "end": 860.8, "word": " about", "probability": 0.80517578125 }, { "start": 860.8, "end": 861.2, "word": " sports", "probability": 0.767578125 }, { "start": 861.2, "end": 861.72, "word": ".", "probability": 0.9658203125 } ] }, { "id": 351, "seek": 85526, "start": 862.5, "end": 864.96, "text": " And so what we want to really hone in on", "tokens": [ 51464, 400, 370, 437, 321, 528, 281, 534, 43212, 294, 322, 51564 ], "temperature": 0.0, "avg_logprob": -0.15073528810709463, "compression_ratio": 1.8169642857142858, "no_speech_prob": 0.0013456344604492188, "words": [ { "start": 862.5, "end": 862.98, "word": " And", "probability": 0.8017578125 }, { "start": 862.98, "end": 863.3, "word": " so", "probability": 0.896484375 }, { "start": 863.3, "end": 863.56, "word": " what", "probability": 0.751953125 }, { "start": 863.56, "end": 863.68, "word": " we", "probability": 0.90869140625 }, { "start": 863.68, "end": 863.8, "word": " want", "probability": 0.533203125 }, { "start": 863.8, "end": 863.88, "word": " to", "probability": 0.90234375 }, { "start": 863.88, "end": 864.08, "word": " really", "probability": 0.77001953125 }, { "start": 864.08, "end": 864.38, "word": " hone", "probability": 0.8935546875 }, { "start": 864.38, "end": 864.62, "word": " in", "probability": 0.9072265625 }, { "start": 864.62, "end": 864.96, "word": " on", "probability": 0.904296875 } ] }, { "id": 352, "seek": 85526, "start": 864.96, "end": 866.64, "text": " are keywords.", "tokens": [ 51614, 366, 21009, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.15073528810709463, "compression_ratio": 1.8169642857142858, "no_speech_prob": 0.0013456344604492188, "words": [ { "start": 864.96, "end": 865.42, "word": " are", "probability": 0.658203125 }, { "start": 865.42, "end": 866.12, "word": " keywords", "probability": 0.65966796875 }, { "start": 866.12, "end": 866.64, "word": ".", "probability": 0.7783203125 } ] }, { "id": 353, "seek": 85526, "start": 866.94, "end": 869.04, "text": " But to put this into a machine learning model,", "tokens": [ 51714, 583, 281, 829, 341, 666, 257, 3479, 2539, 2316, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.15073528810709463, "compression_ratio": 1.8169642857142858, "no_speech_prob": 0.0013456344604492188, "words": [ { "start": 866.94, "end": 867.22, "word": " But", "probability": 0.88623046875 }, { "start": 867.22, "end": 867.36, "word": " to", "probability": 0.8984375 }, { "start": 867.36, "end": 867.54, "word": " put", "probability": 0.900390625 }, { "start": 867.54, "end": 867.74, "word": " this", "probability": 0.87939453125 }, { "start": 867.74, "end": 867.88, "word": " into", "probability": 0.72900390625 }, { "start": 868.0, "end": 868.24, "word": " a machine", "probability": 0.6904296875 }, { "start": 868.24, "end": 868.54, "word": " learning", "probability": 0.81884765625 }, { "start": 868.54, "end": 868.9, "word": " model", "probability": 0.80615234375 }, { "start": 868.9, "end": 869.04, "word": ",", "probability": 0.939453125 } ] }, { "id": 354, "seek": 88044, "start": 869.04, "end": 871.04, "text": " we need to find a way", "tokens": [ 50364, 321, 643, 281, 915, 257, 636, 50414 ], "temperature": 0.0, "avg_logprob": -0.18207644628099173, "compression_ratio": 1.8516746411483254, "no_speech_prob": 0.0002913475036621094, "words": [ { "start": 869.04, "end": 869.14, "word": " we", "probability": 0.31201171875 }, { "start": 869.14, "end": 869.44, "word": " need", "probability": 0.8017578125 }, { "start": 869.44, "end": 869.9, "word": " to", "probability": 0.90283203125 }, { "start": 869.9, "end": 870.8, "word": " find", "probability": 0.79931640625 }, { "start": 870.96, "end": 871.04, "word": " a way", "probability": 0.8916015625 } ] }, { "id": 355, "seek": 88044, "start": 871.04, "end": 873.5, "text": " to turn this into numbers.", "tokens": [ 50464, 281, 1261, 341, 666, 3547, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.18207644628099173, "compression_ratio": 1.8516746411483254, "no_speech_prob": 0.0002913475036621094, "words": [ { "start": 871.04, "end": 871.2, "word": " to", "probability": 0.8994140625 }, { "start": 871.2, "end": 871.52, "word": " turn", "probability": 0.82080078125 }, { "start": 871.52, "end": 871.78, "word": " this", "probability": 0.87841796875 }, { "start": 871.78, "end": 872.24, "word": " into", "probability": 0.7197265625 }, { "start": 872.24, "end": 873.04, "word": " numbers", "probability": 0.85888671875 }, { "start": 873.04, "end": 873.5, "word": ".", "probability": 0.912109375 } ] }, { "id": 356, "seek": 88044, "start": 874.66, "end": 875.72, "text": " So the way that we're going to do this", "tokens": [ 50614, 407, 264, 636, 300, 321, 434, 516, 281, 360, 341, 50664 ], "temperature": 0.0, "avg_logprob": -0.18207644628099173, "compression_ratio": 1.8516746411483254, "no_speech_prob": 0.0002913475036621094, "words": [ { "start": 874.66, "end": 874.74, "word": " So", "probability": 0.7119140625 }, { "start": 874.74, "end": 874.86, "word": " the", "probability": 0.7529296875 }, { "start": 874.86, "end": 874.98, "word": " way", "probability": 0.8984375 }, { "start": 874.98, "end": 875.08, "word": " that", "probability": 0.8212890625 }, { "start": 875.08, "end": 875.22, "word": " we're", "probability": 0.912353515625 }, { "start": 875.22, "end": 875.28, "word": " going", "probability": 0.5185546875 }, { "start": 875.28, "end": 875.34, "word": " to", "probability": 0.90478515625 }, { "start": 875.34, "end": 875.46, "word": " do", "probability": 0.912109375 }, { "start": 875.46, "end": 875.72, "word": " this", "probability": 0.87255859375 } ] }, { "id": 357, "seek": 88044, "start": 875.72, "end": 877.92, "text": " is Bayes' Theorem.", "tokens": [ 50714, 307, 7840, 279, 6, 440, 37956, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.18207644628099173, "compression_ratio": 1.8516746411483254, "no_speech_prob": 0.0002913475036621094, "words": [ { "start": 875.72, "end": 876.16, "word": " is", "probability": 0.888671875 }, { "start": 876.16, "end": 877.26, "word": " Bayes", "probability": 0.77001953125 }, { "start": 877.26, "end": 877.36, "word": "'", "probability": 0.5625 }, { "start": 877.36, "end": 877.64, "word": " Theorem", "probability": 0.6318359375 }, { "start": 877.64, "end": 877.92, "word": ".", "probability": 0.9375 } ] }, { "id": 358, "seek": 88044, "start": 877.92, "end": 879.38, "text": " Bayes' Theorem is...", "tokens": [ 50814, 7840, 279, 6, 440, 37956, 307, 485, 50864 ], "temperature": 0.0, "avg_logprob": -0.18207644628099173, "compression_ratio": 1.8516746411483254, "no_speech_prob": 0.0002913475036621094, "words": [ { "start": 877.92, "end": 878.16, "word": " Bayes", "probability": 0.8095703125 }, { "start": 878.16, "end": 878.3, "word": "'", "probability": 0.9658203125 }, { "start": 878.3, "end": 878.52, "word": " Theorem", "probability": 0.8310546875 }, { "start": 878.52, "end": 879.38, "word": " is...", "probability": 0.32122802734375 } ] }, { "id": 359, "seek": 88044, "start": 880.03, "end": 881.76, "text": " it may look complex at first,", "tokens": [ 50914, 309, 815, 574, 3997, 412, 700, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.18207644628099173, "compression_ratio": 1.8516746411483254, "no_speech_prob": 0.0002913475036621094, "words": [ { "start": 880.03, "end": 880.26, "word": " it", "probability": 0.461669921875 }, { "start": 880.26, "end": 880.6, "word": " may", "probability": 0.892578125 }, { "start": 880.6, "end": 880.86, "word": " look", "probability": 0.9248046875 }, { "start": 880.86, "end": 881.26, "word": " complex", "probability": 0.72900390625 }, { "start": 881.26, "end": 881.42, "word": " at", "probability": 0.90478515625 }, { "start": 881.42, "end": 881.68, "word": " first", "probability": 0.81787109375 }, { "start": 881.68, "end": 881.76, "word": ",", "probability": 0.6435546875 } ] }, { "id": 360, "seek": 88044, "start": 881.76, "end": 882.86, "text": " but it's actually a really easy", "tokens": [ 51014, 457, 309, 311, 767, 257, 534, 1858, 51064 ], "temperature": 0.0, "avg_logprob": -0.18207644628099173, "compression_ratio": 1.8516746411483254, "no_speech_prob": 0.0002913475036621094, "words": [ { "start": 881.76, "end": 881.84, "word": " but", "probability": 0.89794921875 }, { "start": 881.84, "end": 881.98, "word": " it's", "probability": 0.943603515625 }, { "start": 881.98, "end": 882.22, "word": " actually", "probability": 0.78662109375 }, { "start": 882.4, "end": 882.6, "word": " a really", "probability": 0.77001953125 }, { "start": 882.6, "end": 882.86, "word": " easy", "probability": 0.80810546875 } ] }, { "id": 361, "seek": 88044, "start": 882.86, "end": 884.8, "text": " to understand probability theorem.", "tokens": [ 51114, 281, 1223, 8482, 20904, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.18207644628099173, "compression_ratio": 1.8516746411483254, "no_speech_prob": 0.0002913475036621094, "words": [ { "start": 882.86, "end": 882.98, "word": " to", "probability": 0.68212890625 }, { "start": 882.98, "end": 883.42, "word": " understand", "probability": 0.75146484375 }, { "start": 883.42, "end": 883.92, "word": " probability", "probability": 0.81689453125 }, { "start": 883.92, "end": 884.34, "word": " theorem", "probability": 0.787109375 }, { "start": 884.34, "end": 884.8, "word": ".", "probability": 0.81103515625 } ] }, { "id": 362, "seek": 88044, "start": 885.48, "end": 886.08, "text": " And in this case,", "tokens": [ 51214, 400, 294, 341, 1389, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.18207644628099173, "compression_ratio": 1.8516746411483254, "no_speech_prob": 0.0002913475036621094, "words": [ { "start": 885.48, "end": 885.6, "word": " And", "probability": 0.810546875 }, { "start": 885.6, "end": 885.7, "word": " in", "probability": 0.89306640625 }, { "start": 885.7, "end": 885.86, "word": " this", "probability": 0.87841796875 }, { "start": 885.86, "end": 886.04, "word": " case", "probability": 0.8115234375 }, { "start": 886.04, "end": 886.08, "word": ",", "probability": 0.58154296875 } ] }, { "id": 363, "seek": 88044, "start": 886.08, "end": 887.94, "text": " we see the probability of A given B", "tokens": [ 51314, 321, 536, 264, 8482, 295, 316, 2212, 363, 51364 ], "temperature": 0.0, "avg_logprob": -0.18207644628099173, "compression_ratio": 1.8516746411483254, "no_speech_prob": 0.0002913475036621094, "words": [ { "start": 886.08, "end": 886.16, "word": " we", "probability": 0.90478515625 }, { "start": 886.16, "end": 886.3, "word": " see", "probability": 0.81494140625 }, { "start": 886.3, "end": 886.42, "word": " the", "probability": 0.7890625 }, { "start": 886.42, "end": 886.74, "word": " probability", "probability": 0.87255859375 }, { "start": 886.74, "end": 886.98, "word": " of", "probability": 0.89697265625 }, { "start": 886.98, "end": 887.24, "word": " A", "probability": 0.87255859375 }, { "start": 887.24, "end": 887.5, "word": " given", "probability": 0.6875 }, { "start": 887.5, "end": 887.94, "word": " B", "probability": 0.99609375 } ] }, { "id": 364, "seek": 88044, "start": 887.94, "end": 890.26, "text": " equals probability of B given A", "tokens": [ 51414, 6915, 8482, 295, 363, 2212, 316, 51464 ], "temperature": 0.0, "avg_logprob": -0.18207644628099173, "compression_ratio": 1.8516746411483254, "no_speech_prob": 0.0002913475036621094, "words": [ { "start": 887.94, "end": 888.84, "word": " equals", "probability": 0.720703125 }, { "start": 888.84, "end": 889.32, "word": " probability", "probability": 0.66162109375 }, { "start": 889.32, "end": 889.5, "word": " of", "probability": 0.7646484375 }, { "start": 889.5, "end": 889.6, "word": " B", "probability": 0.98486328125 }, { "start": 889.6, "end": 889.84, "word": " given", "probability": 0.80810546875 }, { "start": 889.84, "end": 890.26, "word": " A", "probability": 0.994140625 } ] }, { "id": 365, "seek": 88044, "start": 890.26, "end": 891.66, "text": " times the probability of A", "tokens": [ 51514, 1413, 264, 8482, 295, 316, 51564 ], "temperature": 0.0, "avg_logprob": -0.18207644628099173, "compression_ratio": 1.8516746411483254, "no_speech_prob": 0.0002913475036621094, "words": [ { "start": 890.26, "end": 890.8, "word": " times", "probability": 0.62451171875 }, { "start": 890.8, "end": 890.94, "word": " the", "probability": 0.69091796875 }, { "start": 890.94, "end": 891.22, "word": " probability", "probability": 0.8828125 }, { "start": 891.22, "end": 891.46, "word": " of", "probability": 0.65234375 }, { "start": 891.46, "end": 891.66, "word": " A", "probability": 0.99658203125 } ] }, { "id": 366, "seek": 88044, "start": 891.66, "end": 893.54, "text": " divided by the probability of B.", "tokens": [ 51614, 6666, 538, 264, 8482, 295, 363, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.18207644628099173, "compression_ratio": 1.8516746411483254, "no_speech_prob": 0.0002913475036621094, "words": [ { "start": 891.66, "end": 892.2, "word": " divided", "probability": 0.6591796875 }, { "start": 892.2, "end": 892.34, "word": " by", "probability": 0.90234375 }, { "start": 892.34, "end": 892.48, "word": " the", "probability": 0.81982421875 }, { "start": 892.48, "end": 892.74, "word": " probability", "probability": 0.88818359375 }, { "start": 892.74, "end": 893.0, "word": " of", "probability": 0.90625 }, { "start": 893.0, "end": 893.16, "word": " B", "probability": 0.9990234375 }, { "start": 893.16, "end": 893.54, "word": ".", "probability": 0.9892578125 } ] }, { "id": 367, "seek": 88044, "start": 893.54, "end": 894.22, "text": " So in this case,", "tokens": [ 51714, 407, 294, 341, 1389, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.18207644628099173, "compression_ratio": 1.8516746411483254, "no_speech_prob": 0.0002913475036621094, "words": [ { "start": 893.54, "end": 893.74, "word": " So", "probability": 0.88427734375 }, { "start": 893.74, "end": 893.84, "word": " in", "probability": 0.86328125 }, { "start": 893.84, "end": 893.98, "word": " this", "probability": 0.87841796875 }, { "start": 893.98, "end": 894.18, "word": " case", "probability": 0.80908203125 }, { "start": 894.18, "end": 894.22, "word": ",", "probability": 0.8857421875 } ] }, { "id": 368, "seek": 91044, "start": 894.22, "end": 895.58, "text": " we want to see what is the probability", "tokens": [ 50364, 321, 528, 281, 536, 437, 307, 264, 8482, 50414 ], "temperature": 0.0, "avg_logprob": -0.16071428033642302, "compression_ratio": 2.2152466367713006, "no_speech_prob": 0.009857177734375, "words": [ { "start": 894.22, "end": 894.32, "word": " we", "probability": 0.35205078125 }, { "start": 894.32, "end": 894.46, "word": " want", "probability": 0.70263671875 }, { "start": 894.46, "end": 894.54, "word": " to", "probability": 0.90478515625 }, { "start": 894.54, "end": 894.68, "word": " see", "probability": 0.7880859375 }, { "start": 894.68, "end": 894.88, "word": " what", "probability": 0.74365234375 }, { "start": 894.88, "end": 894.98, "word": " is", "probability": 0.87255859375 }, { "start": 894.98, "end": 895.12, "word": " the", "probability": 0.81298828125 }, { "start": 895.12, "end": 895.58, "word": " probability", "probability": 0.8828125 } ] }, { "id": 369, "seek": 91044, "start": 896.66, "end": 899.12, "text": " that this sentence is talking about sports", "tokens": [ 50464, 300, 341, 8174, 307, 1417, 466, 6573, 50564 ], "temperature": 0.0, "avg_logprob": -0.16071428033642302, "compression_ratio": 2.2152466367713006, "no_speech_prob": 0.009857177734375, "words": [ { "start": 896.66, "end": 897.1, "word": " that", "probability": 0.85302734375 }, { "start": 897.1, "end": 897.54, "word": " this", "probability": 0.6259765625 }, { "start": 897.54, "end": 897.84, "word": " sentence", "probability": 0.82275390625 }, { "start": 897.84, "end": 898.0, "word": " is", "probability": 0.896484375 }, { "start": 898.0, "end": 898.24, "word": " talking", "probability": 0.76904296875 }, { "start": 898.24, "end": 898.5, "word": " about", "probability": 0.80908203125 }, { "start": 898.5, "end": 899.12, "word": " sports", "probability": 0.75439453125 } ] }, { "id": 370, "seek": 91044, "start": 899.12, "end": 901.02, "text": " given that the sentence is", "tokens": [ 50614, 2212, 300, 264, 8174, 307, 50664 ], "temperature": 0.0, "avg_logprob": -0.16071428033642302, "compression_ratio": 2.2152466367713006, "no_speech_prob": 0.009857177734375, "words": [ { "start": 899.12, "end": 899.88, "word": " given", "probability": 0.385986328125 }, { "start": 899.88, "end": 900.06, "word": " that", "probability": 0.8623046875 }, { "start": 900.06, "end": 900.24, "word": " the", "probability": 0.7158203125 }, { "start": 900.24, "end": 900.6, "word": " sentence", "probability": 0.837890625 }, { "start": 900.6, "end": 901.02, "word": " is", "probability": 0.8984375 } ] }, { "id": 371, "seek": 91044, "start": 901.02, "end": 902.8, "text": " A very close game.", "tokens": [ 50714, 316, 588, 1998, 1216, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.16071428033642302, "compression_ratio": 2.2152466367713006, "no_speech_prob": 0.009857177734375, "words": [ { "start": 901.02, "end": 901.44, "word": " A", "probability": 0.037261962890625 }, { "start": 901.44, "end": 901.7, "word": " very", "probability": 0.453125 }, { "start": 901.7, "end": 902.04, "word": " close", "probability": 0.837890625 }, { "start": 902.04, "end": 902.36, "word": " game", "probability": 0.7919921875 }, { "start": 902.36, "end": 902.8, "word": ".", "probability": 0.73828125 } ] }, { "id": 372, "seek": 91044, "start": 903.28, "end": 906.22, "text": " So we don't know the probability of sports", "tokens": [ 50814, 407, 321, 500, 380, 458, 264, 8482, 295, 6573, 50914 ], "temperature": 0.0, "avg_logprob": -0.16071428033642302, "compression_ratio": 2.2152466367713006, "no_speech_prob": 0.009857177734375, "words": [ { "start": 903.28, "end": 903.62, "word": " So", "probability": 0.57666015625 }, { "start": 903.62, "end": 904.36, "word": " we", "probability": 0.71044921875 }, { "start": 904.36, "end": 904.5, "word": " don't", "probability": 0.94384765625 }, { "start": 904.5, "end": 904.64, "word": " know", "probability": 0.81982421875 }, { "start": 904.64, "end": 904.78, "word": " the", "probability": 0.81640625 }, { "start": 904.78, "end": 905.2, "word": " probability", "probability": 0.89306640625 }, { "start": 905.2, "end": 905.8, "word": " of", "probability": 0.90234375 }, { "start": 905.8, "end": 906.22, "word": " sports", "probability": 0.75830078125 } ] }, { "id": 373, "seek": 91044, "start": 906.22, "end": 907.64, "text": " given A very close game,", "tokens": [ 50964, 2212, 316, 588, 1998, 1216, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.16071428033642302, "compression_ratio": 2.2152466367713006, "no_speech_prob": 0.009857177734375, "words": [ { "start": 906.22, "end": 906.6, "word": " given", "probability": 0.67236328125 }, { "start": 906.6, "end": 906.8, "word": " A", "probability": 0.7373046875 }, { "start": 906.8, "end": 906.96, "word": " very", "probability": 0.70458984375 }, { "start": 906.96, "end": 907.24, "word": " close", "probability": 0.85791015625 }, { "start": 907.24, "end": 907.54, "word": " game", "probability": 0.7880859375 }, { "start": 907.54, "end": 907.64, "word": ",", "probability": 0.490966796875 } ] }, { "id": 374, "seek": 91044, "start": 907.64, "end": 909.44, "text": " but we can easily plug that into this formula", "tokens": [ 51064, 457, 321, 393, 3612, 5452, 300, 666, 341, 8513, 51114 ], "temperature": 0.0, "avg_logprob": -0.16071428033642302, "compression_ratio": 2.2152466367713006, "no_speech_prob": 0.009857177734375, "words": [ { "start": 907.64, "end": 907.72, "word": " but", "probability": 0.89404296875 }, { "start": 907.72, "end": 907.82, "word": " we", "probability": 0.90771484375 }, { "start": 907.82, "end": 907.96, "word": " can", "probability": 0.8916015625 }, { "start": 907.96, "end": 908.32, "word": " easily", "probability": 0.83154296875 }, { "start": 908.32, "end": 908.58, "word": " plug", "probability": 0.8212890625 }, { "start": 908.58, "end": 908.74, "word": " that", "probability": 0.873046875 }, { "start": 908.74, "end": 908.9, "word": " into", "probability": 0.708984375 }, { "start": 908.9, "end": 909.1, "word": " this", "probability": 0.8798828125 }, { "start": 909.1, "end": 909.44, "word": " formula", "probability": 0.79736328125 } ] }, { "id": 375, "seek": 91044, "start": 909.44, "end": 911.78, "text": " and say, well, we know the probability of sports.", "tokens": [ 51164, 293, 584, 11, 731, 11, 321, 458, 264, 8482, 295, 6573, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.16071428033642302, "compression_ratio": 2.2152466367713006, "no_speech_prob": 0.009857177734375, "words": [ { "start": 909.44, "end": 909.68, "word": " and", "probability": 0.83740234375 }, { "start": 909.68, "end": 909.84, "word": " say", "probability": 0.8876953125 }, { "start": 909.84, "end": 909.94, "word": ",", "probability": 0.52392578125 }, { "start": 909.94, "end": 910.0, "word": " well", "probability": 0.66943359375 }, { "start": 910.0, "end": 910.02, "word": ",", "probability": 0.73828125 }, { "start": 910.02, "end": 910.14, "word": " we", "probability": 0.90234375 }, { "start": 910.14, "end": 910.26, "word": " know", "probability": 0.82080078125 }, { "start": 910.26, "end": 910.42, "word": " the", "probability": 0.810546875 }, { "start": 910.42, "end": 910.78, "word": " probability", "probability": 0.89306640625 }, { "start": 910.78, "end": 911.08, "word": " of", "probability": 0.908203125 }, { "start": 911.08, "end": 911.6, "word": " sports", "probability": 0.7841796875 }, { "start": 911.6, "end": 911.78, "word": ".", "probability": 0.63232421875 } ] }, { "id": 376, "seek": 91044, "start": 911.78, "end": 913.9, "text": " We saw three out of our five sentences", "tokens": [ 51264, 492, 1866, 1045, 484, 295, 527, 1732, 16579, 51314 ], "temperature": 0.0, "avg_logprob": -0.16071428033642302, "compression_ratio": 2.2152466367713006, "no_speech_prob": 0.009857177734375, "words": [ { "start": 911.78, "end": 911.84, "word": " We", "probability": 0.88623046875 }, { "start": 911.84, "end": 912.16, "word": " saw", "probability": 0.81396484375 }, { "start": 912.16, "end": 913.02, "word": " three", "probability": 0.66748046875 }, { "start": 913.02, "end": 913.22, "word": " out", "probability": 0.78857421875 }, { "start": 913.22, "end": 913.26, "word": " of", "probability": 0.86083984375 }, { "start": 913.26, "end": 913.36, "word": " our", "probability": 0.7021484375 }, { "start": 913.36, "end": 913.6, "word": " five", "probability": 0.83837890625 }, { "start": 913.6, "end": 913.9, "word": " sentences", "probability": 0.8779296875 } ] }, { "id": 377, "seek": 91044, "start": 913.9, "end": 915.12, "text": " were talking about sports.", "tokens": [ 51364, 645, 1417, 466, 6573, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.16071428033642302, "compression_ratio": 2.2152466367713006, "no_speech_prob": 0.009857177734375, "words": [ { "start": 913.9, "end": 914.12, "word": " were", "probability": 0.499267578125 }, { "start": 914.12, "end": 914.36, "word": " talking", "probability": 0.763671875 }, { "start": 914.36, "end": 914.58, "word": " about", "probability": 0.82177734375 }, { "start": 914.58, "end": 915.0, "word": " sports", "probability": 0.7841796875 }, { "start": 915.0, "end": 915.12, "word": ".", "probability": 0.1995849609375 } ] }, { "id": 378, "seek": 91044, "start": 915.12, "end": 916.82, "text": " And we can figure out the probability", "tokens": [ 51464, 400, 321, 393, 2573, 484, 264, 8482, 51514 ], "temperature": 0.0, "avg_logprob": -0.16071428033642302, "compression_ratio": 2.2152466367713006, "no_speech_prob": 0.009857177734375, "words": [ { "start": 915.12, "end": 915.18, "word": " And", "probability": 0.802734375 }, { "start": 915.18, "end": 915.3, "word": " we", "probability": 0.8740234375 }, { "start": 915.3, "end": 915.76, "word": " can", "probability": 0.873046875 }, { "start": 915.76, "end": 916.06, "word": " figure", "probability": 0.89892578125 }, { "start": 916.06, "end": 916.22, "word": " out", "probability": 0.822265625 }, { "start": 916.22, "end": 916.36, "word": " the", "probability": 0.8203125 }, { "start": 916.36, "end": 916.82, "word": " probability", "probability": 0.89892578125 } ] }, { "id": 379, "seek": 91044, "start": 916.82, "end": 919.06, "text": " of A very close game given sports", "tokens": [ 51564, 295, 316, 588, 1998, 1216, 2212, 6573, 51614 ], "temperature": 0.0, "avg_logprob": -0.16071428033642302, "compression_ratio": 2.2152466367713006, "no_speech_prob": 0.009857177734375, "words": [ { "start": 916.82, "end": 917.28, "word": " of", "probability": 0.90185546875 }, { "start": 917.28, "end": 917.5, "word": " A", "probability": 0.84619140625 }, { "start": 917.5, "end": 917.68, "word": " very", "probability": 0.71044921875 }, { "start": 917.68, "end": 917.98, "word": " close", "probability": 0.8564453125 }, { "start": 917.98, "end": 918.32, "word": " game", "probability": 0.80029296875 }, { "start": 918.32, "end": 918.64, "word": " given", "probability": 0.62109375 }, { "start": 918.64, "end": 919.06, "word": " sports", "probability": 0.78662109375 } ] }, { "id": 380, "seek": 91044, "start": 919.06, "end": 921.5, "text": " and the probability of A very close game.", "tokens": [ 51664, 293, 264, 8482, 295, 316, 588, 1998, 1216, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.16071428033642302, "compression_ratio": 2.2152466367713006, "no_speech_prob": 0.009857177734375, "words": [ { "start": 919.06, "end": 919.36, "word": " and", "probability": 0.77978515625 }, { "start": 919.36, "end": 919.52, "word": " the", "probability": 0.81591796875 }, { "start": 919.52, "end": 919.88, "word": " probability", "probability": 0.8955078125 }, { "start": 919.88, "end": 920.1, "word": " of", "probability": 0.90234375 }, { "start": 920.1, "end": 920.3, "word": " A", "probability": 0.95068359375 }, { "start": 920.3, "end": 920.48, "word": " very", "probability": 0.72119140625 }, { "start": 920.48, "end": 920.78, "word": " close", "probability": 0.86279296875 }, { "start": 920.78, "end": 921.06, "word": " game", "probability": 0.8017578125 }, { "start": 921.06, "end": 921.5, "word": ".", "probability": 0.94873046875 } ] }, { "id": 381, "seek": 91044, "start": 922.2, "end": 923.14, "text": " But how do we do that?", "tokens": [ 51764, 583, 577, 360, 321, 360, 300, 30, 51814 ], "temperature": 0.0, "avg_logprob": -0.16071428033642302, "compression_ratio": 2.2152466367713006, "no_speech_prob": 0.009857177734375, "words": [ { "start": 922.2, "end": 922.38, "word": " But", "probability": 0.88525390625 }, { "start": 922.38, "end": 922.5, "word": " how", "probability": 0.89306640625 }, { "start": 922.5, "end": 922.58, "word": " do", "probability": 0.9091796875 }, { "start": 922.58, "end": 922.66, "word": " we", "probability": 0.9013671875 }, { "start": 922.66, "end": 922.8, "word": " do", "probability": 0.90673828125 }, { "start": 922.8, "end": 923.04, "word": " that", "probability": 0.8828125 }, { "start": 923.04, "end": 923.14, "word": "?", "probability": 0.9833984375 } ] }, { "id": 382, "seek": 94044, "start": 924.22, "end": 925.54, "text": " How do we get a sentence like this?", "tokens": [ 50364, 1012, 360, 321, 483, 257, 8174, 411, 341, 30, 50414 ], "temperature": 0.0, "avg_logprob": -0.20486110470913074, "compression_ratio": 1.9912280701754386, "no_speech_prob": 0.0089874267578125, "words": [ { "start": 924.22, "end": 924.22, "word": " How", "probability": 0.01442718505859375 }, { "start": 924.22, "end": 924.22, "word": " do", "probability": 0.3505859375 }, { "start": 924.22, "end": 924.22, "word": " we", "probability": 0.638671875 }, { "start": 924.22, "end": 924.22, "word": " get", "probability": 0.10955810546875 }, { "start": 924.22, "end": 924.48, "word": " a sentence", "probability": 0.85791015625 }, { "start": 924.48, "end": 924.76, "word": " like", "probability": 0.88525390625 }, { "start": 924.76, "end": 925.06, "word": " this", "probability": 0.87744140625 }, { "start": 925.06, "end": 925.54, "word": "?", "probability": 0.96044921875 } ] }, { "id": 383, "seek": 94044, "start": 926.0, "end": 926.94, "text": " Well, with Bayes theorem,", "tokens": [ 50464, 1042, 11, 365, 7840, 279, 20904, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.20486110470913074, "compression_ratio": 1.9912280701754386, "no_speech_prob": 0.0089874267578125, "words": [ { "start": 926.0, "end": 926.12, "word": " Well", "probability": 0.327880859375 }, { "start": 926.12, "end": 926.24, "word": ",", "probability": 0.34716796875 }, { "start": 926.24, "end": 926.3, "word": " with", "probability": 0.78564453125 }, { "start": 926.3, "end": 926.58, "word": " Bayes", "probability": 0.65478515625 }, { "start": 926.58, "end": 926.78, "word": " theorem", "probability": 0.140380859375 }, { "start": 926.78, "end": 926.94, "word": ",", "probability": 0.362060546875 } ] }, { "id": 384, "seek": 94044, "start": 926.94, "end": 929.24, "text": " we can actually, or with probability,", "tokens": [ 50564, 321, 393, 767, 11, 420, 365, 8482, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.20486110470913074, "compression_ratio": 1.9912280701754386, "no_speech_prob": 0.0089874267578125, "words": [ { "start": 926.94, "end": 926.94, "word": " we", "probability": 0.654296875 }, { "start": 926.94, "end": 927.06, "word": " can", "probability": 0.890625 }, { "start": 927.06, "end": 927.42, "word": " actually", "probability": 0.64697265625 }, { "start": 927.42, "end": 928.0, "word": ",", "probability": 0.353271484375 }, { "start": 928.0, "end": 928.16, "word": " or", "probability": 0.5283203125 }, { "start": 928.16, "end": 928.48, "word": " with", "probability": 0.7568359375 }, { "start": 928.48, "end": 928.92, "word": " probability", "probability": 0.84423828125 }, { "start": 928.92, "end": 929.24, "word": ",", "probability": 0.4853515625 } ] }, { "id": 385, "seek": 94044, "start": 929.24, "end": 931.02, "text": " actually, we can split this up.", "tokens": [ 50664, 767, 11, 321, 393, 7472, 341, 493, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.20486110470913074, "compression_ratio": 1.9912280701754386, "no_speech_prob": 0.0089874267578125, "words": [ { "start": 929.24, "end": 929.54, "word": " actually", "probability": 0.58642578125 }, { "start": 929.54, "end": 929.68, "word": ",", "probability": 0.7412109375 }, { "start": 929.68, "end": 929.78, "word": " we", "probability": 0.88818359375 }, { "start": 929.78, "end": 929.96, "word": " can", "probability": 0.896484375 }, { "start": 929.96, "end": 930.26, "word": " split", "probability": 0.833984375 }, { "start": 930.26, "end": 930.48, "word": " this", "probability": 0.87939453125 }, { "start": 930.48, "end": 930.76, "word": " up", "probability": 0.90478515625 }, { "start": 930.76, "end": 931.02, "word": ".", "probability": 0.86279296875 } ] }, { "id": 386, "seek": 94044, "start": 931.02, "end": 932.52, "text": " So instead of A very close game", "tokens": [ 50764, 407, 2602, 295, 316, 588, 1998, 1216, 50814 ], "temperature": 0.0, "avg_logprob": -0.20486110470913074, "compression_ratio": 1.9912280701754386, "no_speech_prob": 0.0089874267578125, "words": [ { "start": 931.02, "end": 931.1, "word": " So", "probability": 0.83056640625 }, { "start": 931.1, "end": 931.36, "word": " instead", "probability": 0.701171875 }, { "start": 931.36, "end": 931.58, "word": " of", "probability": 0.9052734375 }, { "start": 931.58, "end": 931.74, "word": " A", "probability": 0.107421875 }, { "start": 931.74, "end": 931.9, "word": " very", "probability": 0.45166015625 }, { "start": 931.9, "end": 932.2, "word": " close", "probability": 0.8369140625 }, { "start": 932.2, "end": 932.52, "word": " game", "probability": 0.798828125 } ] }, { "id": 387, "seek": 94044, "start": 932.52, "end": 933.62, "text": " as a whole sentence,", "tokens": [ 50864, 382, 257, 1379, 8174, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.20486110470913074, "compression_ratio": 1.9912280701754386, "no_speech_prob": 0.0089874267578125, "words": [ { "start": 932.52, "end": 932.74, "word": " as", "probability": 0.81787109375 }, { "start": 932.86, "end": 933.04, "word": " a whole", "probability": 0.8046875 }, { "start": 933.04, "end": 933.42, "word": " sentence", "probability": 0.845703125 }, { "start": 933.42, "end": 933.62, "word": ",", "probability": 0.85498046875 } ] }, { "id": 388, "seek": 94044, "start": 933.62, "end": 935.5, "text": " we can look at the probability of A", "tokens": [ 50964, 321, 393, 574, 412, 264, 8482, 295, 316, 51014 ], "temperature": 0.0, "avg_logprob": -0.20486110470913074, "compression_ratio": 1.9912280701754386, "no_speech_prob": 0.0089874267578125, "words": [ { "start": 933.62, "end": 933.72, "word": " we", "probability": 0.89404296875 }, { "start": 933.72, "end": 933.88, "word": " can", "probability": 0.8955078125 }, { "start": 933.88, "end": 934.06, "word": " look", "probability": 0.91796875 }, { "start": 934.06, "end": 934.26, "word": " at", "probability": 0.90966796875 }, { "start": 934.26, "end": 934.66, "word": " the", "probability": 0.6767578125 }, { "start": 934.66, "end": 935.02, "word": " probability", "probability": 0.86181640625 }, { "start": 935.02, "end": 935.26, "word": " of", "probability": 0.90087890625 }, { "start": 935.26, "end": 935.5, "word": " A", "probability": 0.96533203125 } ] }, { "id": 389, "seek": 94044, "start": 935.5, "end": 936.74, "text": " times the probability of very", "tokens": [ 51064, 1413, 264, 8482, 295, 588, 51114 ], "temperature": 0.0, "avg_logprob": -0.20486110470913074, "compression_ratio": 1.9912280701754386, "no_speech_prob": 0.0089874267578125, "words": [ { "start": 935.5, "end": 935.76, "word": " times", "probability": 0.7080078125 }, { "start": 935.76, "end": 935.92, "word": " the", "probability": 0.71240234375 }, { "start": 935.92, "end": 936.26, "word": " probability", "probability": 0.8681640625 }, { "start": 936.26, "end": 936.5, "word": " of", "probability": 0.89599609375 }, { "start": 936.5, "end": 936.74, "word": " very", "probability": 0.55517578125 } ] }, { "id": 390, "seek": 94044, "start": 936.74, "end": 939.16, "text": " times close times game.", "tokens": [ 51164, 1413, 1998, 1413, 1216, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.20486110470913074, "compression_ratio": 1.9912280701754386, "no_speech_prob": 0.0089874267578125, "words": [ { "start": 936.74, "end": 937.18, "word": " times", "probability": 0.50048828125 }, { "start": 937.18, "end": 937.78, "word": " close", "probability": 0.81298828125 }, { "start": 937.78, "end": 938.24, "word": " times", "probability": 0.7509765625 }, { "start": 938.24, "end": 938.68, "word": " game", "probability": 0.7060546875 }, { "start": 938.68, "end": 939.16, "word": ".", "probability": 0.9453125 } ] }, { "id": 391, "seek": 94044, "start": 939.64, "end": 941.54, "text": " And so what this turns into", "tokens": [ 51264, 400, 370, 437, 341, 4523, 666, 51314 ], "temperature": 0.0, "avg_logprob": -0.20486110470913074, "compression_ratio": 1.9912280701754386, "no_speech_prob": 0.0089874267578125, "words": [ { "start": 939.64, "end": 939.74, "word": " And", "probability": 0.8095703125 }, { "start": 939.74, "end": 940.06, "word": " so", "probability": 0.89599609375 }, { "start": 940.06, "end": 940.62, "word": " what", "probability": 0.6064453125 }, { "start": 940.62, "end": 940.8, "word": " this", "probability": 0.8818359375 }, { "start": 940.8, "end": 941.12, "word": " turns", "probability": 0.77294921875 }, { "start": 941.12, "end": 941.54, "word": " into", "probability": 0.72705078125 } ] }, { "id": 392, "seek": 94044, "start": 941.54, "end": 944.0, "text": " in our A very close game given sports", "tokens": [ 51364, 294, 527, 316, 588, 1998, 1216, 2212, 6573, 51414 ], "temperature": 0.0, "avg_logprob": -0.20486110470913074, "compression_ratio": 1.9912280701754386, "no_speech_prob": 0.0089874267578125, "words": [ { "start": 941.54, "end": 941.82, "word": " in", "probability": 0.8388671875 }, { "start": 941.82, "end": 941.96, "word": " our", "probability": 0.783203125 }, { "start": 941.96, "end": 942.24, "word": " A", "probability": 0.96142578125 }, { "start": 942.24, "end": 942.44, "word": " very", "probability": 0.68603515625 }, { "start": 942.44, "end": 942.72, "word": " close", "probability": 0.8447265625 }, { "start": 942.72, "end": 943.0, "word": " game", "probability": 0.77880859375 }, { "start": 943.0, "end": 943.44, "word": " given", "probability": 0.68701171875 }, { "start": 943.44, "end": 944.0, "word": " sports", "probability": 0.7373046875 } ] }, { "id": 393, "seek": 94044, "start": 945.06, "end": 947.22, "text": " is probability of A in sports,", "tokens": [ 51464, 307, 8482, 295, 316, 294, 6573, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.20486110470913074, "compression_ratio": 1.9912280701754386, "no_speech_prob": 0.0089874267578125, "words": [ { "start": 945.06, "end": 945.54, "word": " is", "probability": 0.7138671875 }, { "start": 945.54, "end": 946.02, "word": " probability", "probability": 0.75634765625 }, { "start": 946.02, "end": 946.24, "word": " of", "probability": 0.90478515625 }, { "start": 946.24, "end": 946.54, "word": " A", "probability": 0.982421875 }, { "start": 946.54, "end": 946.76, "word": " in", "probability": 0.8447265625 }, { "start": 946.76, "end": 947.06, "word": " sports", "probability": 0.71728515625 }, { "start": 947.06, "end": 947.22, "word": ",", "probability": 0.90625 } ] }, { "id": 394, "seek": 94044, "start": 947.22, "end": 948.82, "text": " probability of very in sports,", "tokens": [ 51564, 8482, 295, 588, 294, 6573, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.20486110470913074, "compression_ratio": 1.9912280701754386, "no_speech_prob": 0.0089874267578125, "words": [ { "start": 947.22, "end": 947.54, "word": " probability", "probability": 0.80517578125 }, { "start": 947.54, "end": 947.78, "word": " of", "probability": 0.8974609375 }, { "start": 947.78, "end": 948.0, "word": " very", "probability": 0.71484375 }, { "start": 948.0, "end": 948.24, "word": " in", "probability": 0.89599609375 }, { "start": 948.24, "end": 948.66, "word": " sports", "probability": 0.77294921875 }, { "start": 948.66, "end": 948.82, "word": ",", "probability": 0.7431640625 } ] }, { "id": 395, "seek": 94044, "start": 948.82, "end": 949.84, "text": " and so on.", "tokens": [ 51664, 293, 370, 322, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.20486110470913074, "compression_ratio": 1.9912280701754386, "no_speech_prob": 0.0089874267578125, "words": [ { "start": 948.82, "end": 949.32, "word": " and", "probability": 0.89404296875 }, { "start": 949.32, "end": 949.54, "word": " so", "probability": 0.90673828125 }, { "start": 949.54, "end": 949.74, "word": " on", "probability": 0.91162109375 }, { "start": 949.74, "end": 949.84, "word": ".", "probability": 0.97265625 } ] }, { "id": 396, "seek": 94044, "start": 949.84, "end": 950.92, "text": " And of course, we're going to want to do", "tokens": [ 51764, 400, 295, 1164, 11, 321, 434, 516, 281, 528, 281, 360, 51814 ], "temperature": 0.0, "avg_logprob": -0.20486110470913074, "compression_ratio": 1.9912280701754386, "no_speech_prob": 0.0089874267578125, "words": [ { "start": 949.84, "end": 949.94, "word": " And", "probability": 0.85693359375 }, { "start": 949.94, "end": 950.08, "word": " of", "probability": 0.81640625 }, { "start": 950.08, "end": 950.26, "word": " course", "probability": 0.86962890625 }, { "start": 950.26, "end": 950.32, "word": ",", "probability": 0.720703125 }, { "start": 950.32, "end": 950.54, "word": " we're", "probability": 0.91455078125 }, { "start": 950.54, "end": 950.54, "word": " going", "probability": 0.4892578125 }, { "start": 950.54, "end": 950.62, "word": " to", "probability": 0.90283203125 }, { "start": 950.62, "end": 950.76, "word": " want", "probability": 0.80908203125 }, { "start": 950.76, "end": 950.84, "word": " to", "probability": 0.90283203125 }, { "start": 950.84, "end": 950.92, "word": " do", "probability": 0.900390625 } ] }, { "id": 397, "seek": 97044, "start": 954.22, "end": 955.54, "text": " is say, okay,", "tokens": [ 50364, 307, 584, 11, 1392, 11, 50414 ], "temperature": 0.0, "avg_logprob": -0.17105263113079214, "compression_ratio": 1.8523206751054853, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 954.22, "end": 954.34, "word": " is", "probability": 0.00577545166015625 }, { "start": 954.34, "end": 954.48, "word": " say", "probability": 0.0210418701171875 }, { "start": 954.48, "end": 954.72, "word": ",", "probability": 0.6171875 }, { "start": 954.72, "end": 955.0, "word": " okay", "probability": 0.32177734375 }, { "start": 955.0, "end": 955.54, "word": ",", "probability": 0.89794921875 } ] }, { "id": 398, "seek": 97044, "start": 955.54, "end": 956.92, "text": " whichever is highest,", "tokens": [ 50464, 24123, 307, 6343, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.17105263113079214, "compression_ratio": 1.8523206751054853, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 955.54, "end": 955.84, "word": " whichever", "probability": 0.79736328125 }, { "start": 955.84, "end": 956.12, "word": " is", "probability": 0.9072265625 }, { "start": 956.12, "end": 956.64, "word": " highest", "probability": 0.84814453125 }, { "start": 956.64, "end": 956.92, "word": ",", "probability": 0.70751953125 } ] }, { "id": 399, "seek": 97044, "start": 956.92, "end": 958.04, "text": " sports or not sports,", "tokens": [ 50564, 6573, 420, 406, 6573, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.17105263113079214, "compression_ratio": 1.8523206751054853, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 956.92, "end": 957.2, "word": " sports", "probability": 0.67431640625 }, { "start": 957.2, "end": 957.4, "word": " or", "probability": 0.88623046875 }, { "start": 957.4, "end": 957.6, "word": " not", "probability": 0.8408203125 }, { "start": 957.6, "end": 957.94, "word": " sports", "probability": 0.77880859375 }, { "start": 957.94, "end": 958.04, "word": ",", "probability": 0.8037109375 } ] }, { "id": 400, "seek": 97044, "start": 958.04, "end": 959.5, "text": " that's the one that we're going to classify", "tokens": [ 50664, 300, 311, 264, 472, 300, 321, 434, 516, 281, 33872, 50714 ], "temperature": 0.0, "avg_logprob": -0.17105263113079214, "compression_ratio": 1.8523206751054853, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 958.04, "end": 958.34, "word": " that's", "probability": 0.9375 }, { "start": 958.34, "end": 958.46, "word": " the", "probability": 0.8134765625 }, { "start": 958.46, "end": 958.58, "word": " one", "probability": 0.8291015625 }, { "start": 958.58, "end": 958.68, "word": " that", "probability": 0.85400390625 }, { "start": 958.68, "end": 958.8, "word": " we're", "probability": 0.9248046875 }, { "start": 958.8, "end": 958.88, "word": " going", "probability": 0.399169921875 }, { "start": 958.88, "end": 958.98, "word": " to", "probability": 0.9013671875 }, { "start": 958.98, "end": 959.5, "word": " classify", "probability": 0.93798828125 } ] }, { "id": 401, "seek": 97044, "start": 959.5, "end": 962.14, "text": " this sentence as being part of.", "tokens": [ 50764, 341, 8174, 382, 885, 644, 295, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.17105263113079214, "compression_ratio": 1.8523206751054853, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 959.5, "end": 960.3, "word": " this", "probability": 0.87109375 }, { "start": 960.3, "end": 960.7, "word": " sentence", "probability": 0.81396484375 }, { "start": 960.7, "end": 961.0, "word": " as", "probability": 0.8984375 }, { "start": 961.0, "end": 961.26, "word": " being", "probability": 0.87646484375 }, { "start": 961.26, "end": 961.56, "word": " part", "probability": 0.82666015625 }, { "start": 961.56, "end": 961.74, "word": " of", "probability": 0.8994140625 }, { "start": 961.74, "end": 962.14, "word": ".", "probability": 0.97705078125 } ] }, { "id": 402, "seek": 97044, "start": 963.38, "end": 964.18, "text": " So at this point,", "tokens": [ 50864, 407, 412, 341, 935, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.17105263113079214, "compression_ratio": 1.8523206751054853, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 963.38, "end": 963.78, "word": " So", "probability": 0.8095703125 }, { "start": 963.78, "end": 963.86, "word": " at", "probability": 0.77197265625 }, { "start": 963.86, "end": 963.98, "word": " this", "probability": 0.8779296875 }, { "start": 963.98, "end": 964.14, "word": " point", "probability": 0.85400390625 }, { "start": 964.14, "end": 964.18, "word": ",", "probability": 0.6044921875 } ] }, { "id": 403, "seek": 97044, "start": 964.18, "end": 966.26, "text": " it becomes a simple counting game, right?", "tokens": [ 50964, 309, 3643, 257, 2199, 13251, 1216, 11, 558, 30, 51014 ], "temperature": 0.0, "avg_logprob": -0.17105263113079214, "compression_ratio": 1.8523206751054853, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 964.18, "end": 964.28, "word": " it", "probability": 0.90283203125 }, { "start": 964.28, "end": 964.5, "word": " becomes", "probability": 0.7890625 }, { "start": 964.66, "end": 964.86, "word": " a simple", "probability": 0.89990234375 }, { "start": 964.86, "end": 965.2, "word": " counting", "probability": 0.79833984375 }, { "start": 965.2, "end": 965.44, "word": " game", "probability": 0.8095703125 }, { "start": 965.44, "end": 965.72, "word": ",", "probability": 0.689453125 }, { "start": 965.72, "end": 965.96, "word": " right", "probability": 0.87646484375 }, { "start": 965.96, "end": 966.26, "word": "?", "probability": 0.93408203125 } ] }, { "id": 404, "seek": 97044, "start": 966.26, "end": 968.52, "text": " So how many times does the word A", "tokens": [ 51064, 407, 577, 867, 1413, 775, 264, 1349, 316, 51114 ], "temperature": 0.0, "avg_logprob": -0.17105263113079214, "compression_ratio": 1.8523206751054853, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 966.26, "end": 966.62, "word": " So", "probability": 0.88720703125 }, { "start": 966.62, "end": 966.92, "word": " how", "probability": 0.78515625 }, { "start": 966.92, "end": 967.06, "word": " many", "probability": 0.8037109375 }, { "start": 967.06, "end": 967.36, "word": " times", "probability": 0.82666015625 }, { "start": 967.36, "end": 967.56, "word": " does", "probability": 0.9228515625 }, { "start": 967.56, "end": 967.74, "word": " the", "probability": 0.80859375 }, { "start": 967.74, "end": 968.1, "word": " word", "probability": 0.80078125 }, { "start": 968.1, "end": 968.52, "word": " A", "probability": 0.2000732421875 } ] }, { "id": 405, "seek": 97044, "start": 968.52, "end": 970.16, "text": " show up in sports?", "tokens": [ 51164, 855, 493, 294, 6573, 30, 51214 ], "temperature": 0.0, "avg_logprob": -0.17105263113079214, "compression_ratio": 1.8523206751054853, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 968.52, "end": 968.98, "word": " show", "probability": 0.8544921875 }, { "start": 968.98, "end": 969.18, "word": " up", "probability": 0.912109375 }, { "start": 969.18, "end": 969.38, "word": " in", "probability": 0.90625 }, { "start": 969.38, "end": 969.76, "word": " sports", "probability": 0.77392578125 }, { "start": 969.76, "end": 970.16, "word": "?", "probability": 0.98828125 } ] }, { "id": 406, "seek": 97044, "start": 970.4, "end": 972.14, "text": " Well, we see that it shows up twice,", "tokens": [ 51264, 1042, 11, 321, 536, 300, 309, 3110, 493, 6091, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.17105263113079214, "compression_ratio": 1.8523206751054853, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 970.4, "end": 970.8, "word": " Well", "probability": 0.7412109375 }, { "start": 970.8, "end": 970.88, "word": ",", "probability": 0.966796875 }, { "start": 970.88, "end": 971.04, "word": " we", "probability": 0.90087890625 }, { "start": 971.04, "end": 971.16, "word": " see", "probability": 0.81494140625 }, { "start": 971.16, "end": 971.28, "word": " that", "probability": 0.88232421875 }, { "start": 971.28, "end": 971.4, "word": " it", "probability": 0.90283203125 }, { "start": 971.4, "end": 971.58, "word": " shows", "probability": 0.8115234375 }, { "start": 971.58, "end": 971.72, "word": " up", "probability": 0.9140625 }, { "start": 971.72, "end": 972.04, "word": " twice", "probability": 0.84130859375 }, { "start": 972.04, "end": 972.14, "word": ",", "probability": 0.62890625 } ] }, { "id": 407, "seek": 97044, "start": 972.14, "end": 973.04, "text": " once in the first sentence", "tokens": [ 51364, 1564, 294, 264, 700, 8174, 51414 ], "temperature": 0.0, "avg_logprob": -0.17105263113079214, "compression_ratio": 1.8523206751054853, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 972.14, "end": 972.3, "word": " once", "probability": 0.8193359375 }, { "start": 972.3, "end": 972.4, "word": " in", "probability": 0.904296875 }, { "start": 972.4, "end": 972.52, "word": " the", "probability": 0.81640625 }, { "start": 972.52, "end": 972.7, "word": " first", "probability": 0.8193359375 }, { "start": 972.7, "end": 973.04, "word": " sentence", "probability": 0.81005859375 } ] }, { "id": 408, "seek": 97044, "start": 973.04, "end": 974.52, "text": " and once in the fourth sentence.", "tokens": [ 51464, 293, 1564, 294, 264, 6409, 8174, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.17105263113079214, "compression_ratio": 1.8523206751054853, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 973.04, "end": 973.24, "word": " and", "probability": 0.6826171875 }, { "start": 973.24, "end": 973.44, "word": " once", "probability": 0.81494140625 }, { "start": 973.44, "end": 973.56, "word": " in", "probability": 0.90625 }, { "start": 973.56, "end": 973.66, "word": " the", "probability": 0.8076171875 }, { "start": 973.66, "end": 973.84, "word": " fourth", "probability": 0.84375 }, { "start": 973.84, "end": 974.22, "word": " sentence", "probability": 0.853515625 }, { "start": 974.22, "end": 974.52, "word": ".", "probability": 0.82958984375 } ] }, { "id": 409, "seek": 97044, "start": 974.52, "end": 975.94, "text": " And then how many times does it show up", "tokens": [ 51564, 400, 550, 577, 867, 1413, 775, 309, 855, 493, 51614 ], "temperature": 0.0, "avg_logprob": -0.17105263113079214, "compression_ratio": 1.8523206751054853, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 974.52, "end": 974.68, "word": " And", "probability": 0.8671875 }, { "start": 974.68, "end": 974.78, "word": " then", "probability": 0.72216796875 }, { "start": 974.78, "end": 974.92, "word": " how", "probability": 0.87109375 }, { "start": 974.92, "end": 975.06, "word": " many", "probability": 0.8037109375 }, { "start": 975.06, "end": 975.3, "word": " times", "probability": 0.8076171875 }, { "start": 975.3, "end": 975.48, "word": " does", "probability": 0.9228515625 }, { "start": 975.48, "end": 975.58, "word": " it", "probability": 0.9091796875 }, { "start": 975.58, "end": 975.78, "word": " show", "probability": 0.892578125 }, { "start": 975.78, "end": 975.94, "word": " up", "probability": 0.9072265625 } ] }, { "id": 410, "seek": 97044, "start": 975.94, "end": 977.34, "text": " in not sports?", "tokens": [ 51664, 294, 406, 6573, 30, 51714 ], "temperature": 0.0, "avg_logprob": -0.17105263113079214, "compression_ratio": 1.8523206751054853, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 975.94, "end": 976.18, "word": " in", "probability": 0.9013671875 }, { "start": 976.18, "end": 976.54, "word": " not", "probability": 0.79248046875 }, { "start": 976.54, "end": 976.94, "word": " sports", "probability": 0.7734375 }, { "start": 976.94, "end": 977.34, "word": "?", "probability": 0.939453125 } ] }, { "id": 411, "seek": 97044, "start": 977.54, "end": 979.6, "text": " Once, right there in the fifth sentence.", "tokens": [ 51764, 3443, 11, 558, 456, 294, 264, 9266, 8174, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.17105263113079214, "compression_ratio": 1.8523206751054853, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 977.54, "end": 977.94, "word": " Once", "probability": 0.86669921875 }, { "start": 977.94, "end": 978.18, "word": ",", "probability": 0.69482421875 }, { "start": 978.18, "end": 978.36, "word": " right", "probability": 0.865234375 }, { "start": 978.36, "end": 978.52, "word": " there", "probability": 0.8525390625 }, { "start": 978.52, "end": 978.6, "word": " in", "probability": 0.89111328125 }, { "start": 978.6, "end": 978.7, "word": " the", "probability": 0.80224609375 }, { "start": 978.7, "end": 978.84, "word": " fifth", "probability": 0.88818359375 }, { "start": 978.84, "end": 979.2, "word": " sentence", "probability": 0.83349609375 }, { "start": 979.2, "end": 979.6, "word": ".", "probability": 0.896484375 } ] }, { "id": 412, "seek": 100044, "start": 984.22, "end": 985.36, "text": " So A does not show up in sports.", "tokens": [ 50364, 407, 316, 775, 406, 855, 493, 294, 6573, 13, 50414 ], "temperature": 0.0, "avg_logprob": -0.17898787068786906, "compression_ratio": 1.8547717842323652, "no_speech_prob": 0.0029811859130859375, "words": [ { "start": 984.22, "end": 984.22, "word": " So", "probability": 0.0186309814453125 }, { "start": 984.22, "end": 984.22, "word": " A", "probability": 0.046905517578125 }, { "start": 984.22, "end": 984.3, "word": " does", "probability": 0.76611328125 }, { "start": 984.3, "end": 984.6, "word": " not", "probability": 0.8759765625 }, { "start": 984.6, "end": 984.78, "word": " show", "probability": 0.86962890625 }, { "start": 984.78, "end": 984.9, "word": " up", "probability": 0.91015625 }, { "start": 984.9, "end": 985.02, "word": " in", "probability": 0.90771484375 }, { "start": 985.02, "end": 985.28, "word": " sports", "probability": 0.69921875 }, { "start": 985.28, "end": 985.36, "word": ".", "probability": 0.289306640625 } ] }, { "id": 413, "seek": 100044, "start": 985.36, "end": 986.92, "text": " It only shows up in not sports.", "tokens": [ 50464, 467, 787, 3110, 493, 294, 406, 6573, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.17898787068786906, "compression_ratio": 1.8547717842323652, "no_speech_prob": 0.0029811859130859375, "words": [ { "start": 985.36, "end": 985.44, "word": " It", "probability": 0.8857421875 }, { "start": 985.44, "end": 985.66, "word": " only", "probability": 0.87158203125 }, { "start": 985.66, "end": 985.9, "word": " shows", "probability": 0.81494140625 }, { "start": 985.9, "end": 986.04, "word": " up", "probability": 0.90625 }, { "start": 986.04, "end": 986.16, "word": " in", "probability": 0.806640625 }, { "start": 986.16, "end": 986.36, "word": " not", "probability": 0.8193359375 }, { "start": 986.36, "end": 986.74, "word": " sports", "probability": 0.73388671875 }, { "start": 986.74, "end": 986.92, "word": ".", "probability": 0.857421875 } ] }, { "id": 414, "seek": 100044, "start": 986.92, "end": 988.04, "text": " And then we see the word game", "tokens": [ 50564, 400, 550, 321, 536, 264, 1349, 1216, 50614 ], "temperature": 0.0, "avg_logprob": -0.17898787068786906, "compression_ratio": 1.8547717842323652, "no_speech_prob": 0.0029811859130859375, "words": [ { "start": 986.92, "end": 987.0, "word": " And", "probability": 0.86767578125 }, { "start": 987.0, "end": 987.08, "word": " then", "probability": 0.732421875 }, { "start": 987.08, "end": 987.18, "word": " we", "probability": 0.8974609375 }, { "start": 987.18, "end": 987.32, "word": " see", "probability": 0.8154296875 }, { "start": 987.32, "end": 987.46, "word": " the", "probability": 0.81005859375 }, { "start": 987.46, "end": 987.64, "word": " word", "probability": 0.83642578125 }, { "start": 987.64, "end": 988.04, "word": " game", "probability": 0.4453125 } ] }, { "id": 415, "seek": 100044, "start": 988.04, "end": 990.04, "text": " show up twice in sports.", "tokens": [ 50664, 855, 493, 6091, 294, 6573, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.17898787068786906, "compression_ratio": 1.8547717842323652, "no_speech_prob": 0.0029811859130859375, "words": [ { "start": 988.04, "end": 988.32, "word": " show", "probability": 0.8203125 }, { "start": 988.32, "end": 988.48, "word": " up", "probability": 0.9208984375 }, { "start": 988.48, "end": 988.88, "word": " twice", "probability": 0.84130859375 }, { "start": 988.88, "end": 989.3, "word": " in", "probability": 0.857421875 }, { "start": 989.3, "end": 989.68, "word": " sports", "probability": 0.7802734375 }, { "start": 989.68, "end": 990.04, "word": ".", "probability": 0.98046875 } ] }, { "id": 416, "seek": 100044, "start": 991.74, "end": 993.02, "text": " So we just take those numbers", "tokens": [ 50764, 407, 321, 445, 747, 729, 3547, 50814 ], "temperature": 0.0, "avg_logprob": -0.17898787068786906, "compression_ratio": 1.8547717842323652, "no_speech_prob": 0.0029811859130859375, "words": [ { "start": 991.74, "end": 992.1, "word": " So", "probability": 0.8994140625 }, { "start": 992.1, "end": 992.22, "word": " we", "probability": 0.8603515625 }, { "start": 992.22, "end": 992.34, "word": " just", "probability": 0.88232421875 }, { "start": 992.34, "end": 992.54, "word": " take", "probability": 0.80224609375 }, { "start": 992.54, "end": 992.72, "word": " those", "probability": 0.85205078125 }, { "start": 992.72, "end": 993.02, "word": " numbers", "probability": 0.86083984375 } ] }, { "id": 417, "seek": 100044, "start": 993.02, "end": 994.62, "text": " and we plug them in and we say,", "tokens": [ 50864, 293, 321, 5452, 552, 294, 293, 321, 584, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.17898787068786906, "compression_ratio": 1.8547717842323652, "no_speech_prob": 0.0029811859130859375, "words": [ { "start": 993.02, "end": 993.16, "word": " and", "probability": 0.86279296875 }, { "start": 993.16, "end": 993.28, "word": " we", "probability": 0.90966796875 }, { "start": 993.28, "end": 993.5, "word": " plug", "probability": 0.7197265625 }, { "start": 993.5, "end": 993.66, "word": " them", "probability": 0.7275390625 }, { "start": 993.66, "end": 993.88, "word": " in", "probability": 0.90576171875 }, { "start": 993.88, "end": 994.06, "word": " and", "probability": 0.75439453125 }, { "start": 994.06, "end": 994.2, "word": " we", "probability": 0.89990234375 }, { "start": 994.2, "end": 994.46, "word": " say", "probability": 0.8837890625 }, { "start": 994.46, "end": 994.62, "word": ",", "probability": 0.87060546875 } ] }, { "id": 418, "seek": 100044, "start": 994.62, "end": 996.72, "text": " okay, A showed up in sports twice,", "tokens": [ 50964, 1392, 11, 316, 4712, 493, 294, 6573, 6091, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.17898787068786906, "compression_ratio": 1.8547717842323652, "no_speech_prob": 0.0029811859130859375, "words": [ { "start": 994.62, "end": 994.8, "word": " okay", "probability": 0.64697265625 }, { "start": 994.8, "end": 994.92, "word": ",", "probability": 0.65576171875 }, { "start": 994.92, "end": 995.08, "word": " A", "probability": 0.94482421875 }, { "start": 995.08, "end": 995.3, "word": " showed", "probability": 0.80517578125 }, { "start": 995.3, "end": 995.44, "word": " up", "probability": 0.91357421875 }, { "start": 995.44, "end": 995.58, "word": " in", "probability": 0.9072265625 }, { "start": 995.58, "end": 995.94, "word": " sports", "probability": 0.77685546875 }, { "start": 995.94, "end": 996.44, "word": " twice", "probability": 0.84130859375 }, { "start": 996.44, "end": 996.72, "word": ",", "probability": 0.5732421875 } ] }, { "id": 419, "seek": 100044, "start": 996.72, "end": 997.94, "text": " very showed up once,", "tokens": [ 51064, 588, 4712, 493, 1564, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.17898787068786906, "compression_ratio": 1.8547717842323652, "no_speech_prob": 0.0029811859130859375, "words": [ { "start": 996.72, "end": 996.84, "word": " very", "probability": 0.326171875 }, { "start": 996.84, "end": 997.12, "word": " showed", "probability": 0.81201171875 }, { "start": 997.12, "end": 997.28, "word": " up", "probability": 0.912109375 }, { "start": 997.28, "end": 997.76, "word": " once", "probability": 0.78515625 }, { "start": 997.76, "end": 997.94, "word": ",", "probability": 0.77978515625 } ] }, { "id": 420, "seek": 100044, "start": 997.94, "end": 999.74, "text": " close showed up zero times,", "tokens": [ 51164, 1998, 4712, 493, 4018, 1413, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.17898787068786906, "compression_ratio": 1.8547717842323652, "no_speech_prob": 0.0029811859130859375, "words": [ { "start": 997.94, "end": 998.24, "word": " close", "probability": 0.7861328125 }, { "start": 998.24, "end": 998.72, "word": " showed", "probability": 0.67431640625 }, { "start": 998.72, "end": 998.86, "word": " up", "probability": 0.91064453125 }, { "start": 998.86, "end": 999.08, "word": " zero", "probability": 0.7900390625 }, { "start": 999.08, "end": 999.56, "word": " times", "probability": 0.8193359375 }, { "start": 999.56, "end": 999.74, "word": ",", "probability": 0.24609375 } ] }, { "id": 421, "seek": 100044, "start": 999.74, "end": 1001.18, "text": " and game showed up twice.", "tokens": [ 51264, 293, 1216, 4712, 493, 6091, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.17898787068786906, "compression_ratio": 1.8547717842323652, "no_speech_prob": 0.0029811859130859375, "words": [ { "start": 999.74, "end": 999.82, "word": " and", "probability": 0.89501953125 }, { "start": 999.82, "end": 1000.06, "word": " game", "probability": 0.70361328125 }, { "start": 1000.06, "end": 1000.28, "word": " showed", "probability": 0.8359375 }, { "start": 1000.28, "end": 1000.42, "word": " up", "probability": 0.912109375 }, { "start": 1000.42, "end": 1000.82, "word": " twice", "probability": 0.8486328125 }, { "start": 1000.82, "end": 1001.18, "word": ".", "probability": 0.98974609375 } ] }, { "id": 422, "seek": 100044, "start": 1001.28, "end": 1003.12, "text": " And if we counted the number of unique words,", "tokens": [ 51364, 400, 498, 321, 20150, 264, 1230, 295, 3845, 2283, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.17898787068786906, "compression_ratio": 1.8547717842323652, "no_speech_prob": 0.0029811859130859375, "words": [ { "start": 1001.28, "end": 1001.42, "word": " And", "probability": 0.89599609375 }, { "start": 1001.42, "end": 1001.52, "word": " if", "probability": 0.90380859375 }, { "start": 1001.52, "end": 1001.62, "word": " we", "probability": 0.9052734375 }, { "start": 1001.62, "end": 1001.84, "word": " counted", "probability": 0.79833984375 }, { "start": 1001.84, "end": 1002.02, "word": " the", "probability": 0.81396484375 }, { "start": 1002.02, "end": 1002.22, "word": " number", "probability": 0.88818359375 }, { "start": 1002.22, "end": 1002.42, "word": " of", "probability": 0.90673828125 }, { "start": 1002.42, "end": 1002.7, "word": " unique", "probability": 0.77490234375 }, { "start": 1002.7, "end": 1003.06, "word": " words", "probability": 0.732421875 }, { "start": 1003.06, "end": 1003.12, "word": ",", "probability": 0.703125 } ] }, { "id": 423, "seek": 100044, "start": 1003.12, "end": 1005.08, "text": " we would have had 11 unique words", "tokens": [ 51464, 321, 576, 362, 632, 2975, 3845, 2283, 51514 ], "temperature": 0.0, "avg_logprob": -0.17898787068786906, "compression_ratio": 1.8547717842323652, "no_speech_prob": 0.0029811859130859375, "words": [ { "start": 1003.12, "end": 1003.22, "word": " we", "probability": 0.90380859375 }, { "start": 1003.22, "end": 1003.34, "word": " would", "probability": 0.8505859375 }, { "start": 1003.34, "end": 1003.44, "word": " have", "probability": 0.8359375 }, { "start": 1003.44, "end": 1003.78, "word": " had", "probability": 0.8046875 }, { "start": 1003.78, "end": 1004.2, "word": " 11", "probability": 0.91455078125 }, { "start": 1004.2, "end": 1004.68, "word": " unique", "probability": 0.76806640625 }, { "start": 1004.68, "end": 1005.08, "word": " words", "probability": 0.67333984375 } ] }, { "id": 424, "seek": 100044, "start": 1005.08, "end": 1006.24, "text": " across all of our sentences", "tokens": [ 51564, 2108, 439, 295, 527, 16579, 51614 ], "temperature": 0.0, "avg_logprob": -0.17898787068786906, "compression_ratio": 1.8547717842323652, "no_speech_prob": 0.0029811859130859375, "words": [ { "start": 1005.08, "end": 1005.4, "word": " across", "probability": 0.666015625 }, { "start": 1005.4, "end": 1005.66, "word": " all", "probability": 0.9072265625 }, { "start": 1005.66, "end": 1005.78, "word": " of", "probability": 0.9052734375 }, { "start": 1005.78, "end": 1005.9, "word": " our", "probability": 0.83154296875 }, { "start": 1005.9, "end": 1006.24, "word": " sentences", "probability": 0.9052734375 } ] }, { "id": 425, "seek": 100044, "start": 1006.64, "end": 1008.02, "text": " talking about sports.", "tokens": [ 51664, 1417, 466, 6573, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.17898787068786906, "compression_ratio": 1.8547717842323652, "no_speech_prob": 0.0029811859130859375, "words": [ { "start": 1006.64, "end": 1007.0, "word": " talking", "probability": 0.60205078125 }, { "start": 1007.0, "end": 1007.22, "word": " about", "probability": 0.810546875 }, { "start": 1007.22, "end": 1007.66, "word": " sports", "probability": 0.77978515625 }, { "start": 1007.66, "end": 1008.02, "word": ".", "probability": 0.76904296875 } ] }, { "id": 426, "seek": 100044, "start": 1008.88, "end": 1010.24, "text": " But we run into a problem", "tokens": [ 51764, 583, 321, 1190, 666, 257, 1154, 51814 ], "temperature": 0.0, "avg_logprob": -0.17898787068786906, "compression_ratio": 1.8547717842323652, "no_speech_prob": 0.0029811859130859375, "words": [ { "start": 1008.88, "end": 1009.24, "word": " But", "probability": 0.88623046875 }, { "start": 1009.24, "end": 1009.34, "word": " we", "probability": 0.908203125 }, { "start": 1009.34, "end": 1009.5, "word": " run", "probability": 0.8232421875 }, { "start": 1009.5, "end": 1009.64, "word": " into", "probability": 0.73095703125 }, { "start": 1009.82, "end": 1010.24, "word": " a problem", "probability": 0.76953125 } ] }, { "id": 427, "seek": 103044, "start": 1014.62, "end": 1016.28, "text": " and the problem is that", "tokens": [ 50364, 293, 264, 1154, 307, 300, 50414 ], "temperature": 0.0, "avg_logprob": -0.1505055174450664, "compression_ratio": 1.7854545454545454, "no_speech_prob": 6.401538848876953e-05, "words": [ { "start": 1014.62, "end": 1015.06, "word": " and", "probability": 0.10540771484375 }, { "start": 1015.06, "end": 1015.14, "word": " the", "probability": 0.75927734375 }, { "start": 1015.14, "end": 1015.42, "word": " problem", "probability": 0.75390625 }, { "start": 1015.42, "end": 1015.8, "word": " is", "probability": 0.8662109375 }, { "start": 1015.8, "end": 1016.28, "word": " that", "probability": 0.8427734375 } ] }, { "id": 428, "seek": 103044, "start": 1016.28, "end": 1018.1, "text": " what we want our machine learning model to do", "tokens": [ 50464, 437, 321, 528, 527, 3479, 2539, 2316, 281, 360, 50514 ], "temperature": 0.0, "avg_logprob": -0.1505055174450664, "compression_ratio": 1.7854545454545454, "no_speech_prob": 6.401538848876953e-05, "words": [ { "start": 1016.28, "end": 1016.78, "word": " what", "probability": 0.8408203125 }, { "start": 1016.78, "end": 1016.9, "word": " we", "probability": 0.90283203125 }, { "start": 1016.9, "end": 1017.04, "word": " want", "probability": 0.810546875 }, { "start": 1017.04, "end": 1017.14, "word": " our", "probability": 0.75390625 }, { "start": 1017.14, "end": 1017.34, "word": " machine", "probability": 0.6337890625 }, { "start": 1017.34, "end": 1017.54, "word": " learning", "probability": 0.8046875 }, { "start": 1017.54, "end": 1017.74, "word": " model", "probability": 0.82080078125 }, { "start": 1017.74, "end": 1017.9, "word": " to", "probability": 0.900390625 }, { "start": 1017.9, "end": 1018.1, "word": " do", "probability": 0.9052734375 } ] }, { "id": 429, "seek": 103044, "start": 1018.1, "end": 1020.56, "text": " is identify and classify sentences", "tokens": [ 50564, 307, 5876, 293, 33872, 16579, 50614 ], "temperature": 0.0, "avg_logprob": -0.1505055174450664, "compression_ratio": 1.7854545454545454, "no_speech_prob": 6.401538848876953e-05, "words": [ { "start": 1018.1, "end": 1018.3, "word": " is", "probability": 0.87451171875 }, { "start": 1018.3, "end": 1018.78, "word": " identify", "probability": 0.8583984375 }, { "start": 1018.78, "end": 1019.06, "word": " and", "probability": 0.88818359375 }, { "start": 1019.06, "end": 1019.54, "word": " classify", "probability": 0.94091796875 }, { "start": 1019.54, "end": 1020.56, "word": " sentences", "probability": 0.86181640625 } ] }, { "id": 430, "seek": 103044, "start": 1020.56, "end": 1022.4, "text": " that it has never seen before.", "tokens": [ 50664, 300, 309, 575, 1128, 1612, 949, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.1505055174450664, "compression_ratio": 1.7854545454545454, "no_speech_prob": 6.401538848876953e-05, "words": [ { "start": 1020.56, "end": 1020.78, "word": " that", "probability": 0.87353515625 }, { "start": 1020.78, "end": 1020.86, "word": " it", "probability": 0.89306640625 }, { "start": 1020.86, "end": 1021.0, "word": " has", "probability": 0.8916015625 }, { "start": 1021.0, "end": 1021.22, "word": " never", "probability": 0.861328125 }, { "start": 1021.22, "end": 1021.52, "word": " seen", "probability": 0.88671875 }, { "start": 1021.52, "end": 1021.96, "word": " before", "probability": 0.79296875 }, { "start": 1021.96, "end": 1022.4, "word": ".", "probability": 0.828125 } ] }, { "id": 431, "seek": 103044, "start": 1022.96, "end": 1024.54, "text": " Unfortunately, it's never seen close", "tokens": [ 50764, 8590, 11, 309, 311, 1128, 1612, 1998, 50814 ], "temperature": 0.0, "avg_logprob": -0.1505055174450664, "compression_ratio": 1.7854545454545454, "no_speech_prob": 6.401538848876953e-05, "words": [ { "start": 1022.96, "end": 1023.4, "word": " Unfortunately", "probability": 0.75537109375 }, { "start": 1023.4, "end": 1023.66, "word": ",", "probability": 0.640625 }, { "start": 1023.66, "end": 1023.78, "word": " it's", "probability": 0.93994140625 }, { "start": 1023.78, "end": 1023.94, "word": " never", "probability": 0.865234375 }, { "start": 1023.94, "end": 1024.16, "word": " seen", "probability": 0.8720703125 }, { "start": 1024.16, "end": 1024.54, "word": " close", "probability": 0.7255859375 } ] }, { "id": 432, "seek": 103044, "start": 1024.54, "end": 1026.06, "text": " and so that winds up being a zero,", "tokens": [ 50864, 293, 370, 300, 17765, 493, 885, 257, 4018, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.1505055174450664, "compression_ratio": 1.7854545454545454, "no_speech_prob": 6.401538848876953e-05, "words": [ { "start": 1024.54, "end": 1024.76, "word": " and", "probability": 0.422607421875 }, { "start": 1024.76, "end": 1024.88, "word": " so", "probability": 0.89111328125 }, { "start": 1024.88, "end": 1025.04, "word": " that", "probability": 0.87158203125 }, { "start": 1025.04, "end": 1025.22, "word": " winds", "probability": 0.85400390625 }, { "start": 1025.22, "end": 1025.36, "word": " up", "probability": 0.9111328125 }, { "start": 1025.36, "end": 1025.54, "word": " being", "probability": 0.875 }, { "start": 1025.68, "end": 1025.9, "word": " a zero", "probability": 0.658203125 }, { "start": 1025.9, "end": 1026.06, "word": ",", "probability": 0.437255859375 } ] }, { "id": 433, "seek": 103044, "start": 1026.06, "end": 1028.38, "text": " zero times everything is zero.", "tokens": [ 50964, 4018, 1413, 1203, 307, 4018, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.1505055174450664, "compression_ratio": 1.7854545454545454, "no_speech_prob": 6.401538848876953e-05, "words": [ { "start": 1026.06, "end": 1026.22, "word": " zero", "probability": 0.80078125 }, { "start": 1026.22, "end": 1026.48, "word": " times", "probability": 0.78369140625 }, { "start": 1026.48, "end": 1026.88, "word": " everything", "probability": 0.86865234375 }, { "start": 1026.88, "end": 1027.6, "word": " is", "probability": 0.8515625 }, { "start": 1027.6, "end": 1027.96, "word": " zero", "probability": 0.8193359375 }, { "start": 1027.96, "end": 1028.38, "word": ".", "probability": 0.488037109375 } ] }, { "id": 434, "seek": 103044, "start": 1028.38, "end": 1030.26, "text": " And we see that that easily cascades down", "tokens": [ 51064, 400, 321, 536, 300, 300, 3612, 3058, 66, 2977, 760, 51114 ], "temperature": 0.0, "avg_logprob": -0.1505055174450664, "compression_ratio": 1.7854545454545454, "no_speech_prob": 6.401538848876953e-05, "words": [ { "start": 1028.38, "end": 1028.48, "word": " And", "probability": 0.75439453125 }, { "start": 1028.48, "end": 1028.56, "word": " we", "probability": 0.900390625 }, { "start": 1028.56, "end": 1028.7, "word": " see", "probability": 0.81689453125 }, { "start": 1028.7, "end": 1028.82, "word": " that", "probability": 0.8818359375 }, { "start": 1028.82, "end": 1028.98, "word": " that", "probability": 0.80419921875 }, { "start": 1028.98, "end": 1029.32, "word": " easily", "probability": 0.83837890625 }, { "start": 1029.32, "end": 1029.94, "word": " cascades", "probability": 0.9322916666666666 }, { "start": 1029.94, "end": 1030.26, "word": " down", "probability": 0.80322265625 } ] }, { "id": 435, "seek": 103044, "start": 1030.26, "end": 1031.38, "text": " and just ruins our model.", "tokens": [ 51164, 293, 445, 24747, 527, 2316, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.1505055174450664, "compression_ratio": 1.7854545454545454, "no_speech_prob": 6.401538848876953e-05, "words": [ { "start": 1030.26, "end": 1030.38, "word": " and", "probability": 0.8740234375 }, { "start": 1030.38, "end": 1030.56, "word": " just", "probability": 0.890625 }, { "start": 1030.56, "end": 1030.82, "word": " ruins", "probability": 0.82861328125 }, { "start": 1030.82, "end": 1031.0, "word": " our", "probability": 0.814453125 }, { "start": 1031.0, "end": 1031.24, "word": " model", "probability": 0.77099609375 }, { "start": 1031.24, "end": 1031.38, "word": ".", "probability": 0.87548828125 } ] }, { "id": 436, "seek": 103044, "start": 1031.38, "end": 1033.12, "text": " So it's because we've never seen the word close,", "tokens": [ 51264, 407, 309, 311, 570, 321, 600, 1128, 1612, 264, 1349, 1998, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.1505055174450664, "compression_ratio": 1.7854545454545454, "no_speech_prob": 6.401538848876953e-05, "words": [ { "start": 1031.38, "end": 1031.48, "word": " So", "probability": 0.6767578125 }, { "start": 1031.48, "end": 1031.56, "word": " it's", "probability": 0.880859375 }, { "start": 1031.56, "end": 1031.82, "word": " because", "probability": 0.8359375 }, { "start": 1031.82, "end": 1032.08, "word": " we've", "probability": 0.924072265625 }, { "start": 1032.08, "end": 1032.24, "word": " never", "probability": 0.86865234375 }, { "start": 1032.24, "end": 1032.44, "word": " seen", "probability": 0.88427734375 }, { "start": 1032.44, "end": 1032.56, "word": " the", "probability": 0.81298828125 }, { "start": 1032.56, "end": 1032.7, "word": " word", "probability": 0.7939453125 }, { "start": 1032.7, "end": 1033.02, "word": " close", "probability": 0.791015625 }, { "start": 1033.02, "end": 1033.12, "word": ",", "probability": 0.6533203125 } ] }, { "id": 437, "seek": 103044, "start": 1033.12, "end": 1034.28, "text": " there's a zero probability", "tokens": [ 51364, 456, 311, 257, 4018, 8482, 51414 ], "temperature": 0.0, "avg_logprob": -0.1505055174450664, "compression_ratio": 1.7854545454545454, "no_speech_prob": 6.401538848876953e-05, "words": [ { "start": 1033.12, "end": 1033.36, "word": " there's", "probability": 0.892578125 }, { "start": 1033.5, "end": 1033.74, "word": " a zero", "probability": 0.82421875 }, { "start": 1033.74, "end": 1034.28, "word": " probability", "probability": 0.89111328125 } ] }, { "id": 438, "seek": 103044, "start": 1034.78, "end": 1037.18, "text": " that this exists in our sentence.", "tokens": [ 51464, 300, 341, 8198, 294, 527, 8174, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.1505055174450664, "compression_ratio": 1.7854545454545454, "no_speech_prob": 6.401538848876953e-05, "words": [ { "start": 1034.78, "end": 1035.22, "word": " that", "probability": 0.880859375 }, { "start": 1035.22, "end": 1035.66, "word": " this", "probability": 0.8759765625 }, { "start": 1035.66, "end": 1036.02, "word": " exists", "probability": 0.7919921875 }, { "start": 1036.02, "end": 1036.26, "word": " in", "probability": 0.90576171875 }, { "start": 1036.26, "end": 1036.4, "word": " our", "probability": 0.82177734375 }, { "start": 1036.4, "end": 1036.74, "word": " sentence", "probability": 0.81103515625 }, { "start": 1036.74, "end": 1037.18, "word": ".", "probability": 0.97119140625 } ] }, { "id": 439, "seek": 103044, "start": 1038.08, "end": 1039.32, "text": " So that's a problem,", "tokens": [ 51564, 407, 300, 311, 257, 1154, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.1505055174450664, "compression_ratio": 1.7854545454545454, "no_speech_prob": 6.401538848876953e-05, "words": [ { "start": 1038.08, "end": 1038.52, "word": " So", "probability": 0.900390625 }, { "start": 1038.52, "end": 1038.7, "word": " that's", "probability": 0.931396484375 }, { "start": 1038.8, "end": 1039.1, "word": " a problem", "probability": 0.76708984375 }, { "start": 1039.1, "end": 1039.32, "word": ",", "probability": 0.689453125 } ] }, { "id": 440, "seek": 103044, "start": 1039.76, "end": 1041.48, "text": " but we can get around that.", "tokens": [ 51664, 457, 321, 393, 483, 926, 300, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.1505055174450664, "compression_ratio": 1.7854545454545454, "no_speech_prob": 6.401538848876953e-05, "words": [ { "start": 1039.76, "end": 1040.02, "word": " but", "probability": 0.9033203125 }, { "start": 1040.02, "end": 1040.36, "word": " we", "probability": 0.89990234375 }, { "start": 1040.36, "end": 1040.48, "word": " can", "probability": 0.89404296875 }, { "start": 1040.48, "end": 1040.6, "word": " get", "probability": 0.90625 }, { "start": 1040.6, "end": 1040.8, "word": " around", "probability": 0.8759765625 }, { "start": 1040.8, "end": 1041.04, "word": " that", "probability": 0.88232421875 }, { "start": 1041.04, "end": 1041.48, "word": ".", "probability": 0.9951171875 } ] }, { "id": 441, "seek": 103044, "start": 1042.7, "end": 1043.74, "text": " There's another algorithm", "tokens": [ 51764, 821, 311, 1071, 9284, 51814 ], "temperature": 0.0, "avg_logprob": -0.1505055174450664, "compression_ratio": 1.7854545454545454, "no_speech_prob": 6.401538848876953e-05, "words": [ { "start": 1042.7, "end": 1043.14, "word": " There's", "probability": 0.9033203125 }, { "start": 1043.14, "end": 1043.34, "word": " another", "probability": 0.83203125 }, { "start": 1043.34, "end": 1043.74, "word": " algorithm", "probability": 0.81640625 } ] }, { "id": 442, "seek": 106044, "start": 1044.22, "end": 1046.06, "text": " called multinomial Naive Bayes.", "tokens": [ 50364, 1219, 45872, 47429, 6056, 488, 7840, 279, 13, 50414 ], "temperature": 0.0, "avg_logprob": -0.15318434119601793, "compression_ratio": 1.9722222222222223, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 1044.22, "end": 1044.32, "word": " called", "probability": 0.01468658447265625 }, { "start": 1044.32, "end": 1044.98, "word": " multinomial", "probability": 0.857666015625 }, { "start": 1044.98, "end": 1045.36, "word": " Naive", "probability": 0.6295166015625 }, { "start": 1045.36, "end": 1045.7, "word": " Bayes", "probability": 0.92529296875 }, { "start": 1045.7, "end": 1046.06, "word": ".", "probability": 0.791015625 } ] }, { "id": 443, "seek": 106044, "start": 1046.18, "end": 1048.0, "text": " And so this is just a small modification", "tokens": [ 50464, 400, 370, 341, 307, 445, 257, 1359, 26747, 50514 ], "temperature": 0.0, "avg_logprob": -0.15318434119601793, "compression_ratio": 1.9722222222222223, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 1046.18, "end": 1046.4, "word": " And", "probability": 0.62451171875 }, { "start": 1046.4, "end": 1046.54, "word": " so", "probability": 0.88671875 }, { "start": 1046.54, "end": 1046.72, "word": " this", "probability": 0.8056640625 }, { "start": 1046.72, "end": 1046.84, "word": " is", "probability": 0.9052734375 }, { "start": 1046.84, "end": 1046.98, "word": " just", "probability": 0.89013671875 }, { "start": 1047.14, "end": 1047.34, "word": " a small", "probability": 0.86474609375 }, { "start": 1047.34, "end": 1048.0, "word": " modification", "probability": 0.80908203125 } ] }, { "id": 444, "seek": 106044, "start": 1048.0, "end": 1049.7, "text": " and what it does is add", "tokens": [ 50564, 293, 437, 309, 775, 307, 909, 50614 ], "temperature": 0.0, "avg_logprob": -0.15318434119601793, "compression_ratio": 1.9722222222222223, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 1048.0, "end": 1048.46, "word": " and", "probability": 0.38818359375 }, { "start": 1048.46, "end": 1048.62, "word": " what", "probability": 0.873046875 }, { "start": 1048.62, "end": 1048.76, "word": " it", "probability": 0.90087890625 }, { "start": 1048.76, "end": 1049.04, "word": " does", "probability": 0.91845703125 }, { "start": 1049.04, "end": 1049.3, "word": " is", "probability": 0.892578125 }, { "start": 1049.3, "end": 1049.7, "word": " add", "probability": 0.814453125 } ] }, { "id": 445, "seek": 106044, "start": 1049.7, "end": 1051.14, "text": " what is called a smoothing filter.", "tokens": [ 50664, 437, 307, 1219, 257, 899, 6259, 571, 6608, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.15318434119601793, "compression_ratio": 1.9722222222222223, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 1049.7, "end": 1049.94, "word": " what", "probability": 0.85205078125 }, { "start": 1049.94, "end": 1050.06, "word": " is", "probability": 0.8955078125 }, { "start": 1050.06, "end": 1050.2, "word": " called", "probability": 0.814453125 }, { "start": 1050.36, "end": 1050.72, "word": " a smoothing", "probability": 0.9088541666666666 }, { "start": 1050.72, "end": 1051.06, "word": " filter", "probability": 0.8955078125 }, { "start": 1051.06, "end": 1051.14, "word": ".", "probability": 0.376953125 } ] }, { "id": 446, "seek": 106044, "start": 1051.14, "end": 1053.08, "text": " And we can see this alpha here.", "tokens": [ 50764, 400, 321, 393, 536, 341, 8961, 510, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.15318434119601793, "compression_ratio": 1.9722222222222223, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 1051.14, "end": 1051.2, "word": " And", "probability": 0.7763671875 }, { "start": 1051.2, "end": 1051.28, "word": " we", "probability": 0.89794921875 }, { "start": 1051.28, "end": 1051.4, "word": " can", "probability": 0.89990234375 }, { "start": 1051.4, "end": 1051.56, "word": " see", "probability": 0.8154296875 }, { "start": 1051.56, "end": 1051.82, "word": " this", "probability": 0.87255859375 }, { "start": 1051.82, "end": 1052.2, "word": " alpha", "probability": 0.74951171875 }, { "start": 1052.2, "end": 1052.94, "word": " here", "probability": 0.7861328125 }, { "start": 1052.94, "end": 1053.08, "word": ".", "probability": 0.32958984375 } ] }, { "id": 447, "seek": 106044, "start": 1053.08, "end": 1055.74, "text": " It's added to the numerator and the denominator.", "tokens": [ 50864, 467, 311, 3869, 281, 264, 30380, 293, 264, 20687, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.15318434119601793, "compression_ratio": 1.9722222222222223, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 1053.08, "end": 1053.14, "word": " It's", "probability": 0.947509765625 }, { "start": 1053.14, "end": 1053.32, "word": " added", "probability": 0.794921875 }, { "start": 1053.32, "end": 1053.5, "word": " to", "probability": 0.90625 }, { "start": 1053.5, "end": 1053.96, "word": " the", "probability": 0.81787109375 }, { "start": 1053.96, "end": 1054.38, "word": " numerator", "probability": 0.826171875 }, { "start": 1054.38, "end": 1054.78, "word": " and", "probability": 0.89208984375 }, { "start": 1054.78, "end": 1054.9, "word": " the", "probability": 0.81103515625 }, { "start": 1054.9, "end": 1055.38, "word": " denominator", "probability": 0.87451171875 }, { "start": 1055.38, "end": 1055.74, "word": ".", "probability": 0.8642578125 } ] }, { "id": 448, "seek": 106044, "start": 1055.8, "end": 1057.46, "text": " And usually this alpha is one,", "tokens": [ 50964, 400, 2673, 341, 8961, 307, 472, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.15318434119601793, "compression_ratio": 1.9722222222222223, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 1055.8, "end": 1056.1, "word": " And", "probability": 0.88623046875 }, { "start": 1056.1, "end": 1056.36, "word": " usually", "probability": 0.82470703125 }, { "start": 1056.36, "end": 1056.62, "word": " this", "probability": 0.841796875 }, { "start": 1056.62, "end": 1056.88, "word": " alpha", "probability": 0.7861328125 }, { "start": 1056.88, "end": 1057.06, "word": " is", "probability": 0.87646484375 }, { "start": 1057.06, "end": 1057.36, "word": " one", "probability": 0.767578125 }, { "start": 1057.36, "end": 1057.46, "word": ",", "probability": 0.5986328125 } ] }, { "id": 449, "seek": 106044, "start": 1057.46, "end": 1059.42, "text": " but this is going to be our hyperparameter", "tokens": [ 51064, 457, 341, 307, 516, 281, 312, 527, 9848, 2181, 335, 2398, 51114 ], "temperature": 0.0, "avg_logprob": -0.15318434119601793, "compression_ratio": 1.9722222222222223, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 1057.46, "end": 1057.56, "word": " but", "probability": 0.8984375 }, { "start": 1057.56, "end": 1057.76, "word": " this", "probability": 0.884765625 }, { "start": 1057.76, "end": 1057.92, "word": " is", "probability": 0.90673828125 }, { "start": 1057.92, "end": 1058.02, "word": " going", "probability": 0.454345703125 }, { "start": 1058.02, "end": 1058.06, "word": " to", "probability": 0.9013671875 }, { "start": 1058.06, "end": 1058.26, "word": " be", "probability": 0.904296875 }, { "start": 1058.26, "end": 1058.62, "word": " our", "probability": 0.81640625 }, { "start": 1058.62, "end": 1059.42, "word": " hyperparameter", "probability": 0.79974365234375 } ] }, { "id": 450, "seek": 106044, "start": 1059.42, "end": 1061.6, "text": " for Naive Bayesian,", "tokens": [ 51164, 337, 6056, 488, 7840, 42434, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.15318434119601793, "compression_ratio": 1.9722222222222223, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 1059.42, "end": 1059.84, "word": " for", "probability": 0.8642578125 }, { "start": 1059.84, "end": 1060.36, "word": " Naive", "probability": 0.819580078125 }, { "start": 1060.36, "end": 1060.78, "word": " Bayesian", "probability": 0.90625 }, { "start": 1060.78, "end": 1061.6, "word": ",", "probability": 0.75048828125 } ] }, { "id": 451, "seek": 106044, "start": 1061.6, "end": 1062.82, "text": " multinomial Naive Bayesian", "tokens": [ 51264, 45872, 47429, 6056, 488, 7840, 42434, 51314 ], "temperature": 0.0, "avg_logprob": -0.15318434119601793, "compression_ratio": 1.9722222222222223, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 1061.6, "end": 1062.18, "word": " multinomial", "probability": 0.91748046875 }, { "start": 1062.18, "end": 1062.48, "word": " Naive", "probability": 0.9072265625 }, { "start": 1062.48, "end": 1062.82, "word": " Bayesian", "probability": 0.938232421875 } ] }, { "id": 452, "seek": 106044, "start": 1062.82, "end": 1064.54, "text": " that we can tweak, right?", "tokens": [ 51364, 300, 321, 393, 29879, 11, 558, 30, 51414 ], "temperature": 0.0, "avg_logprob": -0.15318434119601793, "compression_ratio": 1.9722222222222223, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 1062.82, "end": 1063.5, "word": " that", "probability": 0.5009765625 }, { "start": 1063.5, "end": 1063.66, "word": " we", "probability": 0.90673828125 }, { "start": 1063.66, "end": 1063.82, "word": " can", "probability": 0.89794921875 }, { "start": 1063.82, "end": 1064.18, "word": " tweak", "probability": 0.87158203125 }, { "start": 1064.18, "end": 1064.32, "word": ",", "probability": 0.673828125 }, { "start": 1064.32, "end": 1064.52, "word": " right", "probability": 0.87255859375 }, { "start": 1064.52, "end": 1064.54, "word": "?", "probability": 0.8564453125 } ] }, { "id": 453, "seek": 106044, "start": 1064.54, "end": 1066.36, "text": " We can set it to one, we can set it to two,", "tokens": [ 51464, 492, 393, 992, 309, 281, 472, 11, 321, 393, 992, 309, 281, 732, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.15318434119601793, "compression_ratio": 1.9722222222222223, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 1064.54, "end": 1064.66, "word": " We", "probability": 0.89990234375 }, { "start": 1064.66, "end": 1064.8, "word": " can", "probability": 0.89697265625 }, { "start": 1064.8, "end": 1064.94, "word": " set", "probability": 0.9013671875 }, { "start": 1064.94, "end": 1065.04, "word": " it", "probability": 0.9013671875 }, { "start": 1065.04, "end": 1065.16, "word": " to", "probability": 0.9033203125 }, { "start": 1065.16, "end": 1065.4, "word": " one", "probability": 0.81396484375 }, { "start": 1065.4, "end": 1065.48, "word": ",", "probability": 0.728515625 }, { "start": 1065.48, "end": 1065.54, "word": " we", "probability": 0.89697265625 }, { "start": 1065.54, "end": 1065.68, "word": " can", "probability": 0.89599609375 }, { "start": 1065.68, "end": 1065.8, "word": " set", "probability": 0.89599609375 }, { "start": 1065.8, "end": 1065.9, "word": " it", "probability": 0.9013671875 }, { "start": 1065.9, "end": 1066.02, "word": " to", "probability": 0.90087890625 }, { "start": 1066.02, "end": 1066.28, "word": " two", "probability": 0.8046875 }, { "start": 1066.28, "end": 1066.36, "word": ",", "probability": 0.91064453125 } ] }, { "id": 454, "seek": 106044, "start": 1066.36, "end": 1067.9, "text": " we can set it to 0.1.", "tokens": [ 51564, 321, 393, 992, 309, 281, 1958, 13, 16, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.15318434119601793, "compression_ratio": 1.9722222222222223, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 1066.36, "end": 1066.44, "word": " we", "probability": 0.89892578125 }, { "start": 1066.44, "end": 1066.56, "word": " can", "probability": 0.89599609375 }, { "start": 1066.56, "end": 1066.7, "word": " set", "probability": 0.908203125 }, { "start": 1066.7, "end": 1066.8, "word": " it", "probability": 0.9013671875 }, { "start": 1066.8, "end": 1066.92, "word": " to", "probability": 0.89501953125 }, { "start": 1066.92, "end": 1067.16, "word": " 0", "probability": 0.6064453125 }, { "start": 1067.16, "end": 1067.54, "word": ".1", "probability": 0.99755859375 }, { "start": 1067.54, "end": 1067.9, "word": ".", "probability": 0.87841796875 } ] }, { "id": 455, "seek": 106044, "start": 1068.04, "end": 1070.84, "text": " And so this is a thing that we can tweak", "tokens": [ 51664, 400, 370, 341, 307, 257, 551, 300, 321, 393, 29879, 51714 ], "temperature": 0.0, "avg_logprob": -0.15318434119601793, "compression_ratio": 1.9722222222222223, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 1068.04, "end": 1068.26, "word": " And", "probability": 0.89453125 }, { "start": 1068.26, "end": 1068.58, "word": " so", "probability": 0.89794921875 }, { "start": 1068.58, "end": 1069.24, "word": " this", "probability": 0.8212890625 }, { "start": 1069.24, "end": 1069.52, "word": " is", "probability": 0.90625 }, { "start": 1070.06, "end": 1070.24, "word": " a thing", "probability": 0.82421875 }, { "start": 1070.24, "end": 1070.38, "word": " that", "probability": 0.8818359375 }, { "start": 1070.38, "end": 1070.46, "word": " we", "probability": 0.9013671875 }, { "start": 1070.46, "end": 1070.6, "word": " can", "probability": 0.892578125 }, { "start": 1070.6, "end": 1070.84, "word": " tweak", "probability": 0.8671875 } ] }, { "id": 456, "seek": 106044, "start": 1070.84, "end": 1072.28, "text": " to see if we can get our model", "tokens": [ 51764, 281, 536, 498, 321, 393, 483, 527, 2316, 51814 ], "temperature": 0.0, "avg_logprob": -0.15318434119601793, "compression_ratio": 1.9722222222222223, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 1070.84, "end": 1071.16, "word": " to", "probability": 0.900390625 }, { "start": 1071.16, "end": 1071.46, "word": " see", "probability": 0.80908203125 }, { "start": 1071.46, "end": 1071.58, "word": " if", "probability": 0.904296875 }, { "start": 1071.58, "end": 1071.64, "word": " we", "probability": 0.8984375 }, { "start": 1071.64, "end": 1071.78, "word": " can", "probability": 0.890625 }, { "start": 1071.78, "end": 1071.9, "word": " get", "probability": 0.89453125 }, { "start": 1071.9, "end": 1072.04, "word": " our", "probability": 0.82421875 }, { "start": 1072.04, "end": 1072.28, "word": " model", "probability": 0.828125 } ] }, { "id": 457, "seek": 109044, "start": 1074.22, "end": 1074.66, "text": " to work for us.", "tokens": [ 50364, 281, 589, 337, 505, 13, 50414 ], "temperature": 0.0, "avg_logprob": -0.2053420640326835, "compression_ratio": 1.9461538461538461, "no_speech_prob": 0.00014889240264892578, "words": [ { "start": 1074.22, "end": 1074.22, "word": " to", "probability": 0.00012481212615966797 }, { "start": 1074.22, "end": 1074.22, "word": " work", "probability": 0.0113983154296875 }, { "start": 1074.22, "end": 1074.22, "word": " for", "probability": 0.036468505859375 }, { "start": 1074.22, "end": 1074.22, "word": " us", "probability": 0.2000732421875 }, { "start": 1074.22, "end": 1074.66, "word": ".", "probability": 0.71240234375 } ] }, { "id": 458, "seek": 109044, "start": 1075.44, "end": 1076.78, "text": " So we take the same idea.", "tokens": [ 50464, 407, 321, 747, 264, 912, 1558, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.2053420640326835, "compression_ratio": 1.9461538461538461, "no_speech_prob": 0.00014889240264892578, "words": [ { "start": 1075.44, "end": 1075.88, "word": " So", "probability": 0.603515625 }, { "start": 1075.88, "end": 1075.96, "word": " we", "probability": 0.8408203125 }, { "start": 1075.96, "end": 1076.1, "word": " take", "probability": 0.78369140625 }, { "start": 1076.1, "end": 1076.24, "word": " the", "probability": 0.798828125 }, { "start": 1076.24, "end": 1076.4, "word": " same", "probability": 0.82666015625 }, { "start": 1076.4, "end": 1076.68, "word": " idea", "probability": 0.7724609375 }, { "start": 1076.68, "end": 1076.78, "word": ".", "probability": 0.340087890625 } ] }, { "id": 459, "seek": 109044, "start": 1076.78, "end": 1077.68, "text": " We do the word counts.", "tokens": [ 50564, 492, 360, 264, 1349, 14893, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.2053420640326835, "compression_ratio": 1.9461538461538461, "no_speech_prob": 0.00014889240264892578, "words": [ { "start": 1076.78, "end": 1076.84, "word": " We", "probability": 0.896484375 }, { "start": 1076.84, "end": 1076.96, "word": " do", "probability": 0.875 }, { "start": 1076.96, "end": 1077.08, "word": " the", "probability": 0.814453125 }, { "start": 1077.08, "end": 1077.26, "word": " word", "probability": 0.82373046875 }, { "start": 1077.26, "end": 1077.56, "word": " counts", "probability": 0.73779296875 }, { "start": 1077.56, "end": 1077.68, "word": ".", "probability": 0.84326171875 } ] }, { "id": 460, "seek": 109044, "start": 1077.68, "end": 1079.7, "text": " We saw that a showed up in sports twice,", "tokens": [ 50664, 492, 1866, 300, 257, 4712, 493, 294, 6573, 6091, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.2053420640326835, "compression_ratio": 1.9461538461538461, "no_speech_prob": 0.00014889240264892578, "words": [ { "start": 1077.68, "end": 1077.72, "word": " We", "probability": 0.89501953125 }, { "start": 1077.72, "end": 1077.92, "word": " saw", "probability": 0.8359375 }, { "start": 1077.92, "end": 1078.18, "word": " that", "probability": 0.8759765625 }, { "start": 1078.34, "end": 1078.58, "word": " a showed", "probability": 0.80029296875 }, { "start": 1078.58, "end": 1078.7, "word": " up", "probability": 0.91015625 }, { "start": 1078.7, "end": 1078.84, "word": " in", "probability": 0.90771484375 }, { "start": 1078.84, "end": 1079.12, "word": " sports", "probability": 0.75439453125 }, { "start": 1079.12, "end": 1079.52, "word": " twice", "probability": 0.8408203125 }, { "start": 1079.52, "end": 1079.7, "word": ",", "probability": 0.6005859375 } ] }, { "id": 461, "seek": 109044, "start": 1079.7, "end": 1081.36, "text": " very showed up once, close to zero.", "tokens": [ 50764, 588, 4712, 493, 1564, 11, 1998, 281, 4018, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.2053420640326835, "compression_ratio": 1.9461538461538461, "no_speech_prob": 0.00014889240264892578, "words": [ { "start": 1079.7, "end": 1079.82, "word": " very", "probability": 0.6025390625 }, { "start": 1079.82, "end": 1080.04, "word": " showed", "probability": 0.658203125 }, { "start": 1080.04, "end": 1080.2, "word": " up", "probability": 0.9111328125 }, { "start": 1080.2, "end": 1080.5, "word": " once", "probability": 0.78515625 }, { "start": 1080.5, "end": 1080.6, "word": ",", "probability": 0.73876953125 }, { "start": 1080.6, "end": 1080.8, "word": " close", "probability": 0.8349609375 }, { "start": 1080.8, "end": 1080.96, "word": " to", "probability": 0.67626953125 }, { "start": 1080.96, "end": 1081.22, "word": " zero", "probability": 0.79296875 }, { "start": 1081.22, "end": 1081.36, "word": ".", "probability": 0.337890625 } ] }, { "id": 462, "seek": 109044, "start": 1081.36, "end": 1083.18, "text": " But now we have this plus one.", "tokens": [ 50864, 583, 586, 321, 362, 341, 1804, 472, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.2053420640326835, "compression_ratio": 1.9461538461538461, "no_speech_prob": 0.00014889240264892578, "words": [ { "start": 1081.36, "end": 1081.48, "word": " But", "probability": 0.87646484375 }, { "start": 1081.48, "end": 1081.6, "word": " now", "probability": 0.8916015625 }, { "start": 1081.6, "end": 1081.72, "word": " we", "probability": 0.89794921875 }, { "start": 1081.72, "end": 1081.86, "word": " have", "probability": 0.87841796875 }, { "start": 1081.86, "end": 1082.04, "word": " this", "probability": 0.8798828125 }, { "start": 1082.04, "end": 1082.38, "word": " plus", "probability": 0.81591796875 }, { "start": 1082.38, "end": 1082.74, "word": " one", "probability": 0.80419921875 }, { "start": 1082.74, "end": 1083.18, "word": ".", "probability": 0.95458984375 } ] }, { "id": 463, "seek": 109044, "start": 1083.58, "end": 1086.62, "text": " So the probability of close given sports", "tokens": [ 50964, 407, 264, 8482, 295, 1998, 2212, 6573, 51014 ], "temperature": 0.0, "avg_logprob": -0.2053420640326835, "compression_ratio": 1.9461538461538461, "no_speech_prob": 0.00014889240264892578, "words": [ { "start": 1083.58, "end": 1084.02, "word": " So", "probability": 0.89501953125 }, { "start": 1084.02, "end": 1084.32, "word": " the", "probability": 0.7978515625 }, { "start": 1084.32, "end": 1084.74, "word": " probability", "probability": 0.8984375 }, { "start": 1084.74, "end": 1085.3, "word": " of", "probability": 0.90087890625 }, { "start": 1085.3, "end": 1085.8, "word": " close", "probability": 0.81201171875 }, { "start": 1085.8, "end": 1086.18, "word": " given", "probability": 0.76025390625 }, { "start": 1086.18, "end": 1086.62, "word": " sports", "probability": 0.77197265625 } ] }, { "id": 464, "seek": 109044, "start": 1086.62, "end": 1088.48, "text": " is never going to reach zero.", "tokens": [ 51064, 307, 1128, 516, 281, 2524, 4018, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.2053420640326835, "compression_ratio": 1.9461538461538461, "no_speech_prob": 0.00014889240264892578, "words": [ { "start": 1086.62, "end": 1086.86, "word": " is", "probability": 0.88232421875 }, { "start": 1086.86, "end": 1087.08, "word": " never", "probability": 0.865234375 }, { "start": 1087.08, "end": 1087.34, "word": " going", "probability": 0.8466796875 }, { "start": 1087.34, "end": 1087.48, "word": " to", "probability": 0.90087890625 }, { "start": 1087.48, "end": 1087.7, "word": " reach", "probability": 0.8232421875 }, { "start": 1087.7, "end": 1088.04, "word": " zero", "probability": 0.82275390625 }, { "start": 1088.04, "end": 1088.48, "word": ".", "probability": 0.994140625 } ] }, { "id": 465, "seek": 109044, "start": 1089.18, "end": 1090.76, "text": " And then of course, as I mentioned earlier,", "tokens": [ 51164, 400, 550, 295, 1164, 11, 382, 286, 2835, 3071, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.2053420640326835, "compression_ratio": 1.9461538461538461, "no_speech_prob": 0.00014889240264892578, "words": [ { "start": 1089.18, "end": 1089.58, "word": " And", "probability": 0.88818359375 }, { "start": 1089.58, "end": 1089.68, "word": " then", "probability": 0.72607421875 }, { "start": 1089.68, "end": 1089.82, "word": " of", "probability": 0.8125 }, { "start": 1089.82, "end": 1090.02, "word": " course", "probability": 0.86279296875 }, { "start": 1090.02, "end": 1090.04, "word": ",", "probability": 0.89990234375 }, { "start": 1090.04, "end": 1090.18, "word": " as", "probability": 0.9033203125 }, { "start": 1090.18, "end": 1090.26, "word": " I", "probability": 0.99951171875 }, { "start": 1090.26, "end": 1090.5, "word": " mentioned", "probability": 0.76123046875 }, { "start": 1090.5, "end": 1090.76, "word": " earlier", "probability": 0.9111328125 }, { "start": 1090.76, "end": 1090.76, "word": ",", "probability": 0.76806640625 } ] }, { "id": 466, "seek": 109044, "start": 1090.76, "end": 1093.06, "text": " we need to do the same thing for not sports.", "tokens": [ 51264, 321, 643, 281, 360, 264, 912, 551, 337, 406, 6573, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.2053420640326835, "compression_ratio": 1.9461538461538461, "no_speech_prob": 0.00014889240264892578, "words": [ { "start": 1090.76, "end": 1090.94, "word": " we", "probability": 0.90087890625 }, { "start": 1090.94, "end": 1091.1, "word": " need", "probability": 0.8017578125 }, { "start": 1091.1, "end": 1091.18, "word": " to", "probability": 0.90673828125 }, { "start": 1091.18, "end": 1091.28, "word": " do", "probability": 0.904296875 }, { "start": 1091.28, "end": 1091.44, "word": " the", "probability": 0.8115234375 }, { "start": 1091.44, "end": 1091.64, "word": " same", "probability": 0.822265625 }, { "start": 1091.64, "end": 1091.88, "word": " thing", "probability": 0.81591796875 }, { "start": 1091.88, "end": 1092.1, "word": " for", "probability": 0.89404296875 }, { "start": 1092.1, "end": 1092.3, "word": " not", "probability": 0.81298828125 }, { "start": 1092.3, "end": 1092.72, "word": " sports", "probability": 0.77197265625 }, { "start": 1092.72, "end": 1093.06, "word": ".", "probability": 0.69384765625 } ] }, { "id": 467, "seek": 109044, "start": 1093.06, "end": 1094.82, "text": " And the total number of unique words", "tokens": [ 51364, 400, 264, 3217, 1230, 295, 3845, 2283, 51414 ], "temperature": 0.0, "avg_logprob": -0.2053420640326835, "compression_ratio": 1.9461538461538461, "no_speech_prob": 0.00014889240264892578, "words": [ { "start": 1093.06, "end": 1093.36, "word": " And", "probability": 0.89013671875 }, { "start": 1093.36, "end": 1093.54, "word": " the", "probability": 0.8134765625 }, { "start": 1093.54, "end": 1093.68, "word": " total", "probability": 0.796875 }, { "start": 1093.68, "end": 1093.92, "word": " number", "probability": 0.880859375 }, { "start": 1093.92, "end": 1094.12, "word": " of", "probability": 0.90673828125 }, { "start": 1094.12, "end": 1094.38, "word": " unique", "probability": 0.7861328125 }, { "start": 1094.38, "end": 1094.82, "word": " words", "probability": 0.73095703125 } ] }, { "id": 468, "seek": 109044, "start": 1094.82, "end": 1096.28, "text": " in not sports is nine.", "tokens": [ 51464, 294, 406, 6573, 307, 4949, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.2053420640326835, "compression_ratio": 1.9461538461538461, "no_speech_prob": 0.00014889240264892578, "words": [ { "start": 1094.82, "end": 1095.12, "word": " in", "probability": 0.79638671875 }, { "start": 1095.12, "end": 1095.34, "word": " not", "probability": 0.85400390625 }, { "start": 1095.34, "end": 1095.72, "word": " sports", "probability": 0.8037109375 }, { "start": 1095.72, "end": 1095.98, "word": " is", "probability": 0.89111328125 }, { "start": 1095.98, "end": 1096.2, "word": " nine", "probability": 0.8125 }, { "start": 1096.2, "end": 1096.28, "word": ".", "probability": 0.77392578125 } ] }, { "id": 469, "seek": 109044, "start": 1096.28, "end": 1098.6, "text": " The total number of unique words in sports is 11.", "tokens": [ 51564, 440, 3217, 1230, 295, 3845, 2283, 294, 6573, 307, 2975, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.2053420640326835, "compression_ratio": 1.9461538461538461, "no_speech_prob": 0.00014889240264892578, "words": [ { "start": 1096.28, "end": 1096.36, "word": " The", "probability": 0.80810546875 }, { "start": 1096.36, "end": 1096.52, "word": " total", "probability": 0.81689453125 }, { "start": 1096.52, "end": 1096.74, "word": " number", "probability": 0.888671875 }, { "start": 1096.74, "end": 1096.9, "word": " of", "probability": 0.90673828125 }, { "start": 1096.9, "end": 1097.08, "word": " unique", "probability": 0.7802734375 }, { "start": 1097.08, "end": 1097.38, "word": " words", "probability": 0.71533203125 }, { "start": 1097.38, "end": 1097.6, "word": " in", "probability": 0.89990234375 }, { "start": 1097.6, "end": 1097.96, "word": " sports", "probability": 0.78857421875 }, { "start": 1097.96, "end": 1098.16, "word": " is", "probability": 0.90283203125 }, { "start": 1098.16, "end": 1098.52, "word": " 11", "probability": 0.8857421875 }, { "start": 1098.52, "end": 1098.6, "word": ".", "probability": 0.74951171875 } ] }, { "id": 470, "seek": 109044, "start": 1098.6, "end": 1100.06, "text": " And the total number of unique words", "tokens": [ 51664, 400, 264, 3217, 1230, 295, 3845, 2283, 51714 ], "temperature": 0.0, "avg_logprob": -0.2053420640326835, "compression_ratio": 1.9461538461538461, "no_speech_prob": 0.00014889240264892578, "words": [ { "start": 1098.6, "end": 1098.76, "word": " And", "probability": 0.89111328125 }, { "start": 1098.76, "end": 1098.9, "word": " the", "probability": 0.818359375 }, { "start": 1098.9, "end": 1099.1, "word": " total", "probability": 0.80810546875 }, { "start": 1099.1, "end": 1099.36, "word": " number", "probability": 0.89013671875 }, { "start": 1099.36, "end": 1099.5, "word": " of", "probability": 0.9033203125 }, { "start": 1099.5, "end": 1099.72, "word": " unique", "probability": 0.79248046875 }, { "start": 1099.72, "end": 1100.06, "word": " words", "probability": 0.658203125 } ] }, { "id": 471, "seek": 109044, "start": 1100.06, "end": 1103.32, "text": " across both classes is 14.", "tokens": [ 51764, 2108, 1293, 5359, 307, 3499, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.2053420640326835, "compression_ratio": 1.9461538461538461, "no_speech_prob": 0.00014889240264892578, "words": [ { "start": 1100.06, "end": 1100.58, "word": " across", "probability": 0.70947265625 }, { "start": 1100.58, "end": 1101.12, "word": " both", "probability": 0.8134765625 }, { "start": 1101.12, "end": 1101.68, "word": " classes", "probability": 0.7890625 }, { "start": 1101.68, "end": 1102.6, "word": " is", "probability": 0.89306640625 }, { "start": 1102.6, "end": 1103.1, "word": " 14", "probability": 0.90185546875 }, { "start": 1103.1, "end": 1103.32, "word": ".", "probability": 0.984375 } ] }, { "id": 472, "seek": 112044, "start": 1106.08, "end": 1108.08, "text": " So we plug in our answers", "tokens": [ 50414, 407, 321, 5452, 294, 527, 6338, 50514 ], "temperature": 0.0, "avg_logprob": -0.18402777115503946, "compression_ratio": 1.4975369458128078, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 1106.08, "end": 1106.58, "word": " So", "probability": 0.21923828125 }, { "start": 1106.58, "end": 1107.08, "word": " we", "probability": 0.60888671875 }, { "start": 1107.08, "end": 1107.3, "word": " plug", "probability": 0.79345703125 }, { "start": 1107.3, "end": 1107.4, "word": " in", "probability": 0.8837890625 }, { "start": 1107.4, "end": 1107.62, "word": " our", "probability": 0.8212890625 }, { "start": 1107.62, "end": 1108.08, "word": " answers", "probability": 0.82763671875 } ] }, { "id": 473, "seek": 112044, "start": 1108.08, "end": 1109.36, "text": " and we do our calculations", "tokens": [ 50564, 293, 321, 360, 527, 20448, 50614 ], "temperature": 0.0, "avg_logprob": -0.18402777115503946, "compression_ratio": 1.4975369458128078, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 1108.08, "end": 1108.52, "word": " and", "probability": 0.73291015625 }, { "start": 1108.52, "end": 1108.64, "word": " we", "probability": 0.7861328125 }, { "start": 1108.64, "end": 1108.74, "word": " do", "probability": 0.90087890625 }, { "start": 1108.74, "end": 1108.88, "word": " our", "probability": 0.810546875 }, { "start": 1108.88, "end": 1109.36, "word": " calculations", "probability": 0.8544921875 } ] }, { "id": 474, "seek": 112044, "start": 1109.36, "end": 1113.68, "text": " and we get 0.0000461 for sports", "tokens": [ 50664, 293, 321, 483, 1958, 13, 33202, 16169, 16, 337, 6573, 50814 ], "temperature": 0.0, "avg_logprob": -0.18402777115503946, "compression_ratio": 1.4975369458128078, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 1109.36, "end": 1109.98, "word": " and", "probability": 0.6484375 }, { "start": 1109.98, "end": 1110.14, "word": " we", "probability": 0.88720703125 }, { "start": 1110.14, "end": 1110.4, "word": " get", "probability": 0.8994140625 }, { "start": 1110.4, "end": 1110.72, "word": " 0", "probability": 0.33349609375 }, { "start": 1110.72, "end": 1113.0, "word": ".0000461", "probability": 0.9034423828125 }, { "start": 1113.0, "end": 1113.26, "word": " for", "probability": 0.89306640625 }, { "start": 1113.26, "end": 1113.68, "word": " sports", "probability": 0.7138671875 } ] }, { "id": 475, "seek": 112044, "start": 1113.68, "end": 1117.88, "text": " and 0.0000143 for non-sports.", "tokens": [ 50864, 293, 1958, 13, 33202, 7271, 18, 337, 2107, 12, 82, 17845, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.18402777115503946, "compression_ratio": 1.4975369458128078, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 1113.68, "end": 1114.04, "word": " and", "probability": 0.7861328125 }, { "start": 1114.04, "end": 1114.34, "word": " 0", "probability": 0.939453125 }, { "start": 1114.34, "end": 1116.6, "word": ".0000143", "probability": 0.932861328125 }, { "start": 1116.6, "end": 1116.96, "word": " for", "probability": 0.88330078125 }, { "start": 1116.96, "end": 1117.14, "word": " non", "probability": 0.87109375 }, { "start": 1117.14, "end": 1117.48, "word": "-sports", "probability": 0.79248046875 }, { "start": 1117.48, "end": 1117.88, "word": ".", "probability": 0.404541015625 } ] }, { "id": 476, "seek": 112044, "start": 1118.2, "end": 1119.44, "text": " Classifying the sentence,", "tokens": [ 51064, 9471, 5489, 264, 8174, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.18402777115503946, "compression_ratio": 1.4975369458128078, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 1118.2, "end": 1118.7, "word": " Classifying", "probability": 0.907470703125 }, { "start": 1118.7, "end": 1118.9, "word": " the", "probability": 0.8017578125 }, { "start": 1118.9, "end": 1119.22, "word": " sentence", "probability": 0.8310546875 }, { "start": 1119.22, "end": 1119.44, "word": ",", "probability": 0.301025390625 } ] }, { "id": 477, "seek": 112044, "start": 1119.56, "end": 1122.8, "text": " a very close game being about sports.", "tokens": [ 51164, 257, 588, 1998, 1216, 885, 466, 6573, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.18402777115503946, "compression_ratio": 1.4975369458128078, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 1119.56, "end": 1119.8, "word": " a very", "probability": 0.71240234375 }, { "start": 1119.8, "end": 1120.12, "word": " close", "probability": 0.8408203125 }, { "start": 1120.12, "end": 1120.54, "word": " game", "probability": 0.818359375 }, { "start": 1120.54, "end": 1121.2, "word": " being", "probability": 0.42333984375 }, { "start": 1121.2, "end": 1121.56, "word": " about", "probability": 0.828125 }, { "start": 1121.56, "end": 1122.3, "word": " sports", "probability": 0.76513671875 }, { "start": 1122.3, "end": 1122.8, "word": ".", "probability": 0.98095703125 } ] }, { "id": 478, "seek": 112044, "start": 1125.48, "end": 1128.32, "text": " So that was a lot that I just kind of laid on you.", "tokens": [ 51314, 407, 300, 390, 257, 688, 300, 286, 445, 733, 295, 9897, 322, 291, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.18402777115503946, "compression_ratio": 1.4975369458128078, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 1125.48, "end": 1125.98, "word": " So", "probability": 0.8544921875 }, { "start": 1125.98, "end": 1126.48, "word": " that", "probability": 0.80126953125 }, { "start": 1126.48, "end": 1126.6, "word": " was", "probability": 0.8994140625 }, { "start": 1126.72, "end": 1126.86, "word": " a lot", "probability": 0.890625 }, { "start": 1126.86, "end": 1126.98, "word": " that", "probability": 0.875 }, { "start": 1126.98, "end": 1127.08, "word": " I", "probability": 0.9951171875 }, { "start": 1127.08, "end": 1127.22, "word": " just", "probability": 0.88427734375 }, { "start": 1127.22, "end": 1127.38, "word": " kind", "probability": 0.638671875 }, { "start": 1127.38, "end": 1127.44, "word": " of", "probability": 0.89990234375 }, { "start": 1127.44, "end": 1127.6, "word": " laid", "probability": 0.9140625 }, { "start": 1127.6, "end": 1127.76, "word": " on", "probability": 0.896484375 }, { "start": 1127.76, "end": 1127.94, "word": " you", "probability": 0.89208984375 }, { "start": 1127.94, "end": 1128.32, "word": ".", "probability": 0.94140625 } ] }, { "id": 479, "seek": 112044, "start": 1129.08, "end": 1130.4, "text": " If you have any questions,", "tokens": [ 51564, 759, 291, 362, 604, 1651, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.18402777115503946, "compression_ratio": 1.4975369458128078, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 1129.08, "end": 1129.58, "word": " If", "probability": 0.88134765625 }, { "start": 1129.58, "end": 1129.66, "word": " you", "probability": 0.8935546875 }, { "start": 1129.66, "end": 1129.76, "word": " have", "probability": 0.88427734375 }, { "start": 1129.76, "end": 1129.9, "word": " any", "probability": 0.82275390625 }, { "start": 1129.9, "end": 1130.28, "word": " questions", "probability": 0.90966796875 }, { "start": 1130.28, "end": 1130.4, "word": ",", "probability": 0.71533203125 } ] }, { "id": 480, "seek": 112044, "start": 1130.4, "end": 1131.66, "text": " type them in the chat.", "tokens": [ 51664, 2010, 552, 294, 264, 5081, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.18402777115503946, "compression_ratio": 1.4975369458128078, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 1130.4, "end": 1130.58, "word": " type", "probability": 0.92724609375 }, { "start": 1130.58, "end": 1130.7, "word": " them", "probability": 0.7392578125 }, { "start": 1130.7, "end": 1130.8, "word": " in", "probability": 0.9052734375 }, { "start": 1130.8, "end": 1130.9, "word": " the", "probability": 0.80908203125 }, { "start": 1130.9, "end": 1131.16, "word": " chat", "probability": 0.82861328125 }, { "start": 1131.16, "end": 1131.66, "word": ".", "probability": 0.65087890625 } ] }, { "id": 481, "seek": 112044, "start": 1132.02, "end": 1133.2, "text": " While you're doing that,", "tokens": [ 51764, 3987, 291, 434, 884, 300, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.18402777115503946, "compression_ratio": 1.4975369458128078, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 1132.02, "end": 1132.52, "word": " While", "probability": 0.87646484375 }, { "start": 1132.52, "end": 1132.68, "word": " you're", "probability": 0.922119140625 }, { "start": 1132.68, "end": 1132.84, "word": " doing", "probability": 0.9169921875 }, { "start": 1132.84, "end": 1133.14, "word": " that", "probability": 0.88623046875 }, { "start": 1133.14, "end": 1133.2, "word": ",", "probability": 0.9091796875 } ] }, { "id": 482, "seek": 115044, "start": 1134.22, "end": 1135.58, "text": " I'm going to show you how we can", "tokens": [ 50364, 286, 478, 516, 281, 855, 291, 577, 321, 393, 50414 ], "temperature": 0.0, "avg_logprob": -0.18480604064875636, "compression_ratio": 1.946078431372549, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 1134.22, "end": 1134.22, "word": " I'm", "probability": 0.39178466796875 }, { "start": 1134.22, "end": 1134.22, "word": " going", "probability": 0.485107421875 }, { "start": 1134.22, "end": 1134.22, "word": " to", "probability": 0.90869140625 }, { "start": 1134.22, "end": 1134.36, "word": " show", "probability": 0.8515625 }, { "start": 1134.36, "end": 1134.56, "word": " you", "probability": 0.8955078125 }, { "start": 1134.56, "end": 1134.88, "word": " how", "probability": 0.900390625 }, { "start": 1134.88, "end": 1135.14, "word": " we", "probability": 0.89892578125 }, { "start": 1135.14, "end": 1135.58, "word": " can", "probability": 0.89697265625 } ] }, { "id": 483, "seek": 115044, "start": 1136.72, "end": 1138.38, "text": " take our raw emails", "tokens": [ 50464, 747, 527, 8936, 12524, 50564 ], "temperature": 0.0, "avg_logprob": -0.18480604064875636, "compression_ratio": 1.946078431372549, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 1136.72, "end": 1137.24, "word": " take", "probability": 0.78955078125 }, { "start": 1137.24, "end": 1137.4, "word": " our", "probability": 0.80859375 }, { "start": 1137.4, "end": 1137.92, "word": " raw", "probability": 0.79833984375 }, { "start": 1137.92, "end": 1138.38, "word": " emails", "probability": 0.73193359375 } ] }, { "id": 484, "seek": 115044, "start": 1139.1, "end": 1140.94, "text": " and transform them into", "tokens": [ 50614, 293, 4088, 552, 666, 50664 ], "temperature": 0.0, "avg_logprob": -0.18480604064875636, "compression_ratio": 1.946078431372549, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 1139.1, "end": 1139.36, "word": " and", "probability": 0.82958984375 }, { "start": 1139.36, "end": 1140.06, "word": " transform", "probability": 0.87158203125 }, { "start": 1140.06, "end": 1140.46, "word": " them", "probability": 0.736328125 }, { "start": 1140.46, "end": 1140.94, "word": " into", "probability": 0.74267578125 } ] }, { "id": 485, "seek": 115044, "start": 1140.94, "end": 1142.48, "text": " these types of counts", "tokens": [ 50714, 613, 3467, 295, 14893, 50764 ], "temperature": 0.0, "avg_logprob": -0.18480604064875636, "compression_ratio": 1.946078431372549, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 1140.94, "end": 1141.8, "word": " these", "probability": 0.7041015625 }, { "start": 1141.8, "end": 1142.06, "word": " types", "probability": 0.76025390625 }, { "start": 1142.06, "end": 1142.2, "word": " of", "probability": 0.908203125 }, { "start": 1142.2, "end": 1142.48, "word": " counts", "probability": 0.75341796875 } ] }, { "id": 486, "seek": 115044, "start": 1142.48, "end": 1143.44, "text": " and these types of numbers", "tokens": [ 50814, 293, 613, 3467, 295, 3547, 50864 ], "temperature": 0.0, "avg_logprob": -0.18480604064875636, "compression_ratio": 1.946078431372549, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 1142.48, "end": 1142.6, "word": " and", "probability": 0.7392578125 }, { "start": 1142.6, "end": 1142.76, "word": " these", "probability": 0.6865234375 }, { "start": 1142.76, "end": 1142.94, "word": " types", "probability": 0.76708984375 }, { "start": 1142.94, "end": 1143.12, "word": " of", "probability": 0.90625 }, { "start": 1143.12, "end": 1143.44, "word": " numbers", "probability": 0.86328125 } ] }, { "id": 487, "seek": 115044, "start": 1144.12, "end": 1146.5, "text": " in a very clean and effective way.", "tokens": [ 50914, 294, 257, 588, 2541, 293, 4942, 636, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.18480604064875636, "compression_ratio": 1.946078431372549, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 1144.12, "end": 1144.64, "word": " in", "probability": 0.73974609375 }, { "start": 1144.72, "end": 1144.88, "word": " a very", "probability": 0.748046875 }, { "start": 1144.88, "end": 1145.16, "word": " clean", "probability": 0.8310546875 }, { "start": 1145.16, "end": 1145.3, "word": " and", "probability": 0.89697265625 }, { "start": 1145.3, "end": 1145.6, "word": " effective", "probability": 0.720703125 }, { "start": 1145.6, "end": 1145.98, "word": " way", "probability": 0.8994140625 }, { "start": 1145.98, "end": 1146.5, "word": ".", "probability": 0.990234375 } ] }, { "id": 488, "seek": 115044, "start": 1146.96, "end": 1149.18, "text": " So the five things we need to keep track of", "tokens": [ 51014, 407, 264, 1732, 721, 321, 643, 281, 1066, 2837, 295, 51064 ], "temperature": 0.0, "avg_logprob": -0.18480604064875636, "compression_ratio": 1.946078431372549, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 1146.96, "end": 1147.48, "word": " So", "probability": 0.73291015625 }, { "start": 1147.48, "end": 1147.84, "word": " the", "probability": 0.5869140625 }, { "start": 1147.84, "end": 1148.02, "word": " five", "probability": 0.75927734375 }, { "start": 1148.02, "end": 1148.22, "word": " things", "probability": 0.73583984375 }, { "start": 1148.22, "end": 1148.32, "word": " we", "probability": 0.90185546875 }, { "start": 1148.32, "end": 1148.44, "word": " need", "probability": 0.8134765625 }, { "start": 1148.44, "end": 1148.52, "word": " to", "probability": 0.912109375 }, { "start": 1148.52, "end": 1148.66, "word": " keep", "probability": 0.8134765625 }, { "start": 1148.66, "end": 1148.9, "word": " track", "probability": 0.83349609375 }, { "start": 1148.9, "end": 1149.18, "word": " of", "probability": 0.90234375 } ] }, { "id": 489, "seek": 115044, "start": 1149.18, "end": 1151.92, "text": " are the total number of unique words,", "tokens": [ 51114, 366, 264, 3217, 1230, 295, 3845, 2283, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.18480604064875636, "compression_ratio": 1.946078431372549, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 1149.18, "end": 1149.62, "word": " are", "probability": 0.87890625 }, { "start": 1149.62, "end": 1149.94, "word": " the", "probability": 0.7998046875 }, { "start": 1149.94, "end": 1150.18, "word": " total", "probability": 0.7822265625 }, { "start": 1150.18, "end": 1150.44, "word": " number", "probability": 0.88671875 }, { "start": 1150.44, "end": 1150.6, "word": " of", "probability": 0.90673828125 }, { "start": 1150.6, "end": 1150.9, "word": " unique", "probability": 0.7900390625 }, { "start": 1150.9, "end": 1151.34, "word": " words", "probability": 0.7373046875 }, { "start": 1151.34, "end": 1151.92, "word": ",", "probability": 0.9267578125 } ] }, { "id": 490, "seek": 115044, "start": 1151.92, "end": 1154.24, "text": " the total number of words in spam,", "tokens": [ 51264, 264, 3217, 1230, 295, 2283, 294, 24028, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.18480604064875636, "compression_ratio": 1.946078431372549, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 1151.92, "end": 1152.18, "word": " the", "probability": 0.8115234375 }, { "start": 1152.18, "end": 1152.44, "word": " total", "probability": 0.80810546875 }, { "start": 1152.44, "end": 1152.68, "word": " number", "probability": 0.884765625 }, { "start": 1152.68, "end": 1152.88, "word": " of", "probability": 0.90625 }, { "start": 1152.88, "end": 1153.28, "word": " words", "probability": 0.73681640625 }, { "start": 1153.28, "end": 1153.56, "word": " in", "probability": 0.90087890625 }, { "start": 1153.56, "end": 1153.94, "word": " spam", "probability": 0.896484375 }, { "start": 1153.94, "end": 1154.24, "word": ",", "probability": 0.98291015625 } ] }, { "id": 491, "seek": 115044, "start": 1154.24, "end": 1156.42, "text": " the total number of words in ham,", "tokens": [ 51364, 264, 3217, 1230, 295, 2283, 294, 7852, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.18480604064875636, "compression_ratio": 1.946078431372549, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 1154.24, "end": 1154.48, "word": " the", "probability": 0.81005859375 }, { "start": 1154.48, "end": 1154.72, "word": " total", "probability": 0.810546875 }, { "start": 1154.72, "end": 1154.96, "word": " number", "probability": 0.8857421875 }, { "start": 1154.96, "end": 1155.18, "word": " of", "probability": 0.90576171875 }, { "start": 1155.18, "end": 1155.6, "word": " words", "probability": 0.7275390625 }, { "start": 1155.6, "end": 1155.88, "word": " in", "probability": 0.87841796875 }, { "start": 1155.88, "end": 1156.22, "word": " ham", "probability": 0.69482421875 }, { "start": 1156.22, "end": 1156.42, "word": ",", "probability": 0.30029296875 } ] }, { "id": 492, "seek": 115044, "start": 1156.42, "end": 1158.08, "text": " or regular emails,", "tokens": [ 51464, 420, 3890, 12524, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.18480604064875636, "compression_ratio": 1.946078431372549, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 1156.42, "end": 1156.64, "word": " or", "probability": 0.8837890625 }, { "start": 1156.64, "end": 1157.2, "word": " regular", "probability": 0.890625 }, { "start": 1157.2, "end": 1157.66, "word": " emails", "probability": 0.767578125 }, { "start": 1157.66, "end": 1158.08, "word": ",", "probability": 0.9443359375 } ] }, { "id": 493, "seek": 115044, "start": 1158.08, "end": 1160.42, "text": " the count of each word in spam,", "tokens": [ 51564, 264, 1207, 295, 1184, 1349, 294, 24028, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.18480604064875636, "compression_ratio": 1.946078431372549, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 1158.08, "end": 1158.5, "word": " the", "probability": 0.81494140625 }, { "start": 1158.5, "end": 1158.9, "word": " count", "probability": 0.80419921875 }, { "start": 1158.9, "end": 1159.12, "word": " of", "probability": 0.90087890625 }, { "start": 1159.12, "end": 1159.36, "word": " each", "probability": 0.884765625 }, { "start": 1159.36, "end": 1159.66, "word": " word", "probability": 0.81884765625 }, { "start": 1159.66, "end": 1159.92, "word": " in", "probability": 0.89306640625 }, { "start": 1159.92, "end": 1160.26, "word": " spam", "probability": 0.919921875 }, { "start": 1160.26, "end": 1160.42, "word": ",", "probability": 0.71484375 } ] }, { "id": 494, "seek": 115044, "start": 1160.42, "end": 1162.7, "text": " and the count of each word in ham.", "tokens": [ 51664, 293, 264, 1207, 295, 1184, 1349, 294, 7852, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.18480604064875636, "compression_ratio": 1.946078431372549, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 1160.42, "end": 1160.56, "word": " and", "probability": 0.8955078125 }, { "start": 1160.56, "end": 1160.74, "word": " the", "probability": 0.81787109375 }, { "start": 1160.74, "end": 1161.06, "word": " count", "probability": 0.7880859375 }, { "start": 1161.06, "end": 1161.3, "word": " of", "probability": 0.900390625 }, { "start": 1161.3, "end": 1161.52, "word": " each", "probability": 0.890625 }, { "start": 1161.52, "end": 1161.86, "word": " word", "probability": 0.8212890625 }, { "start": 1161.86, "end": 1162.22, "word": " in", "probability": 0.89697265625 }, { "start": 1162.22, "end": 1162.48, "word": " ham", "probability": 0.8525390625 }, { "start": 1162.48, "end": 1162.7, "word": ".", "probability": 0.99169921875 } ] }, { "id": 495, "seek": 117662, "start": 1165.96, "end": 1168.0, "text": " So let's take a look at one of our emails.", "tokens": [ 50414, 407, 718, 311, 747, 257, 574, 412, 472, 295, 527, 12524, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.19274902762845159, "compression_ratio": 1.5708661417322836, "no_speech_prob": 0.00033020973205566406, "words": [ { "start": 1165.96, "end": 1166.32, "word": " So", "probability": 0.41162109375 }, { "start": 1166.32, "end": 1166.68, "word": " let's", "probability": 0.80126953125 }, { "start": 1166.68, "end": 1166.82, "word": " take", "probability": 0.791015625 }, { "start": 1166.9, "end": 1166.98, "word": " a look", "probability": 0.9189453125 }, { "start": 1166.98, "end": 1167.06, "word": " at", "probability": 0.90087890625 }, { "start": 1167.06, "end": 1167.16, "word": " one", "probability": 0.80859375 }, { "start": 1167.16, "end": 1167.24, "word": " of", "probability": 0.90283203125 }, { "start": 1167.24, "end": 1167.34, "word": " our", "probability": 0.8212890625 }, { "start": 1167.34, "end": 1167.64, "word": " emails", "probability": 0.77197265625 }, { "start": 1167.64, "end": 1168.0, "word": ".", "probability": 0.90869140625 } ] }, { "id": 496, "seek": 117662, "start": 1168.72, "end": 1169.5, "text": " We see here,", "tokens": [ 50564, 492, 536, 510, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.19274902762845159, "compression_ratio": 1.5708661417322836, "no_speech_prob": 0.00033020973205566406, "words": [ { "start": 1168.72, "end": 1168.88, "word": " We", "probability": 0.86181640625 }, { "start": 1168.88, "end": 1169.04, "word": " see", "probability": 0.5927734375 }, { "start": 1169.04, "end": 1169.38, "word": " here", "probability": 0.833984375 }, { "start": 1169.38, "end": 1169.5, "word": ",", "probability": 0.515625 } ] }, { "id": 497, "seek": 117662, "start": 1169.5, "end": 1171.62, "text": " East Asian fonts in Lenny.", "tokens": [ 50664, 6747, 10645, 35316, 294, 23009, 1634, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.19274902762845159, "compression_ratio": 1.5708661417322836, "no_speech_prob": 0.00033020973205566406, "words": [ { "start": 1169.5, "end": 1170.14, "word": " East", "probability": 0.0013370513916015625 }, { "start": 1170.14, "end": 1170.46, "word": " Asian", "probability": 0.74560546875 }, { "start": 1170.46, "end": 1170.92, "word": " fonts", "probability": 0.71044921875 }, { "start": 1170.92, "end": 1171.14, "word": " in", "probability": 0.64501953125 }, { "start": 1171.14, "end": 1171.46, "word": " Lenny", "probability": 0.72705078125 }, { "start": 1171.46, "end": 1171.62, "word": ".", "probability": 0.482177734375 } ] }, { "id": 498, "seek": 117662, "start": 1171.62, "end": 1172.64, "text": " Thanks for your support.", "tokens": [ 50764, 2561, 337, 428, 1406, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.19274902762845159, "compression_ratio": 1.5708661417322836, "no_speech_prob": 0.00033020973205566406, "words": [ { "start": 1171.62, "end": 1171.8, "word": " Thanks", "probability": 0.69140625 }, { "start": 1171.8, "end": 1171.92, "word": " for", "probability": 0.90087890625 }, { "start": 1171.92, "end": 1172.06, "word": " your", "probability": 0.8056640625 }, { "start": 1172.06, "end": 1172.48, "word": " support", "probability": 0.93212890625 }, { "start": 1172.48, "end": 1172.64, "word": ".", "probability": 0.41064453125 } ] }, { "id": 499, "seek": 117662, "start": 1172.64, "end": 1174.76, "text": " Installing Unifonts did it well for me.", "tokens": [ 50864, 2730, 24021, 1156, 351, 896, 82, 630, 309, 731, 337, 385, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.19274902762845159, "compression_ratio": 1.5708661417322836, "no_speech_prob": 0.00033020973205566406, "words": [ { "start": 1172.64, "end": 1172.98, "word": " Installing", "probability": 0.942138671875 }, { "start": 1172.98, "end": 1173.58, "word": " Unifonts", "probability": 0.7918701171875 }, { "start": 1173.58, "end": 1173.74, "word": " did", "probability": 0.79248046875 }, { "start": 1173.74, "end": 1173.86, "word": " it", "probability": 0.90283203125 }, { "start": 1173.86, "end": 1174.02, "word": " well", "probability": 0.88037109375 }, { "start": 1174.02, "end": 1174.2, "word": " for", "probability": 0.89404296875 }, { "start": 1174.2, "end": 1174.4, "word": " me", "probability": 0.904296875 }, { "start": 1174.4, "end": 1174.76, "word": ".", "probability": 0.9833984375 } ] }, { "id": 500, "seek": 117662, "start": 1175.34, "end": 1177.14, "text": " Now we want to take a sentence like this", "tokens": [ 50964, 823, 321, 528, 281, 747, 257, 8174, 411, 341, 51014 ], "temperature": 0.0, "avg_logprob": -0.19274902762845159, "compression_ratio": 1.5708661417322836, "no_speech_prob": 0.00033020973205566406, "words": [ { "start": 1175.34, "end": 1175.7, "word": " Now", "probability": 0.87744140625 }, { "start": 1175.7, "end": 1175.8, "word": " we", "probability": 0.72119140625 }, { "start": 1175.8, "end": 1175.94, "word": " want", "probability": 0.5703125 }, { "start": 1175.94, "end": 1176.02, "word": " to", "probability": 0.90380859375 }, { "start": 1176.02, "end": 1176.16, "word": " take", "probability": 0.810546875 }, { "start": 1176.3, "end": 1176.5, "word": " a sentence", "probability": 0.849609375 }, { "start": 1176.5, "end": 1176.76, "word": " like", "probability": 0.87890625 }, { "start": 1176.76, "end": 1177.14, "word": " this", "probability": 0.8837890625 } ] }, { "id": 501, "seek": 117662, "start": 1177.14, "end": 1179.92, "text": " and find a way to classify it", "tokens": [ 51064, 293, 915, 257, 636, 281, 33872, 309, 51114 ], "temperature": 0.0, "avg_logprob": -0.19274902762845159, "compression_ratio": 1.5708661417322836, "no_speech_prob": 0.00033020973205566406, "words": [ { "start": 1177.14, "end": 1177.6, "word": " and", "probability": 0.81396484375 }, { "start": 1177.6, "end": 1178.04, "word": " find", "probability": 0.8134765625 }, { "start": 1178.2, "end": 1178.4, "word": " a way", "probability": 0.9013671875 }, { "start": 1178.4, "end": 1178.82, "word": " to", "probability": 0.90380859375 }, { "start": 1178.82, "end": 1179.52, "word": " classify", "probability": 0.94287109375 }, { "start": 1179.52, "end": 1179.92, "word": " it", "probability": 0.8876953125 } ] }, { "id": 502, "seek": 117662, "start": 1179.92, "end": 1182.24, "text": " as being spam or ham.", "tokens": [ 51164, 382, 885, 24028, 420, 7852, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.19274902762845159, "compression_ratio": 1.5708661417322836, "no_speech_prob": 0.00033020973205566406, "words": [ { "start": 1179.92, "end": 1180.14, "word": " as", "probability": 0.9033203125 }, { "start": 1180.14, "end": 1180.58, "word": " being", "probability": 0.74951171875 }, { "start": 1180.58, "end": 1181.12, "word": " spam", "probability": 0.85205078125 }, { "start": 1181.12, "end": 1181.48, "word": " or", "probability": 0.88427734375 }, { "start": 1181.48, "end": 1181.88, "word": " ham", "probability": 0.7744140625 }, { "start": 1181.88, "end": 1182.24, "word": ".", "probability": 0.8876953125 } ] }, { "id": 503, "seek": 117662, "start": 1182.7, "end": 1183.86, "text": " But before we do that,", "tokens": [ 51314, 583, 949, 321, 360, 300, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.19274902762845159, "compression_ratio": 1.5708661417322836, "no_speech_prob": 0.00033020973205566406, "words": [ { "start": 1182.7, "end": 1182.94, "word": " But", "probability": 0.88330078125 }, { "start": 1182.94, "end": 1183.22, "word": " before", "probability": 0.79833984375 }, { "start": 1183.22, "end": 1183.4, "word": " we", "probability": 0.90673828125 }, { "start": 1183.4, "end": 1183.54, "word": " do", "probability": 0.90966796875 }, { "start": 1183.54, "end": 1183.8, "word": " that", "probability": 0.88427734375 }, { "start": 1183.8, "end": 1183.86, "word": ",", "probability": 0.92333984375 } ] }, { "id": 504, "seek": 117662, "start": 1183.86, "end": 1185.84, "text": " we want to kind of point out a couple things.", "tokens": [ 51414, 321, 528, 281, 733, 295, 935, 484, 257, 1916, 721, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.19274902762845159, "compression_ratio": 1.5708661417322836, "no_speech_prob": 0.00033020973205566406, "words": [ { "start": 1183.86, "end": 1183.98, "word": " we", "probability": 0.9052734375 }, { "start": 1183.98, "end": 1184.14, "word": " want", "probability": 0.798828125 }, { "start": 1184.14, "end": 1184.26, "word": " to", "probability": 0.9033203125 }, { "start": 1184.26, "end": 1184.44, "word": " kind", "probability": 0.7431640625 }, { "start": 1184.44, "end": 1184.56, "word": " of", "probability": 0.90625 }, { "start": 1184.56, "end": 1184.92, "word": " point", "probability": 0.84814453125 }, { "start": 1184.92, "end": 1185.1, "word": " out", "probability": 0.81787109375 }, { "start": 1185.2, "end": 1185.36, "word": " a couple", "probability": 0.7919921875 }, { "start": 1185.36, "end": 1185.76, "word": " things", "probability": 0.298095703125 }, { "start": 1185.76, "end": 1185.84, "word": ".", "probability": 0.98193359375 } ] }, { "id": 505, "seek": 117662, "start": 1185.84, "end": 1187.5, "text": " So we see here kind of towards the bottom,", "tokens": [ 51514, 407, 321, 536, 510, 733, 295, 3030, 264, 2767, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.19274902762845159, "compression_ratio": 1.5708661417322836, "no_speech_prob": 0.00033020973205566406, "words": [ { "start": 1185.84, "end": 1186.04, "word": " So", "probability": 0.87939453125 }, { "start": 1186.04, "end": 1186.16, "word": " we", "probability": 0.89599609375 }, { "start": 1186.16, "end": 1186.3, "word": " see", "probability": 0.80615234375 }, { "start": 1186.3, "end": 1186.46, "word": " here", "probability": 0.8134765625 }, { "start": 1186.46, "end": 1186.66, "word": " kind", "probability": 0.70703125 }, { "start": 1186.66, "end": 1186.74, "word": " of", "probability": 0.8984375 }, { "start": 1186.74, "end": 1187.0, "word": " towards", "probability": 0.64013671875 }, { "start": 1187.0, "end": 1187.18, "word": " the", "probability": 0.81640625 }, { "start": 1187.18, "end": 1187.38, "word": " bottom", "probability": 0.791015625 }, { "start": 1187.38, "end": 1187.5, "word": ",", "probability": 0.591796875 } ] }, { "id": 506, "seek": 117662, "start": 1187.5, "end": 1189.34, "text": " we have the word unsubscribe,", "tokens": [ 51614, 321, 362, 264, 1349, 2693, 9493, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.19274902762845159, "compression_ratio": 1.5708661417322836, "no_speech_prob": 0.00033020973205566406, "words": [ { "start": 1187.5, "end": 1187.56, "word": " we", "probability": 0.89892578125 }, { "start": 1187.56, "end": 1187.7, "word": " have", "probability": 0.880859375 }, { "start": 1187.7, "end": 1187.82, "word": " the", "probability": 0.80810546875 }, { "start": 1187.82, "end": 1187.98, "word": " word", "probability": 0.8134765625 }, { "start": 1187.98, "end": 1188.78, "word": " unsubscribe", "probability": 0.677490234375 }, { "start": 1188.78, "end": 1189.34, "word": ",", "probability": 0.65869140625 } ] }, { "id": 507, "seek": 117662, "start": 1189.34, "end": 1190.4, "text": " all capitalized,", "tokens": [ 51714, 439, 4238, 1602, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.19274902762845159, "compression_ratio": 1.5708661417322836, "no_speech_prob": 0.00033020973205566406, "words": [ { "start": 1189.34, "end": 1189.6, "word": " all", "probability": 0.87939453125 }, { "start": 1189.6, "end": 1190.26, "word": " capitalized", "probability": 0.90625 }, { "start": 1190.26, "end": 1190.4, "word": ",", "probability": 0.493896484375 } ] }, { "id": 508, "seek": 120492, "start": 1190.4, "end": 1192.7, "text": " and then unsubscribe lowercase.", "tokens": [ 50364, 293, 550, 2693, 9493, 3126, 9765, 13, 50414 ], "temperature": 0.0, "avg_logprob": -0.17006715467153502, "compression_ratio": 1.8311111111111111, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 1190.4, "end": 1190.4, "word": " and", "probability": 0.57666015625 }, { "start": 1190.4, "end": 1190.58, "word": " then", "probability": 0.71435546875 }, { "start": 1190.58, "end": 1191.24, "word": " unsubscribe", "probability": 0.7275390625 }, { "start": 1191.24, "end": 1192.22, "word": " lowercase", "probability": 0.677490234375 }, { "start": 1192.22, "end": 1192.7, "word": ".", "probability": 0.94921875 } ] }, { "id": 509, "seek": 120492, "start": 1192.9, "end": 1195.46, "text": " What we want to do is look at keywords.", "tokens": [ 50464, 708, 321, 528, 281, 360, 307, 574, 412, 21009, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.17006715467153502, "compression_ratio": 1.8311111111111111, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 1192.9, "end": 1193.32, "word": " What", "probability": 0.80029296875 }, { "start": 1193.32, "end": 1193.44, "word": " we", "probability": 0.9091796875 }, { "start": 1193.44, "end": 1193.58, "word": " want", "probability": 0.4501953125 }, { "start": 1193.58, "end": 1193.66, "word": " to", "probability": 0.904296875 }, { "start": 1193.66, "end": 1193.78, "word": " do", "probability": 0.90625 }, { "start": 1193.78, "end": 1193.92, "word": " is", "probability": 0.90185546875 }, { "start": 1193.92, "end": 1194.18, "word": " look", "probability": 0.9091796875 }, { "start": 1194.18, "end": 1194.36, "word": " at", "probability": 0.9033203125 }, { "start": 1194.36, "end": 1194.98, "word": " keywords", "probability": 0.420654296875 }, { "start": 1194.98, "end": 1195.46, "word": ".", "probability": 0.755859375 } ] }, { "id": 510, "seek": 120492, "start": 1195.5, "end": 1197.54, "text": " And so in context,", "tokens": [ 50614, 400, 370, 294, 4319, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.17006715467153502, "compression_ratio": 1.8311111111111111, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 1195.5, "end": 1195.54, "word": " And", "probability": 0.7880859375 }, { "start": 1195.54, "end": 1195.9, "word": " so", "probability": 0.900390625 }, { "start": 1195.9, "end": 1196.78, "word": " in", "probability": 0.68798828125 }, { "start": 1196.78, "end": 1197.38, "word": " context", "probability": 0.77099609375 }, { "start": 1197.38, "end": 1197.54, "word": ",", "probability": 0.87548828125 } ] }, { "id": 511, "seek": 120492, "start": 1197.54, "end": 1201.62, "text": " it doesn't matter if unsubscribe is capitalized", "tokens": [ 50714, 309, 1177, 380, 1871, 498, 2693, 9493, 307, 4238, 1602, 50864 ], "temperature": 0.0, "avg_logprob": -0.17006715467153502, "compression_ratio": 1.8311111111111111, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 1197.54, "end": 1197.64, "word": " it", "probability": 0.90234375 }, { "start": 1197.64, "end": 1197.92, "word": " doesn't", "probability": 0.93603515625 }, { "start": 1197.92, "end": 1198.46, "word": " matter", "probability": 0.8095703125 }, { "start": 1198.46, "end": 1200.26, "word": " if", "probability": 0.82861328125 }, { "start": 1200.26, "end": 1200.74, "word": " unsubscribe", "probability": 0.814697265625 }, { "start": 1200.74, "end": 1201.0, "word": " is", "probability": 0.90234375 }, { "start": 1201.0, "end": 1201.62, "word": " capitalized", "probability": 0.90234375 } ] }, { "id": 512, "seek": 120492, "start": 1201.62, "end": 1202.86, "text": " or the first letter is capitalized", "tokens": [ 50914, 420, 264, 700, 5063, 307, 4238, 1602, 50964 ], "temperature": 0.0, "avg_logprob": -0.17006715467153502, "compression_ratio": 1.8311111111111111, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 1201.62, "end": 1201.74, "word": " or", "probability": 0.6865234375 }, { "start": 1201.74, "end": 1201.84, "word": " the", "probability": 0.80810546875 }, { "start": 1201.84, "end": 1202.06, "word": " first", "probability": 0.82373046875 }, { "start": 1202.06, "end": 1202.26, "word": " letter", "probability": 0.66357421875 }, { "start": 1202.26, "end": 1202.36, "word": " is", "probability": 0.55078125 }, { "start": 1202.36, "end": 1202.86, "word": " capitalized", "probability": 0.917236328125 } ] }, { "id": 513, "seek": 120492, "start": 1202.86, "end": 1204.18, "text": " or it's all lowercase.", "tokens": [ 51014, 420, 309, 311, 439, 3126, 9765, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.17006715467153502, "compression_ratio": 1.8311111111111111, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 1202.86, "end": 1202.98, "word": " or", "probability": 0.6572265625 }, { "start": 1202.98, "end": 1203.1, "word": " it's", "probability": 0.947265625 }, { "start": 1203.1, "end": 1203.32, "word": " all", "probability": 0.9013671875 }, { "start": 1203.32, "end": 1203.88, "word": " lowercase", "probability": 0.8369140625 }, { "start": 1203.88, "end": 1204.18, "word": ".", "probability": 0.444580078125 } ] }, { "id": 514, "seek": 120492, "start": 1204.28, "end": 1206.3, "text": " It means the same thing.", "tokens": [ 51114, 467, 1355, 264, 912, 551, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.17006715467153502, "compression_ratio": 1.8311111111111111, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 1204.28, "end": 1204.76, "word": " It", "probability": 0.89794921875 }, { "start": 1204.76, "end": 1205.0, "word": " means", "probability": 0.8828125 }, { "start": 1205.0, "end": 1205.24, "word": " the", "probability": 0.80859375 }, { "start": 1205.24, "end": 1205.46, "word": " same", "probability": 0.81005859375 }, { "start": 1205.46, "end": 1205.82, "word": " thing", "probability": 0.8125 }, { "start": 1205.82, "end": 1206.3, "word": ".", "probability": 0.97607421875 } ] }, { "id": 515, "seek": 120492, "start": 1206.32, "end": 1210.9, "text": " And so to kind of reduce our problem set,", "tokens": [ 51214, 400, 370, 281, 733, 295, 5407, 527, 1154, 992, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.17006715467153502, "compression_ratio": 1.8311111111111111, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 1206.32, "end": 1206.4, "word": " And", "probability": 0.884765625 }, { "start": 1206.4, "end": 1206.76, "word": " so", "probability": 0.9033203125 }, { "start": 1206.76, "end": 1207.6, "word": " to", "probability": 0.8623046875 }, { "start": 1207.6, "end": 1208.26, "word": " kind", "probability": 0.7822265625 }, { "start": 1208.26, "end": 1208.44, "word": " of", "probability": 0.9013671875 }, { "start": 1208.44, "end": 1209.12, "word": " reduce", "probability": 0.75927734375 }, { "start": 1209.12, "end": 1210.08, "word": " our", "probability": 0.81884765625 }, { "start": 1210.08, "end": 1210.5, "word": " problem", "probability": 0.765625 }, { "start": 1210.5, "end": 1210.82, "word": " set", "probability": 0.89453125 }, { "start": 1210.82, "end": 1210.9, "word": ",", "probability": 0.81005859375 } ] }, { "id": 516, "seek": 120492, "start": 1210.9, "end": 1213.42, "text": " what we're going to do is set everything to lowercase.", "tokens": [ 51364, 437, 321, 434, 516, 281, 360, 307, 992, 1203, 281, 3126, 9765, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.17006715467153502, "compression_ratio": 1.8311111111111111, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 1210.9, "end": 1210.98, "word": " what", "probability": 0.88037109375 }, { "start": 1210.98, "end": 1211.14, "word": " we're", "probability": 0.92578125 }, { "start": 1211.14, "end": 1211.2, "word": " going", "probability": 0.486328125 }, { "start": 1211.2, "end": 1211.26, "word": " to", "probability": 0.90625 }, { "start": 1211.26, "end": 1211.38, "word": " do", "probability": 0.90869140625 }, { "start": 1211.38, "end": 1211.5, "word": " is", "probability": 0.90478515625 }, { "start": 1211.5, "end": 1211.68, "word": " set", "probability": 0.91650390625 }, { "start": 1211.68, "end": 1212.12, "word": " everything", "probability": 0.89111328125 }, { "start": 1212.12, "end": 1212.34, "word": " to", "probability": 0.8984375 }, { "start": 1212.34, "end": 1212.94, "word": " lowercase", "probability": 0.8447265625 }, { "start": 1212.94, "end": 1213.42, "word": ".", "probability": 0.998046875 } ] }, { "id": 517, "seek": 120492, "start": 1213.9, "end": 1215.14, "text": " The other thing we want to do", "tokens": [ 51514, 440, 661, 551, 321, 528, 281, 360, 51564 ], "temperature": 0.0, "avg_logprob": -0.17006715467153502, "compression_ratio": 1.8311111111111111, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 1213.9, "end": 1214.38, "word": " The", "probability": 0.8251953125 }, { "start": 1214.38, "end": 1214.52, "word": " other", "probability": 0.779296875 }, { "start": 1214.52, "end": 1214.68, "word": " thing", "probability": 0.81591796875 }, { "start": 1214.68, "end": 1214.78, "word": " we", "probability": 0.90283203125 }, { "start": 1214.78, "end": 1214.92, "word": " want", "probability": 0.796875 }, { "start": 1214.92, "end": 1215.0, "word": " to", "probability": 0.9072265625 }, { "start": 1215.0, "end": 1215.14, "word": " do", "probability": 0.9013671875 } ] }, { "id": 518, "seek": 120492, "start": 1215.14, "end": 1217.18, "text": " is remove what are called stop words.", "tokens": [ 51614, 307, 4159, 437, 366, 1219, 1590, 2283, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.17006715467153502, "compression_ratio": 1.8311111111111111, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 1215.14, "end": 1215.28, "word": " is", "probability": 0.9013671875 }, { "start": 1215.28, "end": 1215.64, "word": " remove", "probability": 0.86767578125 }, { "start": 1215.64, "end": 1215.86, "word": " what", "probability": 0.86962890625 }, { "start": 1215.86, "end": 1215.96, "word": " are", "probability": 0.89404296875 }, { "start": 1215.96, "end": 1216.28, "word": " called", "probability": 0.8134765625 }, { "start": 1216.28, "end": 1216.76, "word": " stop", "probability": 0.892578125 }, { "start": 1216.76, "end": 1217.02, "word": " words", "probability": 0.51904296875 }, { "start": 1217.02, "end": 1217.18, "word": ".", "probability": 0.947265625 } ] }, { "id": 519, "seek": 120492, "start": 1217.18, "end": 1218.7, "text": " Stop words are words like", "tokens": [ 51714, 5535, 2283, 366, 2283, 411, 51764 ], "temperature": 0.0, "avg_logprob": -0.17006715467153502, "compression_ratio": 1.8311111111111111, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 1217.18, "end": 1217.42, "word": " Stop", "probability": 0.86279296875 }, { "start": 1217.42, "end": 1217.76, "word": " words", "probability": 0.69384765625 }, { "start": 1217.76, "end": 1218.1, "word": " are", "probability": 0.87451171875 }, { "start": 1218.1, "end": 1218.46, "word": " words", "probability": 0.720703125 }, { "start": 1218.46, "end": 1218.7, "word": " like", "probability": 0.8642578125 } ] }, { "id": 520, "seek": 123204, "start": 1218.7, "end": 1221.7, "text": " the, in, of, on, or...", "tokens": [ 50364, 264, 11, 294, 11, 295, 11, 322, 11, 420, 485, 50464 ], "temperature": 0.0, "avg_logprob": -0.15977443160867333, "compression_ratio": 1.847457627118644, "no_speech_prob": 0.002758026123046875, "words": [ { "start": 1218.7, "end": 1218.94, "word": " the", "probability": 0.236328125 }, { "start": 1218.94, "end": 1219.12, "word": ",", "probability": 0.393310546875 }, { "start": 1219.12, "end": 1219.56, "word": " in", "probability": 0.84423828125 }, { "start": 1219.56, "end": 1219.72, "word": ",", "probability": 0.97509765625 }, { "start": 1219.72, "end": 1220.02, "word": " of", "probability": 0.85888671875 }, { "start": 1220.02, "end": 1220.2, "word": ",", "probability": 0.97900390625 }, { "start": 1220.2, "end": 1220.48, "word": " on", "probability": 0.904296875 }, { "start": 1220.48, "end": 1220.74, "word": ",", "probability": 0.76025390625 }, { "start": 1220.74, "end": 1221.7, "word": " or...", "probability": 0.5615234375 } ] }, { "id": 521, "seek": 123204, "start": 1221.7, "end": 1224.42, "text": " They don't add any context to the sentence.", "tokens": [ 50514, 814, 500, 380, 909, 604, 4319, 281, 264, 8174, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.15977443160867333, "compression_ratio": 1.847457627118644, "no_speech_prob": 0.002758026123046875, "words": [ { "start": 1221.7, "end": 1221.9, "word": " They", "probability": 0.349365234375 }, { "start": 1221.9, "end": 1222.12, "word": " don't", "probability": 0.9453125 }, { "start": 1222.12, "end": 1222.44, "word": " add", "probability": 0.81884765625 }, { "start": 1222.44, "end": 1222.66, "word": " any", "probability": 0.81640625 }, { "start": 1222.66, "end": 1223.2, "word": " context", "probability": 0.76611328125 }, { "start": 1223.2, "end": 1223.44, "word": " to", "probability": 0.90869140625 }, { "start": 1223.44, "end": 1223.6, "word": " the", "probability": 0.8134765625 }, { "start": 1223.6, "end": 1223.98, "word": " sentence", "probability": 0.83203125 }, { "start": 1223.98, "end": 1224.42, "word": ".", "probability": 0.85986328125 } ] }, { "id": 522, "seek": 123204, "start": 1224.78, "end": 1227.1, "text": " And we're going to do the same thing for punctuation.", "tokens": [ 50664, 400, 321, 434, 516, 281, 360, 264, 912, 551, 337, 27006, 16073, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.15977443160867333, "compression_ratio": 1.847457627118644, "no_speech_prob": 0.002758026123046875, "words": [ { "start": 1224.78, "end": 1224.92, "word": " And", "probability": 0.6552734375 }, { "start": 1224.92, "end": 1225.04, "word": " we're", "probability": 0.91259765625 }, { "start": 1225.04, "end": 1225.06, "word": " going", "probability": 0.49072265625 }, { "start": 1225.06, "end": 1225.12, "word": " to", "probability": 0.9052734375 }, { "start": 1225.12, "end": 1225.22, "word": " do", "probability": 0.9033203125 }, { "start": 1225.22, "end": 1225.36, "word": " the", "probability": 0.8095703125 }, { "start": 1225.36, "end": 1225.54, "word": " same", "probability": 0.8115234375 }, { "start": 1225.54, "end": 1225.8, "word": " thing", "probability": 0.80322265625 }, { "start": 1225.8, "end": 1226.0, "word": " for", "probability": 0.8935546875 }, { "start": 1226.0, "end": 1226.66, "word": " punctuation", "probability": 0.920654296875 }, { "start": 1226.66, "end": 1227.1, "word": ".", "probability": 0.93017578125 } ] }, { "id": 523, "seek": 123204, "start": 1227.2, "end": 1228.58, "text": " So we're going to remove those.", "tokens": [ 50814, 407, 321, 434, 516, 281, 4159, 729, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.15977443160867333, "compression_ratio": 1.847457627118644, "no_speech_prob": 0.002758026123046875, "words": [ { "start": 1227.2, "end": 1227.42, "word": " So", "probability": 0.8486328125 }, { "start": 1227.42, "end": 1227.64, "word": " we're", "probability": 0.8310546875 }, { "start": 1227.64, "end": 1227.72, "word": " going", "probability": 0.82080078125 }, { "start": 1227.72, "end": 1227.78, "word": " to", "probability": 0.9033203125 }, { "start": 1227.78, "end": 1228.08, "word": " remove", "probability": 0.853515625 }, { "start": 1228.08, "end": 1228.46, "word": " those", "probability": 0.85205078125 }, { "start": 1228.46, "end": 1228.58, "word": ".", "probability": 0.39697265625 } ] }, { "id": 524, "seek": 123204, "start": 1228.58, "end": 1230.3, "text": " We're going to keep our keywords.", "tokens": [ 50914, 492, 434, 516, 281, 1066, 527, 21009, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.15977443160867333, "compression_ratio": 1.847457627118644, "no_speech_prob": 0.002758026123046875, "words": [ { "start": 1228.58, "end": 1228.68, "word": " We're", "probability": 0.926025390625 }, { "start": 1228.68, "end": 1228.84, "word": " going", "probability": 0.85888671875 }, { "start": 1228.84, "end": 1229.0, "word": " to", "probability": 0.9091796875 }, { "start": 1229.0, "end": 1229.24, "word": " keep", "probability": 0.81787109375 }, { "start": 1229.24, "end": 1229.42, "word": " our", "probability": 0.80517578125 }, { "start": 1229.42, "end": 1229.88, "word": " keywords", "probability": 0.47021484375 }, { "start": 1229.88, "end": 1230.3, "word": ".", "probability": 0.64208984375 } ] }, { "id": 525, "seek": 123204, "start": 1230.3, "end": 1231.8, "text": " And then one more thing that we're going to do", "tokens": [ 51014, 400, 550, 472, 544, 551, 300, 321, 434, 516, 281, 360, 51064 ], "temperature": 0.0, "avg_logprob": -0.15977443160867333, "compression_ratio": 1.847457627118644, "no_speech_prob": 0.002758026123046875, "words": [ { "start": 1230.3, "end": 1230.36, "word": " And", "probability": 0.880859375 }, { "start": 1230.36, "end": 1230.56, "word": " then", "probability": 0.72314453125 }, { "start": 1230.56, "end": 1230.82, "word": " one", "probability": 0.78271484375 }, { "start": 1230.82, "end": 1231.0, "word": " more", "probability": 0.88134765625 }, { "start": 1231.0, "end": 1231.18, "word": " thing", "probability": 0.81787109375 }, { "start": 1231.18, "end": 1231.3, "word": " that", "probability": 0.865234375 }, { "start": 1231.3, "end": 1231.46, "word": " we're", "probability": 0.930908203125 }, { "start": 1231.46, "end": 1231.5, "word": " going", "probability": 0.82958984375 }, { "start": 1231.5, "end": 1231.56, "word": " to", "probability": 0.90625 }, { "start": 1231.56, "end": 1231.8, "word": " do", "probability": 0.90576171875 } ] }, { "id": 526, "seek": 123204, "start": 1231.8, "end": 1233.3, "text": " is called stemming.", "tokens": [ 51114, 307, 1219, 12312, 2810, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.15977443160867333, "compression_ratio": 1.847457627118644, "no_speech_prob": 0.002758026123046875, "words": [ { "start": 1231.8, "end": 1232.04, "word": " is", "probability": 0.88232421875 }, { "start": 1232.04, "end": 1232.32, "word": " called", "probability": 0.8076171875 }, { "start": 1232.32, "end": 1232.86, "word": " stemming", "probability": 0.862548828125 }, { "start": 1232.86, "end": 1233.3, "word": ".", "probability": 0.98876953125 } ] }, { "id": 527, "seek": 123204, "start": 1233.58, "end": 1236.06, "text": " So if we have something like the word", "tokens": [ 51214, 407, 498, 321, 362, 746, 411, 264, 1349, 51264 ], "temperature": 0.0, "avg_logprob": -0.15977443160867333, "compression_ratio": 1.847457627118644, "no_speech_prob": 0.002758026123046875, "words": [ { "start": 1233.58, "end": 1234.02, "word": " So", "probability": 0.8916015625 }, { "start": 1234.02, "end": 1234.3, "word": " if", "probability": 0.84521484375 }, { "start": 1234.3, "end": 1234.46, "word": " we", "probability": 0.904296875 }, { "start": 1234.46, "end": 1234.64, "word": " have", "probability": 0.88525390625 }, { "start": 1234.64, "end": 1234.94, "word": " something", "probability": 0.73583984375 }, { "start": 1234.94, "end": 1235.54, "word": " like", "probability": 0.87158203125 }, { "start": 1235.54, "end": 1235.76, "word": " the", "probability": 0.81005859375 }, { "start": 1235.76, "end": 1236.06, "word": " word", "probability": 0.8056640625 } ] }, { "id": 528, "seek": 123204, "start": 1236.82, "end": 1238.7, "text": " congrats or congratulations,", "tokens": [ 51314, 8882, 1720, 420, 13568, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.15977443160867333, "compression_ratio": 1.847457627118644, "no_speech_prob": 0.002758026123046875, "words": [ { "start": 1236.82, "end": 1237.26, "word": " congrats", "probability": 0.6368408203125 }, { "start": 1237.26, "end": 1237.64, "word": " or", "probability": 0.705078125 }, { "start": 1237.64, "end": 1238.48, "word": " congratulations", "probability": 0.7880859375 }, { "start": 1238.48, "end": 1238.7, "word": ",", "probability": 0.53857421875 } ] }, { "id": 529, "seek": 123204, "start": 1239.54, "end": 1240.54, "text": " in the English language,", "tokens": [ 51414, 294, 264, 3669, 2856, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.15977443160867333, "compression_ratio": 1.847457627118644, "no_speech_prob": 0.002758026123046875, "words": [ { "start": 1239.54, "end": 1239.76, "word": " in", "probability": 0.869140625 }, { "start": 1239.76, "end": 1239.88, "word": " the", "probability": 0.8193359375 }, { "start": 1239.88, "end": 1240.14, "word": " English", "probability": 0.88671875 }, { "start": 1240.14, "end": 1240.46, "word": " language", "probability": 0.67626953125 }, { "start": 1240.46, "end": 1240.54, "word": ",", "probability": 0.697265625 } ] }, { "id": 530, "seek": 123204, "start": 1240.54, "end": 1241.62, "text": " they mean the same thing.", "tokens": [ 51514, 436, 914, 264, 912, 551, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.15977443160867333, "compression_ratio": 1.847457627118644, "no_speech_prob": 0.002758026123046875, "words": [ { "start": 1240.54, "end": 1240.66, "word": " they", "probability": 0.728515625 }, { "start": 1240.66, "end": 1240.82, "word": " mean", "probability": 0.93310546875 }, { "start": 1240.82, "end": 1240.98, "word": " the", "probability": 0.81591796875 }, { "start": 1240.98, "end": 1241.16, "word": " same", "probability": 0.8095703125 }, { "start": 1241.16, "end": 1241.5, "word": " thing", "probability": 0.80419921875 }, { "start": 1241.5, "end": 1241.62, "word": ".", "probability": 0.99267578125 } ] }, { "id": 531, "seek": 123204, "start": 1241.62, "end": 1244.2, "text": " So if we're looking at keywords,", "tokens": [ 51614, 407, 498, 321, 434, 1237, 412, 21009, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.15977443160867333, "compression_ratio": 1.847457627118644, "no_speech_prob": 0.002758026123046875, "words": [ { "start": 1241.62, "end": 1241.76, "word": " So", "probability": 0.8955078125 }, { "start": 1241.76, "end": 1241.92, "word": " if", "probability": 0.84619140625 }, { "start": 1241.92, "end": 1242.02, "word": " we're", "probability": 0.927734375 }, { "start": 1242.02, "end": 1242.4, "word": " looking", "probability": 0.79833984375 }, { "start": 1242.4, "end": 1242.88, "word": " at", "probability": 0.8984375 }, { "start": 1242.88, "end": 1243.4, "word": " keywords", "probability": 0.57470703125 }, { "start": 1243.4, "end": 1244.2, "word": ",", "probability": 0.95751953125 } ] }, { "id": 532, "seek": 123204, "start": 1244.2, "end": 1245.82, "text": " we want to treat them the same.", "tokens": [ 51714, 321, 528, 281, 2387, 552, 264, 912, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.15977443160867333, "compression_ratio": 1.847457627118644, "no_speech_prob": 0.002758026123046875, "words": [ { "start": 1244.2, "end": 1244.44, "word": " we", "probability": 0.90380859375 }, { "start": 1244.44, "end": 1244.62, "word": " want", "probability": 0.81298828125 }, { "start": 1244.62, "end": 1244.76, "word": " to", "probability": 0.9072265625 }, { "start": 1244.76, "end": 1245.0, "word": " treat", "probability": 0.796875 }, { "start": 1245.0, "end": 1245.16, "word": " them", "probability": 0.74609375 }, { "start": 1245.16, "end": 1245.36, "word": " the", "probability": 0.81103515625 }, { "start": 1245.36, "end": 1245.6, "word": " same", "probability": 0.8056640625 }, { "start": 1245.6, "end": 1245.82, "word": ".", "probability": 0.96923828125 } ] }, { "id": 533, "seek": 125972, "start": 1245.82, "end": 1247.0, "text": " And so what stemming does", "tokens": [ 50364, 400, 370, 437, 12312, 2810, 775, 50414 ], "temperature": 0.0, "avg_logprob": -0.1854910754731723, "compression_ratio": 1.8446969696969697, "no_speech_prob": 0.00010228157043457031, "words": [ { "start": 1245.82, "end": 1245.9, "word": " And", "probability": 0.67333984375 }, { "start": 1245.9, "end": 1246.08, "word": " so", "probability": 0.89501953125 }, { "start": 1246.08, "end": 1246.28, "word": " what", "probability": 0.82275390625 }, { "start": 1246.28, "end": 1246.66, "word": " stemming", "probability": 0.904296875 }, { "start": 1246.66, "end": 1247.0, "word": " does", "probability": 0.92431640625 } ] }, { "id": 534, "seek": 125972, "start": 1247.0, "end": 1249.6, "text": " is shrink those words down to their base form", "tokens": [ 50464, 307, 23060, 729, 2283, 760, 281, 641, 3096, 1254, 50514 ], "temperature": 0.0, "avg_logprob": -0.1854910754731723, "compression_ratio": 1.8446969696969697, "no_speech_prob": 0.00010228157043457031, "words": [ { "start": 1247.0, "end": 1247.26, "word": " is", "probability": 0.83251953125 }, { "start": 1247.26, "end": 1247.66, "word": " shrink", "probability": 0.8671875 }, { "start": 1247.66, "end": 1247.96, "word": " those", "probability": 0.857421875 }, { "start": 1247.96, "end": 1248.24, "word": " words", "probability": 0.71533203125 }, { "start": 1248.24, "end": 1248.58, "word": " down", "probability": 0.80126953125 }, { "start": 1248.58, "end": 1248.78, "word": " to", "probability": 0.8974609375 }, { "start": 1248.78, "end": 1248.94, "word": " their", "probability": 0.90478515625 }, { "start": 1248.94, "end": 1249.28, "word": " base", "probability": 0.83056640625 }, { "start": 1249.28, "end": 1249.6, "word": " form", "probability": 0.83056640625 } ] }, { "id": 535, "seek": 125972, "start": 1249.6, "end": 1250.96, "text": " or the root form.", "tokens": [ 50564, 420, 264, 5593, 1254, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.1854910754731723, "compression_ratio": 1.8446969696969697, "no_speech_prob": 0.00010228157043457031, "words": [ { "start": 1249.6, "end": 1249.72, "word": " or", "probability": 0.8203125 }, { "start": 1249.72, "end": 1249.88, "word": " the", "probability": 0.7294921875 }, { "start": 1249.88, "end": 1250.1, "word": " root", "probability": 0.791015625 }, { "start": 1250.1, "end": 1250.52, "word": " form", "probability": 0.822265625 }, { "start": 1250.52, "end": 1250.96, "word": ".", "probability": 0.355224609375 } ] }, { "id": 536, "seek": 125972, "start": 1250.96, "end": 1252.86, "text": " And then we can count them the same.", "tokens": [ 50664, 400, 550, 321, 393, 1207, 552, 264, 912, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.1854910754731723, "compression_ratio": 1.8446969696969697, "no_speech_prob": 0.00010228157043457031, "words": [ { "start": 1250.96, "end": 1251.2, "word": " And", "probability": 0.892578125 }, { "start": 1251.2, "end": 1251.32, "word": " then", "probability": 0.73291015625 }, { "start": 1251.32, "end": 1251.44, "word": " we", "probability": 0.8994140625 }, { "start": 1251.44, "end": 1251.58, "word": " can", "probability": 0.8994140625 }, { "start": 1251.58, "end": 1251.86, "word": " count", "probability": 0.802734375 }, { "start": 1251.86, "end": 1251.98, "word": " them", "probability": 0.7294921875 }, { "start": 1251.98, "end": 1252.16, "word": " the", "probability": 0.8134765625 }, { "start": 1252.16, "end": 1252.42, "word": " same", "probability": 0.80859375 }, { "start": 1252.42, "end": 1252.86, "word": ".", "probability": 0.994140625 } ] }, { "id": 537, "seek": 125972, "start": 1252.94, "end": 1256.12, "text": " Another really good example is the word thanks,", "tokens": [ 50764, 3996, 534, 665, 1365, 307, 264, 1349, 3231, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.1854910754731723, "compression_ratio": 1.8446969696969697, "no_speech_prob": 0.00010228157043457031, "words": [ { "start": 1252.94, "end": 1253.2, "word": " Another", "probability": 0.83251953125 }, { "start": 1253.2, "end": 1253.42, "word": " really", "probability": 0.76123046875 }, { "start": 1253.42, "end": 1253.58, "word": " good", "probability": 0.86767578125 }, { "start": 1253.58, "end": 1253.96, "word": " example", "probability": 0.92333984375 }, { "start": 1253.96, "end": 1254.5, "word": " is", "probability": 0.87841796875 }, { "start": 1254.5, "end": 1254.66, "word": " the", "probability": 0.8125 }, { "start": 1254.66, "end": 1254.9, "word": " word", "probability": 0.794921875 }, { "start": 1254.9, "end": 1255.52, "word": " thanks", "probability": 0.5234375 }, { "start": 1255.52, "end": 1256.12, "word": ",", "probability": 0.58544921875 } ] }, { "id": 538, "seek": 125972, "start": 1256.12, "end": 1257.24, "text": " thank you,", "tokens": [ 50864, 1309, 291, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.1854910754731723, "compression_ratio": 1.8446969696969697, "no_speech_prob": 0.00010228157043457031, "words": [ { "start": 1256.12, "end": 1256.36, "word": " thank", "probability": 0.755859375 }, { "start": 1256.36, "end": 1256.78, "word": " you", "probability": 0.89013671875 }, { "start": 1256.78, "end": 1257.24, "word": ",", "probability": 0.64794921875 } ] }, { "id": 539, "seek": 125972, "start": 1257.24, "end": 1259.84, "text": " where it's a just singular thank.", "tokens": [ 50964, 689, 309, 311, 257, 445, 20010, 1309, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.1854910754731723, "compression_ratio": 1.8446969696969697, "no_speech_prob": 0.00010228157043457031, "words": [ { "start": 1257.24, "end": 1257.32, "word": " where", "probability": 0.5068359375 }, { "start": 1257.32, "end": 1257.48, "word": " it's", "probability": 0.9482421875 }, { "start": 1257.7, "end": 1257.96, "word": " a just", "probability": 0.8173828125 }, { "start": 1257.96, "end": 1259.02, "word": " singular", "probability": 0.912109375 }, { "start": 1259.02, "end": 1259.42, "word": " thank", "probability": 0.381103515625 }, { "start": 1259.42, "end": 1259.84, "word": ".", "probability": 0.6484375 } ] }, { "id": 540, "seek": 125972, "start": 1259.84, "end": 1261.76, "text": " And I thanked somebody today", "tokens": [ 51064, 400, 286, 48137, 2618, 965, 51114 ], "temperature": 0.0, "avg_logprob": -0.1854910754731723, "compression_ratio": 1.8446969696969697, "no_speech_prob": 0.00010228157043457031, "words": [ { "start": 1259.84, "end": 1260.14, "word": " And", "probability": 0.87548828125 }, { "start": 1260.14, "end": 1260.36, "word": " I", "probability": 0.96435546875 }, { "start": 1260.36, "end": 1260.76, "word": " thanked", "probability": 0.7080078125 }, { "start": 1260.76, "end": 1261.4, "word": " somebody", "probability": 0.78369140625 }, { "start": 1261.4, "end": 1261.76, "word": " today", "probability": 0.7783203125 } ] }, { "id": 541, "seek": 125972, "start": 1261.76, "end": 1263.38, "text": " with an ed at the end.", "tokens": [ 51164, 365, 364, 1257, 412, 264, 917, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.1854910754731723, "compression_ratio": 1.8446969696969697, "no_speech_prob": 0.00010228157043457031, "words": [ { "start": 1261.76, "end": 1261.94, "word": " with", "probability": 0.810546875 }, { "start": 1261.94, "end": 1262.1, "word": " an", "probability": 0.912109375 }, { "start": 1262.1, "end": 1262.3, "word": " ed", "probability": 0.4677734375 }, { "start": 1262.3, "end": 1262.58, "word": " at", "probability": 0.896484375 }, { "start": 1262.58, "end": 1262.72, "word": " the", "probability": 0.8154296875 }, { "start": 1262.72, "end": 1262.94, "word": " end", "probability": 0.82275390625 }, { "start": 1262.94, "end": 1263.38, "word": ".", "probability": 0.921875 } ] }, { "id": 542, "seek": 125972, "start": 1264.04, "end": 1265.94, "text": " As a keyword, they all mean the same thing.", "tokens": [ 51264, 1018, 257, 20428, 11, 436, 439, 914, 264, 912, 551, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.1854910754731723, "compression_ratio": 1.8446969696969697, "no_speech_prob": 0.00010228157043457031, "words": [ { "start": 1264.04, "end": 1264.22, "word": " As", "probability": 0.8916015625 }, { "start": 1264.32, "end": 1264.56, "word": " a keyword", "probability": 0.462158203125 }, { "start": 1264.56, "end": 1264.82, "word": ",", "probability": 0.8427734375 }, { "start": 1264.82, "end": 1264.96, "word": " they", "probability": 0.7392578125 }, { "start": 1264.96, "end": 1265.12, "word": " all", "probability": 0.908203125 }, { "start": 1265.12, "end": 1265.26, "word": " mean", "probability": 0.931640625 }, { "start": 1265.26, "end": 1265.4, "word": " the", "probability": 0.8134765625 }, { "start": 1265.4, "end": 1265.56, "word": " same", "probability": 0.8154296875 }, { "start": 1265.56, "end": 1265.82, "word": " thing", "probability": 0.81201171875 }, { "start": 1265.82, "end": 1265.94, "word": ".", "probability": 0.83837890625 } ] }, { "id": 543, "seek": 125972, "start": 1265.94, "end": 1268.36, "text": " And so stemming will reduce them all down to thank.", "tokens": [ 51364, 400, 370, 12312, 2810, 486, 5407, 552, 439, 760, 281, 1309, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.1854910754731723, "compression_ratio": 1.8446969696969697, "no_speech_prob": 0.00010228157043457031, "words": [ { "start": 1265.94, "end": 1265.96, "word": " And", "probability": 0.88134765625 }, { "start": 1265.96, "end": 1266.08, "word": " so", "probability": 0.8994140625 }, { "start": 1266.08, "end": 1266.46, "word": " stemming", "probability": 0.89794921875 }, { "start": 1266.46, "end": 1266.6, "word": " will", "probability": 0.79296875 }, { "start": 1266.6, "end": 1266.88, "word": " reduce", "probability": 0.7548828125 }, { "start": 1266.88, "end": 1267.04, "word": " them", "probability": 0.73681640625 }, { "start": 1267.04, "end": 1267.16, "word": " all", "probability": 0.890625 }, { "start": 1267.16, "end": 1267.36, "word": " down", "probability": 0.81640625 }, { "start": 1267.36, "end": 1267.54, "word": " to", "probability": 0.90625 }, { "start": 1267.54, "end": 1267.92, "word": " thank", "probability": 0.5224609375 }, { "start": 1267.92, "end": 1268.36, "word": ".", "probability": 0.9541015625 } ] }, { "id": 544, "seek": 125972, "start": 1268.54, "end": 1270.34, "text": " And so instead of three separate words,", "tokens": [ 51514, 400, 370, 2602, 295, 1045, 4994, 2283, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.1854910754731723, "compression_ratio": 1.8446969696969697, "no_speech_prob": 0.00010228157043457031, "words": [ { "start": 1268.54, "end": 1268.72, "word": " And", "probability": 0.8916015625 }, { "start": 1268.72, "end": 1268.96, "word": " so", "probability": 0.90380859375 }, { "start": 1268.96, "end": 1269.2, "word": " instead", "probability": 0.8310546875 }, { "start": 1269.2, "end": 1269.38, "word": " of", "probability": 0.904296875 }, { "start": 1269.38, "end": 1269.64, "word": " three", "probability": 0.8271484375 }, { "start": 1269.64, "end": 1269.96, "word": " separate", "probability": 0.861328125 }, { "start": 1269.96, "end": 1270.28, "word": " words", "probability": 0.7294921875 }, { "start": 1270.28, "end": 1270.34, "word": ",", "probability": 0.8193359375 } ] }, { "id": 545, "seek": 125972, "start": 1270.34, "end": 1271.76, "text": " it's going to be counted as one word.", "tokens": [ 51614, 309, 311, 516, 281, 312, 20150, 382, 472, 1349, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.1854910754731723, "compression_ratio": 1.8446969696969697, "no_speech_prob": 0.00010228157043457031, "words": [ { "start": 1270.34, "end": 1270.44, "word": " it's", "probability": 0.94873046875 }, { "start": 1270.44, "end": 1270.52, "word": " going", "probability": 0.154541015625 }, { "start": 1270.52, "end": 1270.58, "word": " to", "probability": 0.90625 }, { "start": 1270.58, "end": 1270.7, "word": " be", "probability": 0.90380859375 }, { "start": 1270.7, "end": 1270.92, "word": " counted", "probability": 0.7578125 }, { "start": 1270.92, "end": 1271.12, "word": " as", "probability": 0.90869140625 }, { "start": 1271.12, "end": 1271.38, "word": " one", "probability": 0.81591796875 }, { "start": 1271.38, "end": 1271.66, "word": " word", "probability": 0.79833984375 }, { "start": 1271.66, "end": 1271.76, "word": ".", "probability": 0.87548828125 } ] }, { "id": 546, "seek": 125972, "start": 1271.76, "end": 1273.5, "text": " And so that's going to drastically reduce", "tokens": [ 51714, 400, 370, 300, 311, 516, 281, 29673, 5407, 51764 ], "temperature": 0.0, "avg_logprob": -0.1854910754731723, "compression_ratio": 1.8446969696969697, "no_speech_prob": 0.00010228157043457031, "words": [ { "start": 1271.76, "end": 1271.82, "word": " And", "probability": 0.89111328125 }, { "start": 1271.82, "end": 1271.92, "word": " so", "probability": 0.90087890625 }, { "start": 1271.92, "end": 1272.16, "word": " that's", "probability": 0.9384765625 }, { "start": 1272.16, "end": 1272.26, "word": " going", "probability": 0.65478515625 }, { "start": 1272.26, "end": 1272.56, "word": " to", "probability": 0.90478515625 }, { "start": 1272.56, "end": 1272.94, "word": " drastically", "probability": 0.833984375 }, { "start": 1272.94, "end": 1273.5, "word": " reduce", "probability": 0.77734375 } ] }, { "id": 547, "seek": 128810, "start": 1273.5, "end": 1277.2, "text": " our dimension space.", "tokens": [ 50364, 527, 10139, 1901, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.19814711756410852, "compression_ratio": 1.6126126126126126, "no_speech_prob": 0.00026535987854003906, "words": [ { "start": 1273.5, "end": 1273.94, "word": " our", "probability": 0.42626953125 }, { "start": 1273.94, "end": 1276.2, "word": " dimension", "probability": 0.7744140625 }, { "start": 1276.2, "end": 1276.72, "word": " space", "probability": 0.78466796875 }, { "start": 1276.72, "end": 1277.2, "word": ".", "probability": 0.95751953125 } ] }, { "id": 548, "seek": 128810, "start": 1278.3, "end": 1280.56, "text": " So after our preprocessing,", "tokens": [ 50564, 407, 934, 527, 2666, 340, 780, 278, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.19814711756410852, "compression_ratio": 1.6126126126126126, "no_speech_prob": 0.00026535987854003906, "words": [ { "start": 1278.3, "end": 1278.42, "word": " So", "probability": 0.76513671875 }, { "start": 1278.42, "end": 1278.74, "word": " after", "probability": 0.63134765625 }, { "start": 1278.74, "end": 1279.22, "word": " our", "probability": 0.81201171875 }, { "start": 1279.22, "end": 1280.3, "word": " preprocessing", "probability": 0.820068359375 }, { "start": 1280.3, "end": 1280.56, "word": ",", "probability": 0.8310546875 } ] }, { "id": 549, "seek": 128810, "start": 1280.56, "end": 1282.0, "text": " which is what this is known as,", "tokens": [ 50714, 597, 307, 437, 341, 307, 2570, 382, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.19814711756410852, "compression_ratio": 1.6126126126126126, "no_speech_prob": 0.00026535987854003906, "words": [ { "start": 1280.56, "end": 1280.78, "word": " which", "probability": 0.90087890625 }, { "start": 1280.78, "end": 1280.88, "word": " is", "probability": 0.9033203125 }, { "start": 1280.88, "end": 1281.0, "word": " what", "probability": 0.88134765625 }, { "start": 1281.0, "end": 1281.16, "word": " this", "probability": 0.88037109375 }, { "start": 1281.16, "end": 1281.3, "word": " is", "probability": 0.90283203125 }, { "start": 1281.3, "end": 1281.48, "word": " known", "probability": 0.72509765625 }, { "start": 1281.48, "end": 1281.8, "word": " as", "probability": 0.8896484375 }, { "start": 1281.8, "end": 1282.0, "word": ",", "probability": 0.916015625 } ] }, { "id": 550, "seek": 128810, "start": 1282.0, "end": 1284.52, "text": " we're going to see East Asian fonts in Lenny,", "tokens": [ 50814, 321, 434, 516, 281, 536, 6747, 10645, 35316, 294, 23009, 1634, 11, 50864 ], "temperature": 0.0, "avg_logprob": -0.19814711756410852, "compression_ratio": 1.6126126126126126, "no_speech_prob": 0.00026535987854003906, "words": [ { "start": 1282.0, "end": 1282.2, "word": " we're", "probability": 0.911865234375 }, { "start": 1282.2, "end": 1282.38, "word": " going", "probability": 0.85205078125 }, { "start": 1282.38, "end": 1282.5, "word": " to", "probability": 0.9033203125 }, { "start": 1282.5, "end": 1282.66, "word": " see", "probability": 0.80908203125 }, { "start": 1282.66, "end": 1282.94, "word": " East", "probability": 0.54736328125 }, { "start": 1282.94, "end": 1283.16, "word": " Asian", "probability": 0.54931640625 }, { "start": 1283.16, "end": 1283.58, "word": " fonts", "probability": 0.5947265625 }, { "start": 1283.58, "end": 1283.8, "word": " in", "probability": 0.59228515625 }, { "start": 1283.8, "end": 1284.12, "word": " Lenny", "probability": 0.72900390625 }, { "start": 1284.12, "end": 1284.52, "word": ",", "probability": 0.360107421875 } ] }, { "id": 551, "seek": 128810, "start": 1284.52, "end": 1286.08, "text": " or East Asian fonts Lenny,", "tokens": [ 50914, 420, 6747, 10645, 35316, 23009, 1634, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.19814711756410852, "compression_ratio": 1.6126126126126126, "no_speech_prob": 0.00026535987854003906, "words": [ { "start": 1284.52, "end": 1284.62, "word": " or", "probability": 0.5888671875 }, { "start": 1284.62, "end": 1284.86, "word": " East", "probability": 0.69970703125 }, { "start": 1284.86, "end": 1285.08, "word": " Asian", "probability": 0.84814453125 }, { "start": 1285.08, "end": 1285.44, "word": " fonts", "probability": 0.79345703125 }, { "start": 1285.44, "end": 1285.84, "word": " Lenny", "probability": 0.87890625 }, { "start": 1285.84, "end": 1286.08, "word": ",", "probability": 0.53466796875 } ] }, { "id": 552, "seek": 128810, "start": 1286.08, "end": 1289.24, "text": " thanks support installing Unifonts,", "tokens": [ 51014, 3231, 1406, 20762, 1156, 351, 896, 82, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.19814711756410852, "compression_ratio": 1.6126126126126126, "no_speech_prob": 0.00026535987854003906, "words": [ { "start": 1286.08, "end": 1286.36, "word": " thanks", "probability": 0.6611328125 }, { "start": 1286.36, "end": 1288.08, "word": " support", "probability": 0.2205810546875 }, { "start": 1288.08, "end": 1288.68, "word": " installing", "probability": 0.56396484375 }, { "start": 1288.68, "end": 1289.22, "word": " Unifonts", "probability": 0.73394775390625 }, { "start": 1289.22, "end": 1289.24, "word": ",", "probability": 0.5087890625 } ] }, { "id": 553, "seek": 128810, "start": 1289.24, "end": 1290.08, "text": " well me.", "tokens": [ 51164, 731, 385, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.19814711756410852, "compression_ratio": 1.6126126126126126, "no_speech_prob": 0.00026535987854003906, "words": [ { "start": 1289.24, "end": 1289.38, "word": " well", "probability": 0.80126953125 }, { "start": 1289.38, "end": 1289.6, "word": " me", "probability": 0.72900390625 }, { "start": 1289.6, "end": 1290.08, "word": ".", "probability": 0.88330078125 } ] }, { "id": 554, "seek": 128810, "start": 1291.4, "end": 1294.82, "text": " And then what isn't shown here", "tokens": [ 51264, 400, 550, 437, 1943, 380, 4898, 510, 51364 ], "temperature": 0.0, "avg_logprob": -0.19814711756410852, "compression_ratio": 1.6126126126126126, "no_speech_prob": 0.00026535987854003906, "words": [ { "start": 1291.4, "end": 1291.58, "word": " And", "probability": 0.833984375 }, { "start": 1291.58, "end": 1291.9, "word": " then", "probability": 0.73046875 }, { "start": 1291.9, "end": 1294.06, "word": " what", "probability": 0.6845703125 }, { "start": 1294.06, "end": 1294.36, "word": " isn't", "probability": 0.9248046875 }, { "start": 1294.36, "end": 1294.56, "word": " shown", "probability": 0.8798828125 }, { "start": 1294.56, "end": 1294.82, "word": " here", "probability": 0.80908203125 } ] }, { "id": 555, "seek": 128810, "start": 1294.82, "end": 1296.06, "text": " is what the stemming looks like.", "tokens": [ 51414, 307, 437, 264, 12312, 2810, 1542, 411, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.19814711756410852, "compression_ratio": 1.6126126126126126, "no_speech_prob": 0.00026535987854003906, "words": [ { "start": 1294.82, "end": 1294.98, "word": " is", "probability": 0.87841796875 }, { "start": 1294.98, "end": 1295.1, "word": " what", "probability": 0.8857421875 }, { "start": 1295.1, "end": 1295.24, "word": " the", "probability": 0.8017578125 }, { "start": 1295.24, "end": 1295.5, "word": " stemming", "probability": 0.90283203125 }, { "start": 1295.5, "end": 1295.74, "word": " looks", "probability": 0.796875 }, { "start": 1295.74, "end": 1295.98, "word": " like", "probability": 0.87646484375 }, { "start": 1295.98, "end": 1296.06, "word": ".", "probability": 0.935546875 } ] }, { "id": 556, "seek": 128810, "start": 1296.06, "end": 1297.7, "text": " So as we go through the workbook,", "tokens": [ 51514, 407, 382, 321, 352, 807, 264, 589, 2939, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.19814711756410852, "compression_ratio": 1.6126126126126126, "no_speech_prob": 0.00026535987854003906, "words": [ { "start": 1296.06, "end": 1296.14, "word": " So", "probability": 0.86181640625 }, { "start": 1296.14, "end": 1296.4, "word": " as", "probability": 0.88427734375 }, { "start": 1296.4, "end": 1296.54, "word": " we", "probability": 0.904296875 }, { "start": 1296.54, "end": 1296.68, "word": " go", "probability": 0.89794921875 }, { "start": 1296.68, "end": 1296.86, "word": " through", "probability": 0.79833984375 }, { "start": 1296.86, "end": 1297.06, "word": " the", "probability": 0.8154296875 }, { "start": 1297.06, "end": 1297.52, "word": " workbook", "probability": 0.910888671875 }, { "start": 1297.52, "end": 1297.7, "word": ",", "probability": 0.8583984375 } ] }, { "id": 557, "seek": 128810, "start": 1298.34, "end": 1300.04, "text": " we'll take this exact same email", "tokens": [ 51614, 321, 603, 747, 341, 1900, 912, 3796, 51664 ], "temperature": 0.0, "avg_logprob": -0.19814711756410852, "compression_ratio": 1.6126126126126126, "no_speech_prob": 0.00026535987854003906, "words": [ { "start": 1298.34, "end": 1298.82, "word": " we'll", "probability": 0.924560546875 }, { "start": 1298.82, "end": 1298.98, "word": " take", "probability": 0.482666015625 }, { "start": 1298.98, "end": 1299.22, "word": " this", "probability": 0.8740234375 }, { "start": 1299.22, "end": 1299.46, "word": " exact", "probability": 0.86865234375 }, { "start": 1299.46, "end": 1299.78, "word": " same", "probability": 0.81298828125 }, { "start": 1299.78, "end": 1300.04, "word": " email", "probability": 0.89013671875 } ] }, { "id": 558, "seek": 128810, "start": 1300.04, "end": 1301.88, "text": " and see how it's transformed", "tokens": [ 51714, 293, 536, 577, 309, 311, 16894, 51764 ], "temperature": 0.0, "avg_logprob": -0.19814711756410852, "compression_ratio": 1.6126126126126126, "no_speech_prob": 0.00026535987854003906, "words": [ { "start": 1300.04, "end": 1300.36, "word": " and", "probability": 0.86279296875 }, { "start": 1300.36, "end": 1300.72, "word": " see", "probability": 0.81103515625 }, { "start": 1300.72, "end": 1301.06, "word": " how", "probability": 0.90185546875 }, { "start": 1301.06, "end": 1301.3, "word": " it's", "probability": 0.94970703125 }, { "start": 1301.3, "end": 1301.88, "word": " transformed", "probability": 0.80029296875 } ] }, { "id": 559, "seek": 131810, "start": 1301.88, "end": 1305.84, "text": " at every step of our preprocessing.", "tokens": [ 50364, 412, 633, 1823, 295, 527, 2666, 340, 780, 278, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.18749999621156918, "compression_ratio": 1.5276595744680852, "no_speech_prob": 0.0255584716796875, "words": [ { "start": 1301.88, "end": 1302.08, "word": " at", "probability": 0.05389404296875 }, { "start": 1302.08, "end": 1302.4, "word": " every", "probability": 0.732421875 }, { "start": 1302.4, "end": 1302.8, "word": " step", "probability": 0.81982421875 }, { "start": 1302.8, "end": 1303.42, "word": " of", "probability": 0.89453125 }, { "start": 1303.42, "end": 1303.78, "word": " our", "probability": 0.806640625 }, { "start": 1303.78, "end": 1305.32, "word": " preprocessing", "probability": 0.8416748046875 }, { "start": 1305.32, "end": 1305.84, "word": ".", "probability": 0.9208984375 } ] }, { "id": 560, "seek": 131810, "start": 1306.48, "end": 1309.26, "text": " So are there any questions so far?", "tokens": [ 50564, 407, 366, 456, 604, 1651, 370, 1400, 30, 50714 ], "temperature": 0.0, "avg_logprob": -0.18749999621156918, "compression_ratio": 1.5276595744680852, "no_speech_prob": 0.0255584716796875, "words": [ { "start": 1306.48, "end": 1307.0, "word": " So", "probability": 0.47119140625 }, { "start": 1307.0, "end": 1307.46, "word": " are", "probability": 0.515625 }, { "start": 1307.46, "end": 1307.56, "word": " there", "probability": 0.8525390625 }, { "start": 1307.56, "end": 1307.72, "word": " any", "probability": 0.8330078125 }, { "start": 1307.72, "end": 1308.1, "word": " questions", "probability": 0.908203125 }, { "start": 1308.1, "end": 1308.42, "word": " so", "probability": 0.8994140625 }, { "start": 1308.42, "end": 1308.74, "word": " far", "probability": 0.8935546875 }, { "start": 1308.74, "end": 1309.26, "word": "?", "probability": 0.98046875 } ] }, { "id": 561, "seek": 131810, "start": 1315.42, "end": 1316.68, "text": " I don't think so.", "tokens": [ 50764, 286, 500, 380, 519, 370, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.18749999621156918, "compression_ratio": 1.5276595744680852, "no_speech_prob": 0.0255584716796875, "words": [ { "start": 1315.42, "end": 1315.94, "word": " I", "probability": 0.64013671875 }, { "start": 1315.94, "end": 1316.18, "word": " don't", "probability": 0.94287109375 }, { "start": 1316.18, "end": 1316.4, "word": " think", "probability": 0.8056640625 }, { "start": 1316.4, "end": 1316.62, "word": " so", "probability": 0.8955078125 }, { "start": 1316.62, "end": 1316.68, "word": ".", "probability": 0.52001953125 } ] }, { "id": 562, "seek": 131810, "start": 1316.68, "end": 1317.84, "text": " There's none on Twitch chat,", "tokens": [ 50864, 821, 311, 6022, 322, 22222, 5081, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.18749999621156918, "compression_ratio": 1.5276595744680852, "no_speech_prob": 0.0255584716796875, "words": [ { "start": 1316.68, "end": 1316.8, "word": " There's", "probability": 0.8681640625 }, { "start": 1316.8, "end": 1317.02, "word": " none", "probability": 0.76708984375 }, { "start": 1317.02, "end": 1317.2, "word": " on", "probability": 0.86279296875 }, { "start": 1317.2, "end": 1317.46, "word": " Twitch", "probability": 0.52001953125 }, { "start": 1317.46, "end": 1317.74, "word": " chat", "probability": 0.669921875 }, { "start": 1317.74, "end": 1317.84, "word": ",", "probability": 0.2205810546875 } ] }, { "id": 563, "seek": 131810, "start": 1317.84, "end": 1319.24, "text": " and there's none in the Discord.", "tokens": [ 50964, 293, 456, 311, 6022, 294, 264, 32623, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.18749999621156918, "compression_ratio": 1.5276595744680852, "no_speech_prob": 0.0255584716796875, "words": [ { "start": 1317.84, "end": 1317.92, "word": " and", "probability": 0.4892578125 }, { "start": 1317.92, "end": 1318.1, "word": " there's", "probability": 0.8359375 }, { "start": 1318.1, "end": 1318.26, "word": " none", "probability": 0.86474609375 }, { "start": 1318.26, "end": 1318.48, "word": " in", "probability": 0.6162109375 }, { "start": 1318.48, "end": 1318.52, "word": " the", "probability": 0.7763671875 }, { "start": 1318.52, "end": 1318.78, "word": " Discord", "probability": 0.66162109375 }, { "start": 1318.78, "end": 1319.24, "word": ".", "probability": 0.9716796875 } ] }, { "id": 564, "seek": 131810, "start": 1319.28, "end": 1320.32, "text": " Perfect.", "tokens": [ 51064, 10246, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.18749999621156918, "compression_ratio": 1.5276595744680852, "no_speech_prob": 0.0255584716796875, "words": [ { "start": 1319.28, "end": 1319.8, "word": " Perfect", "probability": 0.7900390625 }, { "start": 1319.8, "end": 1320.32, "word": ".", "probability": 0.8779296875 } ] }, { "id": 565, "seek": 131810, "start": 1322.32, "end": 1323.94, "text": " So what we're going to have", "tokens": [ 51164, 407, 437, 321, 434, 516, 281, 362, 51214 ], "temperature": 0.0, "avg_logprob": -0.18749999621156918, "compression_ratio": 1.5276595744680852, "no_speech_prob": 0.0255584716796875, "words": [ { "start": 1322.32, "end": 1322.84, "word": " So", "probability": 0.8203125 }, { "start": 1322.84, "end": 1323.36, "word": " what", "probability": 0.75390625 }, { "start": 1323.36, "end": 1323.46, "word": " we're", "probability": 0.92626953125 }, { "start": 1323.46, "end": 1323.54, "word": " going", "probability": 0.505859375 }, { "start": 1323.54, "end": 1323.6, "word": " to", "probability": 0.9033203125 }, { "start": 1323.6, "end": 1323.94, "word": " have", "probability": 0.87255859375 } ] }, { "id": 566, "seek": 131810, "start": 1323.94, "end": 1325.86, "text": " are a series of workbooks.", "tokens": [ 51264, 366, 257, 2638, 295, 589, 15170, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.18749999621156918, "compression_ratio": 1.5276595744680852, "no_speech_prob": 0.0255584716796875, "words": [ { "start": 1323.94, "end": 1324.44, "word": " are", "probability": 0.78662109375 }, { "start": 1324.96, "end": 1325.26, "word": " a series", "probability": 0.8037109375 }, { "start": 1325.26, "end": 1325.4, "word": " of", "probability": 0.90380859375 }, { "start": 1325.4, "end": 1325.72, "word": " workbooks", "probability": 0.8671875 }, { "start": 1325.72, "end": 1325.86, "word": ".", "probability": 0.8984375 } ] }, { "id": 567, "seek": 131810, "start": 1325.86, "end": 1327.82, "text": " We're going to use MyBender.", "tokens": [ 51364, 492, 434, 516, 281, 764, 1222, 33, 3216, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.18749999621156918, "compression_ratio": 1.5276595744680852, "no_speech_prob": 0.0255584716796875, "words": [ { "start": 1325.86, "end": 1325.9, "word": " We're", "probability": 0.927734375 }, { "start": 1325.9, "end": 1326.06, "word": " going", "probability": 0.8583984375 }, { "start": 1326.06, "end": 1326.26, "word": " to", "probability": 0.9091796875 }, { "start": 1326.26, "end": 1326.74, "word": " use", "probability": 0.830078125 }, { "start": 1326.74, "end": 1327.74, "word": " MyBender", "probability": 0.6513671875 }, { "start": 1327.74, "end": 1327.82, "word": ".", "probability": 0.822265625 } ] }, { "id": 568, "seek": 131810, "start": 1327.82, "end": 1329.74, "text": " MyBender is really awesome.", "tokens": [ 51464, 1222, 33, 3216, 307, 534, 3476, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.18749999621156918, "compression_ratio": 1.5276595744680852, "no_speech_prob": 0.0255584716796875, "words": [ { "start": 1327.82, "end": 1328.2, "word": " MyBender", "probability": 0.9609375 }, { "start": 1328.2, "end": 1328.4, "word": " is", "probability": 0.8876953125 }, { "start": 1328.4, "end": 1328.7, "word": " really", "probability": 0.77783203125 }, { "start": 1328.7, "end": 1329.22, "word": " awesome", "probability": 0.8662109375 }, { "start": 1329.22, "end": 1329.74, "word": ".", "probability": 0.78955078125 } ] }, { "id": 569, "seek": 131810, "start": 1330.7, "end": 1333.62, "text": " TAs, if you don't mind sharing this link.", "tokens": [ 51564, 314, 10884, 11, 498, 291, 500, 380, 1575, 5414, 341, 2113, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.18749999621156918, "compression_ratio": 1.5276595744680852, "no_speech_prob": 0.0255584716796875, "words": [ { "start": 1330.7, "end": 1331.22, "word": " TAs", "probability": 0.78759765625 }, { "start": 1331.22, "end": 1331.26, "word": ",", "probability": 0.787109375 }, { "start": 1331.26, "end": 1331.34, "word": " if", "probability": 0.904296875 }, { "start": 1331.34, "end": 1331.4, "word": " you", "probability": 0.9013671875 }, { "start": 1331.4, "end": 1331.56, "word": " don't", "probability": 0.947509765625 }, { "start": 1331.56, "end": 1331.84, "word": " mind", "probability": 0.79052734375 }, { "start": 1331.84, "end": 1332.48, "word": " sharing", "probability": 0.86376953125 }, { "start": 1332.48, "end": 1332.76, "word": " this", "probability": 0.87744140625 }, { "start": 1332.76, "end": 1333.1, "word": " link", "probability": 0.884765625 }, { "start": 1333.1, "end": 1333.62, "word": ".", "probability": 0.61669921875 } ] }, { "id": 570, "seek": 131810, "start": 1333.88, "end": 1336.04, "text": " What it will do is spin up a Docker container", "tokens": [ 51714, 708, 309, 486, 360, 307, 6060, 493, 257, 33772, 10129, 51814 ], "temperature": 0.0, "avg_logprob": -0.18749999621156918, "compression_ratio": 1.5276595744680852, "no_speech_prob": 0.0255584716796875, "words": [ { "start": 1333.88, "end": 1334.4, "word": " What", "probability": 0.79736328125 }, { "start": 1334.4, "end": 1334.48, "word": " it", "probability": 0.8994140625 }, { "start": 1334.48, "end": 1334.58, "word": " will", "probability": 0.8193359375 }, { "start": 1334.58, "end": 1334.76, "word": " do", "probability": 0.90966796875 }, { "start": 1334.76, "end": 1334.96, "word": " is", "probability": 0.89501953125 }, { "start": 1334.96, "end": 1335.14, "word": " spin", "probability": 0.8603515625 }, { "start": 1335.14, "end": 1335.24, "word": " up", "probability": 0.904296875 }, { "start": 1335.36, "end": 1335.54, "word": " a Docker", "probability": 0.5205078125 }, { "start": 1335.54, "end": 1336.04, "word": " container", "probability": 0.77392578125 } ] }, { "id": 571, "seek": 134482, "start": 1336.8, "end": 1338.86, "text": " with the workbook linked to my GitHub", "tokens": [ 50364, 365, 264, 589, 2939, 9408, 281, 452, 23331, 50464 ], "temperature": 0.0, "avg_logprob": -0.1987345011766292, "compression_ratio": 1.7119341563786008, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 1336.8, "end": 1337.02, "word": " with", "probability": 0.003963470458984375 }, { "start": 1337.02, "end": 1337.02, "word": " the", "probability": 0.319580078125 }, { "start": 1337.02, "end": 1337.6, "word": " workbook", "probability": 0.718994140625 }, { "start": 1337.6, "end": 1338.32, "word": " linked", "probability": 0.45654296875 }, { "start": 1338.32, "end": 1338.44, "word": " to", "probability": 0.8857421875 }, { "start": 1338.44, "end": 1338.58, "word": " my", "probability": 0.85595703125 }, { "start": 1338.58, "end": 1338.86, "word": " GitHub", "probability": 0.475341796875 } ] }, { "id": 572, "seek": 134482, "start": 1338.86, "end": 1342.42, "text": " so that you can kind of code with me", "tokens": [ 50514, 370, 300, 291, 393, 733, 295, 3089, 365, 385, 50614 ], "temperature": 0.0, "avg_logprob": -0.1987345011766292, "compression_ratio": 1.7119341563786008, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 1338.86, "end": 1339.36, "word": " so", "probability": 0.69921875 }, { "start": 1339.36, "end": 1339.78, "word": " that", "probability": 0.7041015625 }, { "start": 1339.78, "end": 1339.94, "word": " you", "probability": 0.89501953125 }, { "start": 1339.94, "end": 1340.36, "word": " can", "probability": 0.90283203125 }, { "start": 1340.36, "end": 1340.98, "word": " kind", "probability": 0.321533203125 }, { "start": 1340.98, "end": 1341.12, "word": " of", "probability": 0.90283203125 }, { "start": 1341.12, "end": 1341.84, "word": " code", "probability": 0.802734375 }, { "start": 1341.84, "end": 1342.14, "word": " with", "probability": 0.8212890625 }, { "start": 1342.14, "end": 1342.42, "word": " me", "probability": 0.90625 } ] }, { "id": 573, "seek": 134482, "start": 1342.42, "end": 1343.4, "text": " as we walk through", "tokens": [ 50664, 382, 321, 1792, 807, 50714 ], "temperature": 0.0, "avg_logprob": -0.1987345011766292, "compression_ratio": 1.7119341563786008, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 1342.42, "end": 1342.68, "word": " as", "probability": 0.88134765625 }, { "start": 1342.68, "end": 1342.82, "word": " we", "probability": 0.90234375 }, { "start": 1342.82, "end": 1343.08, "word": " walk", "probability": 0.8291015625 }, { "start": 1343.08, "end": 1343.4, "word": " through", "probability": 0.76953125 } ] }, { "id": 574, "seek": 134482, "start": 1343.4, "end": 1346.74, "text": " and build our own machine learning classifiers.", "tokens": [ 50764, 293, 1322, 527, 1065, 3479, 2539, 1508, 23463, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.1987345011766292, "compression_ratio": 1.7119341563786008, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 1343.4, "end": 1344.26, "word": " and", "probability": 0.8828125 }, { "start": 1344.26, "end": 1344.56, "word": " build", "probability": 0.88623046875 }, { "start": 1344.56, "end": 1344.72, "word": " our", "probability": 0.8046875 }, { "start": 1344.72, "end": 1345.0, "word": " own", "probability": 0.8173828125 }, { "start": 1345.0, "end": 1345.3, "word": " machine", "probability": 0.6640625 }, { "start": 1345.3, "end": 1345.58, "word": " learning", "probability": 0.7666015625 }, { "start": 1345.58, "end": 1346.22, "word": " classifiers", "probability": 0.92822265625 }, { "start": 1346.22, "end": 1346.74, "word": ".", "probability": 0.953125 } ] }, { "id": 575, "seek": 134482, "start": 1347.98, "end": 1349.26, "text": " While this is starting up,", "tokens": [ 50914, 3987, 341, 307, 2891, 493, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.1987345011766292, "compression_ratio": 1.7119341563786008, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 1347.98, "end": 1348.5, "word": " While", "probability": 0.79296875 }, { "start": 1348.5, "end": 1348.64, "word": " this", "probability": 0.8759765625 }, { "start": 1348.64, "end": 1348.74, "word": " is", "probability": 0.8984375 }, { "start": 1348.74, "end": 1348.96, "word": " starting", "probability": 0.83544921875 }, { "start": 1348.96, "end": 1349.2, "word": " up", "probability": 0.8447265625 }, { "start": 1349.2, "end": 1349.26, "word": ",", "probability": 0.7744140625 } ] }, { "id": 576, "seek": 134482, "start": 1349.26, "end": 1350.46, "text": " what we're going to be using is", "tokens": [ 51014, 437, 321, 434, 516, 281, 312, 1228, 307, 51064 ], "temperature": 0.0, "avg_logprob": -0.1987345011766292, "compression_ratio": 1.7119341563786008, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 1349.26, "end": 1349.3, "word": " what", "probability": 0.84033203125 }, { "start": 1349.3, "end": 1349.44, "word": " we're", "probability": 0.90869140625 }, { "start": 1349.44, "end": 1349.52, "word": " going", "probability": 0.6064453125 }, { "start": 1349.52, "end": 1349.54, "word": " to", "probability": 0.90478515625 }, { "start": 1349.54, "end": 1349.66, "word": " be", "probability": 0.8994140625 }, { "start": 1349.66, "end": 1349.94, "word": " using", "probability": 0.8349609375 }, { "start": 1349.94, "end": 1350.46, "word": " is", "probability": 0.85693359375 } ] }, { "id": 577, "seek": 134482, "start": 1350.46, "end": 1352.52, "text": " instead of coding everything raw", "tokens": [ 51114, 2602, 295, 17720, 1203, 8936, 51164 ], "temperature": 0.0, "avg_logprob": -0.1987345011766292, "compression_ratio": 1.7119341563786008, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 1350.46, "end": 1350.82, "word": " instead", "probability": 0.50146484375 }, { "start": 1350.82, "end": 1351.22, "word": " of", "probability": 0.90283203125 }, { "start": 1351.22, "end": 1351.72, "word": " coding", "probability": 0.83349609375 }, { "start": 1351.72, "end": 1352.18, "word": " everything", "probability": 0.87744140625 }, { "start": 1352.18, "end": 1352.52, "word": " raw", "probability": 0.72314453125 } ] }, { "id": 578, "seek": 134482, "start": 1352.52, "end": 1353.92, "text": " and doing the raw numbers like we did", "tokens": [ 51214, 293, 884, 264, 8936, 3547, 411, 321, 630, 51264 ], "temperature": 0.0, "avg_logprob": -0.1987345011766292, "compression_ratio": 1.7119341563786008, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 1352.52, "end": 1352.68, "word": " and", "probability": 0.8505859375 }, { "start": 1352.68, "end": 1352.82, "word": " doing", "probability": 0.90576171875 }, { "start": 1352.82, "end": 1352.96, "word": " the", "probability": 0.80517578125 }, { "start": 1352.96, "end": 1353.14, "word": " raw", "probability": 0.8232421875 }, { "start": 1353.14, "end": 1353.48, "word": " numbers", "probability": 0.865234375 }, { "start": 1353.48, "end": 1353.64, "word": " like", "probability": 0.8359375 }, { "start": 1353.64, "end": 1353.76, "word": " we", "probability": 0.89990234375 }, { "start": 1353.76, "end": 1353.92, "word": " did", "probability": 0.8955078125 } ] }, { "id": 579, "seek": 134482, "start": 1353.92, "end": 1356.82, "text": " on our pen and paper,", "tokens": [ 51314, 322, 527, 3435, 293, 3035, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.1987345011766292, "compression_ratio": 1.7119341563786008, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 1353.92, "end": 1354.04, "word": " on", "probability": 0.8828125 }, { "start": 1354.04, "end": 1354.44, "word": " our", "probability": 0.8037109375 }, { "start": 1354.44, "end": 1355.7, "word": " pen", "probability": 0.89111328125 }, { "start": 1355.7, "end": 1355.84, "word": " and", "probability": 0.87646484375 }, { "start": 1355.84, "end": 1356.12, "word": " paper", "probability": 0.80126953125 }, { "start": 1356.12, "end": 1356.82, "word": ",", "probability": 0.884765625 } ] }, { "id": 580, "seek": 134482, "start": 1356.82, "end": 1357.92, "text": " we're going to be using", "tokens": [ 51414, 321, 434, 516, 281, 312, 1228, 51464 ], "temperature": 0.0, "avg_logprob": -0.1987345011766292, "compression_ratio": 1.7119341563786008, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 1356.82, "end": 1357.44, "word": " we're", "probability": 0.91845703125 }, { "start": 1357.44, "end": 1357.52, "word": " going", "probability": 0.83447265625 }, { "start": 1357.52, "end": 1357.58, "word": " to", "probability": 0.90576171875 }, { "start": 1357.58, "end": 1357.7, "word": " be", "probability": 0.900390625 }, { "start": 1357.7, "end": 1357.92, "word": " using", "probability": 0.82470703125 } ] }, { "id": 581, "seek": 134482, "start": 1357.92, "end": 1359.6, "text": " the abstraction library Scikit-learn.", "tokens": [ 51514, 264, 37765, 6405, 16942, 22681, 12, 306, 1083, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.1987345011766292, "compression_ratio": 1.7119341563786008, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 1357.92, "end": 1358.08, "word": " the", "probability": 0.810546875 }, { "start": 1358.08, "end": 1358.44, "word": " abstraction", "probability": 0.6025390625 }, { "start": 1358.44, "end": 1358.88, "word": " library", "probability": 0.83447265625 }, { "start": 1358.88, "end": 1359.28, "word": " Scikit", "probability": 0.637451171875 }, { "start": 1359.28, "end": 1359.48, "word": "-learn", "probability": 0.8525390625 }, { "start": 1359.48, "end": 1359.6, "word": ".", "probability": 0.94677734375 } ] }, { "id": 582, "seek": 134482, "start": 1359.6, "end": 1360.86, "text": " Scikit-learn is very useful", "tokens": [ 51614, 16942, 22681, 12, 306, 1083, 307, 588, 4420, 51664 ], "temperature": 0.0, "avg_logprob": -0.1987345011766292, "compression_ratio": 1.7119341563786008, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 1359.6, "end": 1359.82, "word": " Scikit", "probability": 0.89453125 }, { "start": 1359.82, "end": 1359.96, "word": "-learn", "probability": 0.96826171875 }, { "start": 1359.96, "end": 1360.16, "word": " is", "probability": 0.90625 }, { "start": 1360.16, "end": 1360.42, "word": " very", "probability": 0.73388671875 }, { "start": 1360.42, "end": 1360.86, "word": " useful", "probability": 0.78759765625 } ] }, { "id": 583, "seek": 134482, "start": 1360.86, "end": 1363.52, "text": " and it allows us to treat things", "tokens": [ 51714, 293, 309, 4045, 505, 281, 2387, 721, 51764 ], "temperature": 0.0, "avg_logprob": -0.1987345011766292, "compression_ratio": 1.7119341563786008, "no_speech_prob": 0.0006260871887207031, "words": [ { "start": 1360.86, "end": 1361.64, "word": " and", "probability": 0.69873046875 }, { "start": 1361.64, "end": 1362.12, "word": " it", "probability": 0.8720703125 }, { "start": 1362.12, "end": 1362.5, "word": " allows", "probability": 0.79296875 }, { "start": 1362.5, "end": 1362.72, "word": " us", "probability": 0.900390625 }, { "start": 1362.72, "end": 1362.88, "word": " to", "probability": 0.90087890625 }, { "start": 1362.88, "end": 1363.14, "word": " treat", "probability": 0.791015625 }, { "start": 1363.14, "end": 1363.52, "word": " things", "probability": 0.73291015625 } ] }, { "id": 584, "seek": 137482, "start": 1363.52, "end": 1364.68, "text": " kind of like Legos,", "tokens": [ 50364, 733, 295, 411, 7470, 329, 11, 50414 ], "temperature": 0.0, "avg_logprob": -0.17853682170542637, "compression_ratio": 1.5731707317073171, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1363.52, "end": 1363.7, "word": " kind", "probability": 0.035125732421875 }, { "start": 1363.7, "end": 1363.82, "word": " of", "probability": 0.89892578125 }, { "start": 1363.82, "end": 1363.98, "word": " like", "probability": 0.88623046875 }, { "start": 1363.98, "end": 1364.44, "word": " Legos", "probability": 0.678466796875 }, { "start": 1364.44, "end": 1364.68, "word": ",", "probability": 0.279052734375 } ] }, { "id": 585, "seek": 137482, "start": 1364.68, "end": 1366.8, "text": " where, OK, maybe I don't want", "tokens": [ 50464, 689, 11, 2264, 11, 1310, 286, 500, 380, 528, 50514 ], "temperature": 0.0, "avg_logprob": -0.17853682170542637, "compression_ratio": 1.5731707317073171, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1364.68, "end": 1364.88, "word": " where", "probability": 0.828125 }, { "start": 1364.88, "end": 1365.38, "word": ",", "probability": 0.3291015625 }, { "start": 1365.38, "end": 1365.66, "word": " OK", "probability": 0.1678466796875 }, { "start": 1365.66, "end": 1365.82, "word": ",", "probability": 0.90869140625 }, { "start": 1365.82, "end": 1366.06, "word": " maybe", "probability": 0.8564453125 }, { "start": 1366.06, "end": 1366.24, "word": " I", "probability": 0.99462890625 }, { "start": 1366.24, "end": 1366.54, "word": " don't", "probability": 0.947265625 }, { "start": 1366.54, "end": 1366.8, "word": " want", "probability": 0.7841796875 } ] }, { "id": 586, "seek": 137482, "start": 1366.8, "end": 1368.14, "text": " multinomial Naive Bayesian,", "tokens": [ 50564, 45872, 47429, 6056, 488, 7840, 42434, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.17853682170542637, "compression_ratio": 1.5731707317073171, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1366.8, "end": 1367.36, "word": " multinomial", "probability": 0.843017578125 }, { "start": 1367.36, "end": 1367.74, "word": " Naive", "probability": 0.4490966796875 }, { "start": 1367.74, "end": 1368.04, "word": " Bayesian", "probability": 0.92822265625 }, { "start": 1368.04, "end": 1368.14, "word": ",", "probability": 0.64013671875 } ] }, { "id": 587, "seek": 137482, "start": 1368.14, "end": 1369.3, "text": " maybe I want logistic regression", "tokens": [ 50664, 1310, 286, 528, 3565, 3142, 24590, 50714 ], "temperature": 0.0, "avg_logprob": -0.17853682170542637, "compression_ratio": 1.5731707317073171, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1368.14, "end": 1368.28, "word": " maybe", "probability": 0.8408203125 }, { "start": 1368.28, "end": 1368.4, "word": " I", "probability": 0.98974609375 }, { "start": 1368.4, "end": 1368.54, "word": " want", "probability": 0.8056640625 }, { "start": 1368.54, "end": 1368.9, "word": " logistic", "probability": 0.91162109375 }, { "start": 1368.9, "end": 1369.3, "word": " regression", "probability": 0.89111328125 } ] }, { "id": 588, "seek": 137482, "start": 1369.3, "end": 1370.7, "text": " or random forest.", "tokens": [ 50764, 420, 4974, 6719, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.17853682170542637, "compression_ratio": 1.5731707317073171, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1369.3, "end": 1369.6, "word": " or", "probability": 0.716796875 }, { "start": 1369.6, "end": 1369.9, "word": " random", "probability": 0.5908203125 }, { "start": 1369.9, "end": 1370.46, "word": " forest", "probability": 0.72021484375 }, { "start": 1370.46, "end": 1370.7, "word": ".", "probability": 0.72509765625 } ] }, { "id": 589, "seek": 137482, "start": 1370.7, "end": 1372.68, "text": " We can just swap that out.", "tokens": [ 50864, 492, 393, 445, 18135, 300, 484, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.17853682170542637, "compression_ratio": 1.5731707317073171, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1370.7, "end": 1370.94, "word": " We", "probability": 0.90185546875 }, { "start": 1370.94, "end": 1371.04, "word": " can", "probability": 0.89208984375 }, { "start": 1371.04, "end": 1371.24, "word": " just", "probability": 0.88037109375 }, { "start": 1371.24, "end": 1371.64, "word": " swap", "probability": 0.93115234375 }, { "start": 1371.64, "end": 1371.9, "word": " that", "probability": 0.880859375 }, { "start": 1371.9, "end": 1372.2, "word": " out", "probability": 0.81982421875 }, { "start": 1372.2, "end": 1372.68, "word": ".", "probability": 0.9794921875 } ] }, { "id": 590, "seek": 137482, "start": 1374.78, "end": 1376.38, "text": " So once it's loaded,", "tokens": [ 50964, 407, 1564, 309, 311, 13210, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.17853682170542637, "compression_ratio": 1.5731707317073171, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1374.78, "end": 1375.26, "word": " So", "probability": 0.80517578125 }, { "start": 1375.26, "end": 1375.74, "word": " once", "probability": 0.6875 }, { "start": 1375.74, "end": 1375.94, "word": " it's", "probability": 0.948486328125 }, { "start": 1375.94, "end": 1376.16, "word": " loaded", "probability": 0.81103515625 }, { "start": 1376.16, "end": 1376.38, "word": ",", "probability": 0.53173828125 } ] }, { "id": 591, "seek": 137482, "start": 1376.38, "end": 1378.78, "text": " and I'm going to give you a moment", "tokens": [ 51064, 293, 286, 478, 516, 281, 976, 291, 257, 1623, 51114 ], "temperature": 0.0, "avg_logprob": -0.17853682170542637, "compression_ratio": 1.5731707317073171, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1376.38, "end": 1376.52, "word": " and", "probability": 0.82763671875 }, { "start": 1376.52, "end": 1376.7, "word": " I'm", "probability": 0.996826171875 }, { "start": 1376.7, "end": 1376.82, "word": " going", "probability": 0.77197265625 }, { "start": 1376.82, "end": 1377.5, "word": " to", "probability": 0.90234375 }, { "start": 1377.5, "end": 1378.34, "word": " give", "probability": 0.8125 }, { "start": 1378.34, "end": 1378.44, "word": " you", "probability": 0.8935546875 }, { "start": 1378.56, "end": 1378.78, "word": " a moment", "probability": 0.90869140625 } ] }, { "id": 592, "seek": 137482, "start": 1378.78, "end": 1380.78, "text": " to get this loaded up.", "tokens": [ 51164, 281, 483, 341, 13210, 493, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.17853682170542637, "compression_ratio": 1.5731707317073171, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1378.78, "end": 1379.12, "word": " to", "probability": 0.90380859375 }, { "start": 1379.12, "end": 1379.52, "word": " get", "probability": 0.82275390625 }, { "start": 1379.52, "end": 1379.74, "word": " this", "probability": 0.87890625 }, { "start": 1379.74, "end": 1380.0, "word": " loaded", "probability": 0.8115234375 }, { "start": 1380.0, "end": 1380.3, "word": " up", "probability": 0.89697265625 }, { "start": 1380.3, "end": 1380.78, "word": ".", "probability": 0.603515625 } ] }, { "id": 593, "seek": 137482, "start": 1381.38, "end": 1383.12, "text": " If it takes a little bit longer", "tokens": [ 51264, 759, 309, 2516, 257, 707, 857, 2854, 51314 ], "temperature": 0.0, "avg_logprob": -0.17853682170542637, "compression_ratio": 1.5731707317073171, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1381.38, "end": 1381.86, "word": " If", "probability": 0.890625 }, { "start": 1381.86, "end": 1382.12, "word": " it", "probability": 0.90576171875 }, { "start": 1382.12, "end": 1382.4, "word": " takes", "probability": 0.73779296875 }, { "start": 1382.52, "end": 1382.6, "word": " a little", "probability": 0.806640625 }, { "start": 1382.6, "end": 1382.78, "word": " bit", "probability": 0.88671875 }, { "start": 1382.78, "end": 1383.12, "word": " longer", "probability": 0.84912109375 } ] }, { "id": 594, "seek": 137482, "start": 1383.12, "end": 1385.28, "text": " than it should,", "tokens": [ 51364, 813, 309, 820, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.17853682170542637, "compression_ratio": 1.5731707317073171, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1383.12, "end": 1384.0, "word": " than", "probability": 0.8466796875 }, { "start": 1384.0, "end": 1384.24, "word": " it", "probability": 0.904296875 }, { "start": 1384.24, "end": 1384.64, "word": " should", "probability": 0.9189453125 }, { "start": 1384.64, "end": 1385.28, "word": ",", "probability": 0.916015625 } ] }, { "id": 595, "seek": 137482, "start": 1385.28, "end": 1387.1, "text": " then you'll easily be able", "tokens": [ 51464, 550, 291, 603, 3612, 312, 1075, 51514 ], "temperature": 0.0, "avg_logprob": -0.17853682170542637, "compression_ratio": 1.5731707317073171, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1385.28, "end": 1386.02, "word": " then", "probability": 0.71923828125 }, { "start": 1386.02, "end": 1386.44, "word": " you'll", "probability": 0.8447265625 }, { "start": 1386.44, "end": 1386.76, "word": " easily", "probability": 0.8466796875 }, { "start": 1386.76, "end": 1386.94, "word": " be", "probability": 0.90576171875 }, { "start": 1386.94, "end": 1387.1, "word": " able", "probability": 0.88330078125 } ] }, { "id": 596, "seek": 137482, "start": 1387.1, "end": 1387.98, "text": " to catch up to me", "tokens": [ 51564, 281, 3745, 493, 281, 385, 51614 ], "temperature": 0.0, "avg_logprob": -0.17853682170542637, "compression_ratio": 1.5731707317073171, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1387.1, "end": 1387.26, "word": " to", "probability": 0.90966796875 }, { "start": 1387.26, "end": 1387.5, "word": " catch", "probability": 0.81982421875 }, { "start": 1387.5, "end": 1387.64, "word": " up", "probability": 0.90625 }, { "start": 1387.64, "end": 1387.76, "word": " to", "probability": 0.89697265625 }, { "start": 1387.76, "end": 1387.98, "word": " me", "probability": 0.904296875 } ] }, { "id": 597, "seek": 137482, "start": 1387.98, "end": 1389.6, "text": " and I'll show you how.", "tokens": [ 51664, 293, 286, 603, 855, 291, 577, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.17853682170542637, "compression_ratio": 1.5731707317073171, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1387.98, "end": 1388.46, "word": " and", "probability": 0.38037109375 }, { "start": 1388.46, "end": 1388.56, "word": " I'll", "probability": 0.975830078125 }, { "start": 1388.56, "end": 1388.72, "word": " show", "probability": 0.87646484375 }, { "start": 1388.72, "end": 1388.86, "word": " you", "probability": 0.896484375 }, { "start": 1388.86, "end": 1389.12, "word": " how", "probability": 0.89697265625 }, { "start": 1389.12, "end": 1389.6, "word": ".", "probability": 0.9921875 } ] }, { "id": 598, "seek": 137482, "start": 1390.16, "end": 1391.76, "text": " So we're going to click on workbooks", "tokens": [ 51764, 407, 321, 434, 516, 281, 2052, 322, 589, 15170, 51814 ], "temperature": 0.0, "avg_logprob": -0.17853682170542637, "compression_ratio": 1.5731707317073171, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1390.16, "end": 1390.64, "word": " So", "probability": 0.875 }, { "start": 1390.64, "end": 1390.9, "word": " we're", "probability": 0.900390625 }, { "start": 1390.9, "end": 1390.94, "word": " going", "probability": 0.83056640625 }, { "start": 1390.94, "end": 1391.0, "word": " to", "probability": 0.89697265625 }, { "start": 1391.0, "end": 1391.14, "word": " click", "probability": 0.806640625 }, { "start": 1391.14, "end": 1391.3, "word": " on", "probability": 0.91162109375 }, { "start": 1391.3, "end": 1391.76, "word": " workbooks", "probability": 0.713134765625 } ] }, { "id": 599, "seek": 140482, "start": 1393.54, "end": 1395.86, "text": " spam filter sklearn.", "tokens": [ 50364, 24028, 6608, 1110, 306, 1083, 13, 50414 ], "temperature": 0.0, "avg_logprob": -0.1872577519379845, "compression_ratio": 1.7248062015503876, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 1393.54, "end": 1394.06, "word": " spam", "probability": 0.10015869140625 }, { "start": 1394.06, "end": 1394.52, "word": " filter", "probability": 0.8681640625 }, { "start": 1394.52, "end": 1395.34, "word": " sklearn", "probability": 0.7613932291666666 }, { "start": 1395.34, "end": 1395.86, "word": ".", "probability": 0.81787109375 } ] }, { "id": 600, "seek": 140482, "start": 1395.86, "end": 1397.84, "text": " If you're not very familiar", "tokens": [ 50464, 759, 291, 434, 406, 588, 4963, 50514 ], "temperature": 0.0, "avg_logprob": -0.1872577519379845, "compression_ratio": 1.7248062015503876, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 1395.86, "end": 1396.36, "word": " If", "probability": 0.8818359375 }, { "start": 1396.36, "end": 1396.8, "word": " you're", "probability": 0.909912109375 }, { "start": 1396.8, "end": 1397.22, "word": " not", "probability": 0.89892578125 }, { "start": 1397.22, "end": 1397.54, "word": " very", "probability": 0.72265625 }, { "start": 1397.54, "end": 1397.84, "word": " familiar", "probability": 0.78466796875 } ] }, { "id": 601, "seek": 140482, "start": 1397.84, "end": 1399.94, "text": " with Python, you can still follow along.", "tokens": [ 50564, 365, 15329, 11, 291, 393, 920, 1524, 2051, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.1872577519379845, "compression_ratio": 1.7248062015503876, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 1397.84, "end": 1398.04, "word": " with", "probability": 0.8193359375 }, { "start": 1398.04, "end": 1398.4, "word": " Python", "probability": 0.85205078125 }, { "start": 1398.4, "end": 1398.56, "word": ",", "probability": 0.728515625 }, { "start": 1398.56, "end": 1398.64, "word": " you", "probability": 0.89404296875 }, { "start": 1398.64, "end": 1398.78, "word": " can", "probability": 0.8974609375 }, { "start": 1398.78, "end": 1399.04, "word": " still", "probability": 0.89013671875 }, { "start": 1399.04, "end": 1399.32, "word": " follow", "probability": 0.87646484375 }, { "start": 1399.32, "end": 1399.76, "word": " along", "probability": 0.89306640625 }, { "start": 1399.76, "end": 1399.94, "word": ".", "probability": 0.87939453125 } ] }, { "id": 602, "seek": 140482, "start": 1399.94, "end": 1401.52, "text": " We have a completed workbook,", "tokens": [ 50664, 492, 362, 257, 7365, 589, 2939, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.1872577519379845, "compression_ratio": 1.7248062015503876, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 1399.94, "end": 1400.02, "word": " We", "probability": 0.904296875 }, { "start": 1400.02, "end": 1400.28, "word": " have", "probability": 0.87939453125 }, { "start": 1400.54, "end": 1400.92, "word": " a completed", "probability": 0.623046875 }, { "start": 1400.92, "end": 1401.44, "word": " workbook", "probability": 0.8837890625 }, { "start": 1401.44, "end": 1401.52, "word": ",", "probability": 0.72900390625 } ] }, { "id": 603, "seek": 140482, "start": 1401.52, "end": 1402.66, "text": " which is the workbook complete", "tokens": [ 50764, 597, 307, 264, 589, 2939, 3566, 50814 ], "temperature": 0.0, "avg_logprob": -0.1872577519379845, "compression_ratio": 1.7248062015503876, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 1401.52, "end": 1401.62, "word": " which", "probability": 0.92041015625 }, { "start": 1401.62, "end": 1401.72, "word": " is", "probability": 0.90087890625 }, { "start": 1401.72, "end": 1401.88, "word": " the", "probability": 0.8056640625 }, { "start": 1401.88, "end": 1402.22, "word": " workbook", "probability": 0.845947265625 }, { "start": 1402.22, "end": 1402.66, "word": " complete", "probability": 0.479248046875 } ] }, { "id": 604, "seek": 140482, "start": 1402.66, "end": 1404.78, "text": " spam filter sklearn.", "tokens": [ 50864, 24028, 6608, 1110, 306, 1083, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.1872577519379845, "compression_ratio": 1.7248062015503876, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 1402.66, "end": 1403.08, "word": " spam", "probability": 0.79931640625 }, { "start": 1403.08, "end": 1403.42, "word": " filter", "probability": 0.90234375 }, { "start": 1403.42, "end": 1404.26, "word": " sklearn", "probability": 0.9562174479166666 }, { "start": 1404.26, "end": 1404.78, "word": ".", "probability": 0.8291015625 } ] }, { "id": 605, "seek": 140482, "start": 1405.72, "end": 1406.8, "text": " And these are Jupyter notebooks.", "tokens": [ 50964, 400, 613, 366, 22125, 88, 391, 43782, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.1872577519379845, "compression_ratio": 1.7248062015503876, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 1405.72, "end": 1405.9, "word": " And", "probability": 0.8154296875 }, { "start": 1405.9, "end": 1406.02, "word": " these", "probability": 0.7060546875 }, { "start": 1406.02, "end": 1406.12, "word": " are", "probability": 0.8955078125 }, { "start": 1406.12, "end": 1406.34, "word": " Jupyter", "probability": 0.91845703125 }, { "start": 1406.34, "end": 1406.62, "word": " notebooks", "probability": 0.58056640625 }, { "start": 1406.62, "end": 1406.8, "word": ".", "probability": 0.72265625 } ] }, { "id": 606, "seek": 140482, "start": 1406.8, "end": 1408.12, "text": " If you've never used Jupyter notebooks,", "tokens": [ 51064, 759, 291, 600, 1128, 1143, 22125, 88, 391, 43782, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.1872577519379845, "compression_ratio": 1.7248062015503876, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 1406.8, "end": 1406.88, "word": " If", "probability": 0.900390625 }, { "start": 1406.88, "end": 1407.02, "word": " you've", "probability": 0.922607421875 }, { "start": 1407.02, "end": 1407.16, "word": " never", "probability": 0.86083984375 }, { "start": 1407.16, "end": 1407.36, "word": " used", "probability": 0.81689453125 }, { "start": 1407.36, "end": 1407.6, "word": " Jupyter", "probability": 0.9231770833333334 }, { "start": 1407.6, "end": 1408.0, "word": " notebooks", "probability": 0.72119140625 }, { "start": 1408.0, "end": 1408.12, "word": ",", "probability": 0.91796875 } ] }, { "id": 607, "seek": 140482, "start": 1408.12, "end": 1409.26, "text": " I think they're the best thing", "tokens": [ 51164, 286, 519, 436, 434, 264, 1151, 551, 51214 ], "temperature": 0.0, "avg_logprob": -0.1872577519379845, "compression_ratio": 1.7248062015503876, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 1408.12, "end": 1408.36, "word": " I", "probability": 0.9990234375 }, { "start": 1408.36, "end": 1408.62, "word": " think", "probability": 0.802734375 }, { "start": 1408.62, "end": 1408.82, "word": " they're", "probability": 0.84130859375 }, { "start": 1408.82, "end": 1408.9, "word": " the", "probability": 0.81591796875 }, { "start": 1408.9, "end": 1409.08, "word": " best", "probability": 0.8095703125 }, { "start": 1409.08, "end": 1409.26, "word": " thing", "probability": 0.410400390625 } ] }, { "id": 608, "seek": 140482, "start": 1409.26, "end": 1410.48, "text": " since sliced bread,", "tokens": [ 51264, 1670, 27098, 5961, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.1872577519379845, "compression_ratio": 1.7248062015503876, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 1409.26, "end": 1409.48, "word": " since", "probability": 0.79736328125 }, { "start": 1409.48, "end": 1409.72, "word": " sliced", "probability": 0.607421875 }, { "start": 1409.72, "end": 1410.0, "word": " bread", "probability": 0.90185546875 }, { "start": 1410.0, "end": 1410.48, "word": ",", "probability": 0.85986328125 } ] }, { "id": 609, "seek": 140482, "start": 1410.48, "end": 1412.38, "text": " especially when it comes to data science.", "tokens": [ 51364, 2318, 562, 309, 1487, 281, 1412, 3497, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.1872577519379845, "compression_ratio": 1.7248062015503876, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 1410.48, "end": 1410.94, "word": " especially", "probability": 0.70849609375 }, { "start": 1410.94, "end": 1411.12, "word": " when", "probability": 0.87939453125 }, { "start": 1411.12, "end": 1411.2, "word": " it", "probability": 0.90966796875 }, { "start": 1411.2, "end": 1411.36, "word": " comes", "probability": 0.81396484375 }, { "start": 1411.36, "end": 1411.5, "word": " to", "probability": 0.90576171875 }, { "start": 1411.5, "end": 1411.68, "word": " data", "probability": 0.8134765625 }, { "start": 1411.68, "end": 1412.12, "word": " science", "probability": 0.87060546875 }, { "start": 1412.12, "end": 1412.38, "word": ".", "probability": 0.50390625 } ] }, { "id": 610, "seek": 140482, "start": 1412.82, "end": 1415.26, "text": " But it allows us to interact", "tokens": [ 51464, 583, 309, 4045, 505, 281, 4648, 51514 ], "temperature": 0.0, "avg_logprob": -0.1872577519379845, "compression_ratio": 1.7248062015503876, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 1412.82, "end": 1413.34, "word": " But", "probability": 0.8828125 }, { "start": 1413.34, "end": 1413.5, "word": " it", "probability": 0.87646484375 }, { "start": 1413.5, "end": 1413.74, "word": " allows", "probability": 0.79248046875 }, { "start": 1413.74, "end": 1413.94, "word": " us", "probability": 0.90087890625 }, { "start": 1413.94, "end": 1414.38, "word": " to", "probability": 0.90673828125 }, { "start": 1414.38, "end": 1415.26, "word": " interact", "probability": 0.75390625 } ] }, { "id": 611, "seek": 140482, "start": 1415.26, "end": 1416.2, "text": " with code blocks", "tokens": [ 51564, 365, 3089, 8474, 51614 ], "temperature": 0.0, "avg_logprob": -0.1872577519379845, "compression_ratio": 1.7248062015503876, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 1415.26, "end": 1415.48, "word": " with", "probability": 0.81640625 }, { "start": 1415.48, "end": 1415.76, "word": " code", "probability": 0.82568359375 }, { "start": 1415.76, "end": 1416.2, "word": " blocks", "probability": 0.76416015625 } ] }, { "id": 612, "seek": 140482, "start": 1416.2, "end": 1418.54, "text": " and visualize things in line.", "tokens": [ 51664, 293, 23273, 721, 294, 1622, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.1872577519379845, "compression_ratio": 1.7248062015503876, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 1416.2, "end": 1416.62, "word": " and", "probability": 0.873046875 }, { "start": 1416.62, "end": 1417.02, "word": " visualize", "probability": 0.873046875 }, { "start": 1417.02, "end": 1417.5, "word": " things", "probability": 0.7412109375 }, { "start": 1417.5, "end": 1417.8, "word": " in", "probability": 0.91552734375 }, { "start": 1417.8, "end": 1418.22, "word": " line", "probability": 0.63818359375 }, { "start": 1418.22, "end": 1418.54, "word": ".", "probability": 0.81201171875 } ] }, { "id": 613, "seek": 140482, "start": 1418.54, "end": 1419.74, "text": " And I think they work fantastic", "tokens": [ 51764, 400, 286, 519, 436, 589, 5456, 51814 ], "temperature": 0.0, "avg_logprob": -0.1872577519379845, "compression_ratio": 1.7248062015503876, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 1418.54, "end": 1418.68, "word": " And", "probability": 0.83056640625 }, { "start": 1418.68, "end": 1418.74, "word": " I", "probability": 0.99853515625 }, { "start": 1418.74, "end": 1418.84, "word": " think", "probability": 0.8125 }, { "start": 1418.84, "end": 1418.96, "word": " they", "probability": 0.7373046875 }, { "start": 1418.96, "end": 1419.16, "word": " work", "probability": 0.78125 }, { "start": 1419.16, "end": 1419.74, "word": " fantastic", "probability": 0.89111328125 } ] }, { "id": 614, "seek": 143186, "start": 1423.52, "end": 1424.04, "text": " together.", "tokens": [ 50414, 1214, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.1937004013193978, "compression_ratio": 1.6962025316455696, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 1423.52, "end": 1423.52, "word": " together", "probability": 4.470348358154297e-06 }, { "start": 1423.52, "end": 1424.04, "word": ".", "probability": 0.666015625 } ] }, { "id": 615, "seek": 143186, "start": 1425.08, "end": 1427.8, "text": " So let's go ahead, scroll down.", "tokens": [ 50514, 407, 718, 311, 352, 2286, 11, 11369, 760, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.1937004013193978, "compression_ratio": 1.6962025316455696, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 1425.08, "end": 1425.6, "word": " So", "probability": 0.469482421875 }, { "start": 1425.6, "end": 1425.92, "word": " let's", "probability": 0.8076171875 }, { "start": 1425.92, "end": 1426.06, "word": " go", "probability": 0.869140625 }, { "start": 1426.06, "end": 1426.44, "word": " ahead", "probability": 0.84716796875 }, { "start": 1426.44, "end": 1426.74, "word": ",", "probability": 0.57177734375 }, { "start": 1426.74, "end": 1427.0, "word": " scroll", "probability": 0.892578125 }, { "start": 1427.0, "end": 1427.4, "word": " down", "probability": 0.8212890625 }, { "start": 1427.4, "end": 1427.8, "word": ".", "probability": 0.578125 } ] }, { "id": 616, "seek": 143186, "start": 1427.8, "end": 1430.56, "text": " We're going to run this first code block.", "tokens": [ 50614, 492, 434, 516, 281, 1190, 341, 700, 3089, 3461, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.1937004013193978, "compression_ratio": 1.6962025316455696, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 1427.8, "end": 1427.96, "word": " We're", "probability": 0.822509765625 }, { "start": 1427.96, "end": 1428.0, "word": " going", "probability": 0.65625 }, { "start": 1428.0, "end": 1428.06, "word": " to", "probability": 0.90185546875 }, { "start": 1428.06, "end": 1428.18, "word": " run", "probability": 0.89794921875 }, { "start": 1428.18, "end": 1428.38, "word": " this", "probability": 0.87451171875 }, { "start": 1428.38, "end": 1428.9, "word": " first", "probability": 0.81689453125 }, { "start": 1428.9, "end": 1429.64, "word": " code", "probability": 0.8310546875 }, { "start": 1429.64, "end": 1430.04, "word": " block", "probability": 0.779296875 }, { "start": 1430.04, "end": 1430.56, "word": ".", "probability": 0.6494140625 } ] }, { "id": 617, "seek": 143186, "start": 1431.1, "end": 1432.38, "text": " And so what this is going to do", "tokens": [ 50714, 400, 370, 437, 341, 307, 516, 281, 360, 50764 ], "temperature": 0.0, "avg_logprob": -0.1937004013193978, "compression_ratio": 1.6962025316455696, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 1431.1, "end": 1431.1, "word": " And", "probability": 0.6142578125 }, { "start": 1431.1, "end": 1431.4, "word": " so", "probability": 0.85888671875 }, { "start": 1431.4, "end": 1431.56, "word": " what", "probability": 0.83349609375 }, { "start": 1431.56, "end": 1431.7, "word": " this", "probability": 0.88037109375 }, { "start": 1431.7, "end": 1431.82, "word": " is", "probability": 0.90771484375 }, { "start": 1431.82, "end": 1431.98, "word": " going", "probability": 0.85302734375 }, { "start": 1431.98, "end": 1432.14, "word": " to", "probability": 0.90673828125 }, { "start": 1432.14, "end": 1432.38, "word": " do", "probability": 0.90576171875 } ] }, { "id": 618, "seek": 143186, "start": 1432.38, "end": 1433.88, "text": " is install a couple of libraries", "tokens": [ 50814, 307, 3625, 257, 1916, 295, 15148, 50864 ], "temperature": 0.0, "avg_logprob": -0.1937004013193978, "compression_ratio": 1.6962025316455696, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 1432.38, "end": 1432.72, "word": " is", "probability": 0.87255859375 }, { "start": 1432.72, "end": 1433.08, "word": " install", "probability": 0.8134765625 }, { "start": 1433.22, "end": 1433.36, "word": " a couple", "probability": 0.78955078125 }, { "start": 1433.36, "end": 1433.48, "word": " of", "probability": 0.88525390625 }, { "start": 1433.48, "end": 1433.88, "word": " libraries", "probability": 0.68994140625 } ] }, { "id": 619, "seek": 143186, "start": 1433.88, "end": 1434.84, "text": " that we need,", "tokens": [ 50914, 300, 321, 643, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.1937004013193978, "compression_ratio": 1.6962025316455696, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 1433.88, "end": 1434.06, "word": " that", "probability": 0.8759765625 }, { "start": 1434.06, "end": 1434.18, "word": " we", "probability": 0.90673828125 }, { "start": 1434.18, "end": 1434.58, "word": " need", "probability": 0.81103515625 }, { "start": 1434.58, "end": 1434.84, "word": ",", "probability": 0.64892578125 } ] }, { "id": 620, "seek": 143186, "start": 1434.84, "end": 1437.02, "text": " as well as set our data directory", "tokens": [ 51014, 382, 731, 382, 992, 527, 1412, 21120, 51064 ], "temperature": 0.0, "avg_logprob": -0.1937004013193978, "compression_ratio": 1.6962025316455696, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 1434.84, "end": 1435.18, "word": " as", "probability": 0.90283203125 }, { "start": 1435.18, "end": 1435.52, "word": " well", "probability": 0.87744140625 }, { "start": 1435.52, "end": 1435.94, "word": " as", "probability": 0.8974609375 }, { "start": 1435.94, "end": 1436.2, "word": " set", "probability": 0.89794921875 }, { "start": 1436.2, "end": 1436.4, "word": " our", "probability": 0.80908203125 }, { "start": 1436.4, "end": 1436.6, "word": " data", "probability": 0.759765625 }, { "start": 1436.6, "end": 1437.02, "word": " directory", "probability": 0.7890625 } ] }, { "id": 621, "seek": 143186, "start": 1437.02, "end": 1439.32, "text": " to where the data directory is", "tokens": [ 51114, 281, 689, 264, 1412, 21120, 307, 51164 ], "temperature": 0.0, "avg_logprob": -0.1937004013193978, "compression_ratio": 1.6962025316455696, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 1437.02, "end": 1437.48, "word": " to", "probability": 0.89599609375 }, { "start": 1437.48, "end": 1438.08, "word": " where", "probability": 0.9072265625 }, { "start": 1438.08, "end": 1438.3, "word": " the", "probability": 0.8095703125 }, { "start": 1438.3, "end": 1438.5, "word": " data", "probability": 0.79931640625 }, { "start": 1438.5, "end": 1438.8, "word": " directory", "probability": 0.75927734375 }, { "start": 1438.8, "end": 1439.32, "word": " is", "probability": 0.90283203125 } ] }, { "id": 622, "seek": 143186, "start": 1439.32, "end": 1440.96, "text": " in the GitHub project.", "tokens": [ 51214, 294, 264, 23331, 1716, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.1937004013193978, "compression_ratio": 1.6962025316455696, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 1439.32, "end": 1439.8, "word": " in", "probability": 0.89208984375 }, { "start": 1439.8, "end": 1439.9, "word": " the", "probability": 0.80517578125 }, { "start": 1439.9, "end": 1440.12, "word": " GitHub", "probability": 0.8056640625 }, { "start": 1440.12, "end": 1440.6, "word": " project", "probability": 0.78076171875 }, { "start": 1440.6, "end": 1440.96, "word": ".", "probability": 0.98486328125 } ] }, { "id": 623, "seek": 143186, "start": 1440.96, "end": 1443.4, "text": " So to run these, you can click run", "tokens": [ 51314, 407, 281, 1190, 613, 11, 291, 393, 2052, 1190, 51364 ], "temperature": 0.0, "avg_logprob": -0.1937004013193978, "compression_ratio": 1.6962025316455696, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 1440.96, "end": 1441.02, "word": " So", "probability": 0.876953125 }, { "start": 1441.02, "end": 1441.54, "word": " to", "probability": 0.82080078125 }, { "start": 1441.54, "end": 1441.72, "word": " run", "probability": 0.90966796875 }, { "start": 1441.72, "end": 1442.0, "word": " these", "probability": 0.6943359375 }, { "start": 1442.0, "end": 1442.12, "word": ",", "probability": 0.7978515625 }, { "start": 1442.12, "end": 1442.2, "word": " you", "probability": 0.8896484375 }, { "start": 1442.2, "end": 1442.48, "word": " can", "probability": 0.89453125 }, { "start": 1442.48, "end": 1442.96, "word": " click", "probability": 0.8193359375 }, { "start": 1442.96, "end": 1443.4, "word": " run", "probability": 0.3759765625 } ] }, { "id": 624, "seek": 143186, "start": 1443.4, "end": 1444.36, "text": " up at the top,", "tokens": [ 51414, 493, 412, 264, 1192, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.1937004013193978, "compression_ratio": 1.6962025316455696, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 1443.4, "end": 1443.74, "word": " up", "probability": 0.87939453125 }, { "start": 1443.74, "end": 1443.84, "word": " at", "probability": 0.8984375 }, { "start": 1443.84, "end": 1443.96, "word": " the", "probability": 0.80908203125 }, { "start": 1443.96, "end": 1444.3, "word": " top", "probability": 0.82080078125 }, { "start": 1444.3, "end": 1444.36, "word": ",", "probability": 0.564453125 } ] }, { "id": 625, "seek": 143186, "start": 1444.36, "end": 1446.56, "text": " or you can press shift enter,", "tokens": [ 51514, 420, 291, 393, 1886, 5513, 3242, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.1937004013193978, "compression_ratio": 1.6962025316455696, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 1444.36, "end": 1444.56, "word": " or", "probability": 0.90087890625 }, { "start": 1444.56, "end": 1444.74, "word": " you", "probability": 0.8916015625 }, { "start": 1444.74, "end": 1444.9, "word": " can", "probability": 0.8935546875 }, { "start": 1444.9, "end": 1445.2, "word": " press", "probability": 0.734375 }, { "start": 1445.2, "end": 1445.66, "word": " shift", "probability": 0.587890625 }, { "start": 1445.66, "end": 1446.1, "word": " enter", "probability": 0.403564453125 }, { "start": 1446.1, "end": 1446.56, "word": ",", "probability": 0.96435546875 } ] }, { "id": 626, "seek": 143186, "start": 1446.56, "end": 1447.9, "text": " which is what I'm pressing now.", "tokens": [ 51614, 597, 307, 437, 286, 478, 12417, 586, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.1937004013193978, "compression_ratio": 1.6962025316455696, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 1446.56, "end": 1446.76, "word": " which", "probability": 0.91552734375 }, { "start": 1446.76, "end": 1446.9, "word": " is", "probability": 0.904296875 }, { "start": 1446.9, "end": 1447.04, "word": " what", "probability": 0.884765625 }, { "start": 1447.04, "end": 1447.16, "word": " I'm", "probability": 0.997314453125 }, { "start": 1447.16, "end": 1447.4, "word": " pressing", "probability": 0.6962890625 }, { "start": 1447.4, "end": 1447.74, "word": " now", "probability": 0.900390625 }, { "start": 1447.74, "end": 1447.9, "word": ".", "probability": 0.73388671875 } ] }, { "id": 627, "seek": 143186, "start": 1447.9, "end": 1450.56, "text": " And then you can see that it's running.", "tokens": [ 51714, 400, 550, 291, 393, 536, 300, 309, 311, 2614, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.1937004013193978, "compression_ratio": 1.6962025316455696, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 1447.9, "end": 1448.26, "word": " And", "probability": 0.890625 }, { "start": 1448.26, "end": 1448.36, "word": " then", "probability": 0.732421875 }, { "start": 1448.36, "end": 1448.46, "word": " you", "probability": 0.89501953125 }, { "start": 1448.46, "end": 1448.6, "word": " can", "probability": 0.89453125 }, { "start": 1448.6, "end": 1448.92, "word": " see", "probability": 0.80908203125 }, { "start": 1448.92, "end": 1449.6, "word": " that", "probability": 0.8818359375 }, { "start": 1449.6, "end": 1449.84, "word": " it's", "probability": 0.950439453125 }, { "start": 1449.84, "end": 1450.1, "word": " running", "probability": 0.88330078125 }, { "start": 1450.1, "end": 1450.56, "word": ".", "probability": 0.59326171875 } ] }, { "id": 628, "seek": 146186, "start": 1450.56, "end": 1452.16, "text": " A star in the upper corner", "tokens": [ 50364, 316, 3543, 294, 264, 6597, 4538, 50414 ], "temperature": 0.0, "avg_logprob": -0.18260869331981824, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.0002002716064453125, "words": [ { "start": 1450.56, "end": 1450.82, "word": " A", "probability": 0.7080078125 }, { "start": 1450.82, "end": 1451.2, "word": " star", "probability": 0.84814453125 }, { "start": 1451.2, "end": 1451.44, "word": " in", "probability": 0.90185546875 }, { "start": 1451.44, "end": 1451.58, "word": " the", "probability": 0.8173828125 }, { "start": 1451.58, "end": 1451.78, "word": " upper", "probability": 0.7587890625 }, { "start": 1451.78, "end": 1452.16, "word": " corner", "probability": 0.77001953125 } ] }, { "id": 629, "seek": 146186, "start": 1452.16, "end": 1453.78, "text": " means that it's currently running.", "tokens": [ 50464, 1355, 300, 309, 311, 4362, 2614, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.18260869331981824, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.0002002716064453125, "words": [ { "start": 1452.16, "end": 1452.58, "word": " means", "probability": 0.88037109375 }, { "start": 1452.58, "end": 1452.72, "word": " that", "probability": 0.8212890625 }, { "start": 1452.72, "end": 1452.86, "word": " it's", "probability": 0.935302734375 }, { "start": 1452.86, "end": 1453.18, "word": " currently", "probability": 0.7236328125 }, { "start": 1453.18, "end": 1453.54, "word": " running", "probability": 0.8818359375 }, { "start": 1453.54, "end": 1453.78, "word": ".", "probability": 0.1837158203125 } ] }, { "id": 630, "seek": 146186, "start": 1453.78, "end": 1455.32, "text": " And then a number in the upper corner", "tokens": [ 50564, 400, 550, 257, 1230, 294, 264, 6597, 4538, 50614 ], "temperature": 0.0, "avg_logprob": -0.18260869331981824, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.0002002716064453125, "words": [ { "start": 1453.78, "end": 1453.82, "word": " And", "probability": 0.76025390625 }, { "start": 1453.82, "end": 1453.96, "word": " then", "probability": 0.71337890625 }, { "start": 1454.16, "end": 1454.42, "word": " a number", "probability": 0.87451171875 }, { "start": 1454.42, "end": 1454.64, "word": " in", "probability": 0.90576171875 }, { "start": 1454.64, "end": 1454.74, "word": " the", "probability": 0.8134765625 }, { "start": 1454.74, "end": 1454.92, "word": " upper", "probability": 0.78173828125 }, { "start": 1454.92, "end": 1455.32, "word": " corner", "probability": 0.7490234375 } ] }, { "id": 631, "seek": 146186, "start": 1455.32, "end": 1457.56, "text": " means that that was the order", "tokens": [ 50664, 1355, 300, 300, 390, 264, 1668, 50714 ], "temperature": 0.0, "avg_logprob": -0.18260869331981824, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.0002002716064453125, "words": [ { "start": 1455.32, "end": 1456.02, "word": " means", "probability": 0.86279296875 }, { "start": 1456.02, "end": 1456.48, "word": " that", "probability": 0.87841796875 }, { "start": 1456.48, "end": 1456.86, "word": " that", "probability": 0.73388671875 }, { "start": 1456.86, "end": 1457.02, "word": " was", "probability": 0.88623046875 }, { "start": 1457.02, "end": 1457.22, "word": " the", "probability": 0.81982421875 }, { "start": 1457.22, "end": 1457.56, "word": " order", "probability": 0.8173828125 } ] }, { "id": 632, "seek": 146186, "start": 1457.56, "end": 1459.84, "text": " that code block was ran in.", "tokens": [ 50764, 300, 3089, 3461, 390, 5872, 294, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.18260869331981824, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.0002002716064453125, "words": [ { "start": 1457.56, "end": 1458.02, "word": " that", "probability": 0.8818359375 }, { "start": 1458.02, "end": 1458.26, "word": " code", "probability": 0.7158203125 }, { "start": 1458.26, "end": 1458.5, "word": " block", "probability": 0.705078125 }, { "start": 1458.5, "end": 1458.68, "word": " was", "probability": 0.884765625 }, { "start": 1458.68, "end": 1459.0, "word": " ran", "probability": 0.8720703125 }, { "start": 1459.0, "end": 1459.32, "word": " in", "probability": 0.8935546875 }, { "start": 1459.32, "end": 1459.84, "word": ".", "probability": 0.98974609375 } ] }, { "id": 633, "seek": 146186, "start": 1462.56, "end": 1465.04, "text": " So while that is going,", "tokens": [ 50964, 407, 1339, 300, 307, 516, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.18260869331981824, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.0002002716064453125, "words": [ { "start": 1462.56, "end": 1462.82, "word": " So", "probability": 0.79833984375 }, { "start": 1462.82, "end": 1463.24, "word": " while", "probability": 0.67431640625 }, { "start": 1463.24, "end": 1463.66, "word": " that", "probability": 0.8798828125 }, { "start": 1463.66, "end": 1463.84, "word": " is", "probability": 0.90380859375 }, { "start": 1463.84, "end": 1464.22, "word": " going", "probability": 0.86376953125 }, { "start": 1464.22, "end": 1465.04, "word": ",", "probability": 0.619140625 } ] }, { "id": 634, "seek": 146186, "start": 1465.04, "end": 1465.82, "text": " I'm going to", "tokens": [ 51064, 286, 478, 516, 281, 51114 ], "temperature": 0.0, "avg_logprob": -0.18260869331981824, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.0002002716064453125, "words": [ { "start": 1465.04, "end": 1465.06, "word": " I'm", "probability": 0.78955078125 }, { "start": 1465.06, "end": 1465.14, "word": " going", "probability": 0.34765625 }, { "start": 1465.14, "end": 1465.82, "word": " to", "probability": 0.892578125 } ] }, { "id": 635, "seek": 146186, "start": 1466.78, "end": 1468.22, "text": " let it go until it stops", "tokens": [ 51164, 718, 309, 352, 1826, 309, 10094, 51214 ], "temperature": 0.0, "avg_logprob": -0.18260869331981824, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.0002002716064453125, "words": [ { "start": 1466.78, "end": 1467.3, "word": " let", "probability": 0.861328125 }, { "start": 1467.3, "end": 1467.4, "word": " it", "probability": 0.90283203125 }, { "start": 1467.4, "end": 1467.56, "word": " go", "probability": 0.90380859375 }, { "start": 1467.56, "end": 1467.78, "word": " until", "probability": 0.80517578125 }, { "start": 1467.78, "end": 1467.94, "word": " it", "probability": 0.9072265625 }, { "start": 1467.94, "end": 1468.22, "word": " stops", "probability": 0.7939453125 } ] }, { "id": 636, "seek": 146186, "start": 1468.22, "end": 1469.88, "text": " scrolling my thing.", "tokens": [ 51264, 29053, 452, 551, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.18260869331981824, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.0002002716064453125, "words": [ { "start": 1468.22, "end": 1468.58, "word": " scrolling", "probability": 0.80322265625 }, { "start": 1468.58, "end": 1468.88, "word": " my", "probability": 0.857421875 }, { "start": 1468.88, "end": 1469.36, "word": " thing", "probability": 0.80859375 }, { "start": 1469.36, "end": 1469.88, "word": ".", "probability": 0.8916015625 } ] }, { "id": 637, "seek": 146186, "start": 1470.9, "end": 1472.14, "text": " So we're just going to import", "tokens": [ 51364, 407, 321, 434, 445, 516, 281, 974, 51414 ], "temperature": 0.0, "avg_logprob": -0.18260869331981824, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.0002002716064453125, "words": [ { "start": 1470.9, "end": 1471.38, "word": " So", "probability": 0.79541015625 }, { "start": 1471.38, "end": 1471.48, "word": " we're", "probability": 0.91552734375 }, { "start": 1471.48, "end": 1471.58, "word": " just", "probability": 0.873046875 }, { "start": 1471.58, "end": 1471.7, "word": " going", "probability": 0.84521484375 }, { "start": 1471.7, "end": 1471.76, "word": " to", "probability": 0.9033203125 }, { "start": 1471.76, "end": 1472.14, "word": " import", "probability": 0.8251953125 } ] }, { "id": 638, "seek": 146186, "start": 1472.32, "end": 1473.18, "text": " a couple libraries.", "tokens": [ 51464, 257, 1916, 15148, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.18260869331981824, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.0002002716064453125, "words": [ { "start": 1472.32, "end": 1472.48, "word": " a couple", "probability": 0.791015625 }, { "start": 1472.48, "end": 1473.04, "word": " libraries", "probability": 0.74169921875 }, { "start": 1473.04, "end": 1473.18, "word": ".", "probability": 0.89501953125 } ] }, { "id": 639, "seek": 146186, "start": 1473.18, "end": 1474.8, "text": " We're going to import numpy,", "tokens": [ 51564, 492, 434, 516, 281, 974, 1031, 8200, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.18260869331981824, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.0002002716064453125, "words": [ { "start": 1473.18, "end": 1473.3, "word": " We're", "probability": 0.91455078125 }, { "start": 1473.3, "end": 1473.34, "word": " going", "probability": 0.83740234375 }, { "start": 1473.34, "end": 1473.38, "word": " to", "probability": 0.90283203125 }, { "start": 1473.38, "end": 1473.7, "word": " import", "probability": 0.80810546875 }, { "start": 1473.7, "end": 1474.36, "word": " numpy", "probability": 0.716064453125 }, { "start": 1474.36, "end": 1474.8, "word": ",", "probability": 0.86328125 } ] }, { "id": 640, "seek": 146186, "start": 1474.8, "end": 1476.82, "text": " matplotlib for graphs,", "tokens": [ 51664, 3803, 564, 310, 38270, 337, 24877, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.18260869331981824, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.0002002716064453125, "words": [ { "start": 1474.8, "end": 1475.6, "word": " matplotlib", "probability": 0.90966796875 }, { "start": 1475.6, "end": 1475.84, "word": " for", "probability": 0.88232421875 }, { "start": 1475.84, "end": 1476.46, "word": " graphs", "probability": 0.7158203125 }, { "start": 1476.46, "end": 1476.82, "word": ",", "probability": 0.74365234375 } ] }, { "id": 641, "seek": 146186, "start": 1476.82, "end": 1478.28, "text": " regular expressions we'll be using", "tokens": [ 51764, 3890, 15277, 321, 603, 312, 1228, 51814 ], "temperature": 0.0, "avg_logprob": -0.18260869331981824, "compression_ratio": 1.709090909090909, "no_speech_prob": 0.0002002716064453125, "words": [ { "start": 1476.82, "end": 1477.24, "word": " regular", "probability": 0.9091796875 }, { "start": 1477.24, "end": 1477.7, "word": " expressions", "probability": 0.8583984375 }, { "start": 1477.7, "end": 1477.9, "word": " we'll", "probability": 0.869384765625 }, { "start": 1477.9, "end": 1478.04, "word": " be", "probability": 0.90625 }, { "start": 1478.04, "end": 1478.28, "word": " using", "probability": 0.82666015625 } ] }, { "id": 642, "seek": 148904, "start": 1480.56, "end": 1481.36, "text": " and NLTK.", "tokens": [ 50364, 293, 426, 43, 51, 42, 13, 50414 ], "temperature": 0.0, "avg_logprob": -0.19887609361556538, "compression_ratio": 1.5608695652173914, "no_speech_prob": 0.0002694129943847656, "words": [ { "start": 1480.56, "end": 1480.72, "word": " and", "probability": 0.004184722900390625 }, { "start": 1480.72, "end": 1481.26, "word": " NLTK", "probability": 0.76153564453125 }, { "start": 1481.26, "end": 1481.36, "word": ".", "probability": 0.1524658203125 } ] }, { "id": 643, "seek": 148904, "start": 1481.36, "end": 1482.54, "text": " NLTK stands for", "tokens": [ 50464, 426, 43, 51, 42, 7382, 337, 50514 ], "temperature": 0.0, "avg_logprob": -0.19887609361556538, "compression_ratio": 1.5608695652173914, "no_speech_prob": 0.0002694129943847656, "words": [ { "start": 1481.36, "end": 1481.9, "word": " NLTK", "probability": 0.9776611328125 }, { "start": 1481.9, "end": 1482.28, "word": " stands", "probability": 0.7275390625 }, { "start": 1482.28, "end": 1482.54, "word": " for", "probability": 0.89111328125 } ] }, { "id": 644, "seek": 148904, "start": 1482.54, "end": 1484.38, "text": " Natural Language Toolkit.", "tokens": [ 50564, 20137, 24445, 15934, 22681, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.19887609361556538, "compression_ratio": 1.5608695652173914, "no_speech_prob": 0.0002694129943847656, "words": [ { "start": 1482.54, "end": 1483.06, "word": " Natural", "probability": 0.4306640625 }, { "start": 1483.06, "end": 1483.52, "word": " Language", "probability": 0.8525390625 }, { "start": 1483.52, "end": 1484.16, "word": " Toolkit", "probability": 0.8564453125 }, { "start": 1484.16, "end": 1484.38, "word": ".", "probability": 0.93408203125 } ] }, { "id": 645, "seek": 148904, "start": 1484.38, "end": 1486.4, "text": " This will allow us to identify", "tokens": [ 50664, 639, 486, 2089, 505, 281, 5876, 50714 ], "temperature": 0.0, "avg_logprob": -0.19887609361556538, "compression_ratio": 1.5608695652173914, "no_speech_prob": 0.0002694129943847656, "words": [ { "start": 1484.38, "end": 1484.46, "word": " This", "probability": 0.80419921875 }, { "start": 1484.46, "end": 1484.62, "word": " will", "probability": 0.82421875 }, { "start": 1484.62, "end": 1484.92, "word": " allow", "probability": 0.87158203125 }, { "start": 1484.92, "end": 1485.14, "word": " us", "probability": 0.90087890625 }, { "start": 1485.14, "end": 1485.46, "word": " to", "probability": 0.9033203125 }, { "start": 1485.46, "end": 1486.4, "word": " identify", "probability": 0.87890625 } ] }, { "id": 646, "seek": 148904, "start": 1486.4, "end": 1489.1, "text": " and collect a list of stop words", "tokens": [ 50764, 293, 2500, 257, 1329, 295, 1590, 2283, 50814 ], "temperature": 0.0, "avg_logprob": -0.19887609361556538, "compression_ratio": 1.5608695652173914, "no_speech_prob": 0.0002694129943847656, "words": [ { "start": 1486.4, "end": 1487.28, "word": " and", "probability": 0.88037109375 }, { "start": 1487.28, "end": 1487.9, "word": " collect", "probability": 0.7705078125 }, { "start": 1488.12, "end": 1488.28, "word": " a list", "probability": 0.8994140625 }, { "start": 1488.28, "end": 1488.46, "word": " of", "probability": 0.9052734375 }, { "start": 1488.46, "end": 1488.76, "word": " stop", "probability": 0.89501953125 }, { "start": 1488.76, "end": 1489.1, "word": " words", "probability": 0.634765625 } ] }, { "id": 647, "seek": 148904, "start": 1489.1, "end": 1491.56, "text": " to remove those things.", "tokens": [ 50864, 281, 4159, 729, 721, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.19887609361556538, "compression_ratio": 1.5608695652173914, "no_speech_prob": 0.0002694129943847656, "words": [ { "start": 1489.1, "end": 1490.06, "word": " to", "probability": 0.8154296875 }, { "start": 1490.06, "end": 1490.4, "word": " remove", "probability": 0.861328125 }, { "start": 1490.4, "end": 1490.64, "word": " those", "probability": 0.84326171875 }, { "start": 1490.64, "end": 1491.02, "word": " things", "probability": 0.7216796875 }, { "start": 1491.02, "end": 1491.56, "word": ".", "probability": 0.51318359375 } ] }, { "id": 648, "seek": 148904, "start": 1491.56, "end": 1493.26, "text": " And it will also allow us", "tokens": [ 50964, 400, 309, 486, 611, 2089, 505, 51014 ], "temperature": 0.0, "avg_logprob": -0.19887609361556538, "compression_ratio": 1.5608695652173914, "no_speech_prob": 0.0002694129943847656, "words": [ { "start": 1491.56, "end": 1491.98, "word": " And", "probability": 0.794921875 }, { "start": 1491.98, "end": 1492.12, "word": " it", "probability": 0.8935546875 }, { "start": 1492.12, "end": 1492.26, "word": " will", "probability": 0.81396484375 }, { "start": 1492.26, "end": 1492.56, "word": " also", "probability": 0.8212890625 }, { "start": 1492.56, "end": 1492.96, "word": " allow", "probability": 0.87451171875 }, { "start": 1492.96, "end": 1493.26, "word": " us", "probability": 0.89501953125 } ] }, { "id": 649, "seek": 148904, "start": 1493.26, "end": 1494.9, "text": " to use a stemmer function", "tokens": [ 51064, 281, 764, 257, 12312, 936, 2445, 51114 ], "temperature": 0.0, "avg_logprob": -0.19887609361556538, "compression_ratio": 1.5608695652173914, "no_speech_prob": 0.0002694129943847656, "words": [ { "start": 1493.26, "end": 1493.5, "word": " to", "probability": 0.90625 }, { "start": 1493.5, "end": 1493.82, "word": " use", "probability": 0.82568359375 }, { "start": 1494.1, "end": 1494.48, "word": " a stemmer", "probability": 0.78466796875 }, { "start": 1494.48, "end": 1494.9, "word": " function", "probability": 0.890625 } ] }, { "id": 650, "seek": 148904, "start": 1494.9, "end": 1497.06, "text": " to stem the words", "tokens": [ 51164, 281, 12312, 264, 2283, 51214 ], "temperature": 0.0, "avg_logprob": -0.19887609361556538, "compression_ratio": 1.5608695652173914, "no_speech_prob": 0.0002694129943847656, "words": [ { "start": 1494.9, "end": 1495.98, "word": " to", "probability": 0.8662109375 }, { "start": 1495.98, "end": 1496.36, "word": " stem", "probability": 0.81103515625 }, { "start": 1496.36, "end": 1496.62, "word": " the", "probability": 0.8046875 }, { "start": 1496.62, "end": 1497.06, "word": " words", "probability": 0.72900390625 } ] }, { "id": 651, "seek": 148904, "start": 1497.06, "end": 1499.78, "text": " and reduce our problem space.", "tokens": [ 51264, 293, 5407, 527, 1154, 1901, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.19887609361556538, "compression_ratio": 1.5608695652173914, "no_speech_prob": 0.0002694129943847656, "words": [ { "start": 1497.06, "end": 1497.6, "word": " and", "probability": 0.865234375 }, { "start": 1497.6, "end": 1497.92, "word": " reduce", "probability": 0.763671875 }, { "start": 1497.92, "end": 1498.38, "word": " our", "probability": 0.81640625 }, { "start": 1498.38, "end": 1498.98, "word": " problem", "probability": 0.74462890625 }, { "start": 1498.98, "end": 1499.46, "word": " space", "probability": 0.81787109375 }, { "start": 1499.46, "end": 1499.78, "word": ".", "probability": 0.9755859375 } ] }, { "id": 652, "seek": 148904, "start": 1500.8, "end": 1501.94, "text": " Train test split,", "tokens": [ 51414, 1765, 491, 1500, 7472, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.19887609361556538, "compression_ratio": 1.5608695652173914, "no_speech_prob": 0.0002694129943847656, "words": [ { "start": 1500.8, "end": 1501.36, "word": " Train", "probability": 0.53997802734375 }, { "start": 1501.36, "end": 1501.56, "word": " test", "probability": 0.46875 }, { "start": 1501.56, "end": 1501.84, "word": " split", "probability": 0.82568359375 }, { "start": 1501.84, "end": 1501.94, "word": ",", "probability": 0.376953125 } ] }, { "id": 653, "seek": 148904, "start": 1501.94, "end": 1504.32, "text": " I don't believe we're actually using that in here.", "tokens": [ 51514, 286, 500, 380, 1697, 321, 434, 767, 1228, 300, 294, 510, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.19887609361556538, "compression_ratio": 1.5608695652173914, "no_speech_prob": 0.0002694129943847656, "words": [ { "start": 1501.94, "end": 1502.04, "word": " I", "probability": 0.9970703125 }, { "start": 1502.04, "end": 1502.18, "word": " don't", "probability": 0.947509765625 }, { "start": 1502.18, "end": 1502.38, "word": " believe", "probability": 0.7099609375 }, { "start": 1502.38, "end": 1502.54, "word": " we're", "probability": 0.923828125 }, { "start": 1502.54, "end": 1502.82, "word": " actually", "probability": 0.77880859375 }, { "start": 1502.82, "end": 1503.16, "word": " using", "probability": 0.8310546875 }, { "start": 1503.16, "end": 1503.42, "word": " that", "probability": 0.88720703125 }, { "start": 1503.42, "end": 1503.62, "word": " in", "probability": 0.8955078125 }, { "start": 1503.62, "end": 1503.96, "word": " here", "probability": 0.81201171875 }, { "start": 1503.96, "end": 1504.32, "word": ".", "probability": 0.9560546875 } ] }, { "id": 654, "seek": 148904, "start": 1504.32, "end": 1506.32, "text": " The data directories I have", "tokens": [ 51614, 440, 1412, 5391, 530, 286, 362, 51664 ], "temperature": 0.0, "avg_logprob": -0.19887609361556538, "compression_ratio": 1.5608695652173914, "no_speech_prob": 0.0002694129943847656, "words": [ { "start": 1504.32, "end": 1504.88, "word": " The", "probability": 0.79052734375 }, { "start": 1504.88, "end": 1505.16, "word": " data", "probability": 0.81005859375 }, { "start": 1505.16, "end": 1505.86, "word": " directories", "probability": 0.908447265625 }, { "start": 1505.86, "end": 1506.04, "word": " I", "probability": 0.97119140625 }, { "start": 1506.04, "end": 1506.32, "word": " have", "probability": 0.87744140625 } ] }, { "id": 655, "seek": 148904, "start": 1506.32, "end": 1507.74, "text": " are already split into", "tokens": [ 51714, 366, 1217, 7472, 666, 51764 ], "temperature": 0.0, "avg_logprob": -0.19887609361556538, "compression_ratio": 1.5608695652173914, "no_speech_prob": 0.0002694129943847656, "words": [ { "start": 1506.32, "end": 1506.48, "word": " are", "probability": 0.87109375 }, { "start": 1506.48, "end": 1506.82, "word": " already", "probability": 0.8203125 }, { "start": 1506.82, "end": 1507.2, "word": " split", "probability": 0.84228515625 }, { "start": 1507.2, "end": 1507.74, "word": " into", "probability": 0.7333984375 } ] }, { "id": 656, "seek": 151598, "start": 1507.74, "end": 1509.26, "text": " 80% training,", "tokens": [ 50364, 4688, 4, 3097, 11, 50414 ], "temperature": 0.0, "avg_logprob": -0.19844980009897487, "compression_ratio": 1.7448559670781894, "no_speech_prob": 0.0087127685546875, "words": [ { "start": 1507.74, "end": 1508.06, "word": " 80", "probability": 0.25732421875 }, { "start": 1508.06, "end": 1508.42, "word": "%", "probability": 0.80908203125 }, { "start": 1508.42, "end": 1508.92, "word": " training", "probability": 0.80322265625 }, { "start": 1508.92, "end": 1509.26, "word": ",", "probability": 0.552734375 } ] }, { "id": 657, "seek": 151598, "start": 1509.26, "end": 1511.06, "text": " 20% testing.", "tokens": [ 50464, 945, 4, 4997, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.19844980009897487, "compression_ratio": 1.7448559670781894, "no_speech_prob": 0.0087127685546875, "words": [ { "start": 1509.26, "end": 1509.62, "word": " 20", "probability": 0.87744140625 }, { "start": 1509.62, "end": 1509.96, "word": "%", "probability": 0.99462890625 }, { "start": 1509.96, "end": 1510.5, "word": " testing", "probability": 0.73193359375 }, { "start": 1510.5, "end": 1511.06, "word": ".", "probability": 0.59033203125 } ] }, { "id": 658, "seek": 151598, "start": 1511.3, "end": 1513.32, "text": " And then we're going to use our vectorizers.", "tokens": [ 50564, 400, 550, 321, 434, 516, 281, 764, 527, 8062, 22525, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.19844980009897487, "compression_ratio": 1.7448559670781894, "no_speech_prob": 0.0087127685546875, "words": [ { "start": 1511.3, "end": 1511.56, "word": " And", "probability": 0.419189453125 }, { "start": 1511.56, "end": 1511.64, "word": " then", "probability": 0.44482421875 }, { "start": 1511.64, "end": 1511.76, "word": " we're", "probability": 0.87646484375 }, { "start": 1511.76, "end": 1511.82, "word": " going", "probability": 0.63232421875 }, { "start": 1511.82, "end": 1511.82, "word": " to", "probability": 0.90673828125 }, { "start": 1511.82, "end": 1511.96, "word": " use", "probability": 0.8388671875 }, { "start": 1511.96, "end": 1512.12, "word": " our", "probability": 0.7900390625 }, { "start": 1512.12, "end": 1512.76, "word": " vectorizers", "probability": 0.92724609375 }, { "start": 1512.76, "end": 1513.32, "word": ".", "probability": 0.41943359375 } ] }, { "id": 659, "seek": 151598, "start": 1513.32, "end": 1515.46, "text": " And we'll explain what the vectorizers do,", "tokens": [ 50664, 400, 321, 603, 2903, 437, 264, 8062, 22525, 360, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.19844980009897487, "compression_ratio": 1.7448559670781894, "no_speech_prob": 0.0087127685546875, "words": [ { "start": 1513.32, "end": 1513.46, "word": " And", "probability": 0.6533203125 }, { "start": 1513.46, "end": 1513.78, "word": " we'll", "probability": 0.919189453125 }, { "start": 1513.78, "end": 1514.1, "word": " explain", "probability": 0.814453125 }, { "start": 1514.1, "end": 1514.26, "word": " what", "probability": 0.88623046875 }, { "start": 1514.26, "end": 1514.38, "word": " the", "probability": 0.80712890625 }, { "start": 1514.38, "end": 1514.96, "word": " vectorizers", "probability": 0.9462890625 }, { "start": 1514.96, "end": 1515.34, "word": " do", "probability": 0.90234375 }, { "start": 1515.34, "end": 1515.46, "word": ",", "probability": 0.63037109375 } ] }, { "id": 660, "seek": 151598, "start": 1515.46, "end": 1516.94, "text": " but we're going to take a look at", "tokens": [ 50764, 457, 321, 434, 516, 281, 747, 257, 574, 412, 50814 ], "temperature": 0.0, "avg_logprob": -0.19844980009897487, "compression_ratio": 1.7448559670781894, "no_speech_prob": 0.0087127685546875, "words": [ { "start": 1515.46, "end": 1515.58, "word": " but", "probability": 0.8935546875 }, { "start": 1515.58, "end": 1515.74, "word": " we're", "probability": 0.92724609375 }, { "start": 1515.74, "end": 1515.84, "word": " going", "probability": 0.78759765625 }, { "start": 1515.84, "end": 1516.32, "word": " to", "probability": 0.90087890625 }, { "start": 1516.32, "end": 1516.56, "word": " take", "probability": 0.80126953125 }, { "start": 1516.66, "end": 1516.76, "word": " a look", "probability": 0.91748046875 }, { "start": 1516.76, "end": 1516.94, "word": " at", "probability": 0.9072265625 } ] }, { "id": 661, "seek": 151598, "start": 1516.94, "end": 1519.06, "text": " both of the TF-IDF vectorizer", "tokens": [ 50864, 1293, 295, 264, 40964, 12, 2777, 37, 8062, 6545, 50914 ], "temperature": 0.0, "avg_logprob": -0.19844980009897487, "compression_ratio": 1.7448559670781894, "no_speech_prob": 0.0087127685546875, "words": [ { "start": 1516.94, "end": 1517.3, "word": " both", "probability": 0.81982421875 }, { "start": 1517.3, "end": 1517.5, "word": " of", "probability": 0.658203125 }, { "start": 1517.5, "end": 1517.88, "word": " the", "probability": 0.767578125 }, { "start": 1517.88, "end": 1518.16, "word": " TF", "probability": 0.671875 }, { "start": 1518.16, "end": 1518.54, "word": "-IDF", "probability": 0.9290364583333334 }, { "start": 1518.54, "end": 1519.06, "word": " vectorizer", "probability": 0.90576171875 } ] }, { "id": 662, "seek": 151598, "start": 1519.06, "end": 1520.32, "text": " and the count vectorizer", "tokens": [ 50964, 293, 264, 1207, 8062, 6545, 51014 ], "temperature": 0.0, "avg_logprob": -0.19844980009897487, "compression_ratio": 1.7448559670781894, "no_speech_prob": 0.0087127685546875, "words": [ { "start": 1519.06, "end": 1519.3, "word": " and", "probability": 0.84716796875 }, { "start": 1519.3, "end": 1519.46, "word": " the", "probability": 0.8037109375 }, { "start": 1519.46, "end": 1519.68, "word": " count", "probability": 0.60498046875 }, { "start": 1519.68, "end": 1520.32, "word": " vectorizer", "probability": 0.96630859375 } ] }, { "id": 663, "seek": 151598, "start": 1520.32, "end": 1523.16, "text": " because they operate", "tokens": [ 51064, 570, 436, 9651, 51114 ], "temperature": 0.0, "avg_logprob": -0.19844980009897487, "compression_ratio": 1.7448559670781894, "no_speech_prob": 0.0087127685546875, "words": [ { "start": 1520.32, "end": 1521.2, "word": " because", "probability": 0.326416015625 }, { "start": 1521.2, "end": 1522.8, "word": " they", "probability": 0.68701171875 }, { "start": 1522.8, "end": 1523.16, "word": " operate", "probability": 0.765625 } ] }, { "id": 664, "seek": 151598, "start": 1523.16, "end": 1524.14, "text": " slightly different.", "tokens": [ 51164, 4748, 819, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.19844980009897487, "compression_ratio": 1.7448559670781894, "no_speech_prob": 0.0087127685546875, "words": [ { "start": 1523.16, "end": 1523.52, "word": " slightly", "probability": 0.79248046875 }, { "start": 1523.52, "end": 1523.98, "word": " different", "probability": 0.58056640625 }, { "start": 1523.98, "end": 1524.14, "word": ".", "probability": 0.90966796875 } ] }, { "id": 665, "seek": 151598, "start": 1524.14, "end": 1526.58, "text": " Count vectorizer just takes a straight word count", "tokens": [ 51264, 5247, 8062, 6545, 445, 2516, 257, 2997, 1349, 1207, 51314 ], "temperature": 0.0, "avg_logprob": -0.19844980009897487, "compression_ratio": 1.7448559670781894, "no_speech_prob": 0.0087127685546875, "words": [ { "start": 1524.14, "end": 1524.34, "word": " Count", "probability": 0.68701171875 }, { "start": 1524.34, "end": 1524.82, "word": " vectorizer", "probability": 0.9150390625 }, { "start": 1524.82, "end": 1525.36, "word": " just", "probability": 0.86328125 }, { "start": 1525.36, "end": 1525.7, "word": " takes", "probability": 0.74609375 }, { "start": 1525.9, "end": 1526.12, "word": " a straight", "probability": 0.82666015625 }, { "start": 1526.12, "end": 1526.36, "word": " word", "probability": 0.8310546875 }, { "start": 1526.36, "end": 1526.58, "word": " count", "probability": 0.80078125 } ] }, { "id": 666, "seek": 151598, "start": 1526.58, "end": 1529.3, "text": " like we did with our pen and paper example.", "tokens": [ 51364, 411, 321, 630, 365, 527, 3435, 293, 3035, 1365, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.19844980009897487, "compression_ratio": 1.7448559670781894, "no_speech_prob": 0.0087127685546875, "words": [ { "start": 1526.58, "end": 1526.76, "word": " like", "probability": 0.66748046875 }, { "start": 1526.76, "end": 1526.88, "word": " we", "probability": 0.89697265625 }, { "start": 1526.88, "end": 1527.0, "word": " did", "probability": 0.8984375 }, { "start": 1527.0, "end": 1527.14, "word": " with", "probability": 0.8134765625 }, { "start": 1527.14, "end": 1527.42, "word": " our", "probability": 0.8046875 }, { "start": 1527.42, "end": 1527.9, "word": " pen", "probability": 0.8818359375 }, { "start": 1527.9, "end": 1528.04, "word": " and", "probability": 0.80859375 }, { "start": 1528.04, "end": 1528.32, "word": " paper", "probability": 0.7861328125 }, { "start": 1528.32, "end": 1528.82, "word": " example", "probability": 0.923828125 }, { "start": 1528.82, "end": 1529.3, "word": ".", "probability": 0.57470703125 } ] }, { "id": 667, "seek": 151598, "start": 1529.3, "end": 1530.76, "text": " And then TF-IDF actually takes", "tokens": [ 51464, 400, 550, 40964, 12, 2777, 37, 767, 2516, 51514 ], "temperature": 0.0, "avg_logprob": -0.19844980009897487, "compression_ratio": 1.7448559670781894, "no_speech_prob": 0.0087127685546875, "words": [ { "start": 1529.3, "end": 1529.34, "word": " And", "probability": 0.626953125 }, { "start": 1529.34, "end": 1529.46, "word": " then", "probability": 0.71875 }, { "start": 1529.46, "end": 1529.72, "word": " TF", "probability": 0.8662109375 }, { "start": 1529.72, "end": 1530.2, "word": "-IDF", "probability": 0.9864908854166666 }, { "start": 1530.2, "end": 1530.48, "word": " actually", "probability": 0.7890625 }, { "start": 1530.48, "end": 1530.76, "word": " takes", "probability": 0.72802734375 } ] }, { "id": 668, "seek": 151598, "start": 1530.76, "end": 1532.04, "text": " all of the words into account", "tokens": [ 51564, 439, 295, 264, 2283, 666, 2696, 51614 ], "temperature": 0.0, "avg_logprob": -0.19844980009897487, "compression_ratio": 1.7448559670781894, "no_speech_prob": 0.0087127685546875, "words": [ { "start": 1530.76, "end": 1531.0, "word": " all", "probability": 0.90087890625 }, { "start": 1531.0, "end": 1531.12, "word": " of", "probability": 0.8896484375 }, { "start": 1531.12, "end": 1531.22, "word": " the", "probability": 0.8115234375 }, { "start": 1531.22, "end": 1531.42, "word": " words", "probability": 0.72900390625 }, { "start": 1531.42, "end": 1531.58, "word": " into", "probability": 0.7353515625 }, { "start": 1531.58, "end": 1532.04, "word": " account", "probability": 0.7646484375 } ] }, { "id": 669, "seek": 151598, "start": 1532.04, "end": 1534.68, "text": " and gives them a weight.", "tokens": [ 51664, 293, 2709, 552, 257, 3364, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.19844980009897487, "compression_ratio": 1.7448559670781894, "no_speech_prob": 0.0087127685546875, "words": [ { "start": 1532.04, "end": 1532.78, "word": " and", "probability": 0.85400390625 }, { "start": 1532.78, "end": 1533.1, "word": " gives", "probability": 0.8369140625 }, { "start": 1533.1, "end": 1533.4, "word": " them", "probability": 0.7314453125 }, { "start": 1533.66, "end": 1534.12, "word": " a weight", "probability": 0.859375 }, { "start": 1534.12, "end": 1534.68, "word": ".", "probability": 0.9912109375 } ] }, { "id": 670, "seek": 154294, "start": 1535.8, "end": 1536.6, "text": " Scikit-learn,", "tokens": [ 50414, 16942, 22681, 12, 306, 1083, 11, 50464 ], "temperature": 0.0, "avg_logprob": -0.18715784584518766, "compression_ratio": 1.8150943396226416, "no_speech_prob": 0.00011771917343139648, "words": [ { "start": 1535.8, "end": 1536.24, "word": " Scikit", "probability": 0.513824462890625 }, { "start": 1536.24, "end": 1536.48, "word": "-learn", "probability": 0.9015299479166666 }, { "start": 1536.48, "end": 1536.6, "word": ",", "probability": 0.3212890625 } ] }, { "id": 671, "seek": 154294, "start": 1536.6, "end": 1539.48, "text": " we're going to use logistic regression", "tokens": [ 50514, 321, 434, 516, 281, 764, 3565, 3142, 24590, 50564 ], "temperature": 0.0, "avg_logprob": -0.18715784584518766, "compression_ratio": 1.8150943396226416, "no_speech_prob": 0.00011771917343139648, "words": [ { "start": 1536.6, "end": 1537.42, "word": " we're", "probability": 0.88623046875 }, { "start": 1537.42, "end": 1537.62, "word": " going", "probability": 0.85791015625 }, { "start": 1537.62, "end": 1537.98, "word": " to", "probability": 0.90625 }, { "start": 1537.98, "end": 1538.7, "word": " use", "probability": 0.828125 }, { "start": 1538.7, "end": 1539.1, "word": " logistic", "probability": 0.9091796875 }, { "start": 1539.1, "end": 1539.48, "word": " regression", "probability": 0.87255859375 } ] }, { "id": 672, "seek": 154294, "start": 1539.48, "end": 1541.06, "text": " and multinomial naivetation.", "tokens": [ 50614, 293, 45872, 47429, 1667, 592, 302, 399, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.18715784584518766, "compression_ratio": 1.8150943396226416, "no_speech_prob": 0.00011771917343139648, "words": [ { "start": 1539.48, "end": 1539.64, "word": " and", "probability": 0.8359375 }, { "start": 1539.64, "end": 1540.14, "word": " multinomial", "probability": 0.906005859375 }, { "start": 1540.14, "end": 1540.82, "word": " naivetation", "probability": 0.60089111328125 }, { "start": 1540.82, "end": 1541.06, "word": ".", "probability": 0.5654296875 } ] }, { "id": 673, "seek": 154294, "start": 1541.06, "end": 1542.46, "text": " And the reason why we're going to use both of these", "tokens": [ 50714, 400, 264, 1778, 983, 321, 434, 516, 281, 764, 1293, 295, 613, 50764 ], "temperature": 0.0, "avg_logprob": -0.18715784584518766, "compression_ratio": 1.8150943396226416, "no_speech_prob": 0.00011771917343139648, "words": [ { "start": 1541.06, "end": 1541.08, "word": " And", "probability": 0.646484375 }, { "start": 1541.08, "end": 1541.18, "word": " the", "probability": 0.81103515625 }, { "start": 1541.18, "end": 1541.36, "word": " reason", "probability": 0.9111328125 }, { "start": 1541.36, "end": 1541.52, "word": " why", "probability": 0.78662109375 }, { "start": 1541.52, "end": 1541.66, "word": " we're", "probability": 0.922607421875 }, { "start": 1541.66, "end": 1541.74, "word": " going", "probability": 0.583984375 }, { "start": 1541.74, "end": 1541.78, "word": " to", "probability": 0.90625 }, { "start": 1541.78, "end": 1541.92, "word": " use", "probability": 0.81494140625 }, { "start": 1541.92, "end": 1542.16, "word": " both", "probability": 0.80029296875 }, { "start": 1542.16, "end": 1542.3, "word": " of", "probability": 0.9052734375 }, { "start": 1542.3, "end": 1542.46, "word": " these", "probability": 0.7080078125 } ] }, { "id": 674, "seek": 154294, "start": 1542.46, "end": 1544.04, "text": " is because we don't actually know", "tokens": [ 50814, 307, 570, 321, 500, 380, 767, 458, 50864 ], "temperature": 0.0, "avg_logprob": -0.18715784584518766, "compression_ratio": 1.8150943396226416, "no_speech_prob": 0.00011771917343139648, "words": [ { "start": 1542.46, "end": 1542.6, "word": " is", "probability": 0.85546875 }, { "start": 1542.6, "end": 1542.84, "word": " because", "probability": 0.8134765625 }, { "start": 1542.84, "end": 1543.06, "word": " we", "probability": 0.90283203125 }, { "start": 1543.06, "end": 1543.34, "word": " don't", "probability": 0.947998046875 }, { "start": 1543.34, "end": 1543.74, "word": " actually", "probability": 0.763671875 }, { "start": 1543.74, "end": 1544.04, "word": " know", "probability": 0.810546875 } ] }, { "id": 675, "seek": 154294, "start": 1544.04, "end": 1546.14, "text": " which one's going to perform best.", "tokens": [ 50914, 597, 472, 311, 516, 281, 2042, 1151, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.18715784584518766, "compression_ratio": 1.8150943396226416, "no_speech_prob": 0.00011771917343139648, "words": [ { "start": 1544.04, "end": 1544.24, "word": " which", "probability": 0.90966796875 }, { "start": 1544.24, "end": 1544.5, "word": " one's", "probability": 0.774169921875 }, { "start": 1544.5, "end": 1544.6, "word": " going", "probability": 0.7861328125 }, { "start": 1544.6, "end": 1544.68, "word": " to", "probability": 0.90625 }, { "start": 1544.68, "end": 1545.1, "word": " perform", "probability": 0.7841796875 }, { "start": 1545.1, "end": 1545.7, "word": " best", "probability": 0.79833984375 }, { "start": 1545.7, "end": 1546.14, "word": ".", "probability": 0.81982421875 } ] }, { "id": 676, "seek": 154294, "start": 1546.18, "end": 1547.42, "text": " And so like good data scientists,", "tokens": [ 51014, 400, 370, 411, 665, 1412, 7708, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.18715784584518766, "compression_ratio": 1.8150943396226416, "no_speech_prob": 0.00011771917343139648, "words": [ { "start": 1546.18, "end": 1546.22, "word": " And", "probability": 0.85107421875 }, { "start": 1546.22, "end": 1546.42, "word": " so", "probability": 0.9013671875 }, { "start": 1546.42, "end": 1546.6, "word": " like", "probability": 0.66552734375 }, { "start": 1546.6, "end": 1546.78, "word": " good", "probability": 0.8671875 }, { "start": 1546.78, "end": 1547.0, "word": " data", "probability": 0.82763671875 }, { "start": 1547.0, "end": 1547.4, "word": " scientists", "probability": 0.72119140625 }, { "start": 1547.4, "end": 1547.42, "word": ",", "probability": 0.91357421875 } ] }, { "id": 677, "seek": 154294, "start": 1547.42, "end": 1549.14, "text": " we're going to try a couple different models", "tokens": [ 51114, 321, 434, 516, 281, 853, 257, 1916, 819, 5245, 51164 ], "temperature": 0.0, "avg_logprob": -0.18715784584518766, "compression_ratio": 1.8150943396226416, "no_speech_prob": 0.00011771917343139648, "words": [ { "start": 1547.42, "end": 1547.68, "word": " we're", "probability": 0.9287109375 }, { "start": 1547.68, "end": 1547.74, "word": " going", "probability": 0.837890625 }, { "start": 1547.74, "end": 1547.82, "word": " to", "probability": 0.908203125 }, { "start": 1547.82, "end": 1548.02, "word": " try", "probability": 0.8154296875 }, { "start": 1548.16, "end": 1548.34, "word": " a couple", "probability": 0.79638671875 }, { "start": 1548.34, "end": 1548.66, "word": " different", "probability": 0.52001953125 }, { "start": 1548.66, "end": 1549.14, "word": " models", "probability": 0.79248046875 } ] }, { "id": 678, "seek": 154294, "start": 1549.14, "end": 1551.16, "text": " and take the one that performs best", "tokens": [ 51214, 293, 747, 264, 472, 300, 26213, 1151, 51264 ], "temperature": 0.0, "avg_logprob": -0.18715784584518766, "compression_ratio": 1.8150943396226416, "no_speech_prob": 0.00011771917343139648, "words": [ { "start": 1549.14, "end": 1549.66, "word": " and", "probability": 0.82861328125 }, { "start": 1549.66, "end": 1549.88, "word": " take", "probability": 0.82373046875 }, { "start": 1549.88, "end": 1550.02, "word": " the", "probability": 0.81298828125 }, { "start": 1550.02, "end": 1550.22, "word": " one", "probability": 0.82421875 }, { "start": 1550.22, "end": 1550.4, "word": " that", "probability": 0.8828125 }, { "start": 1550.4, "end": 1550.78, "word": " performs", "probability": 0.7578125 }, { "start": 1550.78, "end": 1551.16, "word": " best", "probability": 0.8046875 } ] }, { "id": 679, "seek": 154294, "start": 1551.16, "end": 1552.96, "text": " with the problem set that we have.", "tokens": [ 51314, 365, 264, 1154, 992, 300, 321, 362, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.18715784584518766, "compression_ratio": 1.8150943396226416, "no_speech_prob": 0.00011771917343139648, "words": [ { "start": 1551.16, "end": 1551.3, "word": " with", "probability": 0.8154296875 }, { "start": 1551.3, "end": 1551.42, "word": " the", "probability": 0.77392578125 }, { "start": 1551.42, "end": 1551.68, "word": " problem", "probability": 0.7578125 }, { "start": 1551.68, "end": 1551.86, "word": " set", "probability": 0.88623046875 }, { "start": 1551.86, "end": 1552.02, "word": " that", "probability": 0.8779296875 }, { "start": 1552.02, "end": 1552.12, "word": " we", "probability": 0.90673828125 }, { "start": 1552.12, "end": 1552.52, "word": " have", "probability": 0.87939453125 }, { "start": 1552.52, "end": 1552.96, "word": ".", "probability": 0.98583984375 } ] }, { "id": 680, "seek": 154294, "start": 1553.56, "end": 1555.78, "text": " And then for a couple metric", "tokens": [ 51414, 400, 550, 337, 257, 1916, 20678, 51464 ], "temperature": 0.0, "avg_logprob": -0.18715784584518766, "compression_ratio": 1.8150943396226416, "no_speech_prob": 0.00011771917343139648, "words": [ { "start": 1553.56, "end": 1553.66, "word": " And", "probability": 0.875 }, { "start": 1553.66, "end": 1553.8, "word": " then", "probability": 0.7255859375 }, { "start": 1553.8, "end": 1553.94, "word": " for", "probability": 0.87548828125 }, { "start": 1554.08, "end": 1554.32, "word": " a couple", "probability": 0.7841796875 }, { "start": 1554.32, "end": 1555.78, "word": " metric", "probability": 0.54052734375 } ] }, { "id": 681, "seek": 154294, "start": 1555.78, "end": 1557.14, "text": " and visualizations,", "tokens": [ 51514, 293, 5056, 14455, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.18715784584518766, "compression_ratio": 1.8150943396226416, "no_speech_prob": 0.00011771917343139648, "words": [ { "start": 1555.78, "end": 1556.26, "word": " and", "probability": 0.8759765625 }, { "start": 1556.26, "end": 1556.92, "word": " visualizations", "probability": 0.947509765625 }, { "start": 1556.92, "end": 1557.14, "word": ",", "probability": 0.8798828125 } ] }, { "id": 682, "seek": 154294, "start": 1557.14, "end": 1558.8, "text": " we're going to use the Scikit-learn", "tokens": [ 51614, 321, 434, 516, 281, 764, 264, 16942, 22681, 12, 306, 1083, 51664 ], "temperature": 0.0, "avg_logprob": -0.18715784584518766, "compression_ratio": 1.8150943396226416, "no_speech_prob": 0.00011771917343139648, "words": [ { "start": 1557.14, "end": 1557.26, "word": " we're", "probability": 0.927490234375 }, { "start": 1557.26, "end": 1557.32, "word": " going", "probability": 0.8193359375 }, { "start": 1557.32, "end": 1557.74, "word": " to", "probability": 0.90576171875 }, { "start": 1557.74, "end": 1558.06, "word": " use", "probability": 0.8193359375 }, { "start": 1558.06, "end": 1558.3, "word": " the", "probability": 0.79931640625 }, { "start": 1558.3, "end": 1558.54, "word": " Scikit", "probability": 0.627197265625 }, { "start": 1558.54, "end": 1558.8, "word": "-learn", "probability": 0.9588216145833334 } ] }, { "id": 683, "seek": 154294, "start": 1558.8, "end": 1561.64, "text": " confusion matrix and classification report.", "tokens": [ 51714, 15075, 8141, 293, 21538, 2275, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.18715784584518766, "compression_ratio": 1.8150943396226416, "no_speech_prob": 0.00011771917343139648, "words": [ { "start": 1558.8, "end": 1559.26, "word": " confusion", "probability": 0.7744140625 }, { "start": 1559.26, "end": 1559.62, "word": " matrix", "probability": 0.841796875 }, { "start": 1559.62, "end": 1560.02, "word": " and", "probability": 0.89111328125 }, { "start": 1560.02, "end": 1560.58, "word": " classification", "probability": 0.9228515625 }, { "start": 1560.58, "end": 1561.2, "word": " report", "probability": 0.8466796875 }, { "start": 1561.2, "end": 1561.64, "word": ".", "probability": 0.99755859375 } ] }, { "id": 684, "seek": 156784, "start": 1563.04, "end": 1564.06, "text": " So I'm going to go ahead", "tokens": [ 50414, 407, 286, 478, 516, 281, 352, 2286, 50464 ], "temperature": 0.0, "avg_logprob": -0.14534883720930233, "compression_ratio": 1.7179487179487178, "no_speech_prob": 0.0003514289855957031, "words": [ { "start": 1563.04, "end": 1563.42, "word": " So", "probability": 0.334228515625 }, { "start": 1563.42, "end": 1563.6, "word": " I'm", "probability": 0.904052734375 }, { "start": 1563.6, "end": 1563.64, "word": " going", "probability": 0.5234375 }, { "start": 1563.64, "end": 1563.66, "word": " to", "probability": 0.90234375 }, { "start": 1563.66, "end": 1563.76, "word": " go", "probability": 0.86572265625 }, { "start": 1563.76, "end": 1564.06, "word": " ahead", "probability": 0.84765625 } ] }, { "id": 685, "seek": 156784, "start": 1564.06, "end": 1565.2, "text": " and press Shift-Enter", "tokens": [ 50514, 293, 1886, 28304, 12, 16257, 391, 50564 ], "temperature": 0.0, "avg_logprob": -0.14534883720930233, "compression_ratio": 1.7179487179487178, "no_speech_prob": 0.0003514289855957031, "words": [ { "start": 1564.06, "end": 1564.2, "word": " and", "probability": 0.43505859375 }, { "start": 1564.2, "end": 1564.42, "word": " press", "probability": 0.71240234375 }, { "start": 1564.42, "end": 1564.8, "word": " Shift", "probability": 0.2432861328125 }, { "start": 1564.8, "end": 1565.2, "word": "-Enter", "probability": 0.6665852864583334 } ] }, { "id": 686, "seek": 156784, "start": 1565.2, "end": 1566.24, "text": " and that's going to run.", "tokens": [ 50614, 293, 300, 311, 516, 281, 1190, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.14534883720930233, "compression_ratio": 1.7179487179487178, "no_speech_prob": 0.0003514289855957031, "words": [ { "start": 1565.2, "end": 1565.44, "word": " and", "probability": 0.51904296875 }, { "start": 1565.44, "end": 1565.64, "word": " that's", "probability": 0.919921875 }, { "start": 1565.64, "end": 1565.74, "word": " going", "probability": 0.8037109375 }, { "start": 1565.74, "end": 1565.84, "word": " to", "probability": 0.9013671875 }, { "start": 1565.84, "end": 1566.08, "word": " run", "probability": 0.8935546875 }, { "start": 1566.08, "end": 1566.24, "word": ".", "probability": 0.8017578125 } ] }, { "id": 687, "seek": 156784, "start": 1566.24, "end": 1568.36, "text": " You will see libraries imported", "tokens": [ 50714, 509, 486, 536, 15148, 25524, 50764 ], "temperature": 0.0, "avg_logprob": -0.14534883720930233, "compression_ratio": 1.7179487179487178, "no_speech_prob": 0.0003514289855957031, "words": [ { "start": 1566.24, "end": 1566.32, "word": " You", "probability": 0.8701171875 }, { "start": 1566.32, "end": 1566.46, "word": " will", "probability": 0.73876953125 }, { "start": 1566.46, "end": 1566.76, "word": " see", "probability": 0.8076171875 }, { "start": 1566.76, "end": 1567.26, "word": " libraries", "probability": 0.211669921875 }, { "start": 1567.26, "end": 1568.36, "word": " imported", "probability": 0.56396484375 } ] }, { "id": 688, "seek": 156784, "start": 1568.36, "end": 1569.96, "text": " once that's complete.", "tokens": [ 50814, 1564, 300, 311, 3566, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.14534883720930233, "compression_ratio": 1.7179487179487178, "no_speech_prob": 0.0003514289855957031, "words": [ { "start": 1568.36, "end": 1568.96, "word": " once", "probability": 0.71484375 }, { "start": 1568.96, "end": 1569.2, "word": " that's", "probability": 0.91552734375 }, { "start": 1569.2, "end": 1569.58, "word": " complete", "probability": 0.62548828125 }, { "start": 1569.58, "end": 1569.96, "word": ".", "probability": 0.78369140625 } ] }, { "id": 689, "seek": 156784, "start": 1571.52, "end": 1573.3, "text": " And we can move on to the next thing.", "tokens": [ 50914, 400, 321, 393, 1286, 322, 281, 264, 958, 551, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.14534883720930233, "compression_ratio": 1.7179487179487178, "no_speech_prob": 0.0003514289855957031, "words": [ { "start": 1571.52, "end": 1571.9, "word": " And", "probability": 0.65869140625 }, { "start": 1571.9, "end": 1572.0, "word": " we", "probability": 0.90234375 }, { "start": 1572.0, "end": 1572.1, "word": " can", "probability": 0.87353515625 }, { "start": 1572.1, "end": 1572.24, "word": " move", "probability": 0.880859375 }, { "start": 1572.24, "end": 1572.36, "word": " on", "probability": 0.7568359375 }, { "start": 1572.36, "end": 1572.42, "word": " to", "probability": 0.9033203125 }, { "start": 1572.42, "end": 1572.54, "word": " the", "probability": 0.81005859375 }, { "start": 1572.54, "end": 1572.68, "word": " next", "probability": 0.86376953125 }, { "start": 1572.68, "end": 1572.92, "word": " thing", "probability": 0.796875 }, { "start": 1572.92, "end": 1573.3, "word": ".", "probability": 0.98046875 } ] }, { "id": 690, "seek": 156784, "start": 1573.62, "end": 1574.7, "text": " So this is our test email.", "tokens": [ 51014, 407, 341, 307, 527, 1500, 3796, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.14534883720930233, "compression_ratio": 1.7179487179487178, "no_speech_prob": 0.0003514289855957031, "words": [ { "start": 1573.62, "end": 1573.76, "word": " So", "probability": 0.77587890625 }, { "start": 1573.76, "end": 1573.94, "word": " this", "probability": 0.86962890625 }, { "start": 1573.94, "end": 1574.02, "word": " is", "probability": 0.90625 }, { "start": 1574.02, "end": 1574.16, "word": " our", "probability": 0.79833984375 }, { "start": 1574.16, "end": 1574.36, "word": " test", "probability": 0.80615234375 }, { "start": 1574.36, "end": 1574.6, "word": " email", "probability": 0.87646484375 }, { "start": 1574.6, "end": 1574.7, "word": ".", "probability": 0.73046875 } ] }, { "id": 691, "seek": 156784, "start": 1574.7, "end": 1575.84, "text": " This is the exact same email", "tokens": [ 51114, 639, 307, 264, 1900, 912, 3796, 51164 ], "temperature": 0.0, "avg_logprob": -0.14534883720930233, "compression_ratio": 1.7179487179487178, "no_speech_prob": 0.0003514289855957031, "words": [ { "start": 1574.7, "end": 1574.82, "word": " This", "probability": 0.8076171875 }, { "start": 1574.82, "end": 1574.92, "word": " is", "probability": 0.90283203125 }, { "start": 1574.92, "end": 1575.02, "word": " the", "probability": 0.8095703125 }, { "start": 1575.02, "end": 1575.3, "word": " exact", "probability": 0.87255859375 }, { "start": 1575.3, "end": 1575.58, "word": " same", "probability": 0.80419921875 }, { "start": 1575.58, "end": 1575.84, "word": " email", "probability": 0.91259765625 } ] }, { "id": 692, "seek": 156784, "start": 1575.84, "end": 1577.76, "text": " that we saw in the slides.", "tokens": [ 51214, 300, 321, 1866, 294, 264, 9788, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.14534883720930233, "compression_ratio": 1.7179487179487178, "no_speech_prob": 0.0003514289855957031, "words": [ { "start": 1575.84, "end": 1576.1, "word": " that", "probability": 0.83984375 }, { "start": 1576.1, "end": 1576.22, "word": " we", "probability": 0.90234375 }, { "start": 1576.22, "end": 1576.56, "word": " saw", "probability": 0.81982421875 }, { "start": 1576.56, "end": 1576.78, "word": " in", "probability": 0.90087890625 }, { "start": 1576.78, "end": 1576.94, "word": " the", "probability": 0.80712890625 }, { "start": 1576.94, "end": 1577.38, "word": " slides", "probability": 0.90966796875 }, { "start": 1577.38, "end": 1577.76, "word": ".", "probability": 0.96337890625 } ] }, { "id": 693, "seek": 156784, "start": 1577.98, "end": 1579.44, "text": " So as I mentioned earlier,", "tokens": [ 51314, 407, 382, 286, 2835, 3071, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.14534883720930233, "compression_ratio": 1.7179487179487178, "no_speech_prob": 0.0003514289855957031, "words": [ { "start": 1577.98, "end": 1578.18, "word": " So", "probability": 0.78076171875 }, { "start": 1578.18, "end": 1578.86, "word": " as", "probability": 0.60498046875 }, { "start": 1578.86, "end": 1578.94, "word": " I", "probability": 0.99072265625 }, { "start": 1578.94, "end": 1579.12, "word": " mentioned", "probability": 0.7744140625 }, { "start": 1579.12, "end": 1579.38, "word": " earlier", "probability": 0.91064453125 }, { "start": 1579.38, "end": 1579.44, "word": ",", "probability": 0.79296875 } ] }, { "id": 694, "seek": 156784, "start": 1579.44, "end": 1580.5, "text": " we're going to use this email", "tokens": [ 51414, 321, 434, 516, 281, 764, 341, 3796, 51464 ], "temperature": 0.0, "avg_logprob": -0.14534883720930233, "compression_ratio": 1.7179487179487178, "no_speech_prob": 0.0003514289855957031, "words": [ { "start": 1579.44, "end": 1579.58, "word": " we're", "probability": 0.904541015625 }, { "start": 1579.58, "end": 1579.7, "word": " going", "probability": 0.85595703125 }, { "start": 1579.7, "end": 1579.8, "word": " to", "probability": 0.90673828125 }, { "start": 1579.8, "end": 1579.98, "word": " use", "probability": 0.8232421875 }, { "start": 1579.98, "end": 1580.16, "word": " this", "probability": 0.8798828125 }, { "start": 1580.16, "end": 1580.5, "word": " email", "probability": 0.91162109375 } ] }, { "id": 695, "seek": 156784, "start": 1580.5, "end": 1582.88, "text": " to see how it's transformed", "tokens": [ 51514, 281, 536, 577, 309, 311, 16894, 51564 ], "temperature": 0.0, "avg_logprob": -0.14534883720930233, "compression_ratio": 1.7179487179487178, "no_speech_prob": 0.0003514289855957031, "words": [ { "start": 1580.5, "end": 1580.94, "word": " to", "probability": 0.900390625 }, { "start": 1580.94, "end": 1581.5, "word": " see", "probability": 0.80615234375 }, { "start": 1581.5, "end": 1582.16, "word": " how", "probability": 0.89892578125 }, { "start": 1582.16, "end": 1582.38, "word": " it's", "probability": 0.9267578125 }, { "start": 1582.38, "end": 1582.88, "word": " transformed", "probability": 0.8046875 } ] }, { "id": 696, "seek": 156784, "start": 1582.88, "end": 1585.04, "text": " at every step of preprocessing.", "tokens": [ 51614, 412, 633, 1823, 295, 2666, 340, 780, 278, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.14534883720930233, "compression_ratio": 1.7179487179487178, "no_speech_prob": 0.0003514289855957031, "words": [ { "start": 1582.88, "end": 1583.14, "word": " at", "probability": 0.59765625 }, { "start": 1583.14, "end": 1583.4, "word": " every", "probability": 0.74462890625 }, { "start": 1583.4, "end": 1583.72, "word": " step", "probability": 0.81103515625 }, { "start": 1583.72, "end": 1584.06, "word": " of", "probability": 0.9013671875 }, { "start": 1584.06, "end": 1584.98, "word": " preprocessing", "probability": 0.85968017578125 }, { "start": 1584.98, "end": 1585.04, "word": ".", "probability": 0.87939453125 } ] }, { "id": 697, "seek": 156784, "start": 1585.04, "end": 1586.54, "text": " So I'm going to go ahead and run that.", "tokens": [ 51714, 407, 286, 478, 516, 281, 352, 2286, 293, 1190, 300, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.14534883720930233, "compression_ratio": 1.7179487179487178, "no_speech_prob": 0.0003514289855957031, "words": [ { "start": 1585.04, "end": 1585.12, "word": " So", "probability": 0.86669921875 }, { "start": 1585.12, "end": 1585.22, "word": " I'm", "probability": 0.983642578125 }, { "start": 1585.22, "end": 1585.28, "word": " going", "probability": 0.8359375 }, { "start": 1585.28, "end": 1585.32, "word": " to", "probability": 0.9033203125 }, { "start": 1585.32, "end": 1585.42, "word": " go", "probability": 0.8974609375 }, { "start": 1585.42, "end": 1585.58, "word": " ahead", "probability": 0.8564453125 }, { "start": 1585.58, "end": 1585.7, "word": " and", "probability": 0.8984375 }, { "start": 1585.7, "end": 1585.88, "word": " run", "probability": 0.8955078125 }, { "start": 1585.88, "end": 1586.16, "word": " that", "probability": 0.88330078125 }, { "start": 1586.16, "end": 1586.54, "word": ".", "probability": 0.92919921875 } ] }, { "id": 698, "seek": 159784, "start": 1587.98, "end": 1590.0, "text": " And then this is our tokenizer function.", "tokens": [ 50414, 400, 550, 341, 307, 527, 14862, 6545, 2445, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.18205493158011726, "compression_ratio": 2.02262443438914, "no_speech_prob": 6.920099258422852e-05, "words": [ { "start": 1587.98, "end": 1588.44, "word": " And", "probability": 0.173095703125 }, { "start": 1588.44, "end": 1588.56, "word": " then", "probability": 0.66650390625 }, { "start": 1588.56, "end": 1588.72, "word": " this", "probability": 0.82373046875 }, { "start": 1588.72, "end": 1588.82, "word": " is", "probability": 0.900390625 }, { "start": 1588.82, "end": 1588.96, "word": " our", "probability": 0.7890625 }, { "start": 1588.96, "end": 1589.36, "word": " tokenizer", "probability": 0.7763671875 }, { "start": 1589.36, "end": 1589.78, "word": " function", "probability": 0.86376953125 }, { "start": 1589.78, "end": 1590.0, "word": ".", "probability": 0.90234375 } ] }, { "id": 699, "seek": 159784, "start": 1590.0, "end": 1592.26, "text": " Tokenizer functions will allow us", "tokens": [ 50564, 314, 8406, 6545, 6828, 486, 2089, 505, 50614 ], "temperature": 0.0, "avg_logprob": -0.18205493158011726, "compression_ratio": 2.02262443438914, "no_speech_prob": 6.920099258422852e-05, "words": [ { "start": 1590.0, "end": 1590.36, "word": " Tokenizer", "probability": 0.912109375 }, { "start": 1590.36, "end": 1590.98, "word": " functions", "probability": 0.8544921875 }, { "start": 1590.98, "end": 1591.68, "word": " will", "probability": 0.787109375 }, { "start": 1591.68, "end": 1592.04, "word": " allow", "probability": 0.86865234375 }, { "start": 1592.04, "end": 1592.26, "word": " us", "probability": 0.90478515625 } ] }, { "id": 700, "seek": 159784, "start": 1592.26, "end": 1593.5, "text": " to pull out the keywords", "tokens": [ 50664, 281, 2235, 484, 264, 21009, 50714 ], "temperature": 0.0, "avg_logprob": -0.18205493158011726, "compression_ratio": 2.02262443438914, "no_speech_prob": 6.920099258422852e-05, "words": [ { "start": 1592.26, "end": 1592.4, "word": " to", "probability": 0.89501953125 }, { "start": 1592.4, "end": 1592.66, "word": " pull", "probability": 0.814453125 }, { "start": 1592.66, "end": 1592.84, "word": " out", "probability": 0.80029296875 }, { "start": 1592.84, "end": 1593.02, "word": " the", "probability": 0.80322265625 }, { "start": 1593.02, "end": 1593.5, "word": " keywords", "probability": 0.44287109375 } ] }, { "id": 701, "seek": 159784, "start": 1593.5, "end": 1595.62, "text": " in the way that we would like them", "tokens": [ 50764, 294, 264, 636, 300, 321, 576, 411, 552, 50814 ], "temperature": 0.0, "avg_logprob": -0.18205493158011726, "compression_ratio": 2.02262443438914, "no_speech_prob": 6.920099258422852e-05, "words": [ { "start": 1593.5, "end": 1594.12, "word": " in", "probability": 0.83837890625 }, { "start": 1594.12, "end": 1594.38, "word": " the", "probability": 0.8037109375 }, { "start": 1594.38, "end": 1594.66, "word": " way", "probability": 0.892578125 }, { "start": 1594.66, "end": 1594.84, "word": " that", "probability": 0.82568359375 }, { "start": 1594.84, "end": 1594.96, "word": " we", "probability": 0.904296875 }, { "start": 1594.96, "end": 1595.1, "word": " would", "probability": 0.8330078125 }, { "start": 1595.1, "end": 1595.36, "word": " like", "probability": 0.8798828125 }, { "start": 1595.36, "end": 1595.62, "word": " them", "probability": 0.73779296875 } ] }, { "id": 702, "seek": 159784, "start": 1595.62, "end": 1597.06, "text": " to be extracted.", "tokens": [ 50864, 281, 312, 34086, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.18205493158011726, "compression_ratio": 2.02262443438914, "no_speech_prob": 6.920099258422852e-05, "words": [ { "start": 1595.62, "end": 1595.82, "word": " to", "probability": 0.9052734375 }, { "start": 1595.82, "end": 1596.06, "word": " be", "probability": 0.9013671875 }, { "start": 1596.06, "end": 1596.6, "word": " extracted", "probability": 0.712890625 }, { "start": 1596.6, "end": 1597.06, "word": ".", "probability": 0.92822265625 } ] }, { "id": 703, "seek": 159784, "start": 1597.18, "end": 1598.76, "text": " So in this case, we're going to grab", "tokens": [ 50964, 407, 294, 341, 1389, 11, 321, 434, 516, 281, 4444, 51014 ], "temperature": 0.0, "avg_logprob": -0.18205493158011726, "compression_ratio": 2.02262443438914, "no_speech_prob": 6.920099258422852e-05, "words": [ { "start": 1597.18, "end": 1597.58, "word": " So", "probability": 0.80224609375 }, { "start": 1597.58, "end": 1597.68, "word": " in", "probability": 0.79296875 }, { "start": 1597.68, "end": 1597.84, "word": " this", "probability": 0.880859375 }, { "start": 1597.84, "end": 1598.08, "word": " case", "probability": 0.80908203125 }, { "start": 1598.08, "end": 1598.14, "word": ",", "probability": 0.61767578125 }, { "start": 1598.14, "end": 1598.28, "word": " we're", "probability": 0.912353515625 }, { "start": 1598.28, "end": 1598.4, "word": " going", "probability": 0.85107421875 }, { "start": 1598.4, "end": 1598.54, "word": " to", "probability": 0.90283203125 }, { "start": 1598.54, "end": 1598.76, "word": " grab", "probability": 0.77294921875 } ] }, { "id": 704, "seek": 159784, "start": 1598.76, "end": 1601.08, "text": " all the punctuation, all the stop words,", "tokens": [ 51064, 439, 264, 27006, 16073, 11, 439, 264, 1590, 2283, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.18205493158011726, "compression_ratio": 2.02262443438914, "no_speech_prob": 6.920099258422852e-05, "words": [ { "start": 1598.76, "end": 1598.94, "word": " all", "probability": 0.8984375 }, { "start": 1598.94, "end": 1599.08, "word": " the", "probability": 0.736328125 }, { "start": 1599.08, "end": 1599.7, "word": " punctuation", "probability": 0.905517578125 }, { "start": 1599.7, "end": 1600.0, "word": ",", "probability": 0.93017578125 }, { "start": 1600.0, "end": 1600.1, "word": " all", "probability": 0.8857421875 }, { "start": 1600.1, "end": 1600.3, "word": " the", "probability": 0.465087890625 }, { "start": 1600.3, "end": 1600.62, "word": " stop", "probability": 0.88427734375 }, { "start": 1600.62, "end": 1600.92, "word": " words", "probability": 0.60888671875 }, { "start": 1600.92, "end": 1601.08, "word": ",", "probability": 0.75927734375 } ] }, { "id": 705, "seek": 159784, "start": 1601.08, "end": 1602.48, "text": " and we're going to create a", "tokens": [ 51164, 293, 321, 434, 516, 281, 1884, 257, 51214 ], "temperature": 0.0, "avg_logprob": -0.18205493158011726, "compression_ratio": 2.02262443438914, "no_speech_prob": 6.920099258422852e-05, "words": [ { "start": 1601.08, "end": 1601.16, "word": " and", "probability": 0.8896484375 }, { "start": 1601.16, "end": 1601.3, "word": " we're", "probability": 0.923095703125 }, { "start": 1601.3, "end": 1601.36, "word": " going", "probability": 0.6953125 }, { "start": 1601.36, "end": 1601.46, "word": " to", "probability": 0.900390625 }, { "start": 1601.46, "end": 1601.74, "word": " create", "probability": 0.8388671875 }, { "start": 1602.14, "end": 1602.48, "word": " a stemmer", "probability": 0.75537109375 } ] }, { "id": 706, "seek": 159784, "start": 1602.48, "end": 1605.02, "text": " stemmer constructor.", "tokens": [ 51264, 12312, 936, 47479, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.18205493158011726, "compression_ratio": 2.02262443438914, "no_speech_prob": 6.920099258422852e-05, "words": [ { "start": 1602.48, "end": 1603.04, "word": " constructor", "probability": 0.732421875 }, { "start": 1603.04, "end": 1603.5, "word": ".", "probability": 0.97900390625 }, { "start": 1604.56, "end": 1605.02, "word": " We're", "probability": 0.928466796875 } ] }, { "id": 707, "seek": 159784, "start": 1605.02, "end": 1607.64, "text": " We're going to use these to", "tokens": [ 51364, 492, 434, 516, 281, 764, 613, 281, 51414 ], "temperature": 0.0, "avg_logprob": -0.18205493158011726, "compression_ratio": 2.02262443438914, "no_speech_prob": 6.920099258422852e-05, "words": [ { "start": 1605.02, "end": 1605.14, "word": " going", "probability": 0.8564453125 }, { "start": 1605.14, "end": 1605.3, "word": " to", "probability": 0.90625 }, { "start": 1605.3, "end": 1605.52, "word": " use", "probability": 0.81640625 }, { "start": 1605.52, "end": 1605.92, "word": " these", "probability": 0.71484375 }, { "start": 1605.92, "end": 1606.42, "word": " to", "probability": 0.8955078125 }, { "start": 1606.42, "end": 1607.4, "word": " remove", "probability": 0.8623046875 }, { "start": 1607.4, "end": 1607.64, "word": " the", "probability": 0.81201171875 } ] }, { "id": 708, "seek": 159784, "start": 1607.64, "end": 1609.26, "text": " remove the stop words from the email.", "tokens": [ 51464, 4159, 264, 1590, 2283, 490, 264, 3796, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.18205493158011726, "compression_ratio": 2.02262443438914, "no_speech_prob": 6.920099258422852e-05, "words": [ { "start": 1607.64, "end": 1607.92, "word": " stop", "probability": 0.83837890625 }, { "start": 1607.92, "end": 1608.16, "word": " words", "probability": 0.658203125 }, { "start": 1608.16, "end": 1608.36, "word": " from", "probability": 0.82470703125 }, { "start": 1608.36, "end": 1608.5, "word": " the", "probability": 0.8056640625 }, { "start": 1608.5, "end": 1608.78, "word": " email", "probability": 0.8779296875 }, { "start": 1608.78, "end": 1609.1, "word": ".", "probability": 0.63134765625 }, { "start": 1609.1, "end": 1609.26, "word": " We're", "probability": 0.929443359375 } ] }, { "id": 709, "seek": 159784, "start": 1609.26, "end": 1611.28, "text": " We're going to use these to remove", "tokens": [ 51564, 492, 434, 516, 281, 764, 613, 281, 4159, 51614 ], "temperature": 0.0, "avg_logprob": -0.18205493158011726, "compression_ratio": 2.02262443438914, "no_speech_prob": 6.920099258422852e-05, "words": [ { "start": 1609.26, "end": 1609.38, "word": " going", "probability": 0.857421875 }, { "start": 1609.38, "end": 1609.54, "word": " to", "probability": 0.90771484375 }, { "start": 1609.54, "end": 1609.74, "word": " use", "probability": 0.82568359375 }, { "start": 1609.74, "end": 1610.12, "word": " these", "probability": 0.71533203125 }, { "start": 1610.12, "end": 1610.44, "word": " to", "probability": 0.8974609375 }, { "start": 1610.44, "end": 1610.72, "word": " remove", "probability": 0.83447265625 }, { "start": 1610.72, "end": 1611.28, "word": " punctuation", "probability": 0.9091796875 } ] }, { "id": 710, "seek": 159784, "start": 1611.28, "end": 1612.38, "text": " punctuation from the email,", "tokens": [ 51664, 27006, 16073, 490, 264, 3796, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.18205493158011726, "compression_ratio": 2.02262443438914, "no_speech_prob": 6.920099258422852e-05, "words": [ { "start": 1611.28, "end": 1611.54, "word": " from", "probability": 0.8251953125 }, { "start": 1611.54, "end": 1611.68, "word": " the", "probability": 0.80859375 }, { "start": 1611.68, "end": 1612.0, "word": " email", "probability": 0.91796875 }, { "start": 1612.0, "end": 1612.12, "word": ",", "probability": 0.515625 }, { "start": 1612.12, "end": 1612.3, "word": " and", "probability": 0.8916015625 }, { "start": 1612.3, "end": 1612.38, "word": " then", "probability": 0.7197265625 } ] }, { "id": 711, "seek": 159784, "start": 1612.38, "end": 1614.12, "text": " and then we're going to stem the words.", "tokens": [ 51764, 293, 550, 321, 434, 516, 281, 12312, 264, 2283, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.18205493158011726, "compression_ratio": 2.02262443438914, "no_speech_prob": 6.920099258422852e-05, "words": [ { "start": 1612.38, "end": 1612.5, "word": " we're", "probability": 0.927001953125 }, { "start": 1612.5, "end": 1612.68, "word": " going", "probability": 0.86083984375 }, { "start": 1612.68, "end": 1612.84, "word": " to", "probability": 0.89794921875 }, { "start": 1612.84, "end": 1613.1, "word": " stem", "probability": 0.81494140625 }, { "start": 1613.1, "end": 1613.28, "word": " the", "probability": 0.80615234375 }, { "start": 1613.28, "end": 1613.66, "word": " words", "probability": 0.7158203125 }, { "start": 1613.66, "end": 1614.12, "word": ".", "probability": 0.9794921875 } ] }, { "id": 712, "seek": 162784, "start": 1616.54, "end": 1616.94, "text": " We're going to move all the words", "tokens": [ 50364, 492, 434, 516, 281, 1286, 439, 264, 2283, 50414 ], "temperature": 0.0, "avg_logprob": -0.19916044231226196, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 1616.54, "end": 1616.54, "word": " We're", "probability": 0.160797119140625 }, { "start": 1616.54, "end": 1616.54, "word": " going", "probability": 0.4443359375 }, { "start": 1616.54, "end": 1616.54, "word": " to", "probability": 0.90673828125 }, { "start": 1616.54, "end": 1616.54, "word": " move", "probability": 0.005229949951171875 }, { "start": 1616.54, "end": 1616.54, "word": " all", "probability": 0.42626953125 }, { "start": 1616.54, "end": 1616.66, "word": " the", "probability": 0.56982421875 }, { "start": 1616.66, "end": 1616.94, "word": " words", "probability": 0.58154296875 } ] }, { "id": 713, "seek": 162784, "start": 1616.94, "end": 1618.28, "text": " to lowercase so that they are", "tokens": [ 50464, 281, 3126, 9765, 370, 300, 436, 366, 50514 ], "temperature": 0.0, "avg_logprob": -0.19916044231226196, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 1616.94, "end": 1617.14, "word": " to", "probability": 0.84326171875 }, { "start": 1617.14, "end": 1617.74, "word": " lowercase", "probability": 0.683349609375 }, { "start": 1617.74, "end": 1617.94, "word": " so", "probability": 0.6396484375 }, { "start": 1617.94, "end": 1618.06, "word": " that", "probability": 0.477294921875 }, { "start": 1618.06, "end": 1618.16, "word": " they", "probability": 0.7275390625 }, { "start": 1618.16, "end": 1618.28, "word": " are", "probability": 0.7109375 } ] }, { "id": 714, "seek": 162784, "start": 1618.28, "end": 1620.1, "text": " treated exactly the same.", "tokens": [ 50564, 8668, 2293, 264, 912, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.19916044231226196, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 1618.28, "end": 1618.66, "word": " treated", "probability": 0.74951171875 }, { "start": 1618.66, "end": 1619.18, "word": " exactly", "probability": 0.6728515625 }, { "start": 1619.18, "end": 1619.42, "word": " the", "probability": 0.810546875 }, { "start": 1619.42, "end": 1619.7, "word": " same", "probability": 0.81689453125 }, { "start": 1619.7, "end": 1620.1, "word": ".", "probability": 0.919921875 } ] }, { "id": 715, "seek": 162784, "start": 1620.98, "end": 1622.1, "text": " So we're just going to go ahead", "tokens": [ 50664, 407, 321, 434, 445, 516, 281, 352, 2286, 50714 ], "temperature": 0.0, "avg_logprob": -0.19916044231226196, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 1620.98, "end": 1621.04, "word": " So", "probability": 0.2303466796875 }, { "start": 1621.04, "end": 1621.32, "word": " we're", "probability": 0.834716796875 }, { "start": 1621.32, "end": 1621.44, "word": " just", "probability": 0.8095703125 }, { "start": 1621.44, "end": 1621.6, "word": " going", "probability": 0.76171875 }, { "start": 1621.6, "end": 1621.64, "word": " to", "probability": 0.9033203125 }, { "start": 1621.64, "end": 1621.76, "word": " go", "probability": 0.8544921875 }, { "start": 1621.76, "end": 1622.1, "word": " ahead", "probability": 0.86083984375 } ] }, { "id": 716, "seek": 162784, "start": 1622.1, "end": 1623.9, "text": " and run this, shift enter,", "tokens": [ 50764, 293, 1190, 341, 11, 5513, 3242, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.19916044231226196, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 1622.1, "end": 1622.32, "word": " and", "probability": 0.890625 }, { "start": 1622.32, "end": 1622.52, "word": " run", "probability": 0.86767578125 }, { "start": 1622.52, "end": 1622.78, "word": " this", "probability": 0.88134765625 }, { "start": 1622.78, "end": 1622.9, "word": ",", "probability": 0.360107421875 }, { "start": 1622.9, "end": 1623.12, "word": " shift", "probability": 0.413330078125 }, { "start": 1623.12, "end": 1623.5, "word": " enter", "probability": 0.28076171875 }, { "start": 1623.5, "end": 1623.9, "word": ",", "probability": 0.6796875 } ] }, { "id": 717, "seek": 162784, "start": 1623.9, "end": 1625.4, "text": " and our tokenizer is defined.", "tokens": [ 50864, 293, 527, 14862, 6545, 307, 7642, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.19916044231226196, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 1623.9, "end": 1623.98, "word": " and", "probability": 0.87744140625 }, { "start": 1623.98, "end": 1624.1, "word": " our", "probability": 0.79052734375 }, { "start": 1624.1, "end": 1624.5, "word": " tokenizer", "probability": 0.82373046875 }, { "start": 1624.5, "end": 1624.68, "word": " is", "probability": 0.9013671875 }, { "start": 1624.68, "end": 1625.0, "word": " defined", "probability": 0.7294921875 }, { "start": 1625.0, "end": 1625.4, "word": ".", "probability": 0.9521484375 } ] }, { "id": 718, "seek": 162784, "start": 1625.96, "end": 1627.18, "text": " And this is where we run into", "tokens": [ 50964, 400, 341, 307, 689, 321, 1190, 666, 51014 ], "temperature": 0.0, "avg_logprob": -0.19916044231226196, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 1625.96, "end": 1626.28, "word": " And", "probability": 0.59423828125 }, { "start": 1626.28, "end": 1626.42, "word": " this", "probability": 0.88037109375 }, { "start": 1626.42, "end": 1626.54, "word": " is", "probability": 0.90380859375 }, { "start": 1626.54, "end": 1626.64, "word": " where", "probability": 0.904296875 }, { "start": 1626.64, "end": 1626.78, "word": " we", "probability": 0.908203125 }, { "start": 1626.78, "end": 1626.96, "word": " run", "probability": 0.89990234375 }, { "start": 1626.96, "end": 1627.18, "word": " into", "probability": 0.73681640625 } ] }, { "id": 719, "seek": 162784, "start": 1627.18, "end": 1629.1, "text": " our first task, which is to", "tokens": [ 51064, 527, 700, 5633, 11, 597, 307, 281, 51114 ], "temperature": 0.0, "avg_logprob": -0.19916044231226196, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 1627.18, "end": 1627.48, "word": " our", "probability": 0.82080078125 }, { "start": 1627.48, "end": 1627.9, "word": " first", "probability": 0.8173828125 }, { "start": 1627.9, "end": 1628.54, "word": " task", "probability": 0.81640625 }, { "start": 1628.54, "end": 1628.72, "word": ",", "probability": 0.78076171875 }, { "start": 1628.72, "end": 1628.8, "word": " which", "probability": 0.91748046875 }, { "start": 1628.8, "end": 1628.94, "word": " is", "probability": 0.90673828125 }, { "start": 1628.94, "end": 1629.1, "word": " to", "probability": 0.89599609375 } ] }, { "id": 720, "seek": 162784, "start": 1629.1, "end": 1630.42, "text": " tokenize an email.", "tokens": [ 51164, 14862, 1125, 364, 3796, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.19916044231226196, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 1629.1, "end": 1629.6, "word": " tokenize", "probability": 0.84619140625 }, { "start": 1629.6, "end": 1629.76, "word": " an", "probability": 0.88916015625 }, { "start": 1629.76, "end": 1630.02, "word": " email", "probability": 0.88232421875 }, { "start": 1630.02, "end": 1630.42, "word": ".", "probability": 0.9775390625 } ] }, { "id": 721, "seek": 162784, "start": 1630.78, "end": 1632.26, "text": " So our task says that we want", "tokens": [ 51264, 407, 527, 5633, 1619, 300, 321, 528, 51314 ], "temperature": 0.0, "avg_logprob": -0.19916044231226196, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 1630.78, "end": 1631.1, "word": " So", "probability": 0.705078125 }, { "start": 1631.1, "end": 1631.36, "word": " our", "probability": 0.763671875 }, { "start": 1631.36, "end": 1631.58, "word": " task", "probability": 0.77001953125 }, { "start": 1631.58, "end": 1631.82, "word": " says", "probability": 0.81005859375 }, { "start": 1631.82, "end": 1631.96, "word": " that", "probability": 0.82958984375 }, { "start": 1631.96, "end": 1632.06, "word": " we", "probability": 0.9033203125 }, { "start": 1632.06, "end": 1632.26, "word": " want", "probability": 0.81640625 } ] }, { "id": 722, "seek": 162784, "start": 1632.26, "end": 1634.42, "text": " to print the full email, test email,", "tokens": [ 51364, 281, 4482, 264, 1577, 3796, 11, 1500, 3796, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.19916044231226196, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 1632.26, "end": 1632.42, "word": " to", "probability": 0.90869140625 }, { "start": 1632.42, "end": 1632.68, "word": " print", "probability": 0.85888671875 }, { "start": 1632.68, "end": 1632.88, "word": " the", "probability": 0.81201171875 }, { "start": 1632.88, "end": 1633.08, "word": " full", "probability": 0.76953125 }, { "start": 1633.08, "end": 1633.48, "word": " email", "probability": 0.884765625 }, { "start": 1633.48, "end": 1633.66, "word": ",", "probability": 0.8369140625 }, { "start": 1633.66, "end": 1633.86, "word": " test", "probability": 0.71044921875 }, { "start": 1633.86, "end": 1634.18, "word": " email", "probability": 0.8037109375 }, { "start": 1634.18, "end": 1634.42, "word": ",", "probability": 0.90478515625 } ] }, { "id": 723, "seek": 162784, "start": 1634.42, "end": 1635.24, "text": " and then we're going to print the", "tokens": [ 51464, 293, 550, 321, 434, 516, 281, 4482, 264, 51514 ], "temperature": 0.0, "avg_logprob": -0.19916044231226196, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 1634.42, "end": 1634.5, "word": " and", "probability": 0.87353515625 }, { "start": 1634.5, "end": 1634.6, "word": " then", "probability": 0.69580078125 }, { "start": 1634.6, "end": 1634.72, "word": " we're", "probability": 0.919189453125 }, { "start": 1634.72, "end": 1634.8, "word": " going", "probability": 0.8291015625 }, { "start": 1634.8, "end": 1634.9, "word": " to", "probability": 0.908203125 }, { "start": 1634.9, "end": 1635.08, "word": " print", "probability": 0.86474609375 }, { "start": 1635.08, "end": 1635.24, "word": " the", "probability": 0.80908203125 } ] }, { "id": 724, "seek": 162784, "start": 1635.24, "end": 1637.68, "text": " results of the tokenized version", "tokens": [ 51564, 3542, 295, 264, 14862, 1602, 3037, 51614 ], "temperature": 0.0, "avg_logprob": -0.19916044231226196, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 1635.24, "end": 1635.8, "word": " results", "probability": 0.701171875 }, { "start": 1635.8, "end": 1636.62, "word": " of", "probability": 0.90087890625 }, { "start": 1636.62, "end": 1636.82, "word": " the", "probability": 0.8046875 }, { "start": 1636.82, "end": 1637.38, "word": " tokenized", "probability": 0.90234375 }, { "start": 1637.38, "end": 1637.68, "word": " version", "probability": 0.7294921875 } ] }, { "id": 725, "seek": 162784, "start": 1637.68, "end": 1638.92, "text": " of that email.", "tokens": [ 51664, 295, 300, 3796, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.19916044231226196, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 1637.68, "end": 1637.96, "word": " of", "probability": 0.90625 }, { "start": 1637.96, "end": 1638.16, "word": " that", "probability": 0.88037109375 }, { "start": 1638.16, "end": 1638.52, "word": " email", "probability": 0.91357421875 }, { "start": 1638.52, "end": 1638.92, "word": ".", "probability": 0.9892578125 } ] }, { "id": 726, "seek": 162784, "start": 1639.58, "end": 1641.14, "text": " So here I'm just going to do", "tokens": [ 51764, 407, 510, 286, 478, 445, 516, 281, 360, 51814 ], "temperature": 0.0, "avg_logprob": -0.19916044231226196, "compression_ratio": 1.8041666666666667, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 1639.58, "end": 1639.96, "word": " So", "probability": 0.82177734375 }, { "start": 1639.96, "end": 1640.34, "word": " here", "probability": 0.78857421875 }, { "start": 1640.34, "end": 1640.56, "word": " I'm", "probability": 0.88330078125 }, { "start": 1640.56, "end": 1640.72, "word": " just", "probability": 0.8701171875 }, { "start": 1640.72, "end": 1640.9, "word": " going", "probability": 0.861328125 }, { "start": 1640.9, "end": 1641.04, "word": " to", "probability": 0.90673828125 }, { "start": 1641.04, "end": 1641.14, "word": " do", "probability": 0.91064453125 } ] }, { "id": 727, "seek": 165520, "start": 1647.88, "end": 1651.04, "text": " print tokenizer test email.", "tokens": [ 50364, 4482, 14862, 6545, 1500, 3796, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.23665048977703723, "compression_ratio": 1.7336683417085428, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 1647.88, "end": 1648.4, "word": " print", "probability": 0.2047119140625 }, { "start": 1648.4, "end": 1648.92, "word": " tokenizer", "probability": 0.73193359375 }, { "start": 1648.92, "end": 1649.9, "word": " test", "probability": 0.7431640625 }, { "start": 1649.9, "end": 1650.52, "word": " email", "probability": 0.9130859375 }, { "start": 1650.52, "end": 1651.04, "word": ".", "probability": 0.31591796875 } ] }, { "id": 728, "seek": 165520, "start": 1651.52, "end": 1652.82, "text": " And we can go ahead and run that,", "tokens": [ 50614, 400, 321, 393, 352, 2286, 293, 1190, 300, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.23665048977703723, "compression_ratio": 1.7336683417085428, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 1651.52, "end": 1651.66, "word": " And", "probability": 0.56396484375 }, { "start": 1651.66, "end": 1651.84, "word": " we", "probability": 0.88818359375 }, { "start": 1651.84, "end": 1651.98, "word": " can", "probability": 0.900390625 }, { "start": 1651.98, "end": 1652.1, "word": " go", "probability": 0.89990234375 }, { "start": 1652.1, "end": 1652.26, "word": " ahead", "probability": 0.85498046875 }, { "start": 1652.26, "end": 1652.4, "word": " and", "probability": 0.89892578125 }, { "start": 1652.4, "end": 1652.54, "word": " run", "probability": 0.88671875 }, { "start": 1652.54, "end": 1652.74, "word": " that", "probability": 0.88720703125 }, { "start": 1652.74, "end": 1652.82, "word": ",", "probability": 0.376220703125 } ] }, { "id": 729, "seek": 165520, "start": 1652.82, "end": 1655.0, "text": " shift enter. We can see the", "tokens": [ 50714, 5513, 3242, 13, 492, 393, 536, 264, 50764 ], "temperature": 0.0, "avg_logprob": -0.23665048977703723, "compression_ratio": 1.7336683417085428, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 1652.82, "end": 1652.98, "word": " shift", "probability": 0.69580078125 }, { "start": 1652.98, "end": 1653.34, "word": " enter", "probability": 0.427734375 }, { "start": 1653.34, "end": 1653.86, "word": ".", "probability": 0.7373046875 }, { "start": 1654.02, "end": 1654.22, "word": " We", "probability": 0.83251953125 }, { "start": 1654.22, "end": 1654.36, "word": " can", "probability": 0.89501953125 }, { "start": 1654.36, "end": 1654.62, "word": " see", "probability": 0.82080078125 }, { "start": 1654.62, "end": 1655.0, "word": " the", "probability": 0.8154296875 } ] }, { "id": 730, "seek": 165520, "start": 1655.36, "end": 1656.88, "text": " original email that we have,", "tokens": [ 50814, 3380, 3796, 300, 321, 362, 11, 50864 ], "temperature": 0.0, "avg_logprob": -0.23665048977703723, "compression_ratio": 1.7336683417085428, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 1655.36, "end": 1655.62, "word": " original", "probability": 0.8369140625 }, { "start": 1655.62, "end": 1655.94, "word": " email", "probability": 0.91455078125 }, { "start": 1655.94, "end": 1656.14, "word": " that", "probability": 0.87890625 }, { "start": 1656.14, "end": 1656.26, "word": " we", "probability": 0.90673828125 }, { "start": 1656.26, "end": 1656.74, "word": " have", "probability": 0.876953125 }, { "start": 1656.74, "end": 1656.88, "word": ",", "probability": 0.66162109375 } ] }, { "id": 731, "seek": 165520, "start": 1656.88, "end": 1658.16, "text": " East Asian Fonts and Lenny,", "tokens": [ 50914, 6747, 10645, 43901, 82, 293, 23009, 1634, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.23665048977703723, "compression_ratio": 1.7336683417085428, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 1656.88, "end": 1657.0, "word": " East", "probability": 0.64892578125 }, { "start": 1657.0, "end": 1657.24, "word": " Asian", "probability": 0.81884765625 }, { "start": 1657.24, "end": 1657.6, "word": " Fonts", "probability": 0.64208984375 }, { "start": 1657.6, "end": 1657.72, "word": " and", "probability": 0.59716796875 }, { "start": 1657.72, "end": 1658.0, "word": " Lenny", "probability": 0.753173828125 }, { "start": 1658.0, "end": 1658.16, "word": ",", "probability": 0.66162109375 } ] }, { "id": 732, "seek": 165520, "start": 1658.16, "end": 1659.66, "text": " thanks for your support.", "tokens": [ 51014, 3231, 337, 428, 1406, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.23665048977703723, "compression_ratio": 1.7336683417085428, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 1658.16, "end": 1658.4, "word": " thanks", "probability": 0.68798828125 }, { "start": 1658.4, "end": 1658.56, "word": " for", "probability": 0.896484375 }, { "start": 1658.56, "end": 1658.7, "word": " your", "probability": 0.8076171875 }, { "start": 1658.7, "end": 1659.14, "word": " support", "probability": 0.93408203125 }, { "start": 1659.14, "end": 1659.66, "word": ".", "probability": 0.93701171875 } ] }, { "id": 733, "seek": 165520, "start": 1659.74, "end": 1661.16, "text": " We can see, just like in our", "tokens": [ 51114, 492, 393, 536, 11, 445, 411, 294, 527, 51164 ], "temperature": 0.0, "avg_logprob": -0.23665048977703723, "compression_ratio": 1.7336683417085428, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 1659.74, "end": 1659.92, "word": " We", "probability": 0.70166015625 }, { "start": 1659.92, "end": 1660.06, "word": " can", "probability": 0.89501953125 }, { "start": 1660.06, "end": 1660.44, "word": " see", "probability": 0.8134765625 }, { "start": 1660.44, "end": 1660.58, "word": ",", "probability": 0.46630859375 }, { "start": 1660.58, "end": 1660.74, "word": " just", "probability": 0.88720703125 }, { "start": 1660.74, "end": 1660.9, "word": " like", "probability": 0.8798828125 }, { "start": 1660.9, "end": 1661.02, "word": " in", "probability": 0.90234375 }, { "start": 1661.02, "end": 1661.16, "word": " our", "probability": 0.82421875 } ] }, { "id": 734, "seek": 165520, "start": 1661.16, "end": 1663.36, "text": " slides, we have East Asian Font", "tokens": [ 51214, 9788, 11, 321, 362, 6747, 10645, 43901, 51264 ], "temperature": 0.0, "avg_logprob": -0.23665048977703723, "compression_ratio": 1.7336683417085428, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 1661.16, "end": 1661.52, "word": " slides", "probability": 0.9150390625 }, { "start": 1661.52, "end": 1661.64, "word": ",", "probability": 0.9423828125 }, { "start": 1661.64, "end": 1661.72, "word": " we", "probability": 0.90185546875 }, { "start": 1661.72, "end": 1661.92, "word": " have", "probability": 0.880859375 }, { "start": 1661.92, "end": 1662.32, "word": " East", "probability": 0.779296875 }, { "start": 1662.32, "end": 1662.76, "word": " Asian", "probability": 0.8818359375 }, { "start": 1662.76, "end": 1663.36, "word": " Font", "probability": 0.7841796875 } ] }, { "id": 735, "seek": 165520, "start": 1663.36, "end": 1665.82, "text": " Lenny, slightly changed,", "tokens": [ 51314, 23009, 1634, 11, 4748, 3105, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.23665048977703723, "compression_ratio": 1.7336683417085428, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 1663.36, "end": 1664.24, "word": " Lenny", "probability": 0.799560546875 }, { "start": 1664.24, "end": 1664.56, "word": ",", "probability": 0.85693359375 }, { "start": 1664.56, "end": 1664.86, "word": " slightly", "probability": 0.74462890625 }, { "start": 1664.86, "end": 1665.44, "word": " changed", "probability": 0.78125 }, { "start": 1665.44, "end": 1665.82, "word": ",", "probability": 0.7548828125 } ] }, { "id": 736, "seek": 165520, "start": 1665.82, "end": 1668.4, "text": " thank instead of thanks,", "tokens": [ 51414, 1309, 2602, 295, 3231, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.23665048977703723, "compression_ratio": 1.7336683417085428, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 1665.82, "end": 1666.06, "word": " thank", "probability": 0.595703125 }, { "start": 1666.06, "end": 1666.8, "word": " instead", "probability": 0.57861328125 }, { "start": 1666.8, "end": 1667.0, "word": " of", "probability": 0.91357421875 }, { "start": 1667.0, "end": 1667.38, "word": " thanks", "probability": 0.7490234375 }, { "start": 1667.38, "end": 1668.4, "word": ",", "probability": 0.296630859375 } ] }, { "id": 737, "seek": 165520, "start": 1668.4, "end": 1670.5, "text": " support install, because we can", "tokens": [ 51514, 1406, 3625, 11, 570, 321, 393, 51564 ], "temperature": 0.0, "avg_logprob": -0.23665048977703723, "compression_ratio": 1.7336683417085428, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 1668.4, "end": 1668.96, "word": " support", "probability": 0.9033203125 }, { "start": 1668.96, "end": 1669.72, "word": " install", "probability": 0.75341796875 }, { "start": 1669.72, "end": 1670.0, "word": ",", "probability": 0.603515625 }, { "start": 1670.0, "end": 1670.26, "word": " because", "probability": 0.84130859375 }, { "start": 1670.26, "end": 1670.38, "word": " we", "probability": 0.9013671875 }, { "start": 1670.38, "end": 1670.5, "word": " can", "probability": 0.89404296875 } ] }, { "id": 738, "seek": 165520, "start": 1670.5, "end": 1673.9, "text": " have installing installed with", "tokens": [ 51614, 362, 20762, 8899, 365, 51714 ], "temperature": 0.0, "avg_logprob": -0.23665048977703723, "compression_ratio": 1.7336683417085428, "no_speech_prob": 5.227327346801758e-05, "words": [ { "start": 1670.5, "end": 1671.06, "word": " have", "probability": 0.892578125 }, { "start": 1671.06, "end": 1672.48, "word": " installing", "probability": 0.68408203125 }, { "start": 1672.48, "end": 1673.5, "word": " installed", "probability": 0.458740234375 }, { "start": 1673.5, "end": 1673.9, "word": " with", "probability": 0.73828125 } ] }, { "id": 739, "seek": 168280, "start": 1673.9, "end": 1676.32, "text": " an ed at the end, or I", "tokens": [ 50364, 364, 1257, 412, 264, 917, 11, 420, 286, 50414 ], "temperature": 0.0, "avg_logprob": -0.18266369662587606, "compression_ratio": 1.6597510373443984, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 1673.9, "end": 1674.0, "word": " an", "probability": 0.251953125 }, { "start": 1674.0, "end": 1674.24, "word": " ed", "probability": 0.1744384765625 }, { "start": 1674.24, "end": 1674.48, "word": " at", "probability": 0.8798828125 }, { "start": 1674.48, "end": 1674.64, "word": " the", "probability": 0.8154296875 }, { "start": 1674.64, "end": 1674.9, "word": " end", "probability": 0.80859375 }, { "start": 1674.9, "end": 1675.04, "word": ",", "probability": 0.34814453125 }, { "start": 1675.04, "end": 1675.22, "word": " or", "probability": 0.892578125 }, { "start": 1675.22, "end": 1676.32, "word": " I", "probability": 0.83740234375 } ] }, { "id": 740, "seek": 168280, "start": 1676.32, "end": 1678.22, "text": " will install this software,", "tokens": [ 50464, 486, 3625, 341, 4722, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.18266369662587606, "compression_ratio": 1.6597510373443984, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 1676.32, "end": 1676.5, "word": " will", "probability": 0.81201171875 }, { "start": 1676.5, "end": 1677.02, "word": " install", "probability": 0.8251953125 }, { "start": 1677.02, "end": 1677.3, "word": " this", "probability": 0.84375 }, { "start": 1677.3, "end": 1677.74, "word": " software", "probability": 0.845703125 }, { "start": 1677.74, "end": 1678.22, "word": ",", "probability": 0.72021484375 } ] }, { "id": 741, "seek": 168280, "start": 1678.22, "end": 1680.14, "text": " which is just a standard install.", "tokens": [ 50564, 597, 307, 445, 257, 3832, 3625, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.18266369662587606, "compression_ratio": 1.6597510373443984, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 1678.22, "end": 1678.42, "word": " which", "probability": 0.90673828125 }, { "start": 1678.42, "end": 1678.54, "word": " is", "probability": 0.9033203125 }, { "start": 1678.54, "end": 1678.74, "word": " just", "probability": 0.8857421875 }, { "start": 1678.94, "end": 1679.2, "word": " a standard", "probability": 0.83837890625 }, { "start": 1679.2, "end": 1679.74, "word": " install", "probability": 0.8232421875 }, { "start": 1679.74, "end": 1680.14, "word": ".", "probability": 0.97314453125 } ] }, { "id": 742, "seek": 168280, "start": 1681.34, "end": 1683.08, "text": " We see unsubscribe has been", "tokens": [ 50714, 492, 536, 2693, 9493, 575, 668, 50764 ], "temperature": 0.0, "avg_logprob": -0.18266369662587606, "compression_ratio": 1.6597510373443984, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 1681.34, "end": 1681.74, "word": " We", "probability": 0.8349609375 }, { "start": 1681.74, "end": 1682.02, "word": " see", "probability": 0.8125 }, { "start": 1682.02, "end": 1682.52, "word": " unsubscribe", "probability": 0.78564453125 }, { "start": 1682.52, "end": 1682.94, "word": " has", "probability": 0.892578125 }, { "start": 1682.94, "end": 1683.08, "word": " been", "probability": 0.8203125 } ] }, { "id": 743, "seek": 168280, "start": 1683.08, "end": 1684.56, "text": " changed. And two of the things", "tokens": [ 50814, 3105, 13, 400, 732, 295, 264, 721, 50864 ], "temperature": 0.0, "avg_logprob": -0.18266369662587606, "compression_ratio": 1.6597510373443984, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 1683.08, "end": 1683.52, "word": " changed", "probability": 0.771484375 }, { "start": 1683.52, "end": 1683.92, "word": ".", "probability": 0.64794921875 }, { "start": 1684.02, "end": 1684.12, "word": " And", "probability": 0.84033203125 }, { "start": 1684.12, "end": 1684.24, "word": " two", "probability": 0.82568359375 }, { "start": 1684.24, "end": 1684.32, "word": " of", "probability": 0.875 }, { "start": 1684.32, "end": 1684.4, "word": " the", "probability": 0.810546875 }, { "start": 1684.4, "end": 1684.56, "word": " things", "probability": 0.740234375 } ] }, { "id": 744, "seek": 168280, "start": 1684.56, "end": 1685.48, "text": " that I want to point out is", "tokens": [ 50914, 300, 286, 528, 281, 935, 484, 307, 50964 ], "temperature": 0.0, "avg_logprob": -0.18266369662587606, "compression_ratio": 1.6597510373443984, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 1684.56, "end": 1684.66, "word": " that", "probability": 0.85107421875 }, { "start": 1684.66, "end": 1684.74, "word": " I", "probability": 0.998046875 }, { "start": 1684.74, "end": 1684.84, "word": " want", "probability": 0.475830078125 }, { "start": 1684.84, "end": 1684.94, "word": " to", "probability": 0.90673828125 }, { "start": 1684.94, "end": 1685.14, "word": " point", "probability": 0.8525390625 }, { "start": 1685.14, "end": 1685.32, "word": " out", "probability": 0.810546875 }, { "start": 1685.32, "end": 1685.48, "word": " is", "probability": 0.8525390625 } ] }, { "id": 745, "seek": 168280, "start": 1685.48, "end": 1686.74, "text": " every single word in here is", "tokens": [ 51014, 633, 2167, 1349, 294, 510, 307, 51064 ], "temperature": 0.0, "avg_logprob": -0.18266369662587606, "compression_ratio": 1.6597510373443984, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 1685.48, "end": 1685.66, "word": " every", "probability": 0.71533203125 }, { "start": 1685.66, "end": 1685.88, "word": " single", "probability": 0.8759765625 }, { "start": 1685.88, "end": 1686.16, "word": " word", "probability": 0.78466796875 }, { "start": 1686.16, "end": 1686.34, "word": " in", "probability": 0.90283203125 }, { "start": 1686.34, "end": 1686.52, "word": " here", "probability": 0.8056640625 }, { "start": 1686.52, "end": 1686.74, "word": " is", "probability": 0.9072265625 } ] }, { "id": 746, "seek": 168280, "start": 1686.74, "end": 1687.86, "text": " unique, except for the word", "tokens": [ 51114, 3845, 11, 3993, 337, 264, 1349, 51164 ], "temperature": 0.0, "avg_logprob": -0.18266369662587606, "compression_ratio": 1.6597510373443984, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 1686.74, "end": 1687.1, "word": " unique", "probability": 0.7802734375 }, { "start": 1687.1, "end": 1687.16, "word": ",", "probability": 0.4580078125 }, { "start": 1687.16, "end": 1687.4, "word": " except", "probability": 0.85009765625 }, { "start": 1687.4, "end": 1687.6, "word": " for", "probability": 0.89453125 }, { "start": 1687.6, "end": 1687.7, "word": " the", "probability": 0.80908203125 }, { "start": 1687.7, "end": 1687.86, "word": " word", "probability": 0.81201171875 } ] }, { "id": 747, "seek": 168280, "start": 1687.86, "end": 1689.32, "text": " unsubscribe, which shows up", "tokens": [ 51214, 2693, 9493, 11, 597, 3110, 493, 51264 ], "temperature": 0.0, "avg_logprob": -0.18266369662587606, "compression_ratio": 1.6597510373443984, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 1687.86, "end": 1688.52, "word": " unsubscribe", "probability": 0.827392578125 }, { "start": 1688.52, "end": 1688.78, "word": ",", "probability": 0.8642578125 }, { "start": 1688.78, "end": 1688.94, "word": " which", "probability": 0.9052734375 }, { "start": 1688.94, "end": 1689.16, "word": " shows", "probability": 0.796875 }, { "start": 1689.16, "end": 1689.32, "word": " up", "probability": 0.90966796875 } ] }, { "id": 748, "seek": 168280, "start": 1689.32, "end": 1692.06, "text": " twice, and list.deviant.org,", "tokens": [ 51314, 6091, 11, 293, 1329, 13, 1479, 4917, 394, 13, 4646, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.18266369662587606, "compression_ratio": 1.6597510373443984, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 1689.32, "end": 1689.68, "word": " twice", "probability": 0.8515625 }, { "start": 1689.68, "end": 1690.02, "word": ",", "probability": 0.44873046875 }, { "start": 1690.02, "end": 1690.12, "word": " and", "probability": 0.8935546875 }, { "start": 1690.12, "end": 1690.6, "word": " list", "probability": 0.6640625 }, { "start": 1690.6, "end": 1691.26, "word": ".deviant", "probability": 0.7249755859375 }, { "start": 1691.26, "end": 1691.96, "word": ".org", "probability": 0.968994140625 }, { "start": 1691.96, "end": 1692.06, "word": ",", "probability": 0.8818359375 } ] }, { "id": 749, "seek": 168280, "start": 1692.06, "end": 1693.94, "text": " which shows up twice.", "tokens": [ 51414, 597, 3110, 493, 6091, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.18266369662587606, "compression_ratio": 1.6597510373443984, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 1692.06, "end": 1692.6, "word": " which", "probability": 0.9150390625 }, { "start": 1692.6, "end": 1692.92, "word": " shows", "probability": 0.78759765625 }, { "start": 1692.92, "end": 1693.12, "word": " up", "probability": 0.90966796875 }, { "start": 1693.12, "end": 1693.54, "word": " twice", "probability": 0.85400390625 }, { "start": 1693.54, "end": 1693.94, "word": ".", "probability": 0.998046875 } ] }, { "id": 750, "seek": 168280, "start": 1696.36, "end": 1697.4, "text": " So we're going to take a look", "tokens": [ 51514, 407, 321, 434, 516, 281, 747, 257, 574, 51564 ], "temperature": 0.0, "avg_logprob": -0.18266369662587606, "compression_ratio": 1.6597510373443984, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 1696.36, "end": 1696.76, "word": " So", "probability": 0.87158203125 }, { "start": 1696.76, "end": 1696.98, "word": " we're", "probability": 0.859375 }, { "start": 1696.98, "end": 1697.02, "word": " going", "probability": 0.55517578125 }, { "start": 1697.02, "end": 1697.1, "word": " to", "probability": 0.90625 }, { "start": 1697.1, "end": 1697.22, "word": " take", "probability": 0.8046875 }, { "start": 1697.3, "end": 1697.4, "word": " a look", "probability": 0.9140625 } ] }, { "id": 751, "seek": 168280, "start": 1697.4, "end": 1698.68, "text": " at our training data. What this", "tokens": [ 51614, 412, 527, 3097, 1412, 13, 708, 341, 51664 ], "temperature": 0.0, "avg_logprob": -0.18266369662587606, "compression_ratio": 1.6597510373443984, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 1697.4, "end": 1697.48, "word": " at", "probability": 0.90673828125 }, { "start": 1697.48, "end": 1697.6, "word": " our", "probability": 0.81005859375 }, { "start": 1697.6, "end": 1697.9, "word": " training", "probability": 0.80078125 }, { "start": 1697.9, "end": 1698.28, "word": " data", "probability": 0.818359375 }, { "start": 1698.28, "end": 1698.44, "word": ".", "probability": 0.8369140625 }, { "start": 1698.44, "end": 1698.52, "word": " What", "probability": 0.81201171875 }, { "start": 1698.52, "end": 1698.68, "word": " this", "probability": 0.8837890625 } ] }, { "id": 752, "seek": 168280, "start": 1698.68, "end": 1701.5, "text": " is going to do is identify the", "tokens": [ 51714, 307, 516, 281, 360, 307, 5876, 264, 51764 ], "temperature": 0.0, "avg_logprob": -0.18266369662587606, "compression_ratio": 1.6597510373443984, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 1698.68, "end": 1698.8, "word": " is", "probability": 0.90673828125 }, { "start": 1698.8, "end": 1698.94, "word": " going", "probability": 0.859375 }, { "start": 1698.94, "end": 1699.1, "word": " to", "probability": 0.9072265625 }, { "start": 1699.1, "end": 1699.38, "word": " do", "probability": 0.9013671875 }, { "start": 1699.38, "end": 1699.86, "word": " is", "probability": 0.89794921875 }, { "start": 1699.86, "end": 1700.58, "word": " identify", "probability": 0.89990234375 }, { "start": 1700.58, "end": 1701.5, "word": " the", "probability": 0.8134765625 } ] }, { "id": 753, "seek": 171020, "start": 1702.14, "end": 1704.98, "text": " directories where our spam", "tokens": [ 50364, 5391, 530, 689, 527, 24028, 50464 ], "temperature": 0.0, "avg_logprob": -0.2003816748393401, "compression_ratio": 1.8214285714285714, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 1702.14, "end": 1702.52, "word": " directories", "probability": 0.5107269287109375 }, { "start": 1702.52, "end": 1702.9, "word": " where", "probability": 0.7353515625 }, { "start": 1702.9, "end": 1704.56, "word": " our", "probability": 0.72705078125 }, { "start": 1704.56, "end": 1704.98, "word": " spam", "probability": 0.546875 } ] }, { "id": 754, "seek": 171020, "start": 1704.98, "end": 1707.1, "text": " files are, our ham files are,", "tokens": [ 50514, 7098, 366, 11, 527, 7852, 7098, 366, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.2003816748393401, "compression_ratio": 1.8214285714285714, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 1704.98, "end": 1705.34, "word": " files", "probability": 0.72314453125 }, { "start": 1705.34, "end": 1705.6, "word": " are", "probability": 0.7939453125 }, { "start": 1705.6, "end": 1705.72, "word": ",", "probability": 0.7021484375 }, { "start": 1705.72, "end": 1705.78, "word": " our", "probability": 0.625 }, { "start": 1705.78, "end": 1706.3, "word": " ham", "probability": 0.7314453125 }, { "start": 1706.3, "end": 1706.66, "word": " files", "probability": 0.72119140625 }, { "start": 1706.66, "end": 1706.96, "word": " are", "probability": 0.861328125 }, { "start": 1706.96, "end": 1707.1, "word": ",", "probability": 0.76171875 } ] }, { "id": 755, "seek": 171020, "start": 1707.1, "end": 1709.16, "text": " and our test files are. We're", "tokens": [ 50614, 293, 527, 1500, 7098, 366, 13, 492, 434, 50664 ], "temperature": 0.0, "avg_logprob": -0.2003816748393401, "compression_ratio": 1.8214285714285714, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 1707.1, "end": 1707.3, "word": " and", "probability": 0.884765625 }, { "start": 1707.3, "end": 1707.58, "word": " our", "probability": 0.80517578125 }, { "start": 1707.58, "end": 1707.98, "word": " test", "probability": 0.82861328125 }, { "start": 1707.98, "end": 1708.3, "word": " files", "probability": 0.79736328125 }, { "start": 1708.3, "end": 1708.66, "word": " are", "probability": 0.8759765625 }, { "start": 1708.66, "end": 1708.98, "word": ".", "probability": 0.79931640625 }, { "start": 1708.98, "end": 1709.16, "word": " We're", "probability": 0.892578125 } ] }, { "id": 756, "seek": 171020, "start": 1709.16, "end": 1710.18, "text": " going to get a count, because", "tokens": [ 50714, 516, 281, 483, 257, 1207, 11, 570, 50764 ], "temperature": 0.0, "avg_logprob": -0.2003816748393401, "compression_ratio": 1.8214285714285714, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 1709.16, "end": 1709.24, "word": " going", "probability": 0.72119140625 }, { "start": 1709.24, "end": 1709.28, "word": " to", "probability": 0.9052734375 }, { "start": 1709.28, "end": 1709.4, "word": " get", "probability": 0.88232421875 }, { "start": 1709.56, "end": 1709.9, "word": " a count", "probability": 0.75048828125 }, { "start": 1709.9, "end": 1710.04, "word": ",", "probability": 0.192138671875 }, { "start": 1710.04, "end": 1710.18, "word": " because", "probability": 0.8203125 } ] }, { "id": 757, "seek": 171020, "start": 1710.18, "end": 1711.42, "text": " that's one of the five things", "tokens": [ 50814, 300, 311, 472, 295, 264, 1732, 721, 50864 ], "temperature": 0.0, "avg_logprob": -0.2003816748393401, "compression_ratio": 1.8214285714285714, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 1710.18, "end": 1710.4, "word": " that's", "probability": 0.9130859375 }, { "start": 1710.4, "end": 1710.56, "word": " one", "probability": 0.81689453125 }, { "start": 1710.56, "end": 1710.66, "word": " of", "probability": 0.90087890625 }, { "start": 1710.66, "end": 1710.82, "word": " the", "probability": 0.81494140625 }, { "start": 1710.82, "end": 1711.16, "word": " five", "probability": 0.73828125 }, { "start": 1711.16, "end": 1711.42, "word": " things", "probability": 0.71875 } ] }, { "id": 758, "seek": 171020, "start": 1711.42, "end": 1712.4, "text": " that we needed to keep track", "tokens": [ 50914, 300, 321, 2978, 281, 1066, 2837, 50964 ], "temperature": 0.0, "avg_logprob": -0.2003816748393401, "compression_ratio": 1.8214285714285714, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 1711.42, "end": 1711.56, "word": " that", "probability": 0.75830078125 }, { "start": 1711.56, "end": 1711.64, "word": " we", "probability": 0.90576171875 }, { "start": 1711.64, "end": 1711.8, "word": " needed", "probability": 0.460693359375 }, { "start": 1711.8, "end": 1711.94, "word": " to", "probability": 0.9111328125 }, { "start": 1711.94, "end": 1712.08, "word": " keep", "probability": 0.81787109375 }, { "start": 1712.08, "end": 1712.4, "word": " track", "probability": 0.8232421875 } ] }, { "id": 759, "seek": 171020, "start": 1712.4, "end": 1715.5, "text": " of, was the count of, actually", "tokens": [ 51014, 295, 11, 390, 264, 1207, 295, 11, 767, 51064 ], "temperature": 0.0, "avg_logprob": -0.2003816748393401, "compression_ratio": 1.8214285714285714, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 1712.4, "end": 1712.62, "word": " of", "probability": 0.9033203125 }, { "start": 1712.62, "end": 1712.68, "word": ",", "probability": 0.310791015625 }, { "start": 1712.68, "end": 1712.8, "word": " was", "probability": 0.7236328125 }, { "start": 1712.8, "end": 1712.98, "word": " the", "probability": 0.810546875 }, { "start": 1712.98, "end": 1713.44, "word": " count", "probability": 0.81640625 }, { "start": 1713.44, "end": 1714.4, "word": " of", "probability": 0.82421875 }, { "start": 1714.4, "end": 1715.28, "word": ",", "probability": 0.12078857421875 }, { "start": 1715.28, "end": 1715.5, "word": " actually", "probability": 0.5634765625 } ] }, { "id": 760, "seek": 171020, "start": 1716.8, "end": 1717.8, "text": " we want to keep track of the", "tokens": [ 51114, 321, 528, 281, 1066, 2837, 295, 264, 51164 ], "temperature": 0.0, "avg_logprob": -0.2003816748393401, "compression_ratio": 1.8214285714285714, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 1716.8, "end": 1717.18, "word": " we", "probability": 0.5029296875 }, { "start": 1717.18, "end": 1717.32, "word": " want", "probability": 0.81640625 }, { "start": 1717.32, "end": 1717.38, "word": " to", "probability": 0.90869140625 }, { "start": 1717.38, "end": 1717.5, "word": " keep", "probability": 0.77294921875 }, { "start": 1717.5, "end": 1717.64, "word": " track", "probability": 0.8583984375 }, { "start": 1717.64, "end": 1717.74, "word": " of", "probability": 0.703125 }, { "start": 1717.74, "end": 1717.8, "word": " the", "probability": 0.8095703125 } ] }, { "id": 761, "seek": 171020, "start": 1717.8, "end": 1718.74, "text": " count of words, we don't care", "tokens": [ 51214, 1207, 295, 2283, 11, 321, 500, 380, 1127, 51264 ], "temperature": 0.0, "avg_logprob": -0.2003816748393401, "compression_ratio": 1.8214285714285714, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 1717.8, "end": 1717.98, "word": " count", "probability": 0.7978515625 }, { "start": 1717.98, "end": 1718.12, "word": " of", "probability": 0.89697265625 }, { "start": 1718.12, "end": 1718.32, "word": " words", "probability": 0.681640625 }, { "start": 1718.32, "end": 1718.36, "word": ",", "probability": 0.4736328125 }, { "start": 1718.36, "end": 1718.44, "word": " we", "probability": 0.8935546875 }, { "start": 1718.44, "end": 1718.56, "word": " don't", "probability": 0.94677734375 }, { "start": 1718.56, "end": 1718.74, "word": " care", "probability": 0.8115234375 } ] }, { "id": 762, "seek": 171020, "start": 1718.74, "end": 1720.7, "text": " how many emails we have. So", "tokens": [ 51314, 577, 867, 12524, 321, 362, 13, 407, 51364 ], "temperature": 0.0, "avg_logprob": -0.2003816748393401, "compression_ratio": 1.8214285714285714, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 1718.74, "end": 1718.9, "word": " how", "probability": 0.89404296875 }, { "start": 1718.9, "end": 1719.12, "word": " many", "probability": 0.826171875 }, { "start": 1719.12, "end": 1719.4, "word": " emails", "probability": 0.75439453125 }, { "start": 1719.4, "end": 1719.68, "word": " we", "probability": 0.89697265625 }, { "start": 1719.68, "end": 1720.0, "word": " have", "probability": 0.87744140625 }, { "start": 1720.0, "end": 1720.38, "word": ".", "probability": 0.8935546875 }, { "start": 1720.48, "end": 1720.7, "word": " So", "probability": 0.8056640625 } ] }, { "id": 763, "seek": 171020, "start": 1720.7, "end": 1721.68, "text": " I'm going to go ahead and run", "tokens": [ 51414, 286, 478, 516, 281, 352, 2286, 293, 1190, 51464 ], "temperature": 0.0, "avg_logprob": -0.2003816748393401, "compression_ratio": 1.8214285714285714, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 1720.7, "end": 1720.92, "word": " I'm", "probability": 0.8798828125 }, { "start": 1720.92, "end": 1720.96, "word": " going", "probability": 0.75537109375 }, { "start": 1720.96, "end": 1721.0, "word": " to", "probability": 0.90576171875 }, { "start": 1721.0, "end": 1721.1, "word": " go", "probability": 0.89990234375 }, { "start": 1721.1, "end": 1721.26, "word": " ahead", "probability": 0.85302734375 }, { "start": 1721.26, "end": 1721.46, "word": " and", "probability": 0.8916015625 }, { "start": 1721.46, "end": 1721.68, "word": " run", "probability": 0.9072265625 } ] }, { "id": 764, "seek": 171020, "start": 1721.68, "end": 1725.18, "text": " this, and what we're going to", "tokens": [ 51514, 341, 11, 293, 437, 321, 434, 516, 281, 51564 ], "temperature": 0.0, "avg_logprob": -0.2003816748393401, "compression_ratio": 1.8214285714285714, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 1721.68, "end": 1722.08, "word": " this", "probability": 0.88232421875 }, { "start": 1722.08, "end": 1722.52, "word": ",", "probability": 0.54248046875 }, { "start": 1722.52, "end": 1722.66, "word": " and", "probability": 0.87939453125 }, { "start": 1722.66, "end": 1724.92, "word": " what", "probability": 0.83984375 }, { "start": 1724.92, "end": 1725.04, "word": " we're", "probability": 0.9296875 }, { "start": 1725.04, "end": 1725.12, "word": " going", "probability": 0.82958984375 }, { "start": 1725.12, "end": 1725.18, "word": " to", "probability": 0.9091796875 } ] }, { "id": 765, "seek": 171020, "start": 1725.18, "end": 1727.72, "text": " do is put those emails into", "tokens": [ 51614, 360, 307, 829, 729, 12524, 666, 51664 ], "temperature": 0.0, "avg_logprob": -0.2003816748393401, "compression_ratio": 1.8214285714285714, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 1725.18, "end": 1725.38, "word": " do", "probability": 0.90625 }, { "start": 1725.38, "end": 1725.86, "word": " is", "probability": 0.89990234375 }, { "start": 1725.86, "end": 1726.42, "word": " put", "probability": 0.8701171875 }, { "start": 1726.42, "end": 1726.7, "word": " those", "probability": 0.8486328125 }, { "start": 1726.7, "end": 1727.1, "word": " emails", "probability": 0.810546875 }, { "start": 1727.1, "end": 1727.72, "word": " into", "probability": 0.7421875 } ] }, { "id": 766, "seek": 171020, "start": 1727.72, "end": 1728.9, "text": " what is known as a corpus.", "tokens": [ 51714, 437, 307, 2570, 382, 257, 1181, 31624, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.2003816748393401, "compression_ratio": 1.8214285714285714, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 1727.72, "end": 1728.04, "word": " what", "probability": 0.85400390625 }, { "start": 1728.04, "end": 1728.14, "word": " is", "probability": 0.90234375 }, { "start": 1728.14, "end": 1728.28, "word": " known", "probability": 0.72216796875 }, { "start": 1728.28, "end": 1728.38, "word": " as", "probability": 0.90869140625 }, { "start": 1728.5, "end": 1728.8, "word": " a corpus", "probability": 0.85400390625 }, { "start": 1728.8, "end": 1728.9, "word": ".", "probability": 0.748046875 } ] }, { "id": 767, "seek": 173624, "start": 1728.9, "end": 1729.64, "text": " So we're going to create two", "tokens": [ 50364, 407, 321, 434, 516, 281, 1884, 732, 50414 ], "temperature": 0.0, "avg_logprob": -0.15899332083818565, "compression_ratio": 2.05, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1728.9, "end": 1728.96, "word": " So", "probability": 0.194091796875 }, { "start": 1728.96, "end": 1729.08, "word": " we're", "probability": 0.862060546875 }, { "start": 1729.08, "end": 1729.12, "word": " going", "probability": 0.428955078125 }, { "start": 1729.12, "end": 1729.18, "word": " to", "probability": 0.90234375 }, { "start": 1729.18, "end": 1729.38, "word": " create", "probability": 0.82763671875 }, { "start": 1729.38, "end": 1729.64, "word": " two", "probability": 0.775390625 } ] }, { "id": 768, "seek": 173624, "start": 1729.64, "end": 1731.66, "text": " list arrays, so corpus and", "tokens": [ 50464, 1329, 41011, 11, 370, 1181, 31624, 293, 50514 ], "temperature": 0.0, "avg_logprob": -0.15899332083818565, "compression_ratio": 2.05, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1729.64, "end": 1729.92, "word": " list", "probability": 0.76318359375 }, { "start": 1729.92, "end": 1730.26, "word": " arrays", "probability": 0.57177734375 }, { "start": 1730.26, "end": 1730.56, "word": ",", "probability": 0.58984375 }, { "start": 1730.56, "end": 1730.6, "word": " so", "probability": 0.716796875 }, { "start": 1730.6, "end": 1731.18, "word": " corpus", "probability": 0.76416015625 }, { "start": 1731.18, "end": 1731.66, "word": " and", "probability": 0.87744140625 } ] }, { "id": 769, "seek": 173624, "start": 1731.66, "end": 1732.84, "text": " labels. Corpus is going to", "tokens": [ 50564, 16949, 13, 3925, 31624, 307, 516, 281, 50614 ], "temperature": 0.0, "avg_logprob": -0.15899332083818565, "compression_ratio": 2.05, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1731.66, "end": 1732.06, "word": " labels", "probability": 0.82666015625 }, { "start": 1732.06, "end": 1732.18, "word": ".", "probability": 0.93359375 }, { "start": 1732.18, "end": 1732.44, "word": " Corpus", "probability": 0.78857421875 }, { "start": 1732.44, "end": 1732.6, "word": " is", "probability": 0.89892578125 }, { "start": 1732.6, "end": 1732.72, "word": " going", "probability": 0.81982421875 }, { "start": 1732.72, "end": 1732.84, "word": " to", "probability": 0.90478515625 } ] }, { "id": 770, "seek": 173624, "start": 1732.84, "end": 1734.82, "text": " hold all of our emails for", "tokens": [ 50664, 1797, 439, 295, 527, 12524, 337, 50714 ], "temperature": 0.0, "avg_logprob": -0.15899332083818565, "compression_ratio": 2.05, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1732.84, "end": 1733.08, "word": " hold", "probability": 0.81689453125 }, { "start": 1733.08, "end": 1733.34, "word": " all", "probability": 0.90380859375 }, { "start": 1733.34, "end": 1733.44, "word": " of", "probability": 0.869140625 }, { "start": 1733.44, "end": 1733.56, "word": " our", "probability": 0.82373046875 }, { "start": 1733.56, "end": 1733.94, "word": " emails", "probability": 0.75439453125 }, { "start": 1733.94, "end": 1734.82, "word": " for", "probability": 0.87109375 } ] }, { "id": 771, "seek": 173624, "start": 1734.82, "end": 1738.44, "text": " spam and ham, and then the", "tokens": [ 50764, 24028, 293, 7852, 11, 293, 550, 264, 50814 ], "temperature": 0.0, "avg_logprob": -0.15899332083818565, "compression_ratio": 2.05, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1734.82, "end": 1735.4, "word": " spam", "probability": 0.8310546875 }, { "start": 1735.4, "end": 1735.84, "word": " and", "probability": 0.8935546875 }, { "start": 1735.84, "end": 1736.14, "word": " ham", "probability": 0.7392578125 }, { "start": 1736.14, "end": 1736.62, "word": ",", "probability": 0.3359375 }, { "start": 1736.62, "end": 1738.16, "word": " and", "probability": 0.86328125 }, { "start": 1738.16, "end": 1738.28, "word": " then", "probability": 0.7099609375 }, { "start": 1738.28, "end": 1738.44, "word": " the", "probability": 0.80126953125 } ] }, { "id": 772, "seek": 173624, "start": 1738.44, "end": 1739.8, "text": " labels is going to be each", "tokens": [ 50864, 16949, 307, 516, 281, 312, 1184, 50914 ], "temperature": 0.0, "avg_logprob": -0.15899332083818565, "compression_ratio": 2.05, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1738.44, "end": 1738.78, "word": " labels", "probability": 0.84912109375 }, { "start": 1738.78, "end": 1738.98, "word": " is", "probability": 0.7919921875 }, { "start": 1738.98, "end": 1739.18, "word": " going", "probability": 0.84912109375 }, { "start": 1739.18, "end": 1739.36, "word": " to", "probability": 0.90380859375 }, { "start": 1739.36, "end": 1739.54, "word": " be", "probability": 0.90234375 }, { "start": 1739.54, "end": 1739.8, "word": " each", "probability": 0.84619140625 } ] }, { "id": 773, "seek": 173624, "start": 1739.8, "end": 1741.9, "text": " label for our data. So the", "tokens": [ 50964, 7645, 337, 527, 1412, 13, 407, 264, 51014 ], "temperature": 0.0, "avg_logprob": -0.15899332083818565, "compression_ratio": 2.05, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1739.8, "end": 1740.22, "word": " label", "probability": 0.7841796875 }, { "start": 1740.22, "end": 1740.78, "word": " for", "probability": 0.89892578125 }, { "start": 1740.78, "end": 1740.98, "word": " our", "probability": 0.81689453125 }, { "start": 1740.98, "end": 1741.22, "word": " data", "probability": 0.81689453125 }, { "start": 1741.22, "end": 1741.62, "word": ".", "probability": 0.986328125 }, { "start": 1741.68, "end": 1741.78, "word": " So", "probability": 0.85693359375 }, { "start": 1741.78, "end": 1741.9, "word": " the", "probability": 0.80126953125 } ] }, { "id": 774, "seek": 173624, "start": 1741.9, "end": 1742.7, "text": " first thing we're going to do", "tokens": [ 51064, 700, 551, 321, 434, 516, 281, 360, 51114 ], "temperature": 0.0, "avg_logprob": -0.15899332083818565, "compression_ratio": 2.05, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1741.9, "end": 1742.08, "word": " first", "probability": 0.82275390625 }, { "start": 1742.08, "end": 1742.2, "word": " thing", "probability": 0.8076171875 }, { "start": 1742.2, "end": 1742.32, "word": " we're", "probability": 0.92236328125 }, { "start": 1742.32, "end": 1742.4, "word": " going", "probability": 0.82373046875 }, { "start": 1742.4, "end": 1742.46, "word": " to", "probability": 0.90576171875 }, { "start": 1742.46, "end": 1742.7, "word": " do", "probability": 0.9072265625 } ] }, { "id": 775, "seek": 173624, "start": 1742.7, "end": 1746.02, "text": " is corpus equals a new list,", "tokens": [ 51164, 307, 1181, 31624, 6915, 257, 777, 1329, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.15899332083818565, "compression_ratio": 2.05, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1742.7, "end": 1743.18, "word": " is", "probability": 0.900390625 }, { "start": 1743.18, "end": 1743.76, "word": " corpus", "probability": 0.81201171875 }, { "start": 1743.76, "end": 1744.6, "word": " equals", "probability": 0.59619140625 }, { "start": 1744.76, "end": 1744.86, "word": " a new", "probability": 0.7900390625 }, { "start": 1744.86, "end": 1745.3, "word": " list", "probability": 0.857421875 }, { "start": 1745.3, "end": 1746.02, "word": ",", "probability": 0.68505859375 } ] }, { "id": 776, "seek": 173624, "start": 1746.02, "end": 1748.0, "text": " labels equals a new list,", "tokens": [ 51264, 16949, 6915, 257, 777, 1329, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.15899332083818565, "compression_ratio": 2.05, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1746.02, "end": 1746.62, "word": " labels", "probability": 0.83056640625 }, { "start": 1746.62, "end": 1747.12, "word": " equals", "probability": 0.85791015625 }, { "start": 1747.3, "end": 1747.42, "word": " a new", "probability": 0.818359375 }, { "start": 1747.42, "end": 1747.8, "word": " list", "probability": 0.8828125 }, { "start": 1747.8, "end": 1748.0, "word": ",", "probability": 0.62060546875 } ] }, { "id": 777, "seek": 173624, "start": 1748.72, "end": 1749.5, "text": " and then we're going to do", "tokens": [ 51364, 293, 550, 321, 434, 516, 281, 360, 51414 ], "temperature": 0.0, "avg_logprob": -0.15899332083818565, "compression_ratio": 2.05, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1748.72, "end": 1749.04, "word": " and", "probability": 0.8857421875 }, { "start": 1749.04, "end": 1749.16, "word": " then", "probability": 0.7265625 }, { "start": 1749.16, "end": 1749.3, "word": " we're", "probability": 0.928466796875 }, { "start": 1749.3, "end": 1749.36, "word": " going", "probability": 0.837890625 }, { "start": 1749.36, "end": 1749.4, "word": " to", "probability": 0.90234375 }, { "start": 1749.4, "end": 1749.5, "word": " do", "probability": 0.908203125 } ] }, { "id": 778, "seek": 173624, "start": 1749.5, "end": 1750.56, "text": " the same thing for spam and", "tokens": [ 51464, 264, 912, 551, 337, 24028, 293, 51514 ], "temperature": 0.0, "avg_logprob": -0.15899332083818565, "compression_ratio": 2.05, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1749.5, "end": 1749.64, "word": " the", "probability": 0.81640625 }, { "start": 1749.64, "end": 1749.8, "word": " same", "probability": 0.8173828125 }, { "start": 1749.8, "end": 1749.98, "word": " thing", "probability": 0.80908203125 }, { "start": 1749.98, "end": 1750.12, "word": " for", "probability": 0.90087890625 }, { "start": 1750.12, "end": 1750.4, "word": " spam", "probability": 0.92333984375 }, { "start": 1750.4, "end": 1750.56, "word": " and", "probability": 0.89990234375 } ] }, { "id": 779, "seek": 173624, "start": 1750.56, "end": 1751.54, "text": " ham. We're going to load the", "tokens": [ 51564, 7852, 13, 492, 434, 516, 281, 3677, 264, 51614 ], "temperature": 0.0, "avg_logprob": -0.15899332083818565, "compression_ratio": 2.05, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1750.56, "end": 1750.72, "word": " ham", "probability": 0.86083984375 }, { "start": 1750.72, "end": 1750.78, "word": ".", "probability": 0.94384765625 }, { "start": 1750.78, "end": 1750.92, "word": " We're", "probability": 0.929443359375 }, { "start": 1750.92, "end": 1751.0, "word": " going", "probability": 0.85302734375 }, { "start": 1751.0, "end": 1751.1, "word": " to", "probability": 0.9033203125 }, { "start": 1751.1, "end": 1751.36, "word": " load", "probability": 0.92236328125 }, { "start": 1751.36, "end": 1751.54, "word": " the", "probability": 0.81591796875 } ] }, { "id": 780, "seek": 173624, "start": 1751.54, "end": 1753.98, "text": " email bodies from the ham", "tokens": [ 51664, 3796, 7510, 490, 264, 7852, 51714 ], "temperature": 0.0, "avg_logprob": -0.15899332083818565, "compression_ratio": 2.05, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1751.54, "end": 1751.84, "word": " email", "probability": 0.912109375 }, { "start": 1751.84, "end": 1752.36, "word": " bodies", "probability": 0.771484375 }, { "start": 1752.36, "end": 1753.5, "word": " from", "probability": 0.80029296875 }, { "start": 1753.5, "end": 1753.76, "word": " the", "probability": 0.81298828125 }, { "start": 1753.76, "end": 1753.98, "word": " ham", "probability": 0.904296875 } ] }, { "id": 781, "seek": 173624, "start": 1753.98, "end": 1754.94, "text": " directories and the spam", "tokens": [ 51764, 5391, 530, 293, 264, 24028, 51814 ], "temperature": 0.0, "avg_logprob": -0.15899332083818565, "compression_ratio": 2.05, "no_speech_prob": 0.0008831024169921875, "words": [ { "start": 1753.98, "end": 1754.46, "word": " directories", "probability": 0.854248046875 }, { "start": 1754.46, "end": 1754.6, "word": " and", "probability": 0.8193359375 }, { "start": 1754.6, "end": 1754.74, "word": " the", "probability": 0.806640625 }, { "start": 1754.74, "end": 1754.94, "word": " spam", "probability": 0.93505859375 } ] }, { "id": 782, "seek": 176624, "start": 1754.94, "end": 1756.52, "text": " directory into the corpus", "tokens": [ 50364, 21120, 666, 264, 1181, 31624, 50414 ], "temperature": 0.0, "avg_logprob": -0.23988309180993828, "compression_ratio": 1.9817351598173516, "no_speech_prob": 0.0029354095458984375, "words": [ { "start": 1754.94, "end": 1755.4, "word": " directory", "probability": 0.2486572265625 }, { "start": 1755.4, "end": 1756.08, "word": " into", "probability": 0.751953125 }, { "start": 1756.08, "end": 1756.24, "word": " the", "probability": 0.814453125 }, { "start": 1756.24, "end": 1756.52, "word": " corpus", "probability": 0.822998046875 } ] }, { "id": 783, "seek": 176624, "start": 1756.52, "end": 1757.12, "text": " array, and then we're going", "tokens": [ 50414, 10225, 11, 293, 550, 321, 434, 516, 50464 ], "temperature": 0.0, "avg_logprob": -0.23988309180993828, "compression_ratio": 1.9817351598173516, "no_speech_prob": 0.0029354095458984375, "words": [ { "start": 1756.52, "end": 1756.76, "word": " array", "probability": 0.697265625 }, { "start": 1756.76, "end": 1756.86, "word": ",", "probability": 0.2705078125 }, { "start": 1756.86, "end": 1756.9, "word": " and", "probability": 0.8662109375 }, { "start": 1756.9, "end": 1756.96, "word": " then", "probability": 0.65087890625 }, { "start": 1756.96, "end": 1757.08, "word": " we're", "probability": 0.908935546875 }, { "start": 1757.08, "end": 1757.12, "word": " going", "probability": 0.69384765625 } ] }, { "id": 784, "seek": 176624, "start": 1757.12, "end": 1758.26, "text": " to load the labels for each", "tokens": [ 50464, 281, 3677, 264, 16949, 337, 1184, 50514 ], "temperature": 0.0, "avg_logprob": -0.23988309180993828, "compression_ratio": 1.9817351598173516, "no_speech_prob": 0.0029354095458984375, "words": [ { "start": 1757.12, "end": 1757.16, "word": " to", "probability": 0.90234375 }, { "start": 1757.16, "end": 1757.3, "word": " load", "probability": 0.90185546875 }, { "start": 1757.3, "end": 1757.52, "word": " the", "probability": 0.81640625 }, { "start": 1757.52, "end": 1757.84, "word": " labels", "probability": 0.8515625 }, { "start": 1757.84, "end": 1758.02, "word": " for", "probability": 0.89306640625 }, { "start": 1758.02, "end": 1758.26, "word": " each", "probability": 0.85693359375 } ] }, { "id": 785, "seek": 176624, "start": 1758.26, "end": 1760.38, "text": " email into the labels array.", "tokens": [ 50514, 3796, 666, 264, 16949, 10225, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.23988309180993828, "compression_ratio": 1.9817351598173516, "no_speech_prob": 0.0029354095458984375, "words": [ { "start": 1758.26, "end": 1758.6, "word": " email", "probability": 0.9169921875 }, { "start": 1758.6, "end": 1758.94, "word": " into", "probability": 0.73974609375 }, { "start": 1758.94, "end": 1759.2, "word": " the", "probability": 0.81591796875 }, { "start": 1759.2, "end": 1759.54, "word": " labels", "probability": 0.83203125 }, { "start": 1759.54, "end": 1759.94, "word": " array", "probability": 0.7412109375 }, { "start": 1759.94, "end": 1760.38, "word": ".", "probability": 0.951171875 } ] }, { "id": 786, "seek": 176624, "start": 1760.98, "end": 1761.72, "text": " So what that's going to", "tokens": [ 50614, 407, 437, 300, 311, 516, 281, 50664 ], "temperature": 0.0, "avg_logprob": -0.23988309180993828, "compression_ratio": 1.9817351598173516, "no_speech_prob": 0.0029354095458984375, "words": [ { "start": 1760.98, "end": 1761.18, "word": " So", "probability": 0.75146484375 }, { "start": 1761.18, "end": 1761.38, "word": " what", "probability": 0.75048828125 }, { "start": 1761.38, "end": 1761.58, "word": " that's", "probability": 0.93603515625 }, { "start": 1761.58, "end": 1761.66, "word": " going", "probability": 0.8466796875 }, { "start": 1761.66, "end": 1761.72, "word": " to", "probability": 0.90625 } ] }, { "id": 787, "seek": 176624, "start": 1761.72, "end": 1762.3, "text": " look like is we're going to", "tokens": [ 50664, 574, 411, 307, 321, 434, 516, 281, 50714 ], "temperature": 0.0, "avg_logprob": -0.23988309180993828, "compression_ratio": 1.9817351598173516, "no_speech_prob": 0.0029354095458984375, "words": [ { "start": 1761.72, "end": 1761.86, "word": " look", "probability": 0.9189453125 }, { "start": 1761.86, "end": 1762.0, "word": " like", "probability": 0.87841796875 }, { "start": 1762.0, "end": 1762.1, "word": " is", "probability": 0.8388671875 }, { "start": 1762.1, "end": 1762.2, "word": " we're", "probability": 0.5848388671875 }, { "start": 1762.2, "end": 1762.3, "word": " going", "probability": 0.75830078125 }, { "start": 1762.3, "end": 1762.3, "word": " to", "probability": 0.90478515625 } ] }, { "id": 788, "seek": 176624, "start": 1762.3, "end": 1763.28, "text": " use a for loop here, so", "tokens": [ 50714, 764, 257, 337, 6367, 510, 11, 370, 50764 ], "temperature": 0.0, "avg_logprob": -0.23988309180993828, "compression_ratio": 1.9817351598173516, "no_speech_prob": 0.0029354095458984375, "words": [ { "start": 1762.3, "end": 1762.4, "word": " use", "probability": 0.82958984375 }, { "start": 1762.54, "end": 1762.72, "word": " a for", "probability": 0.75341796875 }, { "start": 1762.72, "end": 1762.92, "word": " loop", "probability": 0.86669921875 }, { "start": 1762.92, "end": 1763.12, "word": " here", "probability": 0.80859375 }, { "start": 1763.12, "end": 1763.2, "word": ",", "probability": 0.41015625 }, { "start": 1763.2, "end": 1763.28, "word": " so", "probability": 0.88427734375 } ] }, { "id": 789, "seek": 176624, "start": 1763.28, "end": 1765.2, "text": " we can say for each in", "tokens": [ 50764, 321, 393, 584, 337, 1184, 294, 50814 ], "temperature": 0.0, "avg_logprob": -0.23988309180993828, "compression_ratio": 1.9817351598173516, "no_speech_prob": 0.0029354095458984375, "words": [ { "start": 1763.28, "end": 1763.4, "word": " we", "probability": 0.89990234375 }, { "start": 1763.4, "end": 1763.5, "word": " can", "probability": 0.896484375 }, { "start": 1763.5, "end": 1763.7, "word": " say", "probability": 0.89404296875 }, { "start": 1763.7, "end": 1764.16, "word": " for", "probability": 0.57373046875 }, { "start": 1764.16, "end": 1764.7, "word": " each", "probability": 0.8037109375 }, { "start": 1764.7, "end": 1765.2, "word": " in", "probability": 0.8388671875 } ] }, { "id": 790, "seek": 176624, "start": 1765.2, "end": 1767.78, "text": " os.listdir, and then we", "tokens": [ 50864, 3003, 13, 8264, 35043, 11, 293, 550, 321, 50914 ], "temperature": 0.0, "avg_logprob": -0.23988309180993828, "compression_ratio": 1.9817351598173516, "no_speech_prob": 0.0029354095458984375, "words": [ { "start": 1765.2, "end": 1765.6, "word": " os", "probability": 0.728515625 }, { "start": 1765.6, "end": 1766.68, "word": ".listdir", "probability": 0.8395182291666666 }, { "start": 1766.68, "end": 1767.1, "word": ",", "probability": 0.53515625 }, { "start": 1767.1, "end": 1767.6, "word": " and", "probability": 0.89208984375 }, { "start": 1767.6, "end": 1767.68, "word": " then", "probability": 0.734375 }, { "start": 1767.68, "end": 1767.78, "word": " we", "probability": 0.9091796875 } ] }, { "id": 791, "seek": 176624, "start": 1767.78, "end": 1769.34, "text": " have our data directory,", "tokens": [ 50964, 362, 527, 1412, 21120, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.23988309180993828, "compression_ratio": 1.9817351598173516, "no_speech_prob": 0.0029354095458984375, "words": [ { "start": 1767.78, "end": 1767.98, "word": " have", "probability": 0.8759765625 }, { "start": 1767.98, "end": 1768.34, "word": " our", "probability": 0.81298828125 }, { "start": 1768.34, "end": 1768.66, "word": " data", "probability": 0.80126953125 }, { "start": 1768.66, "end": 1769.12, "word": " directory", "probability": 0.81591796875 }, { "start": 1769.12, "end": 1769.34, "word": ",", "probability": 0.494873046875 } ] }, { "id": 792, "seek": 176624, "start": 1769.34, "end": 1771.4, "text": " which is defined above.", "tokens": [ 51064, 597, 307, 7642, 3673, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.23988309180993828, "compression_ratio": 1.9817351598173516, "no_speech_prob": 0.0029354095458984375, "words": [ { "start": 1769.34, "end": 1769.44, "word": " which", "probability": 0.90966796875 }, { "start": 1769.44, "end": 1769.68, "word": " is", "probability": 0.90966796875 }, { "start": 1769.68, "end": 1770.2, "word": " defined", "probability": 0.744140625 }, { "start": 1770.2, "end": 1770.96, "word": " above", "probability": 0.87744140625 }, { "start": 1770.96, "end": 1771.4, "word": ".", "probability": 0.8798828125 } ] }, { "id": 793, "seek": 176624, "start": 1771.9, "end": 1773.26, "text": " We're going to look at our", "tokens": [ 51164, 492, 434, 516, 281, 574, 412, 527, 51214 ], "temperature": 0.0, "avg_logprob": -0.23988309180993828, "compression_ratio": 1.9817351598173516, "no_speech_prob": 0.0029354095458984375, "words": [ { "start": 1771.9, "end": 1772.34, "word": " We're", "probability": 0.920166015625 }, { "start": 1772.34, "end": 1772.38, "word": " going", "probability": 0.8173828125 }, { "start": 1772.38, "end": 1772.4, "word": " to", "probability": 0.900390625 }, { "start": 1772.4, "end": 1772.56, "word": " look", "probability": 0.9228515625 }, { "start": 1772.56, "end": 1772.8, "word": " at", "probability": 0.90673828125 }, { "start": 1772.8, "end": 1773.26, "word": " our", "probability": 0.81298828125 } ] }, { "id": 794, "seek": 176624, "start": 1773.82, "end": 1775.26, "text": " ham directory for this", "tokens": [ 51264, 7852, 21120, 337, 341, 51314 ], "temperature": 0.0, "avg_logprob": -0.23988309180993828, "compression_ratio": 1.9817351598173516, "no_speech_prob": 0.0029354095458984375, "words": [ { "start": 1773.82, "end": 1774.26, "word": " ham", "probability": 0.7529296875 }, { "start": 1774.26, "end": 1774.7, "word": " directory", "probability": 0.79345703125 }, { "start": 1774.7, "end": 1775.08, "word": " for", "probability": 0.8828125 }, { "start": 1775.08, "end": 1775.26, "word": " this", "probability": 0.88134765625 } ] }, { "id": 795, "seek": 176624, "start": 1775.26, "end": 1777.48, "text": " first round. With each", "tokens": [ 51364, 700, 3098, 13, 2022, 1184, 51414 ], "temperature": 0.0, "avg_logprob": -0.23988309180993828, "compression_ratio": 1.9817351598173516, "no_speech_prob": 0.0029354095458984375, "words": [ { "start": 1775.26, "end": 1775.5, "word": " first", "probability": 0.8076171875 }, { "start": 1775.5, "end": 1775.88, "word": " round", "probability": 0.8642578125 }, { "start": 1775.88, "end": 1776.08, "word": ".", "probability": 0.52197265625 }, { "start": 1776.76, "end": 1777.2, "word": " With", "probability": 0.869140625 }, { "start": 1777.2, "end": 1777.48, "word": " each", "probability": 0.86767578125 } ] }, { "id": 796, "seek": 176624, "start": 1777.48, "end": 1778.8, "text": " open file, we're going to", "tokens": [ 51464, 1269, 3991, 11, 321, 434, 516, 281, 51514 ], "temperature": 0.0, "avg_logprob": -0.23988309180993828, "compression_ratio": 1.9817351598173516, "no_speech_prob": 0.0029354095458984375, "words": [ { "start": 1777.48, "end": 1777.78, "word": " open", "probability": 0.8037109375 }, { "start": 1777.78, "end": 1778.24, "word": " file", "probability": 0.80029296875 }, { "start": 1778.24, "end": 1778.44, "word": ",", "probability": 0.6162109375 }, { "start": 1778.44, "end": 1778.66, "word": " we're", "probability": 0.9296875 }, { "start": 1778.66, "end": 1778.72, "word": " going", "probability": 0.8388671875 }, { "start": 1778.72, "end": 1778.8, "word": " to", "probability": 0.90087890625 } ] }, { "id": 797, "seek": 176624, "start": 1778.8, "end": 1781.7, "text": " look at our data directory", "tokens": [ 51564, 574, 412, 527, 1412, 21120, 51614 ], "temperature": 0.0, "avg_logprob": -0.23988309180993828, "compression_ratio": 1.9817351598173516, "no_speech_prob": 0.0029354095458984375, "words": [ { "start": 1778.8, "end": 1778.98, "word": " look", "probability": 0.92138671875 }, { "start": 1778.98, "end": 1779.36, "word": " at", "probability": 0.9013671875 }, { "start": 1779.36, "end": 1779.84, "word": " our", "probability": 0.806640625 }, { "start": 1779.84, "end": 1781.24, "word": " data", "probability": 0.79736328125 }, { "start": 1781.24, "end": 1781.7, "word": " directory", "probability": 0.79541015625 } ] }, { "id": 798, "seek": 176624, "start": 1781.7, "end": 1784.92, "text": " plus ham plus os.listdir.", "tokens": [ 51664, 1804, 7852, 1804, 3003, 13, 8264, 35043, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.23988309180993828, "compression_ratio": 1.9817351598173516, "no_speech_prob": 0.0029354095458984375, "words": [ { "start": 1781.7, "end": 1782.52, "word": " plus", "probability": 0.61669921875 }, { "start": 1782.52, "end": 1783.58, "word": " ham", "probability": 0.9033203125 }, { "start": 1783.58, "end": 1784.8, "word": " plus", "probability": 0.7666015625 }, { "start": 1784.8, "end": 1784.92, "word": " os", "probability": 0.214111328125 }, { "start": 1784.92, "end": 1784.92, "word": ".listdir", "probability": 0.7923177083333334 }, { "start": 1784.92, "end": 1784.92, "word": ".", "probability": 0.68603515625 } ] }, { "id": 799, "seek": 179624, "start": 1784.94, "end": 1785.32, "text": " We're going to look at", "tokens": [ 50364, 492, 434, 516, 281, 574, 412, 50414 ], "temperature": 0.0, "avg_logprob": -0.25396455957818387, "compression_ratio": 1.7566371681415929, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 1784.94, "end": 1785.32, "word": " We're", "probability": 0.2581787109375 }, { "start": 1785.32, "end": 1785.32, "word": " going", "probability": 0.65283203125 }, { "start": 1785.32, "end": 1785.32, "word": " to", "probability": 0.90673828125 }, { "start": 1785.32, "end": 1785.32, "word": " look", "probability": 0.0009975433349609375 }, { "start": 1785.32, "end": 1785.32, "word": " at", "probability": 0.65869140625 } ] }, { "id": 800, "seek": 179624, "start": 1785.32, "end": 1786.86, "text": " each, because each is the", "tokens": [ 50414, 1184, 11, 570, 1184, 307, 264, 50464 ], "temperature": 0.0, "avg_logprob": -0.25396455957818387, "compression_ratio": 1.7566371681415929, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 1785.32, "end": 1785.32, "word": " each", "probability": 0.51806640625 }, { "start": 1785.32, "end": 1785.44, "word": ",", "probability": 0.30712890625 }, { "start": 1785.44, "end": 1785.82, "word": " because", "probability": 0.7509765625 }, { "start": 1785.82, "end": 1786.14, "word": " each", "probability": 0.7998046875 }, { "start": 1786.14, "end": 1786.5, "word": " is", "probability": 0.9091796875 }, { "start": 1786.5, "end": 1786.86, "word": " the", "probability": 0.8076171875 } ] }, { "id": 801, "seek": 179624, "start": 1786.86, "end": 1788.28, "text": " name of our file, and", "tokens": [ 50464, 1315, 295, 527, 3991, 11, 293, 50514 ], "temperature": 0.0, "avg_logprob": -0.25396455957818387, "compression_ratio": 1.7566371681415929, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 1786.86, "end": 1787.22, "word": " name", "probability": 0.7734375 }, { "start": 1787.22, "end": 1787.52, "word": " of", "probability": 0.8994140625 }, { "start": 1787.52, "end": 1787.74, "word": " our", "probability": 0.7978515625 }, { "start": 1787.74, "end": 1788.08, "word": " file", "probability": 0.7919921875 }, { "start": 1788.08, "end": 1788.24, "word": ",", "probability": 0.51025390625 }, { "start": 1788.24, "end": 1788.28, "word": " and", "probability": 0.87255859375 } ] }, { "id": 802, "seek": 179624, "start": 1788.28, "end": 1788.84, "text": " we're going to want to", "tokens": [ 50514, 321, 434, 516, 281, 528, 281, 50564 ], "temperature": 0.0, "avg_logprob": -0.25396455957818387, "compression_ratio": 1.7566371681415929, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 1788.28, "end": 1788.44, "word": " we're", "probability": 0.90966796875 }, { "start": 1788.44, "end": 1788.52, "word": " going", "probability": 0.78125 }, { "start": 1788.52, "end": 1788.58, "word": " to", "probability": 0.9052734375 }, { "start": 1788.58, "end": 1788.72, "word": " want", "probability": 0.78125 }, { "start": 1788.72, "end": 1788.84, "word": " to", "probability": 0.9052734375 } ] }, { "id": 803, "seek": 179624, "start": 1788.84, "end": 1790.84, "text": " read those as the file", "tokens": [ 50564, 1401, 729, 382, 264, 3991, 50614 ], "temperature": 0.0, "avg_logprob": -0.25396455957818387, "compression_ratio": 1.7566371681415929, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 1788.84, "end": 1789.12, "word": " read", "probability": 0.88525390625 }, { "start": 1789.12, "end": 1789.54, "word": " those", "probability": 0.830078125 }, { "start": 1789.54, "end": 1790.4, "word": " as", "probability": 0.90234375 }, { "start": 1790.4, "end": 1790.62, "word": " the", "probability": 0.8095703125 }, { "start": 1790.62, "end": 1790.84, "word": " file", "probability": 0.74462890625 } ] }, { "id": 804, "seek": 179624, "start": 1790.84, "end": 1792.98, "text": " descriptor f. So for", "tokens": [ 50664, 31280, 284, 283, 13, 407, 337, 50714 ], "temperature": 0.0, "avg_logprob": -0.25396455957818387, "compression_ratio": 1.7566371681415929, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 1790.84, "end": 1791.38, "word": " descriptor", "probability": 0.8681640625 }, { "start": 1791.7, "end": 1792.24, "word": " f.", "probability": 0.94482421875 }, { "start": 1792.42, "end": 1792.74, "word": " So", "probability": 0.595703125 }, { "start": 1792.74, "end": 1792.98, "word": " for", "probability": 0.6796875 } ] }, { "id": 805, "seek": 179624, "start": 1792.98, "end": 1795.8, "text": " our corpus, we can do", "tokens": [ 50764, 527, 1181, 31624, 11, 321, 393, 360, 50864 ], "temperature": 0.0, "avg_logprob": -0.25396455957818387, "compression_ratio": 1.7566371681415929, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 1792.98, "end": 1793.18, "word": " our", "probability": 0.77783203125 }, { "start": 1793.18, "end": 1793.64, "word": " corpus", "probability": 0.874755859375 }, { "start": 1793.64, "end": 1794.44, "word": ",", "probability": 0.72265625 }, { "start": 1794.44, "end": 1795.28, "word": " we", "probability": 0.880859375 }, { "start": 1795.28, "end": 1795.48, "word": " can", "probability": 0.8974609375 }, { "start": 1795.48, "end": 1795.8, "word": " do", "probability": 0.90380859375 } ] }, { "id": 806, "seek": 179624, "start": 1795.8, "end": 1799.32, "text": " an append and then f.read.", "tokens": [ 50914, 364, 34116, 293, 550, 283, 13, 2538, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.25396455957818387, "compression_ratio": 1.7566371681415929, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 1795.8, "end": 1796.22, "word": " an", "probability": 0.82666015625 }, { "start": 1796.22, "end": 1796.76, "word": " append", "probability": 0.76708984375 }, { "start": 1796.76, "end": 1798.34, "word": " and", "probability": 0.439697265625 }, { "start": 1798.34, "end": 1798.5, "word": " then", "probability": 0.72705078125 }, { "start": 1798.7, "end": 1799.16, "word": " f.read", "probability": 0.901611328125 }, { "start": 1799.16, "end": 1799.32, "word": ".", "probability": 0.63427734375 } ] }, { "id": 807, "seek": 179624, "start": 1799.32, "end": 1800.38, "text": " So this will read each", "tokens": [ 51064, 407, 341, 486, 1401, 1184, 51114 ], "temperature": 0.0, "avg_logprob": -0.25396455957818387, "compression_ratio": 1.7566371681415929, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 1799.32, "end": 1799.48, "word": " So", "probability": 0.66943359375 }, { "start": 1799.48, "end": 1799.62, "word": " this", "probability": 0.8603515625 }, { "start": 1799.62, "end": 1799.78, "word": " will", "probability": 0.81689453125 }, { "start": 1799.78, "end": 1800.08, "word": " read", "probability": 0.9091796875 }, { "start": 1800.08, "end": 1800.38, "word": " each", "probability": 0.849609375 } ] }, { "id": 808, "seek": 179624, "start": 1800.38, "end": 1801.5, "text": " email into our corpus", "tokens": [ 51114, 3796, 666, 527, 1181, 31624, 51164 ], "temperature": 0.0, "avg_logprob": -0.25396455957818387, "compression_ratio": 1.7566371681415929, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 1800.38, "end": 1800.66, "word": " email", "probability": 0.89013671875 }, { "start": 1800.66, "end": 1800.96, "word": " into", "probability": 0.75341796875 }, { "start": 1800.96, "end": 1801.16, "word": " our", "probability": 0.81298828125 }, { "start": 1801.16, "end": 1801.5, "word": " corpus", "probability": 0.9189453125 } ] }, { "id": 809, "seek": 179624, "start": 1801.5, "end": 1803.42, "text": " and then labels.append", "tokens": [ 51214, 293, 550, 16949, 13, 1746, 521, 51264 ], "temperature": 0.0, "avg_logprob": -0.25396455957818387, "compression_ratio": 1.7566371681415929, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 1801.5, "end": 1801.74, "word": " and", "probability": 0.434326171875 }, { "start": 1801.74, "end": 1801.94, "word": " then", "probability": 0.70947265625 }, { "start": 1801.94, "end": 1802.42, "word": " labels", "probability": 0.80224609375 }, { "start": 1802.42, "end": 1803.42, "word": ".append", "probability": 0.9070638020833334 } ] }, { "id": 810, "seek": 179624, "start": 1804.08, "end": 1806.56, "text": " ham, because we know", "tokens": [ 51314, 7852, 11, 570, 321, 458, 51414 ], "temperature": 0.0, "avg_logprob": -0.25396455957818387, "compression_ratio": 1.7566371681415929, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 1804.08, "end": 1804.62, "word": " ham", "probability": 0.49462890625 }, { "start": 1804.62, "end": 1805.0, "word": ",", "probability": 0.2255859375 }, { "start": 1805.0, "end": 1806.22, "word": " because", "probability": 0.810546875 }, { "start": 1806.22, "end": 1806.4, "word": " we", "probability": 0.9033203125 }, { "start": 1806.4, "end": 1806.56, "word": " know", "probability": 0.8193359375 } ] }, { "id": 811, "seek": 179624, "start": 1806.56, "end": 1808.38, "text": " that all of the emails", "tokens": [ 51414, 300, 439, 295, 264, 12524, 51464 ], "temperature": 0.0, "avg_logprob": -0.25396455957818387, "compression_ratio": 1.7566371681415929, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 1806.56, "end": 1806.72, "word": " that", "probability": 0.85888671875 }, { "start": 1806.72, "end": 1806.88, "word": " all", "probability": 0.89111328125 }, { "start": 1806.88, "end": 1806.98, "word": " of", "probability": 0.662109375 }, { "start": 1806.98, "end": 1807.1, "word": " the", "probability": 0.80810546875 }, { "start": 1807.1, "end": 1808.38, "word": " emails", "probability": 0.7587890625 } ] }, { "id": 812, "seek": 179624, "start": 1808.38, "end": 1809.44, "text": " in the ham directory are", "tokens": [ 51514, 294, 264, 7852, 21120, 366, 51564 ], "temperature": 0.0, "avg_logprob": -0.25396455957818387, "compression_ratio": 1.7566371681415929, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 1808.38, "end": 1808.56, "word": " in", "probability": 0.892578125 }, { "start": 1808.56, "end": 1808.66, "word": " the", "probability": 0.80810546875 }, { "start": 1808.66, "end": 1808.78, "word": " ham", "probability": 0.81494140625 }, { "start": 1808.78, "end": 1809.14, "word": " directory", "probability": 0.7998046875 }, { "start": 1809.14, "end": 1809.44, "word": " are", "probability": 0.8896484375 } ] }, { "id": 813, "seek": 179624, "start": 1809.44, "end": 1812.38, "text": " part of the ham data set.", "tokens": [ 51564, 644, 295, 264, 7852, 1412, 992, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.25396455957818387, "compression_ratio": 1.7566371681415929, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 1809.44, "end": 1809.66, "word": " part", "probability": 0.81591796875 }, { "start": 1809.66, "end": 1809.78, "word": " of", "probability": 0.904296875 }, { "start": 1809.78, "end": 1809.98, "word": " the", "probability": 0.81005859375 }, { "start": 1809.98, "end": 1810.42, "word": " ham", "probability": 0.890625 }, { "start": 1810.42, "end": 1811.52, "word": " data", "probability": 0.315185546875 }, { "start": 1811.52, "end": 1811.84, "word": " set", "probability": 0.88330078125 }, { "start": 1811.84, "end": 1812.38, "word": ".", "probability": 0.8017578125 } ] }, { "id": 814, "seek": 179624, "start": 1812.46, "end": 1813.66, "text": " And so we can easily do", "tokens": [ 51714, 400, 370, 321, 393, 3612, 360, 51764 ], "temperature": 0.0, "avg_logprob": -0.25396455957818387, "compression_ratio": 1.7566371681415929, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 1812.46, "end": 1812.54, "word": " And", "probability": 0.73828125 }, { "start": 1812.54, "end": 1812.74, "word": " so", "probability": 0.89990234375 }, { "start": 1812.74, "end": 1812.9, "word": " we", "probability": 0.84423828125 }, { "start": 1812.9, "end": 1813.06, "word": " can", "probability": 0.8935546875 }, { "start": 1813.06, "end": 1813.42, "word": " easily", "probability": 0.85986328125 }, { "start": 1813.42, "end": 1813.66, "word": " do", "probability": 0.9013671875 } ] }, { "id": 815, "seek": 179624, "start": 1813.66, "end": 1814.92, "text": " the same thing for spam", "tokens": [ 51764, 264, 912, 551, 337, 24028, 51814 ], "temperature": 0.0, "avg_logprob": -0.25396455957818387, "compression_ratio": 1.7566371681415929, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 1813.66, "end": 1813.84, "word": " the", "probability": 0.802734375 }, { "start": 1813.84, "end": 1814.1, "word": " same", "probability": 0.8173828125 }, { "start": 1814.1, "end": 1814.5, "word": " thing", "probability": 0.8134765625 }, { "start": 1814.5, "end": 1814.82, "word": " for", "probability": 0.7587890625 }, { "start": 1814.82, "end": 1814.92, "word": " spam", "probability": 0.0814208984375 } ] }, { "id": 816, "seek": 182600, "start": 1814.94, "end": 1815.94, "text": " which is we need to be", "tokens": [ 50364, 597, 307, 321, 643, 281, 312, 50414 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1814.94, "end": 1815.38, "word": " which", "probability": 0.044097900390625 }, { "start": 1815.38, "end": 1815.56, "word": " is", "probability": 0.63671875 }, { "start": 1815.56, "end": 1815.66, "word": " we", "probability": 0.023193359375 }, { "start": 1815.66, "end": 1815.74, "word": " need", "probability": 0.64794921875 }, { "start": 1815.74, "end": 1815.78, "word": " to", "probability": 0.90771484375 }, { "start": 1815.78, "end": 1815.94, "word": " be", "probability": 0.896484375 } ] }, { "id": 817, "seek": 182600, "start": 1815.94, "end": 1817.3, "text": " careful on how we change", "tokens": [ 50414, 5026, 322, 577, 321, 1319, 50464 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1815.94, "end": 1816.4, "word": " careful", "probability": 0.90283203125 }, { "start": 1816.4, "end": 1816.72, "word": " on", "probability": 0.73388671875 }, { "start": 1816.72, "end": 1816.88, "word": " how", "probability": 0.89453125 }, { "start": 1816.88, "end": 1817.02, "word": " we", "probability": 0.88671875 }, { "start": 1817.02, "end": 1817.3, "word": " change", "probability": 0.810546875 } ] }, { "id": 818, "seek": 182600, "start": 1817.3, "end": 1818.32, "text": " this. So instead of", "tokens": [ 50464, 341, 13, 407, 2602, 295, 50514 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1817.3, "end": 1817.54, "word": " this", "probability": 0.8642578125 }, { "start": 1817.54, "end": 1817.78, "word": ".", "probability": 0.446044921875 }, { "start": 1817.78, "end": 1817.78, "word": " So", "probability": 0.7314453125 }, { "start": 1817.78, "end": 1818.14, "word": " instead", "probability": 0.6796875 }, { "start": 1818.14, "end": 1818.32, "word": " of", "probability": 0.89501953125 } ] }, { "id": 819, "seek": 182600, "start": 1818.32, "end": 1819.28, "text": " slash ham, it's going to", "tokens": [ 50514, 17330, 7852, 11, 309, 311, 516, 281, 50564 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1818.32, "end": 1818.64, "word": " slash", "probability": 0.08123779296875 }, { "start": 1818.64, "end": 1818.92, "word": " ham", "probability": 0.5380859375 }, { "start": 1818.92, "end": 1819.0, "word": ",", "probability": 0.5185546875 }, { "start": 1819.0, "end": 1819.12, "word": " it's", "probability": 0.932861328125 }, { "start": 1819.12, "end": 1819.24, "word": " going", "probability": 0.51611328125 }, { "start": 1819.24, "end": 1819.28, "word": " to", "probability": 0.9033203125 } ] }, { "id": 820, "seek": 182600, "start": 1819.28, "end": 1821.44, "text": " be slash spam, and then", "tokens": [ 50564, 312, 17330, 24028, 11, 293, 550, 50664 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1819.28, "end": 1819.5, "word": " be", "probability": 0.89111328125 }, { "start": 1819.5, "end": 1820.44, "word": " slash", "probability": 0.75146484375 }, { "start": 1820.44, "end": 1821.04, "word": " spam", "probability": 0.89990234375 }, { "start": 1821.04, "end": 1821.28, "word": ",", "probability": 0.18701171875 }, { "start": 1821.28, "end": 1821.34, "word": " and", "probability": 0.88525390625 }, { "start": 1821.34, "end": 1821.44, "word": " then", "probability": 0.6884765625 } ] }, { "id": 821, "seek": 182600, "start": 1821.44, "end": 1822.64, "text": " of course our label is", "tokens": [ 50664, 295, 1164, 527, 7645, 307, 50714 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1821.44, "end": 1821.58, "word": " of", "probability": 0.7978515625 }, { "start": 1821.58, "end": 1821.76, "word": " course", "probability": 0.86279296875 }, { "start": 1821.76, "end": 1821.98, "word": " our", "probability": 0.57275390625 }, { "start": 1821.98, "end": 1822.34, "word": " label", "probability": 0.80908203125 }, { "start": 1822.34, "end": 1822.64, "word": " is", "probability": 0.9013671875 } ] }, { "id": 822, "seek": 182600, "start": 1822.64, "end": 1824.14, "text": " also going to be spam.", "tokens": [ 50714, 611, 516, 281, 312, 24028, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1822.64, "end": 1822.92, "word": " also", "probability": 0.8251953125 }, { "start": 1822.92, "end": 1823.14, "word": " going", "probability": 0.86865234375 }, { "start": 1823.14, "end": 1823.26, "word": " to", "probability": 0.90673828125 }, { "start": 1823.26, "end": 1823.4, "word": " be", "probability": 0.89892578125 }, { "start": 1823.4, "end": 1823.7, "word": " spam", "probability": 0.86572265625 }, { "start": 1823.7, "end": 1824.14, "word": ".", "probability": 0.99169921875 } ] }, { "id": 823, "seek": 182600, "start": 1826.06, "end": 1827.26, "text": " So I'm going to let this", "tokens": [ 50914, 407, 286, 478, 516, 281, 718, 341, 50964 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1826.06, "end": 1826.5, "word": " So", "probability": 0.822265625 }, { "start": 1826.5, "end": 1826.94, "word": " I'm", "probability": 0.8818359375 }, { "start": 1826.94, "end": 1826.98, "word": " going", "probability": 0.67919921875 }, { "start": 1826.98, "end": 1826.98, "word": " to", "probability": 0.896484375 }, { "start": 1826.98, "end": 1827.12, "word": " let", "probability": 0.89404296875 }, { "start": 1827.12, "end": 1827.26, "word": " this", "probability": 0.87890625 } ] }, { "id": 824, "seek": 182600, "start": 1827.26, "end": 1828.1, "text": " sit for a minute and let", "tokens": [ 50964, 1394, 337, 257, 3456, 293, 718, 51014 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1827.26, "end": 1827.42, "word": " sit", "probability": 0.9111328125 }, { "start": 1827.42, "end": 1827.58, "word": " for", "probability": 0.8974609375 }, { "start": 1827.7, "end": 1827.82, "word": " a minute", "probability": 0.89013671875 }, { "start": 1827.82, "end": 1827.98, "word": " and", "probability": 0.127685546875 }, { "start": 1827.98, "end": 1828.1, "word": " let", "probability": 0.8857421875 } ] }, { "id": 825, "seek": 182600, "start": 1828.1, "end": 1829.76, "text": " you guys go ahead and", "tokens": [ 51014, 291, 1074, 352, 2286, 293, 51064 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1828.1, "end": 1828.2, "word": " you", "probability": 0.8935546875 }, { "start": 1828.2, "end": 1828.6, "word": " guys", "probability": 0.875 }, { "start": 1828.6, "end": 1829.38, "word": " go", "probability": 0.82470703125 }, { "start": 1829.38, "end": 1829.64, "word": " ahead", "probability": 0.83984375 }, { "start": 1829.64, "end": 1829.76, "word": " and", "probability": 0.8798828125 } ] }, { "id": 826, "seek": 182600, "start": 1829.76, "end": 1830.5, "text": " make sure that you copy", "tokens": [ 51064, 652, 988, 300, 291, 5055, 51114 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1829.76, "end": 1829.88, "word": " make", "probability": 0.88037109375 }, { "start": 1829.88, "end": 1830.0, "word": " sure", "probability": 0.81494140625 }, { "start": 1830.0, "end": 1830.1, "word": " that", "probability": 0.78662109375 }, { "start": 1830.1, "end": 1830.2, "word": " you", "probability": 0.89404296875 }, { "start": 1830.2, "end": 1830.5, "word": " copy", "probability": 0.78125 } ] }, { "id": 827, "seek": 182600, "start": 1830.5, "end": 1832.0, "text": " this down correctly.", "tokens": [ 51114, 341, 760, 8944, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1830.5, "end": 1830.72, "word": " this", "probability": 0.8857421875 }, { "start": 1830.72, "end": 1830.96, "word": " down", "probability": 0.8203125 }, { "start": 1830.96, "end": 1831.56, "word": " correctly", "probability": 0.85693359375 }, { "start": 1831.56, "end": 1832.0, "word": ".", "probability": 0.9892578125 } ] }, { "id": 828, "seek": 182600, "start": 1833.52, "end": 1835.52, "text": " This bit is pretty easy", "tokens": [ 51264, 639, 857, 307, 1238, 1858, 51364 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1833.52, "end": 1833.96, "word": " This", "probability": 0.79150390625 }, { "start": 1833.96, "end": 1834.2, "word": " bit", "probability": 0.88525390625 }, { "start": 1834.2, "end": 1834.56, "word": " is", "probability": 0.90283203125 }, { "start": 1834.56, "end": 1835.24, "word": " pretty", "probability": 0.8740234375 }, { "start": 1835.24, "end": 1835.52, "word": " easy", "probability": 0.8095703125 } ] }, { "id": 829, "seek": 182600, "start": 1835.52, "end": 1836.22, "text": " if you're familiar with", "tokens": [ 51364, 498, 291, 434, 4963, 365, 51414 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1835.52, "end": 1835.68, "word": " if", "probability": 0.76708984375 }, { "start": 1835.68, "end": 1835.8, "word": " you're", "probability": 0.917236328125 }, { "start": 1835.8, "end": 1836.02, "word": " familiar", "probability": 0.7802734375 }, { "start": 1836.02, "end": 1836.22, "word": " with", "probability": 0.81494140625 } ] }, { "id": 830, "seek": 182600, "start": 1836.22, "end": 1837.6, "text": " Python. It might be a", "tokens": [ 51414, 15329, 13, 467, 1062, 312, 257, 51464 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1836.22, "end": 1836.62, "word": " Python", "probability": 0.90576171875 }, { "start": 1836.62, "end": 1836.92, "word": ".", "probability": 0.5283203125 }, { "start": 1836.92, "end": 1836.96, "word": " It", "probability": 0.60888671875 }, { "start": 1836.96, "end": 1837.1, "word": " might", "probability": 0.80615234375 }, { "start": 1837.1, "end": 1837.24, "word": " be", "probability": 0.90380859375 }, { "start": 1837.44, "end": 1837.6, "word": " a little", "probability": 0.80322265625 } ] }, { "id": 831, "seek": 182600, "start": 1837.6, "end": 1838.8, "text": " little confusing if you", "tokens": [ 51464, 707, 13181, 498, 291, 51514 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1837.6, "end": 1838.12, "word": " confusing", "probability": 0.93017578125 }, { "start": 1838.12, "end": 1838.54, "word": " if", "probability": 0.8984375 }, { "start": 1838.54, "end": 1838.66, "word": " you", "probability": 0.89599609375 }, { "start": 1838.66, "end": 1838.8, "word": " are", "probability": 0.78662109375 } ] }, { "id": 832, "seek": 182600, "start": 1838.8, "end": 1840.78, "text": " are not, but that's okay.", "tokens": [ 51514, 366, 406, 11, 457, 300, 311, 1392, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1838.8, "end": 1839.22, "word": " not", "probability": 0.89453125 }, { "start": 1839.22, "end": 1839.7, "word": ",", "probability": 0.81884765625 }, { "start": 1839.7, "end": 1840.0, "word": " but", "probability": 0.90283203125 }, { "start": 1840.0, "end": 1840.28, "word": " that's", "probability": 0.9404296875 }, { "start": 1840.28, "end": 1840.54, "word": " okay", "probability": 0.70166015625 }, { "start": 1840.54, "end": 1840.58, "word": ".", "probability": 0.89794921875 }, { "start": 1840.58, "end": 1840.78, "word": " If", "probability": 0.900390625 } ] }, { "id": 833, "seek": 182600, "start": 1840.78, "end": 1842.14, "text": " If you ever get lost at", "tokens": [ 51614, 759, 291, 1562, 483, 2731, 412, 51664 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1840.78, "end": 1840.98, "word": " you", "probability": 0.892578125 }, { "start": 1840.98, "end": 1841.26, "word": " ever", "probability": 0.82373046875 }, { "start": 1841.26, "end": 1841.44, "word": " get", "probability": 0.89306640625 }, { "start": 1841.44, "end": 1841.76, "word": " lost", "probability": 0.81591796875 }, { "start": 1841.76, "end": 1841.92, "word": " at", "probability": 0.90625 }, { "start": 1841.92, "end": 1842.14, "word": " any", "probability": 0.82763671875 } ] }, { "id": 834, "seek": 182600, "start": 1842.14, "end": 1843.8, "text": " any point, just remember", "tokens": [ 51664, 604, 935, 11, 445, 1604, 51764 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1842.14, "end": 1842.5, "word": " point", "probability": 0.8642578125 }, { "start": 1842.5, "end": 1842.86, "word": ",", "probability": 0.86669921875 }, { "start": 1842.86, "end": 1843.3, "word": " just", "probability": 0.8818359375 }, { "start": 1843.3, "end": 1843.58, "word": " remember", "probability": 0.78125 }, { "start": 1843.58, "end": 1843.8, "word": " that", "probability": 0.87744140625 } ] }, { "id": 835, "seek": 182600, "start": 1843.8, "end": 1844.7, "text": " that there are a", "tokens": [ 51764, 300, 456, 366, 257, 51814 ], "temperature": 0.0, "avg_logprob": -0.20106908610384716, "compression_ratio": 1.684782608695652, "no_speech_prob": 0.005218505859375, "words": [ { "start": 1843.8, "end": 1843.96, "word": " there", "probability": 0.857421875 }, { "start": 1843.96, "end": 1844.36, "word": " are", "probability": 0.8837890625 }, { "start": 1844.36, "end": 1844.7, "word": " a", "probability": 0.9609375 } ] }, { "id": 836, "seek": 185598, "start": 1844.7, "end": 1846.06, "text": " completed solutions manual", "tokens": [ 50364, 1209, 10993, 6547, 9688, 50414 ], "temperature": 0.0, "avg_logprob": -0.2637362774911818, "compression_ratio": 1.5885714285714285, "no_speech_prob": 0.00025725364685058594, "words": [ { "start": 1844.7, "end": 1845.1, "word": " completed", "probability": 0.5167388916015625 }, { "start": 1845.1, "end": 1845.6, "word": " solutions", "probability": 0.787109375 }, { "start": 1845.6, "end": 1846.06, "word": " manual", "probability": 0.89013671875 } ] }, { "id": 837, "seek": 185598, "start": 1846.06, "end": 1847.99, "text": " in the workbooks directory.", "tokens": [ 50414, 294, 264, 589, 15170, 21120, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.2637362774911818, "compression_ratio": 1.5885714285714285, "no_speech_prob": 0.00025725364685058594, "words": [ { "start": 1846.06, "end": 1846.72, "word": " in", "probability": 0.88134765625 }, { "start": 1846.72, "end": 1846.82, "word": " the", "probability": 0.81298828125 }, { "start": 1846.82, "end": 1847.16, "word": " workbooks", "probability": 0.74072265625 }, { "start": 1847.16, "end": 1847.58, "word": " directory", "probability": 0.8369140625 }, { "start": 1847.58, "end": 1847.99, "word": ".", "probability": 0.92919921875 } ] }, { "id": 838, "seek": 185598, "start": 1850.58, "end": 1852.84, "text": " So I'm going to go ahead", "tokens": [ 50664, 407, 286, 478, 516, 281, 352, 2286, 50764 ], "temperature": 0.0, "avg_logprob": -0.2637362774911818, "compression_ratio": 1.5885714285714285, "no_speech_prob": 0.00025725364685058594, "words": [ { "start": 1850.58, "end": 1851.4, "word": " So", "probability": 0.76611328125 }, { "start": 1851.4, "end": 1852.22, "word": " I'm", "probability": 0.864990234375 }, { "start": 1852.22, "end": 1852.26, "word": " going", "probability": 0.3671875 }, { "start": 1852.26, "end": 1852.3, "word": " to", "probability": 0.908203125 }, { "start": 1852.3, "end": 1852.42, "word": " go", "probability": 0.90185546875 }, { "start": 1852.42, "end": 1852.84, "word": " ahead", "probability": 0.849609375 } ] }, { "id": 839, "seek": 185598, "start": 1852.84, "end": 1855.34, "text": " and run this. So shift", "tokens": [ 50764, 293, 1190, 341, 13, 407, 5513, 50864 ], "temperature": 0.0, "avg_logprob": -0.2637362774911818, "compression_ratio": 1.5885714285714285, "no_speech_prob": 0.00025725364685058594, "words": [ { "start": 1852.84, "end": 1853.3, "word": " and", "probability": 0.89697265625 }, { "start": 1853.3, "end": 1853.86, "word": " run", "probability": 0.8955078125 }, { "start": 1853.86, "end": 1854.34, "word": " this", "probability": 0.8896484375 }, { "start": 1854.34, "end": 1854.82, "word": ".", "probability": 0.53955078125 }, { "start": 1854.82, "end": 1854.84, "word": " So", "probability": 0.87548828125 }, { "start": 1854.84, "end": 1855.34, "word": " shift", "probability": 0.65283203125 } ] }, { "id": 840, "seek": 185598, "start": 1855.34, "end": 1856.93, "text": " enter to run.", "tokens": [ 50864, 3242, 281, 1190, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.2637362774911818, "compression_ratio": 1.5885714285714285, "no_speech_prob": 0.00025725364685058594, "words": [ { "start": 1855.34, "end": 1855.72, "word": " enter", "probability": 0.39794921875 }, { "start": 1855.72, "end": 1856.12, "word": " to", "probability": 0.90283203125 }, { "start": 1856.12, "end": 1856.52, "word": " run", "probability": 0.908203125 }, { "start": 1856.52, "end": 1856.93, "word": ".", "probability": 0.305419921875 } ] }, { "id": 841, "seek": 185598, "start": 1857.74, "end": 1859.74, "text": " And I spelled labels", "tokens": [ 50964, 400, 286, 34388, 16949, 51114 ], "temperature": 0.0, "avg_logprob": -0.2637362774911818, "compression_ratio": 1.5885714285714285, "no_speech_prob": 0.00025725364685058594, "words": [ { "start": 1857.74, "end": 1857.96, "word": " And", "probability": 0.798828125 }, { "start": 1857.96, "end": 1859.06, "word": " I", "probability": 0.9541015625 }, { "start": 1859.06, "end": 1859.24, "word": " spelled", "probability": 0.455810546875 }, { "start": 1859.24, "end": 1859.74, "word": " labels", "probability": 0.80810546875 } ] }, { "id": 842, "seek": 185598, "start": 1859.74, "end": 1864.16, "text": " wrong. Labels, shift", "tokens": [ 51114, 2085, 13, 10137, 1625, 11, 5513, 51314 ], "temperature": 0.0, "avg_logprob": -0.2637362774911818, "compression_ratio": 1.5885714285714285, "no_speech_prob": 0.00025725364685058594, "words": [ { "start": 1859.74, "end": 1860.16, "word": " wrong", "probability": 0.79345703125 }, { "start": 1860.16, "end": 1860.98, "word": ".", "probability": 0.8427734375 }, { "start": 1862.68, "end": 1863.5, "word": " Labels", "probability": 0.893798828125 }, { "start": 1863.5, "end": 1863.72, "word": ",", "probability": 0.501953125 }, { "start": 1863.72, "end": 1864.16, "word": " shift", "probability": 0.66259765625 } ] }, { "id": 843, "seek": 185598, "start": 1864.16, "end": 1865.98, "text": " enter to run. Loading", "tokens": [ 51314, 3242, 281, 1190, 13, 6130, 8166, 51414 ], "temperature": 0.0, "avg_logprob": -0.2637362774911818, "compression_ratio": 1.5885714285714285, "no_speech_prob": 0.00025725364685058594, "words": [ { "start": 1864.16, "end": 1864.44, "word": " enter", "probability": 0.58349609375 }, { "start": 1864.44, "end": 1864.68, "word": " to", "probability": 0.90087890625 }, { "start": 1864.68, "end": 1865.04, "word": " run", "probability": 0.9150390625 }, { "start": 1865.04, "end": 1865.66, "word": ".", "probability": 0.556640625 }, { "start": 1865.66, "end": 1865.98, "word": " Loading", "probability": 0.9423828125 } ] }, { "id": 844, "seek": 185598, "start": 1865.98, "end": 1867.81, "text": " ham, loading spam, done.", "tokens": [ 51414, 7852, 11, 15114, 24028, 11, 1096, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.2637362774911818, "compression_ratio": 1.5885714285714285, "no_speech_prob": 0.00025725364685058594, "words": [ { "start": 1865.98, "end": 1866.22, "word": " ham", "probability": 0.66259765625 }, { "start": 1866.22, "end": 1866.32, "word": ",", "probability": 0.80810546875 }, { "start": 1866.32, "end": 1866.46, "word": " loading", "probability": 0.78173828125 }, { "start": 1866.46, "end": 1866.82, "word": " spam", "probability": 0.900390625 }, { "start": 1866.82, "end": 1867.2, "word": ",", "probability": 0.70263671875 }, { "start": 1867.2, "end": 1867.4, "word": " done", "probability": 0.79638671875 }, { "start": 1867.4, "end": 1867.81, "word": ".", "probability": 0.99609375 } ] }, { "id": 845, "seek": 185598, "start": 1868.94, "end": 1870.04, "text": " So what this is going to", "tokens": [ 51564, 407, 437, 341, 307, 516, 281, 51614 ], "temperature": 0.0, "avg_logprob": -0.2637362774911818, "compression_ratio": 1.5885714285714285, "no_speech_prob": 0.00025725364685058594, "words": [ { "start": 1868.94, "end": 1869.48, "word": " So", "probability": 0.89404296875 }, { "start": 1869.48, "end": 1869.6, "word": " what", "probability": 0.87353515625 }, { "start": 1869.6, "end": 1869.74, "word": " this", "probability": 0.87939453125 }, { "start": 1869.74, "end": 1869.86, "word": " is", "probability": 0.9052734375 }, { "start": 1869.86, "end": 1869.96, "word": " going", "probability": 0.76611328125 }, { "start": 1869.96, "end": 1870.04, "word": " to", "probability": 0.90673828125 } ] }, { "id": 846, "seek": 185598, "start": 1870.04, "end": 1872.6, "text": " do is graphically load", "tokens": [ 51614, 360, 307, 4295, 984, 3677, 51764 ], "temperature": 0.0, "avg_logprob": -0.2637362774911818, "compression_ratio": 1.5885714285714285, "no_speech_prob": 0.00025725364685058594, "words": [ { "start": 1870.04, "end": 1870.28, "word": " do", "probability": 0.90576171875 }, { "start": 1870.28, "end": 1870.82, "word": " is", "probability": 0.88525390625 }, { "start": 1870.82, "end": 1871.98, "word": " graphically", "probability": 0.840576171875 }, { "start": 1871.98, "end": 1872.6, "word": " load", "probability": 0.86279296875 } ] }, { "id": 847, "seek": 185598, "start": 1872.6, "end": 1874.68, "text": " or graphically visualize", "tokens": [ 51764, 420, 4295, 984, 23273, 51814 ], "temperature": 0.0, "avg_logprob": -0.2637362774911818, "compression_ratio": 1.5885714285714285, "no_speech_prob": 0.00025725364685058594, "words": [ { "start": 1872.6, "end": 1873.52, "word": " or", "probability": 0.62939453125 }, { "start": 1873.52, "end": 1873.98, "word": " graphically", "probability": 0.85986328125 }, { "start": 1873.98, "end": 1874.68, "word": " visualize", "probability": 0.8369140625 } ] }, { "id": 848, "seek": 188538, "start": 1874.68, "end": 1876.26, "text": " how many ham emails we", "tokens": [ 50364, 577, 867, 7852, 12524, 321, 50414 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1874.68, "end": 1875.34, "word": " how", "probability": 0.26416015625 }, { "start": 1875.34, "end": 1875.58, "word": " many", "probability": 0.80126953125 }, { "start": 1875.58, "end": 1875.8, "word": " ham", "probability": 0.53076171875 }, { "start": 1875.8, "end": 1876.04, "word": " emails", "probability": 0.7607421875 }, { "start": 1876.04, "end": 1876.26, "word": " we", "probability": 0.88720703125 } ] }, { "id": 849, "seek": 188538, "start": 1876.26, "end": 1877.14, "text": " have versus how many", "tokens": [ 50414, 362, 5717, 577, 867, 50464 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1876.26, "end": 1876.56, "word": " have", "probability": 0.87939453125 }, { "start": 1876.56, "end": 1876.76, "word": " versus", "probability": 0.6396484375 }, { "start": 1876.76, "end": 1876.98, "word": " how", "probability": 0.9033203125 }, { "start": 1876.98, "end": 1877.14, "word": " many", "probability": 0.830078125 } ] }, { "id": 850, "seek": 188538, "start": 1877.14, "end": 1878.24, "text": " spam emails we have.", "tokens": [ 50464, 24028, 12524, 321, 362, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1877.14, "end": 1877.42, "word": " spam", "probability": 0.9296875 }, { "start": 1877.42, "end": 1877.78, "word": " emails", "probability": 0.8251953125 }, { "start": 1877.78, "end": 1877.96, "word": " we", "probability": 0.89990234375 }, { "start": 1877.96, "end": 1878.14, "word": " have", "probability": 0.8798828125 }, { "start": 1878.14, "end": 1878.24, "word": ".", "probability": 0.65625 } ] }, { "id": 851, "seek": 188538, "start": 1878.24, "end": 1878.82, "text": " And this is something we", "tokens": [ 50514, 400, 341, 307, 746, 321, 50564 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1878.24, "end": 1878.26, "word": " And", "probability": 0.5068359375 }, { "start": 1878.26, "end": 1878.38, "word": " this", "probability": 0.8740234375 }, { "start": 1878.38, "end": 1878.48, "word": " is", "probability": 0.908203125 }, { "start": 1878.48, "end": 1878.66, "word": " something", "probability": 0.7275390625 }, { "start": 1878.66, "end": 1878.82, "word": " we", "probability": 0.88330078125 } ] }, { "id": 852, "seek": 188538, "start": 1878.82, "end": 1879.72, "text": " want to generally do with", "tokens": [ 50564, 528, 281, 5101, 360, 365, 50614 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1878.82, "end": 1878.92, "word": " want", "probability": 0.71142578125 }, { "start": 1878.92, "end": 1879.02, "word": " to", "probability": 0.89990234375 }, { "start": 1879.02, "end": 1879.38, "word": " generally", "probability": 0.85693359375 }, { "start": 1879.38, "end": 1879.58, "word": " do", "probability": 0.90771484375 }, { "start": 1879.58, "end": 1879.72, "word": " with", "probability": 0.81494140625 } ] }, { "id": 853, "seek": 188538, "start": 1879.72, "end": 1881.0, "text": " our data just to see if", "tokens": [ 50614, 527, 1412, 445, 281, 536, 498, 50664 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1879.72, "end": 1879.84, "word": " our", "probability": 0.8154296875 }, { "start": 1879.84, "end": 1880.12, "word": " data", "probability": 0.79736328125 }, { "start": 1880.12, "end": 1880.48, "word": " just", "probability": 0.6318359375 }, { "start": 1880.48, "end": 1880.64, "word": " to", "probability": 0.90625 }, { "start": 1880.64, "end": 1880.86, "word": " see", "probability": 0.806640625 }, { "start": 1880.86, "end": 1881.0, "word": " if", "probability": 0.90478515625 } ] }, { "id": 854, "seek": 188538, "start": 1881.0, "end": 1881.68, "text": " there's any sort of", "tokens": [ 50664, 456, 311, 604, 1333, 295, 50714 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1881.0, "end": 1881.2, "word": " there's", "probability": 0.897216796875 }, { "start": 1881.2, "end": 1881.36, "word": " any", "probability": 0.82958984375 }, { "start": 1881.36, "end": 1881.56, "word": " sort", "probability": 0.80810546875 }, { "start": 1881.56, "end": 1881.68, "word": " of", "probability": 0.90869140625 } ] }, { "id": 855, "seek": 188538, "start": 1881.68, "end": 1883.28, "text": " imbalanced data sets.", "tokens": [ 50714, 566, 40251, 1412, 6352, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1881.68, "end": 1882.16, "word": " imbalanced", "probability": 0.720703125 }, { "start": 1882.16, "end": 1882.48, "word": " data", "probability": 0.489013671875 }, { "start": 1882.48, "end": 1882.92, "word": " sets", "probability": 0.8046875 }, { "start": 1882.92, "end": 1883.28, "word": ".", "probability": 0.9697265625 } ] }, { "id": 856, "seek": 188538, "start": 1883.38, "end": 1884.44, "text": " This one we have about", "tokens": [ 50814, 639, 472, 321, 362, 466, 50864 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1883.38, "end": 1883.82, "word": " This", "probability": 0.79052734375 }, { "start": 1883.82, "end": 1883.98, "word": " one", "probability": 0.81884765625 }, { "start": 1883.98, "end": 1884.1, "word": " we", "probability": 0.67578125 }, { "start": 1884.1, "end": 1884.24, "word": " have", "probability": 0.88037109375 }, { "start": 1884.24, "end": 1884.44, "word": " about", "probability": 0.8046875 } ] }, { "id": 857, "seek": 188538, "start": 1884.44, "end": 1888.6, "text": " 50% spam per ham.", "tokens": [ 50864, 2625, 4, 24028, 680, 7852, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1884.44, "end": 1884.72, "word": " 50", "probability": 0.86083984375 }, { "start": 1884.72, "end": 1885.08, "word": "%", "probability": 0.90625 }, { "start": 1885.08, "end": 1885.92, "word": " spam", "probability": 0.7978515625 }, { "start": 1885.92, "end": 1887.2, "word": " per", "probability": 0.73095703125 }, { "start": 1887.2, "end": 1888.16, "word": " ham", "probability": 0.86669921875 }, { "start": 1888.16, "end": 1888.6, "word": ".", "probability": 0.69091796875 } ] }, { "id": 858, "seek": 188538, "start": 1889.28, "end": 1890.32, "text": " It's like 2 to 1", "tokens": [ 51064, 467, 311, 411, 568, 281, 502, 51114 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1889.28, "end": 1889.72, "word": " It's", "probability": 0.4940185546875 }, { "start": 1889.72, "end": 1889.84, "word": " like", "probability": 0.806640625 }, { "start": 1889.84, "end": 1890.08, "word": " 2", "probability": 0.211669921875 }, { "start": 1890.08, "end": 1890.18, "word": " to", "probability": 0.6962890625 }, { "start": 1890.18, "end": 1890.32, "word": " 1", "probability": 0.98828125 } ] }, { "id": 859, "seek": 188538, "start": 1890.32, "end": 1892.56, "text": " ratio of ham to spam.", "tokens": [ 51114, 8509, 295, 7852, 281, 24028, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1890.32, "end": 1890.76, "word": " ratio", "probability": 0.890625 }, { "start": 1890.76, "end": 1890.94, "word": " of", "probability": 0.53271484375 }, { "start": 1890.94, "end": 1891.16, "word": " ham", "probability": 0.89892578125 }, { "start": 1891.16, "end": 1892.06, "word": " to", "probability": 0.705078125 }, { "start": 1892.06, "end": 1892.28, "word": " spam", "probability": 0.92578125 }, { "start": 1892.28, "end": 1892.56, "word": ".", "probability": 0.84326171875 } ] }, { "id": 860, "seek": 188538, "start": 1892.56, "end": 1894.58, "text": " And so this I'm not", "tokens": [ 51214, 400, 370, 341, 286, 478, 406, 51314 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1892.56, "end": 1892.56, "word": " And", "probability": 0.6640625 }, { "start": 1892.56, "end": 1892.96, "word": " so", "probability": 0.89794921875 }, { "start": 1892.96, "end": 1894.26, "word": " this", "probability": 0.59375 }, { "start": 1894.26, "end": 1894.42, "word": " I'm", "probability": 0.83935546875 }, { "start": 1894.42, "end": 1894.58, "word": " not", "probability": 0.8955078125 } ] }, { "id": 861, "seek": 188538, "start": 1894.58, "end": 1895.74, "text": " going to consider an", "tokens": [ 51314, 516, 281, 1949, 364, 51414 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1894.58, "end": 1894.68, "word": " going", "probability": 0.67529296875 }, { "start": 1894.68, "end": 1894.8, "word": " to", "probability": 0.90234375 }, { "start": 1894.8, "end": 1895.28, "word": " consider", "probability": 0.794921875 }, { "start": 1895.28, "end": 1895.74, "word": " an", "probability": 0.8779296875 } ] }, { "id": 862, "seek": 188538, "start": 1895.74, "end": 1896.88, "text": " imbalanced data set for", "tokens": [ 51414, 566, 40251, 1412, 992, 337, 51464 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1895.74, "end": 1896.22, "word": " imbalanced", "probability": 0.825439453125 }, { "start": 1896.22, "end": 1896.5, "word": " data", "probability": 0.6943359375 }, { "start": 1896.5, "end": 1896.72, "word": " set", "probability": 0.9033203125 }, { "start": 1896.72, "end": 1896.88, "word": " for", "probability": 0.89306640625 } ] }, { "id": 863, "seek": 188538, "start": 1896.88, "end": 1898.98, "text": " this example, but if we", "tokens": [ 51464, 341, 1365, 11, 457, 498, 321, 51564 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1896.88, "end": 1897.06, "word": " this", "probability": 0.87841796875 }, { "start": 1897.06, "end": 1897.48, "word": " example", "probability": 0.927734375 }, { "start": 1897.48, "end": 1898.02, "word": ",", "probability": 0.4658203125 }, { "start": 1898.02, "end": 1898.28, "word": " but", "probability": 0.8935546875 }, { "start": 1898.28, "end": 1898.88, "word": " if", "probability": 0.90087890625 }, { "start": 1898.88, "end": 1898.98, "word": " we", "probability": 0.90380859375 } ] }, { "id": 864, "seek": 188538, "start": 1898.98, "end": 1900.0, "text": " have something such as", "tokens": [ 51564, 362, 746, 1270, 382, 51614 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1898.98, "end": 1899.14, "word": " have", "probability": 0.88525390625 }, { "start": 1899.14, "end": 1899.46, "word": " something", "probability": 0.72412109375 }, { "start": 1899.46, "end": 1899.76, "word": " such", "probability": 0.861328125 }, { "start": 1899.76, "end": 1900.0, "word": " as", "probability": 0.8994140625 } ] }, { "id": 865, "seek": 188538, "start": 1900.0, "end": 1901.08, "text": " like credit card fraud", "tokens": [ 51614, 411, 5397, 2920, 14560, 51664 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1900.0, "end": 1900.24, "word": " like", "probability": 0.572265625 }, { "start": 1900.24, "end": 1900.48, "word": " credit", "probability": 0.80322265625 }, { "start": 1900.48, "end": 1900.74, "word": " card", "probability": 0.8154296875 }, { "start": 1900.74, "end": 1901.08, "word": " fraud", "probability": 0.87158203125 } ] }, { "id": 866, "seek": 188538, "start": 1901.08, "end": 1901.94, "text": " where it happens less", "tokens": [ 51664, 689, 309, 2314, 1570, 51714 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1901.08, "end": 1901.3, "word": " where", "probability": 0.6494140625 }, { "start": 1901.3, "end": 1901.4, "word": " it", "probability": 0.90283203125 }, { "start": 1901.4, "end": 1901.7, "word": " happens", "probability": 0.9111328125 }, { "start": 1901.7, "end": 1901.94, "word": " less", "probability": 0.86767578125 } ] }, { "id": 867, "seek": 188538, "start": 1901.94, "end": 1903.22, "text": " than a fraction of a", "tokens": [ 51714, 813, 257, 14135, 295, 257, 51764 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1901.94, "end": 1902.08, "word": " than", "probability": 0.8740234375 }, { "start": 1902.2, "end": 1902.52, "word": " a fraction", "probability": 0.7666015625 }, { "start": 1902.52, "end": 1902.9, "word": " of", "probability": 0.9033203125 }, { "start": 1903.0, "end": 1903.22, "word": " a percent", "probability": 0.87548828125 } ] }, { "id": 868, "seek": 188538, "start": 1903.22, "end": 1904.08, "text": " percent of the time,", "tokens": [ 51764, 3043, 295, 264, 565, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.19031249274810155, "compression_ratio": 1.7228464419475655, "no_speech_prob": 0.0006561279296875, "words": [ { "start": 1903.22, "end": 1903.36, "word": " of", "probability": 0.89404296875 }, { "start": 1903.36, "end": 1903.48, "word": " the", "probability": 0.8173828125 }, { "start": 1903.48, "end": 1903.86, "word": " time", "probability": 0.80419921875 }, { "start": 1903.86, "end": 1904.08, "word": ",", "probability": 0.79833984375 } ] }, { "id": 869, "seek": 191356, "start": 1904.08, "end": 1904.8, "text": " that's something that we", "tokens": [ 50364, 300, 311, 746, 300, 321, 50414 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1904.08, "end": 1904.42, "word": " that's", "probability": 0.53778076171875 }, { "start": 1904.42, "end": 1904.58, "word": " something", "probability": 0.7421875 }, { "start": 1904.58, "end": 1904.72, "word": " that", "probability": 0.806640625 }, { "start": 1904.72, "end": 1904.8, "word": " we", "probability": 0.9033203125 } ] }, { "id": 870, "seek": 191356, "start": 1904.8, "end": 1905.9, "text": " really want to dive into", "tokens": [ 50414, 534, 528, 281, 9192, 666, 50464 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1904.8, "end": 1905.04, "word": " really", "probability": 0.7578125 }, { "start": 1905.04, "end": 1905.2, "word": " want", "probability": 0.7021484375 }, { "start": 1905.2, "end": 1905.3, "word": " to", "probability": 0.9111328125 }, { "start": 1905.3, "end": 1905.5, "word": " dive", "probability": 0.791015625 }, { "start": 1905.5, "end": 1905.9, "word": " into", "probability": 0.7294921875 } ] }, { "id": 871, "seek": 191356, "start": 1905.9, "end": 1907.5, "text": " simply because if we try", "tokens": [ 50464, 2935, 570, 498, 321, 853, 50514 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1905.9, "end": 1906.28, "word": " simply", "probability": 0.576171875 }, { "start": 1906.28, "end": 1906.72, "word": " because", "probability": 0.83056640625 }, { "start": 1906.72, "end": 1907.06, "word": " if", "probability": 0.87890625 }, { "start": 1907.06, "end": 1907.2, "word": " we", "probability": 0.90087890625 }, { "start": 1907.2, "end": 1907.5, "word": " try", "probability": 0.80615234375 } ] }, { "id": 872, "seek": 191356, "start": 1907.5, "end": 1909.44, "text": " and use this exact", "tokens": [ 50514, 293, 764, 341, 1900, 50614 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1907.5, "end": 1907.68, "word": " and", "probability": 0.87841796875 }, { "start": 1907.68, "end": 1908.1, "word": " use", "probability": 0.81494140625 }, { "start": 1908.1, "end": 1909.02, "word": " this", "probability": 0.82470703125 }, { "start": 1909.02, "end": 1909.44, "word": " exact", "probability": 0.81884765625 } ] }, { "id": 873, "seek": 191356, "start": 1909.44, "end": 1911.24, "text": " example on credit card", "tokens": [ 50614, 1365, 322, 5397, 2920, 50714 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1909.44, "end": 1909.9, "word": " example", "probability": 0.91943359375 }, { "start": 1909.9, "end": 1910.7, "word": " on", "probability": 0.89892578125 }, { "start": 1910.7, "end": 1911.04, "word": " credit", "probability": 0.8125 }, { "start": 1911.04, "end": 1911.24, "word": " card", "probability": 0.79052734375 } ] }, { "id": 874, "seek": 191356, "start": 1911.24, "end": 1912.06, "text": " fraud, it's not going to", "tokens": [ 50714, 14560, 11, 309, 311, 406, 516, 281, 50764 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1911.24, "end": 1911.5, "word": " fraud", "probability": 0.86181640625 }, { "start": 1911.5, "end": 1911.58, "word": ",", "probability": 0.5009765625 }, { "start": 1911.58, "end": 1911.7, "word": " it's", "probability": 0.945556640625 }, { "start": 1911.7, "end": 1911.84, "word": " not", "probability": 0.89599609375 }, { "start": 1911.84, "end": 1911.94, "word": " going", "probability": 0.732421875 }, { "start": 1911.94, "end": 1912.06, "word": " to", "probability": 0.900390625 } ] }, { "id": 875, "seek": 191356, "start": 1912.06, "end": 1913.04, "text": " work because what we", "tokens": [ 50764, 589, 570, 437, 321, 50814 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1912.06, "end": 1912.28, "word": " work", "probability": 0.81640625 }, { "start": 1912.28, "end": 1912.64, "word": " because", "probability": 0.57568359375 }, { "start": 1912.64, "end": 1912.92, "word": " what", "probability": 0.8798828125 }, { "start": 1912.92, "end": 1913.04, "word": " we", "probability": 0.90576171875 } ] }, { "id": 876, "seek": 191356, "start": 1913.04, "end": 1914.7, "text": " will do is create a", "tokens": [ 50814, 486, 360, 307, 1884, 257, 50864 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1913.04, "end": 1913.2, "word": " will", "probability": 0.80859375 }, { "start": 1913.2, "end": 1913.5, "word": " do", "probability": 0.90673828125 }, { "start": 1913.5, "end": 1913.74, "word": " is", "probability": 0.8974609375 }, { "start": 1913.74, "end": 1914.16, "word": " create", "probability": 0.81884765625 }, { "start": 1914.44, "end": 1914.7, "word": " a model", "probability": 0.7998046875 } ] }, { "id": 877, "seek": 191356, "start": 1914.7, "end": 1916.98, "text": " model that is 99%", "tokens": [ 50864, 2316, 300, 307, 11803, 4, 50964 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1914.7, "end": 1915.16, "word": " that", "probability": 0.87841796875 }, { "start": 1915.16, "end": 1915.46, "word": " is", "probability": 0.908203125 }, { "start": 1915.46, "end": 1916.0, "word": " 99", "probability": 0.84033203125 }, { "start": 1916.0, "end": 1916.42, "word": "%", "probability": 0.7998046875 }, { "start": 1916.42, "end": 1916.98, "word": " accurate", "probability": 0.65087890625 } ] }, { "id": 878, "seek": 191356, "start": 1917.54, "end": 1918.98, "text": " accurate because it just", "tokens": [ 50964, 8559, 570, 309, 445, 51064 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1917.54, "end": 1918.02, "word": " because", "probability": 0.6396484375 }, { "start": 1918.02, "end": 1918.24, "word": " it", "probability": 0.90869140625 }, { "start": 1918.24, "end": 1918.4, "word": " just", "probability": 0.92578125 }, { "start": 1918.4, "end": 1918.98, "word": " classifies", "probability": 0.977783203125 } ] }, { "id": 879, "seek": 191356, "start": 1918.98, "end": 1920.46, "text": " classifies all credit", "tokens": [ 51064, 1508, 11221, 439, 5397, 51114 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1918.98, "end": 1919.44, "word": " all", "probability": 0.90185546875 }, { "start": 1919.44, "end": 1919.76, "word": " credit", "probability": 0.810546875 }, { "start": 1919.76, "end": 1919.94, "word": " card", "probability": 0.82763671875 }, { "start": 1919.94, "end": 1920.46, "word": " transactions", "probability": 0.82177734375 } ] }, { "id": 880, "seek": 191356, "start": 1920.46, "end": 1921.54, "text": " card transactions as", "tokens": [ 51114, 2920, 16856, 382, 51164 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1920.46, "end": 1920.68, "word": " as", "probability": 0.916015625 }, { "start": 1920.68, "end": 1921.06, "word": " legitimate", "probability": 0.78759765625 }, { "start": 1921.06, "end": 1921.54, "word": ".", "probability": 0.95263671875 } ] }, { "id": 881, "seek": 191356, "start": 1921.82, "end": 1922.4, "text": " legitimate. Now if we", "tokens": [ 51164, 17956, 13, 823, 498, 321, 51264 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1921.82, "end": 1921.96, "word": " Now", "probability": 0.8447265625 }, { "start": 1921.96, "end": 1922.08, "word": " if", "probability": 0.52392578125 }, { "start": 1922.08, "end": 1922.16, "word": " we", "probability": 0.88720703125 }, { "start": 1922.16, "end": 1922.3, "word": " want", "probability": 0.80908203125 }, { "start": 1922.3, "end": 1922.4, "word": " to", "probability": 0.900390625 } ] }, { "id": 882, "seek": 191356, "start": 1922.4, "end": 1923.48, "text": " want to identify credit", "tokens": [ 51264, 528, 281, 5876, 5397, 51314 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1922.4, "end": 1922.76, "word": " identify", "probability": 0.88916015625 }, { "start": 1922.76, "end": 1923.06, "word": " credit", "probability": 0.8115234375 }, { "start": 1923.06, "end": 1923.28, "word": " card", "probability": 0.8154296875 }, { "start": 1923.28, "end": 1923.48, "word": " fraud", "probability": 0.8720703125 } ] }, { "id": 883, "seek": 191356, "start": 1923.48, "end": 1924.34, "text": " card fraud, that's not", "tokens": [ 51314, 2920, 14560, 11, 300, 311, 406, 51364 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1923.48, "end": 1923.56, "word": ",", "probability": 0.6337890625 }, { "start": 1923.56, "end": 1923.72, "word": " that's", "probability": 0.93701171875 }, { "start": 1923.72, "end": 1923.86, "word": " not", "probability": 0.89892578125 }, { "start": 1923.86, "end": 1924.08, "word": " very", "probability": 0.724609375 }, { "start": 1924.08, "end": 1924.34, "word": " helpful", "probability": 0.8369140625 } ] }, { "id": 884, "seek": 191356, "start": 1924.34, "end": 1925.7, "text": " very helpful for us.", "tokens": [ 51364, 588, 4961, 337, 505, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1924.34, "end": 1924.62, "word": " for", "probability": 0.89501953125 }, { "start": 1924.62, "end": 1924.9, "word": " us", "probability": 0.904296875 }, { "start": 1924.9, "end": 1925.34, "word": ".", "probability": 0.82421875 }, { "start": 1925.34, "end": 1925.48, "word": " So", "probability": 0.7763671875 }, { "start": 1925.48, "end": 1925.7, "word": " this", "probability": 0.828125 } ] }, { "id": 885, "seek": 191356, "start": 1925.7, "end": 1926.92, "text": " So this just allows us", "tokens": [ 51414, 407, 341, 445, 4045, 505, 51464 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1925.7, "end": 1925.92, "word": " just", "probability": 0.890625 }, { "start": 1925.92, "end": 1926.22, "word": " allows", "probability": 0.79541015625 }, { "start": 1926.22, "end": 1926.4, "word": " us", "probability": 0.900390625 }, { "start": 1926.4, "end": 1926.68, "word": " to", "probability": 0.90380859375 }, { "start": 1926.68, "end": 1926.92, "word": " kind", "probability": 0.71240234375 } ] }, { "id": 886, "seek": 191356, "start": 1926.92, "end": 1928.26, "text": " to kind of explore the", "tokens": [ 51464, 281, 733, 295, 6839, 264, 51514 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1926.92, "end": 1927.0, "word": " of", "probability": 0.90380859375 }, { "start": 1927.0, "end": 1927.4, "word": " explore", "probability": 0.779296875 }, { "start": 1927.4, "end": 1927.6, "word": " the", "probability": 0.81591796875 }, { "start": 1927.6, "end": 1927.86, "word": " data", "probability": 0.8193359375 }, { "start": 1927.86, "end": 1928.26, "word": " and", "probability": 0.88427734375 } ] }, { "id": 887, "seek": 191356, "start": 1928.26, "end": 1930.1, "text": " data and see how much", "tokens": [ 51514, 1412, 293, 536, 577, 709, 51614 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1928.26, "end": 1928.66, "word": " see", "probability": 0.806640625 }, { "start": 1928.66, "end": 1929.36, "word": " how", "probability": 0.89599609375 }, { "start": 1929.36, "end": 1929.6, "word": " much", "probability": 0.814453125 }, { "start": 1929.6, "end": 1929.8, "word": " of", "probability": 0.9013671875 }, { "start": 1929.8, "end": 1930.1, "word": " what", "probability": 0.88525390625 } ] }, { "id": 888, "seek": 191356, "start": 1930.1, "end": 1931.4, "text": " of what we have.", "tokens": [ 51614, 295, 437, 321, 362, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1930.1, "end": 1930.3, "word": " we", "probability": 0.904296875 }, { "start": 1930.3, "end": 1930.7, "word": " have", "probability": 0.87744140625 }, { "start": 1930.7, "end": 1931.06, "word": ".", "probability": 0.96484375 }, { "start": 1931.06, "end": 1931.3, "word": " So", "probability": 0.865234375 }, { "start": 1931.3, "end": 1931.4, "word": " in", "probability": 0.89306640625 } ] }, { "id": 889, "seek": 191356, "start": 1931.4, "end": 1932.26, "text": " So in this case we have", "tokens": [ 51714, 407, 294, 341, 1389, 321, 362, 51764 ], "temperature": 0.0, "avg_logprob": -0.1479525878511626, "compression_ratio": 1.755639097744361, "no_speech_prob": 0.0007319450378417969, "words": [ { "start": 1931.4, "end": 1931.54, "word": " this", "probability": 0.88134765625 }, { "start": 1931.54, "end": 1931.76, "word": " case", "probability": 0.81201171875 }, { "start": 1931.76, "end": 1931.94, "word": " we", "probability": 0.5361328125 }, { "start": 1931.94, "end": 1932.26, "word": " have", "probability": 0.8740234375 } ] }, { "id": 890, "seek": 194252, "start": 1932.26, "end": 1935.0, "text": " 2,359 ham emails and", "tokens": [ 50364, 568, 11, 8794, 24, 7852, 12524, 293, 50464 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1932.26, "end": 1932.4, "word": " 2", "probability": 0.160888671875 }, { "start": 1932.4, "end": 1933.68, "word": ",359", "probability": 0.9153645833333334 }, { "start": 1933.68, "end": 1934.12, "word": " ham", "probability": 0.673828125 }, { "start": 1934.12, "end": 1934.62, "word": " emails", "probability": 0.7470703125 }, { "start": 1934.62, "end": 1935.0, "word": " and", "probability": 0.59130859375 } ] }, { "id": 891, "seek": 194252, "start": 1935.0, "end": 1937.78, "text": " about 1,100 spam emails.", "tokens": [ 50464, 466, 502, 11, 6879, 24028, 12524, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1935.0, "end": 1935.38, "word": " about", "probability": 0.8115234375 }, { "start": 1935.38, "end": 1935.64, "word": " 1", "probability": 0.775390625 }, { "start": 1935.64, "end": 1936.2, "word": ",100", "probability": 0.958984375 }, { "start": 1936.2, "end": 1936.92, "word": " spam", "probability": 0.8994140625 }, { "start": 1936.92, "end": 1937.38, "word": " emails", "probability": 0.79345703125 }, { "start": 1937.38, "end": 1937.78, "word": ".", "probability": 0.97802734375 } ] }, { "id": 892, "seek": 194252, "start": 1939.7, "end": 1941.56, "text": " So task 2A, we're going", "tokens": [ 50714, 407, 5633, 568, 32, 11, 321, 434, 516, 50814 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1939.7, "end": 1940.1, "word": " So", "probability": 0.8095703125 }, { "start": 1940.1, "end": 1940.5, "word": " task", "probability": 0.62451171875 }, { "start": 1940.5, "end": 1941.1, "word": " 2A", "probability": 0.695068359375 }, { "start": 1941.1, "end": 1941.24, "word": ",", "probability": 0.794921875 }, { "start": 1941.24, "end": 1941.4, "word": " we're", "probability": 0.92431640625 }, { "start": 1941.4, "end": 1941.56, "word": " going", "probability": 0.841796875 } ] }, { "id": 893, "seek": 194252, "start": 1941.56, "end": 1942.5, "text": " to view our training", "tokens": [ 50814, 281, 1910, 527, 3097, 50864 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1941.56, "end": 1941.74, "word": " to", "probability": 0.90625 }, { "start": 1941.74, "end": 1942.06, "word": " view", "probability": 0.8037109375 }, { "start": 1942.06, "end": 1942.24, "word": " our", "probability": 0.7978515625 }, { "start": 1942.24, "end": 1942.5, "word": " training", "probability": 0.80810546875 } ] }, { "id": 894, "seek": 194252, "start": 1942.5, "end": 1944.52, "text": " data. So this one's just", "tokens": [ 50864, 1412, 13, 407, 341, 472, 311, 445, 50964 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1942.5, "end": 1942.84, "word": " data", "probability": 0.82080078125 }, { "start": 1942.84, "end": 1943.02, "word": ".", "probability": 0.92529296875 }, { "start": 1943.02, "end": 1943.12, "word": " So", "probability": 0.87646484375 }, { "start": 1943.12, "end": 1943.3, "word": " this", "probability": 0.87353515625 }, { "start": 1943.3, "end": 1943.8, "word": " one's", "probability": 0.879638671875 }, { "start": 1943.8, "end": 1944.52, "word": " just", "probability": 0.845703125 } ] }, { "id": 895, "seek": 194252, "start": 1944.52, "end": 1945.64, "text": " to kind of see what our", "tokens": [ 50964, 281, 733, 295, 536, 437, 527, 51014 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1944.52, "end": 1944.66, "word": " to", "probability": 0.89306640625 }, { "start": 1944.66, "end": 1944.82, "word": " kind", "probability": 0.76904296875 }, { "start": 1944.82, "end": 1944.92, "word": " of", "probability": 0.90380859375 }, { "start": 1944.92, "end": 1945.18, "word": " see", "probability": 0.8134765625 }, { "start": 1945.18, "end": 1945.44, "word": " what", "probability": 0.88623046875 }, { "start": 1945.44, "end": 1945.64, "word": " our", "probability": 0.81298828125 } ] }, { "id": 896, "seek": 194252, "start": 1945.64, "end": 1948.26, "text": " data looks like. We", "tokens": [ 51014, 1412, 1542, 411, 13, 492, 51164 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1945.64, "end": 1945.9, "word": " data", "probability": 0.81298828125 }, { "start": 1945.9, "end": 1946.46, "word": " looks", "probability": 0.796875 }, { "start": 1946.46, "end": 1946.86, "word": " like", "probability": 0.87744140625 }, { "start": 1946.86, "end": 1947.26, "word": ".", "probability": 0.96484375 }, { "start": 1947.86, "end": 1948.26, "word": " We", "probability": 0.89892578125 } ] }, { "id": 897, "seek": 194252, "start": 1948.26, "end": 1949.38, "text": " generally have an idea,", "tokens": [ 51164, 5101, 362, 364, 1558, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1948.26, "end": 1948.62, "word": " generally", "probability": 0.83984375 }, { "start": 1948.62, "end": 1948.84, "word": " have", "probability": 0.876953125 }, { "start": 1948.84, "end": 1948.94, "word": " an", "probability": 0.9013671875 }, { "start": 1948.94, "end": 1949.18, "word": " idea", "probability": 0.77392578125 }, { "start": 1949.18, "end": 1949.38, "word": ",", "probability": 0.70068359375 } ] }, { "id": 898, "seek": 194252, "start": 1949.38, "end": 1950.14, "text": " but we just kind of want", "tokens": [ 51214, 457, 321, 445, 733, 295, 528, 51264 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1949.38, "end": 1949.5, "word": " but", "probability": 0.89990234375 }, { "start": 1949.5, "end": 1949.66, "word": " we", "probability": 0.90625 }, { "start": 1949.66, "end": 1949.84, "word": " just", "probability": 0.88427734375 }, { "start": 1949.84, "end": 1950.0, "word": " kind", "probability": 0.5380859375 }, { "start": 1950.0, "end": 1950.02, "word": " of", "probability": 0.9072265625 }, { "start": 1950.02, "end": 1950.14, "word": " want", "probability": 0.42431640625 } ] }, { "id": 899, "seek": 194252, "start": 1950.14, "end": 1950.88, "text": " to play around with it.", "tokens": [ 51264, 281, 862, 926, 365, 309, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1950.14, "end": 1950.22, "word": " to", "probability": 0.9091796875 }, { "start": 1950.22, "end": 1950.38, "word": " play", "probability": 0.8837890625 }, { "start": 1950.38, "end": 1950.6, "word": " around", "probability": 0.87060546875 }, { "start": 1950.6, "end": 1950.76, "word": " with", "probability": 0.81884765625 }, { "start": 1950.76, "end": 1950.86, "word": " it", "probability": 0.90380859375 }, { "start": 1950.86, "end": 1950.88, "word": ".", "probability": 0.84130859375 } ] }, { "id": 900, "seek": 194252, "start": 1950.88, "end": 1951.62, "text": " And this is another thing", "tokens": [ 51314, 400, 341, 307, 1071, 551, 51364 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1950.88, "end": 1950.96, "word": " And", "probability": 0.880859375 }, { "start": 1950.96, "end": 1951.08, "word": " this", "probability": 0.8828125 }, { "start": 1951.08, "end": 1951.2, "word": " is", "probability": 0.90625 }, { "start": 1951.2, "end": 1951.42, "word": " another", "probability": 0.8173828125 }, { "start": 1951.42, "end": 1951.62, "word": " thing", "probability": 0.8125 } ] }, { "id": 901, "seek": 194252, "start": 1951.62, "end": 1952.44, "text": " that you would want to", "tokens": [ 51364, 300, 291, 576, 528, 281, 51414 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1951.62, "end": 1951.72, "word": " that", "probability": 0.8779296875 }, { "start": 1951.72, "end": 1951.78, "word": " you", "probability": 0.89599609375 }, { "start": 1951.78, "end": 1951.92, "word": " would", "probability": 0.845703125 }, { "start": 1951.92, "end": 1952.26, "word": " want", "probability": 0.81298828125 }, { "start": 1952.26, "end": 1952.44, "word": " to", "probability": 0.8974609375 } ] }, { "id": 902, "seek": 194252, "start": 1952.44, "end": 1953.8, "text": " do in a data discovery", "tokens": [ 51414, 360, 294, 257, 1412, 12114, 51464 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1952.44, "end": 1952.68, "word": " do", "probability": 0.90625 }, { "start": 1952.68, "end": 1953.0, "word": " in", "probability": 0.89306640625 }, { "start": 1953.2, "end": 1953.4, "word": " a data", "probability": 0.8095703125 }, { "start": 1953.4, "end": 1953.8, "word": " discovery", "probability": 0.7880859375 } ] }, { "id": 903, "seek": 194252, "start": 1953.8, "end": 1954.98, "text": " process is just kind of", "tokens": [ 51464, 1399, 307, 445, 733, 295, 51514 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1953.8, "end": 1954.32, "word": " process", "probability": 0.85546875 }, { "start": 1954.32, "end": 1954.52, "word": " is", "probability": 0.6630859375 }, { "start": 1954.52, "end": 1954.7, "word": " just", "probability": 0.88232421875 }, { "start": 1954.7, "end": 1954.9, "word": " kind", "probability": 0.82080078125 }, { "start": 1954.9, "end": 1954.98, "word": " of", "probability": 0.90380859375 } ] }, { "id": 904, "seek": 194252, "start": 1954.98, "end": 1955.84, "text": " see, okay, what is it", "tokens": [ 51514, 536, 11, 1392, 11, 437, 307, 309, 51564 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1954.98, "end": 1955.12, "word": " see", "probability": 0.73583984375 }, { "start": 1955.12, "end": 1955.22, "word": ",", "probability": 0.91162109375 }, { "start": 1955.22, "end": 1955.38, "word": " okay", "probability": 0.74169921875 }, { "start": 1955.38, "end": 1955.38, "word": ",", "probability": 0.85107421875 }, { "start": 1955.38, "end": 1955.62, "word": " what", "probability": 0.88134765625 }, { "start": 1955.62, "end": 1955.74, "word": " is", "probability": 0.90673828125 }, { "start": 1955.74, "end": 1955.84, "word": " it", "probability": 0.8955078125 } ] }, { "id": 905, "seek": 194252, "start": 1955.84, "end": 1956.3, "text": " that we're actually", "tokens": [ 51564, 300, 321, 434, 767, 51614 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1955.84, "end": 1955.92, "word": " that", "probability": 0.88623046875 }, { "start": 1955.92, "end": 1956.04, "word": " we're", "probability": 0.9326171875 }, { "start": 1956.04, "end": 1956.3, "word": " actually", "probability": 0.78173828125 } ] }, { "id": 906, "seek": 194252, "start": 1956.3, "end": 1958.34, "text": " working with? So in this", "tokens": [ 51614, 1364, 365, 30, 407, 294, 341, 51664 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1956.3, "end": 1956.6, "word": " working", "probability": 0.7294921875 }, { "start": 1956.6, "end": 1956.8, "word": " with", "probability": 0.7451171875 }, { "start": 1956.8, "end": 1957.2, "word": "?", "probability": 0.94873046875 }, { "start": 1957.6, "end": 1958.0, "word": " So", "probability": 0.90087890625 }, { "start": 1958.0, "end": 1958.2, "word": " in", "probability": 0.88427734375 }, { "start": 1958.2, "end": 1958.34, "word": " this", "probability": 0.87939453125 } ] }, { "id": 907, "seek": 194252, "start": 1958.34, "end": 1961.22, "text": " case, I'm going to pick", "tokens": [ 51664, 1389, 11, 286, 478, 516, 281, 1888, 51814 ], "temperature": 0.0, "avg_logprob": -0.18881118714392603, "compression_ratio": 1.6496062992125984, "no_speech_prob": 0.010009765625, "words": [ { "start": 1958.34, "end": 1958.58, "word": " case", "probability": 0.81103515625 }, { "start": 1958.58, "end": 1958.64, "word": ",", "probability": 0.9443359375 }, { "start": 1958.64, "end": 1958.86, "word": " I'm", "probability": 0.999267578125 }, { "start": 1958.86, "end": 1959.08, "word": " going", "probability": 0.859375 }, { "start": 1959.08, "end": 1959.58, "word": " to", "probability": 0.90380859375 }, { "start": 1959.58, "end": 1961.22, "word": " pick", "probability": 0.802734375 } ] }, { "id": 908, "seek": 197176, "start": 1961.22, "end": 1963.2, "text": " an email ID, just email", "tokens": [ 50364, 364, 3796, 7348, 11, 445, 3796, 50464 ], "temperature": 0.0, "avg_logprob": -0.19431089386980757, "compression_ratio": 1.8571428571428572, "no_speech_prob": 0.00926971435546875, "words": [ { "start": 1961.22, "end": 1961.3, "word": " an", "probability": 0.02545166015625 }, { "start": 1961.3, "end": 1961.62, "word": " email", "probability": 0.78271484375 }, { "start": 1961.62, "end": 1962.26, "word": " ID", "probability": 0.403076171875 }, { "start": 1962.26, "end": 1962.62, "word": ",", "probability": 0.54541015625 }, { "start": 1962.62, "end": 1962.78, "word": " just", "probability": 0.669921875 }, { "start": 1962.78, "end": 1963.2, "word": " email", "probability": 0.73583984375 } ] }, { "id": 909, "seek": 197176, "start": 1963.2, "end": 1965.18, "text": " ID 5. You can pick 5 or", "tokens": [ 50464, 7348, 1025, 13, 509, 393, 1888, 1025, 420, 50564 ], "temperature": 0.0, "avg_logprob": -0.19431089386980757, "compression_ratio": 1.8571428571428572, "no_speech_prob": 0.00926971435546875, "words": [ { "start": 1963.2, "end": 1963.54, "word": " ID", "probability": 0.68603515625 }, { "start": 1963.54, "end": 1964.04, "word": " 5", "probability": 0.66748046875 }, { "start": 1964.04, "end": 1964.36, "word": ".", "probability": 0.62939453125 }, { "start": 1964.36, "end": 1964.46, "word": " You", "probability": 0.8017578125 }, { "start": 1964.46, "end": 1964.6, "word": " can", "probability": 0.89453125 }, { "start": 1964.6, "end": 1964.74, "word": " pick", "probability": 0.79833984375 }, { "start": 1964.74, "end": 1965.06, "word": " 5", "probability": 0.76416015625 }, { "start": 1965.06, "end": 1965.18, "word": " or", "probability": 0.7548828125 } ] }, { "id": 910, "seek": 197176, "start": 1965.18, "end": 1966.64, "text": " you can pick any other.", "tokens": [ 50564, 291, 393, 1888, 604, 661, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.19431089386980757, "compression_ratio": 1.8571428571428572, "no_speech_prob": 0.00926971435546875, "words": [ { "start": 1965.18, "end": 1965.26, "word": " you", "probability": 0.81640625 }, { "start": 1965.26, "end": 1965.4, "word": " can", "probability": 0.89208984375 }, { "start": 1965.4, "end": 1965.56, "word": " pick", "probability": 0.8125 }, { "start": 1965.56, "end": 1965.76, "word": " any", "probability": 0.81689453125 }, { "start": 1965.76, "end": 1966.04, "word": " other", "probability": 0.7783203125 }, { "start": 1966.04, "end": 1966.64, "word": ".", "probability": 0.82177734375 } ] }, { "id": 911, "seek": 197176, "start": 1967.52, "end": 1969.0, "text": " And then I'm going to", "tokens": [ 50614, 400, 550, 286, 478, 516, 281, 50714 ], "temperature": 0.0, "avg_logprob": -0.19431089386980757, "compression_ratio": 1.8571428571428572, "no_speech_prob": 0.00926971435546875, "words": [ { "start": 1967.52, "end": 1967.72, "word": " And", "probability": 0.5751953125 }, { "start": 1967.72, "end": 1967.96, "word": " then", "probability": 0.712890625 }, { "start": 1967.96, "end": 1968.18, "word": " I'm", "probability": 0.941650390625 }, { "start": 1968.18, "end": 1968.38, "word": " going", "probability": 0.8603515625 }, { "start": 1968.38, "end": 1969.0, "word": " to", "probability": 0.908203125 } ] }, { "id": 912, "seek": 197176, "start": 1969.0, "end": 1970.56, "text": " grab the email, which", "tokens": [ 50714, 4444, 264, 3796, 11, 597, 50814 ], "temperature": 0.0, "avg_logprob": -0.19431089386980757, "compression_ratio": 1.8571428571428572, "no_speech_prob": 0.00926971435546875, "words": [ { "start": 1969.0, "end": 1969.58, "word": " grab", "probability": 0.7841796875 }, { "start": 1969.58, "end": 1969.72, "word": " the", "probability": 0.81005859375 }, { "start": 1969.72, "end": 1970.04, "word": " email", "probability": 0.91015625 }, { "start": 1970.04, "end": 1970.36, "word": ",", "probability": 0.56787109375 }, { "start": 1970.36, "end": 1970.56, "word": " which", "probability": 0.91259765625 } ] }, { "id": 913, "seek": 197176, "start": 1970.56, "end": 1971.58, "text": " is part of the corpus", "tokens": [ 50814, 307, 644, 295, 264, 1181, 31624, 50864 ], "temperature": 0.0, "avg_logprob": -0.19431089386980757, "compression_ratio": 1.8571428571428572, "no_speech_prob": 0.00926971435546875, "words": [ { "start": 1970.56, "end": 1970.86, "word": " is", "probability": 0.90576171875 }, { "start": 1970.86, "end": 1971.08, "word": " part", "probability": 0.80615234375 }, { "start": 1971.08, "end": 1971.16, "word": " of", "probability": 0.90576171875 }, { "start": 1971.16, "end": 1971.28, "word": " the", "probability": 0.81201171875 }, { "start": 1971.28, "end": 1971.58, "word": " corpus", "probability": 0.8203125 } ] }, { "id": 914, "seek": 197176, "start": 1971.58, "end": 1974.16, "text": " array. Corpus and then", "tokens": [ 50864, 10225, 13, 3925, 31624, 293, 550, 51014 ], "temperature": 0.0, "avg_logprob": -0.19431089386980757, "compression_ratio": 1.8571428571428572, "no_speech_prob": 0.00926971435546875, "words": [ { "start": 1971.58, "end": 1971.96, "word": " array", "probability": 0.7646484375 }, { "start": 1971.96, "end": 1972.56, "word": ".", "probability": 0.54150390625 }, { "start": 1973.0, "end": 1973.6, "word": " Corpus", "probability": 0.693603515625 }, { "start": 1973.6, "end": 1973.86, "word": " and", "probability": 0.58642578125 }, { "start": 1973.86, "end": 1974.16, "word": " then", "probability": 0.72021484375 } ] }, { "id": 915, "seek": 197176, "start": 1974.16, "end": 1977.34, "text": " our email ID. And then", "tokens": [ 51014, 527, 3796, 7348, 13, 400, 550, 51164 ], "temperature": 0.0, "avg_logprob": -0.19431089386980757, "compression_ratio": 1.8571428571428572, "no_speech_prob": 0.00926971435546875, "words": [ { "start": 1974.16, "end": 1974.54, "word": " our", "probability": 0.8154296875 }, { "start": 1974.54, "end": 1974.9, "word": " email", "probability": 0.91259765625 }, { "start": 1974.9, "end": 1975.32, "word": " ID", "probability": 0.86083984375 }, { "start": 1975.32, "end": 1975.92, "word": ".", "probability": 0.73681640625 }, { "start": 1976.88, "end": 1977.12, "word": " And", "probability": 0.8427734375 }, { "start": 1977.12, "end": 1977.34, "word": " then", "probability": 0.72802734375 } ] }, { "id": 916, "seek": 197176, "start": 1977.34, "end": 1979.74, "text": " I'm going to print that", "tokens": [ 51164, 286, 478, 516, 281, 4482, 300, 51264 ], "temperature": 0.0, "avg_logprob": -0.19431089386980757, "compression_ratio": 1.8571428571428572, "no_speech_prob": 0.00926971435546875, "words": [ { "start": 1977.34, "end": 1977.62, "word": " I'm", "probability": 0.98681640625 }, { "start": 1977.62, "end": 1977.86, "word": " going", "probability": 0.86083984375 }, { "start": 1977.86, "end": 1978.38, "word": " to", "probability": 0.91162109375 }, { "start": 1978.38, "end": 1979.5, "word": " print", "probability": 0.86572265625 }, { "start": 1979.5, "end": 1979.74, "word": " that", "probability": 0.88037109375 } ] }, { "id": 917, "seek": 197176, "start": 1979.74, "end": 1981.56, "text": " email, and then I'm", "tokens": [ 51264, 3796, 11, 293, 550, 286, 478, 51364 ], "temperature": 0.0, "avg_logprob": -0.19431089386980757, "compression_ratio": 1.8571428571428572, "no_speech_prob": 0.00926971435546875, "words": [ { "start": 1979.74, "end": 1980.14, "word": " email", "probability": 0.92578125 }, { "start": 1980.14, "end": 1980.7, "word": ",", "probability": 0.338623046875 }, { "start": 1980.7, "end": 1981.1, "word": " and", "probability": 0.87939453125 }, { "start": 1981.1, "end": 1981.34, "word": " then", "probability": 0.71435546875 }, { "start": 1981.34, "end": 1981.56, "word": " I'm", "probability": 0.994140625 } ] }, { "id": 918, "seek": 197176, "start": 1981.56, "end": 1982.4, "text": " going to do the same", "tokens": [ 51364, 516, 281, 360, 264, 912, 51414 ], "temperature": 0.0, "avg_logprob": -0.19431089386980757, "compression_ratio": 1.8571428571428572, "no_speech_prob": 0.00926971435546875, "words": [ { "start": 1981.56, "end": 1981.76, "word": " going", "probability": 0.861328125 }, { "start": 1981.76, "end": 1981.96, "word": " to", "probability": 0.90625 }, { "start": 1981.96, "end": 1982.06, "word": " do", "probability": 0.90673828125 }, { "start": 1982.06, "end": 1982.2, "word": " the", "probability": 0.81201171875 }, { "start": 1982.2, "end": 1982.4, "word": " same", "probability": 0.81982421875 } ] }, { "id": 919, "seek": 197176, "start": 1982.4, "end": 1984.52, "text": " thing and print the", "tokens": [ 51414, 551, 293, 4482, 264, 51514 ], "temperature": 0.0, "avg_logprob": -0.19431089386980757, "compression_ratio": 1.8571428571428572, "no_speech_prob": 0.00926971435546875, "words": [ { "start": 1982.4, "end": 1982.72, "word": " thing", "probability": 0.810546875 }, { "start": 1982.72, "end": 1983.22, "word": " and", "probability": 0.8037109375 }, { "start": 1983.22, "end": 1983.98, "word": " print", "probability": 0.869140625 }, { "start": 1983.98, "end": 1984.52, "word": " the", "probability": 0.80810546875 } ] }, { "id": 920, "seek": 197176, "start": 1985.46, "end": 1987.3, "text": " tokenized version using", "tokens": [ 51514, 14862, 1602, 3037, 1228, 51664 ], "temperature": 0.0, "avg_logprob": -0.19431089386980757, "compression_ratio": 1.8571428571428572, "no_speech_prob": 0.00926971435546875, "words": [ { "start": 1985.46, "end": 1986.06, "word": " tokenized", "probability": 0.887451171875 }, { "start": 1986.06, "end": 1986.66, "word": " version", "probability": 0.74072265625 }, { "start": 1986.66, "end": 1987.3, "word": " using", "probability": 0.51416015625 } ] }, { "id": 921, "seek": 197176, "start": 1987.46, "end": 1989.1, "text": " a tokenizer function of", "tokens": [ 51664, 257, 14862, 6545, 2445, 295, 51714 ], "temperature": 0.0, "avg_logprob": -0.19431089386980757, "compression_ratio": 1.8571428571428572, "no_speech_prob": 0.00926971435546875, "words": [ { "start": 1987.46, "end": 1987.8, "word": " a tokenizer", "probability": 0.88427734375 }, { "start": 1987.8, "end": 1988.32, "word": " function", "probability": 0.89306640625 }, { "start": 1988.32, "end": 1989.1, "word": " of", "probability": 0.87158203125 } ] }, { "id": 922, "seek": 197176, "start": 1989.1, "end": 1990.46, "text": " that email. So we can", "tokens": [ 51714, 300, 3796, 13, 407, 321, 393, 51814 ], "temperature": 0.0, "avg_logprob": -0.19431089386980757, "compression_ratio": 1.8571428571428572, "no_speech_prob": 0.00926971435546875, "words": [ { "start": 1989.1, "end": 1989.3, "word": " that", "probability": 0.87109375 }, { "start": 1989.3, "end": 1989.62, "word": " email", "probability": 0.9208984375 }, { "start": 1989.62, "end": 1989.92, "word": ".", "probability": 0.615234375 }, { "start": 1989.92, "end": 1990.28, "word": " So", "probability": 0.8515625 }, { "start": 1990.28, "end": 1990.36, "word": " we", "probability": 0.79931640625 }, { "start": 1990.36, "end": 1990.46, "word": " can", "probability": 0.89404296875 } ] }, { "id": 923, "seek": 200094, "start": 1990.46, "end": 1991.7, "text": " see how it's transformed.", "tokens": [ 50364, 536, 577, 309, 311, 16894, 13, 50414 ], "temperature": 0.0, "avg_logprob": -0.2057549534457745, "compression_ratio": 1.4776119402985075, "no_speech_prob": 0.225341796875, "words": [ { "start": 1990.46, "end": 1990.6, "word": " see", "probability": 0.054351806640625 }, { "start": 1990.6, "end": 1990.78, "word": " how", "probability": 0.9052734375 }, { "start": 1990.78, "end": 1990.94, "word": " it's", "probability": 0.92919921875 }, { "start": 1990.94, "end": 1991.4, "word": " transformed", "probability": 0.8056640625 }, { "start": 1991.4, "end": 1991.7, "word": ".", "probability": 0.90966796875 } ] }, { "id": 924, "seek": 200094, "start": 1994.18, "end": 1995.84, "text": " So just so I don't go", "tokens": [ 50414, 407, 445, 370, 286, 500, 380, 352, 50614 ], "temperature": 0.0, "avg_logprob": -0.2057549534457745, "compression_ratio": 1.4776119402985075, "no_speech_prob": 0.225341796875, "words": [ { "start": 1994.18, "end": 1994.54, "word": " So", "probability": 0.73095703125 }, { "start": 1994.54, "end": 1995.3, "word": " just", "probability": 0.63818359375 }, { "start": 1995.3, "end": 1995.42, "word": " so", "probability": 0.87646484375 }, { "start": 1995.42, "end": 1995.48, "word": " I", "probability": 0.42041015625 }, { "start": 1995.48, "end": 1995.64, "word": " don't", "probability": 0.94287109375 }, { "start": 1995.64, "end": 1995.84, "word": " go", "probability": 0.8984375 } ] }, { "id": 925, "seek": 200094, "start": 1995.84, "end": 1997.24, "text": " too fast, I want to make", "tokens": [ 50614, 886, 2370, 11, 286, 528, 281, 652, 50664 ], "temperature": 0.0, "avg_logprob": -0.2057549534457745, "compression_ratio": 1.4776119402985075, "no_speech_prob": 0.225341796875, "words": [ { "start": 1995.84, "end": 1996.34, "word": " too", "probability": 0.8193359375 }, { "start": 1996.34, "end": 1996.78, "word": " fast", "probability": 0.80859375 }, { "start": 1996.78, "end": 1996.84, "word": ",", "probability": 0.78466796875 }, { "start": 1996.84, "end": 1996.96, "word": " I", "probability": 0.98681640625 }, { "start": 1996.96, "end": 1997.04, "word": " want", "probability": 0.70751953125 }, { "start": 1997.04, "end": 1997.1, "word": " to", "probability": 0.90185546875 }, { "start": 1997.1, "end": 1997.24, "word": " make", "probability": 0.8798828125 } ] }, { "id": 926, "seek": 200094, "start": 1997.24, "end": 1998.2, "text": " sure that you're able to", "tokens": [ 50664, 988, 300, 291, 434, 1075, 281, 50714 ], "temperature": 0.0, "avg_logprob": -0.2057549534457745, "compression_ratio": 1.4776119402985075, "no_speech_prob": 0.225341796875, "words": [ { "start": 1997.24, "end": 1997.36, "word": " sure", "probability": 0.8212890625 }, { "start": 1997.36, "end": 1997.5, "word": " that", "probability": 0.82958984375 }, { "start": 1997.5, "end": 1997.64, "word": " you're", "probability": 0.916748046875 }, { "start": 1997.64, "end": 1997.88, "word": " able", "probability": 0.88427734375 }, { "start": 1997.88, "end": 1998.2, "word": " to", "probability": 0.9091796875 } ] }, { "id": 927, "seek": 200094, "start": 1998.2, "end": 1999.66, "text": " follow along and copy", "tokens": [ 50714, 1524, 2051, 293, 5055, 50814 ], "temperature": 0.0, "avg_logprob": -0.2057549534457745, "compression_ratio": 1.4776119402985075, "no_speech_prob": 0.225341796875, "words": [ { "start": 1998.2, "end": 1998.58, "word": " follow", "probability": 0.87060546875 }, { "start": 1998.58, "end": 1999.0, "word": " along", "probability": 0.89404296875 }, { "start": 1999.0, "end": 1999.18, "word": " and", "probability": 0.87744140625 }, { "start": 1999.18, "end": 1999.66, "word": " copy", "probability": 0.80517578125 } ] }, { "id": 928, "seek": 200094, "start": 1999.66, "end": 2001.94, "text": " this down. It's fairly", "tokens": [ 50814, 341, 760, 13, 467, 311, 6457, 50914 ], "temperature": 0.0, "avg_logprob": -0.2057549534457745, "compression_ratio": 1.4776119402985075, "no_speech_prob": 0.225341796875, "words": [ { "start": 1999.66, "end": 1999.86, "word": " this", "probability": 0.88330078125 }, { "start": 1999.86, "end": 2000.16, "word": " down", "probability": 0.81005859375 }, { "start": 2000.16, "end": 2000.76, "word": ".", "probability": 0.9814453125 }, { "start": 2001.28, "end": 2001.72, "word": " It's", "probability": 0.931884765625 }, { "start": 2001.72, "end": 2001.94, "word": " fairly", "probability": 0.84619140625 } ] }, { "id": 929, "seek": 200094, "start": 2001.94, "end": 2004.32, "text": " simple. So I will wait", "tokens": [ 50914, 2199, 13, 407, 286, 486, 1699, 51014 ], "temperature": 0.0, "avg_logprob": -0.2057549534457745, "compression_ratio": 1.4776119402985075, "no_speech_prob": 0.225341796875, "words": [ { "start": 2001.94, "end": 2002.3, "word": " simple", "probability": 0.9150390625 }, { "start": 2002.3, "end": 2002.9, "word": ".", "probability": 0.6796875 }, { "start": 2003.12, "end": 2003.72, "word": " So", "probability": 0.88525390625 }, { "start": 2003.72, "end": 2003.88, "word": " I", "probability": 0.9931640625 }, { "start": 2003.88, "end": 2004.02, "word": " will", "probability": 0.8095703125 }, { "start": 2004.02, "end": 2004.32, "word": " wait", "probability": 0.8232421875 } ] }, { "id": 930, "seek": 200094, "start": 2004.32, "end": 2007.62, "text": " just a few seconds. How", "tokens": [ 51014, 445, 257, 1326, 3949, 13, 1012, 51214 ], "temperature": 0.0, "avg_logprob": -0.2057549534457745, "compression_ratio": 1.4776119402985075, "no_speech_prob": 0.225341796875, "words": [ { "start": 2004.32, "end": 2004.62, "word": " just", "probability": 0.8857421875 }, { "start": 2004.78, "end": 2004.94, "word": " a few", "probability": 0.814453125 }, { "start": 2004.94, "end": 2005.44, "word": " seconds", "probability": 0.72412109375 }, { "start": 2005.44, "end": 2006.04, "word": ".", "probability": 0.9912109375 }, { "start": 2007.06, "end": 2007.62, "word": " How", "probability": 0.8857421875 } ] }, { "id": 931, "seek": 200094, "start": 2007.62, "end": 2008.42, "text": " are we doing on", "tokens": [ 51214, 366, 321, 884, 322, 51264 ], "temperature": 0.0, "avg_logprob": -0.2057549534457745, "compression_ratio": 1.4776119402985075, "no_speech_prob": 0.225341796875, "words": [ { "start": 2007.62, "end": 2007.94, "word": " are", "probability": 0.90478515625 }, { "start": 2007.94, "end": 2008.04, "word": " we", "probability": 0.640625 }, { "start": 2008.04, "end": 2008.22, "word": " doing", "probability": 0.89892578125 }, { "start": 2008.22, "end": 2008.42, "word": " on", "probability": 0.888671875 } ] }, { "id": 932, "seek": 200094, "start": 2008.42, "end": 2009.46, "text": " questions?", "tokens": [ 51264, 1651, 30, 51314 ], "temperature": 0.0, "avg_logprob": -0.2057549534457745, "compression_ratio": 1.4776119402985075, "no_speech_prob": 0.225341796875, "words": [ { "start": 2008.42, "end": 2008.86, "word": " questions", "probability": 0.81005859375 }, { "start": 2008.86, "end": 2009.46, "word": "?", "probability": 0.9853515625 } ] }, { "id": 933, "seek": 200094, "start": 2011.18, "end": 2012.52, "text": " No one has been", "tokens": [ 51314, 883, 472, 575, 668, 51464 ], "temperature": 0.0, "avg_logprob": -0.2057549534457745, "compression_ratio": 1.4776119402985075, "no_speech_prob": 0.225341796875, "words": [ { "start": 2011.18, "end": 2011.78, "word": " No", "probability": 0.4833984375 }, { "start": 2011.78, "end": 2011.92, "word": " one", "probability": 0.420654296875 }, { "start": 2011.92, "end": 2012.1, "word": " has", "probability": 0.88427734375 }, { "start": 2012.1, "end": 2012.52, "word": " been", "probability": 0.810546875 } ] }, { "id": 934, "seek": 200094, "start": 2012.52, "end": 2014.16, "text": " posting some helpful", "tokens": [ 51464, 15978, 512, 4961, 51514 ], "temperature": 0.0, "avg_logprob": -0.2057549534457745, "compression_ratio": 1.4776119402985075, "no_speech_prob": 0.225341796875, "words": [ { "start": 2012.52, "end": 2013.36, "word": " posting", "probability": 0.765625 }, { "start": 2013.36, "end": 2013.86, "word": " some", "probability": 0.81103515625 }, { "start": 2013.86, "end": 2014.16, "word": " helpful", "probability": 0.83349609375 } ] }, { "id": 935, "seek": 200094, "start": 2014.16, "end": 2018.64, "text": " links, but hasn't had", "tokens": [ 51514, 6123, 11, 457, 6132, 380, 632, 51764 ], "temperature": 0.0, "avg_logprob": -0.2057549534457745, "compression_ratio": 1.4776119402985075, "no_speech_prob": 0.225341796875, "words": [ { "start": 2014.16, "end": 2014.52, "word": " links", "probability": 0.78515625 }, { "start": 2014.52, "end": 2015.14, "word": ",", "probability": 0.496826171875 }, { "start": 2015.14, "end": 2017.96, "word": " but", "probability": 0.89697265625 }, { "start": 2017.96, "end": 2018.44, "word": " hasn't", "probability": 0.87060546875 }, { "start": 2018.44, "end": 2018.64, "word": " had", "probability": 0.82421875 } ] }, { "id": 936, "seek": 200094, "start": 2018.64, "end": 2019.64, "text": " too many questions so", "tokens": [ 51764, 886, 867, 1651, 370, 51814 ], "temperature": 0.0, "avg_logprob": -0.2057549534457745, "compression_ratio": 1.4776119402985075, "no_speech_prob": 0.225341796875, "words": [ { "start": 2018.64, "end": 2018.94, "word": " too", "probability": 0.70947265625 }, { "start": 2018.94, "end": 2019.1, "word": " many", "probability": 0.8271484375 }, { "start": 2019.1, "end": 2019.42, "word": " questions", "probability": 0.8994140625 }, { "start": 2019.42, "end": 2019.64, "word": " so", "probability": 0.896484375 } ] }, { "id": 937, "seek": 203092, "start": 2019.64, "end": 2022.14, "text": " far. So thank you very", "tokens": [ 50364, 1400, 13, 407, 1309, 291, 588, 50464 ], "temperature": 0.0, "avg_logprob": -0.21948242071084678, "compression_ratio": 1.6431924882629108, "no_speech_prob": 0.2093505859375, "words": [ { "start": 2019.64, "end": 2019.88, "word": " far", "probability": 0.05657958984375 }, { "start": 2019.88, "end": 2020.46, "word": ".", "probability": 0.6162109375 }, { "start": 2020.5, "end": 2020.72, "word": " So", "probability": 0.5087890625 }, { "start": 2020.72, "end": 2021.86, "word": " thank", "probability": 0.499267578125 }, { "start": 2021.86, "end": 2022.0, "word": " you", "probability": 0.89794921875 }, { "start": 2022.0, "end": 2022.14, "word": " very", "probability": 0.5732421875 } ] }, { "id": 938, "seek": 203092, "start": 2022.14, "end": 2023.42, "text": " much. No winner.", "tokens": [ 50464, 709, 13, 883, 8507, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.21948242071084678, "compression_ratio": 1.6431924882629108, "no_speech_prob": 0.2093505859375, "words": [ { "start": 2022.14, "end": 2022.42, "word": " much", "probability": 0.82275390625 }, { "start": 2022.42, "end": 2022.5, "word": ".", "probability": 0.56298828125 }, { "start": 2022.5, "end": 2022.6, "word": " No", "probability": 0.8623046875 }, { "start": 2022.6, "end": 2022.84, "word": " winner", "probability": 0.76806640625 }, { "start": 2022.84, "end": 2023.42, "word": ".", "probability": 0.953125 } ] }, { "id": 939, "seek": 203092, "start": 2024.54, "end": 2026.26, "text": " Okay. So when we run", "tokens": [ 50514, 1033, 13, 407, 562, 321, 1190, 50664 ], "temperature": 0.0, "avg_logprob": -0.21948242071084678, "compression_ratio": 1.6431924882629108, "no_speech_prob": 0.2093505859375, "words": [ { "start": 2024.54, "end": 2025.12, "word": " Okay", "probability": 0.52734375 }, { "start": 2025.12, "end": 2025.3, "word": ".", "probability": 0.51904296875 }, { "start": 2025.3, "end": 2025.68, "word": " So", "probability": 0.87890625 }, { "start": 2025.68, "end": 2025.92, "word": " when", "probability": 0.83935546875 }, { "start": 2025.92, "end": 2026.04, "word": " we", "probability": 0.91064453125 }, { "start": 2026.04, "end": 2026.26, "word": " run", "probability": 0.8818359375 } ] }, { "id": 940, "seek": 203092, "start": 2026.26, "end": 2027.76, "text": " that, what we have is", "tokens": [ 50664, 300, 11, 437, 321, 362, 307, 50714 ], "temperature": 0.0, "avg_logprob": -0.21948242071084678, "compression_ratio": 1.6431924882629108, "no_speech_prob": 0.2093505859375, "words": [ { "start": 2026.26, "end": 2026.56, "word": " that", "probability": 0.88330078125 }, { "start": 2026.56, "end": 2026.66, "word": ",", "probability": 0.74853515625 }, { "start": 2026.66, "end": 2026.74, "word": " what", "probability": 0.8701171875 }, { "start": 2026.74, "end": 2026.88, "word": " we", "probability": 0.90625 }, { "start": 2026.88, "end": 2027.32, "word": " have", "probability": 0.876953125 }, { "start": 2027.32, "end": 2027.76, "word": " is", "probability": 0.90380859375 } ] }, { "id": 941, "seek": 203092, "start": 2027.76, "end": 2029.1, "text": " the email body. We see", "tokens": [ 50714, 264, 3796, 1772, 13, 492, 536, 50814 ], "temperature": 0.0, "avg_logprob": -0.21948242071084678, "compression_ratio": 1.6431924882629108, "no_speech_prob": 0.2093505859375, "words": [ { "start": 2027.76, "end": 2028.06, "word": " the", "probability": 0.80908203125 }, { "start": 2028.06, "end": 2028.34, "word": " email", "probability": 0.8935546875 }, { "start": 2028.34, "end": 2028.64, "word": " body", "probability": 0.7880859375 }, { "start": 2028.64, "end": 2028.78, "word": ".", "probability": 0.53857421875 }, { "start": 2028.78, "end": 2028.78, "word": " We", "probability": 0.89697265625 }, { "start": 2028.78, "end": 2029.1, "word": " see", "probability": 0.80029296875 } ] }, { "id": 942, "seek": 203092, "start": 2029.1, "end": 2030.28, "text": " product review, vert", "tokens": [ 50814, 1674, 3131, 11, 6509, 50864 ], "temperature": 0.0, "avg_logprob": -0.21948242071084678, "compression_ratio": 1.6431924882629108, "no_speech_prob": 0.2093505859375, "words": [ { "start": 2029.1, "end": 2029.58, "word": " product", "probability": 0.728515625 }, { "start": 2029.58, "end": 2029.96, "word": " review", "probability": 0.62646484375 }, { "start": 2029.96, "end": 2030.12, "word": ",", "probability": 0.53564453125 }, { "start": 2030.12, "end": 2030.28, "word": " vert", "probability": 0.353759765625 } ] }, { "id": 943, "seek": 203092, "start": 2030.28, "end": 2032.32, "text": " tools, dev, 2.0 URL, and", "tokens": [ 50864, 3873, 11, 1905, 11, 568, 13, 15, 12905, 11, 293, 50964 ], "temperature": 0.0, "avg_logprob": -0.21948242071084678, "compression_ratio": 1.6431924882629108, "no_speech_prob": 0.2093505859375, "words": [ { "start": 2030.28, "end": 2030.66, "word": " tools", "probability": 0.69921875 }, { "start": 2030.66, "end": 2030.8, "word": ",", "probability": 0.783203125 }, { "start": 2030.8, "end": 2031.06, "word": " dev", "probability": 0.69482421875 }, { "start": 2031.06, "end": 2031.16, "word": ",", "probability": 0.2362060546875 }, { "start": 2031.16, "end": 2031.3, "word": " 2", "probability": 0.90234375 }, { "start": 2031.3, "end": 2031.56, "word": ".0", "probability": 0.9931640625 }, { "start": 2031.56, "end": 2031.9, "word": " URL", "probability": 0.6982421875 }, { "start": 2031.9, "end": 2032.24, "word": ",", "probability": 0.437255859375 }, { "start": 2032.24, "end": 2032.32, "word": " and", "probability": 0.884765625 } ] }, { "id": 944, "seek": 203092, "start": 2032.32, "end": 2035.02, "text": " then this URL. We see", "tokens": [ 50964, 550, 341, 12905, 13, 492, 536, 51114 ], "temperature": 0.0, "avg_logprob": -0.21948242071084678, "compression_ratio": 1.6431924882629108, "no_speech_prob": 0.2093505859375, "words": [ { "start": 2032.32, "end": 2032.44, "word": " then", "probability": 0.7060546875 }, { "start": 2032.44, "end": 2032.74, "word": " this", "probability": 0.86279296875 }, { "start": 2032.74, "end": 2033.76, "word": " URL", "probability": 0.87158203125 }, { "start": 2033.76, "end": 2033.9, "word": ".", "probability": 0.55859375 }, { "start": 2034.28, "end": 2034.86, "word": " We", "probability": 0.77587890625 }, { "start": 2034.86, "end": 2035.02, "word": " see", "probability": 0.74609375 } ] }, { "id": 945, "seek": 203092, "start": 2035.02, "end": 2036.56, "text": " product review, vert", "tokens": [ 51114, 1674, 3131, 11, 6509, 51164 ], "temperature": 0.0, "avg_logprob": -0.21948242071084678, "compression_ratio": 1.6431924882629108, "no_speech_prob": 0.2093505859375, "words": [ { "start": 2035.02, "end": 2035.48, "word": " product", "probability": 0.78564453125 }, { "start": 2035.48, "end": 2036.02, "word": " review", "probability": 0.58056640625 }, { "start": 2036.02, "end": 2036.22, "word": ",", "probability": 0.716796875 }, { "start": 2036.22, "end": 2036.56, "word": " vert", "probability": 0.7646484375 } ] }, { "id": 946, "seek": 203092, "start": 2036.56, "end": 2039.28, "text": " tool, dev, 2.0 URL as", "tokens": [ 51164, 2290, 11, 1905, 11, 568, 13, 15, 12905, 382, 51314 ], "temperature": 0.0, "avg_logprob": -0.21948242071084678, "compression_ratio": 1.6431924882629108, "no_speech_prob": 0.2093505859375, "words": [ { "start": 2036.56, "end": 2036.94, "word": " tool", "probability": 0.8291015625 }, { "start": 2036.94, "end": 2037.2, "word": ",", "probability": 0.91064453125 }, { "start": 2037.2, "end": 2037.78, "word": " dev", "probability": 0.7998046875 }, { "start": 2037.78, "end": 2037.9, "word": ",", "probability": 0.74462890625 }, { "start": 2037.9, "end": 2038.14, "word": " 2", "probability": 0.9892578125 }, { "start": 2038.14, "end": 2038.48, "word": ".0", "probability": 0.998046875 }, { "start": 2038.48, "end": 2038.96, "word": " URL", "probability": 0.81982421875 }, { "start": 2038.96, "end": 2039.28, "word": " as", "probability": 0.5732421875 } ] }, { "id": 947, "seek": 203092, "start": 2039.28, "end": 2042.06, "text": " one word, HTTP, and then", "tokens": [ 51314, 472, 1349, 11, 33283, 11, 293, 550, 51464 ], "temperature": 0.0, "avg_logprob": -0.21948242071084678, "compression_ratio": 1.6431924882629108, "no_speech_prob": 0.2093505859375, "words": [ { "start": 2039.28, "end": 2039.48, "word": " one", "probability": 0.806640625 }, { "start": 2039.48, "end": 2039.88, "word": " word", "probability": 0.75830078125 }, { "start": 2039.88, "end": 2040.44, "word": ",", "probability": 0.70751953125 }, { "start": 2040.44, "end": 2040.86, "word": " HTTP", "probability": 0.6826171875 }, { "start": 2040.86, "end": 2041.38, "word": ",", "probability": 0.68603515625 }, { "start": 2041.38, "end": 2041.72, "word": " and", "probability": 0.89599609375 }, { "start": 2041.72, "end": 2042.06, "word": " then", "probability": 0.71923828125 } ] }, { "id": 948, "seek": 203092, "start": 2042.06, "end": 2044.6, "text": " the full URL. So this", "tokens": [ 51464, 264, 1577, 12905, 13, 407, 341, 51564 ], "temperature": 0.0, "avg_logprob": -0.21948242071084678, "compression_ratio": 1.6431924882629108, "no_speech_prob": 0.2093505859375, "words": [ { "start": 2042.06, "end": 2042.72, "word": " the", "probability": 0.81005859375 }, { "start": 2042.72, "end": 2043.0, "word": " full", "probability": 0.79345703125 }, { "start": 2043.0, "end": 2043.42, "word": " URL", "probability": 0.900390625 }, { "start": 2043.42, "end": 2043.92, "word": ".", "probability": 0.9970703125 }, { "start": 2043.92, "end": 2044.44, "word": " So", "probability": 0.892578125 }, { "start": 2044.44, "end": 2044.6, "word": " this", "probability": 0.87841796875 } ] }, { "id": 949, "seek": 203092, "start": 2044.6, "end": 2045.46, "text": " is how we can identify", "tokens": [ 51564, 307, 577, 321, 393, 5876, 51614 ], "temperature": 0.0, "avg_logprob": -0.21948242071084678, "compression_ratio": 1.6431924882629108, "no_speech_prob": 0.2093505859375, "words": [ { "start": 2044.6, "end": 2044.72, "word": " is", "probability": 0.90576171875 }, { "start": 2044.72, "end": 2044.82, "word": " how", "probability": 0.89404296875 }, { "start": 2044.82, "end": 2044.92, "word": " we", "probability": 0.9052734375 }, { "start": 2044.92, "end": 2045.06, "word": " can", "probability": 0.89697265625 }, { "start": 2045.06, "end": 2045.46, "word": " identify", "probability": 0.88525390625 } ] }, { "id": 950, "seek": 203092, "start": 2045.46, "end": 2047.68, "text": " and kind of track our", "tokens": [ 51614, 293, 733, 295, 2837, 527, 51714 ], "temperature": 0.0, "avg_logprob": -0.21948242071084678, "compression_ratio": 1.6431924882629108, "no_speech_prob": 0.2093505859375, "words": [ { "start": 2045.46, "end": 2046.0, "word": " and", "probability": 0.8701171875 }, { "start": 2046.0, "end": 2046.6, "word": " kind", "probability": 0.64501953125 }, { "start": 2046.6, "end": 2046.72, "word": " of", "probability": 0.9013671875 }, { "start": 2046.72, "end": 2047.18, "word": " track", "probability": 0.85888671875 }, { "start": 2047.18, "end": 2047.68, "word": " our", "probability": 0.81787109375 } ] }, { "id": 951, "seek": 203092, "start": 2047.68, "end": 2048.52, "text": " data as it's being", "tokens": [ 51714, 1412, 382, 309, 311, 885, 51764 ], "temperature": 0.0, "avg_logprob": -0.21948242071084678, "compression_ratio": 1.6431924882629108, "no_speech_prob": 0.2093505859375, "words": [ { "start": 2047.68, "end": 2047.94, "word": " data", "probability": 0.8173828125 }, { "start": 2047.94, "end": 2048.18, "word": " as", "probability": 0.900390625 }, { "start": 2048.18, "end": 2048.34, "word": " it's", "probability": 0.943115234375 }, { "start": 2048.34, "end": 2048.52, "word": " being", "probability": 0.8837890625 } ] }, { "id": 952, "seek": 203092, "start": 2048.52, "end": 2049.62, "text": " transformed over time.", "tokens": [ 51764, 16894, 670, 565, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.21948242071084678, "compression_ratio": 1.6431924882629108, "no_speech_prob": 0.2093505859375, "words": [ { "start": 2048.52, "end": 2049.14, "word": " transformed", "probability": 0.748046875 }, { "start": 2049.14, "end": 2049.62, "word": " over", "probability": 0.84033203125 }, { "start": 2049.62, "end": 2049.62, "word": " time", "probability": 0.67529296875 }, { "start": 2049.62, "end": 2049.62, "word": ".", "probability": 0.9169921875 } ] }, { "id": 953, "seek": 205822, "start": 2051.98, "end": 2053.2, "text": " So task 3 is where", "tokens": [ 50364, 407, 5633, 805, 307, 689, 50514 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2051.98, "end": 2052.34, "word": " So", "probability": 0.1142578125 }, { "start": 2052.34, "end": 2052.7, "word": " task", "probability": 0.45166015625 }, { "start": 2052.7, "end": 2052.9, "word": " 3", "probability": 0.298095703125 }, { "start": 2052.9, "end": 2053.06, "word": " is", "probability": 0.89111328125 }, { "start": 2053.06, "end": 2053.2, "word": " where", "probability": 0.8837890625 } ] }, { "id": 954, "seek": 205822, "start": 2053.2, "end": 2053.62, "text": " we're going to start", "tokens": [ 50514, 321, 434, 516, 281, 722, 50564 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2053.2, "end": 2053.32, "word": " we're", "probability": 0.88671875 }, { "start": 2053.32, "end": 2053.4, "word": " going", "probability": 0.625 }, { "start": 2053.4, "end": 2053.46, "word": " to", "probability": 0.8984375 }, { "start": 2053.46, "end": 2053.62, "word": " start", "probability": 0.85400390625 } ] }, { "id": 955, "seek": 205822, "start": 2053.62, "end": 2054.7, "text": " using our vectorizers.", "tokens": [ 50564, 1228, 527, 8062, 22525, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2053.62, "end": 2053.84, "word": " using", "probability": 0.8232421875 }, { "start": 2053.84, "end": 2054.0, "word": " our", "probability": 0.79931640625 }, { "start": 2054.0, "end": 2054.54, "word": " vectorizers", "probability": 0.919189453125 }, { "start": 2054.54, "end": 2054.7, "word": ".", "probability": 0.89111328125 } ] }, { "id": 956, "seek": 205822, "start": 2054.7, "end": 2055.94, "text": " What we want to do is", "tokens": [ 50614, 708, 321, 528, 281, 360, 307, 50664 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2054.7, "end": 2054.8, "word": " What", "probability": 0.79248046875 }, { "start": 2054.8, "end": 2054.94, "word": " we", "probability": 0.90625 }, { "start": 2054.94, "end": 2055.12, "word": " want", "probability": 0.81494140625 }, { "start": 2055.12, "end": 2055.22, "word": " to", "probability": 0.9091796875 }, { "start": 2055.22, "end": 2055.5, "word": " do", "probability": 0.908203125 }, { "start": 2055.5, "end": 2055.94, "word": " is", "probability": 0.89306640625 } ] }, { "id": 957, "seek": 205822, "start": 2055.94, "end": 2057.56, "text": " get a count of each", "tokens": [ 50664, 483, 257, 1207, 295, 1184, 50714 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2055.94, "end": 2056.18, "word": " get", "probability": 0.8779296875 }, { "start": 2056.4, "end": 2056.88, "word": " a count", "probability": 0.7822265625 }, { "start": 2056.88, "end": 2057.28, "word": " of", "probability": 0.904296875 }, { "start": 2057.28, "end": 2057.56, "word": " each", "probability": 0.8603515625 } ] }, { "id": 958, "seek": 205822, "start": 2057.56, "end": 2058.72, "text": " unique word, and we want", "tokens": [ 50714, 3845, 1349, 11, 293, 321, 528, 50814 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2057.56, "end": 2057.94, "word": " unique", "probability": 0.7900390625 }, { "start": 2057.94, "end": 2058.28, "word": " word", "probability": 0.798828125 }, { "start": 2058.28, "end": 2058.42, "word": ",", "probability": 0.3544921875 }, { "start": 2058.42, "end": 2058.48, "word": " and", "probability": 0.87353515625 }, { "start": 2058.48, "end": 2058.6, "word": " we", "probability": 0.87744140625 }, { "start": 2058.6, "end": 2058.72, "word": " want", "probability": 0.810546875 } ] }, { "id": 959, "seek": 205822, "start": 2058.72, "end": 2060.62, "text": " to get a count of each", "tokens": [ 50814, 281, 483, 257, 1207, 295, 1184, 50914 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2058.72, "end": 2058.8, "word": " to", "probability": 0.90185546875 }, { "start": 2058.8, "end": 2058.88, "word": " get", "probability": 0.896484375 }, { "start": 2059.04, "end": 2059.42, "word": " a count", "probability": 0.8125 }, { "start": 2059.42, "end": 2060.16, "word": " of", "probability": 0.8974609375 }, { "start": 2060.16, "end": 2060.62, "word": " each", "probability": 0.865234375 } ] }, { "id": 960, "seek": 205822, "start": 2061.46, "end": 2063.54, "text": " unique word per class so", "tokens": [ 50914, 3845, 1349, 680, 1508, 370, 51014 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2061.46, "end": 2061.76, "word": " unique", "probability": 0.783203125 }, { "start": 2061.76, "end": 2062.02, "word": " word", "probability": 0.806640625 }, { "start": 2062.02, "end": 2062.3, "word": " per", "probability": 0.89208984375 }, { "start": 2062.3, "end": 2062.88, "word": " class", "probability": 0.9189453125 }, { "start": 2062.88, "end": 2063.54, "word": " so", "probability": 0.46728515625 } ] }, { "id": 961, "seek": 205822, "start": 2063.54, "end": 2064.76, "text": " that we can use that in", "tokens": [ 51014, 300, 321, 393, 764, 300, 294, 51114 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2063.54, "end": 2063.64, "word": " that", "probability": 0.83642578125 }, { "start": 2063.64, "end": 2063.72, "word": " we", "probability": 0.90380859375 }, { "start": 2063.72, "end": 2063.86, "word": " can", "probability": 0.89404296875 }, { "start": 2063.86, "end": 2064.16, "word": " use", "probability": 0.8173828125 }, { "start": 2064.16, "end": 2064.46, "word": " that", "probability": 0.8828125 }, { "start": 2064.46, "end": 2064.76, "word": " in", "probability": 0.9033203125 } ] }, { "id": 962, "seek": 205822, "start": 2064.76, "end": 2066.14, "text": " our classification. So", "tokens": [ 51114, 527, 21538, 13, 407, 51164 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2064.76, "end": 2065.0, "word": " our", "probability": 0.82080078125 }, { "start": 2065.0, "end": 2065.52, "word": " classification", "probability": 0.8310546875 }, { "start": 2065.52, "end": 2065.88, "word": ".", "probability": 0.96044921875 }, { "start": 2065.98, "end": 2066.14, "word": " So", "probability": 0.77490234375 } ] }, { "id": 963, "seek": 205822, "start": 2066.14, "end": 2066.92, "text": " there's two ways we can", "tokens": [ 51164, 456, 311, 732, 2098, 321, 393, 51214 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2066.14, "end": 2066.42, "word": " there's", "probability": 0.884765625 }, { "start": 2066.42, "end": 2066.54, "word": " two", "probability": 0.7900390625 }, { "start": 2066.54, "end": 2066.7, "word": " ways", "probability": 0.8056640625 }, { "start": 2066.7, "end": 2066.82, "word": " we", "probability": 0.89501953125 }, { "start": 2066.82, "end": 2066.92, "word": " can", "probability": 0.8916015625 } ] }, { "id": 964, "seek": 205822, "start": 2066.92, "end": 2067.76, "text": " do that. We can use the", "tokens": [ 51214, 360, 300, 13, 492, 393, 764, 264, 51264 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2066.92, "end": 2067.02, "word": " do", "probability": 0.9033203125 }, { "start": 2067.02, "end": 2067.16, "word": " that", "probability": 0.88134765625 }, { "start": 2067.16, "end": 2067.18, "word": ".", "probability": 0.8505859375 }, { "start": 2067.18, "end": 2067.28, "word": " We", "probability": 0.9013671875 }, { "start": 2067.28, "end": 2067.38, "word": " can", "probability": 0.89599609375 }, { "start": 2067.38, "end": 2067.58, "word": " use", "probability": 0.802734375 }, { "start": 2067.58, "end": 2067.76, "word": " the", "probability": 0.79833984375 } ] }, { "id": 965, "seek": 205822, "start": 2067.76, "end": 2068.94, "text": " straight count vectorizer,", "tokens": [ 51264, 2997, 1207, 8062, 6545, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2067.76, "end": 2067.96, "word": " straight", "probability": 0.6728515625 }, { "start": 2067.96, "end": 2068.32, "word": " count", "probability": 0.748046875 }, { "start": 2068.32, "end": 2068.88, "word": " vectorizer", "probability": 0.951416015625 }, { "start": 2068.88, "end": 2068.94, "word": ",", "probability": 0.67724609375 } ] }, { "id": 966, "seek": 205822, "start": 2068.94, "end": 2069.9, "text": " which will get the count", "tokens": [ 51314, 597, 486, 483, 264, 1207, 51364 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2068.94, "end": 2069.08, "word": " which", "probability": 0.919921875 }, { "start": 2069.08, "end": 2069.2, "word": " will", "probability": 0.78173828125 }, { "start": 2069.2, "end": 2069.32, "word": " get", "probability": 0.89697265625 }, { "start": 2069.32, "end": 2069.5, "word": " the", "probability": 0.80908203125 }, { "start": 2069.5, "end": 2069.9, "word": " count", "probability": 0.80224609375 } ] }, { "id": 967, "seek": 205822, "start": 2069.9, "end": 2072.56, "text": " of our words, and we can", "tokens": [ 51364, 295, 527, 2283, 11, 293, 321, 393, 51464 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2069.9, "end": 2070.48, "word": " of", "probability": 0.90478515625 }, { "start": 2070.48, "end": 2070.6, "word": " our", "probability": 0.822265625 }, { "start": 2070.6, "end": 2071.88, "word": " words", "probability": 0.3974609375 }, { "start": 2071.88, "end": 2072.24, "word": ",", "probability": 0.421875 }, { "start": 2072.24, "end": 2072.36, "word": " and", "probability": 0.428955078125 }, { "start": 2072.36, "end": 2072.44, "word": " we", "probability": 0.67529296875 }, { "start": 2072.44, "end": 2072.56, "word": " can", "probability": 0.89453125 } ] }, { "id": 968, "seek": 205822, "start": 2072.56, "end": 2074.02, "text": " use a TF-IDF vectorizer,", "tokens": [ 51464, 764, 257, 40964, 12, 2777, 37, 8062, 6545, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2072.56, "end": 2072.72, "word": " use", "probability": 0.81298828125 }, { "start": 2072.84, "end": 2073.1, "word": " a TF", "probability": 0.5712890625 }, { "start": 2073.1, "end": 2073.46, "word": "-IDF", "probability": 0.8580729166666666 }, { "start": 2073.46, "end": 2073.96, "word": " vectorizer", "probability": 0.9404296875 }, { "start": 2073.96, "end": 2074.02, "word": ",", "probability": 0.81689453125 } ] }, { "id": 969, "seek": 205822, "start": 2074.02, "end": 2075.4, "text": " which will give us a", "tokens": [ 51564, 597, 486, 976, 505, 257, 51614 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2074.02, "end": 2074.2, "word": " which", "probability": 0.91650390625 }, { "start": 2074.2, "end": 2074.34, "word": " will", "probability": 0.81640625 }, { "start": 2074.34, "end": 2074.52, "word": " give", "probability": 0.8125 }, { "start": 2074.52, "end": 2074.74, "word": " us", "probability": 0.9091796875 }, { "start": 2075.0, "end": 2075.4, "word": " a weight", "probability": 0.86767578125 } ] }, { "id": 970, "seek": 205822, "start": 2075.4, "end": 2076.92, "text": " weight of each count.", "tokens": [ 51614, 3364, 295, 1184, 1207, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.21875000042574747, "compression_ratio": 1.9216589861751152, "no_speech_prob": 0.0226287841796875, "words": [ { "start": 2075.4, "end": 2075.86, "word": " of", "probability": 0.9033203125 }, { "start": 2075.86, "end": 2076.14, "word": " each", "probability": 0.857421875 }, { "start": 2076.14, "end": 2076.56, "word": " count", "probability": 0.77587890625 }, { "start": 2076.56, "end": 2076.92, "word": ".", "probability": 0.998046875 } ] }, { "id": 971, "seek": 208796, "start": 2079.48, "end": 2081.07, "text": " So no winner says he's", "tokens": [ 50414, 407, 572, 8507, 1619, 415, 311, 50564 ], "temperature": 0.0, "avg_logprob": -0.269457534799036, "compression_ratio": 1.6119402985074627, "no_speech_prob": 0.2420654296875, "words": [ { "start": 2079.48, "end": 2080.06, "word": " So", "probability": 0.306640625 }, { "start": 2080.06, "end": 2080.2, "word": " no", "probability": 0.499267578125 }, { "start": 2080.2, "end": 2080.38, "word": " winner", "probability": 0.409423828125 }, { "start": 2080.38, "end": 2080.78, "word": " says", "probability": 0.78076171875 }, { "start": 2080.78, "end": 2081.07, "word": " he's", "probability": 0.931396484375 } ] }, { "id": 972, "seek": 208796, "start": 2081.82, "end": 2084.32, "text": " behind. He's catching up", "tokens": [ 50564, 2261, 13, 634, 311, 16124, 493, 50714 ], "temperature": 0.0, "avg_logprob": -0.269457534799036, "compression_ratio": 1.6119402985074627, "no_speech_prob": 0.2420654296875, "words": [ { "start": 2081.82, "end": 2082.4, "word": " behind", "probability": 0.50244140625 }, { "start": 2082.4, "end": 2082.98, "word": ".", "probability": 0.26025390625 }, { "start": 2083.52, "end": 2083.8, "word": " He's", "probability": 0.861083984375 }, { "start": 2083.8, "end": 2084.1, "word": " catching", "probability": 0.73974609375 }, { "start": 2084.1, "end": 2084.32, "word": " up", "probability": 0.90771484375 } ] }, { "id": 973, "seek": 208796, "start": 2084.32, "end": 2085.3, "text": " and he'll catch up", "tokens": [ 50714, 293, 415, 603, 3745, 493, 50764 ], "temperature": 0.0, "avg_logprob": -0.269457534799036, "compression_ratio": 1.6119402985074627, "no_speech_prob": 0.2420654296875, "words": [ { "start": 2084.32, "end": 2084.4, "word": " and", "probability": 0.325927734375 }, { "start": 2084.4, "end": 2084.52, "word": " he'll", "probability": 0.815673828125 }, { "start": 2084.52, "end": 2085.18, "word": " catch", "probability": 0.86669921875 }, { "start": 2085.18, "end": 2085.3, "word": " up", "probability": 0.88818359375 } ] }, { "id": 974, "seek": 208796, "start": 2085.3, "end": 2086.76, "text": " later and follow along.", "tokens": [ 50764, 1780, 293, 1524, 2051, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.269457534799036, "compression_ratio": 1.6119402985074627, "no_speech_prob": 0.2420654296875, "words": [ { "start": 2085.3, "end": 2085.48, "word": " later", "probability": 0.80615234375 }, { "start": 2085.48, "end": 2085.6, "word": " and", "probability": 0.1312255859375 }, { "start": 2085.6, "end": 2085.74, "word": " follow", "probability": 0.8349609375 }, { "start": 2085.74, "end": 2086.18, "word": " along", "probability": 0.8955078125 }, { "start": 2086.18, "end": 2086.76, "word": ".", "probability": 0.896484375 } ] }, { "id": 975, "seek": 208796, "start": 2089.5, "end": 2091.44, "text": " I can try to figure out", "tokens": [ 50814, 286, 393, 853, 281, 2573, 484, 51064 ], "temperature": 0.0, "avg_logprob": -0.269457534799036, "compression_ratio": 1.6119402985074627, "no_speech_prob": 0.2420654296875, "words": [ { "start": 2089.5, "end": 2090.08, "word": " I", "probability": 0.459716796875 }, { "start": 2090.08, "end": 2090.66, "word": " can", "probability": 0.8876953125 }, { "start": 2090.66, "end": 2090.82, "word": " try", "probability": 0.77490234375 }, { "start": 2090.82, "end": 2090.94, "word": " to", "probability": 0.6171875 }, { "start": 2090.94, "end": 2091.1, "word": " figure", "probability": 0.908203125 }, { "start": 2091.1, "end": 2091.44, "word": " out", "probability": 0.81640625 } ] }, { "id": 976, "seek": 208796, "start": 2091.76, "end": 2093.8, "text": " a system of helping the", "tokens": [ 51064, 257, 1185, 295, 4315, 264, 51164 ], "temperature": 0.0, "avg_logprob": -0.269457534799036, "compression_ratio": 1.6119402985074627, "no_speech_prob": 0.2420654296875, "words": [ { "start": 2091.76, "end": 2092.1, "word": " a system", "probability": 0.88232421875 }, { "start": 2092.1, "end": 2092.64, "word": " of", "probability": 0.78125 }, { "start": 2092.64, "end": 2092.98, "word": " helping", "probability": 0.7392578125 }, { "start": 2092.98, "end": 2093.8, "word": " the", "probability": 0.6015625 } ] }, { "id": 977, "seek": 208796, "start": 2093.8, "end": 2095.46, "text": " winner. I can send you a", "tokens": [ 51164, 8507, 13, 286, 393, 2845, 291, 257, 51264 ], "temperature": 0.0, "avg_logprob": -0.269457534799036, "compression_ratio": 1.6119402985074627, "no_speech_prob": 0.2420654296875, "words": [ { "start": 2093.8, "end": 2094.04, "word": " winner", "probability": 0.85009765625 }, { "start": 2094.04, "end": 2094.62, "word": ".", "probability": 0.8876953125 }, { "start": 2094.7, "end": 2094.78, "word": " I", "probability": 0.4599609375 }, { "start": 2094.78, "end": 2094.86, "word": " can", "probability": 0.8564453125 }, { "start": 2094.86, "end": 2095.02, "word": " send", "probability": 0.7763671875 }, { "start": 2095.02, "end": 2095.16, "word": " you", "probability": 0.8896484375 }, { "start": 2095.28, "end": 2095.46, "word": " a Zoom", "probability": 0.64697265625 } ] }, { "id": 978, "seek": 208796, "start": 2095.46, "end": 2097.5, "text": " Zoom link or something", "tokens": [ 51264, 13453, 2113, 420, 746, 51314 ], "temperature": 0.0, "avg_logprob": -0.269457534799036, "compression_ratio": 1.6119402985074627, "no_speech_prob": 0.2420654296875, "words": [ { "start": 2095.46, "end": 2095.72, "word": " link", "probability": 0.87548828125 }, { "start": 2095.72, "end": 2096.04, "word": " or", "probability": 0.7861328125 }, { "start": 2096.04, "end": 2096.4, "word": " something", "probability": 0.7373046875 }, { "start": 2096.4, "end": 2097.5, "word": " and", "probability": 0.64892578125 } ] }, { "id": 979, "seek": 208796, "start": 2097.5, "end": 2099.14, "text": " and look over your", "tokens": [ 51314, 293, 574, 670, 428, 51414 ], "temperature": 0.0, "avg_logprob": -0.269457534799036, "compression_ratio": 1.6119402985074627, "no_speech_prob": 0.2420654296875, "words": [ { "start": 2097.5, "end": 2098.56, "word": " look", "probability": 0.7158203125 }, { "start": 2098.56, "end": 2098.68, "word": " over", "probability": 0.86376953125 }, { "start": 2098.68, "end": 2098.84, "word": " your", "probability": 0.8037109375 }, { "start": 2098.84, "end": 2099.14, "word": " shoulder", "probability": 0.79541015625 } ] }, { "id": 980, "seek": 208796, "start": 2099.14, "end": 2101.68, "text": " shoulder metaphorically.", "tokens": [ 51414, 7948, 19157, 984, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.269457534799036, "compression_ratio": 1.6119402985074627, "no_speech_prob": 0.2420654296875, "words": [ { "start": 2099.14, "end": 2100.1, "word": " metaphorically", "probability": 0.716552734375 }, { "start": 2100.1, "end": 2100.68, "word": ".", "probability": 0.96630859375 }, { "start": 2101.1, "end": 2101.68, "word": " Also", "probability": 0.8251953125 } ] }, { "id": 981, "seek": 208796, "start": 2101.68, "end": 2103.06, "text": " Also, in the workbooks,", "tokens": [ 51514, 2743, 11, 294, 264, 589, 15170, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.269457534799036, "compression_ratio": 1.6119402985074627, "no_speech_prob": 0.2420654296875, "words": [ { "start": 2101.68, "end": 2101.9, "word": ",", "probability": 0.312255859375 }, { "start": 2101.9, "end": 2101.96, "word": " in", "probability": 0.90234375 }, { "start": 2101.96, "end": 2102.1, "word": " the", "probability": 0.81298828125 }, { "start": 2102.1, "end": 2102.68, "word": " workbooks", "probability": 0.86083984375 }, { "start": 2102.68, "end": 2102.98, "word": ",", "probability": 0.67236328125 }, { "start": 2102.98, "end": 2103.06, "word": " you", "probability": 0.89453125 } ] }, { "id": 982, "seek": 208796, "start": 2103.06, "end": 2104.98, "text": " you can just open up", "tokens": [ 51614, 291, 393, 445, 1269, 493, 51714 ], "temperature": 0.0, "avg_logprob": -0.269457534799036, "compression_ratio": 1.6119402985074627, "no_speech_prob": 0.2420654296875, "words": [ { "start": 2103.06, "end": 2103.24, "word": " can", "probability": 0.89453125 }, { "start": 2103.24, "end": 2103.58, "word": " just", "probability": 0.86083984375 }, { "start": 2103.58, "end": 2104.14, "word": " open", "probability": 0.8212890625 }, { "start": 2104.14, "end": 2104.38, "word": " up", "probability": 0.91064453125 }, { "start": 2104.38, "end": 2104.98, "word": " the...", "probability": 0.439208984375 } ] }, { "id": 983, "seek": 208796, "start": 2104.98, "end": 2106.0, "text": " the... that's the wrong", "tokens": [ 51714, 264, 485, 300, 311, 264, 2085, 51764 ], "temperature": 0.0, "avg_logprob": -0.269457534799036, "compression_ratio": 1.6119402985074627, "no_speech_prob": 0.2420654296875, "words": [ { "start": 2104.98, "end": 2105.38, "word": " that's", "probability": 0.551055908203125 }, { "start": 2105.38, "end": 2105.5, "word": " the", "probability": 0.81103515625 }, { "start": 2105.5, "end": 2105.66, "word": " wrong", "probability": 0.8271484375 }, { "start": 2105.66, "end": 2106.0, "word": " one...", "probability": 0.50164794921875 } ] }, { "id": 984, "seek": 208796, "start": 2106.0, "end": 2106.66, "text": " one... you can just open", "tokens": [ 51764, 472, 485, 291, 393, 445, 1269, 51814 ], "temperature": 0.0, "avg_logprob": -0.269457534799036, "compression_ratio": 1.6119402985074627, "no_speech_prob": 0.2420654296875, "words": [ { "start": 2106.0, "end": 2106.08, "word": " you", "probability": 0.67236328125 }, { "start": 2106.08, "end": 2106.2, "word": " can", "probability": 0.89208984375 }, { "start": 2106.2, "end": 2106.36, "word": " just", "probability": 0.86181640625 }, { "start": 2106.36, "end": 2106.66, "word": " open", "probability": 0.80517578125 } ] }, { "id": 985, "seek": 211684, "start": 2106.66, "end": 2108.6, "text": " up the completed spam", "tokens": [ 50364, 493, 264, 7365, 24028, 50464 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2106.66, "end": 2106.86, "word": " up", "probability": 0.1572265625 }, { "start": 2106.86, "end": 2107.24, "word": " the", "probability": 0.73681640625 }, { "start": 2107.24, "end": 2108.02, "word": " completed", "probability": 0.71435546875 }, { "start": 2108.02, "end": 2108.6, "word": " spam", "probability": 0.48388671875 } ] }, { "id": 986, "seek": 211684, "start": 2108.6, "end": 2110.64, "text": " filter SK Learn, and", "tokens": [ 50464, 6608, 21483, 17216, 11, 293, 50564 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2108.6, "end": 2108.98, "word": " filter", "probability": 0.89697265625 }, { "start": 2108.98, "end": 2109.38, "word": " SK", "probability": 0.281982421875 }, { "start": 2109.38, "end": 2109.8, "word": " Learn", "probability": 0.1319580078125 }, { "start": 2109.8, "end": 2110.44, "word": ",", "probability": 0.2496337890625 }, { "start": 2110.44, "end": 2110.64, "word": " and", "probability": 0.85546875 } ] }, { "id": 987, "seek": 211684, "start": 2110.64, "end": 2111.68, "text": " it's completely filled out", "tokens": [ 50564, 309, 311, 2584, 6412, 484, 50614 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2110.64, "end": 2110.84, "word": " it's", "probability": 0.932373046875 }, { "start": 2110.84, "end": 2111.2, "word": " completely", "probability": 0.640625 }, { "start": 2111.2, "end": 2111.5, "word": " filled", "probability": 0.82373046875 }, { "start": 2111.5, "end": 2111.68, "word": " out", "probability": 0.81494140625 } ] }, { "id": 988, "seek": 211684, "start": 2111.68, "end": 2113.08, "text": " for you. So if you ever", "tokens": [ 50614, 337, 291, 13, 407, 498, 291, 1562, 50664 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2111.68, "end": 2111.94, "word": " for", "probability": 0.89404296875 }, { "start": 2111.94, "end": 2112.22, "word": " you", "probability": 0.8935546875 }, { "start": 2112.22, "end": 2112.56, "word": ".", "probability": 0.73828125 }, { "start": 2112.56, "end": 2112.66, "word": " So", "probability": 0.66015625 }, { "start": 2112.66, "end": 2112.84, "word": " if", "probability": 0.7333984375 }, { "start": 2112.84, "end": 2112.94, "word": " you", "probability": 0.89404296875 }, { "start": 2112.94, "end": 2113.08, "word": " ever", "probability": 0.80029296875 } ] }, { "id": 989, "seek": 211684, "start": 2113.08, "end": 2113.94, "text": " do fall behind and you", "tokens": [ 50664, 360, 2100, 2261, 293, 291, 50714 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2113.08, "end": 2113.22, "word": " do", "probability": 0.904296875 }, { "start": 2113.22, "end": 2113.4, "word": " fall", "probability": 0.806640625 }, { "start": 2113.4, "end": 2113.74, "word": " behind", "probability": 0.853515625 }, { "start": 2113.74, "end": 2113.86, "word": " and", "probability": 0.78125 }, { "start": 2113.86, "end": 2113.94, "word": " you", "probability": 0.85546875 } ] }, { "id": 990, "seek": 211684, "start": 2113.94, "end": 2114.74, "text": " would like to catch up,", "tokens": [ 50714, 576, 411, 281, 3745, 493, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2113.94, "end": 2114.04, "word": " would", "probability": 0.7802734375 }, { "start": 2114.04, "end": 2114.18, "word": " like", "probability": 0.88330078125 }, { "start": 2114.18, "end": 2114.32, "word": " to", "probability": 0.9052734375 }, { "start": 2114.32, "end": 2114.5, "word": " catch", "probability": 0.82666015625 }, { "start": 2114.5, "end": 2114.68, "word": " up", "probability": 0.91259765625 }, { "start": 2114.68, "end": 2114.74, "word": ",", "probability": 0.80322265625 } ] }, { "id": 991, "seek": 211684, "start": 2114.74, "end": 2115.76, "text": " you can look at the", "tokens": [ 50764, 291, 393, 574, 412, 264, 50814 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2114.74, "end": 2114.82, "word": " you", "probability": 0.8974609375 }, { "start": 2114.82, "end": 2114.94, "word": " can", "probability": 0.896484375 }, { "start": 2114.94, "end": 2115.16, "word": " look", "probability": 0.92138671875 }, { "start": 2115.16, "end": 2115.34, "word": " at", "probability": 0.90478515625 }, { "start": 2115.34, "end": 2115.76, "word": " the", "probability": 0.81005859375 } ] }, { "id": 992, "seek": 211684, "start": 2115.76, "end": 2116.96, "text": " answers there.", "tokens": [ 50814, 6338, 456, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2115.76, "end": 2116.14, "word": " answers", "probability": 0.8212890625 }, { "start": 2116.14, "end": 2116.56, "word": " there", "probability": 0.85595703125 }, { "start": 2116.56, "end": 2116.96, "word": ".", "probability": 0.98876953125 } ] }, { "id": 993, "seek": 211684, "start": 2118.82, "end": 2120.4, "text": " There is a way to", "tokens": [ 50964, 821, 307, 257, 636, 281, 51064 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2118.82, "end": 2119.22, "word": " There", "probability": 0.204833984375 }, { "start": 2119.22, "end": 2119.62, "word": " is", "probability": 0.87744140625 }, { "start": 2119.84, "end": 2120.14, "word": " a way", "probability": 0.89208984375 }, { "start": 2120.14, "end": 2120.4, "word": " to", "probability": 0.90478515625 } ] }, { "id": 994, "seek": 211684, "start": 2120.4, "end": 2121.84, "text": " follow along and make", "tokens": [ 51064, 1524, 2051, 293, 652, 51114 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2120.4, "end": 2121.12, "word": " follow", "probability": 0.87744140625 }, { "start": 2121.12, "end": 2121.54, "word": " along", "probability": 0.8935546875 }, { "start": 2121.54, "end": 2121.66, "word": " and", "probability": 0.84326171875 }, { "start": 2121.66, "end": 2121.84, "word": " make", "probability": 0.87646484375 } ] }, { "id": 995, "seek": 211684, "start": 2121.84, "end": 2123.0, "text": " sure your code works.", "tokens": [ 51114, 988, 428, 3089, 1985, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2121.84, "end": 2122.0, "word": " sure", "probability": 0.8271484375 }, { "start": 2122.0, "end": 2122.16, "word": " your", "probability": 0.80078125 }, { "start": 2122.16, "end": 2122.36, "word": " code", "probability": 0.8515625 }, { "start": 2122.36, "end": 2122.6, "word": " works", "probability": 0.705078125 }, { "start": 2122.6, "end": 2123.0, "word": ".", "probability": 0.92041015625 } ] }, { "id": 996, "seek": 211684, "start": 2123.88, "end": 2125.4, "text": " Yeah, absolutely. And I", "tokens": [ 51214, 865, 11, 3122, 13, 400, 286, 51264 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2123.88, "end": 2124.28, "word": " Yeah", "probability": 0.81884765625 }, { "start": 2124.28, "end": 2124.44, "word": ",", "probability": 0.9072265625 }, { "start": 2124.44, "end": 2124.84, "word": " absolutely", "probability": 0.6982421875 }, { "start": 2124.84, "end": 2125.14, "word": ".", "probability": 0.9091796875 }, { "start": 2125.14, "end": 2125.3, "word": " And", "probability": 0.84130859375 }, { "start": 2125.3, "end": 2125.4, "word": " I", "probability": 0.99658203125 } ] }, { "id": 997, "seek": 211684, "start": 2125.4, "end": 2126.22, "text": " like using the completed", "tokens": [ 51264, 411, 1228, 264, 7365, 51314 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2125.4, "end": 2125.56, "word": " like", "probability": 0.8798828125 }, { "start": 2125.56, "end": 2125.76, "word": " using", "probability": 0.8193359375 }, { "start": 2125.76, "end": 2125.94, "word": " the", "probability": 0.80712890625 }, { "start": 2125.94, "end": 2126.22, "word": " completed", "probability": 0.60791015625 } ] }, { "id": 998, "seek": 211684, "start": 2126.22, "end": 2127.14, "text": " workbook. You can just", "tokens": [ 51314, 589, 2939, 13, 509, 393, 445, 51364 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2126.22, "end": 2126.68, "word": " workbook", "probability": 0.890869140625 }, { "start": 2126.68, "end": 2126.78, "word": ".", "probability": 0.74267578125 }, { "start": 2126.78, "end": 2126.86, "word": " You", "probability": 0.89501953125 }, { "start": 2126.86, "end": 2126.96, "word": " can", "probability": 0.8994140625 }, { "start": 2126.96, "end": 2127.14, "word": " just", "probability": 0.8798828125 } ] }, { "id": 999, "seek": 211684, "start": 2127.14, "end": 2128.26, "text": " run everything and see", "tokens": [ 51364, 1190, 1203, 293, 536, 51414 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2127.14, "end": 2127.4, "word": " run", "probability": 0.91455078125 }, { "start": 2127.4, "end": 2127.82, "word": " everything", "probability": 0.89208984375 }, { "start": 2127.82, "end": 2128.1, "word": " and", "probability": 0.88671875 }, { "start": 2128.1, "end": 2128.26, "word": " see", "probability": 0.80859375 } ] }, { "id": 1000, "seek": 211684, "start": 2128.26, "end": 2129.32, "text": " how things are supposed", "tokens": [ 51414, 577, 721, 366, 3442, 51464 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2128.26, "end": 2128.6, "word": " how", "probability": 0.8994140625 }, { "start": 2128.6, "end": 2129.0, "word": " things", "probability": 0.73095703125 }, { "start": 2129.0, "end": 2129.14, "word": " are", "probability": 0.890625 }, { "start": 2129.14, "end": 2129.32, "word": " supposed", "probability": 0.9140625 } ] }, { "id": 1001, "seek": 211684, "start": 2129.32, "end": 2131.2, "text": " to be at each step of", "tokens": [ 51464, 281, 312, 412, 1184, 1823, 295, 51564 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2129.32, "end": 2129.52, "word": " to", "probability": 0.9072265625 }, { "start": 2129.52, "end": 2129.88, "word": " be", "probability": 0.9013671875 }, { "start": 2129.88, "end": 2130.72, "word": " at", "probability": 0.8291015625 }, { "start": 2130.72, "end": 2130.9, "word": " each", "probability": 0.8642578125 }, { "start": 2130.9, "end": 2131.12, "word": " step", "probability": 0.802734375 }, { "start": 2131.12, "end": 2131.2, "word": " of", "probability": 0.9013671875 } ] }, { "id": 1002, "seek": 211684, "start": 2131.2, "end": 2134.14, "text": " the process. So we're", "tokens": [ 51564, 264, 1399, 13, 407, 321, 434, 51714 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2131.2, "end": 2131.3, "word": " the", "probability": 0.81396484375 }, { "start": 2131.3, "end": 2131.64, "word": " process", "probability": 0.875 }, { "start": 2131.64, "end": 2132.04, "word": ".", "probability": 0.994140625 }, { "start": 2133.54, "end": 2133.94, "word": " So", "probability": 0.85595703125 }, { "start": 2133.94, "end": 2134.14, "word": " we're", "probability": 0.901123046875 } ] }, { "id": 1003, "seek": 211684, "start": 2134.14, "end": 2134.6, "text": " going to go ahead and", "tokens": [ 51714, 516, 281, 352, 2286, 293, 51764 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2134.14, "end": 2134.22, "word": " going", "probability": 0.626953125 }, { "start": 2134.22, "end": 2134.26, "word": " to", "probability": 0.90185546875 }, { "start": 2134.26, "end": 2134.36, "word": " go", "probability": 0.8994140625 }, { "start": 2134.36, "end": 2134.5, "word": " ahead", "probability": 0.8427734375 }, { "start": 2134.5, "end": 2134.6, "word": " and", "probability": 0.89404296875 } ] }, { "id": 1004, "seek": 211684, "start": 2134.6, "end": 2135.54, "text": " train our vectorizers.", "tokens": [ 51764, 3847, 527, 8062, 22525, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.18805017521683598, "compression_ratio": 1.6420664206642066, "no_speech_prob": 0.0182647705078125, "words": [ { "start": 2134.6, "end": 2134.74, "word": " train", "probability": 0.84033203125 }, { "start": 2134.74, "end": 2134.86, "word": " our", "probability": 0.8134765625 }, { "start": 2134.86, "end": 2135.38, "word": " vectorizers", "probability": 0.913330078125 }, { "start": 2135.38, "end": 2135.54, "word": ".", "probability": 0.30078125 } ] }, { "id": 1005, "seek": 214584, "start": 2135.54, "end": 2136.38, "text": " And the instructions tell", "tokens": [ 50364, 400, 264, 9415, 980, 50414 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2135.54, "end": 2135.6, "word": " And", "probability": 0.278564453125 }, { "start": 2135.6, "end": 2135.74, "word": " the", "probability": 0.81689453125 }, { "start": 2135.74, "end": 2136.08, "word": " instructions", "probability": 0.77734375 }, { "start": 2136.08, "end": 2136.38, "word": " tell", "probability": 0.79443359375 } ] }, { "id": 1006, "seek": 214584, "start": 2136.38, "end": 2137.24, "text": " us exactly how to do", "tokens": [ 50414, 505, 2293, 577, 281, 360, 50464 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2136.38, "end": 2136.5, "word": " us", "probability": 0.90380859375 }, { "start": 2136.5, "end": 2136.82, "word": " exactly", "probability": 0.7548828125 }, { "start": 2136.82, "end": 2137.0, "word": " how", "probability": 0.8955078125 }, { "start": 2137.0, "end": 2137.12, "word": " to", "probability": 0.90625 }, { "start": 2137.12, "end": 2137.24, "word": " do", "probability": 0.90625 } ] }, { "id": 1007, "seek": 214584, "start": 2137.24, "end": 2138.34, "text": " this. So we're going to", "tokens": [ 50464, 341, 13, 407, 321, 434, 516, 281, 50514 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2137.24, "end": 2137.5, "word": " this", "probability": 0.8818359375 }, { "start": 2137.5, "end": 2137.62, "word": ".", "probability": 0.970703125 }, { "start": 2137.62, "end": 2137.76, "word": " So", "probability": 0.8740234375 }, { "start": 2137.76, "end": 2137.92, "word": " we're", "probability": 0.889892578125 }, { "start": 2137.92, "end": 2138.14, "word": " going", "probability": 0.8291015625 }, { "start": 2138.14, "end": 2138.34, "word": " to", "probability": 0.9033203125 } ] }, { "id": 1008, "seek": 214584, "start": 2138.34, "end": 2139.52, "text": " use the vectorizer.", "tokens": [ 50514, 764, 264, 8062, 6545, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2138.34, "end": 2138.6, "word": " use", "probability": 0.83056640625 }, { "start": 2138.6, "end": 2138.88, "word": " the", "probability": 0.8095703125 }, { "start": 2138.88, "end": 2139.38, "word": " vectorizer", "probability": 0.9150390625 }, { "start": 2139.38, "end": 2139.52, "word": ".", "probability": 0.57080078125 } ] }, { "id": 1009, "seek": 214584, "start": 2139.52, "end": 2140.06, "text": " We're going to call it", "tokens": [ 50564, 492, 434, 516, 281, 818, 309, 50614 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2139.52, "end": 2139.6, "word": " We're", "probability": 0.92333984375 }, { "start": 2139.6, "end": 2139.62, "word": " going", "probability": 0.32763671875 }, { "start": 2139.62, "end": 2139.72, "word": " to", "probability": 0.90283203125 }, { "start": 2139.72, "end": 2139.92, "word": " call", "probability": 0.81005859375 }, { "start": 2139.92, "end": 2140.06, "word": " it", "probability": 0.90234375 } ] }, { "id": 1010, "seek": 214584, "start": 2140.06, "end": 2141.04, "text": " cvec for the count", "tokens": [ 50614, 269, 303, 66, 337, 264, 1207, 50664 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2140.06, "end": 2140.58, "word": " cvec", "probability": 0.601318359375 }, { "start": 2140.58, "end": 2140.76, "word": " for", "probability": 0.8388671875 }, { "start": 2140.76, "end": 2140.88, "word": " the", "probability": 0.81103515625 }, { "start": 2140.88, "end": 2141.04, "word": " count", "probability": 0.669921875 } ] }, { "id": 1011, "seek": 214584, "start": 2141.04, "end": 2142.68, "text": " vectorizer, tvec for the", "tokens": [ 50664, 8062, 6545, 11, 256, 303, 66, 337, 264, 50714 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2141.04, "end": 2141.58, "word": " vectorizer", "probability": 0.94287109375 }, { "start": 2141.58, "end": 2141.78, "word": ",", "probability": 0.77099609375 }, { "start": 2141.78, "end": 2142.22, "word": " tvec", "probability": 0.9231770833333334 }, { "start": 2142.22, "end": 2142.46, "word": " for", "probability": 0.88134765625 }, { "start": 2142.46, "end": 2142.68, "word": " the", "probability": 0.78955078125 } ] }, { "id": 1012, "seek": 214584, "start": 2142.68, "end": 2144.04, "text": " tfidf vectorizer, and", "tokens": [ 50714, 256, 69, 327, 69, 8062, 6545, 11, 293, 50764 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2142.68, "end": 2143.24, "word": " tfidf", "probability": 0.771484375 }, { "start": 2143.24, "end": 2143.82, "word": " vectorizer", "probability": 0.9501953125 }, { "start": 2143.82, "end": 2143.94, "word": ",", "probability": 0.478271484375 }, { "start": 2143.94, "end": 2144.04, "word": " and", "probability": 0.89501953125 } ] }, { "id": 1013, "seek": 214584, "start": 2144.04, "end": 2144.64, "text": " we're going to perform", "tokens": [ 50764, 321, 434, 516, 281, 2042, 50814 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2144.04, "end": 2144.16, "word": " we're", "probability": 0.930419921875 }, { "start": 2144.16, "end": 2144.22, "word": " going", "probability": 0.65869140625 }, { "start": 2144.22, "end": 2144.3, "word": " to", "probability": 0.90625 }, { "start": 2144.3, "end": 2144.64, "word": " perform", "probability": 0.7548828125 } ] }, { "id": 1014, "seek": 214584, "start": 2144.64, "end": 2147.44, "text": " fit transform. Fit in", "tokens": [ 50814, 3318, 4088, 13, 29263, 294, 50914 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2144.64, "end": 2145.0, "word": " fit", "probability": 0.76318359375 }, { "start": 2145.0, "end": 2145.62, "word": " transform", "probability": 0.80712890625 }, { "start": 2145.62, "end": 2146.02, "word": ".", "probability": 0.96533203125 }, { "start": 2146.78, "end": 2147.18, "word": " Fit", "probability": 0.89111328125 }, { "start": 2147.18, "end": 2147.44, "word": " in", "probability": 0.7919921875 } ] }, { "id": 1015, "seek": 214584, "start": 2147.44, "end": 2148.98, "text": " scikit-learn world is", "tokens": [ 50914, 2180, 22681, 12, 306, 1083, 1002, 307, 51014 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2147.44, "end": 2147.72, "word": " scikit", "probability": 0.6849365234375 }, { "start": 2147.72, "end": 2148.1, "word": "-learn", "probability": 0.8113606770833334 }, { "start": 2148.1, "end": 2148.46, "word": " world", "probability": 0.5107421875 }, { "start": 2148.46, "end": 2148.98, "word": " is", "probability": 0.88916015625 } ] }, { "id": 1016, "seek": 214584, "start": 2149.42, "end": 2151.2, "text": " code for train. So this", "tokens": [ 51014, 3089, 337, 3847, 13, 407, 341, 51114 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2149.42, "end": 2149.82, "word": " code", "probability": 0.474365234375 }, { "start": 2149.82, "end": 2150.04, "word": " for", "probability": 0.89892578125 }, { "start": 2150.04, "end": 2150.44, "word": " train", "probability": 0.74658203125 }, { "start": 2150.44, "end": 2150.84, "word": ".", "probability": 0.9326171875 }, { "start": 2150.88, "end": 2151.06, "word": " So", "probability": 0.87890625 }, { "start": 2151.06, "end": 2151.2, "word": " this", "probability": 0.873046875 } ] }, { "id": 1017, "seek": 214584, "start": 2151.2, "end": 2151.82, "text": " is going to, quote", "tokens": [ 51114, 307, 516, 281, 11, 6513, 51164 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2151.2, "end": 2151.3, "word": " is", "probability": 0.900390625 }, { "start": 2151.3, "end": 2151.38, "word": " going", "probability": 0.77001953125 }, { "start": 2151.38, "end": 2151.64, "word": " to", "probability": 0.90185546875 }, { "start": 2151.64, "end": 2151.78, "word": ",", "probability": 0.1612548828125 }, { "start": 2151.78, "end": 2151.82, "word": " quote", "probability": 0.814453125 } ] }, { "id": 1018, "seek": 214584, "start": 2151.82, "end": 2152.8, "text": " unquote, train our", "tokens": [ 51164, 37557, 11, 3847, 527, 51214 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2151.82, "end": 2151.98, "word": " unquote", "probability": 0.463134765625 }, { "start": 2151.98, "end": 2152.16, "word": ",", "probability": 0.95556640625 }, { "start": 2152.16, "end": 2152.56, "word": " train", "probability": 0.43701171875 }, { "start": 2152.56, "end": 2152.8, "word": " our", "probability": 0.80517578125 } ] }, { "id": 1019, "seek": 214584, "start": 2152.8, "end": 2153.9, "text": " vectorizers so they can", "tokens": [ 51214, 8062, 22525, 370, 436, 393, 51264 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2152.8, "end": 2153.42, "word": " vectorizers", "probability": 0.671142578125 }, { "start": 2153.42, "end": 2153.64, "word": " so", "probability": 0.76123046875 }, { "start": 2153.64, "end": 2153.76, "word": " they", "probability": 0.1739501953125 }, { "start": 2153.76, "end": 2153.9, "word": " can", "probability": 0.8935546875 } ] }, { "id": 1020, "seek": 214584, "start": 2153.9, "end": 2154.74, "text": " get the count of each", "tokens": [ 51264, 483, 264, 1207, 295, 1184, 51314 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2153.9, "end": 2154.04, "word": " get", "probability": 0.89599609375 }, { "start": 2154.04, "end": 2154.18, "word": " the", "probability": 0.814453125 }, { "start": 2154.18, "end": 2154.42, "word": " count", "probability": 0.8134765625 }, { "start": 2154.42, "end": 2154.58, "word": " of", "probability": 0.90283203125 }, { "start": 2154.58, "end": 2154.74, "word": " each", "probability": 0.8662109375 } ] }, { "id": 1021, "seek": 214584, "start": 2154.74, "end": 2155.46, "text": " words. And then we're", "tokens": [ 51314, 2283, 13, 400, 550, 321, 434, 51364 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2154.74, "end": 2155.06, "word": " words", "probability": 0.4111328125 }, { "start": 2155.06, "end": 2155.16, "word": ".", "probability": 0.94384765625 }, { "start": 2155.16, "end": 2155.26, "word": " And", "probability": 0.89892578125 }, { "start": 2155.26, "end": 2155.34, "word": " then", "probability": 0.716796875 }, { "start": 2155.34, "end": 2155.46, "word": " we're", "probability": 0.925537109375 } ] }, { "id": 1022, "seek": 214584, "start": 2155.46, "end": 2155.88, "text": " going to save the", "tokens": [ 51364, 516, 281, 3155, 264, 51414 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2155.46, "end": 2155.52, "word": " going", "probability": 0.8095703125 }, { "start": 2155.52, "end": 2155.58, "word": " to", "probability": 0.90283203125 }, { "start": 2155.58, "end": 2155.76, "word": " save", "probability": 0.86669921875 }, { "start": 2155.76, "end": 2155.88, "word": " the", "probability": 0.81005859375 } ] }, { "id": 1023, "seek": 214584, "start": 2155.88, "end": 2157.84, "text": " results as count x and", "tokens": [ 51414, 3542, 382, 1207, 2031, 293, 51464 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2155.88, "end": 2156.2, "word": " results", "probability": 0.67626953125 }, { "start": 2156.2, "end": 2156.38, "word": " as", "probability": 0.87060546875 }, { "start": 2156.38, "end": 2156.78, "word": " count", "probability": 0.67822265625 }, { "start": 2156.78, "end": 2157.54, "word": " x", "probability": 0.3994140625 }, { "start": 2157.54, "end": 2157.84, "word": " and", "probability": 0.8515625 } ] }, { "id": 1024, "seek": 214584, "start": 2158.26, "end": 2160.94, "text": " tfidf x. So what that", "tokens": [ 51464, 256, 69, 327, 69, 2031, 13, 407, 437, 300, 51614 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2158.26, "end": 2158.66, "word": " tfidf", "probability": 0.976318359375 }, { "start": 2158.66, "end": 2159.06, "word": " x", "probability": 0.876953125 }, { "start": 2159.06, "end": 2159.46, "word": ".", "probability": 0.99267578125 }, { "start": 2160.4, "end": 2160.74, "word": " So", "probability": 0.8935546875 }, { "start": 2160.74, "end": 2160.84, "word": " what", "probability": 0.8095703125 }, { "start": 2160.84, "end": 2160.94, "word": " that", "probability": 0.884765625 } ] }, { "id": 1025, "seek": 214584, "start": 2160.94, "end": 2162.54, "text": " looks like is cvec", "tokens": [ 51614, 1542, 411, 307, 269, 303, 66, 51714 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2160.94, "end": 2161.08, "word": " looks", "probability": 0.79248046875 }, { "start": 2161.08, "end": 2161.26, "word": " like", "probability": 0.8759765625 }, { "start": 2161.26, "end": 2161.52, "word": " is", "probability": 0.89453125 }, { "start": 2161.52, "end": 2162.54, "word": " cvec", "probability": 0.9334309895833334 } ] }, { "id": 1026, "seek": 214584, "start": 2163.74, "end": 2164.54, "text": " equals count", "tokens": [ 51714, 6915, 1207, 51814 ], "temperature": 0.0, "avg_logprob": -0.21135354394743427, "compression_ratio": 1.9068825910931173, "no_speech_prob": 0.009857177734375, "words": [ { "start": 2163.74, "end": 2164.14, "word": " equals", "probability": 0.7041015625 }, { "start": 2164.14, "end": 2164.54, "word": " count", "probability": 0.74365234375 } ] }, { "id": 1027, "seek": 217582, "start": 2165.26, "end": 2166.38, "text": " vectorizer. And then we", "tokens": [ 50364, 8062, 6545, 13, 400, 550, 321, 50414 ], "temperature": 0.0, "avg_logprob": -0.19885254034306854, "compression_ratio": 1.775, "no_speech_prob": 0.0006461143493652344, "words": [ { "start": 2165.26, "end": 2165.76, "word": " vectorizer", "probability": 0.6048583984375 }, { "start": 2165.76, "end": 2166.16, "word": ".", "probability": 0.2283935546875 }, { "start": 2166.16, "end": 2166.2, "word": " And", "probability": 0.64501953125 }, { "start": 2166.2, "end": 2166.28, "word": " then", "probability": 0.72509765625 }, { "start": 2166.28, "end": 2166.38, "word": " we", "probability": 0.8857421875 } ] }, { "id": 1028, "seek": 217582, "start": 2166.38, "end": 2167.4, "text": " want to use our", "tokens": [ 50414, 528, 281, 764, 527, 50464 ], "temperature": 0.0, "avg_logprob": -0.19885254034306854, "compression_ratio": 1.775, "no_speech_prob": 0.0006461143493652344, "words": [ { "start": 2166.38, "end": 2166.56, "word": " want", "probability": 0.810546875 }, { "start": 2166.56, "end": 2166.68, "word": " to", "probability": 0.90673828125 }, { "start": 2166.68, "end": 2166.94, "word": " use", "probability": 0.83740234375 }, { "start": 2166.94, "end": 2167.4, "word": " our", "probability": 0.8134765625 } ] }, { "id": 1029, "seek": 217582, "start": 2167.4, "end": 2168.3, "text": " tokenizer that we", "tokens": [ 50464, 14862, 6545, 300, 321, 50514 ], "temperature": 0.0, "avg_logprob": -0.19885254034306854, "compression_ratio": 1.775, "no_speech_prob": 0.0006461143493652344, "words": [ { "start": 2167.4, "end": 2168.0, "word": " tokenizer", "probability": 0.859375 }, { "start": 2168.0, "end": 2168.2, "word": " that", "probability": 0.85791015625 }, { "start": 2168.2, "end": 2168.3, "word": " we", "probability": 0.90625 } ] }, { "id": 1030, "seek": 217582, "start": 2168.3, "end": 2170.58, "text": " defined above. So the", "tokens": [ 50514, 7642, 3673, 13, 407, 264, 50614 ], "temperature": 0.0, "avg_logprob": -0.19885254034306854, "compression_ratio": 1.775, "no_speech_prob": 0.0006461143493652344, "words": [ { "start": 2168.3, "end": 2168.76, "word": " defined", "probability": 0.72216796875 }, { "start": 2168.76, "end": 2169.32, "word": " above", "probability": 0.888671875 }, { "start": 2169.32, "end": 2169.56, "word": ".", "probability": 0.8037109375 }, { "start": 2169.56, "end": 2169.7, "word": " So", "probability": 0.74951171875 }, { "start": 2169.7, "end": 2170.58, "word": " the", "probability": 0.658203125 } ] }, { "id": 1031, "seek": 217582, "start": 2170.58, "end": 2171.86, "text": " tokenizer that we're", "tokens": [ 50614, 14862, 6545, 300, 321, 434, 50714 ], "temperature": 0.0, "avg_logprob": -0.19885254034306854, "compression_ratio": 1.775, "no_speech_prob": 0.0006461143493652344, "words": [ { "start": 2170.58, "end": 2171.4, "word": " tokenizer", "probability": 0.89306640625 }, { "start": 2171.4, "end": 2171.74, "word": " that", "probability": 0.8701171875 }, { "start": 2171.74, "end": 2171.86, "word": " we're", "probability": 0.928466796875 } ] }, { "id": 1032, "seek": 217582, "start": 2171.86, "end": 2172.92, "text": " going to use is called", "tokens": [ 50714, 516, 281, 764, 307, 1219, 50764 ], "temperature": 0.0, "avg_logprob": -0.19885254034306854, "compression_ratio": 1.775, "no_speech_prob": 0.0006461143493652344, "words": [ { "start": 2171.86, "end": 2171.94, "word": " going", "probability": 0.73193359375 }, { "start": 2171.94, "end": 2172.02, "word": " to", "probability": 0.90869140625 }, { "start": 2172.02, "end": 2172.28, "word": " use", "probability": 0.82470703125 }, { "start": 2172.28, "end": 2172.5, "word": " is", "probability": 0.8984375 }, { "start": 2172.5, "end": 2172.92, "word": " called", "probability": 0.7939453125 } ] }, { "id": 1033, "seek": 217582, "start": 2173.72, "end": 2175.1, "text": " tokenizer. I know, not", "tokens": [ 50764, 14862, 6545, 13, 286, 458, 11, 406, 50864 ], "temperature": 0.0, "avg_logprob": -0.19885254034306854, "compression_ratio": 1.775, "no_speech_prob": 0.0006461143493652344, "words": [ { "start": 2173.72, "end": 2174.22, "word": " tokenizer", "probability": 0.7059326171875 }, { "start": 2174.22, "end": 2174.54, "word": ".", "probability": 0.84375 }, { "start": 2174.54, "end": 2174.6, "word": " I", "probability": 0.853515625 }, { "start": 2174.6, "end": 2174.76, "word": " know", "probability": 0.82080078125 }, { "start": 2174.76, "end": 2174.82, "word": ",", "probability": 0.5615234375 }, { "start": 2174.82, "end": 2175.1, "word": " not", "probability": 0.8896484375 } ] }, { "id": 1034, "seek": 217582, "start": 2175.1, "end": 2176.96, "text": " confusing at all. But", "tokens": [ 50864, 13181, 412, 439, 13, 583, 50964 ], "temperature": 0.0, "avg_logprob": -0.19885254034306854, "compression_ratio": 1.775, "no_speech_prob": 0.0006461143493652344, "words": [ { "start": 2175.1, "end": 2175.62, "word": " confusing", "probability": 0.92431640625 }, { "start": 2175.62, "end": 2176.08, "word": " at", "probability": 0.8994140625 }, { "start": 2176.08, "end": 2176.38, "word": " all", "probability": 0.900390625 }, { "start": 2176.38, "end": 2176.74, "word": ".", "probability": 0.494140625 }, { "start": 2176.74, "end": 2176.96, "word": " But", "probability": 0.662109375 } ] }, { "id": 1035, "seek": 217582, "start": 2178.36, "end": 2179.44, "text": " we're going to use our", "tokens": [ 50964, 321, 434, 516, 281, 764, 527, 51064 ], "temperature": 0.0, "avg_logprob": -0.19885254034306854, "compression_ratio": 1.775, "no_speech_prob": 0.0006461143493652344, "words": [ { "start": 2178.36, "end": 2178.86, "word": " we're", "probability": 0.733154296875 }, { "start": 2178.86, "end": 2178.86, "word": " going", "probability": 0.49267578125 }, { "start": 2178.86, "end": 2178.86, "word": " to", "probability": 0.90380859375 }, { "start": 2178.86, "end": 2179.0, "word": " use", "probability": 0.85009765625 }, { "start": 2179.0, "end": 2179.44, "word": " our", "probability": 0.7998046875 } ] }, { "id": 1036, "seek": 217582, "start": 2181.92, "end": 2183.34, "text": " count x. And pay", "tokens": [ 51064, 1207, 2031, 13, 400, 1689, 51264 ], "temperature": 0.0, "avg_logprob": -0.19885254034306854, "compression_ratio": 1.775, "no_speech_prob": 0.0006461143493652344, "words": [ { "start": 2181.92, "end": 2182.42, "word": " count", "probability": 0.53125 }, { "start": 2182.42, "end": 2182.92, "word": " x", "probability": 0.23193359375 }, { "start": 2182.92, "end": 2183.14, "word": ".", "probability": 0.489990234375 }, { "start": 2183.14, "end": 2183.2, "word": " And", "probability": 0.8291015625 }, { "start": 2183.2, "end": 2183.34, "word": " pay", "probability": 0.87841796875 } ] }, { "id": 1037, "seek": 217582, "start": 2183.34, "end": 2183.88, "text": " attention to your", "tokens": [ 51264, 3202, 281, 428, 51314 ], "temperature": 0.0, "avg_logprob": -0.19885254034306854, "compression_ratio": 1.775, "no_speech_prob": 0.0006461143493652344, "words": [ { "start": 2183.34, "end": 2183.58, "word": " attention", "probability": 0.859375 }, { "start": 2183.58, "end": 2183.72, "word": " to", "probability": 0.90185546875 }, { "start": 2183.72, "end": 2183.88, "word": " your", "probability": 0.818359375 } ] }, { "id": 1038, "seek": 217582, "start": 2183.88, "end": 2185.38, "text": " capitals. Scikit-learn", "tokens": [ 51314, 1410, 11118, 13, 16942, 22681, 12, 306, 1083, 51364 ], "temperature": 0.0, "avg_logprob": -0.19885254034306854, "compression_ratio": 1.775, "no_speech_prob": 0.0006461143493652344, "words": [ { "start": 2183.88, "end": 2184.52, "word": " capitals", "probability": 0.92138671875 }, { "start": 2184.52, "end": 2185.02, "word": ".", "probability": 0.708984375 }, { "start": 2185.04, "end": 2185.2, "word": " Scikit", "probability": 0.7127685546875 }, { "start": 2185.2, "end": 2185.38, "word": "-learn", "probability": 0.9109700520833334 } ] }, { "id": 1039, "seek": 217582, "start": 2185.38, "end": 2187.06, "text": " is very picky and so is", "tokens": [ 51364, 307, 588, 41099, 293, 370, 307, 51464 ], "temperature": 0.0, "avg_logprob": -0.19885254034306854, "compression_ratio": 1.775, "no_speech_prob": 0.0006461143493652344, "words": [ { "start": 2185.38, "end": 2185.54, "word": " is", "probability": 0.89892578125 }, { "start": 2185.54, "end": 2185.72, "word": " very", "probability": 0.748046875 }, { "start": 2185.72, "end": 2186.02, "word": " picky", "probability": 0.74267578125 }, { "start": 2186.02, "end": 2186.46, "word": " and", "probability": 0.62890625 }, { "start": 2186.46, "end": 2186.8, "word": " so", "probability": 0.9013671875 }, { "start": 2186.8, "end": 2187.06, "word": " is", "probability": 0.90625 } ] }, { "id": 1040, "seek": 217582, "start": 2187.06, "end": 2188.88, "text": " my workbook. We're going", "tokens": [ 51464, 452, 589, 2939, 13, 492, 434, 516, 51564 ], "temperature": 0.0, "avg_logprob": -0.19885254034306854, "compression_ratio": 1.775, "no_speech_prob": 0.0006461143493652344, "words": [ { "start": 2187.06, "end": 2187.22, "word": " my", "probability": 0.90380859375 }, { "start": 2187.22, "end": 2187.7, "word": " workbook", "probability": 0.889404296875 }, { "start": 2187.7, "end": 2188.2, "word": ".", "probability": 0.98388671875 }, { "start": 2188.5, "end": 2188.8, "word": " We're", "probability": 0.9189453125 }, { "start": 2188.8, "end": 2188.88, "word": " going", "probability": 0.8056640625 } ] }, { "id": 1041, "seek": 217582, "start": 2188.88, "end": 2190.71, "text": " to use cvec.fit", "tokens": [ 51564, 281, 764, 269, 303, 66, 13, 6845, 51664 ], "temperature": 0.0, "avg_logprob": -0.19885254034306854, "compression_ratio": 1.775, "no_speech_prob": 0.0006461143493652344, "words": [ { "start": 2188.88, "end": 2188.92, "word": " to", "probability": 0.90185546875 }, { "start": 2188.92, "end": 2189.1, "word": " use", "probability": 0.814453125 }, { "start": 2189.1, "end": 2190.46, "word": " cvec", "probability": 0.4545338948567708 }, { "start": 2190.46, "end": 2190.71, "word": ".fit", "probability": 0.810791015625 } ] }, { "id": 1042, "seek": 217582, "start": 2192.38, "end": 2193.66, "text": " transform. And then", "tokens": [ 51664, 4088, 13, 400, 550, 51764 ], "temperature": 0.0, "avg_logprob": -0.19885254034306854, "compression_ratio": 1.775, "no_speech_prob": 0.0006461143493652344, "words": [ { "start": 2192.38, "end": 2192.88, "word": " transform", "probability": 0.2032470703125 }, { "start": 2192.88, "end": 2193.26, "word": ".", "probability": 0.27587890625 }, { "start": 2193.26, "end": 2193.5, "word": " And", "probability": 0.87939453125 }, { "start": 2193.5, "end": 2193.66, "word": " then", "probability": 0.7216796875 } ] }, { "id": 1043, "seek": 217582, "start": 2193.66, "end": 2194.52, "text": " we're going to train", "tokens": [ 51764, 321, 434, 516, 281, 3847, 51814 ], "temperature": 0.0, "avg_logprob": -0.19885254034306854, "compression_ratio": 1.775, "no_speech_prob": 0.0006461143493652344, "words": [ { "start": 2193.66, "end": 2193.84, "word": " we're", "probability": 0.93017578125 }, { "start": 2193.84, "end": 2194.02, "word": " going", "probability": 0.8564453125 }, { "start": 2194.02, "end": 2194.34, "word": " to", "probability": 0.90673828125 }, { "start": 2194.34, "end": 2194.52, "word": " train", "probability": 0.061279296875 } ] }, { "id": 1044, "seek": 220580, "start": 2194.52, "end": 2196.34, "text": " transform or count the", "tokens": [ 50364, 4088, 420, 1207, 264, 50464 ], "temperature": 0.0, "avg_logprob": -0.16763771110672063, "compression_ratio": 1.8375, "no_speech_prob": 0.384765625, "words": [ { "start": 2194.52, "end": 2194.98, "word": " transform", "probability": 0.53857421875 }, { "start": 2194.98, "end": 2195.66, "word": " or", "probability": 0.69921875 }, { "start": 2195.66, "end": 2196.1, "word": " count", "probability": 0.7666015625 }, { "start": 2196.1, "end": 2196.34, "word": " the", "probability": 0.7919921875 } ] }, { "id": 1045, "seek": 220580, "start": 2196.34, "end": 2199.4, "text": " words for our corpus.", "tokens": [ 50464, 2283, 337, 527, 1181, 31624, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.16763771110672063, "compression_ratio": 1.8375, "no_speech_prob": 0.384765625, "words": [ { "start": 2196.34, "end": 2196.82, "word": " words", "probability": 0.7236328125 }, { "start": 2196.82, "end": 2197.6, "word": " for", "probability": 0.88134765625 }, { "start": 2197.6, "end": 2197.96, "word": " our", "probability": 0.8173828125 }, { "start": 2197.96, "end": 2198.68, "word": " corpus", "probability": 0.8896484375 }, { "start": 2198.68, "end": 2199.4, "word": ".", "probability": 0.90380859375 } ] }, { "id": 1046, "seek": 220580, "start": 2200.16, "end": 2200.6, "text": " And then we're going", "tokens": [ 50564, 400, 550, 321, 434, 516, 50664 ], "temperature": 0.0, "avg_logprob": -0.16763771110672063, "compression_ratio": 1.8375, "no_speech_prob": 0.384765625, "words": [ { "start": 2200.16, "end": 2200.36, "word": " And", "probability": 0.8388671875 }, { "start": 2200.36, "end": 2200.42, "word": " then", "probability": 0.72119140625 }, { "start": 2200.42, "end": 2200.58, "word": " we're", "probability": 0.9013671875 }, { "start": 2200.58, "end": 2200.6, "word": " going", "probability": 0.2183837890625 } ] }, { "id": 1047, "seek": 220580, "start": 2200.6, "end": 2201.28, "text": " to do the same thing", "tokens": [ 50664, 281, 360, 264, 912, 551, 50714 ], "temperature": 0.0, "avg_logprob": -0.16763771110672063, "compression_ratio": 1.8375, "no_speech_prob": 0.384765625, "words": [ { "start": 2200.6, "end": 2200.66, "word": " to", "probability": 0.90234375 }, { "start": 2200.66, "end": 2200.76, "word": " do", "probability": 0.9033203125 }, { "start": 2200.76, "end": 2200.92, "word": " the", "probability": 0.81103515625 }, { "start": 2200.92, "end": 2201.08, "word": " same", "probability": 0.81005859375 }, { "start": 2201.08, "end": 2201.28, "word": " thing", "probability": 0.81689453125 } ] }, { "id": 1048, "seek": 220580, "start": 2201.28, "end": 2202.22, "text": " with our tfidf", "tokens": [ 50714, 365, 527, 256, 69, 327, 69, 50764 ], "temperature": 0.0, "avg_logprob": -0.16763771110672063, "compression_ratio": 1.8375, "no_speech_prob": 0.384765625, "words": [ { "start": 2201.28, "end": 2201.4, "word": " with", "probability": 0.80615234375 }, { "start": 2201.4, "end": 2201.56, "word": " our", "probability": 0.802734375 }, { "start": 2201.56, "end": 2202.22, "word": " tfidf", "probability": 0.7149658203125 } ] }, { "id": 1049, "seek": 220580, "start": 2202.22, "end": 2204.54, "text": " vectorizer. tvec", "tokens": [ 50764, 8062, 6545, 13, 256, 303, 66, 50864 ], "temperature": 0.0, "avg_logprob": -0.16763771110672063, "compression_ratio": 1.8375, "no_speech_prob": 0.384765625, "words": [ { "start": 2202.22, "end": 2202.9, "word": " vectorizer", "probability": 0.835205078125 }, { "start": 2202.9, "end": 2203.62, "word": ".", "probability": 0.482666015625 }, { "start": 2203.82, "end": 2204.54, "word": " tvec", "probability": 0.7685546875 } ] }, { "id": 1050, "seek": 220580, "start": 2204.54, "end": 2206.6, "text": " equals tfidf", "tokens": [ 50864, 6915, 256, 69, 327, 69, 50964 ], "temperature": 0.0, "avg_logprob": -0.16763771110672063, "compression_ratio": 1.8375, "no_speech_prob": 0.384765625, "words": [ { "start": 2204.54, "end": 2205.18, "word": " equals", "probability": 0.587890625 }, { "start": 2205.18, "end": 2206.6, "word": " tfidf", "probability": 0.971435546875 } ] }, { "id": 1051, "seek": 220580, "start": 2206.6, "end": 2208.36, "text": " vectorizer. And we're", "tokens": [ 50964, 8062, 6545, 13, 400, 321, 434, 51064 ], "temperature": 0.0, "avg_logprob": -0.16763771110672063, "compression_ratio": 1.8375, "no_speech_prob": 0.384765625, "words": [ { "start": 2206.6, "end": 2207.86, "word": " vectorizer", "probability": 0.87451171875 }, { "start": 2207.86, "end": 2208.1, "word": ".", "probability": 0.3798828125 }, { "start": 2208.1, "end": 2208.22, "word": " And", "probability": 0.8447265625 }, { "start": 2208.22, "end": 2208.36, "word": " we're", "probability": 0.9189453125 } ] }, { "id": 1052, "seek": 220580, "start": 2208.36, "end": 2209.18, "text": " going to use our", "tokens": [ 51064, 516, 281, 764, 527, 51114 ], "temperature": 0.0, "avg_logprob": -0.16763771110672063, "compression_ratio": 1.8375, "no_speech_prob": 0.384765625, "words": [ { "start": 2208.36, "end": 2208.48, "word": " going", "probability": 0.6494140625 }, { "start": 2208.48, "end": 2208.48, "word": " to", "probability": 0.91015625 }, { "start": 2208.48, "end": 2208.7, "word": " use", "probability": 0.85498046875 }, { "start": 2208.7, "end": 2209.18, "word": " our", "probability": 0.79443359375 } ] }, { "id": 1053, "seek": 220580, "start": 2209.18, "end": 2210.72, "text": " tokenizer called", "tokens": [ 51114, 14862, 6545, 1219, 51164 ], "temperature": 0.0, "avg_logprob": -0.16763771110672063, "compression_ratio": 1.8375, "no_speech_prob": 0.384765625, "words": [ { "start": 2209.18, "end": 2210.18, "word": " tokenizer", "probability": 0.867919921875 }, { "start": 2210.18, "end": 2210.72, "word": " called", "probability": 0.76416015625 } ] }, { "id": 1054, "seek": 220580, "start": 2210.72, "end": 2212.82, "text": " tokenizer. And then", "tokens": [ 51164, 14862, 6545, 13, 400, 550, 51264 ], "temperature": 0.0, "avg_logprob": -0.16763771110672063, "compression_ratio": 1.8375, "no_speech_prob": 0.384765625, "words": [ { "start": 2210.72, "end": 2211.6, "word": " tokenizer", "probability": 0.858154296875 }, { "start": 2211.6, "end": 2212.22, "word": ".", "probability": 0.685546875 }, { "start": 2212.22, "end": 2212.58, "word": " And", "probability": 0.89599609375 }, { "start": 2212.58, "end": 2212.82, "word": " then", "probability": 0.74072265625 } ] }, { "id": 1055, "seek": 220580, "start": 2212.82, "end": 2214.68, "text": " our tfidf x", "tokens": [ 51264, 527, 256, 69, 327, 69, 2031, 51364 ], "temperature": 0.0, "avg_logprob": -0.16763771110672063, "compression_ratio": 1.8375, "no_speech_prob": 0.384765625, "words": [ { "start": 2212.82, "end": 2213.16, "word": " our", "probability": 0.7978515625 }, { "start": 2213.16, "end": 2214.2, "word": " tfidf", "probability": 0.97509765625 }, { "start": 2214.2, "end": 2214.68, "word": " x", "probability": 0.185546875 } ] }, { "id": 1056, "seek": 220580, "start": 2214.68, "end": 2219.22, "text": " equals tvec.fit", "tokens": [ 51364, 6915, 256, 303, 66, 13, 6845, 51614 ], "temperature": 0.0, "avg_logprob": -0.16763771110672063, "compression_ratio": 1.8375, "no_speech_prob": 0.384765625, "words": [ { "start": 2214.68, "end": 2215.48, "word": " equals", "probability": 0.85009765625 }, { "start": 2215.48, "end": 2217.96, "word": " tvec", "probability": 0.9615885416666666 }, { "start": 2217.96, "end": 2219.22, "word": ".fit", "probability": 0.86669921875 } ] }, { "id": 1057, "seek": 220580, "start": 2219.22, "end": 2222.02, "text": " transform. And it's", "tokens": [ 51614, 4088, 13, 400, 309, 311, 51714 ], "temperature": 0.0, "avg_logprob": -0.16763771110672063, "compression_ratio": 1.8375, "no_speech_prob": 0.384765625, "words": [ { "start": 2219.22, "end": 2220.5, "word": " transform", "probability": 0.433349609375 }, { "start": 2220.5, "end": 2221.08, "word": ".", "probability": 0.5673828125 }, { "start": 2221.08, "end": 2221.76, "word": " And", "probability": 0.8896484375 }, { "start": 2221.76, "end": 2222.02, "word": " it's", "probability": 0.95166015625 } ] }, { "id": 1058, "seek": 220580, "start": 2222.02, "end": 2222.86, "text": " also going to be on", "tokens": [ 51714, 611, 516, 281, 312, 322, 51764 ], "temperature": 0.0, "avg_logprob": -0.16763771110672063, "compression_ratio": 1.8375, "no_speech_prob": 0.384765625, "words": [ { "start": 2222.02, "end": 2222.24, "word": " also", "probability": 0.82763671875 }, { "start": 2222.24, "end": 2222.42, "word": " going", "probability": 0.72021484375 }, { "start": 2222.42, "end": 2222.44, "word": " to", "probability": 0.9013671875 }, { "start": 2222.44, "end": 2222.62, "word": " be", "probability": 0.904296875 }, { "start": 2222.62, "end": 2222.86, "word": " on", "probability": 0.9052734375 } ] }, { "id": 1059, "seek": 220580, "start": 2222.86, "end": 2224.5, "text": " our corpus. So I'm", "tokens": [ 51764, 527, 1181, 31624, 13, 407, 286, 478, 51814 ], "temperature": 0.0, "avg_logprob": -0.16763771110672063, "compression_ratio": 1.8375, "no_speech_prob": 0.384765625, "words": [ { "start": 2222.86, "end": 2223.02, "word": " our", "probability": 0.81298828125 }, { "start": 2223.02, "end": 2223.5, "word": " corpus", "probability": 0.916259765625 }, { "start": 2223.5, "end": 2224.16, "word": ".", "probability": 0.99072265625 }, { "start": 2224.16, "end": 2224.32, "word": " So", "probability": 0.8984375 }, { "start": 2224.32, "end": 2224.5, "word": " I'm", "probability": 0.747802734375 } ] }, { "id": 1060, "seek": 223540, "start": 2224.5, "end": 2225.16, "text": " going to let this sit", "tokens": [ 50364, 516, 281, 718, 341, 1394, 50414 ], "temperature": 0.0, "avg_logprob": -0.18055555453667274, "compression_ratio": 1.7427184466019416, "no_speech_prob": 0.1666259765625, "words": [ { "start": 2224.5, "end": 2224.58, "word": " going", "probability": 0.03717041015625 }, { "start": 2224.58, "end": 2224.62, "word": " to", "probability": 0.89404296875 }, { "start": 2224.62, "end": 2224.76, "word": " let", "probability": 0.84912109375 }, { "start": 2224.76, "end": 2224.94, "word": " this", "probability": 0.85693359375 }, { "start": 2224.94, "end": 2225.16, "word": " sit", "probability": 0.90576171875 } ] }, { "id": 1061, "seek": 223540, "start": 2225.16, "end": 2227.24, "text": " for a minute and let", "tokens": [ 50414, 337, 257, 3456, 293, 718, 50464 ], "temperature": 0.0, "avg_logprob": -0.18055555453667274, "compression_ratio": 1.7427184466019416, "no_speech_prob": 0.1666259765625, "words": [ { "start": 2225.16, "end": 2225.34, "word": " for", "probability": 0.89306640625 }, { "start": 2225.46, "end": 2225.64, "word": " a minute", "probability": 0.89404296875 }, { "start": 2225.64, "end": 2227.12, "word": " and", "probability": 0.191650390625 }, { "start": 2227.12, "end": 2227.24, "word": " let", "probability": 0.88671875 } ] }, { "id": 1062, "seek": 223540, "start": 2227.24, "end": 2228.12, "text": " you guys be able to", "tokens": [ 50464, 291, 1074, 312, 1075, 281, 50514 ], "temperature": 0.0, "avg_logprob": -0.18055555453667274, "compression_ratio": 1.7427184466019416, "no_speech_prob": 0.1666259765625, "words": [ { "start": 2227.24, "end": 2227.36, "word": " you", "probability": 0.89599609375 }, { "start": 2227.36, "end": 2227.6, "word": " guys", "probability": 0.85791015625 }, { "start": 2227.6, "end": 2227.86, "word": " be", "probability": 0.87255859375 }, { "start": 2227.86, "end": 2227.98, "word": " able", "probability": 0.87060546875 }, { "start": 2227.98, "end": 2228.12, "word": " to", "probability": 0.9033203125 } ] }, { "id": 1063, "seek": 223540, "start": 2228.12, "end": 2233.06, "text": " catch up. And this", "tokens": [ 50514, 3745, 493, 13, 400, 341, 50764 ], "temperature": 0.0, "avg_logprob": -0.18055555453667274, "compression_ratio": 1.7427184466019416, "no_speech_prob": 0.1666259765625, "words": [ { "start": 2228.12, "end": 2228.38, "word": " catch", "probability": 0.8212890625 }, { "start": 2228.38, "end": 2228.66, "word": " up", "probability": 0.8974609375 }, { "start": 2228.66, "end": 2229.1, "word": ".", "probability": 0.8408203125 }, { "start": 2232.72, "end": 2232.92, "word": " And", "probability": 0.61279296875 }, { "start": 2232.92, "end": 2233.06, "word": " this", "probability": 0.875 } ] }, { "id": 1064, "seek": 223540, "start": 2233.06, "end": 2233.82, "text": " takes a little bit.", "tokens": [ 50764, 2516, 257, 707, 857, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.18055555453667274, "compression_ratio": 1.7427184466019416, "no_speech_prob": 0.1666259765625, "words": [ { "start": 2233.06, "end": 2233.3, "word": " takes", "probability": 0.7568359375 }, { "start": 2233.46, "end": 2233.58, "word": " a little", "probability": 0.80029296875 }, { "start": 2233.58, "end": 2233.74, "word": " bit", "probability": 0.88916015625 }, { "start": 2233.74, "end": 2233.82, "word": ".", "probability": 0.5458984375 } ] }, { "id": 1065, "seek": 223540, "start": 2233.82, "end": 2235.8, "text": " This takes about two", "tokens": [ 50814, 639, 2516, 466, 732, 50914 ], "temperature": 0.0, "avg_logprob": -0.18055555453667274, "compression_ratio": 1.7427184466019416, "no_speech_prob": 0.1666259765625, "words": [ { "start": 2233.82, "end": 2233.92, "word": " This", "probability": 0.79248046875 }, { "start": 2233.92, "end": 2234.18, "word": " takes", "probability": 0.75537109375 }, { "start": 2234.18, "end": 2234.6, "word": " about", "probability": 0.81982421875 }, { "start": 2234.6, "end": 2235.8, "word": " two", "probability": 0.66064453125 } ] }, { "id": 1066, "seek": 223540, "start": 2235.8, "end": 2237.84, "text": " minutes to run because", "tokens": [ 50914, 2077, 281, 1190, 570, 51014 ], "temperature": 0.0, "avg_logprob": -0.18055555453667274, "compression_ratio": 1.7427184466019416, "no_speech_prob": 0.1666259765625, "words": [ { "start": 2235.8, "end": 2236.26, "word": " minutes", "probability": 0.87451171875 }, { "start": 2236.26, "end": 2236.76, "word": " to", "probability": 0.9013671875 }, { "start": 2236.76, "end": 2237.1, "word": " run", "probability": 0.89453125 }, { "start": 2237.1, "end": 2237.84, "word": " because", "probability": 0.54296875 } ] }, { "id": 1067, "seek": 223540, "start": 2237.84, "end": 2238.62, "text": " what it's doing is it's", "tokens": [ 51014, 437, 309, 311, 884, 307, 309, 311, 51064 ], "temperature": 0.0, "avg_logprob": -0.18055555453667274, "compression_ratio": 1.7427184466019416, "no_speech_prob": 0.1666259765625, "words": [ { "start": 2237.84, "end": 2238.0, "word": " what", "probability": 0.87255859375 }, { "start": 2238.0, "end": 2238.14, "word": " it's", "probability": 0.91015625 }, { "start": 2238.14, "end": 2238.34, "word": " doing", "probability": 0.90576171875 }, { "start": 2238.34, "end": 2238.48, "word": " is", "probability": 0.87939453125 }, { "start": 2238.48, "end": 2238.62, "word": " it's", "probability": 0.896240234375 } ] }, { "id": 1068, "seek": 223540, "start": 2238.62, "end": 2239.64, "text": " reading every single", "tokens": [ 51064, 3760, 633, 2167, 51114 ], "temperature": 0.0, "avg_logprob": -0.18055555453667274, "compression_ratio": 1.7427184466019416, "no_speech_prob": 0.1666259765625, "words": [ { "start": 2238.62, "end": 2238.9, "word": " reading", "probability": 0.81103515625 }, { "start": 2238.9, "end": 2239.32, "word": " every", "probability": 0.75390625 }, { "start": 2239.32, "end": 2239.64, "word": " single", "probability": 0.87255859375 } ] }, { "id": 1069, "seek": 223540, "start": 2239.64, "end": 2241.0, "text": " email and it is", "tokens": [ 51114, 3796, 293, 309, 307, 51164 ], "temperature": 0.0, "avg_logprob": -0.18055555453667274, "compression_ratio": 1.7427184466019416, "no_speech_prob": 0.1666259765625, "words": [ { "start": 2239.64, "end": 2240.08, "word": " email", "probability": 0.84619140625 }, { "start": 2240.08, "end": 2240.76, "word": " and", "probability": 0.60693359375 }, { "start": 2240.76, "end": 2240.86, "word": " it", "probability": 0.8505859375 }, { "start": 2240.86, "end": 2241.0, "word": " is", "probability": 0.732421875 } ] }, { "id": 1070, "seek": 223540, "start": 2241.0, "end": 2242.26, "text": " counting the words in", "tokens": [ 51164, 13251, 264, 2283, 294, 51214 ], "temperature": 0.0, "avg_logprob": -0.18055555453667274, "compression_ratio": 1.7427184466019416, "no_speech_prob": 0.1666259765625, "words": [ { "start": 2241.0, "end": 2241.42, "word": " counting", "probability": 0.76220703125 }, { "start": 2241.42, "end": 2241.72, "word": " the", "probability": 0.8095703125 }, { "start": 2241.72, "end": 2242.04, "word": " words", "probability": 0.70556640625 }, { "start": 2242.04, "end": 2242.26, "word": " in", "probability": 0.90576171875 } ] }, { "id": 1071, "seek": 223540, "start": 2242.26, "end": 2245.1, "text": " those emails in order", "tokens": [ 51214, 729, 12524, 294, 1668, 51364 ], "temperature": 0.0, "avg_logprob": -0.18055555453667274, "compression_ratio": 1.7427184466019416, "no_speech_prob": 0.1666259765625, "words": [ { "start": 2242.26, "end": 2242.48, "word": " those", "probability": 0.8486328125 }, { "start": 2242.48, "end": 2242.96, "word": " emails", "probability": 0.7822265625 }, { "start": 2242.96, "end": 2244.98, "word": " in", "probability": 0.8447265625 }, { "start": 2244.98, "end": 2245.1, "word": " order", "probability": 0.82373046875 } ] }, { "id": 1072, "seek": 223540, "start": 2245.1, "end": 2246.06, "text": " to get the number of", "tokens": [ 51364, 281, 483, 264, 1230, 295, 51414 ], "temperature": 0.0, "avg_logprob": -0.18055555453667274, "compression_ratio": 1.7427184466019416, "no_speech_prob": 0.1666259765625, "words": [ { "start": 2245.1, "end": 2245.2, "word": " to", "probability": 0.90283203125 }, { "start": 2245.2, "end": 2245.3, "word": " get", "probability": 0.8974609375 }, { "start": 2245.3, "end": 2245.44, "word": " the", "probability": 0.80712890625 }, { "start": 2245.44, "end": 2245.84, "word": " number", "probability": 0.8896484375 }, { "start": 2245.84, "end": 2246.06, "word": " of", "probability": 0.90478515625 } ] }, { "id": 1073, "seek": 223540, "start": 2246.06, "end": 2250.76, "text": " unique words. So I'm", "tokens": [ 51414, 3845, 2283, 13, 407, 286, 478, 51664 ], "temperature": 0.0, "avg_logprob": -0.18055555453667274, "compression_ratio": 1.7427184466019416, "no_speech_prob": 0.1666259765625, "words": [ { "start": 2246.06, "end": 2246.52, "word": " unique", "probability": 0.779296875 }, { "start": 2246.52, "end": 2247.0, "word": " words", "probability": 0.7275390625 }, { "start": 2247.0, "end": 2247.44, "word": ".", "probability": 0.98974609375 }, { "start": 2250.06, "end": 2250.5, "word": " So", "probability": 0.86865234375 }, { "start": 2250.5, "end": 2250.76, "word": " I'm", "probability": 0.904296875 } ] }, { "id": 1074, "seek": 223540, "start": 2250.76, "end": 2251.68, "text": " going to go ahead and", "tokens": [ 51664, 516, 281, 352, 2286, 293, 51714 ], "temperature": 0.0, "avg_logprob": -0.18055555453667274, "compression_ratio": 1.7427184466019416, "no_speech_prob": 0.1666259765625, "words": [ { "start": 2250.76, "end": 2250.82, "word": " going", "probability": 0.8037109375 }, { "start": 2250.82, "end": 2250.88, "word": " to", "probability": 0.90234375 }, { "start": 2250.88, "end": 2251.02, "word": " go", "probability": 0.8955078125 }, { "start": 2251.02, "end": 2251.38, "word": " ahead", "probability": 0.85888671875 }, { "start": 2251.38, "end": 2251.68, "word": " and", "probability": 0.89794921875 } ] }, { "id": 1075, "seek": 223540, "start": 2251.68, "end": 2253.32, "text": " run this because it's", "tokens": [ 51714, 1190, 341, 570, 309, 311, 51764 ], "temperature": 0.0, "avg_logprob": -0.18055555453667274, "compression_ratio": 1.7427184466019416, "no_speech_prob": 0.1666259765625, "words": [ { "start": 2251.68, "end": 2252.02, "word": " run", "probability": 0.89599609375 }, { "start": 2252.02, "end": 2252.42, "word": " this", "probability": 0.88232421875 }, { "start": 2252.42, "end": 2252.88, "word": " because", "probability": 0.76953125 }, { "start": 2252.88, "end": 2253.32, "word": " it's", "probability": 0.9462890625 } ] }, { "id": 1076, "seek": 223540, "start": 2253.32, "end": 2254.1, "text": " going to take a little", "tokens": [ 51764, 516, 281, 747, 257, 707, 51814 ], "temperature": 0.0, "avg_logprob": -0.18055555453667274, "compression_ratio": 1.7427184466019416, "no_speech_prob": 0.1666259765625, "words": [ { "start": 2253.32, "end": 2253.46, "word": " going", "probability": 0.853515625 }, { "start": 2253.46, "end": 2253.62, "word": " to", "probability": 0.90380859375 }, { "start": 2253.62, "end": 2253.82, "word": " take", "probability": 0.82080078125 }, { "start": 2253.96, "end": 2254.1, "word": " a little", "probability": 0.79296875 } ] }, { "id": 1077, "seek": 226456, "start": 2254.1, "end": 2255.8, "text": " bit. But in case you", "tokens": [ 50364, 857, 13, 583, 294, 1389, 291, 50414 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2254.1, "end": 2254.26, "word": " bit", "probability": 0.06072998046875 }, { "start": 2254.26, "end": 2254.62, "word": ".", "probability": 0.249755859375 }, { "start": 2255.02, "end": 2255.2, "word": " But", "probability": 0.5205078125 }, { "start": 2255.2, "end": 2255.46, "word": " in", "probability": 0.78662109375 }, { "start": 2255.46, "end": 2255.66, "word": " case", "probability": 0.794921875 }, { "start": 2255.66, "end": 2255.8, "word": " you", "probability": 0.89697265625 } ] }, { "id": 1078, "seek": 226456, "start": 2255.8, "end": 2257.24, "text": " need, here is the", "tokens": [ 50414, 643, 11, 510, 307, 264, 50464 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2255.8, "end": 2256.14, "word": " need", "probability": 0.81787109375 }, { "start": 2256.14, "end": 2256.36, "word": ",", "probability": 0.64892578125 }, { "start": 2256.36, "end": 2256.68, "word": " here", "probability": 0.81591796875 }, { "start": 2256.68, "end": 2257.02, "word": " is", "probability": 0.89599609375 }, { "start": 2257.02, "end": 2257.24, "word": " the", "probability": 0.81005859375 } ] }, { "id": 1079, "seek": 226456, "start": 2257.24, "end": 2258.44, "text": " code while this is", "tokens": [ 50464, 3089, 1339, 341, 307, 50514 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2257.24, "end": 2257.66, "word": " code", "probability": 0.830078125 }, { "start": 2257.66, "end": 2258.2, "word": " while", "probability": 0.7890625 }, { "start": 2258.2, "end": 2258.34, "word": " this", "probability": 0.87744140625 }, { "start": 2258.34, "end": 2258.44, "word": " is", "probability": 0.90478515625 } ] }, { "id": 1080, "seek": 226456, "start": 2258.44, "end": 2259.24, "text": " operating. And so we", "tokens": [ 50514, 7447, 13, 400, 370, 321, 50564 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2258.44, "end": 2258.82, "word": " operating", "probability": 0.87548828125 }, { "start": 2258.82, "end": 2259.02, "word": ".", "probability": 0.51171875 }, { "start": 2259.02, "end": 2259.02, "word": " And", "probability": 0.425048828125 }, { "start": 2259.02, "end": 2259.12, "word": " so", "probability": 0.888671875 }, { "start": 2259.12, "end": 2259.24, "word": " we", "probability": 0.85986328125 } ] }, { "id": 1081, "seek": 226456, "start": 2259.24, "end": 2260.56, "text": " can see that it is", "tokens": [ 50564, 393, 536, 300, 309, 307, 50614 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2259.24, "end": 2259.36, "word": " can", "probability": 0.89794921875 }, { "start": 2259.36, "end": 2259.6, "word": " see", "probability": 0.8134765625 }, { "start": 2259.6, "end": 2260.0, "word": " that", "probability": 0.87646484375 }, { "start": 2260.0, "end": 2260.44, "word": " it", "probability": 0.85986328125 }, { "start": 2260.44, "end": 2260.56, "word": " is", "probability": 0.8095703125 } ] }, { "id": 1082, "seek": 226456, "start": 2260.56, "end": 2261.56, "text": " currently training the", "tokens": [ 50614, 4362, 3097, 264, 50664 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2260.56, "end": 2260.86, "word": " currently", "probability": 0.73095703125 }, { "start": 2260.86, "end": 2261.38, "word": " training", "probability": 0.7841796875 }, { "start": 2261.38, "end": 2261.56, "word": " the", "probability": 0.8046875 } ] }, { "id": 1083, "seek": 226456, "start": 2261.56, "end": 2262.64, "text": " count vectorizer, kind", "tokens": [ 50664, 1207, 8062, 6545, 11, 733, 50714 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2261.56, "end": 2261.74, "word": " count", "probability": 0.6240234375 }, { "start": 2261.74, "end": 2262.36, "word": " vectorizer", "probability": 0.93017578125 }, { "start": 2262.36, "end": 2262.46, "word": ",", "probability": 0.35693359375 }, { "start": 2262.46, "end": 2262.64, "word": " kind", "probability": 0.75927734375 } ] }, { "id": 1084, "seek": 226456, "start": 2262.64, "end": 2263.32, "text": " of down here at the", "tokens": [ 50714, 295, 760, 510, 412, 264, 50764 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2262.64, "end": 2262.74, "word": " of", "probability": 0.90283203125 }, { "start": 2262.74, "end": 2262.92, "word": " down", "probability": 0.8046875 }, { "start": 2262.92, "end": 2263.08, "word": " here", "probability": 0.81787109375 }, { "start": 2263.08, "end": 2263.2, "word": " at", "probability": 0.89404296875 }, { "start": 2263.2, "end": 2263.32, "word": " the", "probability": 0.8115234375 } ] }, { "id": 1085, "seek": 226456, "start": 2263.32, "end": 2265.0, "text": " bottom. And then once", "tokens": [ 50764, 2767, 13, 400, 550, 1564, 50814 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2263.32, "end": 2263.56, "word": " bottom", "probability": 0.7783203125 }, { "start": 2263.56, "end": 2263.92, "word": ".", "probability": 0.79296875 }, { "start": 2264.38, "end": 2264.74, "word": " And", "probability": 0.83056640625 }, { "start": 2264.74, "end": 2264.86, "word": " then", "probability": 0.740234375 }, { "start": 2264.86, "end": 2265.0, "word": " once", "probability": 0.80712890625 } ] }, { "id": 1086, "seek": 226456, "start": 2265.0, "end": 2265.78, "text": " the count vectorizer is", "tokens": [ 50814, 264, 1207, 8062, 6545, 307, 50864 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2265.0, "end": 2265.1, "word": " the", "probability": 0.7138671875 }, { "start": 2265.1, "end": 2265.26, "word": " count", "probability": 0.73779296875 }, { "start": 2265.26, "end": 2265.66, "word": " vectorizer", "probability": 0.922119140625 }, { "start": 2265.66, "end": 2265.78, "word": " is", "probability": 0.85205078125 } ] }, { "id": 1087, "seek": 226456, "start": 2265.78, "end": 2266.54, "text": " complete, it will start", "tokens": [ 50864, 3566, 11, 309, 486, 722, 50914 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2265.78, "end": 2266.08, "word": " complete", "probability": 0.65673828125 }, { "start": 2266.08, "end": 2266.18, "word": ",", "probability": 0.74560546875 }, { "start": 2266.18, "end": 2266.26, "word": " it", "probability": 0.8916015625 }, { "start": 2266.26, "end": 2266.34, "word": " will", "probability": 0.81396484375 }, { "start": 2266.34, "end": 2266.54, "word": " start", "probability": 0.87646484375 } ] }, { "id": 1088, "seek": 226456, "start": 2266.54, "end": 2267.6, "text": " training the tfidf", "tokens": [ 50914, 3097, 264, 256, 69, 327, 69, 50964 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2266.54, "end": 2266.84, "word": " training", "probability": 0.81201171875 }, { "start": 2266.84, "end": 2267.0, "word": " the", "probability": 0.80029296875 }, { "start": 2267.0, "end": 2267.6, "word": " tfidf", "probability": 0.62982177734375 } ] }, { "id": 1089, "seek": 226456, "start": 2267.6, "end": 2269.28, "text": " vectorizer. And then it", "tokens": [ 50964, 8062, 6545, 13, 400, 550, 309, 51014 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2267.6, "end": 2268.26, "word": " vectorizer", "probability": 0.887451171875 }, { "start": 2268.26, "end": 2268.62, "word": ".", "probability": 0.304931640625 }, { "start": 2268.72, "end": 2268.98, "word": " And", "probability": 0.87646484375 }, { "start": 2268.98, "end": 2269.12, "word": " then", "probability": 0.7373046875 }, { "start": 2269.12, "end": 2269.28, "word": " it", "probability": 0.8935546875 } ] }, { "id": 1090, "seek": 226456, "start": 2269.28, "end": 2270.42, "text": " will let us know when", "tokens": [ 51014, 486, 718, 505, 458, 562, 51064 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2269.28, "end": 2269.4, "word": " will", "probability": 0.810546875 }, { "start": 2269.4, "end": 2269.6, "word": " let", "probability": 0.904296875 }, { "start": 2269.6, "end": 2269.76, "word": " us", "probability": 0.9072265625 }, { "start": 2269.76, "end": 2270.04, "word": " know", "probability": 0.8193359375 }, { "start": 2270.04, "end": 2270.42, "word": " when", "probability": 0.87841796875 } ] }, { "id": 1091, "seek": 226456, "start": 2270.42, "end": 2282.48, "text": " that is complete. So", "tokens": [ 51064, 300, 307, 3566, 13, 407, 51364 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2270.42, "end": 2270.54, "word": " that", "probability": 0.88232421875 }, { "start": 2270.54, "end": 2270.74, "word": " is", "probability": 0.9091796875 }, { "start": 2270.74, "end": 2271.38, "word": " complete", "probability": 0.65283203125 }, { "start": 2271.38, "end": 2271.74, "word": ".", "probability": 0.99267578125 }, { "start": 2282.12, "end": 2282.48, "word": " So", "probability": 0.8720703125 } ] }, { "id": 1092, "seek": 226456, "start": 2282.48, "end": 2283.44, "text": " while this is going,", "tokens": [ 51364, 1339, 341, 307, 516, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2282.48, "end": 2282.74, "word": " while", "probability": 0.76513671875 }, { "start": 2282.74, "end": 2282.92, "word": " this", "probability": 0.880859375 }, { "start": 2282.92, "end": 2283.06, "word": " is", "probability": 0.9091796875 }, { "start": 2283.06, "end": 2283.34, "word": " going", "probability": 0.8603515625 }, { "start": 2283.34, "end": 2283.44, "word": ",", "probability": 0.89208984375 } ] }, { "id": 1093, "seek": 226456, "start": 2283.44, "end": 2284.22, "text": " I'm going to go ahead", "tokens": [ 51414, 286, 478, 516, 281, 352, 2286, 51464 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2283.44, "end": 2283.62, "word": " I'm", "probability": 0.987548828125 }, { "start": 2283.62, "end": 2283.66, "word": " going", "probability": 0.72265625 }, { "start": 2283.66, "end": 2283.7, "word": " to", "probability": 0.9091796875 }, { "start": 2283.7, "end": 2283.82, "word": " go", "probability": 0.89306640625 }, { "start": 2283.82, "end": 2284.22, "word": " ahead", "probability": 0.85791015625 } ] }, { "id": 1094, "seek": 226456, "start": 2284.22, "end": 2285.86, "text": " and move on to the", "tokens": [ 51464, 293, 1286, 322, 281, 264, 51514 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2284.22, "end": 2284.62, "word": " and", "probability": 0.89404296875 }, { "start": 2284.62, "end": 2285.02, "word": " move", "probability": 0.87744140625 }, { "start": 2285.02, "end": 2285.3, "word": " on", "probability": 0.908203125 }, { "start": 2285.3, "end": 2285.58, "word": " to", "probability": 0.90673828125 }, { "start": 2285.58, "end": 2285.86, "word": " the", "probability": 0.8115234375 } ] }, { "id": 1095, "seek": 226456, "start": 2285.86, "end": 2286.98, "text": " next code block. We", "tokens": [ 51514, 958, 3089, 3461, 13, 492, 51564 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2285.86, "end": 2286.22, "word": " next", "probability": 0.85546875 }, { "start": 2286.22, "end": 2286.58, "word": " code", "probability": 0.82763671875 }, { "start": 2286.58, "end": 2286.82, "word": " block", "probability": 0.796875 }, { "start": 2286.82, "end": 2286.84, "word": ".", "probability": 0.95947265625 }, { "start": 2286.84, "end": 2286.98, "word": " We", "probability": 0.9033203125 } ] }, { "id": 1096, "seek": 226456, "start": 2286.98, "end": 2287.8, "text": " can write the code", "tokens": [ 51564, 393, 2464, 264, 3089, 51614 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2286.98, "end": 2287.1, "word": " can", "probability": 0.89990234375 }, { "start": 2287.1, "end": 2287.36, "word": " write", "probability": 0.7978515625 }, { "start": 2287.36, "end": 2287.56, "word": " the", "probability": 0.80859375 }, { "start": 2287.56, "end": 2287.8, "word": " code", "probability": 0.826171875 } ] }, { "id": 1097, "seek": 226456, "start": 2287.8, "end": 2288.5, "text": " while this is still", "tokens": [ 51614, 1339, 341, 307, 920, 51664 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2287.8, "end": 2287.98, "word": " while", "probability": 0.90771484375 }, { "start": 2287.98, "end": 2288.16, "word": " this", "probability": 0.8779296875 }, { "start": 2288.16, "end": 2288.28, "word": " is", "probability": 0.90673828125 }, { "start": 2288.28, "end": 2288.5, "word": " still", "probability": 0.89892578125 } ] }, { "id": 1098, "seek": 226456, "start": 2288.5, "end": 2289.4, "text": " training, but we won't", "tokens": [ 51664, 3097, 11, 457, 321, 1582, 380, 51714 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2288.5, "end": 2288.84, "word": " training", "probability": 0.78515625 }, { "start": 2288.84, "end": 2288.92, "word": ",", "probability": 0.82568359375 }, { "start": 2288.92, "end": 2289.08, "word": " but", "probability": 0.90087890625 }, { "start": 2289.08, "end": 2289.24, "word": " we", "probability": 0.904296875 }, { "start": 2289.24, "end": 2289.4, "word": " won't", "probability": 0.944091796875 } ] }, { "id": 1099, "seek": 226456, "start": 2289.4, "end": 2290.1, "text": " be able to run it", "tokens": [ 51714, 312, 1075, 281, 1190, 309, 51764 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2289.4, "end": 2289.54, "word": " be", "probability": 0.90185546875 }, { "start": 2289.54, "end": 2289.62, "word": " able", "probability": 0.8759765625 }, { "start": 2289.62, "end": 2289.8, "word": " to", "probability": 0.904296875 }, { "start": 2289.8, "end": 2289.98, "word": " run", "probability": 0.89990234375 }, { "start": 2289.98, "end": 2290.1, "word": " it", "probability": 0.90087890625 } ] }, { "id": 1100, "seek": 226456, "start": 2290.1, "end": 2290.86, "text": " because it can run", "tokens": [ 51764, 570, 309, 393, 1190, 51814 ], "temperature": 0.0, "avg_logprob": -0.17511094533480132, "compression_ratio": 1.893939393939394, "no_speech_prob": 0.2449951171875, "words": [ { "start": 2290.1, "end": 2290.32, "word": " because", "probability": 0.6943359375 }, { "start": 2290.32, "end": 2290.44, "word": " it", "probability": 0.89892578125 }, { "start": 2290.44, "end": 2290.6, "word": " can", "probability": 0.900390625 }, { "start": 2290.6, "end": 2290.86, "word": " run", "probability": 0.8994140625 } ] }, { "id": 1101, "seek": 229412, "start": 2290.86, "end": 2292.08, "text": " only one code block at", "tokens": [ 50364, 787, 472, 3089, 3461, 412, 50414 ], "temperature": 0.0, "avg_logprob": -0.21679687511641532, "compression_ratio": 1.7810945273631842, "no_speech_prob": 0.070556640625, "words": [ { "start": 2290.86, "end": 2291.14, "word": " only", "probability": 0.40380859375 }, { "start": 2291.14, "end": 2291.46, "word": " one", "probability": 0.82421875 }, { "start": 2291.46, "end": 2291.7, "word": " code", "probability": 0.8388671875 }, { "start": 2291.7, "end": 2291.94, "word": " block", "probability": 0.77099609375 }, { "start": 2291.94, "end": 2292.08, "word": " at", "probability": 0.90283203125 } ] }, { "id": 1102, "seek": 229412, "start": 2292.18, "end": 2293.8, "text": " a time. So in this", "tokens": [ 50414, 257, 565, 13, 407, 294, 341, 50464 ], "temperature": 0.0, "avg_logprob": -0.21679687511641532, "compression_ratio": 1.7810945273631842, "no_speech_prob": 0.070556640625, "words": [ { "start": 2292.18, "end": 2292.5, "word": " a time", "probability": 0.79638671875 }, { "start": 2292.5, "end": 2292.98, "word": ".", "probability": 0.8876953125 }, { "start": 2293.5, "end": 2293.58, "word": " So", "probability": 0.6083984375 }, { "start": 2293.58, "end": 2293.66, "word": " in", "probability": 0.81494140625 }, { "start": 2293.66, "end": 2293.8, "word": " this", "probability": 0.880859375 } ] }, { "id": 1103, "seek": 229412, "start": 2293.8, "end": 2294.72, "text": " case, we have task", "tokens": [ 50464, 1389, 11, 321, 362, 5633, 50514 ], "temperature": 0.0, "avg_logprob": -0.21679687511641532, "compression_ratio": 1.7810945273631842, "no_speech_prob": 0.070556640625, "words": [ { "start": 2293.8, "end": 2294.04, "word": " case", "probability": 0.80517578125 }, { "start": 2294.04, "end": 2294.06, "word": ",", "probability": 0.2371826171875 }, { "start": 2294.06, "end": 2294.2, "word": " we", "probability": 0.90576171875 }, { "start": 2294.2, "end": 2294.42, "word": " have", "probability": 0.880859375 }, { "start": 2294.42, "end": 2294.72, "word": " task", "probability": 0.625 } ] }, { "id": 1104, "seek": 229412, "start": 2294.72, "end": 2296.24, "text": " 3a, which is to count", "tokens": [ 50514, 805, 64, 11, 597, 307, 281, 1207, 50564 ], "temperature": 0.0, "avg_logprob": -0.21679687511641532, "compression_ratio": 1.7810945273631842, "no_speech_prob": 0.070556640625, "words": [ { "start": 2294.72, "end": 2295.28, "word": " 3a", "probability": 0.721923828125 }, { "start": 2295.28, "end": 2295.42, "word": ",", "probability": 0.67138671875 }, { "start": 2295.42, "end": 2295.58, "word": " which", "probability": 0.91650390625 }, { "start": 2295.58, "end": 2295.7, "word": " is", "probability": 0.9091796875 }, { "start": 2295.7, "end": 2295.86, "word": " to", "probability": 0.89697265625 }, { "start": 2295.86, "end": 2296.24, "word": " count", "probability": 0.80078125 } ] }, { "id": 1105, "seek": 229412, "start": 2296.24, "end": 2298.06, "text": " the test email tokens.", "tokens": [ 50564, 264, 1500, 3796, 22667, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.21679687511641532, "compression_ratio": 1.7810945273631842, "no_speech_prob": 0.070556640625, "words": [ { "start": 2296.24, "end": 2296.52, "word": " the", "probability": 0.81201171875 }, { "start": 2296.52, "end": 2296.9, "word": " test", "probability": 0.76220703125 }, { "start": 2296.9, "end": 2297.28, "word": " email", "probability": 0.8544921875 }, { "start": 2297.28, "end": 2297.78, "word": " tokens", "probability": 0.75830078125 }, { "start": 2297.78, "end": 2298.06, "word": ".", "probability": 0.8896484375 } ] }, { "id": 1106, "seek": 229412, "start": 2298.06, "end": 2298.9, "text": " So we're going to", "tokens": [ 50614, 407, 321, 434, 516, 281, 50664 ], "temperature": 0.0, "avg_logprob": -0.21679687511641532, "compression_ratio": 1.7810945273631842, "no_speech_prob": 0.070556640625, "words": [ { "start": 2298.06, "end": 2298.24, "word": " So", "probability": 0.7724609375 }, { "start": 2298.24, "end": 2298.46, "word": " we're", "probability": 0.886962890625 }, { "start": 2298.46, "end": 2298.64, "word": " going", "probability": 0.85400390625 }, { "start": 2298.64, "end": 2298.9, "word": " to", "probability": 0.90966796875 } ] }, { "id": 1107, "seek": 229412, "start": 2298.9, "end": 2300.12, "text": " manually count out", "tokens": [ 50664, 16945, 1207, 484, 50714 ], "temperature": 0.0, "avg_logprob": -0.21679687511641532, "compression_ratio": 1.7810945273631842, "no_speech_prob": 0.070556640625, "words": [ { "start": 2298.9, "end": 2299.32, "word": " manually", "probability": 0.81884765625 }, { "start": 2299.32, "end": 2299.74, "word": " count", "probability": 0.82177734375 }, { "start": 2299.74, "end": 2300.12, "word": " out", "probability": 0.8134765625 } ] }, { "id": 1108, "seek": 229412, "start": 2300.88, "end": 2302.42, "text": " each of the tokens.", "tokens": [ 50714, 1184, 295, 264, 22667, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.21679687511641532, "compression_ratio": 1.7810945273631842, "no_speech_prob": 0.070556640625, "words": [ { "start": 2300.88, "end": 2301.36, "word": " each", "probability": 0.81005859375 }, { "start": 2301.36, "end": 2301.48, "word": " of", "probability": 0.904296875 }, { "start": 2301.48, "end": 2301.62, "word": " the", "probability": 0.8115234375 }, { "start": 2301.62, "end": 2301.96, "word": " tokens", "probability": 0.7490234375 }, { "start": 2301.96, "end": 2302.42, "word": ".", "probability": 0.88134765625 } ] }, { "id": 1109, "seek": 229412, "start": 2302.42, "end": 2303.28, "text": " So what we're going to", "tokens": [ 50764, 407, 437, 321, 434, 516, 281, 50814 ], "temperature": 0.0, "avg_logprob": -0.21679687511641532, "compression_ratio": 1.7810945273631842, "no_speech_prob": 0.070556640625, "words": [ { "start": 2302.42, "end": 2302.42, "word": " So", "probability": 0.779296875 }, { "start": 2302.42, "end": 2303.02, "word": " what", "probability": 0.82958984375 }, { "start": 2303.02, "end": 2303.14, "word": " we're", "probability": 0.9296875 }, { "start": 2303.14, "end": 2303.2, "word": " going", "probability": 0.74169921875 }, { "start": 2303.2, "end": 2303.28, "word": " to", "probability": 0.90869140625 } ] }, { "id": 1110, "seek": 229412, "start": 2303.28, "end": 2307.48, "text": " do is say for i in", "tokens": [ 50814, 360, 307, 584, 337, 741, 294, 50864 ], "temperature": 0.0, "avg_logprob": -0.21679687511641532, "compression_ratio": 1.7810945273631842, "no_speech_prob": 0.070556640625, "words": [ { "start": 2303.28, "end": 2303.52, "word": " do", "probability": 0.90625 }, { "start": 2303.52, "end": 2304.0, "word": " is", "probability": 0.8974609375 }, { "start": 2304.0, "end": 2304.42, "word": " say", "probability": 0.775390625 }, { "start": 2304.42, "end": 2306.42, "word": " for", "probability": 0.274658203125 }, { "start": 2306.42, "end": 2306.96, "word": " i", "probability": 0.7548828125 }, { "start": 2306.96, "end": 2307.48, "word": " in", "probability": 0.7890625 } ] }, { "id": 1111, "seek": 229412, "start": 2307.48, "end": 2308.8, "text": " and this is a bit of", "tokens": [ 50864, 293, 341, 307, 257, 857, 295, 50914 ], "temperature": 0.0, "avg_logprob": -0.21679687511641532, "compression_ratio": 1.7810945273631842, "no_speech_prob": 0.070556640625, "words": [ { "start": 2307.48, "end": 2308.22, "word": " and", "probability": 0.2081298828125 }, { "start": 2308.22, "end": 2308.44, "word": " this", "probability": 0.78759765625 }, { "start": 2308.44, "end": 2308.54, "word": " is", "probability": 0.9072265625 }, { "start": 2308.64, "end": 2308.7, "word": " a bit", "probability": 0.89794921875 }, { "start": 2308.7, "end": 2308.8, "word": " of", "probability": 0.90673828125 } ] }, { "id": 1112, "seek": 229412, "start": 2308.96, "end": 2309.82, "text": " a trick so that we can", "tokens": [ 50914, 257, 4282, 370, 300, 321, 393, 50964 ], "temperature": 0.0, "avg_logprob": -0.21679687511641532, "compression_ratio": 1.7810945273631842, "no_speech_prob": 0.070556640625, "words": [ { "start": 2308.96, "end": 2309.22, "word": " a trick", "probability": 0.87060546875 }, { "start": 2309.22, "end": 2309.42, "word": " so", "probability": 0.80810546875 }, { "start": 2309.42, "end": 2309.54, "word": " that", "probability": 0.87646484375 }, { "start": 2309.54, "end": 2309.64, "word": " we", "probability": 0.904296875 }, { "start": 2309.64, "end": 2309.82, "word": " can", "probability": 0.89697265625 } ] }, { "id": 1113, "seek": 229412, "start": 2309.82, "end": 2311.8, "text": " keep the count as well", "tokens": [ 50964, 1066, 264, 1207, 382, 731, 51014 ], "temperature": 0.0, "avg_logprob": -0.21679687511641532, "compression_ratio": 1.7810945273631842, "no_speech_prob": 0.070556640625, "words": [ { "start": 2309.82, "end": 2310.26, "word": " keep", "probability": 0.80908203125 }, { "start": 2310.26, "end": 2310.88, "word": " the", "probability": 0.81396484375 }, { "start": 2310.88, "end": 2311.3, "word": " count", "probability": 0.79931640625 }, { "start": 2311.3, "end": 2311.62, "word": " as", "probability": 0.833984375 }, { "start": 2311.62, "end": 2311.8, "word": " well", "probability": 0.88037109375 } ] }, { "id": 1114, "seek": 229412, "start": 2311.8, "end": 2313.04, "text": " as the words in order.", "tokens": [ 51014, 382, 264, 2283, 294, 1668, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.21679687511641532, "compression_ratio": 1.7810945273631842, "no_speech_prob": 0.070556640625, "words": [ { "start": 2311.8, "end": 2311.94, "word": " as", "probability": 0.8935546875 }, { "start": 2311.94, "end": 2312.14, "word": " the", "probability": 0.81103515625 }, { "start": 2312.14, "end": 2312.4, "word": " words", "probability": 0.72802734375 }, { "start": 2312.4, "end": 2312.54, "word": " in", "probability": 0.90625 }, { "start": 2312.54, "end": 2312.8, "word": " order", "probability": 0.83203125 }, { "start": 2312.8, "end": 2313.04, "word": ".", "probability": 0.76171875 } ] }, { "id": 1115, "seek": 229412, "start": 2313.04, "end": 2313.56, "text": " So we're going to use", "tokens": [ 51064, 407, 321, 434, 516, 281, 764, 51114 ], "temperature": 0.0, "avg_logprob": -0.21679687511641532, "compression_ratio": 1.7810945273631842, "no_speech_prob": 0.070556640625, "words": [ { "start": 2313.04, "end": 2313.1, "word": " So", "probability": 0.8916015625 }, { "start": 2313.1, "end": 2313.24, "word": " we're", "probability": 0.92919921875 }, { "start": 2313.24, "end": 2313.36, "word": " going", "probability": 0.7861328125 }, { "start": 2313.36, "end": 2313.4, "word": " to", "probability": 0.9072265625 }, { "start": 2313.4, "end": 2313.56, "word": " use", "probability": 0.83447265625 } ] }, { "id": 1116, "seek": 229412, "start": 2313.74, "end": 2315.62, "text": " a list of a dictionary", "tokens": [ 51114, 257, 1329, 295, 257, 25890, 51164 ], "temperature": 0.0, "avg_logprob": -0.21679687511641532, "compression_ratio": 1.7810945273631842, "no_speech_prob": 0.070556640625, "words": [ { "start": 2313.74, "end": 2314.2, "word": " a list", "probability": 0.8876953125 }, { "start": 2314.2, "end": 2314.98, "word": " of", "probability": 0.90234375 }, { "start": 2315.28, "end": 2315.62, "word": " a dictionary", "probability": 0.78759765625 } ] }, { "id": 1117, "seek": 229412, "start": 2318.82, "end": 2320.42, "text": " and we're going to", "tokens": [ 51164, 293, 321, 434, 516, 281, 51214 ], "temperature": 0.0, "avg_logprob": -0.21679687511641532, "compression_ratio": 1.7810945273631842, "no_speech_prob": 0.070556640625, "words": [ { "start": 2318.82, "end": 2319.3, "word": " and", "probability": 0.5517578125 }, { "start": 2319.3, "end": 2319.78, "word": " we're", "probability": 0.926025390625 }, { "start": 2319.78, "end": 2319.96, "word": " going", "probability": 0.8564453125 }, { "start": 2319.96, "end": 2320.42, "word": " to", "probability": 0.90673828125 } ] }, { "id": 1118, "seek": 232410, "start": 2320.42, "end": 2323.24, "text": " want to grab the", "tokens": [ 50364, 528, 281, 4444, 264, 50514 ], "temperature": 0.6000000000000001, "avg_logprob": -0.3374602683565833, "compression_ratio": 1.7393617021276595, "no_speech_prob": 0.78466796875, "words": [ { "start": 2320.42, "end": 2321.44, "word": " want", "probability": 0.072265625 }, { "start": 2321.44, "end": 2321.88, "word": " to", "probability": 0.90478515625 }, { "start": 2321.88, "end": 2322.98, "word": " grab", "probability": 0.779296875 }, { "start": 2322.98, "end": 2323.24, "word": " the", "probability": 0.787109375 } ] }, { "id": 1119, "seek": 232410, "start": 2323.24, "end": 2324.26, "text": " tokenized version of", "tokens": [ 50514, 14862, 1602, 3037, 295, 50564 ], "temperature": 0.6000000000000001, "avg_logprob": -0.3374602683565833, "compression_ratio": 1.7393617021276595, "no_speech_prob": 0.78466796875, "words": [ { "start": 2323.24, "end": 2323.86, "word": " tokenized", "probability": 0.863037109375 }, { "start": 2323.86, "end": 2324.1, "word": " version", "probability": 0.6748046875 }, { "start": 2324.1, "end": 2324.26, "word": " of", "probability": 0.9091796875 } ] }, { "id": 1120, "seek": 232410, "start": 2324.26, "end": 2325.08, "text": " our email. So let's", "tokens": [ 50564, 527, 3796, 13, 407, 718, 311, 50614 ], "temperature": 0.6000000000000001, "avg_logprob": -0.3374602683565833, "compression_ratio": 1.7393617021276595, "no_speech_prob": 0.78466796875, "words": [ { "start": 2324.26, "end": 2324.36, "word": " our", "probability": 0.818359375 }, { "start": 2324.36, "end": 2324.66, "word": " email", "probability": 0.84228515625 }, { "start": 2324.66, "end": 2324.88, "word": ".", "probability": 0.280029296875 }, { "start": 2324.88, "end": 2324.94, "word": " So", "probability": 0.73486328125 }, { "start": 2324.94, "end": 2325.08, "word": " let's", "probability": 0.9033203125 } ] }, { "id": 1121, "seek": 232410, "start": 2325.08, "end": 2328.72, "text": " call this tokenized", "tokens": [ 50614, 818, 341, 14862, 1602, 50814 ], "temperature": 0.6000000000000001, "avg_logprob": -0.3374602683565833, "compression_ratio": 1.7393617021276595, "no_speech_prob": 0.78466796875, "words": [ { "start": 2325.08, "end": 2325.48, "word": " call", "probability": 0.00792694091796875 }, { "start": 2325.48, "end": 2325.9, "word": " this", "probability": 0.81298828125 }, { "start": 2325.9, "end": 2328.72, "word": " tokenized", "probability": 0.7548828125 } ] }, { "id": 1122, "seek": 232410, "start": 2329.36, "end": 2331.28, "text": " email equals tokenizer", "tokens": [ 50814, 3796, 6915, 14862, 6545, 50964 ], "temperature": 0.6000000000000001, "avg_logprob": -0.3374602683565833, "compression_ratio": 1.7393617021276595, "no_speech_prob": 0.78466796875, "words": [ { "start": 2329.36, "end": 2329.66, "word": " email", "probability": 0.525390625 }, { "start": 2329.66, "end": 2330.34, "word": " equals", "probability": 0.356689453125 }, { "start": 2330.34, "end": 2331.28, "word": " tokenizer", "probability": 0.86376953125 } ] }, { "id": 1123, "seek": 232410, "start": 2332.86, "end": 2335.5, "text": " test email. And then", "tokens": [ 50964, 1500, 3796, 13, 400, 550, 51114 ], "temperature": 0.6000000000000001, "avg_logprob": -0.3374602683565833, "compression_ratio": 1.7393617021276595, "no_speech_prob": 0.78466796875, "words": [ { "start": 2332.86, "end": 2333.46, "word": " test", "probability": 0.7158203125 }, { "start": 2333.46, "end": 2333.98, "word": " email", "probability": 0.88232421875 }, { "start": 2333.98, "end": 2334.58, "word": ".", "probability": 0.75341796875 }, { "start": 2334.72, "end": 2335.32, "word": " And", "probability": 0.7158203125 }, { "start": 2335.32, "end": 2335.5, "word": " then", "probability": 0.71484375 } ] }, { "id": 1124, "seek": 232410, "start": 2335.5, "end": 2336.62, "text": " our from keys we're", "tokens": [ 51114, 527, 490, 9317, 321, 434, 51164 ], "temperature": 0.6000000000000001, "avg_logprob": -0.3374602683565833, "compression_ratio": 1.7393617021276595, "no_speech_prob": 0.78466796875, "words": [ { "start": 2335.5, "end": 2335.84, "word": " our", "probability": 0.7412109375 }, { "start": 2335.84, "end": 2336.12, "word": " from", "probability": 0.5703125 }, { "start": 2336.12, "end": 2336.44, "word": " keys", "probability": 0.59228515625 }, { "start": 2336.44, "end": 2336.62, "word": " we're", "probability": 0.58447265625 } ] }, { "id": 1125, "seek": 232410, "start": 2336.62, "end": 2337.3, "text": " going to have tokenized", "tokens": [ 51164, 516, 281, 362, 14862, 1602, 51214 ], "temperature": 0.6000000000000001, "avg_logprob": -0.3374602683565833, "compression_ratio": 1.7393617021276595, "no_speech_prob": 0.78466796875, "words": [ { "start": 2336.62, "end": 2336.68, "word": " going", "probability": 0.5322265625 }, { "start": 2336.68, "end": 2336.7, "word": " to", "probability": 0.89990234375 }, { "start": 2336.7, "end": 2336.82, "word": " have", "probability": 0.89111328125 }, { "start": 2336.82, "end": 2337.3, "word": " tokenized", "probability": 0.8515625 } ] }, { "id": 1126, "seek": 232410, "start": 2337.3, "end": 2338.38, "text": " email which we saw", "tokens": [ 51214, 3796, 597, 321, 1866, 51264 ], "temperature": 0.6000000000000001, "avg_logprob": -0.3374602683565833, "compression_ratio": 1.7393617021276595, "no_speech_prob": 0.78466796875, "words": [ { "start": 2337.3, "end": 2337.6, "word": " email", "probability": 0.90771484375 }, { "start": 2337.6, "end": 2337.88, "word": " which", "probability": 0.430419921875 }, { "start": 2337.88, "end": 2338.08, "word": " we", "probability": 0.87646484375 }, { "start": 2338.08, "end": 2338.38, "word": " saw", "probability": 0.7392578125 } ] }, { "id": 1127, "seek": 232410, "start": 2338.38, "end": 2339.66, "text": " above is going to be a", "tokens": [ 51264, 3673, 307, 516, 281, 312, 257, 51314 ], "temperature": 0.6000000000000001, "avg_logprob": -0.3374602683565833, "compression_ratio": 1.7393617021276595, "no_speech_prob": 0.78466796875, "words": [ { "start": 2338.38, "end": 2338.64, "word": " above", "probability": 0.89208984375 }, { "start": 2338.64, "end": 2338.78, "word": " is", "probability": 0.81787109375 }, { "start": 2338.78, "end": 2338.92, "word": " going", "probability": 0.845703125 }, { "start": 2338.92, "end": 2339.1, "word": " to", "probability": 0.90380859375 }, { "start": 2339.1, "end": 2339.2, "word": " be", "probability": 0.90234375 }, { "start": 2339.36, "end": 2339.66, "word": " a list", "probability": 0.88037109375 } ] }, { "id": 1128, "seek": 232410, "start": 2339.66, "end": 2340.42, "text": " list. So we'll just", "tokens": [ 51314, 1329, 13, 407, 321, 603, 445, 51364 ], "temperature": 0.6000000000000001, "avg_logprob": -0.3374602683565833, "compression_ratio": 1.7393617021276595, "no_speech_prob": 0.78466796875, "words": [ { "start": 2339.66, "end": 2339.9, "word": ".", "probability": 0.492919921875 }, { "start": 2339.9, "end": 2339.94, "word": " So", "probability": 0.83056640625 }, { "start": 2339.94, "end": 2340.08, "word": " we'll", "probability": 0.853515625 }, { "start": 2340.08, "end": 2340.22, "word": " just", "probability": 0.826171875 }, { "start": 2340.22, "end": 2340.42, "word": " call", "probability": 0.82470703125 } ] }, { "id": 1129, "seek": 232410, "start": 2340.42, "end": 2343.26, "text": " call that tokenized", "tokens": [ 51364, 818, 300, 14862, 1602, 51464 ], "temperature": 0.6000000000000001, "avg_logprob": -0.3374602683565833, "compression_ratio": 1.7393617021276595, "no_speech_prob": 0.78466796875, "words": [ { "start": 2340.42, "end": 2340.76, "word": " that", "probability": 0.88427734375 }, { "start": 2340.76, "end": 2342.9, "word": " tokenized", "probability": 0.8876953125 }, { "start": 2342.9, "end": 2343.26, "word": " email", "probability": 0.9189453125 } ] }, { "id": 1130, "seek": 232410, "start": 2343.26, "end": 2345.04, "text": " email and then we're", "tokens": [ 51464, 3796, 293, 550, 321, 434, 51564 ], "temperature": 0.6000000000000001, "avg_logprob": -0.3374602683565833, "compression_ratio": 1.7393617021276595, "no_speech_prob": 0.78466796875, "words": [ { "start": 2343.26, "end": 2344.04, "word": " and", "probability": 0.359130859375 }, { "start": 2344.04, "end": 2344.28, "word": " then", "probability": 0.7314453125 }, { "start": 2344.28, "end": 2344.84, "word": " we're", "probability": 0.9208984375 }, { "start": 2344.84, "end": 2345.04, "word": " going", "probability": 0.85595703125 } ] }, { "id": 1131, "seek": 232410, "start": 2345.04, "end": 2346.58, "text": " going to count the", "tokens": [ 51564, 516, 281, 1207, 264, 51664 ], "temperature": 0.6000000000000001, "avg_logprob": -0.3374602683565833, "compression_ratio": 1.7393617021276595, "no_speech_prob": 0.78466796875, "words": [ { "start": 2345.04, "end": 2345.46, "word": " to", "probability": 0.90625 }, { "start": 2345.46, "end": 2346.02, "word": " count", "probability": 0.77490234375 }, { "start": 2346.02, "end": 2346.22, "word": " the", "probability": 0.80615234375 }, { "start": 2346.22, "end": 2346.58, "word": " words", "probability": 0.5927734375 } ] }, { "id": 1132, "seek": 232410, "start": 2346.58, "end": 2349.62, "text": " words. So print, do", "tokens": [ 51664, 2283, 13, 407, 4482, 11, 360, 51764 ], "temperature": 0.6000000000000001, "avg_logprob": -0.3374602683565833, "compression_ratio": 1.7393617021276595, "no_speech_prob": 0.78466796875, "words": [ { "start": 2346.58, "end": 2346.86, "word": ".", "probability": 0.6708984375 }, { "start": 2346.86, "end": 2347.0, "word": " So", "probability": 0.85107421875 }, { "start": 2347.0, "end": 2347.6, "word": " print", "probability": 0.7548828125 }, { "start": 2347.6, "end": 2348.54, "word": ",", "probability": 0.346923828125 }, { "start": 2348.54, "end": 2348.98, "word": " do", "probability": 0.84814453125 }, { "start": 2348.98, "end": 2349.62, "word": " some", "probability": 0.8076171875 } ] }, { "id": 1133, "seek": 232410, "start": 2349.62, "end": 2350.4, "text": " some Python format,", "tokens": [ 51764, 512, 15329, 7877, 11, 51814 ], "temperature": 0.6000000000000001, "avg_logprob": -0.3374602683565833, "compression_ratio": 1.7393617021276595, "no_speech_prob": 0.78466796875, "words": [ { "start": 2349.62, "end": 2349.96, "word": " Python", "probability": 0.72021484375 }, { "start": 2349.96, "end": 2350.4, "word": " format", "probability": 0.26611328125 }, { "start": 2350.4, "end": 2350.4, "word": ",", "probability": 0.40283203125 } ] }, { "id": 1134, "seek": 234976, "start": 2350.4, "end": 2363.0, "text": " And then we're going to look at our tokenized email.count of each word, and then the word itself.", "tokens": [ 50414, 400, 550, 321, 434, 516, 281, 574, 412, 527, 14862, 1602, 3796, 13, 26050, 295, 1184, 1349, 11, 293, 550, 264, 1349, 2564, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.34397976582541184, "compression_ratio": 1.4437869822485208, "no_speech_prob": 0.5498046875, "words": [ { "start": 2350.4, "end": 2351.26, "word": " And", "probability": 0.05157470703125 }, { "start": 2351.26, "end": 2352.24, "word": " then", "probability": 0.599609375 }, { "start": 2352.24, "end": 2352.46, "word": " we're", "probability": 0.736083984375 }, { "start": 2352.46, "end": 2352.58, "word": " going", "probability": 0.5146484375 }, { "start": 2352.58, "end": 2352.6, "word": " to", "probability": 0.9033203125 }, { "start": 2352.6, "end": 2352.76, "word": " look", "probability": 0.91455078125 }, { "start": 2352.76, "end": 2353.0, "word": " at", "probability": 0.9033203125 }, { "start": 2353.0, "end": 2353.5, "word": " our", "probability": 0.775390625 }, { "start": 2353.5, "end": 2356.16, "word": " tokenized", "probability": 0.777099609375 }, { "start": 2356.16, "end": 2356.74, "word": " email", "probability": 0.63720703125 }, { "start": 2356.74, "end": 2358.38, "word": ".count", "probability": 0.5279541015625 }, { "start": 2358.38, "end": 2358.72, "word": " of", "probability": 0.8408203125 }, { "start": 2358.72, "end": 2359.02, "word": " each", "probability": 0.86083984375 }, { "start": 2359.02, "end": 2359.46, "word": " word", "probability": 0.79345703125 }, { "start": 2359.46, "end": 2359.74, "word": ",", "probability": 0.273193359375 }, { "start": 2359.74, "end": 2360.82, "word": " and", "probability": 0.85546875 }, { "start": 2360.82, "end": 2360.98, "word": " then", "probability": 0.6962890625 }, { "start": 2360.98, "end": 2361.44, "word": " the", "probability": 0.80712890625 }, { "start": 2361.44, "end": 2361.74, "word": " word", "probability": 0.8154296875 }, { "start": 2361.74, "end": 2362.4, "word": " itself", "probability": 0.7724609375 }, { "start": 2362.4, "end": 2363.0, "word": ".", "probability": 0.9658203125 } ] }, { "id": 1135, "seek": 234976, "start": 2363.44, "end": 2369.66, "text": " So we see our vectorizing is complete, so we are ready to run this.", "tokens": [ 51014, 407, 321, 536, 527, 8062, 3319, 307, 3566, 11, 370, 321, 366, 1919, 281, 1190, 341, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.34397976582541184, "compression_ratio": 1.4437869822485208, "no_speech_prob": 0.5498046875, "words": [ { "start": 2363.44, "end": 2363.76, "word": " So", "probability": 0.82861328125 }, { "start": 2363.76, "end": 2363.92, "word": " we", "probability": 0.6328125 }, { "start": 2363.92, "end": 2364.26, "word": " see", "probability": 0.60986328125 }, { "start": 2364.26, "end": 2364.52, "word": " our", "probability": 0.77685546875 }, { "start": 2364.52, "end": 2365.08, "word": " vectorizing", "probability": 0.93994140625 }, { "start": 2365.08, "end": 2365.48, "word": " is", "probability": 0.90283203125 }, { "start": 2365.48, "end": 2366.04, "word": " complete", "probability": 0.6484375 }, { "start": 2366.04, "end": 2366.84, "word": ",", "probability": 0.30517578125 }, { "start": 2366.84, "end": 2368.08, "word": " so", "probability": 0.87451171875 }, { "start": 2368.08, "end": 2368.34, "word": " we", "probability": 0.904296875 }, { "start": 2368.34, "end": 2368.5, "word": " are", "probability": 0.7939453125 }, { "start": 2368.5, "end": 2368.86, "word": " ready", "probability": 0.802734375 }, { "start": 2368.86, "end": 2369.08, "word": " to", "probability": 0.90673828125 }, { "start": 2369.08, "end": 2369.28, "word": " run", "probability": 0.900390625 }, { "start": 2369.28, "end": 2369.54, "word": " this", "probability": 0.8720703125 }, { "start": 2369.54, "end": 2369.66, "word": ".", "probability": 0.95947265625 } ] }, { "id": 1136, "seek": 234976, "start": 2369.66, "end": 2376.06, "text": " I'm going to let this sit for about 30 more seconds and let you guys catch up.", "tokens": [ 51314, 286, 478, 516, 281, 718, 341, 1394, 337, 466, 2217, 544, 3949, 293, 718, 291, 1074, 3745, 493, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.34397976582541184, "compression_ratio": 1.4437869822485208, "no_speech_prob": 0.5498046875, "words": [ { "start": 2369.66, "end": 2369.74, "word": " I'm", "probability": 0.924560546875 }, { "start": 2369.74, "end": 2369.82, "word": " going", "probability": 0.74072265625 }, { "start": 2369.82, "end": 2369.82, "word": " to", "probability": 0.9013671875 }, { "start": 2369.82, "end": 2369.96, "word": " let", "probability": 0.88330078125 }, { "start": 2369.96, "end": 2370.14, "word": " this", "probability": 0.873046875 }, { "start": 2370.14, "end": 2370.38, "word": " sit", "probability": 0.89306640625 }, { "start": 2370.38, "end": 2370.68, "word": " for", "probability": 0.8955078125 }, { "start": 2370.68, "end": 2371.5, "word": " about", "probability": 0.80615234375 }, { "start": 2371.5, "end": 2371.94, "word": " 30", "probability": 0.8056640625 }, { "start": 2371.94, "end": 2372.18, "word": " more", "probability": 0.88427734375 }, { "start": 2372.18, "end": 2372.7, "word": " seconds", "probability": 0.72705078125 }, { "start": 2372.7, "end": 2373.62, "word": " and", "probability": 0.5458984375 }, { "start": 2373.62, "end": 2374.74, "word": " let", "probability": 0.7060546875 }, { "start": 2374.74, "end": 2374.84, "word": " you", "probability": 0.89404296875 }, { "start": 2374.84, "end": 2375.02, "word": " guys", "probability": 0.892578125 }, { "start": 2375.02, "end": 2375.26, "word": " catch", "probability": 0.8125 }, { "start": 2375.26, "end": 2375.46, "word": " up", "probability": 0.90966796875 }, { "start": 2375.46, "end": 2376.06, "word": ".", "probability": 0.97412109375 } ] }, { "id": 1137, "seek": 237530, "start": 2376.06, "end": 2390.97, "text": " And then, of course, after this workshop, I have a whole series of workbooks, as well as their solutions.", "tokens": [ 50414, 400, 550, 11, 295, 1164, 11, 934, 341, 13541, 11, 286, 362, 257, 1379, 2638, 295, 589, 15170, 11, 382, 731, 382, 641, 6547, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.270089281129313, "compression_ratio": 1.5526315789473684, "no_speech_prob": 0.037872314453125, "words": [ { "start": 2376.06, "end": 2376.96, "word": " And", "probability": 0.2337646484375 }, { "start": 2383.71, "end": 2384.93, "word": " then", "probability": 0.65966796875 }, { "start": 2384.93, "end": 2385.03, "word": ",", "probability": 0.2120361328125 }, { "start": 2385.03, "end": 2385.05, "word": " of", "probability": 0.89404296875 }, { "start": 2385.05, "end": 2385.17, "word": " course", "probability": 0.87060546875 }, { "start": 2385.17, "end": 2385.23, "word": ",", "probability": 0.9375 }, { "start": 2385.23, "end": 2385.41, "word": " after", "probability": 0.73046875 }, { "start": 2385.41, "end": 2385.63, "word": " this", "probability": 0.8896484375 }, { "start": 2385.63, "end": 2385.99, "word": " workshop", "probability": 0.68798828125 }, { "start": 2385.99, "end": 2386.15, "word": ",", "probability": 0.56640625 }, { "start": 2386.15, "end": 2386.21, "word": " I", "probability": 0.9931640625 }, { "start": 2386.21, "end": 2386.39, "word": " have", "probability": 0.81982421875 }, { "start": 2387.07, "end": 2387.37, "word": " a whole", "probability": 0.7724609375 }, { "start": 2387.37, "end": 2387.99, "word": " series", "probability": 0.806640625 }, { "start": 2387.99, "end": 2388.21, "word": " of", "probability": 0.90087890625 }, { "start": 2388.21, "end": 2388.83, "word": " workbooks", "probability": 0.863037109375 }, { "start": 2388.83, "end": 2389.21, "word": ",", "probability": 0.454345703125 }, { "start": 2389.21, "end": 2389.95, "word": " as", "probability": 0.89013671875 }, { "start": 2389.95, "end": 2390.07, "word": " well", "probability": 0.8779296875 }, { "start": 2390.07, "end": 2390.21, "word": " as", "probability": 0.90283203125 }, { "start": 2390.21, "end": 2390.35, "word": " their", "probability": 0.875 }, { "start": 2390.35, "end": 2390.77, "word": " solutions", "probability": 0.669921875 }, { "start": 2390.77, "end": 2390.97, "word": ".", "probability": 0.84033203125 } ] }, { "id": 1138, "seek": 237530, "start": 2390.97, "end": 2395.83, "text": " So if you're interested in other ways to apply machine learning and security to different problems,", "tokens": [ 50764, 407, 498, 291, 434, 3102, 294, 661, 2098, 281, 3079, 3479, 2539, 293, 3825, 281, 819, 2740, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.270089281129313, "compression_ratio": 1.5526315789473684, "no_speech_prob": 0.037872314453125, "words": [ { "start": 2390.97, "end": 2391.03, "word": " So", "probability": 0.76611328125 }, { "start": 2391.03, "end": 2391.11, "word": " if", "probability": 0.74072265625 }, { "start": 2391.11, "end": 2391.21, "word": " you're", "probability": 0.9130859375 }, { "start": 2391.21, "end": 2391.49, "word": " interested", "probability": 0.6552734375 }, { "start": 2391.49, "end": 2391.67, "word": " in", "probability": 0.91064453125 }, { "start": 2391.67, "end": 2391.91, "word": " other", "probability": 0.78564453125 }, { "start": 2391.91, "end": 2392.23, "word": " ways", "probability": 0.80908203125 }, { "start": 2392.23, "end": 2392.49, "word": " to", "probability": 0.90673828125 }, { "start": 2392.49, "end": 2392.89, "word": " apply", "probability": 0.845703125 }, { "start": 2392.89, "end": 2393.23, "word": " machine", "probability": 0.68798828125 }, { "start": 2393.23, "end": 2393.45, "word": " learning", "probability": 0.8330078125 }, { "start": 2393.45, "end": 2393.61, "word": " and", "probability": 0.880859375 }, { "start": 2393.61, "end": 2393.99, "word": " security", "probability": 0.9140625 }, { "start": 2393.99, "end": 2395.01, "word": " to", "probability": 0.8486328125 }, { "start": 2395.01, "end": 2395.27, "word": " different", "probability": 0.6630859375 }, { "start": 2395.27, "end": 2395.75, "word": " problems", "probability": 0.68603515625 }, { "start": 2395.75, "end": 2395.83, "word": ",", "probability": 0.128662109375 } ] }, { "id": 1139, "seek": 237530, "start": 2395.83, "end": 2400.05, "text": " and using different algorithms, don't forget to take a look at those.", "tokens": [ 51014, 293, 1228, 819, 14642, 11, 500, 380, 2870, 281, 747, 257, 574, 412, 729, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.270089281129313, "compression_ratio": 1.5526315789473684, "no_speech_prob": 0.037872314453125, "words": [ { "start": 2395.83, "end": 2395.93, "word": " and", "probability": 0.82470703125 }, { "start": 2395.93, "end": 2396.09, "word": " using", "probability": 0.82373046875 }, { "start": 2396.09, "end": 2396.37, "word": " different", "probability": 0.69384765625 }, { "start": 2396.37, "end": 2396.91, "word": " algorithms", "probability": 0.87548828125 }, { "start": 2396.91, "end": 2397.71, "word": ",", "probability": 0.94482421875 }, { "start": 2397.71, "end": 2398.33, "word": " don't", "probability": 0.9384765625 }, { "start": 2398.33, "end": 2398.51, "word": " forget", "probability": 0.87109375 }, { "start": 2398.51, "end": 2398.69, "word": " to", "probability": 0.904296875 }, { "start": 2398.69, "end": 2398.87, "word": " take", "probability": 0.81591796875 }, { "start": 2398.99, "end": 2399.07, "word": " a look", "probability": 0.91552734375 }, { "start": 2399.07, "end": 2399.21, "word": " at", "probability": 0.9013671875 }, { "start": 2399.21, "end": 2399.57, "word": " those", "probability": 0.84814453125 }, { "start": 2399.57, "end": 2400.05, "word": ".", "probability": 0.99169921875 } ] }, { "id": 1140, "seek": 237530, "start": 2402.63, "end": 2408.35, "text": " So I'm going to go ahead and run this, Shift-Enter, and we can see the counts.", "tokens": [ 51314, 407, 286, 478, 516, 281, 352, 2286, 293, 1190, 341, 11, 28304, 12, 16257, 391, 11, 293, 321, 393, 536, 264, 14893, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.270089281129313, "compression_ratio": 1.5526315789473684, "no_speech_prob": 0.037872314453125, "words": [ { "start": 2402.63, "end": 2403.11, "word": " So", "probability": 0.822265625 }, { "start": 2403.11, "end": 2403.35, "word": " I'm", "probability": 0.93701171875 }, { "start": 2403.35, "end": 2403.37, "word": " going", "probability": 0.61181640625 }, { "start": 2403.37, "end": 2403.41, "word": " to", "probability": 0.9033203125 }, { "start": 2403.41, "end": 2403.51, "word": " go", "probability": 0.8994140625 }, { "start": 2403.51, "end": 2403.83, "word": " ahead", "probability": 0.8583984375 }, { "start": 2403.83, "end": 2404.23, "word": " and", "probability": 0.8916015625 }, { "start": 2404.23, "end": 2404.65, "word": " run", "probability": 0.89697265625 }, { "start": 2404.65, "end": 2404.99, "word": " this", "probability": 0.884765625 }, { "start": 2404.99, "end": 2405.03, "word": ",", "probability": 0.50439453125 }, { "start": 2405.03, "end": 2405.39, "word": " Shift", "probability": 0.2220458984375 }, { "start": 2405.39, "end": 2405.79, "word": "-Enter", "probability": 0.6447957356770834 }, { "start": 2405.79, "end": 2406.23, "word": ",", "probability": 0.61328125 }, { "start": 2406.23, "end": 2406.97, "word": " and", "probability": 0.89208984375 }, { "start": 2406.97, "end": 2407.29, "word": " we", "probability": 0.90283203125 }, { "start": 2407.29, "end": 2407.45, "word": " can", "probability": 0.8974609375 }, { "start": 2407.45, "end": 2407.71, "word": " see", "probability": 0.8134765625 }, { "start": 2407.71, "end": 2407.93, "word": " the", "probability": 0.802734375 }, { "start": 2407.93, "end": 2408.23, "word": " counts", "probability": 0.432861328125 }, { "start": 2408.23, "end": 2408.35, "word": ".", "probability": 0.90087890625 } ] }, { "id": 1141, "seek": 239998, "start": 2408.35, "end": 2411.49, "text": " So we have East Asian font, Lenny, thanks, support.", "tokens": [ 50364, 407, 321, 362, 6747, 10645, 10703, 11, 23009, 1634, 11, 3231, 11, 1406, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.241421563076038, "compression_ratio": 1.6064814814814814, "no_speech_prob": 0.054168701171875, "words": [ { "start": 2408.35, "end": 2408.39, "word": " So", "probability": 0.42822265625 }, { "start": 2408.39, "end": 2408.47, "word": " we", "probability": 0.82080078125 }, { "start": 2408.47, "end": 2408.61, "word": " have", "probability": 0.88427734375 }, { "start": 2408.61, "end": 2408.93, "word": " East", "probability": 0.5595703125 }, { "start": 2408.93, "end": 2409.23, "word": " Asian", "probability": 0.7080078125 }, { "start": 2409.23, "end": 2409.65, "word": " font", "probability": 0.67333984375 }, { "start": 2409.65, "end": 2409.77, "word": ",", "probability": 0.2396240234375 }, { "start": 2409.77, "end": 2410.05, "word": " Lenny", "probability": 0.7354736328125 }, { "start": 2410.05, "end": 2410.21, "word": ",", "probability": 0.7041015625 }, { "start": 2410.21, "end": 2410.47, "word": " thanks", "probability": 0.376220703125 }, { "start": 2410.47, "end": 2410.55, "word": ",", "probability": 0.468994140625 }, { "start": 2410.55, "end": 2410.97, "word": " support", "probability": 0.90283203125 }, { "start": 2410.97, "end": 2411.49, "word": ".", "probability": 0.935546875 } ] }, { "id": 1142, "seek": 239998, "start": 2411.83, "end": 2417.71, "text": " Each of these, we have our unique words, they only show up once in our email.", "tokens": [ 50514, 6947, 295, 613, 11, 321, 362, 527, 3845, 2283, 11, 436, 787, 855, 493, 1564, 294, 527, 3796, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.241421563076038, "compression_ratio": 1.6064814814814814, "no_speech_prob": 0.054168701171875, "words": [ { "start": 2411.83, "end": 2412.25, "word": " Each", "probability": 0.818359375 }, { "start": 2412.25, "end": 2412.39, "word": " of", "probability": 0.9013671875 }, { "start": 2412.39, "end": 2412.77, "word": " these", "probability": 0.7158203125 }, { "start": 2412.77, "end": 2412.97, "word": ",", "probability": 0.515625 }, { "start": 2412.97, "end": 2413.05, "word": " we", "probability": 0.89013671875 }, { "start": 2413.05, "end": 2413.61, "word": " have", "probability": 0.8828125 }, { "start": 2413.61, "end": 2414.79, "word": " our", "probability": 0.7666015625 }, { "start": 2414.79, "end": 2415.17, "word": " unique", "probability": 0.78564453125 }, { "start": 2415.17, "end": 2415.57, "word": " words", "probability": 0.73974609375 }, { "start": 2415.57, "end": 2415.63, "word": ",", "probability": 0.34912109375 }, { "start": 2415.63, "end": 2415.73, "word": " they", "probability": 0.72607421875 }, { "start": 2415.73, "end": 2415.87, "word": " only", "probability": 0.8720703125 }, { "start": 2415.87, "end": 2416.15, "word": " show", "probability": 0.892578125 }, { "start": 2416.15, "end": 2416.31, "word": " up", "probability": 0.921875 }, { "start": 2416.31, "end": 2416.77, "word": " once", "probability": 0.81298828125 }, { "start": 2416.77, "end": 2416.95, "word": " in", "probability": 0.90087890625 }, { "start": 2416.95, "end": 2417.09, "word": " our", "probability": 0.81298828125 }, { "start": 2417.09, "end": 2417.43, "word": " email", "probability": 0.88623046875 }, { "start": 2417.43, "end": 2417.71, "word": ".", "probability": 0.82568359375 } ] }, { "id": 1143, "seek": 239998, "start": 2417.71, "end": 2423.83, "text": " The only two that are outliers is unsubscribe, or unsubscrib, after our stemmer.", "tokens": [ 50814, 440, 787, 732, 300, 366, 484, 23646, 307, 2693, 9493, 11, 420, 2693, 5432, 1142, 65, 11, 934, 527, 12312, 936, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.241421563076038, "compression_ratio": 1.6064814814814814, "no_speech_prob": 0.054168701171875, "words": [ { "start": 2417.71, "end": 2417.99, "word": " The", "probability": 0.80712890625 }, { "start": 2417.99, "end": 2418.11, "word": " only", "probability": 0.857421875 }, { "start": 2418.11, "end": 2418.37, "word": " two", "probability": 0.8173828125 }, { "start": 2418.37, "end": 2418.61, "word": " that", "probability": 0.8828125 }, { "start": 2418.61, "end": 2418.83, "word": " are", "probability": 0.8759765625 }, { "start": 2418.83, "end": 2419.39, "word": " outliers", "probability": 0.874267578125 }, { "start": 2419.39, "end": 2419.85, "word": " is", "probability": 0.865234375 }, { "start": 2419.85, "end": 2420.63, "word": " unsubscribe", "probability": 0.839111328125 }, { "start": 2420.63, "end": 2420.85, "word": ",", "probability": 0.160888671875 }, { "start": 2420.85, "end": 2420.95, "word": " or", "probability": 0.8779296875 }, { "start": 2420.95, "end": 2421.79, "word": " unsubscrib", "probability": 0.66461181640625 }, { "start": 2421.79, "end": 2422.39, "word": ",", "probability": 0.57958984375 }, { "start": 2422.39, "end": 2423.15, "word": " after", "probability": 0.7314453125 }, { "start": 2423.15, "end": 2423.35, "word": " our", "probability": 0.75439453125 }, { "start": 2423.35, "end": 2423.67, "word": " stemmer", "probability": 0.7144775390625 }, { "start": 2423.67, "end": 2423.83, "word": ".", "probability": 0.2235107421875 } ] }, { "id": 1144, "seek": 239998, "start": 2423.83, "end": 2428.89, "text": " And this list.debian.org, they show up twice in our email.", "tokens": [ 51114, 400, 341, 1329, 13, 1479, 20196, 13, 4646, 11, 436, 855, 493, 6091, 294, 527, 3796, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.241421563076038, "compression_ratio": 1.6064814814814814, "no_speech_prob": 0.054168701171875, "words": [ { "start": 2423.83, "end": 2423.99, "word": " And", "probability": 0.873046875 }, { "start": 2423.99, "end": 2424.29, "word": " this", "probability": 0.9052734375 }, { "start": 2424.29, "end": 2424.65, "word": " list", "probability": 0.81494140625 }, { "start": 2424.65, "end": 2425.11, "word": ".debian", "probability": 0.8401692708333334 }, { "start": 2425.11, "end": 2426.49, "word": ".org", "probability": 0.97119140625 }, { "start": 2426.49, "end": 2426.77, "word": ",", "probability": 0.6875 }, { "start": 2426.77, "end": 2427.13, "word": " they", "probability": 0.73046875 }, { "start": 2427.13, "end": 2427.33, "word": " show", "probability": 0.8759765625 }, { "start": 2427.33, "end": 2427.47, "word": " up", "probability": 0.912109375 }, { "start": 2427.47, "end": 2427.81, "word": " twice", "probability": 0.85888671875 }, { "start": 2427.81, "end": 2427.95, "word": " in", "probability": 0.90087890625 }, { "start": 2427.95, "end": 2428.07, "word": " our", "probability": 0.81982421875 }, { "start": 2428.07, "end": 2428.37, "word": " email", "probability": 0.90771484375 }, { "start": 2428.37, "end": 2428.89, "word": ".", "probability": 0.99755859375 } ] }, { "id": 1145, "seek": 239998, "start": 2428.89, "end": 2433.03, "text": " So this is if we manually counted these, but what if we used our vectorizers?", "tokens": [ 51364, 407, 341, 307, 498, 321, 16945, 20150, 613, 11, 457, 437, 498, 321, 1143, 527, 8062, 22525, 30, 51614 ], "temperature": 0.0, "avg_logprob": -0.241421563076038, "compression_ratio": 1.6064814814814814, "no_speech_prob": 0.054168701171875, "words": [ { "start": 2428.89, "end": 2429.07, "word": " So", "probability": 0.880859375 }, { "start": 2429.07, "end": 2429.21, "word": " this", "probability": 0.86181640625 }, { "start": 2429.21, "end": 2429.31, "word": " is", "probability": 0.896484375 }, { "start": 2429.31, "end": 2429.45, "word": " if", "probability": 0.90478515625 }, { "start": 2429.45, "end": 2429.55, "word": " we", "probability": 0.89501953125 }, { "start": 2429.55, "end": 2430.09, "word": " manually", "probability": 0.8505859375 }, { "start": 2430.09, "end": 2430.51, "word": " counted", "probability": 0.7568359375 }, { "start": 2430.51, "end": 2430.87, "word": " these", "probability": 0.71533203125 }, { "start": 2430.87, "end": 2430.97, "word": ",", "probability": 0.50537109375 }, { "start": 2430.97, "end": 2431.07, "word": " but", "probability": 0.90234375 }, { "start": 2431.07, "end": 2431.21, "word": " what", "probability": 0.888671875 }, { "start": 2431.21, "end": 2431.31, "word": " if", "probability": 0.90576171875 }, { "start": 2431.31, "end": 2431.41, "word": " we", "probability": 0.9052734375 }, { "start": 2431.41, "end": 2431.61, "word": " used", "probability": 0.71484375 }, { "start": 2431.61, "end": 2431.75, "word": " our", "probability": 0.81982421875 }, { "start": 2431.75, "end": 2432.51, "word": " vectorizers", "probability": 0.937255859375 }, { "start": 2432.51, "end": 2433.03, "word": "?", "probability": 0.92041015625 } ] }, { "id": 1146, "seek": 242410, "start": 2433.77, "end": 2438.47, "text": " So what we're going to do here in Task 3B is create new vectorizers,", "tokens": [ 50414, 407, 437, 321, 434, 516, 281, 360, 510, 294, 30428, 805, 33, 307, 1884, 777, 8062, 22525, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.24769176441160115, "compression_ratio": 1.6954022988505748, "no_speech_prob": 0.039031982421875, "words": [ { "start": 2433.77, "end": 2434.33, "word": " So", "probability": 0.75244140625 }, { "start": 2434.33, "end": 2434.47, "word": " what", "probability": 0.7529296875 }, { "start": 2434.47, "end": 2434.57, "word": " we're", "probability": 0.91650390625 }, { "start": 2434.57, "end": 2434.65, "word": " going", "probability": 0.34765625 }, { "start": 2434.65, "end": 2434.71, "word": " to", "probability": 0.90576171875 }, { "start": 2434.71, "end": 2434.83, "word": " do", "probability": 0.91552734375 }, { "start": 2434.83, "end": 2435.05, "word": " here", "probability": 0.79833984375 }, { "start": 2435.05, "end": 2435.27, "word": " in", "probability": 0.8857421875 }, { "start": 2435.27, "end": 2435.57, "word": " Task", "probability": 0.2178955078125 }, { "start": 2435.57, "end": 2436.17, "word": " 3B", "probability": 0.79541015625 }, { "start": 2436.17, "end": 2436.93, "word": " is", "probability": 0.7958984375 }, { "start": 2436.93, "end": 2437.23, "word": " create", "probability": 0.83447265625 }, { "start": 2437.23, "end": 2437.49, "word": " new", "probability": 0.8017578125 }, { "start": 2437.49, "end": 2438.21, "word": " vectorizers", "probability": 0.92041015625 }, { "start": 2438.21, "end": 2438.47, "word": ",", "probability": 0.6689453125 } ] }, { "id": 1147, "seek": 242410, "start": 2438.47, "end": 2440.77, "text": " the count vectorizer and TF-IDF vectorizer,", "tokens": [ 50614, 264, 1207, 8062, 6545, 293, 40964, 12, 2777, 37, 8062, 6545, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.24769176441160115, "compression_ratio": 1.6954022988505748, "no_speech_prob": 0.039031982421875, "words": [ { "start": 2438.47, "end": 2438.55, "word": " the", "probability": 0.78759765625 }, { "start": 2438.55, "end": 2438.73, "word": " count", "probability": 0.410888671875 }, { "start": 2438.73, "end": 2439.13, "word": " vectorizer", "probability": 0.860107421875 }, { "start": 2439.13, "end": 2439.25, "word": " and", "probability": 0.84912109375 }, { "start": 2439.25, "end": 2439.47, "word": " TF", "probability": 0.38671875 }, { "start": 2439.47, "end": 2439.85, "word": "-IDF", "probability": 0.859375 }, { "start": 2439.85, "end": 2440.43, "word": " vectorizer", "probability": 0.942626953125 }, { "start": 2440.43, "end": 2440.77, "word": ",", "probability": 0.48876953125 } ] }, { "id": 1148, "seek": 242410, "start": 2440.77, "end": 2447.43, "text": " and then we're going to print out the counts that each of them represent.", "tokens": [ 50764, 293, 550, 321, 434, 516, 281, 4482, 484, 264, 14893, 300, 1184, 295, 552, 2906, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.24769176441160115, "compression_ratio": 1.6954022988505748, "no_speech_prob": 0.039031982421875, "words": [ { "start": 2440.77, "end": 2441.15, "word": " and", "probability": 0.8876953125 }, { "start": 2441.15, "end": 2441.33, "word": " then", "probability": 0.7353515625 }, { "start": 2441.33, "end": 2441.61, "word": " we're", "probability": 0.924560546875 }, { "start": 2441.61, "end": 2441.85, "word": " going", "probability": 0.85888671875 }, { "start": 2441.85, "end": 2442.47, "word": " to", "probability": 0.90673828125 }, { "start": 2442.47, "end": 2443.41, "word": " print", "probability": 0.85546875 }, { "start": 2443.41, "end": 2443.79, "word": " out", "probability": 0.80859375 }, { "start": 2443.79, "end": 2444.67, "word": " the", "probability": 0.81201171875 }, { "start": 2444.67, "end": 2445.13, "word": " counts", "probability": 0.76611328125 }, { "start": 2445.13, "end": 2445.57, "word": " that", "probability": 0.87841796875 }, { "start": 2445.57, "end": 2445.89, "word": " each", "probability": 0.86474609375 }, { "start": 2445.89, "end": 2446.09, "word": " of", "probability": 0.90673828125 }, { "start": 2446.09, "end": 2446.37, "word": " them", "probability": 0.74169921875 }, { "start": 2446.37, "end": 2446.87, "word": " represent", "probability": 0.75341796875 }, { "start": 2446.87, "end": 2447.43, "word": ".", "probability": 0.98779296875 } ] }, { "id": 1149, "seek": 242410, "start": 2447.67, "end": 2451.95, "text": " So in the first one here, I'll just call this example-cvec,", "tokens": [ 51064, 407, 294, 264, 700, 472, 510, 11, 286, 603, 445, 818, 341, 1365, 12, 66, 303, 66, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.24769176441160115, "compression_ratio": 1.6954022988505748, "no_speech_prob": 0.039031982421875, "words": [ { "start": 2447.67, "end": 2447.89, "word": " So", "probability": 0.85888671875 }, { "start": 2447.89, "end": 2447.97, "word": " in", "probability": 0.50634765625 }, { "start": 2447.97, "end": 2448.03, "word": " the", "probability": 0.8134765625 }, { "start": 2448.03, "end": 2448.21, "word": " first", "probability": 0.81640625 }, { "start": 2448.21, "end": 2448.37, "word": " one", "probability": 0.81298828125 }, { "start": 2448.37, "end": 2448.61, "word": " here", "probability": 0.80078125 }, { "start": 2448.61, "end": 2448.67, "word": ",", "probability": 0.69775390625 }, { "start": 2448.67, "end": 2448.77, "word": " I'll", "probability": 0.96728515625 }, { "start": 2448.77, "end": 2448.91, "word": " just", "probability": 0.8818359375 }, { "start": 2448.91, "end": 2449.11, "word": " call", "probability": 0.80517578125 }, { "start": 2449.11, "end": 2449.47, "word": " this", "probability": 0.88427734375 }, { "start": 2449.47, "end": 2450.53, "word": " example", "probability": 0.51025390625 }, { "start": 2450.53, "end": 2451.75, "word": "-cvec", "probability": 0.615234375 }, { "start": 2451.75, "end": 2451.95, "word": ",", "probability": 0.5615234375 } ] }, { "id": 1150, "seek": 242410, "start": 2451.95, "end": 2457.15, "text": " and then we're going to define a new vectorizer.", "tokens": [ 51314, 293, 550, 321, 434, 516, 281, 6964, 257, 777, 8062, 6545, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.24769176441160115, "compression_ratio": 1.6954022988505748, "no_speech_prob": 0.039031982421875, "words": [ { "start": 2451.95, "end": 2452.47, "word": " and", "probability": 0.884765625 }, { "start": 2452.47, "end": 2452.57, "word": " then", "probability": 0.71630859375 }, { "start": 2452.57, "end": 2452.73, "word": " we're", "probability": 0.929443359375 }, { "start": 2452.73, "end": 2452.89, "word": " going", "probability": 0.857421875 }, { "start": 2452.89, "end": 2453.35, "word": " to", "probability": 0.90380859375 }, { "start": 2453.35, "end": 2454.35, "word": " define", "probability": 0.90576171875 }, { "start": 2454.81, "end": 2455.43, "word": " a new", "probability": 0.81884765625 }, { "start": 2455.43, "end": 2456.59, "word": " vectorizer", "probability": 0.943115234375 }, { "start": 2456.59, "end": 2457.15, "word": ".", "probability": 0.62646484375 } ] }, { "id": 1151, "seek": 244736, "start": 2462.22, "end": 2473.76, "text": " And I'll just call this example-x equals example-cvec.fit-transform.", "tokens": [ 50414, 400, 286, 603, 445, 818, 341, 1365, 12, 87, 6915, 1365, 12, 66, 303, 66, 13, 6845, 12, 24999, 837, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.22564338125726757, "compression_ratio": 1.4697986577181208, "no_speech_prob": 0.0206451416015625, "words": [ { "start": 2462.22, "end": 2462.74, "word": " And", "probability": 0.478515625 }, { "start": 2462.74, "end": 2462.92, "word": " I'll", "probability": 0.5960693359375 }, { "start": 2462.92, "end": 2463.06, "word": " just", "probability": 0.89013671875 }, { "start": 2463.06, "end": 2463.28, "word": " call", "probability": 0.81494140625 }, { "start": 2463.28, "end": 2463.66, "word": " this", "probability": 0.88134765625 }, { "start": 2463.66, "end": 2464.94, "word": " example", "probability": 0.67138671875 }, { "start": 2464.94, "end": 2465.74, "word": "-x", "probability": 0.436065673828125 }, { "start": 2465.74, "end": 2467.14, "word": " equals", "probability": 0.490966796875 }, { "start": 2467.14, "end": 2468.18, "word": " example", "probability": 0.86279296875 }, { "start": 2468.18, "end": 2469.98, "word": "-cvec", "probability": 0.7620849609375 }, { "start": 2469.98, "end": 2471.82, "word": ".fit", "probability": 0.8974609375 }, { "start": 2471.82, "end": 2473.32, "word": "-transform", "probability": 0.6763509114583334 }, { "start": 2473.32, "end": 2473.76, "word": ".", "probability": 0.64208984375 } ] }, { "id": 1152, "seek": 244736, "start": 2474.34, "end": 2478.1, "text": " And then it expects a list, our email is a string,", "tokens": [ 51014, 400, 550, 309, 33280, 257, 1329, 11, 527, 3796, 307, 257, 6798, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.22564338125726757, "compression_ratio": 1.4697986577181208, "no_speech_prob": 0.0206451416015625, "words": [ { "start": 2474.34, "end": 2474.86, "word": " And", "probability": 0.8935546875 }, { "start": 2474.86, "end": 2475.06, "word": " then", "probability": 0.73876953125 }, { "start": 2475.06, "end": 2475.26, "word": " it", "probability": 0.79931640625 }, { "start": 2475.26, "end": 2475.6, "word": " expects", "probability": 0.751953125 }, { "start": 2475.86, "end": 2476.24, "word": " a list", "probability": 0.8935546875 }, { "start": 2476.24, "end": 2476.36, "word": ",", "probability": 0.340576171875 }, { "start": 2476.36, "end": 2476.52, "word": " our", "probability": 0.79833984375 }, { "start": 2476.52, "end": 2476.78, "word": " email", "probability": 0.89697265625 }, { "start": 2476.78, "end": 2477.22, "word": " is", "probability": 0.900390625 }, { "start": 2477.42, "end": 2477.88, "word": " a string", "probability": 0.75537109375 }, { "start": 2477.88, "end": 2478.1, "word": ",", "probability": 0.55078125 } ] }, { "id": 1153, "seek": 244736, "start": 2478.1, "end": 2480.7, "text": " so we're going to wrap it in these square brackets.", "tokens": [ 51214, 370, 321, 434, 516, 281, 7019, 309, 294, 613, 3732, 26179, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.22564338125726757, "compression_ratio": 1.4697986577181208, "no_speech_prob": 0.0206451416015625, "words": [ { "start": 2478.1, "end": 2478.3, "word": " so", "probability": 0.8984375 }, { "start": 2478.3, "end": 2478.54, "word": " we're", "probability": 0.919189453125 }, { "start": 2478.54, "end": 2478.62, "word": " going", "probability": 0.16455078125 }, { "start": 2478.62, "end": 2478.72, "word": " to", "probability": 0.90966796875 }, { "start": 2478.72, "end": 2478.98, "word": " wrap", "probability": 0.830078125 }, { "start": 2478.98, "end": 2479.08, "word": " it", "probability": 0.90185546875 }, { "start": 2479.08, "end": 2479.2, "word": " in", "probability": 0.90673828125 }, { "start": 2479.2, "end": 2479.4, "word": " these", "probability": 0.671875 }, { "start": 2479.4, "end": 2479.66, "word": " square", "probability": 0.87255859375 }, { "start": 2479.66, "end": 2480.18, "word": " brackets", "probability": 0.7939453125 }, { "start": 2480.18, "end": 2480.7, "word": ".", "probability": 0.62451171875 } ] }, { "id": 1154, "seek": 244736, "start": 2481.0, "end": 2483.6, "text": " And we're just going to use our raw test email.", "tokens": [ 51364, 400, 321, 434, 445, 516, 281, 764, 527, 8936, 1500, 3796, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.22564338125726757, "compression_ratio": 1.4697986577181208, "no_speech_prob": 0.0206451416015625, "words": [ { "start": 2481.0, "end": 2481.06, "word": " And", "probability": 0.61669921875 }, { "start": 2481.06, "end": 2481.26, "word": " we're", "probability": 0.920166015625 }, { "start": 2481.26, "end": 2481.38, "word": " just", "probability": 0.88134765625 }, { "start": 2481.38, "end": 2481.54, "word": " going", "probability": 0.7900390625 }, { "start": 2481.54, "end": 2481.6, "word": " to", "probability": 0.90869140625 }, { "start": 2481.6, "end": 2481.76, "word": " use", "probability": 0.83740234375 }, { "start": 2481.76, "end": 2481.9, "word": " our", "probability": 0.8212890625 }, { "start": 2481.9, "end": 2482.24, "word": " raw", "probability": 0.73876953125 }, { "start": 2482.24, "end": 2482.62, "word": " test", "probability": 0.7177734375 }, { "start": 2482.62, "end": 2483.08, "word": " email", "probability": 0.89794921875 }, { "start": 2483.08, "end": 2483.6, "word": ".", "probability": 0.955078125 } ] }, { "id": 1155, "seek": 247660, "start": 2486.08, "end": 2490.96, "text": " And then we're going to want to print our example-x.", "tokens": [ 50414, 400, 550, 321, 434, 516, 281, 528, 281, 4482, 527, 1365, 12, 87, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.175951080477756, "compression_ratio": 1.6933962264150944, "no_speech_prob": 0.008575439453125, "words": [ { "start": 2486.08, "end": 2486.5, "word": " And", "probability": 0.48046875 }, { "start": 2486.5, "end": 2486.6, "word": " then", "probability": 0.72119140625 }, { "start": 2486.6, "end": 2486.72, "word": " we're", "probability": 0.9033203125 }, { "start": 2486.72, "end": 2486.88, "word": " going", "probability": 0.8330078125 }, { "start": 2486.88, "end": 2487.06, "word": " to", "probability": 0.9033203125 }, { "start": 2487.06, "end": 2487.2, "word": " want", "probability": 0.63818359375 }, { "start": 2487.2, "end": 2487.38, "word": " to", "probability": 0.9052734375 }, { "start": 2487.38, "end": 2487.92, "word": " print", "probability": 0.86376953125 }, { "start": 2487.92, "end": 2488.8, "word": " our", "probability": 0.81494140625 }, { "start": 2488.8, "end": 2489.58, "word": " example", "probability": 0.8349609375 }, { "start": 2489.58, "end": 2490.54, "word": "-x", "probability": 0.403900146484375 }, { "start": 2490.54, "end": 2490.96, "word": ".", "probability": 0.912109375 } ] }, { "id": 1156, "seek": 247660, "start": 2493.14, "end": 2498.18, "text": " And we can easily just copy and paste, do the same thing for our TF-IDF code.", "tokens": [ 50814, 400, 321, 393, 3612, 445, 5055, 293, 9163, 11, 360, 264, 912, 551, 337, 527, 40964, 12, 2777, 37, 3089, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.175951080477756, "compression_ratio": 1.6933962264150944, "no_speech_prob": 0.008575439453125, "words": [ { "start": 2493.14, "end": 2493.56, "word": " And", "probability": 0.317626953125 }, { "start": 2493.56, "end": 2493.66, "word": " we", "probability": 0.8251953125 }, { "start": 2493.66, "end": 2493.8, "word": " can", "probability": 0.89111328125 }, { "start": 2493.8, "end": 2494.08, "word": " easily", "probability": 0.8681640625 }, { "start": 2494.08, "end": 2494.34, "word": " just", "probability": 0.88330078125 }, { "start": 2494.34, "end": 2494.66, "word": " copy", "probability": 0.8154296875 }, { "start": 2494.66, "end": 2494.86, "word": " and", "probability": 0.875 }, { "start": 2494.86, "end": 2495.16, "word": " paste", "probability": 0.74462890625 }, { "start": 2495.16, "end": 2495.26, "word": ",", "probability": 0.73974609375 }, { "start": 2495.26, "end": 2495.34, "word": " do", "probability": 0.89990234375 }, { "start": 2495.34, "end": 2495.52, "word": " the", "probability": 0.8115234375 }, { "start": 2495.52, "end": 2495.74, "word": " same", "probability": 0.81005859375 }, { "start": 2495.74, "end": 2496.08, "word": " thing", "probability": 0.8125 }, { "start": 2496.08, "end": 2496.44, "word": " for", "probability": 0.8876953125 }, { "start": 2496.44, "end": 2496.86, "word": " our", "probability": 0.806640625 }, { "start": 2496.86, "end": 2497.28, "word": " TF", "probability": 0.461181640625 }, { "start": 2497.28, "end": 2497.72, "word": "-IDF", "probability": 0.8777669270833334 }, { "start": 2497.72, "end": 2498.06, "word": " code", "probability": 0.8037109375 }, { "start": 2498.06, "end": 2498.18, "word": ".", "probability": 0.830078125 } ] }, { "id": 1157, "seek": 247660, "start": 2498.18, "end": 2503.7, "text": " We'll just call this example-tvec, we'll use the TF-IDF vectorizer,", "tokens": [ 51064, 492, 603, 445, 818, 341, 1365, 12, 83, 303, 66, 11, 321, 603, 764, 264, 40964, 12, 2777, 37, 8062, 6545, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.175951080477756, "compression_ratio": 1.6933962264150944, "no_speech_prob": 0.008575439453125, "words": [ { "start": 2498.18, "end": 2498.28, "word": " We'll", "probability": 0.917724609375 }, { "start": 2498.28, "end": 2498.42, "word": " just", "probability": 0.88671875 }, { "start": 2498.42, "end": 2498.6, "word": " call", "probability": 0.8251953125 }, { "start": 2498.6, "end": 2498.76, "word": " this", "probability": 0.8671875 }, { "start": 2498.76, "end": 2499.14, "word": " example", "probability": 0.9072265625 }, { "start": 2499.14, "end": 2499.88, "word": "-tvec", "probability": 0.652618408203125 }, { "start": 2499.88, "end": 2500.24, "word": ",", "probability": 0.19189453125 }, { "start": 2500.24, "end": 2500.7, "word": " we'll", "probability": 0.914794921875 }, { "start": 2500.7, "end": 2501.12, "word": " use", "probability": 0.81591796875 }, { "start": 2501.12, "end": 2501.44, "word": " the", "probability": 0.79736328125 }, { "start": 2501.44, "end": 2502.12, "word": " TF", "probability": 0.82958984375 }, { "start": 2502.12, "end": 2502.64, "word": "-IDF", "probability": 0.9728190104166666 }, { "start": 2502.64, "end": 2503.44, "word": " vectorizer", "probability": 0.908203125 }, { "start": 2503.44, "end": 2503.7, "word": ",", "probability": 0.7919921875 } ] }, { "id": 1158, "seek": 247660, "start": 2503.7, "end": 2508.12, "text": " tokenizer is tokenizer, we change this to tvec,", "tokens": [ 51314, 14862, 6545, 307, 14862, 6545, 11, 321, 1319, 341, 281, 256, 303, 66, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.175951080477756, "compression_ratio": 1.6933962264150944, "no_speech_prob": 0.008575439453125, "words": [ { "start": 2503.7, "end": 2504.16, "word": " tokenizer", "probability": 0.828369140625 }, { "start": 2504.16, "end": 2504.36, "word": " is", "probability": 0.61181640625 }, { "start": 2504.36, "end": 2504.92, "word": " tokenizer", "probability": 0.873046875 }, { "start": 2504.92, "end": 2505.98, "word": ",", "probability": 0.469970703125 }, { "start": 2505.98, "end": 2506.78, "word": " we", "probability": 0.78515625 }, { "start": 2506.78, "end": 2507.08, "word": " change", "probability": 0.802734375 }, { "start": 2507.08, "end": 2507.34, "word": " this", "probability": 0.88037109375 }, { "start": 2507.34, "end": 2507.54, "word": " to", "probability": 0.89892578125 }, { "start": 2507.54, "end": 2508.06, "word": " tvec", "probability": 0.9217122395833334 }, { "start": 2508.06, "end": 2508.12, "word": ",", "probability": 0.59619140625 } ] }, { "id": 1159, "seek": 247660, "start": 2508.12, "end": 2510.16, "text": " and then we're already done with our example-x,", "tokens": [ 51564, 293, 550, 321, 434, 1217, 1096, 365, 527, 1365, 12, 87, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.175951080477756, "compression_ratio": 1.6933962264150944, "no_speech_prob": 0.008575439453125, "words": [ { "start": 2508.12, "end": 2508.22, "word": " and", "probability": 0.8955078125 }, { "start": 2508.22, "end": 2508.32, "word": " then", "probability": 0.7236328125 }, { "start": 2508.32, "end": 2508.44, "word": " we're", "probability": 0.92822265625 }, { "start": 2508.44, "end": 2508.7, "word": " already", "probability": 0.83740234375 }, { "start": 2508.7, "end": 2508.98, "word": " done", "probability": 0.81298828125 }, { "start": 2508.98, "end": 2509.14, "word": " with", "probability": 0.81689453125 }, { "start": 2509.14, "end": 2509.3, "word": " our", "probability": 0.8115234375 }, { "start": 2509.3, "end": 2509.78, "word": " example", "probability": 0.91357421875 }, { "start": 2509.78, "end": 2510.1, "word": "-x", "probability": 0.986572265625 }, { "start": 2510.1, "end": 2510.16, "word": ",", "probability": 0.630859375 } ] }, { "id": 1160, "seek": 247660, "start": 2510.16, "end": 2512.84, "text": " so we don't need to change the name, we can just leave it as is.", "tokens": [ 51664, 370, 321, 500, 380, 643, 281, 1319, 264, 1315, 11, 321, 393, 445, 1856, 309, 382, 307, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.175951080477756, "compression_ratio": 1.6933962264150944, "no_speech_prob": 0.008575439453125, "words": [ { "start": 2510.16, "end": 2510.26, "word": " so", "probability": 0.89990234375 }, { "start": 2510.26, "end": 2510.34, "word": " we", "probability": 0.90087890625 }, { "start": 2510.34, "end": 2510.48, "word": " don't", "probability": 0.94873046875 }, { "start": 2510.48, "end": 2510.64, "word": " need", "probability": 0.81494140625 }, { "start": 2510.64, "end": 2510.78, "word": " to", "probability": 0.90380859375 }, { "start": 2510.78, "end": 2511.08, "word": " change", "probability": 0.833984375 }, { "start": 2511.08, "end": 2511.26, "word": " the", "probability": 0.8115234375 }, { "start": 2511.26, "end": 2511.44, "word": " name", "probability": 0.8037109375 }, { "start": 2511.44, "end": 2511.5, "word": ",", "probability": 0.71044921875 }, { "start": 2511.5, "end": 2511.58, "word": " we", "probability": 0.90283203125 }, { "start": 2511.58, "end": 2511.72, "word": " can", "probability": 0.8916015625 }, { "start": 2511.72, "end": 2511.92, "word": " just", "probability": 0.87939453125 }, { "start": 2511.92, "end": 2512.1, "word": " leave", "probability": 0.91455078125 }, { "start": 2512.1, "end": 2512.18, "word": " it", "probability": 0.90185546875 }, { "start": 2512.18, "end": 2512.38, "word": " as", "probability": 0.90087890625 }, { "start": 2512.38, "end": 2512.66, "word": " is", "probability": 0.734375 }, { "start": 2512.66, "end": 2512.84, "word": ".", "probability": 0.99609375 } ] }, { "id": 1161, "seek": 250600, "start": 2513.98, "end": 2518.44, "text": " Example-tvec, fit-transform, and then square brackets, test-email,", "tokens": [ 50414, 24755, 781, 12, 83, 303, 66, 11, 3318, 12, 24999, 837, 11, 293, 550, 3732, 26179, 11, 1500, 12, 443, 864, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.2567770990980677, "compression_ratio": 1.3854748603351956, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 2513.98, "end": 2514.62, "word": " Example", "probability": 0.58489990234375 }, { "start": 2514.62, "end": 2515.06, "word": "-tvec", "probability": 0.5220985412597656 }, { "start": 2515.06, "end": 2515.08, "word": ",", "probability": 0.409423828125 }, { "start": 2515.08, "end": 2515.26, "word": " fit", "probability": 0.70166015625 }, { "start": 2515.26, "end": 2515.96, "word": "-transform", "probability": 0.6722005208333334 }, { "start": 2515.96, "end": 2516.16, "word": ",", "probability": 0.7939453125 }, { "start": 2516.16, "end": 2516.22, "word": " and", "probability": 0.71875 }, { "start": 2516.22, "end": 2516.44, "word": " then", "probability": 0.7548828125 }, { "start": 2516.44, "end": 2516.78, "word": " square", "probability": 0.6015625 }, { "start": 2516.78, "end": 2517.3, "word": " brackets", "probability": 0.83740234375 }, { "start": 2517.3, "end": 2517.42, "word": ",", "probability": 0.449951171875 }, { "start": 2517.42, "end": 2517.76, "word": " test", "probability": 0.7548828125 }, { "start": 2517.76, "end": 2518.26, "word": "-email", "probability": 0.7435709635416666 }, { "start": 2518.26, "end": 2518.44, "word": ",", "probability": 0.5283203125 } ] }, { "id": 1162, "seek": 250600, "start": 2518.44, "end": 2519.94, "text": " so that it's a list.", "tokens": [ 50614, 370, 300, 309, 311, 257, 1329, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.2567770990980677, "compression_ratio": 1.3854748603351956, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 2518.44, "end": 2518.6, "word": " so", "probability": 0.8798828125 }, { "start": 2518.6, "end": 2518.7, "word": " that", "probability": 0.853515625 }, { "start": 2518.7, "end": 2518.86, "word": " it's", "probability": 0.942138671875 }, { "start": 2518.96, "end": 2519.3, "word": " a list", "probability": 0.87841796875 }, { "start": 2519.3, "end": 2519.94, "word": ".", "probability": 0.9228515625 } ] }, { "id": 1163, "seek": 250600, "start": 2520.86, "end": 2521.76, "text": " Yes.", "tokens": [ 50764, 1079, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.2567770990980677, "compression_ratio": 1.3854748603351956, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 2520.86, "end": 2521.12, "word": " Yes", "probability": 0.76806640625 }, { "start": 2521.12, "end": 2521.76, "word": ".", "probability": 0.55029296875 } ] }, { "id": 1164, "seek": 250600, "start": 2524.9, "end": 2527.8, "text": " Oh, it sounded like there was possibly a question.", "tokens": [ 50864, 876, 11, 309, 17714, 411, 456, 390, 6264, 257, 1168, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.2567770990980677, "compression_ratio": 1.3854748603351956, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 2524.9, "end": 2525.42, "word": " Oh", "probability": 0.7294921875 }, { "start": 2525.42, "end": 2525.44, "word": ",", "probability": 0.83837890625 }, { "start": 2525.44, "end": 2525.54, "word": " it", "probability": 0.89404296875 }, { "start": 2525.54, "end": 2525.74, "word": " sounded", "probability": 0.66552734375 }, { "start": 2525.74, "end": 2525.94, "word": " like", "probability": 0.8818359375 }, { "start": 2525.94, "end": 2526.06, "word": " there", "probability": 0.8515625 }, { "start": 2526.06, "end": 2526.22, "word": " was", "probability": 0.89599609375 }, { "start": 2526.22, "end": 2526.76, "word": " possibly", "probability": 0.7060546875 }, { "start": 2526.9, "end": 2527.16, "word": " a question", "probability": 0.78955078125 }, { "start": 2527.16, "end": 2527.8, "word": ".", "probability": 0.96826171875 } ] }, { "id": 1165, "seek": 250600, "start": 2533.19, "end": 2538.51, "text": " So Voto on the stream is asking, where are those workbooks again?", "tokens": [ 51164, 407, 691, 6738, 322, 264, 4309, 307, 3365, 11, 689, 366, 729, 589, 15170, 797, 30, 51414 ], "temperature": 0.0, "avg_logprob": -0.2567770990980677, "compression_ratio": 1.3854748603351956, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 2533.19, "end": 2533.83, "word": " So", "probability": 0.78759765625 }, { "start": 2533.83, "end": 2534.47, "word": " Voto", "probability": 0.6248779296875 }, { "start": 2534.47, "end": 2535.07, "word": " on", "probability": 0.88037109375 }, { "start": 2535.07, "end": 2535.37, "word": " the", "probability": 0.80078125 }, { "start": 2535.37, "end": 2535.93, "word": " stream", "probability": 0.86328125 }, { "start": 2535.93, "end": 2536.25, "word": " is", "probability": 0.90087890625 }, { "start": 2536.25, "end": 2536.63, "word": " asking", "probability": 0.81689453125 }, { "start": 2536.63, "end": 2536.97, "word": ",", "probability": 0.6708984375 }, { "start": 2536.97, "end": 2537.05, "word": " where", "probability": 0.31689453125 }, { "start": 2537.05, "end": 2537.21, "word": " are", "probability": 0.890625 }, { "start": 2537.21, "end": 2537.39, "word": " those", "probability": 0.8603515625 }, { "start": 2537.39, "end": 2537.87, "word": " workbooks", "probability": 0.88330078125 }, { "start": 2537.87, "end": 2538.19, "word": " again", "probability": 0.8828125 }, { "start": 2538.19, "end": 2538.51, "word": "?", "probability": 0.96240234375 } ] }, { "id": 1166, "seek": 250600, "start": 2544.05, "end": 2548.07, "text": " Can one of the TAs post in the stream?", "tokens": [ 51614, 1664, 472, 295, 264, 314, 10884, 2183, 294, 264, 4309, 30, 51814 ], "temperature": 0.0, "avg_logprob": -0.2567770990980677, "compression_ratio": 1.3854748603351956, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 2544.05, "end": 2544.69, "word": " Can", "probability": 0.845703125 }, { "start": 2544.69, "end": 2545.33, "word": " one", "probability": 0.80712890625 }, { "start": 2545.33, "end": 2545.41, "word": " of", "probability": 0.90380859375 }, { "start": 2545.41, "end": 2545.53, "word": " the", "probability": 0.8134765625 }, { "start": 2545.53, "end": 2545.91, "word": " TAs", "probability": 0.862548828125 }, { "start": 2545.91, "end": 2546.45, "word": " post", "probability": 0.83642578125 }, { "start": 2546.45, "end": 2546.79, "word": " in", "probability": 0.900390625 }, { "start": 2546.79, "end": 2546.97, "word": " the", "probability": 0.7998046875 }, { "start": 2546.97, "end": 2547.43, "word": " stream", "probability": 0.88232421875 }, { "start": 2547.43, "end": 2548.07, "word": "?", "probability": 0.51025390625 } ] }, { "id": 1167, "seek": 253168, "start": 2548.07, "end": 2549.75, "text": " There you go, perfect.", "tokens": [ 50364, 821, 291, 352, 11, 2176, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.21498326185558522, "compression_ratio": 1.613821138211382, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 2548.07, "end": 2548.33, "word": " There", "probability": 0.48583984375 }, { "start": 2548.33, "end": 2548.43, "word": " you", "probability": 0.8896484375 }, { "start": 2548.43, "end": 2548.67, "word": " go", "probability": 0.90576171875 }, { "start": 2548.67, "end": 2548.81, "word": ",", "probability": 0.38037109375 }, { "start": 2548.81, "end": 2549.31, "word": " perfect", "probability": 0.84033203125 }, { "start": 2549.31, "end": 2549.75, "word": ".", "probability": 0.427734375 } ] }, { "id": 1168, "seek": 253168, "start": 2550.27, "end": 2552.17, "text": " Machine learning for a security analyst.", "tokens": [ 50464, 22155, 2539, 337, 257, 3825, 19085, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.21498326185558522, "compression_ratio": 1.613821138211382, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 2550.27, "end": 2550.53, "word": " Machine", "probability": 0.5751953125 }, { "start": 2550.53, "end": 2550.77, "word": " learning", "probability": 0.576171875 }, { "start": 2550.77, "end": 2550.97, "word": " for", "probability": 0.896484375 }, { "start": 2551.09, "end": 2551.29, "word": " a security", "probability": 0.91162109375 }, { "start": 2551.29, "end": 2551.73, "word": " analyst", "probability": 0.57958984375 }, { "start": 2551.73, "end": 2552.17, "word": ".", "probability": 0.9677734375 } ] }, { "id": 1169, "seek": 253168, "start": 2553.53, "end": 2557.83, "text": " Okay, so I'm going to go ahead and run this.", "tokens": [ 50614, 1033, 11, 370, 286, 478, 516, 281, 352, 2286, 293, 1190, 341, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.21498326185558522, "compression_ratio": 1.613821138211382, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 2553.53, "end": 2553.69, "word": " Okay", "probability": 0.41943359375 }, { "start": 2553.69, "end": 2554.03, "word": ",", "probability": 0.712890625 }, { "start": 2554.03, "end": 2554.41, "word": " so", "probability": 0.8564453125 }, { "start": 2554.41, "end": 2554.87, "word": " I'm", "probability": 0.937255859375 }, { "start": 2554.87, "end": 2555.11, "word": " going", "probability": 0.857421875 }, { "start": 2555.11, "end": 2555.71, "word": " to", "probability": 0.90673828125 }, { "start": 2555.71, "end": 2556.17, "word": " go", "probability": 0.88720703125 }, { "start": 2556.17, "end": 2556.45, "word": " ahead", "probability": 0.8525390625 }, { "start": 2556.45, "end": 2556.75, "word": " and", "probability": 0.89599609375 }, { "start": 2556.75, "end": 2556.99, "word": " run", "probability": 0.89990234375 }, { "start": 2556.99, "end": 2557.39, "word": " this", "probability": 0.88232421875 }, { "start": 2557.39, "end": 2557.83, "word": ".", "probability": 0.810546875 } ] }, { "id": 1170, "seek": 253168, "start": 2558.57, "end": 2561.03, "text": " Scroll up, let's take a look at the count vectorizer.", "tokens": [ 50864, 35395, 493, 11, 718, 311, 747, 257, 574, 412, 264, 1207, 8062, 6545, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.21498326185558522, "compression_ratio": 1.613821138211382, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 2558.57, "end": 2558.91, "word": " Scroll", "probability": 0.671875 }, { "start": 2558.91, "end": 2559.09, "word": " up", "probability": 0.89404296875 }, { "start": 2559.09, "end": 2559.13, "word": ",", "probability": 0.5625 }, { "start": 2559.13, "end": 2559.27, "word": " let's", "probability": 0.90869140625 }, { "start": 2559.27, "end": 2559.41, "word": " take", "probability": 0.8212890625 }, { "start": 2559.49, "end": 2559.55, "word": " a look", "probability": 0.91552734375 }, { "start": 2559.55, "end": 2559.65, "word": " at", "probability": 0.89990234375 }, { "start": 2559.65, "end": 2559.79, "word": " the", "probability": 0.8134765625 }, { "start": 2559.79, "end": 2560.03, "word": " count", "probability": 0.6630859375 }, { "start": 2560.03, "end": 2560.59, "word": " vectorizer", "probability": 0.916015625 }, { "start": 2560.59, "end": 2561.03, "word": ".", "probability": 0.96044921875 } ] }, { "id": 1171, "seek": 253168, "start": 2561.13, "end": 2563.69, "text": " So instead of seeing the words, we see these numbers,", "tokens": [ 51014, 407, 2602, 295, 2577, 264, 2283, 11, 321, 536, 613, 3547, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.21498326185558522, "compression_ratio": 1.613821138211382, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 2561.13, "end": 2561.31, "word": " So", "probability": 0.83251953125 }, { "start": 2561.31, "end": 2561.51, "word": " instead", "probability": 0.7548828125 }, { "start": 2561.51, "end": 2561.65, "word": " of", "probability": 0.9072265625 }, { "start": 2561.65, "end": 2561.81, "word": " seeing", "probability": 0.70947265625 }, { "start": 2561.81, "end": 2561.99, "word": " the", "probability": 0.810546875 }, { "start": 2561.99, "end": 2562.27, "word": " words", "probability": 0.71923828125 }, { "start": 2562.27, "end": 2562.33, "word": ",", "probability": 0.77197265625 }, { "start": 2562.33, "end": 2562.49, "word": " we", "probability": 0.9033203125 }, { "start": 2562.49, "end": 2562.67, "word": " see", "probability": 0.81787109375 }, { "start": 2562.67, "end": 2562.91, "word": " these", "probability": 0.7080078125 }, { "start": 2562.91, "end": 2563.39, "word": " numbers", "probability": 0.8642578125 }, { "start": 2563.39, "end": 2563.69, "word": ",", "probability": 0.400390625 } ] }, { "id": 1172, "seek": 253168, "start": 2563.69, "end": 2564.89, "text": " and that's exactly what we want.", "tokens": [ 51114, 293, 300, 311, 2293, 437, 321, 528, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.21498326185558522, "compression_ratio": 1.613821138211382, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 2563.69, "end": 2563.77, "word": " and", "probability": 0.896484375 }, { "start": 2563.77, "end": 2563.97, "word": " that's", "probability": 0.9404296875 }, { "start": 2563.97, "end": 2564.29, "word": " exactly", "probability": 0.771484375 }, { "start": 2564.29, "end": 2564.45, "word": " what", "probability": 0.8916015625 }, { "start": 2564.45, "end": 2564.57, "word": " we", "probability": 0.90380859375 }, { "start": 2564.57, "end": 2564.79, "word": " want", "probability": 0.80419921875 }, { "start": 2564.79, "end": 2564.89, "word": ".", "probability": 0.943359375 } ] }, { "id": 1173, "seek": 253168, "start": 2564.89, "end": 2567.09, "text": " We've created what are called tokens.", "tokens": [ 51214, 492, 600, 2942, 437, 366, 1219, 22667, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.21498326185558522, "compression_ratio": 1.613821138211382, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 2564.89, "end": 2565.13, "word": " We've", "probability": 0.804443359375 }, { "start": 2565.13, "end": 2565.53, "word": " created", "probability": 0.73974609375 }, { "start": 2565.53, "end": 2565.79, "word": " what", "probability": 0.86669921875 }, { "start": 2565.79, "end": 2565.89, "word": " are", "probability": 0.89404296875 }, { "start": 2565.89, "end": 2566.11, "word": " called", "probability": 0.810546875 }, { "start": 2566.11, "end": 2566.65, "word": " tokens", "probability": 0.70703125 }, { "start": 2566.65, "end": 2567.09, "word": ".", "probability": 0.861328125 } ] }, { "id": 1174, "seek": 253168, "start": 2567.33, "end": 2570.97, "text": " So the words themselves, the tokenizers will be able,", "tokens": [ 51314, 407, 264, 2283, 2969, 11, 264, 14862, 22525, 486, 312, 1075, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.21498326185558522, "compression_ratio": 1.613821138211382, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 2567.33, "end": 2567.35, "word": " So", "probability": 0.77734375 }, { "start": 2567.35, "end": 2568.81, "word": " the", "probability": 0.66015625 }, { "start": 2568.81, "end": 2569.03, "word": " words", "probability": 0.72021484375 }, { "start": 2569.03, "end": 2569.51, "word": " themselves", "probability": 0.7216796875 }, { "start": 2569.51, "end": 2569.73, "word": ",", "probability": 0.94140625 }, { "start": 2569.73, "end": 2569.79, "word": " the", "probability": 0.79833984375 }, { "start": 2569.79, "end": 2570.33, "word": " tokenizers", "probability": 0.89208984375 }, { "start": 2570.33, "end": 2570.53, "word": " will", "probability": 0.662109375 }, { "start": 2570.53, "end": 2570.65, "word": " be", "probability": 0.90576171875 }, { "start": 2570.65, "end": 2570.85, "word": " able", "probability": 0.8876953125 }, { "start": 2570.85, "end": 2570.97, "word": ",", "probability": 0.54296875 } ] }, { "id": 1175, "seek": 253168, "start": 2570.97, "end": 2573.75, "text": " or the vectorizers will be able to match them together.", "tokens": [ 51514, 420, 264, 8062, 22525, 486, 312, 1075, 281, 2995, 552, 1214, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.21498326185558522, "compression_ratio": 1.613821138211382, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 2570.97, "end": 2571.09, "word": " or", "probability": 0.88232421875 }, { "start": 2571.09, "end": 2571.21, "word": " the", "probability": 0.810546875 }, { "start": 2571.21, "end": 2571.75, "word": " vectorizers", "probability": 0.942626953125 }, { "start": 2571.75, "end": 2571.95, "word": " will", "probability": 0.71484375 }, { "start": 2571.95, "end": 2572.09, "word": " be", "probability": 0.90673828125 }, { "start": 2572.09, "end": 2572.23, "word": " able", "probability": 0.87646484375 }, { "start": 2572.23, "end": 2572.41, "word": " to", "probability": 0.84912109375 }, { "start": 2572.41, "end": 2572.71, "word": " match", "probability": 0.794921875 }, { "start": 2572.71, "end": 2572.93, "word": " them", "probability": 0.73095703125 }, { "start": 2572.93, "end": 2573.31, "word": " together", "probability": 0.78515625 }, { "start": 2573.31, "end": 2573.75, "word": ".", "probability": 0.97998046875 } ] }, { "id": 1176, "seek": 255992, "start": 2575.09, "end": 2579.87, "text": " So all of them are one in their count, all of them are unique,", "tokens": [ 50414, 407, 439, 295, 552, 366, 472, 294, 641, 1207, 11, 439, 295, 552, 366, 3845, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.19487028062905906, "compression_ratio": 1.7213930348258706, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 2575.09, "end": 2575.71, "word": " So", "probability": 0.334228515625 }, { "start": 2575.71, "end": 2575.93, "word": " all", "probability": 0.76513671875 }, { "start": 2575.93, "end": 2576.05, "word": " of", "probability": 0.8896484375 }, { "start": 2576.05, "end": 2576.19, "word": " them", "probability": 0.7373046875 }, { "start": 2576.19, "end": 2576.61, "word": " are", "probability": 0.88232421875 }, { "start": 2576.61, "end": 2577.55, "word": " one", "probability": 0.489013671875 }, { "start": 2577.55, "end": 2577.93, "word": " in", "probability": 0.84033203125 }, { "start": 2577.93, "end": 2578.09, "word": " their", "probability": 0.8994140625 }, { "start": 2578.09, "end": 2578.49, "word": " count", "probability": 0.479736328125 }, { "start": 2578.49, "end": 2578.67, "word": ",", "probability": 0.413330078125 }, { "start": 2578.67, "end": 2578.81, "word": " all", "probability": 0.86572265625 }, { "start": 2578.81, "end": 2578.89, "word": " of", "probability": 0.8916015625 }, { "start": 2578.89, "end": 2578.99, "word": " them", "probability": 0.73974609375 }, { "start": 2578.99, "end": 2579.11, "word": " are", "probability": 0.88232421875 }, { "start": 2579.11, "end": 2579.49, "word": " unique", "probability": 0.78466796875 }, { "start": 2579.49, "end": 2579.87, "word": ",", "probability": 0.505859375 } ] }, { "id": 1177, "seek": 255992, "start": 2579.87, "end": 2583.15, "text": " except for token 16 and token 9.", "tokens": [ 50664, 3993, 337, 14862, 3165, 293, 14862, 1722, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.19487028062905906, "compression_ratio": 1.7213930348258706, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 2579.87, "end": 2580.19, "word": " except", "probability": 0.8427734375 }, { "start": 2580.19, "end": 2580.67, "word": " for", "probability": 0.8974609375 }, { "start": 2580.67, "end": 2580.99, "word": " token", "probability": 0.6845703125 }, { "start": 2580.99, "end": 2581.47, "word": " 16", "probability": 0.6923828125 }, { "start": 2581.47, "end": 2581.93, "word": " and", "probability": 0.87744140625 }, { "start": 2581.93, "end": 2582.27, "word": " token", "probability": 0.748046875 }, { "start": 2582.27, "end": 2582.71, "word": " 9", "probability": 0.765625 }, { "start": 2582.71, "end": 2583.15, "word": ".", "probability": 0.95263671875 } ] }, { "id": 1178, "seek": 255992, "start": 2583.15, "end": 2587.81, "text": " We don't know which one, either unsubscribe or list.wn.org,", "tokens": [ 50814, 492, 500, 380, 458, 597, 472, 11, 2139, 2693, 9493, 420, 1329, 13, 895, 13, 4646, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.19487028062905906, "compression_ratio": 1.7213930348258706, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 2583.15, "end": 2583.47, "word": " We", "probability": 0.89453125 }, { "start": 2583.47, "end": 2583.59, "word": " don't", "probability": 0.93994140625 }, { "start": 2583.59, "end": 2583.77, "word": " know", "probability": 0.80908203125 }, { "start": 2583.77, "end": 2584.01, "word": " which", "probability": 0.8974609375 }, { "start": 2584.01, "end": 2584.33, "word": " one", "probability": 0.78662109375 }, { "start": 2584.33, "end": 2584.65, "word": ",", "probability": 0.38525390625 }, { "start": 2584.65, "end": 2585.23, "word": " either", "probability": 0.828125 }, { "start": 2585.23, "end": 2585.87, "word": " unsubscribe", "probability": 0.77783203125 }, { "start": 2585.87, "end": 2586.37, "word": " or", "probability": 0.82763671875 }, { "start": 2586.37, "end": 2586.59, "word": " list", "probability": 0.7470703125 }, { "start": 2586.59, "end": 2586.93, "word": ".wn", "probability": 0.766357421875 }, { "start": 2586.93, "end": 2587.43, "word": ".org", "probability": 0.95556640625 }, { "start": 2587.43, "end": 2587.81, "word": ",", "probability": 0.414794921875 } ] }, { "id": 1179, "seek": 255992, "start": 2587.81, "end": 2592.91, "text": " maps to 16 or 9, but what we do know is that both of them show up twice.", "tokens": [ 51064, 11317, 281, 3165, 420, 1722, 11, 457, 437, 321, 360, 458, 307, 300, 1293, 295, 552, 855, 493, 6091, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.19487028062905906, "compression_ratio": 1.7213930348258706, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 2587.81, "end": 2588.29, "word": " maps", "probability": 0.74609375 }, { "start": 2588.29, "end": 2588.51, "word": " to", "probability": 0.89697265625 }, { "start": 2588.51, "end": 2588.93, "word": " 16", "probability": 0.8876953125 }, { "start": 2588.93, "end": 2589.27, "word": " or", "probability": 0.90283203125 }, { "start": 2589.27, "end": 2589.53, "word": " 9", "probability": 0.97412109375 }, { "start": 2589.53, "end": 2589.63, "word": ",", "probability": 0.64306640625 }, { "start": 2589.63, "end": 2589.71, "word": " but", "probability": 0.82373046875 }, { "start": 2589.71, "end": 2589.85, "word": " what", "probability": 0.48388671875 }, { "start": 2589.85, "end": 2589.87, "word": " we", "probability": 0.90380859375 }, { "start": 2589.87, "end": 2590.01, "word": " do", "probability": 0.8994140625 }, { "start": 2590.01, "end": 2590.31, "word": " know", "probability": 0.80859375 }, { "start": 2590.31, "end": 2590.53, "word": " is", "probability": 0.88037109375 }, { "start": 2590.53, "end": 2590.67, "word": " that", "probability": 0.8525390625 }, { "start": 2590.67, "end": 2590.93, "word": " both", "probability": 0.8115234375 }, { "start": 2590.93, "end": 2591.09, "word": " of", "probability": 0.89111328125 }, { "start": 2591.09, "end": 2591.35, "word": " them", "probability": 0.73583984375 }, { "start": 2591.35, "end": 2591.87, "word": " show", "probability": 0.892578125 }, { "start": 2591.87, "end": 2592.05, "word": " up", "probability": 0.90869140625 }, { "start": 2592.05, "end": 2592.51, "word": " twice", "probability": 0.86376953125 }, { "start": 2592.51, "end": 2592.91, "word": ".", "probability": 0.75439453125 } ] }, { "id": 1180, "seek": 255992, "start": 2592.91, "end": 2597.41, "text": " So given that, list.wn.org is either 16 or 9,", "tokens": [ 51314, 407, 2212, 300, 11, 1329, 13, 895, 13, 4646, 307, 2139, 3165, 420, 1722, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.19487028062905906, "compression_ratio": 1.7213930348258706, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 2592.91, "end": 2593.15, "word": " So", "probability": 0.81103515625 }, { "start": 2593.15, "end": 2593.95, "word": " given", "probability": 0.46044921875 }, { "start": 2593.95, "end": 2594.31, "word": " that", "probability": 0.88037109375 }, { "start": 2594.31, "end": 2594.81, "word": ",", "probability": 0.646484375 }, { "start": 2594.81, "end": 2595.33, "word": " list", "probability": 0.8564453125 }, { "start": 2595.33, "end": 2595.67, "word": ".wn", "probability": 0.983642578125 }, { "start": 2595.67, "end": 2596.09, "word": ".org", "probability": 0.969482421875 }, { "start": 2596.09, "end": 2596.27, "word": " is", "probability": 0.88671875 }, { "start": 2596.27, "end": 2596.47, "word": " either", "probability": 0.8076171875 }, { "start": 2596.47, "end": 2596.81, "word": " 16", "probability": 0.908203125 }, { "start": 2596.81, "end": 2597.01, "word": " or", "probability": 0.90380859375 }, { "start": 2597.01, "end": 2597.27, "word": " 9", "probability": 0.98974609375 }, { "start": 2597.27, "end": 2597.41, "word": ",", "probability": 0.625 } ] }, { "id": 1181, "seek": 255992, "start": 2597.41, "end": 2601.99, "text": " and then the other one belongs to unsubscribe, or the word unsubscribe.", "tokens": [ 51514, 293, 550, 264, 661, 472, 12953, 281, 2693, 9493, 11, 420, 264, 1349, 2693, 9493, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.19487028062905906, "compression_ratio": 1.7213930348258706, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 2597.41, "end": 2597.51, "word": " and", "probability": 0.8828125 }, { "start": 2597.51, "end": 2597.61, "word": " then", "probability": 0.55126953125 }, { "start": 2597.61, "end": 2597.75, "word": " the", "probability": 0.80859375 }, { "start": 2597.75, "end": 2597.95, "word": " other", "probability": 0.7822265625 }, { "start": 2597.95, "end": 2598.39, "word": " one", "probability": 0.7939453125 }, { "start": 2598.39, "end": 2599.03, "word": " belongs", "probability": 0.669921875 }, { "start": 2599.03, "end": 2599.33, "word": " to", "probability": 0.9052734375 }, { "start": 2599.33, "end": 2599.95, "word": " unsubscribe", "probability": 0.849365234375 }, { "start": 2599.95, "end": 2600.21, "word": ",", "probability": 0.65576171875 }, { "start": 2600.21, "end": 2600.43, "word": " or", "probability": 0.88916015625 }, { "start": 2600.43, "end": 2600.59, "word": " the", "probability": 0.802734375 }, { "start": 2600.59, "end": 2600.79, "word": " word", "probability": 0.8173828125 }, { "start": 2600.79, "end": 2601.37, "word": " unsubscribe", "probability": 0.811767578125 }, { "start": 2601.37, "end": 2601.99, "word": ".", "probability": 0.99072265625 } ] }, { "id": 1182, "seek": 258788, "start": 2601.99, "end": 2607.01, "text": " So this looks exactly the same as if we had done our raw count.", "tokens": [ 50364, 407, 341, 1542, 2293, 264, 912, 382, 498, 321, 632, 1096, 527, 8936, 1207, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.18810680335007826, "compression_ratio": 1.506726457399103, "no_speech_prob": 0.000720977783203125, "words": [ { "start": 2601.99, "end": 2602.67, "word": " So", "probability": 0.455078125 }, { "start": 2602.67, "end": 2602.85, "word": " this", "probability": 0.79541015625 }, { "start": 2602.85, "end": 2603.01, "word": " looks", "probability": 0.78955078125 }, { "start": 2603.01, "end": 2603.35, "word": " exactly", "probability": 0.77734375 }, { "start": 2603.35, "end": 2603.57, "word": " the", "probability": 0.80419921875 }, { "start": 2603.57, "end": 2603.89, "word": " same", "probability": 0.8173828125 }, { "start": 2603.89, "end": 2604.27, "word": " as", "probability": 0.888671875 }, { "start": 2604.27, "end": 2604.81, "word": " if", "probability": 0.8935546875 }, { "start": 2604.81, "end": 2604.91, "word": " we", "probability": 0.9033203125 }, { "start": 2604.91, "end": 2605.05, "word": " had", "probability": 0.80322265625 }, { "start": 2605.05, "end": 2605.25, "word": " done", "probability": 0.806640625 }, { "start": 2605.25, "end": 2605.49, "word": " our", "probability": 0.6826171875 }, { "start": 2605.49, "end": 2605.83, "word": " raw", "probability": 0.75390625 }, { "start": 2605.83, "end": 2606.41, "word": " count", "probability": 0.76708984375 }, { "start": 2606.41, "end": 2607.01, "word": ".", "probability": 0.91015625 } ] }, { "id": 1183, "seek": 258788, "start": 2607.65, "end": 2610.81, "text": " If we look at our TF-IDF vectorizer, though,", "tokens": [ 50614, 759, 321, 574, 412, 527, 40964, 12, 2777, 37, 8062, 6545, 11, 1673, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.18810680335007826, "compression_ratio": 1.506726457399103, "no_speech_prob": 0.000720977783203125, "words": [ { "start": 2607.65, "end": 2607.91, "word": " If", "probability": 0.89111328125 }, { "start": 2607.91, "end": 2607.99, "word": " we", "probability": 0.90185546875 }, { "start": 2607.99, "end": 2608.13, "word": " look", "probability": 0.919921875 }, { "start": 2608.13, "end": 2608.33, "word": " at", "probability": 0.87646484375 }, { "start": 2608.33, "end": 2608.59, "word": " our", "probability": 0.80029296875 }, { "start": 2608.59, "end": 2608.91, "word": " TF", "probability": 0.60400390625 }, { "start": 2608.91, "end": 2609.33, "word": "-IDF", "probability": 0.8986002604166666 }, { "start": 2609.33, "end": 2609.91, "word": " vectorizer", "probability": 0.898193359375 }, { "start": 2609.91, "end": 2610.05, "word": ",", "probability": 0.26220703125 }, { "start": 2610.05, "end": 2610.29, "word": " though", "probability": 0.73974609375 }, { "start": 2610.29, "end": 2610.81, "word": ",", "probability": 0.93994140625 } ] }, { "id": 1184, "seek": 258788, "start": 2610.81, "end": 2612.47, "text": " we see something a little differently.", "tokens": [ 50764, 321, 536, 746, 257, 707, 7614, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.18810680335007826, "compression_ratio": 1.506726457399103, "no_speech_prob": 0.000720977783203125, "words": [ { "start": 2610.81, "end": 2611.19, "word": " we", "probability": 0.89404296875 }, { "start": 2611.19, "end": 2611.33, "word": " see", "probability": 0.80810546875 }, { "start": 2611.33, "end": 2611.53, "word": " something", "probability": 0.7451171875 }, { "start": 2611.69, "end": 2611.77, "word": " a little", "probability": 0.802734375 }, { "start": 2611.77, "end": 2612.17, "word": " differently", "probability": 0.64111328125 }, { "start": 2612.17, "end": 2612.47, "word": ".", "probability": 0.97900390625 } ] }, { "id": 1185, "seek": 258788, "start": 2612.47, "end": 2616.03, "text": " TF-IDF, what it does is use term frequency", "tokens": [ 50864, 40964, 12, 2777, 37, 11, 437, 309, 775, 307, 764, 1433, 7893, 51064 ], "temperature": 0.0, "avg_logprob": -0.18810680335007826, "compression_ratio": 1.506726457399103, "no_speech_prob": 0.000720977783203125, "words": [ { "start": 2612.47, "end": 2612.85, "word": " TF", "probability": 0.7451171875 }, { "start": 2612.85, "end": 2613.25, "word": "-IDF", "probability": 0.9879557291666666 }, { "start": 2613.25, "end": 2613.31, "word": ",", "probability": 0.87109375 }, { "start": 2613.31, "end": 2613.43, "word": " what", "probability": 0.8857421875 }, { "start": 2613.43, "end": 2613.53, "word": " it", "probability": 0.90087890625 }, { "start": 2613.53, "end": 2613.83, "word": " does", "probability": 0.91845703125 }, { "start": 2613.83, "end": 2614.31, "word": " is", "probability": 0.83447265625 }, { "start": 2614.31, "end": 2615.11, "word": " use", "probability": 0.76953125 }, { "start": 2615.11, "end": 2615.53, "word": " term", "probability": 0.81982421875 }, { "start": 2615.53, "end": 2616.03, "word": " frequency", "probability": 0.85888671875 } ] }, { "id": 1186, "seek": 258788, "start": 2616.03, "end": 2619.95, "text": " to give each term or token a weight.", "tokens": [ 51064, 281, 976, 1184, 1433, 420, 14862, 257, 3364, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.18810680335007826, "compression_ratio": 1.506726457399103, "no_speech_prob": 0.000720977783203125, "words": [ { "start": 2616.03, "end": 2616.49, "word": " to", "probability": 0.900390625 }, { "start": 2616.49, "end": 2616.89, "word": " give", "probability": 0.8173828125 }, { "start": 2616.89, "end": 2617.29, "word": " each", "probability": 0.85693359375 }, { "start": 2617.29, "end": 2618.03, "word": " term", "probability": 0.8232421875 }, { "start": 2618.03, "end": 2618.29, "word": " or", "probability": 0.85595703125 }, { "start": 2618.29, "end": 2618.69, "word": " token", "probability": 0.82666015625 }, { "start": 2619.09, "end": 2619.35, "word": " a weight", "probability": 0.8603515625 }, { "start": 2619.35, "end": 2619.95, "word": ".", "probability": 0.90625 } ] }, { "id": 1187, "seek": 258788, "start": 2620.03, "end": 2624.31, "text": " And so in this case, we see all of the ones that showed up once", "tokens": [ 51214, 400, 370, 294, 341, 1389, 11, 321, 536, 439, 295, 264, 2306, 300, 4712, 493, 1564, 51464 ], "temperature": 0.0, "avg_logprob": -0.18810680335007826, "compression_ratio": 1.506726457399103, "no_speech_prob": 0.000720977783203125, "words": [ { "start": 2620.03, "end": 2620.17, "word": " And", "probability": 0.8369140625 }, { "start": 2620.17, "end": 2620.29, "word": " so", "probability": 0.89501953125 }, { "start": 2620.29, "end": 2620.41, "word": " in", "probability": 0.81298828125 }, { "start": 2620.41, "end": 2620.57, "word": " this", "probability": 0.87841796875 }, { "start": 2620.57, "end": 2620.81, "word": " case", "probability": 0.80224609375 }, { "start": 2620.81, "end": 2620.87, "word": ",", "probability": 0.734375 }, { "start": 2620.87, "end": 2620.99, "word": " we", "probability": 0.8994140625 }, { "start": 2620.99, "end": 2621.37, "word": " see", "probability": 0.806640625 }, { "start": 2621.37, "end": 2622.17, "word": " all", "probability": 0.873046875 }, { "start": 2622.17, "end": 2622.35, "word": " of", "probability": 0.88525390625 }, { "start": 2622.35, "end": 2622.75, "word": " the", "probability": 0.82275390625 }, { "start": 2622.75, "end": 2623.37, "word": " ones", "probability": 0.7900390625 }, { "start": 2623.37, "end": 2623.53, "word": " that", "probability": 0.8857421875 }, { "start": 2623.53, "end": 2623.77, "word": " showed", "probability": 0.80224609375 }, { "start": 2623.77, "end": 2623.93, "word": " up", "probability": 0.90673828125 }, { "start": 2623.93, "end": 2624.31, "word": " once", "probability": 0.8046875 } ] }, { "id": 1188, "seek": 258788, "start": 2624.31, "end": 2629.95, "text": " have a weight of 0.204, token 9 and token 16", "tokens": [ 51464, 362, 257, 3364, 295, 1958, 13, 2009, 19, 11, 14862, 1722, 293, 14862, 3165, 51764 ], "temperature": 0.0, "avg_logprob": -0.18810680335007826, "compression_ratio": 1.506726457399103, "no_speech_prob": 0.000720977783203125, "words": [ { "start": 2624.31, "end": 2624.51, "word": " have", "probability": 0.85205078125 }, { "start": 2624.63, "end": 2624.75, "word": " a weight", "probability": 0.7626953125 }, { "start": 2624.75, "end": 2624.93, "word": " of", "probability": 0.8984375 }, { "start": 2624.93, "end": 2625.21, "word": " 0", "probability": 0.62841796875 }, { "start": 2625.21, "end": 2626.31, "word": ".204", "probability": 0.9833984375 }, { "start": 2626.31, "end": 2627.01, "word": ",", "probability": 0.61328125 }, { "start": 2627.01, "end": 2627.59, "word": " token", "probability": 0.7666015625 }, { "start": 2627.59, "end": 2628.11, "word": " 9", "probability": 0.300048828125 }, { "start": 2628.11, "end": 2628.75, "word": " and", "probability": 0.78369140625 }, { "start": 2628.75, "end": 2629.07, "word": " token", "probability": 0.79833984375 }, { "start": 2629.07, "end": 2629.95, "word": " 16", "probability": 0.89990234375 } ] }, { "id": 1189, "seek": 261702, "start": 2630.45, "end": 2633.79, "text": " have a weight of 0.408.", "tokens": [ 50364, 362, 257, 3364, 295, 1958, 13, 5254, 23, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.19087837354556933, "compression_ratio": 1.596638655462185, "no_speech_prob": 0.004608154296875, "words": [ { "start": 2630.45, "end": 2630.93, "word": " have", "probability": 0.3916015625 }, { "start": 2631.11, "end": 2631.35, "word": " a weight", "probability": 0.822265625 }, { "start": 2631.35, "end": 2631.73, "word": " of", "probability": 0.8955078125 }, { "start": 2631.73, "end": 2632.17, "word": " 0", "probability": 0.55322265625 }, { "start": 2632.17, "end": 2633.31, "word": ".408", "probability": 0.9501953125 }, { "start": 2633.31, "end": 2633.79, "word": ".", "probability": 0.78369140625 } ] }, { "id": 1190, "seek": 261702, "start": 2634.27, "end": 2636.69, "text": " So you don't really need to understand the underlying math,", "tokens": [ 50564, 407, 291, 500, 380, 534, 643, 281, 1223, 264, 14217, 5221, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.19087837354556933, "compression_ratio": 1.596638655462185, "no_speech_prob": 0.004608154296875, "words": [ { "start": 2634.27, "end": 2634.69, "word": " So", "probability": 0.50244140625 }, { "start": 2634.69, "end": 2634.75, "word": " you", "probability": 0.82763671875 }, { "start": 2634.75, "end": 2634.87, "word": " don't", "probability": 0.94189453125 }, { "start": 2634.87, "end": 2635.03, "word": " really", "probability": 0.74462890625 }, { "start": 2635.03, "end": 2635.17, "word": " need", "probability": 0.8046875 }, { "start": 2635.17, "end": 2635.27, "word": " to", "probability": 0.90478515625 }, { "start": 2635.27, "end": 2635.59, "word": " understand", "probability": 0.73583984375 }, { "start": 2635.59, "end": 2635.77, "word": " the", "probability": 0.81298828125 }, { "start": 2635.77, "end": 2636.19, "word": " underlying", "probability": 0.88427734375 }, { "start": 2636.19, "end": 2636.59, "word": " math", "probability": 0.89306640625 }, { "start": 2636.59, "end": 2636.69, "word": ",", "probability": 0.47607421875 } ] }, { "id": 1191, "seek": 261702, "start": 2636.69, "end": 2640.93, "text": " you just need to know that there are different ways to vectorize your data.", "tokens": [ 50714, 291, 445, 643, 281, 458, 300, 456, 366, 819, 2098, 281, 8062, 1125, 428, 1412, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.19087837354556933, "compression_ratio": 1.596638655462185, "no_speech_prob": 0.004608154296875, "words": [ { "start": 2636.69, "end": 2636.77, "word": " you", "probability": 0.8798828125 }, { "start": 2636.77, "end": 2636.91, "word": " just", "probability": 0.89306640625 }, { "start": 2636.91, "end": 2637.09, "word": " need", "probability": 0.8056640625 }, { "start": 2637.09, "end": 2637.19, "word": " to", "probability": 0.904296875 }, { "start": 2637.19, "end": 2637.33, "word": " know", "probability": 0.8203125 }, { "start": 2637.33, "end": 2637.49, "word": " that", "probability": 0.81787109375 }, { "start": 2637.49, "end": 2637.61, "word": " there", "probability": 0.85009765625 }, { "start": 2637.61, "end": 2637.73, "word": " are", "probability": 0.8857421875 }, { "start": 2637.73, "end": 2638.01, "word": " different", "probability": 0.68115234375 }, { "start": 2638.01, "end": 2638.39, "word": " ways", "probability": 0.7978515625 }, { "start": 2638.39, "end": 2638.77, "word": " to", "probability": 0.90087890625 }, { "start": 2638.77, "end": 2639.87, "word": " vectorize", "probability": 0.891845703125 }, { "start": 2639.87, "end": 2640.11, "word": " your", "probability": 0.79541015625 }, { "start": 2640.11, "end": 2640.45, "word": " data", "probability": 0.8203125 }, { "start": 2640.45, "end": 2640.93, "word": ".", "probability": 0.8173828125 } ] }, { "id": 1192, "seek": 261702, "start": 2641.59, "end": 2645.55, "text": " So there's TF-IDF, count vectorizer, word2vec,", "tokens": [ 50914, 407, 456, 311, 40964, 12, 2777, 37, 11, 1207, 8062, 6545, 11, 1349, 17, 303, 66, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.19087837354556933, "compression_ratio": 1.596638655462185, "no_speech_prob": 0.004608154296875, "words": [ { "start": 2641.59, "end": 2641.87, "word": " So", "probability": 0.69140625 }, { "start": 2641.87, "end": 2642.33, "word": " there's", "probability": 0.8720703125 }, { "start": 2642.33, "end": 2642.55, "word": " TF", "probability": 0.5205078125 }, { "start": 2642.55, "end": 2643.03, "word": "-IDF", "probability": 0.8640950520833334 }, { "start": 2643.03, "end": 2643.15, "word": ",", "probability": 0.970703125 }, { "start": 2643.15, "end": 2643.35, "word": " count", "probability": 0.26318359375 }, { "start": 2643.35, "end": 2644.07, "word": " vectorizer", "probability": 0.844482421875 }, { "start": 2644.07, "end": 2644.45, "word": ",", "probability": 0.97705078125 }, { "start": 2644.45, "end": 2645.21, "word": " word2vec", "probability": 0.863525390625 }, { "start": 2645.21, "end": 2645.55, "word": ",", "probability": 0.78369140625 } ] }, { "id": 1193, "seek": 261702, "start": 2645.55, "end": 2648.13, "text": " and a couple others, bag of words.", "tokens": [ 51114, 293, 257, 1916, 2357, 11, 3411, 295, 2283, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.19087837354556933, "compression_ratio": 1.596638655462185, "no_speech_prob": 0.004608154296875, "words": [ { "start": 2645.55, "end": 2645.91, "word": " and", "probability": 0.88671875 }, { "start": 2646.11, "end": 2646.31, "word": " a couple", "probability": 0.7861328125 }, { "start": 2646.31, "end": 2646.69, "word": " others", "probability": 0.6630859375 }, { "start": 2646.69, "end": 2646.83, "word": ",", "probability": 0.701171875 }, { "start": 2646.83, "end": 2647.05, "word": " bag", "probability": 0.76806640625 }, { "start": 2647.05, "end": 2647.19, "word": " of", "probability": 0.61767578125 }, { "start": 2647.19, "end": 2647.65, "word": " words", "probability": 0.7353515625 }, { "start": 2647.65, "end": 2648.13, "word": ".", "probability": 0.7734375 } ] }, { "id": 1194, "seek": 261702, "start": 2648.87, "end": 2652.47, "text": " And so there's different ones that we can try and see which one works better for us.", "tokens": [ 51264, 400, 370, 456, 311, 819, 2306, 300, 321, 393, 853, 293, 536, 597, 472, 1985, 1101, 337, 505, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.19087837354556933, "compression_ratio": 1.596638655462185, "no_speech_prob": 0.004608154296875, "words": [ { "start": 2648.87, "end": 2649.03, "word": " And", "probability": 0.740234375 }, { "start": 2649.03, "end": 2649.15, "word": " so", "probability": 0.892578125 }, { "start": 2649.15, "end": 2649.35, "word": " there's", "probability": 0.89599609375 }, { "start": 2649.35, "end": 2649.57, "word": " different", "probability": 0.70263671875 }, { "start": 2649.57, "end": 2649.81, "word": " ones", "probability": 0.77783203125 }, { "start": 2649.81, "end": 2649.91, "word": " that", "probability": 0.84716796875 }, { "start": 2649.91, "end": 2650.01, "word": " we", "probability": 0.9033203125 }, { "start": 2650.01, "end": 2650.11, "word": " can", "probability": 0.8857421875 }, { "start": 2650.11, "end": 2650.41, "word": " try", "probability": 0.80908203125 }, { "start": 2650.41, "end": 2650.57, "word": " and", "probability": 0.8232421875 }, { "start": 2650.57, "end": 2650.75, "word": " see", "probability": 0.8095703125 }, { "start": 2650.75, "end": 2650.91, "word": " which", "probability": 0.9130859375 }, { "start": 2650.91, "end": 2651.09, "word": " one", "probability": 0.81103515625 }, { "start": 2651.09, "end": 2651.33, "word": " works", "probability": 0.7294921875 }, { "start": 2651.33, "end": 2651.55, "word": " better", "probability": 0.81787109375 }, { "start": 2651.55, "end": 2651.73, "word": " for", "probability": 0.8974609375 }, { "start": 2651.73, "end": 2651.99, "word": " us", "probability": 0.904296875 }, { "start": 2651.99, "end": 2652.47, "word": ".", "probability": 0.994140625 } ] }, { "id": 1195, "seek": 261702, "start": 2654.17, "end": 2659.09, "text": " So let's hop down and start to load our testing data.", "tokens": [ 51514, 407, 718, 311, 3818, 760, 293, 722, 281, 3677, 527, 4997, 1412, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.19087837354556933, "compression_ratio": 1.596638655462185, "no_speech_prob": 0.004608154296875, "words": [ { "start": 2654.17, "end": 2654.65, "word": " So", "probability": 0.83837890625 }, { "start": 2654.65, "end": 2655.13, "word": " let's", "probability": 0.843017578125 }, { "start": 2655.13, "end": 2655.25, "word": " hop", "probability": 0.9150390625 }, { "start": 2655.25, "end": 2655.55, "word": " down", "probability": 0.80322265625 }, { "start": 2655.55, "end": 2655.89, "word": " and", "probability": 0.88916015625 }, { "start": 2655.89, "end": 2656.27, "word": " start", "probability": 0.86767578125 }, { "start": 2656.27, "end": 2656.75, "word": " to", "probability": 0.90380859375 }, { "start": 2656.75, "end": 2657.35, "word": " load", "probability": 0.92333984375 }, { "start": 2657.35, "end": 2657.85, "word": " our", "probability": 0.8017578125 }, { "start": 2657.85, "end": 2658.41, "word": " testing", "probability": 0.72412109375 }, { "start": 2658.41, "end": 2658.75, "word": " data", "probability": 0.818359375 }, { "start": 2658.75, "end": 2659.09, "word": ".", "probability": 0.96240234375 } ] }, { "id": 1196, "seek": 264646, "start": 2659.09, "end": 2662.39, "text": " So loading our testing data, what this is going to do is", "tokens": [ 50364, 407, 15114, 527, 4997, 1412, 11, 437, 341, 307, 516, 281, 360, 307, 50564 ], "temperature": 0.0, "avg_logprob": -0.20937499490876993, "compression_ratio": 1.9262672811059909, "no_speech_prob": 0.00243377685546875, "words": [ { "start": 2659.09, "end": 2659.29, "word": " So", "probability": 0.32177734375 }, { "start": 2659.29, "end": 2659.89, "word": " loading", "probability": 0.52490234375 }, { "start": 2659.89, "end": 2660.03, "word": " our", "probability": 0.7265625 }, { "start": 2660.03, "end": 2660.27, "word": " testing", "probability": 0.67333984375 }, { "start": 2660.27, "end": 2660.61, "word": " data", "probability": 0.8291015625 }, { "start": 2660.61, "end": 2660.81, "word": ",", "probability": 0.662109375 }, { "start": 2660.81, "end": 2660.89, "word": " what", "probability": 0.81201171875 }, { "start": 2660.89, "end": 2661.03, "word": " this", "probability": 0.87353515625 }, { "start": 2661.03, "end": 2661.15, "word": " is", "probability": 0.90234375 }, { "start": 2661.15, "end": 2661.29, "word": " going", "probability": 0.8603515625 }, { "start": 2661.29, "end": 2661.43, "word": " to", "probability": 0.90869140625 }, { "start": 2661.43, "end": 2661.75, "word": " do", "probability": 0.9052734375 }, { "start": 2661.75, "end": 2662.39, "word": " is", "probability": 0.87841796875 } ] }, { "id": 1197, "seek": 264646, "start": 2662.99, "end": 2670.45, "text": " just show us the names of each of our files in our testing directory.", "tokens": [ 50564, 445, 855, 505, 264, 5288, 295, 1184, 295, 527, 7098, 294, 527, 4997, 21120, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.20937499490876993, "compression_ratio": 1.9262672811059909, "no_speech_prob": 0.00243377685546875, "words": [ { "start": 2662.99, "end": 2663.39, "word": " just", "probability": 0.54833984375 }, { "start": 2663.39, "end": 2663.71, "word": " show", "probability": 0.8818359375 }, { "start": 2663.71, "end": 2663.99, "word": " us", "probability": 0.9033203125 }, { "start": 2663.99, "end": 2665.61, "word": " the", "probability": 0.80078125 }, { "start": 2665.61, "end": 2666.19, "word": " names", "probability": 0.80322265625 }, { "start": 2666.19, "end": 2666.63, "word": " of", "probability": 0.90380859375 }, { "start": 2666.63, "end": 2666.95, "word": " each", "probability": 0.84521484375 }, { "start": 2666.95, "end": 2667.13, "word": " of", "probability": 0.90478515625 }, { "start": 2667.13, "end": 2667.59, "word": " our", "probability": 0.81884765625 }, { "start": 2667.59, "end": 2668.61, "word": " files", "probability": 0.81005859375 }, { "start": 2668.61, "end": 2669.09, "word": " in", "probability": 0.89453125 }, { "start": 2669.09, "end": 2669.29, "word": " our", "probability": 0.80712890625 }, { "start": 2669.29, "end": 2669.57, "word": " testing", "probability": 0.67919921875 }, { "start": 2669.57, "end": 2670.05, "word": " directory", "probability": 0.81884765625 }, { "start": 2670.05, "end": 2670.45, "word": ".", "probability": 0.61865234375 } ] }, { "id": 1198, "seek": 264646, "start": 2671.43, "end": 2674.25, "text": " And we have train email.txt,", "tokens": [ 50964, 400, 321, 362, 3847, 3796, 13, 83, 734, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.20937499490876993, "compression_ratio": 1.9262672811059909, "no_speech_prob": 0.00243377685546875, "words": [ { "start": 2671.43, "end": 2671.83, "word": " And", "probability": 0.7314453125 }, { "start": 2671.83, "end": 2672.07, "word": " we", "probability": 0.880859375 }, { "start": 2672.07, "end": 2672.33, "word": " have", "probability": 0.87109375 }, { "start": 2672.33, "end": 2672.83, "word": " train", "probability": 0.720703125 }, { "start": 2672.83, "end": 2673.21, "word": " email", "probability": 0.2978515625 }, { "start": 2673.21, "end": 2673.89, "word": ".txt", "probability": 0.7684733072916666 }, { "start": 2673.89, "end": 2674.25, "word": ",", "probability": 0.277099609375 } ] }, { "id": 1199, "seek": 264646, "start": 2674.25, "end": 2676.65, "text": " and then at the end we have the class that it belongs to.", "tokens": [ 51114, 293, 550, 412, 264, 917, 321, 362, 264, 1508, 300, 309, 12953, 281, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.20937499490876993, "compression_ratio": 1.9262672811059909, "no_speech_prob": 0.00243377685546875, "words": [ { "start": 2674.25, "end": 2674.33, "word": " and", "probability": 0.88037109375 }, { "start": 2674.33, "end": 2674.43, "word": " then", "probability": 0.63720703125 }, { "start": 2674.43, "end": 2674.55, "word": " at", "probability": 0.89599609375 }, { "start": 2674.55, "end": 2674.67, "word": " the", "probability": 0.81787109375 }, { "start": 2674.67, "end": 2674.97, "word": " end", "probability": 0.81787109375 }, { "start": 2674.97, "end": 2675.11, "word": " we", "probability": 0.6591796875 }, { "start": 2675.11, "end": 2675.25, "word": " have", "probability": 0.8759765625 }, { "start": 2675.25, "end": 2675.39, "word": " the", "probability": 0.80712890625 }, { "start": 2675.39, "end": 2675.79, "word": " class", "probability": 0.900390625 }, { "start": 2675.79, "end": 2675.95, "word": " that", "probability": 0.85595703125 }, { "start": 2675.95, "end": 2676.05, "word": " it", "probability": 0.88818359375 }, { "start": 2676.05, "end": 2676.35, "word": " belongs", "probability": 0.70751953125 }, { "start": 2676.35, "end": 2676.55, "word": " to", "probability": 0.89453125 }, { "start": 2676.55, "end": 2676.65, "word": ".", "probability": 0.73291015625 } ] }, { "id": 1200, "seek": 264646, "start": 2676.65, "end": 2679.03, "text": " So we have ham, we have spam.", "tokens": [ 51264, 407, 321, 362, 7852, 11, 321, 362, 24028, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.20937499490876993, "compression_ratio": 1.9262672811059909, "no_speech_prob": 0.00243377685546875, "words": [ { "start": 2676.65, "end": 2676.71, "word": " So", "probability": 0.85791015625 }, { "start": 2676.71, "end": 2676.83, "word": " we", "probability": 0.88671875 }, { "start": 2676.83, "end": 2676.97, "word": " have", "probability": 0.87841796875 }, { "start": 2676.97, "end": 2677.33, "word": " ham", "probability": 0.57373046875 }, { "start": 2677.33, "end": 2677.87, "word": ",", "probability": 0.8779296875 }, { "start": 2677.87, "end": 2678.03, "word": " we", "probability": 0.8828125 }, { "start": 2678.03, "end": 2678.17, "word": " have", "probability": 0.8818359375 }, { "start": 2678.17, "end": 2678.63, "word": " spam", "probability": 0.90673828125 }, { "start": 2678.63, "end": 2679.03, "word": ".", "probability": 0.90185546875 } ] }, { "id": 1201, "seek": 264646, "start": 2679.75, "end": 2682.77, "text": " So what we're going to want to do as part of loading our testing data", "tokens": [ 51414, 407, 437, 321, 434, 516, 281, 528, 281, 360, 382, 644, 295, 15114, 527, 4997, 1412, 51564 ], "temperature": 0.0, "avg_logprob": -0.20937499490876993, "compression_ratio": 1.9262672811059909, "no_speech_prob": 0.00243377685546875, "words": [ { "start": 2679.75, "end": 2679.91, "word": " So", "probability": 0.8671875 }, { "start": 2679.91, "end": 2680.03, "word": " what", "probability": 0.86328125 }, { "start": 2680.03, "end": 2680.15, "word": " we're", "probability": 0.90966796875 }, { "start": 2680.15, "end": 2680.23, "word": " going", "probability": 0.56591796875 }, { "start": 2680.23, "end": 2680.29, "word": " to", "probability": 0.90185546875 }, { "start": 2680.29, "end": 2680.41, "word": " want", "probability": 0.8076171875 }, { "start": 2680.41, "end": 2680.49, "word": " to", "probability": 0.9033203125 }, { "start": 2680.49, "end": 2680.63, "word": " do", "probability": 0.9052734375 }, { "start": 2680.63, "end": 2680.77, "word": " as", "probability": 0.75048828125 }, { "start": 2680.77, "end": 2680.97, "word": " part", "probability": 0.80908203125 }, { "start": 2680.97, "end": 2681.07, "word": " of", "probability": 0.9052734375 }, { "start": 2681.07, "end": 2681.59, "word": " loading", "probability": 0.440673828125 }, { "start": 2681.59, "end": 2681.77, "word": " our", "probability": 0.7939453125 }, { "start": 2681.77, "end": 2682.47, "word": " testing", "probability": 0.73486328125 }, { "start": 2682.47, "end": 2682.77, "word": " data", "probability": 0.818359375 } ] }, { "id": 1202, "seek": 264646, "start": 2682.77, "end": 2685.31, "text": " is we're going to want to strip off these labels.", "tokens": [ 51564, 307, 321, 434, 516, 281, 528, 281, 12828, 766, 613, 16949, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.20937499490876993, "compression_ratio": 1.9262672811059909, "no_speech_prob": 0.00243377685546875, "words": [ { "start": 2682.77, "end": 2683.03, "word": " is", "probability": 0.72705078125 }, { "start": 2683.03, "end": 2683.19, "word": " we're", "probability": 0.888916015625 }, { "start": 2683.19, "end": 2683.25, "word": " going", "probability": 0.84130859375 }, { "start": 2683.25, "end": 2683.33, "word": " to", "probability": 0.90478515625 }, { "start": 2683.33, "end": 2683.45, "word": " want", "probability": 0.78466796875 }, { "start": 2683.45, "end": 2683.59, "word": " to", "probability": 0.90380859375 }, { "start": 2683.59, "end": 2683.91, "word": " strip", "probability": 0.77099609375 }, { "start": 2683.91, "end": 2684.19, "word": " off", "probability": 0.8037109375 }, { "start": 2684.19, "end": 2684.43, "word": " these", "probability": 0.69873046875 }, { "start": 2684.43, "end": 2684.91, "word": " labels", "probability": 0.8408203125 }, { "start": 2684.91, "end": 2685.31, "word": ".", "probability": 0.85546875 } ] }, { "id": 1203, "seek": 264646, "start": 2685.91, "end": 2688.53, "text": " So we're going to read the full email into our corpus,", "tokens": [ 51714, 407, 321, 434, 516, 281, 1401, 264, 1577, 3796, 666, 527, 1181, 31624, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.20937499490876993, "compression_ratio": 1.9262672811059909, "no_speech_prob": 0.00243377685546875, "words": [ { "start": 2685.91, "end": 2686.29, "word": " So", "probability": 0.8583984375 }, { "start": 2686.29, "end": 2686.45, "word": " we're", "probability": 0.923583984375 }, { "start": 2686.45, "end": 2686.53, "word": " going", "probability": 0.8466796875 }, { "start": 2686.53, "end": 2686.61, "word": " to", "probability": 0.90234375 }, { "start": 2686.61, "end": 2686.77, "word": " read", "probability": 0.88818359375 }, { "start": 2686.77, "end": 2686.91, "word": " the", "probability": 0.8154296875 }, { "start": 2686.91, "end": 2687.11, "word": " full", "probability": 0.79931640625 }, { "start": 2687.11, "end": 2687.49, "word": " email", "probability": 0.91162109375 }, { "start": 2687.49, "end": 2687.87, "word": " into", "probability": 0.73974609375 }, { "start": 2687.87, "end": 2688.09, "word": " our", "probability": 0.802734375 }, { "start": 2688.09, "end": 2688.43, "word": " corpus", "probability": 0.82470703125 }, { "start": 2688.43, "end": 2688.53, "word": ",", "probability": 0.65625 } ] }, { "id": 1204, "seek": 267224, "start": 2688.53, "end": 2689.85, "text": " and we're going to strip off these labels,", "tokens": [ 50364, 293, 321, 434, 516, 281, 12828, 766, 613, 16949, 11, 50414 ], "temperature": 0.0, "avg_logprob": -0.2282072369728172, "compression_ratio": 2.019047619047619, "no_speech_prob": 0.0011339187622070312, "words": [ { "start": 2688.53, "end": 2688.61, "word": " and", "probability": 0.07000732421875 }, { "start": 2688.61, "end": 2688.73, "word": " we're", "probability": 0.7578125 }, { "start": 2688.73, "end": 2688.79, "word": " going", "probability": 0.347900390625 }, { "start": 2688.79, "end": 2688.81, "word": " to", "probability": 0.90087890625 }, { "start": 2688.81, "end": 2688.99, "word": " strip", "probability": 0.7216796875 }, { "start": 2688.99, "end": 2689.13, "word": " off", "probability": 0.80517578125 }, { "start": 2689.13, "end": 2689.33, "word": " these", "probability": 0.68994140625 }, { "start": 2689.33, "end": 2689.71, "word": " labels", "probability": 0.8486328125 }, { "start": 2689.71, "end": 2689.85, "word": ",", "probability": 0.37841796875 } ] }, { "id": 1205, "seek": 267224, "start": 2689.85, "end": 2695.01, "text": " and those are going to be the new labels for our testing data.", "tokens": [ 50414, 293, 729, 366, 516, 281, 312, 264, 777, 16949, 337, 527, 4997, 1412, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.2282072369728172, "compression_ratio": 2.019047619047619, "no_speech_prob": 0.0011339187622070312, "words": [ { "start": 2689.85, "end": 2689.89, "word": " and", "probability": 0.87744140625 }, { "start": 2689.89, "end": 2690.03, "word": " those", "probability": 0.8330078125 }, { "start": 2690.03, "end": 2690.13, "word": " are", "probability": 0.888671875 }, { "start": 2690.13, "end": 2690.21, "word": " going", "probability": 0.83544921875 }, { "start": 2690.21, "end": 2690.25, "word": " to", "probability": 0.90283203125 }, { "start": 2690.25, "end": 2690.37, "word": " be", "probability": 0.9033203125 }, { "start": 2690.37, "end": 2690.57, "word": " the", "probability": 0.8125 }, { "start": 2690.57, "end": 2691.09, "word": " new", "probability": 0.83740234375 }, { "start": 2691.09, "end": 2692.71, "word": " labels", "probability": 0.79443359375 }, { "start": 2692.71, "end": 2693.51, "word": " for", "probability": 0.890625 }, { "start": 2693.51, "end": 2693.79, "word": " our", "probability": 0.81201171875 }, { "start": 2693.79, "end": 2694.19, "word": " testing", "probability": 0.703125 }, { "start": 2694.19, "end": 2694.57, "word": " data", "probability": 0.81787109375 }, { "start": 2694.57, "end": 2695.01, "word": ".", "probability": 0.984375 } ] }, { "id": 1206, "seek": 267224, "start": 2696.41, "end": 2700.11, "text": " So that hops us into task 4 to load the testing data.", "tokens": [ 50764, 407, 300, 47579, 505, 666, 5633, 1017, 281, 3677, 264, 4997, 1412, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.2282072369728172, "compression_ratio": 2.019047619047619, "no_speech_prob": 0.0011339187622070312, "words": [ { "start": 2696.41, "end": 2696.85, "word": " So", "probability": 0.7734375 }, { "start": 2696.85, "end": 2696.99, "word": " that", "probability": 0.7607421875 }, { "start": 2696.99, "end": 2697.17, "word": " hops", "probability": 0.434326171875 }, { "start": 2697.17, "end": 2697.31, "word": " us", "probability": 0.88916015625 }, { "start": 2697.31, "end": 2697.59, "word": " into", "probability": 0.712890625 }, { "start": 2697.59, "end": 2698.11, "word": " task", "probability": 0.658203125 }, { "start": 2698.11, "end": 2698.49, "word": " 4", "probability": 0.330078125 }, { "start": 2698.49, "end": 2698.83, "word": " to", "probability": 0.50927734375 }, { "start": 2698.83, "end": 2699.17, "word": " load", "probability": 0.9306640625 }, { "start": 2699.17, "end": 2699.33, "word": " the", "probability": 0.81298828125 }, { "start": 2699.33, "end": 2699.61, "word": " testing", "probability": 0.72705078125 }, { "start": 2699.61, "end": 2699.95, "word": " data", "probability": 0.82666015625 }, { "start": 2699.95, "end": 2700.11, "word": ".", "probability": 0.736328125 } ] }, { "id": 1207, "seek": 267224, "start": 2700.11, "end": 2703.53, "text": " Just like loading the training data, we're going to create two list arrays,", "tokens": [ 50914, 1449, 411, 15114, 264, 3097, 1412, 11, 321, 434, 516, 281, 1884, 732, 1329, 41011, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.2282072369728172, "compression_ratio": 2.019047619047619, "no_speech_prob": 0.0011339187622070312, "words": [ { "start": 2700.11, "end": 2700.35, "word": " Just", "probability": 0.80615234375 }, { "start": 2700.35, "end": 2700.59, "word": " like", "probability": 0.88916015625 }, { "start": 2700.59, "end": 2701.37, "word": " loading", "probability": 0.78271484375 }, { "start": 2701.37, "end": 2701.53, "word": " the", "probability": 0.806640625 }, { "start": 2701.53, "end": 2701.73, "word": " training", "probability": 0.82275390625 }, { "start": 2701.73, "end": 2702.01, "word": " data", "probability": 0.830078125 }, { "start": 2702.01, "end": 2702.07, "word": ",", "probability": 0.8974609375 }, { "start": 2702.07, "end": 2702.23, "word": " we're", "probability": 0.925048828125 }, { "start": 2702.23, "end": 2702.31, "word": " going", "probability": 0.84521484375 }, { "start": 2702.31, "end": 2702.37, "word": " to", "probability": 0.90283203125 }, { "start": 2702.37, "end": 2702.59, "word": " create", "probability": 0.828125 }, { "start": 2702.59, "end": 2702.83, "word": " two", "probability": 0.7412109375 }, { "start": 2702.83, "end": 2703.07, "word": " list", "probability": 0.826171875 }, { "start": 2703.07, "end": 2703.37, "word": " arrays", "probability": 0.63427734375 }, { "start": 2703.37, "end": 2703.53, "word": ",", "probability": 0.52587890625 } ] }, { "id": 1208, "seek": 267224, "start": 2703.53, "end": 2706.81, "text": " our corpus, we're going to call this test corpus, and our test labels.", "tokens": [ 51114, 527, 1181, 31624, 11, 321, 434, 516, 281, 818, 341, 1500, 1181, 31624, 11, 293, 527, 1500, 16949, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.2282072369728172, "compression_ratio": 2.019047619047619, "no_speech_prob": 0.0011339187622070312, "words": [ { "start": 2703.53, "end": 2703.63, "word": " our", "probability": 0.416259765625 }, { "start": 2703.63, "end": 2704.15, "word": " corpus", "probability": 0.81640625 }, { "start": 2704.15, "end": 2704.23, "word": ",", "probability": 0.42138671875 }, { "start": 2704.23, "end": 2704.37, "word": " we're", "probability": 0.907958984375 }, { "start": 2704.37, "end": 2704.41, "word": " going", "probability": 0.8369140625 }, { "start": 2704.41, "end": 2704.49, "word": " to", "probability": 0.90234375 }, { "start": 2704.49, "end": 2704.59, "word": " call", "probability": 0.8134765625 }, { "start": 2704.59, "end": 2704.73, "word": " this", "probability": 0.87255859375 }, { "start": 2704.73, "end": 2704.99, "word": " test", "probability": 0.65673828125 }, { "start": 2704.99, "end": 2705.35, "word": " corpus", "probability": 0.76123046875 }, { "start": 2705.35, "end": 2705.53, "word": ",", "probability": 0.626953125 }, { "start": 2705.53, "end": 2705.59, "word": " and", "probability": 0.8916015625 }, { "start": 2705.59, "end": 2705.73, "word": " our", "probability": 0.81689453125 }, { "start": 2705.73, "end": 2706.01, "word": " test", "probability": 0.81396484375 }, { "start": 2706.01, "end": 2706.37, "word": " labels", "probability": 0.82080078125 }, { "start": 2706.37, "end": 2706.81, "word": ".", "probability": 0.74560546875 } ] }, { "id": 1209, "seek": 267224, "start": 2706.97, "end": 2709.79, "text": " And then we're going to load each email body,", "tokens": [ 51264, 400, 550, 321, 434, 516, 281, 3677, 1184, 3796, 1772, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.2282072369728172, "compression_ratio": 2.019047619047619, "no_speech_prob": 0.0011339187622070312, "words": [ { "start": 2706.97, "end": 2707.35, "word": " And", "probability": 0.8505859375 }, { "start": 2707.35, "end": 2707.47, "word": " then", "probability": 0.7197265625 }, { "start": 2707.47, "end": 2707.63, "word": " we're", "probability": 0.91748046875 }, { "start": 2707.63, "end": 2707.77, "word": " going", "probability": 0.85107421875 }, { "start": 2707.77, "end": 2707.99, "word": " to", "probability": 0.90380859375 }, { "start": 2707.99, "end": 2708.21, "word": " load", "probability": 0.919921875 }, { "start": 2708.21, "end": 2708.55, "word": " each", "probability": 0.86083984375 }, { "start": 2708.55, "end": 2708.97, "word": " email", "probability": 0.875 }, { "start": 2708.97, "end": 2709.39, "word": " body", "probability": 0.81201171875 }, { "start": 2709.39, "end": 2709.79, "word": ",", "probability": 0.5263671875 } ] }, { "id": 1210, "seek": 267224, "start": 2709.79, "end": 2714.31, "text": " and then strip off the label and throw that into the test labels array.", "tokens": [ 51414, 293, 550, 12828, 766, 264, 7645, 293, 3507, 300, 666, 264, 1500, 16949, 10225, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.2282072369728172, "compression_ratio": 2.019047619047619, "no_speech_prob": 0.0011339187622070312, "words": [ { "start": 2709.79, "end": 2710.07, "word": " and", "probability": 0.8974609375 }, { "start": 2710.07, "end": 2710.21, "word": " then", "probability": 0.7138671875 }, { "start": 2710.21, "end": 2710.57, "word": " strip", "probability": 0.7060546875 }, { "start": 2710.57, "end": 2710.77, "word": " off", "probability": 0.7998046875 }, { "start": 2710.77, "end": 2710.93, "word": " the", "probability": 0.81640625 }, { "start": 2710.93, "end": 2711.19, "word": " label", "probability": 0.79052734375 }, { "start": 2711.19, "end": 2711.67, "word": " and", "probability": 0.5390625 }, { "start": 2711.67, "end": 2712.07, "word": " throw", "probability": 0.80810546875 }, { "start": 2712.07, "end": 2712.27, "word": " that", "probability": 0.88232421875 }, { "start": 2712.27, "end": 2712.55, "word": " into", "probability": 0.7373046875 }, { "start": 2712.55, "end": 2712.77, "word": " the", "probability": 0.81298828125 }, { "start": 2712.77, "end": 2713.07, "word": " test", "probability": 0.794921875 }, { "start": 2713.07, "end": 2713.49, "word": " labels", "probability": 0.61474609375 }, { "start": 2713.49, "end": 2713.87, "word": " array", "probability": 0.68701171875 }, { "start": 2713.87, "end": 2714.31, "word": ".", "probability": 0.99755859375 } ] }, { "id": 1211, "seek": 269536, "start": 2716.45, "end": 2720.81, "text": " So what that's going to look like is...", "tokens": [ 50414, 407, 437, 300, 311, 516, 281, 574, 411, 307, 485, 50714 ], "temperature": 0.0, "avg_logprob": -0.22420933699033346, "compression_ratio": 1.6832298136645962, "no_speech_prob": 0.010009765625, "words": [ { "start": 2716.45, "end": 2716.85, "word": " So", "probability": 0.58056640625 }, { "start": 2716.85, "end": 2717.25, "word": " what", "probability": 0.63037109375 }, { "start": 2717.25, "end": 2717.59, "word": " that's", "probability": 0.92724609375 }, { "start": 2717.59, "end": 2717.75, "word": " going", "probability": 0.861328125 }, { "start": 2717.75, "end": 2717.95, "word": " to", "probability": 0.90673828125 }, { "start": 2717.95, "end": 2718.17, "word": " look", "probability": 0.91748046875 }, { "start": 2718.17, "end": 2718.51, "word": " like", "probability": 0.87841796875 }, { "start": 2718.51, "end": 2720.81, "word": " is...", "probability": 0.5870361328125 } ] }, { "id": 1212, "seek": 269536, "start": 2725.55, "end": 2728.53, "text": " So we're going to look at... what was the name of that?", "tokens": [ 50714, 407, 321, 434, 516, 281, 574, 412, 485, 437, 390, 264, 1315, 295, 300, 30, 50864 ], "temperature": 0.0, "avg_logprob": -0.22420933699033346, "compression_ratio": 1.6832298136645962, "no_speech_prob": 0.010009765625, "words": [ { "start": 2725.55, "end": 2725.95, "word": " So", "probability": 0.66796875 }, { "start": 2725.95, "end": 2726.17, "word": " we're", "probability": 0.897705078125 }, { "start": 2726.17, "end": 2726.27, "word": " going", "probability": 0.43017578125 }, { "start": 2726.27, "end": 2726.35, "word": " to", "probability": 0.90283203125 }, { "start": 2726.35, "end": 2726.59, "word": " look", "probability": 0.908203125 }, { "start": 2726.59, "end": 2727.47, "word": " at...", "probability": 0.6119384765625 }, { "start": 2727.47, "end": 2727.75, "word": " what", "probability": 0.2271728515625 }, { "start": 2727.75, "end": 2727.85, "word": " was", "probability": 0.75 }, { "start": 2727.85, "end": 2727.91, "word": " the", "probability": 0.80712890625 }, { "start": 2727.91, "end": 2728.01, "word": " name", "probability": 0.818359375 }, { "start": 2728.01, "end": 2728.09, "word": " of", "probability": 0.90478515625 }, { "start": 2728.09, "end": 2728.27, "word": " that", "probability": 0.88330078125 }, { "start": 2728.27, "end": 2728.53, "word": "?", "probability": 0.830078125 } ] }, { "id": 1213, "seek": 269536, "start": 2728.73, "end": 2730.77, "text": " Test corpus.", "tokens": [ 50864, 9279, 1181, 31624, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.22420933699033346, "compression_ratio": 1.6832298136645962, "no_speech_prob": 0.010009765625, "words": [ { "start": 2728.73, "end": 2729.13, "word": " Test", "probability": 0.48583984375 }, { "start": 2729.13, "end": 2730.37, "word": " corpus", "probability": 0.5985107421875 }, { "start": 2730.37, "end": 2730.77, "word": ".", "probability": 0.681640625 } ] }, { "id": 1214, "seek": 269536, "start": 2730.95, "end": 2732.93, "text": " And we're just going to set that as a blank list,", "tokens": [ 51014, 400, 321, 434, 445, 516, 281, 992, 300, 382, 257, 8247, 1329, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.22420933699033346, "compression_ratio": 1.6832298136645962, "no_speech_prob": 0.010009765625, "words": [ { "start": 2730.95, "end": 2731.09, "word": " And", "probability": 0.5908203125 }, { "start": 2731.09, "end": 2731.19, "word": " we're", "probability": 0.91796875 }, { "start": 2731.19, "end": 2731.31, "word": " just", "probability": 0.859375 }, { "start": 2731.31, "end": 2731.43, "word": " going", "probability": 0.7470703125 }, { "start": 2731.43, "end": 2731.47, "word": " to", "probability": 0.90576171875 }, { "start": 2731.47, "end": 2731.61, "word": " set", "probability": 0.8662109375 }, { "start": 2731.61, "end": 2731.73, "word": " that", "probability": 0.88427734375 }, { "start": 2731.73, "end": 2731.83, "word": " as", "probability": 0.90869140625 }, { "start": 2731.91, "end": 2732.13, "word": " a blank", "probability": 0.8984375 }, { "start": 2732.13, "end": 2732.77, "word": " list", "probability": 0.828125 }, { "start": 2732.77, "end": 2732.93, "word": ",", "probability": 0.3603515625 } ] }, { "id": 1215, "seek": 269536, "start": 2732.93, "end": 2737.27, "text": " and then test labels as a blank list.", "tokens": [ 51114, 293, 550, 1500, 16949, 382, 257, 8247, 1329, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.22420933699033346, "compression_ratio": 1.6832298136645962, "no_speech_prob": 0.010009765625, "words": [ { "start": 2732.93, "end": 2733.03, "word": " and", "probability": 0.87646484375 }, { "start": 2733.03, "end": 2733.23, "word": " then", "probability": 0.75244140625 }, { "start": 2733.23, "end": 2733.83, "word": " test", "probability": 0.68115234375 }, { "start": 2733.83, "end": 2734.87, "word": " labels", "probability": 0.5595703125 }, { "start": 2734.87, "end": 2735.79, "word": " as", "probability": 0.86474609375 }, { "start": 2735.95, "end": 2736.23, "word": " a blank", "probability": 0.8154296875 }, { "start": 2736.23, "end": 2736.87, "word": " list", "probability": 0.876953125 }, { "start": 2736.87, "end": 2737.27, "word": ".", "probability": 0.72119140625 } ] }, { "id": 1216, "seek": 269536, "start": 2737.99, "end": 2741.01, "text": " For loading each of the emails, we're going to do just like we did before,", "tokens": [ 51364, 1171, 15114, 1184, 295, 264, 12524, 11, 321, 434, 516, 281, 360, 445, 411, 321, 630, 949, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.22420933699033346, "compression_ratio": 1.6832298136645962, "no_speech_prob": 0.010009765625, "words": [ { "start": 2737.99, "end": 2738.39, "word": " For", "probability": 0.86962890625 }, { "start": 2738.39, "end": 2738.61, "word": " loading", "probability": 0.7275390625 }, { "start": 2738.61, "end": 2738.83, "word": " each", "probability": 0.85205078125 }, { "start": 2738.83, "end": 2738.93, "word": " of", "probability": 0.88623046875 }, { "start": 2738.93, "end": 2738.99, "word": " the", "probability": 0.80615234375 }, { "start": 2738.99, "end": 2739.35, "word": " emails", "probability": 0.7783203125 }, { "start": 2739.35, "end": 2739.47, "word": ",", "probability": 0.7470703125 }, { "start": 2739.47, "end": 2739.63, "word": " we're", "probability": 0.926025390625 }, { "start": 2739.63, "end": 2739.63, "word": " going", "probability": 0.79541015625 }, { "start": 2739.63, "end": 2739.69, "word": " to", "probability": 0.90576171875 }, { "start": 2739.69, "end": 2739.81, "word": " do", "probability": 0.90234375 }, { "start": 2739.81, "end": 2739.99, "word": " just", "probability": 0.8408203125 }, { "start": 2739.99, "end": 2740.11, "word": " like", "probability": 0.88134765625 }, { "start": 2740.11, "end": 2740.21, "word": " we", "probability": 0.89892578125 }, { "start": 2740.21, "end": 2740.35, "word": " did", "probability": 0.90673828125 }, { "start": 2740.35, "end": 2740.81, "word": " before", "probability": 0.78076171875 }, { "start": 2740.81, "end": 2741.01, "word": ",", "probability": 0.319580078125 } ] }, { "id": 1217, "seek": 272258, "start": 2741.01, "end": 2744.51, "text": " filename in ls.listdir,", "tokens": [ 50364, 1387, 268, 529, 294, 287, 82, 13, 8264, 35043, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.30597311107418207, "compression_ratio": 1.6689655172413793, "no_speech_prob": 0.41845703125, "words": [ { "start": 2741.01, "end": 2742.35, "word": " filename", "probability": 0.6248906453450521 }, { "start": 2742.35, "end": 2742.69, "word": " in", "probability": 0.6201171875 }, { "start": 2742.69, "end": 2743.07, "word": " ls", "probability": 0.55718994140625 }, { "start": 2743.07, "end": 2743.95, "word": ".listdir", "probability": 0.8157552083333334 }, { "start": 2743.95, "end": 2744.51, "word": ",", "probability": 0.2320556640625 } ] }, { "id": 1218, "seek": 272258, "start": 2744.51, "end": 2750.13, "text": " and then our data directory plus the test directory.", "tokens": [ 50514, 293, 550, 527, 1412, 21120, 1804, 264, 1500, 21120, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.30597311107418207, "compression_ratio": 1.6689655172413793, "no_speech_prob": 0.41845703125, "words": [ { "start": 2744.51, "end": 2744.97, "word": " and", "probability": 0.78466796875 }, { "start": 2744.97, "end": 2745.17, "word": " then", "probability": 0.724609375 }, { "start": 2745.17, "end": 2745.67, "word": " our", "probability": 0.79638671875 }, { "start": 2745.67, "end": 2746.37, "word": " data", "probability": 0.6943359375 }, { "start": 2746.37, "end": 2746.83, "word": " directory", "probability": 0.72705078125 }, { "start": 2746.83, "end": 2747.67, "word": " plus", "probability": 0.6396484375 }, { "start": 2747.67, "end": 2748.55, "word": " the", "probability": 0.802734375 }, { "start": 2748.55, "end": 2748.91, "word": " test", "probability": 0.7822265625 }, { "start": 2748.91, "end": 2749.45, "word": " directory", "probability": 0.79833984375 }, { "start": 2749.45, "end": 2750.13, "word": ".", "probability": 0.68359375 } ] }, { "id": 1219, "seek": 272258, "start": 2750.13, "end": 2751.43, "text": " So we're going to look at each filename,", "tokens": [ 50764, 407, 321, 434, 516, 281, 574, 412, 1184, 1387, 268, 529, 11, 50864 ], "temperature": 0.0, "avg_logprob": -0.30597311107418207, "compression_ratio": 1.6689655172413793, "no_speech_prob": 0.41845703125, "words": [ { "start": 2750.13, "end": 2750.17, "word": " So", "probability": 0.65087890625 }, { "start": 2750.17, "end": 2750.29, "word": " we're", "probability": 0.34600830078125 }, { "start": 2750.29, "end": 2750.31, "word": " going", "probability": 0.76416015625 }, { "start": 2750.31, "end": 2750.41, "word": " to", "probability": 0.83984375 }, { "start": 2750.41, "end": 2750.51, "word": " look", "probability": 0.1851806640625 }, { "start": 2750.51, "end": 2750.51, "word": " at", "probability": 0.9052734375 }, { "start": 2750.51, "end": 2750.69, "word": " each", "probability": 0.869140625 }, { "start": 2750.69, "end": 2751.27, "word": " filename", "probability": 0.8956705729166666 }, { "start": 2751.27, "end": 2751.43, "word": ",", "probability": 0.316650390625 } ] }, { "id": 1220, "seek": 272258, "start": 2751.43, "end": 2756.01, "text": " we're going to open each file,", "tokens": [ 50864, 321, 434, 516, 281, 1269, 1184, 3991, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.30597311107418207, "compression_ratio": 1.6689655172413793, "no_speech_prob": 0.41845703125, "words": [ { "start": 2751.43, "end": 2751.63, "word": " we're", "probability": 0.89697265625 }, { "start": 2751.63, "end": 2751.85, "word": " going", "probability": 0.8515625 }, { "start": 2751.85, "end": 2752.47, "word": " to", "probability": 0.9091796875 }, { "start": 2752.47, "end": 2753.95, "word": " open", "probability": 0.75634765625 }, { "start": 2753.95, "end": 2755.23, "word": " each", "probability": 0.85009765625 }, { "start": 2755.23, "end": 2755.67, "word": " file", "probability": 0.80712890625 }, { "start": 2755.67, "end": 2756.01, "word": ",", "probability": 0.47216796875 } ] }, { "id": 1221, "seek": 272258, "start": 2756.01, "end": 2763.11, "text": " so data.dir plus test plus filename,", "tokens": [ 51064, 370, 1412, 13, 35043, 1804, 1500, 1804, 1387, 268, 529, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.30597311107418207, "compression_ratio": 1.6689655172413793, "no_speech_prob": 0.41845703125, "words": [ { "start": 2756.01, "end": 2756.25, "word": " so", "probability": 0.82080078125 }, { "start": 2756.25, "end": 2757.17, "word": " data", "probability": 0.50927734375 }, { "start": 2757.17, "end": 2758.11, "word": ".dir", "probability": 0.6953125 }, { "start": 2758.11, "end": 2758.81, "word": " plus", "probability": 0.4931640625 }, { "start": 2758.81, "end": 2759.65, "word": " test", "probability": 0.7666015625 }, { "start": 2759.65, "end": 2760.95, "word": " plus", "probability": 0.81396484375 }, { "start": 2760.95, "end": 2762.99, "word": " filename", "probability": 0.9405924479166666 }, { "start": 2762.99, "end": 2763.11, "word": ",", "probability": 0.6484375 } ] }, { "id": 1222, "seek": 272258, "start": 2763.11, "end": 2768.23, "text": " and then we want to read those as the file descriptor F.", "tokens": [ 51464, 293, 550, 321, 528, 281, 1401, 729, 382, 264, 3991, 31280, 284, 479, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.30597311107418207, "compression_ratio": 1.6689655172413793, "no_speech_prob": 0.41845703125, "words": [ { "start": 2763.11, "end": 2763.27, "word": " and", "probability": 0.88525390625 }, { "start": 2763.27, "end": 2763.39, "word": " then", "probability": 0.7275390625 }, { "start": 2763.39, "end": 2763.47, "word": " we", "probability": 0.8994140625 }, { "start": 2763.47, "end": 2763.67, "word": " want", "probability": 0.796875 }, { "start": 2763.67, "end": 2763.91, "word": " to", "probability": 0.90673828125 }, { "start": 2763.91, "end": 2764.47, "word": " read", "probability": 0.904296875 }, { "start": 2764.47, "end": 2764.95, "word": " those", "probability": 0.8486328125 }, { "start": 2764.95, "end": 2765.81, "word": " as", "probability": 0.8916015625 }, { "start": 2765.81, "end": 2766.03, "word": " the", "probability": 0.81396484375 }, { "start": 2766.03, "end": 2766.29, "word": " file", "probability": 0.74267578125 }, { "start": 2766.29, "end": 2766.81, "word": " descriptor", "probability": 0.880859375 }, { "start": 2766.81, "end": 2767.31, "word": " F", "probability": 0.408447265625 }, { "start": 2767.31, "end": 2768.23, "word": ".", "probability": 0.96044921875 } ] }, { "id": 1223, "seek": 275106, "start": 2769.19, "end": 2774.09, "text": " So our test corpus, we're going to append F.read,", "tokens": [ 50414, 407, 527, 1500, 1181, 31624, 11, 321, 434, 516, 281, 34116, 479, 13, 2538, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.192425266718087, "compression_ratio": 1.5837837837837838, "no_speech_prob": 0.00690460205078125, "words": [ { "start": 2769.19, "end": 2769.75, "word": " So", "probability": 0.425537109375 }, { "start": 2769.75, "end": 2770.11, "word": " our", "probability": 0.625 }, { "start": 2770.11, "end": 2770.43, "word": " test", "probability": 0.744140625 }, { "start": 2770.43, "end": 2770.87, "word": " corpus", "probability": 0.794189453125 }, { "start": 2770.87, "end": 2771.09, "word": ",", "probability": 0.62109375 }, { "start": 2771.09, "end": 2771.19, "word": " we're", "probability": 0.910888671875 }, { "start": 2771.19, "end": 2771.41, "word": " going", "probability": 0.85302734375 }, { "start": 2771.41, "end": 2771.71, "word": " to", "probability": 0.90234375 }, { "start": 2771.71, "end": 2772.31, "word": " append", "probability": 0.85302734375 }, { "start": 2772.31, "end": 2773.17, "word": " F", "probability": 0.3125 }, { "start": 2773.17, "end": 2773.67, "word": ".read", "probability": 0.71435546875 }, { "start": 2773.67, "end": 2774.09, "word": ",", "probability": 0.65625 } ] }, { "id": 1224, "seek": 275106, "start": 2774.09, "end": 2777.29, "text": " which is going to read that email into our test corpus array,", "tokens": [ 50664, 597, 307, 516, 281, 1401, 300, 3796, 666, 527, 1500, 1181, 31624, 10225, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.192425266718087, "compression_ratio": 1.5837837837837838, "no_speech_prob": 0.00690460205078125, "words": [ { "start": 2774.09, "end": 2774.37, "word": " which", "probability": 0.9111328125 }, { "start": 2774.37, "end": 2774.47, "word": " is", "probability": 0.90478515625 }, { "start": 2774.47, "end": 2774.59, "word": " going", "probability": 0.86328125 }, { "start": 2774.59, "end": 2774.75, "word": " to", "probability": 0.90625 }, { "start": 2774.75, "end": 2774.95, "word": " read", "probability": 0.904296875 }, { "start": 2774.95, "end": 2775.13, "word": " that", "probability": 0.88134765625 }, { "start": 2775.13, "end": 2775.39, "word": " email", "probability": 0.876953125 }, { "start": 2775.39, "end": 2775.71, "word": " into", "probability": 0.7216796875 }, { "start": 2775.71, "end": 2775.89, "word": " our", "probability": 0.818359375 }, { "start": 2775.89, "end": 2776.17, "word": " test", "probability": 0.81005859375 }, { "start": 2776.17, "end": 2776.55, "word": " corpus", "probability": 0.90673828125 }, { "start": 2776.55, "end": 2776.97, "word": " array", "probability": 0.7587890625 }, { "start": 2776.97, "end": 2777.29, "word": ",", "probability": 0.431884765625 } ] }, { "id": 1225, "seek": 275106, "start": 2777.29, "end": 2779.83, "text": " and then we want to grab the label.", "tokens": [ 50814, 293, 550, 321, 528, 281, 4444, 264, 7645, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.192425266718087, "compression_ratio": 1.5837837837837838, "no_speech_prob": 0.00690460205078125, "words": [ { "start": 2777.29, "end": 2777.33, "word": " and", "probability": 0.88623046875 }, { "start": 2777.33, "end": 2777.61, "word": " then", "probability": 0.70751953125 }, { "start": 2777.61, "end": 2778.11, "word": " we", "probability": 0.6953125 }, { "start": 2778.11, "end": 2778.25, "word": " want", "probability": 0.76025390625 }, { "start": 2778.25, "end": 2778.43, "word": " to", "probability": 0.9033203125 }, { "start": 2778.43, "end": 2778.93, "word": " grab", "probability": 0.822265625 }, { "start": 2778.93, "end": 2779.21, "word": " the", "probability": 0.818359375 }, { "start": 2779.21, "end": 2779.57, "word": " label", "probability": 0.818359375 }, { "start": 2779.57, "end": 2779.83, "word": ".", "probability": 0.64404296875 } ] }, { "id": 1226, "seek": 275106, "start": 2779.83, "end": 2783.95, "text": " And in this case, I'm just going to use a simple regular expression.", "tokens": [ 50914, 400, 294, 341, 1389, 11, 286, 478, 445, 516, 281, 764, 257, 2199, 3890, 6114, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.192425266718087, "compression_ratio": 1.5837837837837838, "no_speech_prob": 0.00690460205078125, "words": [ { "start": 2779.83, "end": 2779.87, "word": " And", "probability": 0.703125 }, { "start": 2779.87, "end": 2779.97, "word": " in", "probability": 0.89013671875 }, { "start": 2779.97, "end": 2780.09, "word": " this", "probability": 0.87939453125 }, { "start": 2780.09, "end": 2780.25, "word": " case", "probability": 0.8095703125 }, { "start": 2780.25, "end": 2780.31, "word": ",", "probability": 0.81103515625 }, { "start": 2780.31, "end": 2780.41, "word": " I'm", "probability": 0.995849609375 }, { "start": 2780.41, "end": 2780.55, "word": " just", "probability": 0.8779296875 }, { "start": 2780.55, "end": 2780.69, "word": " going", "probability": 0.418212890625 }, { "start": 2780.69, "end": 2780.75, "word": " to", "probability": 0.9052734375 }, { "start": 2780.75, "end": 2780.97, "word": " use", "probability": 0.82568359375 }, { "start": 2781.17, "end": 2781.57, "word": " a simple", "probability": 0.9013671875 }, { "start": 2781.57, "end": 2782.19, "word": " regular", "probability": 0.6552734375 }, { "start": 2782.19, "end": 2783.39, "word": " expression", "probability": 0.84521484375 }, { "start": 2783.39, "end": 2783.95, "word": ".", "probability": 0.9228515625 } ] }, { "id": 1227, "seek": 275106, "start": 2785.39, "end": 2790.67, "text": " We're going to use txt, and then this is a backslash period,", "tokens": [ 51214, 492, 434, 516, 281, 764, 256, 734, 11, 293, 550, 341, 307, 257, 646, 10418, 1299, 2896, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.192425266718087, "compression_ratio": 1.5837837837837838, "no_speech_prob": 0.00690460205078125, "words": [ { "start": 2785.39, "end": 2785.95, "word": " We're", "probability": 0.89697265625 }, { "start": 2785.95, "end": 2786.03, "word": " going", "probability": 0.693359375 }, { "start": 2786.03, "end": 2786.05, "word": " to", "probability": 0.9072265625 }, { "start": 2786.05, "end": 2786.43, "word": " use", "probability": 0.8232421875 }, { "start": 2786.43, "end": 2787.13, "word": " txt", "probability": 0.763427734375 }, { "start": 2787.13, "end": 2787.49, "word": ",", "probability": 0.60205078125 }, { "start": 2787.49, "end": 2787.63, "word": " and", "probability": 0.88720703125 }, { "start": 2787.63, "end": 2787.75, "word": " then", "probability": 0.681640625 }, { "start": 2787.75, "end": 2787.91, "word": " this", "probability": 0.88623046875 }, { "start": 2787.91, "end": 2788.01, "word": " is", "probability": 0.90966796875 }, { "start": 2788.27, "end": 2789.05, "word": " a backslash", "probability": 0.8714192708333334 }, { "start": 2789.05, "end": 2789.71, "word": " period", "probability": 0.80712890625 }, { "start": 2789.71, "end": 2790.67, "word": ",", "probability": 0.404541015625 } ] }, { "id": 1228, "seek": 275106, "start": 2793.33, "end": 2796.71, "text": " and filename 1.", "tokens": [ 51564, 293, 1387, 268, 529, 502, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.192425266718087, "compression_ratio": 1.5837837837837838, "no_speech_prob": 0.00690460205078125, "words": [ { "start": 2793.33, "end": 2793.89, "word": " and", "probability": 0.869140625 }, { "start": 2793.89, "end": 2794.45, "word": " filename", "probability": 0.8331705729166666 }, { "start": 2794.45, "end": 2796.43, "word": " 1", "probability": 0.2298583984375 }, { "start": 2796.43, "end": 2796.71, "word": ".", "probability": 0.94921875 } ] }, { "id": 1229, "seek": 277696, "start": 2796.71, "end": 2800.05, "text": " I'm going to scroll up real quick, because the reason why I want to do that is", "tokens": [ 50364, 286, 478, 516, 281, 11369, 493, 957, 1702, 11, 570, 264, 1778, 983, 286, 528, 281, 360, 300, 307, 50514 ], "temperature": 0.0, "avg_logprob": -0.21337089699799897, "compression_ratio": 1.8454545454545455, "no_speech_prob": 0.063720703125, "words": [ { "start": 2796.71, "end": 2797.33, "word": " I'm", "probability": 0.492889404296875 }, { "start": 2797.33, "end": 2797.43, "word": " going", "probability": 0.5859375 }, { "start": 2797.43, "end": 2797.45, "word": " to", "probability": 0.90625 }, { "start": 2797.45, "end": 2797.65, "word": " scroll", "probability": 0.88671875 }, { "start": 2797.65, "end": 2797.83, "word": " up", "probability": 0.90576171875 }, { "start": 2797.83, "end": 2797.99, "word": " real", "probability": 0.82421875 }, { "start": 2797.99, "end": 2798.17, "word": " quick", "probability": 0.91357421875 }, { "start": 2798.17, "end": 2798.31, "word": ",", "probability": 0.193115234375 }, { "start": 2798.31, "end": 2798.49, "word": " because", "probability": 0.81494140625 }, { "start": 2798.49, "end": 2798.69, "word": " the", "probability": 0.802734375 }, { "start": 2798.69, "end": 2798.91, "word": " reason", "probability": 0.91650390625 }, { "start": 2798.91, "end": 2799.17, "word": " why", "probability": 0.73046875 }, { "start": 2799.17, "end": 2799.25, "word": " I", "probability": 0.96826171875 }, { "start": 2799.25, "end": 2799.37, "word": " want", "probability": 0.80810546875 }, { "start": 2799.37, "end": 2799.47, "word": " to", "probability": 0.90478515625 }, { "start": 2799.47, "end": 2799.63, "word": " do", "probability": 0.9072265625 }, { "start": 2799.63, "end": 2799.87, "word": " that", "probability": 0.87109375 }, { "start": 2799.87, "end": 2800.05, "word": " is", "probability": 0.7685546875 } ] }, { "id": 1230, "seek": 277696, "start": 2800.05, "end": 2805.35, "text": " what this is saying is, where we see txt.period, we're going to split,", "tokens": [ 50514, 437, 341, 307, 1566, 307, 11, 689, 321, 536, 256, 734, 13, 610, 2695, 11, 321, 434, 516, 281, 7472, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.21337089699799897, "compression_ratio": 1.8454545454545455, "no_speech_prob": 0.063720703125, "words": [ { "start": 2800.05, "end": 2800.21, "word": " what", "probability": 0.625 }, { "start": 2800.21, "end": 2800.41, "word": " this", "probability": 0.87353515625 }, { "start": 2800.41, "end": 2800.55, "word": " is", "probability": 0.89697265625 }, { "start": 2800.55, "end": 2800.91, "word": " saying", "probability": 0.81884765625 }, { "start": 2800.91, "end": 2801.43, "word": " is", "probability": 0.8623046875 }, { "start": 2801.43, "end": 2801.83, "word": ",", "probability": 0.26220703125 }, { "start": 2801.83, "end": 2801.91, "word": " where", "probability": 0.751953125 }, { "start": 2801.91, "end": 2802.05, "word": " we", "probability": 0.8994140625 }, { "start": 2802.05, "end": 2802.25, "word": " see", "probability": 0.80078125 }, { "start": 2802.25, "end": 2802.87, "word": " txt", "probability": 0.65283203125 }, { "start": 2802.87, "end": 2804.11, "word": ".period", "probability": 0.5318806966145834 }, { "start": 2804.11, "end": 2804.25, "word": ",", "probability": 0.736328125 }, { "start": 2804.25, "end": 2804.59, "word": " we're", "probability": 0.90771484375 }, { "start": 2804.59, "end": 2804.67, "word": " going", "probability": 0.7998046875 }, { "start": 2804.67, "end": 2804.81, "word": " to", "probability": 0.9013671875 }, { "start": 2804.81, "end": 2805.15, "word": " split", "probability": 0.80712890625 }, { "start": 2805.15, "end": 2805.35, "word": ",", "probability": 0.345703125 } ] }, { "id": 1231, "seek": 277696, "start": 2805.35, "end": 2809.69, "text": " so we have this full train txt.period, and then we have ham.", "tokens": [ 50764, 370, 321, 362, 341, 1577, 3847, 256, 734, 13, 610, 2695, 11, 293, 550, 321, 362, 7852, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.21337089699799897, "compression_ratio": 1.8454545454545455, "no_speech_prob": 0.063720703125, "words": [ { "start": 2805.35, "end": 2805.45, "word": " so", "probability": 0.8818359375 }, { "start": 2805.45, "end": 2805.59, "word": " we", "probability": 0.8984375 }, { "start": 2805.59, "end": 2805.99, "word": " have", "probability": 0.880859375 }, { "start": 2805.99, "end": 2806.31, "word": " this", "probability": 0.8564453125 }, { "start": 2806.31, "end": 2806.59, "word": " full", "probability": 0.67236328125 }, { "start": 2806.59, "end": 2807.03, "word": " train", "probability": 0.53271484375 }, { "start": 2807.03, "end": 2807.53, "word": " txt", "probability": 0.9208984375 }, { "start": 2807.53, "end": 2808.17, "word": ".period", "probability": 0.94970703125 }, { "start": 2808.17, "end": 2808.25, "word": ",", "probability": 0.453857421875 }, { "start": 2808.25, "end": 2808.37, "word": " and", "probability": 0.87353515625 }, { "start": 2808.37, "end": 2808.49, "word": " then", "probability": 0.6953125 }, { "start": 2808.49, "end": 2808.59, "word": " we", "probability": 0.87939453125 }, { "start": 2808.59, "end": 2808.83, "word": " have", "probability": 0.87841796875 }, { "start": 2808.83, "end": 2809.29, "word": " ham", "probability": 0.705078125 }, { "start": 2809.29, "end": 2809.69, "word": ".", "probability": 0.68212890625 } ] }, { "id": 1232, "seek": 277696, "start": 2809.91, "end": 2814.65, "text": " And then the bracket 1, what that is going to do is say,", "tokens": [ 51014, 400, 550, 264, 16904, 502, 11, 437, 300, 307, 516, 281, 360, 307, 584, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.21337089699799897, "compression_ratio": 1.8454545454545455, "no_speech_prob": 0.063720703125, "words": [ { "start": 2809.91, "end": 2810.09, "word": " And", "probability": 0.662109375 }, { "start": 2810.09, "end": 2810.25, "word": " then", "probability": 0.72119140625 }, { "start": 2810.25, "end": 2810.63, "word": " the", "probability": 0.74658203125 }, { "start": 2810.63, "end": 2811.67, "word": " bracket", "probability": 0.7138671875 }, { "start": 2811.67, "end": 2812.27, "word": " 1", "probability": 0.452392578125 }, { "start": 2812.27, "end": 2812.75, "word": ",", "probability": 0.87451171875 }, { "start": 2812.75, "end": 2812.95, "word": " what", "probability": 0.85546875 }, { "start": 2812.95, "end": 2813.09, "word": " that", "probability": 0.87841796875 }, { "start": 2813.09, "end": 2813.21, "word": " is", "probability": 0.8974609375 }, { "start": 2813.21, "end": 2813.33, "word": " going", "probability": 0.85595703125 }, { "start": 2813.33, "end": 2813.43, "word": " to", "probability": 0.90625 }, { "start": 2813.43, "end": 2813.69, "word": " do", "probability": 0.9013671875 }, { "start": 2813.69, "end": 2813.97, "word": " is", "probability": 0.845703125 }, { "start": 2813.97, "end": 2814.35, "word": " say", "probability": 0.81494140625 }, { "start": 2814.35, "end": 2814.65, "word": ",", "probability": 0.5185546875 } ] }, { "id": 1233, "seek": 277696, "start": 2814.65, "end": 2817.89, "text": " this is bracket 0 once it's split, and then this is bracket 1,", "tokens": [ 51264, 341, 307, 16904, 1958, 1564, 309, 311, 7472, 11, 293, 550, 341, 307, 16904, 502, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.21337089699799897, "compression_ratio": 1.8454545454545455, "no_speech_prob": 0.063720703125, "words": [ { "start": 2814.65, "end": 2815.15, "word": " this", "probability": 0.78271484375 }, { "start": 2815.15, "end": 2815.31, "word": " is", "probability": 0.869140625 }, { "start": 2815.31, "end": 2815.55, "word": " bracket", "probability": 0.7705078125 }, { "start": 2815.55, "end": 2815.97, "word": " 0", "probability": 0.91015625 }, { "start": 2815.97, "end": 2816.31, "word": " once", "probability": 0.5546875 }, { "start": 2816.31, "end": 2816.45, "word": " it's", "probability": 0.879150390625 }, { "start": 2816.45, "end": 2816.69, "word": " split", "probability": 0.845703125 }, { "start": 2816.69, "end": 2816.79, "word": ",", "probability": 0.78515625 }, { "start": 2816.79, "end": 2816.83, "word": " and", "probability": 0.8798828125 }, { "start": 2816.83, "end": 2816.97, "word": " then", "probability": 0.60546875 }, { "start": 2816.97, "end": 2817.15, "word": " this", "probability": 0.8759765625 }, { "start": 2817.15, "end": 2817.31, "word": " is", "probability": 0.904296875 }, { "start": 2817.31, "end": 2817.53, "word": " bracket", "probability": 0.8154296875 }, { "start": 2817.53, "end": 2817.83, "word": " 1", "probability": 0.9765625 }, { "start": 2817.83, "end": 2817.89, "word": ",", "probability": 0.529296875 } ] }, { "id": 1234, "seek": 277696, "start": 2817.89, "end": 2822.61, "text": " so we're just going to keep our labels, which are at the end of that split.", "tokens": [ 51414, 370, 321, 434, 445, 516, 281, 1066, 527, 16949, 11, 597, 366, 412, 264, 917, 295, 300, 7472, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.21337089699799897, "compression_ratio": 1.8454545454545455, "no_speech_prob": 0.063720703125, "words": [ { "start": 2817.89, "end": 2817.99, "word": " so", "probability": 0.88037109375 }, { "start": 2817.99, "end": 2818.11, "word": " we're", "probability": 0.9267578125 }, { "start": 2818.11, "end": 2818.23, "word": " just", "probability": 0.876953125 }, { "start": 2818.23, "end": 2818.39, "word": " going", "probability": 0.85693359375 }, { "start": 2818.39, "end": 2818.53, "word": " to", "probability": 0.9091796875 }, { "start": 2818.53, "end": 2818.79, "word": " keep", "probability": 0.83251953125 }, { "start": 2818.79, "end": 2819.11, "word": " our", "probability": 0.80908203125 }, { "start": 2819.11, "end": 2819.77, "word": " labels", "probability": 0.8623046875 }, { "start": 2819.77, "end": 2820.19, "word": ",", "probability": 0.61279296875 }, { "start": 2820.19, "end": 2820.43, "word": " which", "probability": 0.91357421875 }, { "start": 2820.43, "end": 2820.55, "word": " are", "probability": 0.89599609375 }, { "start": 2820.55, "end": 2820.95, "word": " at", "probability": 0.89404296875 }, { "start": 2820.95, "end": 2821.13, "word": " the", "probability": 0.82177734375 }, { "start": 2821.13, "end": 2821.39, "word": " end", "probability": 0.8154296875 }, { "start": 2821.39, "end": 2821.61, "word": " of", "probability": 0.9091796875 }, { "start": 2821.61, "end": 2821.83, "word": " that", "probability": 0.8798828125 }, { "start": 2821.83, "end": 2822.21, "word": " split", "probability": 0.86572265625 }, { "start": 2822.21, "end": 2822.61, "word": ".", "probability": 0.99609375 } ] }, { "id": 1235, "seek": 280306, "start": 2825.23, "end": 2829.99, "text": " And then with that label, or each label that we grab from the filename,", "tokens": [ 50414, 400, 550, 365, 300, 7645, 11, 420, 1184, 7645, 300, 321, 4444, 490, 264, 1387, 268, 529, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.21334135073881882, "compression_ratio": 1.5511363636363635, "no_speech_prob": 0.0014781951904296875, "words": [ { "start": 2825.23, "end": 2825.79, "word": " And", "probability": 0.71337890625 }, { "start": 2825.79, "end": 2826.03, "word": " then", "probability": 0.740234375 }, { "start": 2826.03, "end": 2826.49, "word": " with", "probability": 0.6513671875 }, { "start": 2826.49, "end": 2826.67, "word": " that", "probability": 0.86767578125 }, { "start": 2826.67, "end": 2827.11, "word": " label", "probability": 0.83251953125 }, { "start": 2827.11, "end": 2827.51, "word": ",", "probability": 0.5341796875 }, { "start": 2827.51, "end": 2827.83, "word": " or", "probability": 0.89453125 }, { "start": 2827.83, "end": 2828.07, "word": " each", "probability": 0.86376953125 }, { "start": 2828.07, "end": 2828.37, "word": " label", "probability": 0.81103515625 }, { "start": 2828.37, "end": 2828.53, "word": " that", "probability": 0.82763671875 }, { "start": 2828.53, "end": 2828.63, "word": " we", "probability": 0.9033203125 }, { "start": 2828.63, "end": 2828.83, "word": " grab", "probability": 0.548828125 }, { "start": 2828.83, "end": 2828.99, "word": " from", "probability": 0.81640625 }, { "start": 2828.99, "end": 2829.13, "word": " the", "probability": 0.81201171875 }, { "start": 2829.13, "end": 2829.71, "word": " filename", "probability": 0.7034505208333334 }, { "start": 2829.71, "end": 2829.99, "word": ",", "probability": 0.90625 } ] }, { "id": 1236, "seek": 280306, "start": 2829.99, "end": 2837.35, "text": " we're going to append it to our labels directory, or our labels array.", "tokens": [ 50714, 321, 434, 516, 281, 34116, 309, 281, 527, 16949, 21120, 11, 420, 527, 16949, 10225, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.21334135073881882, "compression_ratio": 1.5511363636363635, "no_speech_prob": 0.0014781951904296875, "words": [ { "start": 2829.99, "end": 2830.41, "word": " we're", "probability": 0.918701171875 }, { "start": 2830.41, "end": 2830.69, "word": " going", "probability": 0.85546875 }, { "start": 2830.69, "end": 2831.19, "word": " to", "probability": 0.90771484375 }, { "start": 2831.19, "end": 2832.01, "word": " append", "probability": 0.8798828125 }, { "start": 2832.01, "end": 2832.29, "word": " it", "probability": 0.8994140625 }, { "start": 2832.29, "end": 2833.39, "word": " to", "probability": 0.89306640625 }, { "start": 2833.39, "end": 2833.83, "word": " our", "probability": 0.81787109375 }, { "start": 2833.83, "end": 2834.37, "word": " labels", "probability": 0.80419921875 }, { "start": 2834.37, "end": 2835.03, "word": " directory", "probability": 0.8203125 }, { "start": 2835.03, "end": 2835.45, "word": ",", "probability": 0.57275390625 }, { "start": 2835.45, "end": 2835.89, "word": " or", "probability": 0.88232421875 }, { "start": 2835.89, "end": 2836.11, "word": " our", "probability": 0.7919921875 }, { "start": 2836.11, "end": 2836.37, "word": " labels", "probability": 0.8515625 }, { "start": 2836.37, "end": 2836.79, "word": " array", "probability": 0.79052734375 }, { "start": 2836.79, "end": 2837.35, "word": ".", "probability": 0.99365234375 } ] }, { "id": 1237, "seek": 280306, "start": 2839.21, "end": 2841.45, "text": " So this is what our code looks like.", "tokens": [ 51114, 407, 341, 307, 437, 527, 3089, 1542, 411, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.21334135073881882, "compression_ratio": 1.5511363636363635, "no_speech_prob": 0.0014781951904296875, "words": [ { "start": 2839.21, "end": 2839.77, "word": " So", "probability": 0.8544921875 }, { "start": 2839.77, "end": 2839.95, "word": " this", "probability": 0.80078125 }, { "start": 2839.95, "end": 2840.05, "word": " is", "probability": 0.9033203125 }, { "start": 2840.05, "end": 2840.17, "word": " what", "probability": 0.88623046875 }, { "start": 2840.17, "end": 2840.29, "word": " our", "probability": 0.81689453125 }, { "start": 2840.29, "end": 2840.49, "word": " code", "probability": 0.818359375 }, { "start": 2840.49, "end": 2840.71, "word": " looks", "probability": 0.7978515625 }, { "start": 2840.71, "end": 2841.05, "word": " like", "probability": 0.880859375 }, { "start": 2841.05, "end": 2841.45, "word": ".", "probability": 0.70263671875 } ] }, { "id": 1238, "seek": 280306, "start": 2841.45, "end": 2845.99, "text": " Double checking for errors, looks good to me.", "tokens": [ 51264, 16633, 8568, 337, 13603, 11, 1542, 665, 281, 385, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.21334135073881882, "compression_ratio": 1.5511363636363635, "no_speech_prob": 0.0014781951904296875, "words": [ { "start": 2841.45, "end": 2841.73, "word": " Double", "probability": 0.84130859375 }, { "start": 2841.73, "end": 2842.01, "word": " checking", "probability": 0.6201171875 }, { "start": 2842.01, "end": 2842.39, "word": " for", "probability": 0.7861328125 }, { "start": 2842.39, "end": 2843.05, "word": " errors", "probability": 0.83154296875 }, { "start": 2843.05, "end": 2843.53, "word": ",", "probability": 0.340576171875 }, { "start": 2843.53, "end": 2844.11, "word": " looks", "probability": 0.59375 }, { "start": 2844.11, "end": 2844.73, "word": " good", "probability": 0.87646484375 }, { "start": 2844.73, "end": 2845.01, "word": " to", "probability": 0.90673828125 }, { "start": 2845.01, "end": 2845.43, "word": " me", "probability": 0.904296875 }, { "start": 2845.43, "end": 2845.99, "word": ".", "probability": 0.75390625 } ] }, { "id": 1239, "seek": 280306, "start": 2846.39, "end": 2848.71, "text": " And I'm going to let this sit for a little bit,", "tokens": [ 51514, 400, 286, 478, 516, 281, 718, 341, 1394, 337, 257, 707, 857, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.21334135073881882, "compression_ratio": 1.5511363636363635, "no_speech_prob": 0.0014781951904296875, "words": [ { "start": 2846.39, "end": 2846.95, "word": " And", "probability": 0.8759765625 }, { "start": 2846.95, "end": 2847.17, "word": " I'm", "probability": 0.986083984375 }, { "start": 2847.17, "end": 2847.19, "word": " going", "probability": 0.2333984375 }, { "start": 2847.19, "end": 2847.21, "word": " to", "probability": 0.89404296875 }, { "start": 2847.21, "end": 2847.35, "word": " let", "probability": 0.888671875 }, { "start": 2847.35, "end": 2847.51, "word": " this", "probability": 0.86572265625 }, { "start": 2847.51, "end": 2847.69, "word": " sit", "probability": 0.90283203125 }, { "start": 2847.69, "end": 2847.85, "word": " for", "probability": 0.89306640625 }, { "start": 2847.97, "end": 2848.09, "word": " a little", "probability": 0.80224609375 }, { "start": 2848.09, "end": 2848.43, "word": " bit", "probability": 0.89404296875 }, { "start": 2848.43, "end": 2848.71, "word": ",", "probability": 0.398681640625 } ] }, { "id": 1240, "seek": 282966, "start": 2848.71, "end": 2851.63, "text": " so you guys can go ahead and copy that down.", "tokens": [ 50364, 370, 291, 1074, 393, 352, 2286, 293, 5055, 300, 760, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.23321759553603183, "compression_ratio": 1.4684210526315788, "no_speech_prob": 0.02716064453125, "words": [ { "start": 2848.71, "end": 2849.15, "word": " so", "probability": 0.259033203125 }, { "start": 2849.15, "end": 2849.33, "word": " you", "probability": 0.546875 }, { "start": 2849.33, "end": 2849.55, "word": " guys", "probability": 0.85498046875 }, { "start": 2849.55, "end": 2849.79, "word": " can", "probability": 0.896484375 }, { "start": 2849.79, "end": 2849.99, "word": " go", "probability": 0.87353515625 }, { "start": 2849.99, "end": 2850.17, "word": " ahead", "probability": 0.8369140625 }, { "start": 2850.17, "end": 2850.31, "word": " and", "probability": 0.88818359375 }, { "start": 2850.31, "end": 2850.55, "word": " copy", "probability": 0.7900390625 }, { "start": 2850.55, "end": 2850.77, "word": " that", "probability": 0.88232421875 }, { "start": 2850.77, "end": 2851.15, "word": " down", "probability": 0.82763671875 }, { "start": 2851.15, "end": 2851.63, "word": ".", "probability": 0.75 } ] }, { "id": 1241, "seek": 282966, "start": 2859.29, "end": 2861.17, "text": " How are we doing?", "tokens": [ 50564, 1012, 366, 321, 884, 30, 50764 ], "temperature": 0.0, "avg_logprob": -0.23321759553603183, "compression_ratio": 1.4684210526315788, "no_speech_prob": 0.02716064453125, "words": [ { "start": 2859.29, "end": 2859.77, "word": " How", "probability": 0.78271484375 }, { "start": 2859.77, "end": 2860.15, "word": " are", "probability": 0.8955078125 }, { "start": 2860.15, "end": 2860.39, "word": " we", "probability": 0.90576171875 }, { "start": 2860.39, "end": 2860.69, "word": " doing", "probability": 0.9228515625 }, { "start": 2860.69, "end": 2861.17, "word": "?", "probability": 0.95068359375 } ] }, { "id": 1242, "seek": 282966, "start": 2865.46, "end": 2870.78, "text": " No questions in Twitch stream, are there any questions in the Discord channel?", "tokens": [ 50764, 883, 1651, 294, 22222, 4309, 11, 366, 456, 604, 1651, 294, 264, 32623, 2269, 30, 51114 ], "temperature": 0.0, "avg_logprob": -0.23321759553603183, "compression_ratio": 1.4684210526315788, "no_speech_prob": 0.02716064453125, "words": [ { "start": 2865.46, "end": 2865.94, "word": " No", "probability": 0.88623046875 }, { "start": 2865.94, "end": 2866.38, "word": " questions", "probability": 0.90576171875 }, { "start": 2866.38, "end": 2866.6, "word": " in", "probability": 0.83447265625 }, { "start": 2866.6, "end": 2866.9, "word": " Twitch", "probability": 0.841796875 }, { "start": 2866.9, "end": 2867.3, "word": " stream", "probability": 0.798828125 }, { "start": 2867.3, "end": 2867.4, "word": ",", "probability": 0.233154296875 }, { "start": 2867.4, "end": 2867.5, "word": " are", "probability": 0.88818359375 }, { "start": 2867.5, "end": 2867.64, "word": " there", "probability": 0.86474609375 }, { "start": 2867.64, "end": 2867.84, "word": " any", "probability": 0.8251953125 }, { "start": 2867.84, "end": 2868.42, "word": " questions", "probability": 0.896484375 }, { "start": 2868.42, "end": 2869.14, "word": " in", "probability": 0.8984375 }, { "start": 2869.14, "end": 2869.66, "word": " the", "probability": 0.787109375 }, { "start": 2869.66, "end": 2869.96, "word": " Discord", "probability": 0.65087890625 }, { "start": 2869.96, "end": 2870.3, "word": " channel", "probability": 0.73681640625 }, { "start": 2870.3, "end": 2870.78, "word": "?", "probability": 0.98681640625 } ] }, { "id": 1243, "seek": 282966, "start": 2877.98, "end": 2881.42, "text": " Okay, I'm going to go ahead, shift, enter, and run.", "tokens": [ 51114, 1033, 11, 286, 478, 516, 281, 352, 2286, 11, 5513, 11, 3242, 11, 293, 1190, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.23321759553603183, "compression_ratio": 1.4684210526315788, "no_speech_prob": 0.02716064453125, "words": [ { "start": 2877.98, "end": 2878.46, "word": " Okay", "probability": 0.64794921875 }, { "start": 2878.46, "end": 2878.94, "word": ",", "probability": 0.505859375 }, { "start": 2878.94, "end": 2879.34, "word": " I'm", "probability": 0.860107421875 }, { "start": 2879.34, "end": 2879.36, "word": " going", "probability": 0.5322265625 }, { "start": 2879.36, "end": 2879.38, "word": " to", "probability": 0.904296875 }, { "start": 2879.38, "end": 2879.5, "word": " go", "probability": 0.89306640625 }, { "start": 2879.5, "end": 2879.84, "word": " ahead", "probability": 0.8505859375 }, { "start": 2879.84, "end": 2879.96, "word": ",", "probability": 0.479248046875 }, { "start": 2879.96, "end": 2880.18, "word": " shift", "probability": 0.591796875 }, { "start": 2880.18, "end": 2880.22, "word": ",", "probability": 0.353271484375 }, { "start": 2880.22, "end": 2880.54, "word": " enter", "probability": 0.70751953125 }, { "start": 2880.54, "end": 2880.68, "word": ",", "probability": 0.53515625 }, { "start": 2880.68, "end": 2880.82, "word": " and", "probability": 0.89453125 }, { "start": 2880.82, "end": 2881.18, "word": " run", "probability": 0.896484375 }, { "start": 2881.18, "end": 2881.42, "word": ".", "probability": 0.548828125 } ] }, { "id": 1244, "seek": 282966, "start": 2881.42, "end": 2884.04, "text": " So this is going to quickly load the emails.", "tokens": [ 51264, 407, 341, 307, 516, 281, 2661, 3677, 264, 12524, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.23321759553603183, "compression_ratio": 1.4684210526315788, "no_speech_prob": 0.02716064453125, "words": [ { "start": 2881.42, "end": 2881.56, "word": " So", "probability": 0.8740234375 }, { "start": 2881.56, "end": 2881.74, "word": " this", "probability": 0.744140625 }, { "start": 2881.74, "end": 2881.86, "word": " is", "probability": 0.90087890625 }, { "start": 2881.86, "end": 2882.02, "word": " going", "probability": 0.85595703125 }, { "start": 2882.02, "end": 2882.28, "word": " to", "probability": 0.90625 }, { "start": 2882.28, "end": 2882.68, "word": " quickly", "probability": 0.86474609375 }, { "start": 2882.68, "end": 2883.02, "word": " load", "probability": 0.91650390625 }, { "start": 2883.02, "end": 2883.18, "word": " the", "probability": 0.80712890625 }, { "start": 2883.18, "end": 2883.56, "word": " emails", "probability": 0.70263671875 }, { "start": 2883.56, "end": 2884.04, "word": ".", "probability": 0.55419921875 } ] }, { "id": 1245, "seek": 282966, "start": 2886.24, "end": 2889.4, "text": " And then let's run this next code block.", "tokens": [ 51514, 400, 550, 718, 311, 1190, 341, 958, 3089, 3461, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.23321759553603183, "compression_ratio": 1.4684210526315788, "no_speech_prob": 0.02716064453125, "words": [ { "start": 2886.24, "end": 2886.72, "word": " And", "probability": 0.87451171875 }, { "start": 2886.72, "end": 2887.02, "word": " then", "probability": 0.72314453125 }, { "start": 2887.02, "end": 2887.82, "word": " let's", "probability": 0.888916015625 }, { "start": 2887.82, "end": 2888.44, "word": " run", "probability": 0.91064453125 }, { "start": 2888.44, "end": 2888.64, "word": " this", "probability": 0.8798828125 }, { "start": 2888.64, "end": 2888.88, "word": " next", "probability": 0.87109375 }, { "start": 2888.88, "end": 2889.08, "word": " code", "probability": 0.82470703125 }, { "start": 2889.08, "end": 2889.32, "word": " block", "probability": 0.802734375 }, { "start": 2889.32, "end": 2889.4, "word": ".", "probability": 0.84228515625 } ] }, { "id": 1246, "seek": 285854, "start": 2889.4, "end": 2893.06, "text": " So what this is going to do is allow us to visualize our data, just like we did before.", "tokens": [ 50364, 407, 437, 341, 307, 516, 281, 360, 307, 2089, 505, 281, 23273, 527, 1412, 11, 445, 411, 321, 630, 949, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.1978210992769364, "compression_ratio": 1.6215139442231075, "no_speech_prob": 0.22802734375, "words": [ { "start": 2889.4, "end": 2889.4, "word": " So", "probability": 0.02880859375 }, { "start": 2889.4, "end": 2889.46, "word": " what", "probability": 0.703125 }, { "start": 2889.46, "end": 2889.62, "word": " this", "probability": 0.87451171875 }, { "start": 2889.62, "end": 2889.72, "word": " is", "probability": 0.9052734375 }, { "start": 2889.72, "end": 2889.88, "word": " going", "probability": 0.85498046875 }, { "start": 2889.88, "end": 2890.02, "word": " to", "probability": 0.90625 }, { "start": 2890.02, "end": 2890.18, "word": " do", "probability": 0.9072265625 }, { "start": 2890.18, "end": 2890.36, "word": " is", "probability": 0.87890625 }, { "start": 2890.36, "end": 2890.54, "word": " allow", "probability": 0.787109375 }, { "start": 2890.54, "end": 2890.74, "word": " us", "probability": 0.88525390625 }, { "start": 2890.74, "end": 2890.9, "word": " to", "probability": 0.90673828125 }, { "start": 2890.9, "end": 2891.24, "word": " visualize", "probability": 0.85498046875 }, { "start": 2891.24, "end": 2891.52, "word": " our", "probability": 0.8037109375 }, { "start": 2891.52, "end": 2891.76, "word": " data", "probability": 0.82470703125 }, { "start": 2891.76, "end": 2891.86, "word": ",", "probability": 0.25048828125 }, { "start": 2891.86, "end": 2892.0, "word": " just", "probability": 0.8798828125 }, { "start": 2892.0, "end": 2892.14, "word": " like", "probability": 0.87744140625 }, { "start": 2892.14, "end": 2892.26, "word": " we", "probability": 0.904296875 }, { "start": 2892.26, "end": 2892.38, "word": " did", "probability": 0.89892578125 }, { "start": 2892.38, "end": 2892.82, "word": " before", "probability": 0.794921875 }, { "start": 2892.82, "end": 2893.06, "word": ".", "probability": 0.85107421875 } ] }, { "id": 1247, "seek": 285854, "start": 2893.06, "end": 2899.2, "text": " So we see in our testing set, we have 590 ham emails, 276 spam emails,", "tokens": [ 50564, 407, 321, 536, 294, 527, 4997, 992, 11, 321, 362, 1025, 7771, 7852, 12524, 11, 7634, 21, 24028, 12524, 11, 50864 ], "temperature": 0.0, "avg_logprob": -0.1978210992769364, "compression_ratio": 1.6215139442231075, "no_speech_prob": 0.22802734375, "words": [ { "start": 2893.06, "end": 2893.26, "word": " So", "probability": 0.76611328125 }, { "start": 2893.26, "end": 2893.38, "word": " we", "probability": 0.86181640625 }, { "start": 2893.38, "end": 2893.5, "word": " see", "probability": 0.81884765625 }, { "start": 2893.5, "end": 2893.6, "word": " in", "probability": 0.86279296875 }, { "start": 2893.6, "end": 2893.76, "word": " our", "probability": 0.814453125 }, { "start": 2893.76, "end": 2894.4, "word": " testing", "probability": 0.66357421875 }, { "start": 2894.4, "end": 2894.8, "word": " set", "probability": 0.8984375 }, { "start": 2894.8, "end": 2894.98, "word": ",", "probability": 0.60546875 }, { "start": 2894.98, "end": 2895.1, "word": " we", "probability": 0.89306640625 }, { "start": 2895.1, "end": 2895.4, "word": " have", "probability": 0.88037109375 }, { "start": 2895.4, "end": 2896.18, "word": " 590", "probability": 0.946533203125 }, { "start": 2896.18, "end": 2896.62, "word": " ham", "probability": 0.463134765625 }, { "start": 2896.62, "end": 2897.02, "word": " emails", "probability": 0.7333984375 }, { "start": 2897.02, "end": 2897.16, "word": ",", "probability": 0.97802734375 }, { "start": 2897.16, "end": 2898.02, "word": " 276", "probability": 0.901611328125 }, { "start": 2898.02, "end": 2898.38, "word": " spam", "probability": 0.93359375 }, { "start": 2898.38, "end": 2898.88, "word": " emails", "probability": 0.7587890625 }, { "start": 2898.88, "end": 2899.2, "word": ",", "probability": 0.452880859375 } ] }, { "id": 1248, "seek": 285854, "start": 2899.2, "end": 2903.04, "text": " and the graph itself looks nearly identical to the one above,", "tokens": [ 50864, 293, 264, 4295, 2564, 1542, 6217, 14800, 281, 264, 472, 3673, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.1978210992769364, "compression_ratio": 1.6215139442231075, "no_speech_prob": 0.22802734375, "words": [ { "start": 2899.2, "end": 2899.84, "word": " and", "probability": 0.890625 }, { "start": 2899.84, "end": 2899.98, "word": " the", "probability": 0.8134765625 }, { "start": 2899.98, "end": 2900.2, "word": " graph", "probability": 0.7939453125 }, { "start": 2900.2, "end": 2900.54, "word": " itself", "probability": 0.7529296875 }, { "start": 2900.54, "end": 2900.86, "word": " looks", "probability": 0.80615234375 }, { "start": 2900.86, "end": 2901.26, "word": " nearly", "probability": 0.84619140625 }, { "start": 2901.26, "end": 2901.76, "word": " identical", "probability": 0.806640625 }, { "start": 2901.76, "end": 2902.44, "word": " to", "probability": 0.89697265625 }, { "start": 2902.44, "end": 2902.56, "word": " the", "probability": 0.81787109375 }, { "start": 2902.56, "end": 2902.68, "word": " one", "probability": 0.81982421875 }, { "start": 2902.68, "end": 2902.94, "word": " above", "probability": 0.89501953125 }, { "start": 2902.94, "end": 2903.04, "word": ",", "probability": 0.49267578125 } ] }, { "id": 1249, "seek": 285854, "start": 2903.04, "end": 2909.16, "text": " and that's because we did a random 80-20 split for our training and testing.", "tokens": [ 51064, 293, 300, 311, 570, 321, 630, 257, 4974, 4688, 12, 2009, 7472, 337, 527, 3097, 293, 4997, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.1978210992769364, "compression_ratio": 1.6215139442231075, "no_speech_prob": 0.22802734375, "words": [ { "start": 2903.04, "end": 2903.08, "word": " and", "probability": 0.89599609375 }, { "start": 2903.08, "end": 2903.26, "word": " that's", "probability": 0.937744140625 }, { "start": 2903.26, "end": 2903.44, "word": " because", "probability": 0.83740234375 }, { "start": 2903.44, "end": 2903.62, "word": " we", "probability": 0.90380859375 }, { "start": 2903.62, "end": 2903.98, "word": " did", "probability": 0.89404296875 }, { "start": 2904.56, "end": 2905.96, "word": " a random", "probability": 0.6826171875 }, { "start": 2905.96, "end": 2906.36, "word": " 80", "probability": 0.93310546875 }, { "start": 2906.36, "end": 2906.74, "word": "-20", "probability": 0.64453125 }, { "start": 2906.74, "end": 2907.22, "word": " split", "probability": 0.8857421875 }, { "start": 2907.22, "end": 2907.9, "word": " for", "probability": 0.86279296875 }, { "start": 2907.9, "end": 2908.04, "word": " our", "probability": 0.79736328125 }, { "start": 2908.04, "end": 2908.24, "word": " training", "probability": 0.79248046875 }, { "start": 2908.24, "end": 2908.42, "word": " and", "probability": 0.8955078125 }, { "start": 2908.42, "end": 2908.72, "word": " testing", "probability": 0.7353515625 }, { "start": 2908.72, "end": 2909.16, "word": ".", "probability": 0.80810546875 } ] }, { "id": 1250, "seek": 285854, "start": 2910.3, "end": 2913.02, "text": " And that was already done beforehand.", "tokens": [ 51414, 400, 300, 390, 1217, 1096, 22893, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.1978210992769364, "compression_ratio": 1.6215139442231075, "no_speech_prob": 0.22802734375, "words": [ { "start": 2910.3, "end": 2910.74, "word": " And", "probability": 0.822265625 }, { "start": 2910.74, "end": 2910.84, "word": " that", "probability": 0.88037109375 }, { "start": 2910.84, "end": 2910.98, "word": " was", "probability": 0.8935546875 }, { "start": 2910.98, "end": 2911.2, "word": " already", "probability": 0.845703125 }, { "start": 2911.2, "end": 2911.64, "word": " done", "probability": 0.7939453125 }, { "start": 2911.64, "end": 2912.58, "word": " beforehand", "probability": 0.8193359375 }, { "start": 2912.58, "end": 2913.02, "word": ".", "probability": 0.99365234375 } ] }, { "id": 1251, "seek": 285854, "start": 2914.46, "end": 2918.28, "text": " So the next thing we want to do is use the vectorizers that we created,", "tokens": [ 51614, 407, 264, 958, 551, 321, 528, 281, 360, 307, 764, 264, 8062, 22525, 300, 321, 2942, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.1978210992769364, "compression_ratio": 1.6215139442231075, "no_speech_prob": 0.22802734375, "words": [ { "start": 2914.46, "end": 2914.9, "word": " So", "probability": 0.88037109375 }, { "start": 2914.9, "end": 2915.12, "word": " the", "probability": 0.712890625 }, { "start": 2915.12, "end": 2915.24, "word": " next", "probability": 0.8623046875 }, { "start": 2915.24, "end": 2915.36, "word": " thing", "probability": 0.8125 }, { "start": 2915.36, "end": 2915.46, "word": " we", "probability": 0.8896484375 }, { "start": 2915.46, "end": 2915.58, "word": " want", "probability": 0.623046875 }, { "start": 2915.58, "end": 2915.66, "word": " to", "probability": 0.90673828125 }, { "start": 2915.66, "end": 2915.88, "word": " do", "probability": 0.90625 }, { "start": 2915.88, "end": 2916.28, "word": " is", "probability": 0.89501953125 }, { "start": 2916.28, "end": 2916.66, "word": " use", "probability": 0.8125 }, { "start": 2916.66, "end": 2916.88, "word": " the", "probability": 0.81103515625 }, { "start": 2916.88, "end": 2917.44, "word": " vectorizers", "probability": 0.933349609375 }, { "start": 2917.44, "end": 2917.64, "word": " that", "probability": 0.87255859375 }, { "start": 2917.64, "end": 2917.74, "word": " we", "probability": 0.904296875 }, { "start": 2917.74, "end": 2918.14, "word": " created", "probability": 0.732421875 }, { "start": 2918.14, "end": 2918.28, "word": ",", "probability": 0.8515625 } ] }, { "id": 1252, "seek": 288668, "start": 2918.28, "end": 2922.64, "text": " the cvec and the tvec vectorizer,", "tokens": [ 50364, 264, 269, 303, 66, 293, 264, 256, 303, 66, 8062, 6545, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.21585647637645403, "compression_ratio": 1.78, "no_speech_prob": 0.05108642578125, "words": [ { "start": 2918.28, "end": 2918.44, "word": " the", "probability": 0.171875 }, { "start": 2918.44, "end": 2919.02, "word": " cvec", "probability": 0.6116129557291666 }, { "start": 2919.02, "end": 2919.32, "word": " and", "probability": 0.85107421875 }, { "start": 2919.32, "end": 2920.46, "word": " the", "probability": 0.71142578125 }, { "start": 2920.46, "end": 2921.12, "word": " tvec", "probability": 0.93701171875 }, { "start": 2921.12, "end": 2921.84, "word": " vectorizer", "probability": 0.9033203125 }, { "start": 2921.84, "end": 2922.64, "word": ",", "probability": 0.36376953125 } ] }, { "id": 1253, "seek": 288668, "start": 2922.64, "end": 2926.28, "text": " and take a look at the test corpus,", "tokens": [ 50564, 293, 747, 257, 574, 412, 264, 1500, 1181, 31624, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.21585647637645403, "compression_ratio": 1.78, "no_speech_prob": 0.05108642578125, "words": [ { "start": 2922.64, "end": 2923.3, "word": " and", "probability": 0.8466796875 }, { "start": 2923.3, "end": 2924.22, "word": " take", "probability": 0.79833984375 }, { "start": 2924.36, "end": 2924.56, "word": " a look", "probability": 0.91162109375 }, { "start": 2924.56, "end": 2924.86, "word": " at", "probability": 0.90234375 }, { "start": 2924.86, "end": 2925.06, "word": " the", "probability": 0.8125 }, { "start": 2925.06, "end": 2925.34, "word": " test", "probability": 0.7275390625 }, { "start": 2925.34, "end": 2925.82, "word": " corpus", "probability": 0.831787109375 }, { "start": 2925.82, "end": 2926.28, "word": ",", "probability": 0.25244140625 } ] }, { "id": 1254, "seek": 288668, "start": 2926.28, "end": 2931.78, "text": " and get our counts of each word in the new emails.", "tokens": [ 50764, 293, 483, 527, 14893, 295, 1184, 1349, 294, 264, 777, 12524, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.21585647637645403, "compression_ratio": 1.78, "no_speech_prob": 0.05108642578125, "words": [ { "start": 2926.28, "end": 2926.76, "word": " and", "probability": 0.88037109375 }, { "start": 2926.76, "end": 2927.28, "word": " get", "probability": 0.88916015625 }, { "start": 2927.28, "end": 2927.72, "word": " our", "probability": 0.80029296875 }, { "start": 2927.72, "end": 2928.44, "word": " counts", "probability": 0.7724609375 }, { "start": 2928.44, "end": 2928.72, "word": " of", "probability": 0.8974609375 }, { "start": 2928.72, "end": 2928.96, "word": " each", "probability": 0.8701171875 }, { "start": 2928.96, "end": 2929.4, "word": " word", "probability": 0.80126953125 }, { "start": 2929.4, "end": 2930.24, "word": " in", "probability": 0.87255859375 }, { "start": 2930.24, "end": 2930.56, "word": " the", "probability": 0.8154296875 }, { "start": 2930.56, "end": 2930.8, "word": " new", "probability": 0.822265625 }, { "start": 2930.8, "end": 2931.24, "word": " emails", "probability": 0.7705078125 }, { "start": 2931.24, "end": 2931.78, "word": ".", "probability": 0.98291015625 } ] }, { "id": 1255, "seek": 288668, "start": 2932.56, "end": 2938.56, "text": " So let's go ahead, testCountX equals, and we're already going to use cvec,", "tokens": [ 51064, 407, 718, 311, 352, 2286, 11, 1500, 34, 792, 55, 6915, 11, 293, 321, 434, 1217, 516, 281, 764, 269, 303, 66, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.21585647637645403, "compression_ratio": 1.78, "no_speech_prob": 0.05108642578125, "words": [ { "start": 2932.56, "end": 2932.68, "word": " So", "probability": 0.658203125 }, { "start": 2932.68, "end": 2932.98, "word": " let's", "probability": 0.816650390625 }, { "start": 2932.98, "end": 2933.14, "word": " go", "probability": 0.888671875 }, { "start": 2933.14, "end": 2933.66, "word": " ahead", "probability": 0.849609375 }, { "start": 2933.66, "end": 2934.6, "word": ",", "probability": 0.5810546875 }, { "start": 2934.6, "end": 2935.96, "word": " testCountX", "probability": 0.660491943359375 }, { "start": 2935.96, "end": 2936.86, "word": " equals", "probability": 0.492431640625 }, { "start": 2936.86, "end": 2937.08, "word": ",", "probability": 0.67919921875 }, { "start": 2937.08, "end": 2937.18, "word": " and", "probability": 0.826171875 }, { "start": 2937.18, "end": 2937.32, "word": " we're", "probability": 0.917236328125 }, { "start": 2937.32, "end": 2937.58, "word": " already", "probability": 0.81884765625 }, { "start": 2937.58, "end": 2937.74, "word": " going", "probability": 0.36083984375 }, { "start": 2937.74, "end": 2937.74, "word": " to", "probability": 0.90283203125 }, { "start": 2937.74, "end": 2938.0, "word": " use", "probability": 0.78271484375 }, { "start": 2938.0, "end": 2938.5, "word": " cvec", "probability": 0.9495442708333334 }, { "start": 2938.5, "end": 2938.56, "word": ",", "probability": 0.437744140625 } ] }, { "id": 1256, "seek": 288668, "start": 2938.56, "end": 2941.9, "text": " we're not going to use fitTransform, instead we're going to use transform,", "tokens": [ 51364, 321, 434, 406, 516, 281, 764, 3318, 33339, 837, 11, 2602, 321, 434, 516, 281, 764, 4088, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.21585647637645403, "compression_ratio": 1.78, "no_speech_prob": 0.05108642578125, "words": [ { "start": 2938.56, "end": 2938.66, "word": " we're", "probability": 0.91845703125 }, { "start": 2938.66, "end": 2938.78, "word": " not", "probability": 0.88525390625 }, { "start": 2938.78, "end": 2938.88, "word": " going", "probability": 0.828125 }, { "start": 2938.88, "end": 2938.9, "word": " to", "probability": 0.90576171875 }, { "start": 2938.9, "end": 2939.08, "word": " use", "probability": 0.77490234375 }, { "start": 2939.08, "end": 2939.88, "word": " fitTransform", "probability": 0.732421875 }, { "start": 2939.88, "end": 2940.0, "word": ",", "probability": 0.75537109375 }, { "start": 2940.0, "end": 2940.18, "word": " instead", "probability": 0.8173828125 }, { "start": 2940.18, "end": 2940.34, "word": " we're", "probability": 0.893798828125 }, { "start": 2940.34, "end": 2940.42, "word": " going", "probability": 0.83447265625 }, { "start": 2940.42, "end": 2940.48, "word": " to", "probability": 0.90576171875 }, { "start": 2940.48, "end": 2940.66, "word": " use", "probability": 0.77880859375 }, { "start": 2940.66, "end": 2941.3, "word": " transform", "probability": 0.8076171875 }, { "start": 2941.3, "end": 2941.9, "word": ",", "probability": 0.66162109375 } ] }, { "id": 1257, "seek": 288668, "start": 2941.9, "end": 2946.42, "text": " because we're not trying to train it, we're just trying to save the words themselves.", "tokens": [ 51564, 570, 321, 434, 406, 1382, 281, 3847, 309, 11, 321, 434, 445, 1382, 281, 3155, 264, 2283, 2969, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.21585647637645403, "compression_ratio": 1.78, "no_speech_prob": 0.05108642578125, "words": [ { "start": 2941.9, "end": 2942.34, "word": " because", "probability": 0.828125 }, { "start": 2942.34, "end": 2942.48, "word": " we're", "probability": 0.93017578125 }, { "start": 2942.48, "end": 2942.7, "word": " not", "probability": 0.89306640625 }, { "start": 2942.7, "end": 2943.08, "word": " trying", "probability": 0.80029296875 }, { "start": 2943.08, "end": 2943.28, "word": " to", "probability": 0.900390625 }, { "start": 2943.28, "end": 2943.7, "word": " train", "probability": 0.81640625 }, { "start": 2943.7, "end": 2943.88, "word": " it", "probability": 0.89892578125 }, { "start": 2943.88, "end": 2943.96, "word": ",", "probability": 0.921875 }, { "start": 2943.96, "end": 2944.08, "word": " we're", "probability": 0.927734375 }, { "start": 2944.08, "end": 2944.22, "word": " just", "probability": 0.880859375 }, { "start": 2944.22, "end": 2944.44, "word": " trying", "probability": 0.802734375 }, { "start": 2944.44, "end": 2944.66, "word": " to", "probability": 0.900390625 }, { "start": 2944.66, "end": 2945.0, "word": " save", "probability": 0.8779296875 }, { "start": 2945.0, "end": 2945.2, "word": " the", "probability": 0.81103515625 }, { "start": 2945.2, "end": 2945.44, "word": " words", "probability": 0.708984375 }, { "start": 2945.44, "end": 2946.0, "word": " themselves", "probability": 0.7607421875 }, { "start": 2946.0, "end": 2946.42, "word": ".", "probability": 0.98486328125 } ] }, { "id": 1258, "seek": 291388, "start": 2947.68, "end": 2960.04, "text": " We'll do testCorpus, and then testTFIDFX equals tvec.transform testCorpus.", "tokens": [ 50414, 492, 603, 360, 1500, 34, 18703, 301, 11, 293, 550, 1500, 51, 37, 2777, 36092, 6915, 256, 303, 66, 13, 24999, 837, 1500, 34, 18703, 301, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.22220203176487324, "compression_ratio": 1.5027932960893855, "no_speech_prob": 0.0018100738525390625, "words": [ { "start": 2947.68, "end": 2948.16, "word": " We'll", "probability": 0.7041015625 }, { "start": 2948.16, "end": 2948.32, "word": " do", "probability": 0.9052734375 }, { "start": 2948.32, "end": 2949.18, "word": " testCorpus", "probability": 0.704345703125 }, { "start": 2949.18, "end": 2949.52, "word": ",", "probability": 0.324951171875 }, { "start": 2949.52, "end": 2951.0, "word": " and", "probability": 0.8828125 }, { "start": 2951.0, "end": 2951.36, "word": " then", "probability": 0.76123046875 }, { "start": 2951.36, "end": 2953.36, "word": " testTFIDFX", "probability": 0.525537109375 }, { "start": 2953.36, "end": 2954.16, "word": " equals", "probability": 0.541015625 }, { "start": 2954.16, "end": 2955.02, "word": " tvec", "probability": 0.79443359375 }, { "start": 2955.02, "end": 2956.74, "word": ".transform", "probability": 0.8499348958333334 }, { "start": 2956.74, "end": 2959.56, "word": " testCorpus", "probability": 0.83807373046875 }, { "start": 2959.56, "end": 2960.04, "word": ".", "probability": 0.77880859375 } ] }, { "id": 1259, "seek": 291388, "start": 2960.28, "end": 2965.94, "text": " And that's all we need to do when we're using a piece of testing data.", "tokens": [ 51064, 400, 300, 311, 439, 321, 643, 281, 360, 562, 321, 434, 1228, 257, 2522, 295, 4997, 1412, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.22220203176487324, "compression_ratio": 1.5027932960893855, "no_speech_prob": 0.0018100738525390625, "words": [ { "start": 2960.28, "end": 2960.76, "word": " And", "probability": 0.86181640625 }, { "start": 2960.76, "end": 2960.96, "word": " that's", "probability": 0.9384765625 }, { "start": 2960.96, "end": 2961.3, "word": " all", "probability": 0.8994140625 }, { "start": 2961.3, "end": 2961.44, "word": " we", "probability": 0.90673828125 }, { "start": 2961.44, "end": 2961.62, "word": " need", "probability": 0.81103515625 }, { "start": 2961.62, "end": 2961.74, "word": " to", "probability": 0.90673828125 }, { "start": 2961.74, "end": 2962.06, "word": " do", "probability": 0.90869140625 }, { "start": 2962.06, "end": 2962.58, "word": " when", "probability": 0.8515625 }, { "start": 2962.58, "end": 2962.72, "word": " we're", "probability": 0.931640625 }, { "start": 2962.72, "end": 2963.1, "word": " using", "probability": 0.8291015625 }, { "start": 2963.7, "end": 2964.54, "word": " a piece", "probability": 0.794921875 }, { "start": 2964.54, "end": 2964.68, "word": " of", "probability": 0.90673828125 }, { "start": 2964.68, "end": 2965.08, "word": " testing", "probability": 0.7197265625 }, { "start": 2965.08, "end": 2965.46, "word": " data", "probability": 0.80078125 }, { "start": 2965.46, "end": 2965.94, "word": ".", "probability": 0.98828125 } ] }, { "id": 1260, "seek": 291388, "start": 2967.7, "end": 2970.32, "text": " So I'm going to let that sit for a second,", "tokens": [ 51414, 407, 286, 478, 516, 281, 718, 300, 1394, 337, 257, 1150, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.22220203176487324, "compression_ratio": 1.5027932960893855, "no_speech_prob": 0.0018100738525390625, "words": [ { "start": 2967.7, "end": 2968.18, "word": " So", "probability": 0.822265625 }, { "start": 2968.18, "end": 2968.66, "word": " I'm", "probability": 0.5537109375 }, { "start": 2968.66, "end": 2968.68, "word": " going", "probability": 0.19189453125 }, { "start": 2968.68, "end": 2968.68, "word": " to", "probability": 0.89404296875 }, { "start": 2968.68, "end": 2968.86, "word": " let", "probability": 0.8896484375 }, { "start": 2968.86, "end": 2969.08, "word": " that", "probability": 0.88037109375 }, { "start": 2969.08, "end": 2969.26, "word": " sit", "probability": 0.90576171875 }, { "start": 2969.26, "end": 2969.42, "word": " for", "probability": 0.89697265625 }, { "start": 2969.58, "end": 2969.82, "word": " a second", "probability": 0.7998046875 }, { "start": 2969.82, "end": 2970.32, "word": ",", "probability": 0.10174560546875 } ] }, { "id": 1261, "seek": 291388, "start": 2970.32, "end": 2973.62, "text": " actually I'm going to run it because this is going to take a little bit as well.", "tokens": [ 51564, 767, 286, 478, 516, 281, 1190, 309, 570, 341, 307, 516, 281, 747, 257, 707, 857, 382, 731, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.22220203176487324, "compression_ratio": 1.5027932960893855, "no_speech_prob": 0.0018100738525390625, "words": [ { "start": 2970.32, "end": 2970.6, "word": " actually", "probability": 0.70166015625 }, { "start": 2970.6, "end": 2970.8, "word": " I'm", "probability": 0.860595703125 }, { "start": 2970.8, "end": 2970.82, "word": " going", "probability": 0.77978515625 }, { "start": 2970.82, "end": 2970.88, "word": " to", "probability": 0.8994140625 }, { "start": 2970.88, "end": 2971.12, "word": " run", "probability": 0.90673828125 }, { "start": 2971.12, "end": 2971.26, "word": " it", "probability": 0.8994140625 }, { "start": 2971.26, "end": 2971.42, "word": " because", "probability": 0.39013671875 }, { "start": 2971.42, "end": 2971.58, "word": " this", "probability": 0.79296875 }, { "start": 2971.58, "end": 2971.68, "word": " is", "probability": 0.9052734375 }, { "start": 2971.68, "end": 2971.8, "word": " going", "probability": 0.82861328125 }, { "start": 2971.8, "end": 2971.88, "word": " to", "probability": 0.90087890625 }, { "start": 2971.88, "end": 2972.04, "word": " take", "probability": 0.82177734375 }, { "start": 2972.16, "end": 2972.26, "word": " a little", "probability": 0.80712890625 }, { "start": 2972.26, "end": 2972.46, "word": " bit", "probability": 0.890625 }, { "start": 2972.46, "end": 2972.7, "word": " as", "probability": 0.88623046875 }, { "start": 2972.7, "end": 2973.14, "word": " well", "probability": 0.86962890625 }, { "start": 2973.14, "end": 2973.62, "word": ".", "probability": 0.9794921875 } ] }, { "id": 1262, "seek": 294254, "start": 2976.62, "end": 2978.9, "text": " Slightly shorter than when we were training it,", "tokens": [ 50414, 318, 44872, 11639, 813, 562, 321, 645, 3097, 309, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.21141304943872535, "compression_ratio": 1.7098039215686274, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 2976.62, "end": 2977.02, "word": " Slightly", "probability": 0.5052490234375 }, { "start": 2977.02, "end": 2977.42, "word": " shorter", "probability": 0.62158203125 }, { "start": 2977.42, "end": 2977.84, "word": " than", "probability": 0.86376953125 }, { "start": 2977.84, "end": 2977.98, "word": " when", "probability": 0.70361328125 }, { "start": 2977.98, "end": 2978.12, "word": " we", "probability": 0.90576171875 }, { "start": 2978.12, "end": 2978.24, "word": " were", "probability": 0.8720703125 }, { "start": 2978.24, "end": 2978.58, "word": " training", "probability": 0.7900390625 }, { "start": 2978.58, "end": 2978.8, "word": " it", "probability": 0.90087890625 }, { "start": 2978.8, "end": 2978.9, "word": ",", "probability": 0.70556640625 } ] }, { "id": 1263, "seek": 294254, "start": 2978.9, "end": 2984.94, "text": " but it still needs to go through all the emails and apply the counts,", "tokens": [ 50614, 457, 309, 920, 2203, 281, 352, 807, 439, 264, 12524, 293, 3079, 264, 14893, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.21141304943872535, "compression_ratio": 1.7098039215686274, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 2978.9, "end": 2979.06, "word": " but", "probability": 0.8994140625 }, { "start": 2979.06, "end": 2979.26, "word": " it", "probability": 0.90625 }, { "start": 2979.26, "end": 2979.44, "word": " still", "probability": 0.91015625 }, { "start": 2979.44, "end": 2979.64, "word": " needs", "probability": 0.755859375 }, { "start": 2979.64, "end": 2979.78, "word": " to", "probability": 0.90380859375 }, { "start": 2979.78, "end": 2979.92, "word": " go", "probability": 0.896484375 }, { "start": 2979.92, "end": 2980.1, "word": " through", "probability": 0.787109375 }, { "start": 2980.1, "end": 2980.3, "word": " all", "probability": 0.9033203125 }, { "start": 2980.3, "end": 2980.46, "word": " the", "probability": 0.72705078125 }, { "start": 2980.46, "end": 2980.92, "word": " emails", "probability": 0.72900390625 }, { "start": 2980.92, "end": 2981.44, "word": " and", "probability": 0.83642578125 }, { "start": 2981.44, "end": 2982.06, "word": " apply", "probability": 0.84228515625 }, { "start": 2982.06, "end": 2984.16, "word": " the", "probability": 0.77392578125 }, { "start": 2984.16, "end": 2984.58, "word": " counts", "probability": 0.72705078125 }, { "start": 2984.58, "end": 2984.94, "word": ",", "probability": 0.2451171875 } ] }, { "id": 1264, "seek": 294254, "start": 2984.94, "end": 2987.46, "text": " and then the TFIDF, it needs to apply the weights.", "tokens": [ 50914, 293, 550, 264, 40964, 2777, 37, 11, 309, 2203, 281, 3079, 264, 17443, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.21141304943872535, "compression_ratio": 1.7098039215686274, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 2984.94, "end": 2985.32, "word": " and", "probability": 0.890625 }, { "start": 2985.32, "end": 2985.44, "word": " then", "probability": 0.73681640625 }, { "start": 2985.44, "end": 2985.6, "word": " the", "probability": 0.7958984375 }, { "start": 2985.6, "end": 2986.2, "word": " TFIDF", "probability": 0.3759358723958333 }, { "start": 2986.2, "end": 2986.24, "word": ",", "probability": 0.5791015625 }, { "start": 2986.24, "end": 2986.32, "word": " it", "probability": 0.90087890625 }, { "start": 2986.32, "end": 2986.5, "word": " needs", "probability": 0.751953125 }, { "start": 2986.5, "end": 2986.64, "word": " to", "probability": 0.9091796875 }, { "start": 2986.64, "end": 2986.94, "word": " apply", "probability": 0.85693359375 }, { "start": 2986.94, "end": 2987.12, "word": " the", "probability": 0.81103515625 }, { "start": 2987.12, "end": 2987.36, "word": " weights", "probability": 0.66357421875 }, { "start": 2987.36, "end": 2987.46, "word": ".", "probability": 0.97314453125 } ] }, { "id": 1265, "seek": 294254, "start": 2987.46, "end": 2989.64, "text": " We already know what the counts are, we already know what the weights are,", "tokens": [ 51014, 492, 1217, 458, 437, 264, 14893, 366, 11, 321, 1217, 458, 437, 264, 17443, 366, 11, 51164 ], "temperature": 0.0, "avg_logprob": -0.21141304943872535, "compression_ratio": 1.7098039215686274, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 2987.46, "end": 2987.56, "word": " We", "probability": 0.8916015625 }, { "start": 2987.56, "end": 2987.72, "word": " already", "probability": 0.83740234375 }, { "start": 2987.72, "end": 2987.9, "word": " know", "probability": 0.81689453125 }, { "start": 2987.9, "end": 2988.02, "word": " what", "probability": 0.88232421875 }, { "start": 2988.02, "end": 2988.12, "word": " the", "probability": 0.81201171875 }, { "start": 2988.12, "end": 2988.36, "word": " counts", "probability": 0.7216796875 }, { "start": 2988.36, "end": 2988.54, "word": " are", "probability": 0.89453125 }, { "start": 2988.54, "end": 2988.6, "word": ",", "probability": 0.5556640625 }, { "start": 2988.6, "end": 2988.66, "word": " we", "probability": 0.89794921875 }, { "start": 2988.66, "end": 2988.86, "word": " already", "probability": 0.83544921875 }, { "start": 2988.86, "end": 2989.04, "word": " know", "probability": 0.806640625 }, { "start": 2989.04, "end": 2989.16, "word": " what", "probability": 0.88134765625 }, { "start": 2989.16, "end": 2989.26, "word": " the", "probability": 0.8154296875 }, { "start": 2989.26, "end": 2989.44, "word": " weights", "probability": 0.73779296875 }, { "start": 2989.44, "end": 2989.6, "word": " are", "probability": 0.88916015625 }, { "start": 2989.6, "end": 2989.64, "word": ",", "probability": 0.76025390625 } ] }, { "id": 1266, "seek": 294254, "start": 2989.64, "end": 2991.64, "text": " we just need to apply them to each token.", "tokens": [ 51164, 321, 445, 643, 281, 3079, 552, 281, 1184, 14862, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.21141304943872535, "compression_ratio": 1.7098039215686274, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 2989.64, "end": 2989.72, "word": " we", "probability": 0.89892578125 }, { "start": 2989.72, "end": 2989.86, "word": " just", "probability": 0.8916015625 }, { "start": 2989.86, "end": 2990.0, "word": " need", "probability": 0.81640625 }, { "start": 2990.0, "end": 2990.1, "word": " to", "probability": 0.90771484375 }, { "start": 2990.1, "end": 2990.34, "word": " apply", "probability": 0.83837890625 }, { "start": 2990.34, "end": 2990.54, "word": " them", "probability": 0.689453125 }, { "start": 2990.54, "end": 2990.68, "word": " to", "probability": 0.89794921875 }, { "start": 2990.68, "end": 2990.92, "word": " each", "probability": 0.84912109375 }, { "start": 2990.92, "end": 2991.24, "word": " token", "probability": 0.8125 }, { "start": 2991.24, "end": 2991.64, "word": ".", "probability": 0.97314453125 } ] }, { "id": 1267, "seek": 294254, "start": 2992.22, "end": 2993.84, "text": " So vectorizing is complete.", "tokens": [ 51264, 407, 8062, 3319, 307, 3566, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.21141304943872535, "compression_ratio": 1.7098039215686274, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 2992.22, "end": 2992.42, "word": " So", "probability": 0.8984375 }, { "start": 2992.42, "end": 2992.9, "word": " vectorizing", "probability": 0.8720703125 }, { "start": 2992.9, "end": 2993.06, "word": " is", "probability": 0.86572265625 }, { "start": 2993.06, "end": 2993.44, "word": " complete", "probability": 0.66015625 }, { "start": 2993.44, "end": 2993.84, "word": ".", "probability": 0.791015625 } ] }, { "id": 1268, "seek": 294254, "start": 2994.52, "end": 2999.22, "text": " And now we're finally on to testing and evaluating our model.", "tokens": [ 51364, 400, 586, 321, 434, 2721, 322, 281, 4997, 293, 27479, 527, 2316, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.21141304943872535, "compression_ratio": 1.7098039215686274, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 2994.52, "end": 2994.82, "word": " And", "probability": 0.8857421875 }, { "start": 2994.82, "end": 2995.14, "word": " now", "probability": 0.892578125 }, { "start": 2995.14, "end": 2995.38, "word": " we're", "probability": 0.889892578125 }, { "start": 2995.38, "end": 2995.92, "word": " finally", "probability": 0.82275390625 }, { "start": 2995.92, "end": 2996.32, "word": " on", "probability": 0.4775390625 }, { "start": 2996.32, "end": 2996.74, "word": " to", "probability": 0.90380859375 }, { "start": 2996.74, "end": 2997.68, "word": " testing", "probability": 0.7255859375 }, { "start": 2997.68, "end": 2997.96, "word": " and", "probability": 0.87451171875 }, { "start": 2997.96, "end": 2998.36, "word": " evaluating", "probability": 0.783203125 }, { "start": 2998.36, "end": 2998.58, "word": " our", "probability": 0.8212890625 }, { "start": 2998.58, "end": 2998.82, "word": " model", "probability": 0.80908203125 }, { "start": 2998.82, "end": 2999.22, "word": ".", "probability": 0.99755859375 } ] }, { "id": 1269, "seek": 294254, "start": 2999.64, "end": 3002.28, "text": " So you remember how I said data collection and preprocessing", "tokens": [ 51614, 407, 291, 1604, 577, 286, 848, 1412, 5765, 293, 2666, 340, 780, 278, 51764 ], "temperature": 0.0, "avg_logprob": -0.21141304943872535, "compression_ratio": 1.7098039215686274, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 2999.64, "end": 2999.88, "word": " So", "probability": 0.88134765625 }, { "start": 2999.88, "end": 3000.06, "word": " you", "probability": 0.814453125 }, { "start": 3000.06, "end": 3000.26, "word": " remember", "probability": 0.7890625 }, { "start": 3000.26, "end": 3000.46, "word": " how", "probability": 0.90576171875 }, { "start": 3000.46, "end": 3000.58, "word": " I", "probability": 0.99951171875 }, { "start": 3000.58, "end": 3000.78, "word": " said", "probability": 0.88330078125 }, { "start": 3000.78, "end": 3001.0, "word": " data", "probability": 0.72314453125 }, { "start": 3001.0, "end": 3001.42, "word": " collection", "probability": 0.6279296875 }, { "start": 3001.42, "end": 3001.62, "word": " and", "probability": 0.67529296875 }, { "start": 3001.62, "end": 3002.28, "word": " preprocessing", "probability": 0.83770751953125 } ] }, { "id": 1270, "seek": 296954, "start": 3002.28, "end": 3005.46, "text": " is what's going to take the most amount of time?", "tokens": [ 50364, 307, 437, 311, 516, 281, 747, 264, 881, 2372, 295, 565, 30, 50514 ], "temperature": 0.0, "avg_logprob": -0.16067477876106195, "compression_ratio": 1.6198347107438016, "no_speech_prob": 0.00388336181640625, "words": [ { "start": 3002.28, "end": 3002.44, "word": " is", "probability": 0.496337890625 }, { "start": 3002.44, "end": 3002.64, "word": " what's", "probability": 0.906494140625 }, { "start": 3002.64, "end": 3002.76, "word": " going", "probability": 0.6552734375 }, { "start": 3002.76, "end": 3002.86, "word": " to", "probability": 0.9052734375 }, { "start": 3002.86, "end": 3003.18, "word": " take", "probability": 0.8046875 }, { "start": 3003.18, "end": 3004.18, "word": " the", "probability": 0.783203125 }, { "start": 3004.18, "end": 3004.44, "word": " most", "probability": 0.8056640625 }, { "start": 3004.44, "end": 3004.66, "word": " amount", "probability": 0.8349609375 }, { "start": 3004.66, "end": 3004.8, "word": " of", "probability": 0.90625 }, { "start": 3004.8, "end": 3005.12, "word": " time", "probability": 0.796875 }, { "start": 3005.12, "end": 3005.46, "word": "?", "probability": 0.052398681640625 } ] }, { "id": 1271, "seek": 296954, "start": 3005.46, "end": 3007.64, "text": " Well, that was about 80% of this workbook.", "tokens": [ 50514, 1042, 11, 300, 390, 466, 4688, 4, 295, 341, 589, 2939, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.16067477876106195, "compression_ratio": 1.6198347107438016, "no_speech_prob": 0.00388336181640625, "words": [ { "start": 3005.46, "end": 3005.48, "word": " Well", "probability": 0.65283203125 }, { "start": 3005.48, "end": 3005.54, "word": ",", "probability": 0.640625 }, { "start": 3005.54, "end": 3005.68, "word": " that", "probability": 0.8779296875 }, { "start": 3005.68, "end": 3005.82, "word": " was", "probability": 0.888671875 }, { "start": 3005.82, "end": 3006.0, "word": " about", "probability": 0.818359375 }, { "start": 3006.0, "end": 3006.26, "word": " 80", "probability": 0.87646484375 }, { "start": 3006.26, "end": 3006.5, "word": "%", "probability": 0.72802734375 }, { "start": 3006.5, "end": 3006.64, "word": " of", "probability": 0.8984375 }, { "start": 3006.64, "end": 3006.78, "word": " this", "probability": 0.880859375 }, { "start": 3006.78, "end": 3007.24, "word": " workbook", "probability": 0.9072265625 }, { "start": 3007.24, "end": 3007.64, "word": ".", "probability": 0.7900390625 } ] }, { "id": 1272, "seek": 296954, "start": 3008.14, "end": 3011.34, "text": " If not, maybe a little more, maybe 85%.", "tokens": [ 50664, 759, 406, 11, 1310, 257, 707, 544, 11, 1310, 14695, 6856, 50814 ], "temperature": 0.0, "avg_logprob": -0.16067477876106195, "compression_ratio": 1.6198347107438016, "no_speech_prob": 0.00388336181640625, "words": [ { "start": 3008.14, "end": 3008.54, "word": " If", "probability": 0.826171875 }, { "start": 3008.54, "end": 3008.9, "word": " not", "probability": 0.888671875 }, { "start": 3008.9, "end": 3009.04, "word": ",", "probability": 0.86083984375 }, { "start": 3009.04, "end": 3009.42, "word": " maybe", "probability": 0.86474609375 }, { "start": 3009.58, "end": 3009.68, "word": " a little", "probability": 0.8173828125 }, { "start": 3009.68, "end": 3009.96, "word": " more", "probability": 0.8818359375 }, { "start": 3009.96, "end": 3010.06, "word": ",", "probability": 0.724609375 }, { "start": 3010.06, "end": 3010.2, "word": " maybe", "probability": 0.86669921875 }, { "start": 3010.2, "end": 3011.34, "word": " 85%.", "probability": 0.813720703125 } ] }, { "id": 1273, "seek": 296954, "start": 3012.32, "end": 3014.74, "text": " But yeah, data science in a nutshell.", "tokens": [ 50814, 583, 1338, 11, 1412, 3497, 294, 257, 37711, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.16067477876106195, "compression_ratio": 1.6198347107438016, "no_speech_prob": 0.00388336181640625, "words": [ { "start": 3012.32, "end": 3012.72, "word": " But", "probability": 0.7890625 }, { "start": 3012.72, "end": 3013.12, "word": " yeah", "probability": 0.70703125 }, { "start": 3013.12, "end": 3013.36, "word": ",", "probability": 0.93505859375 }, { "start": 3013.36, "end": 3013.64, "word": " data", "probability": 0.79345703125 }, { "start": 3013.64, "end": 3013.92, "word": " science", "probability": 0.85498046875 }, { "start": 3013.92, "end": 3014.06, "word": " in", "probability": 0.88232421875 }, { "start": 3014.12, "end": 3014.34, "word": " a nutshell", "probability": 0.759765625 }, { "start": 3014.34, "end": 3014.74, "word": ".", "probability": 0.98388671875 } ] }, { "id": 1274, "seek": 296954, "start": 3015.68, "end": 3020.62, "text": " So here we have a very helpful report generator function.", "tokens": [ 51014, 407, 510, 321, 362, 257, 588, 4961, 2275, 19265, 2445, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.16067477876106195, "compression_ratio": 1.6198347107438016, "no_speech_prob": 0.00388336181640625, "words": [ { "start": 3015.68, "end": 3016.08, "word": " So", "probability": 0.78515625 }, { "start": 3016.08, "end": 3016.48, "word": " here", "probability": 0.580078125 }, { "start": 3016.48, "end": 3016.68, "word": " we", "probability": 0.78076171875 }, { "start": 3016.68, "end": 3016.98, "word": " have", "probability": 0.87744140625 }, { "start": 3017.3, "end": 3017.5, "word": " a very", "probability": 0.7333984375 }, { "start": 3017.5, "end": 3017.92, "word": " helpful", "probability": 0.84521484375 }, { "start": 3017.92, "end": 3019.22, "word": " report", "probability": 0.7568359375 }, { "start": 3019.22, "end": 3019.74, "word": " generator", "probability": 0.8037109375 }, { "start": 3019.74, "end": 3020.22, "word": " function", "probability": 0.87939453125 }, { "start": 3020.22, "end": 3020.62, "word": ".", "probability": 0.9658203125 } ] }, { "id": 1275, "seek": 296954, "start": 3020.92, "end": 3024.9, "text": " It's not important to know what's going on in this,", "tokens": [ 51264, 467, 311, 406, 1021, 281, 458, 437, 311, 516, 322, 294, 341, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.16067477876106195, "compression_ratio": 1.6198347107438016, "no_speech_prob": 0.00388336181640625, "words": [ { "start": 3020.92, "end": 3021.24, "word": " It's", "probability": 0.94970703125 }, { "start": 3021.24, "end": 3021.42, "word": " not", "probability": 0.8974609375 }, { "start": 3021.42, "end": 3022.14, "word": " important", "probability": 0.78076171875 }, { "start": 3022.14, "end": 3023.5, "word": " to", "probability": 0.89208984375 }, { "start": 3023.5, "end": 3023.8, "word": " know", "probability": 0.8203125 }, { "start": 3023.8, "end": 3024.06, "word": " what's", "probability": 0.943359375 }, { "start": 3024.06, "end": 3024.22, "word": " going", "probability": 0.85400390625 }, { "start": 3024.22, "end": 3024.52, "word": " on", "probability": 0.91015625 }, { "start": 3024.52, "end": 3024.66, "word": " in", "probability": 0.8994140625 }, { "start": 3024.66, "end": 3024.84, "word": " this", "probability": 0.87939453125 }, { "start": 3024.84, "end": 3024.9, "word": ",", "probability": 0.412841796875 } ] }, { "id": 1276, "seek": 296954, "start": 3024.9, "end": 3026.28, "text": " it's just going to be a helper function,", "tokens": [ 51464, 309, 311, 445, 516, 281, 312, 257, 36133, 2445, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.16067477876106195, "compression_ratio": 1.6198347107438016, "no_speech_prob": 0.00388336181640625, "words": [ { "start": 3024.9, "end": 3025.06, "word": " it's", "probability": 0.847412109375 }, { "start": 3025.06, "end": 3025.22, "word": " just", "probability": 0.85302734375 }, { "start": 3025.22, "end": 3025.32, "word": " going", "probability": 0.73974609375 }, { "start": 3025.32, "end": 3025.34, "word": " to", "probability": 0.90625 }, { "start": 3025.34, "end": 3025.42, "word": " be", "probability": 0.9013671875 }, { "start": 3025.5, "end": 3025.66, "word": " a helper", "probability": 0.8623046875 }, { "start": 3025.66, "end": 3026.1, "word": " function", "probability": 0.880859375 }, { "start": 3026.1, "end": 3026.28, "word": ",", "probability": 0.53466796875 } ] }, { "id": 1277, "seek": 296954, "start": 3026.28, "end": 3029.28, "text": " but we do need to know that it's going to take in our confusion matrix,", "tokens": [ 51564, 457, 321, 360, 643, 281, 458, 300, 309, 311, 516, 281, 747, 294, 527, 15075, 8141, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.16067477876106195, "compression_ratio": 1.6198347107438016, "no_speech_prob": 0.00388336181640625, "words": [ { "start": 3026.28, "end": 3026.38, "word": " but", "probability": 0.8994140625 }, { "start": 3026.38, "end": 3026.52, "word": " we", "probability": 0.9091796875 }, { "start": 3026.52, "end": 3026.64, "word": " do", "probability": 0.904296875 }, { "start": 3026.64, "end": 3026.78, "word": " need", "probability": 0.81298828125 }, { "start": 3026.78, "end": 3026.88, "word": " to", "probability": 0.90673828125 }, { "start": 3026.88, "end": 3027.02, "word": " know", "probability": 0.8134765625 }, { "start": 3027.02, "end": 3027.18, "word": " that", "probability": 0.87255859375 }, { "start": 3027.18, "end": 3027.32, "word": " it's", "probability": 0.948486328125 }, { "start": 3027.32, "end": 3027.4, "word": " going", "probability": 0.845703125 }, { "start": 3027.4, "end": 3027.46, "word": " to", "probability": 0.9033203125 }, { "start": 3027.46, "end": 3027.66, "word": " take", "probability": 0.818359375 }, { "start": 3027.66, "end": 3027.84, "word": " in", "probability": 0.904296875 }, { "start": 3027.84, "end": 3028.06, "word": " our", "probability": 0.8212890625 }, { "start": 3028.06, "end": 3028.46, "word": " confusion", "probability": 0.89111328125 }, { "start": 3028.46, "end": 3029.0, "word": " matrix", "probability": 0.84619140625 }, { "start": 3029.0, "end": 3029.28, "word": ",", "probability": 0.97412109375 } ] }, { "id": 1278, "seek": 299842, "start": 3029.28, "end": 3032.56, "text": " our score, which is our accuracy, and the classification report,", "tokens": [ 50364, 527, 6175, 11, 597, 307, 527, 14170, 11, 293, 264, 21538, 2275, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.1828750066757202, "compression_ratio": 1.8070866141732282, "no_speech_prob": 0.010986328125, "words": [ { "start": 3029.28, "end": 3029.44, "word": " our", "probability": 0.317626953125 }, { "start": 3029.44, "end": 3029.8, "word": " score", "probability": 0.7646484375 }, { "start": 3029.8, "end": 3029.96, "word": ",", "probability": 0.61962890625 }, { "start": 3029.96, "end": 3030.0, "word": " which", "probability": 0.8955078125 }, { "start": 3030.0, "end": 3030.1, "word": " is", "probability": 0.9052734375 }, { "start": 3030.1, "end": 3030.24, "word": " our", "probability": 0.806640625 }, { "start": 3030.24, "end": 3030.66, "word": " accuracy", "probability": 0.71337890625 }, { "start": 3030.66, "end": 3030.98, "word": ",", "probability": 0.505859375 }, { "start": 3030.98, "end": 3031.14, "word": " and", "probability": 0.89208984375 }, { "start": 3031.14, "end": 3031.38, "word": " the", "probability": 0.7978515625 }, { "start": 3031.38, "end": 3032.0, "word": " classification", "probability": 0.9345703125 }, { "start": 3032.0, "end": 3032.42, "word": " report", "probability": 0.841796875 }, { "start": 3032.42, "end": 3032.56, "word": ",", "probability": 0.445068359375 } ] }, { "id": 1279, "seek": 299842, "start": 3032.56, "end": 3035.12, "text": " and then it's going to print out all the stats that we need.", "tokens": [ 50514, 293, 550, 309, 311, 516, 281, 4482, 484, 439, 264, 18152, 300, 321, 643, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.1828750066757202, "compression_ratio": 1.8070866141732282, "no_speech_prob": 0.010986328125, "words": [ { "start": 3032.56, "end": 3032.62, "word": " and", "probability": 0.88037109375 }, { "start": 3032.62, "end": 3032.72, "word": " then", "probability": 0.7197265625 }, { "start": 3032.72, "end": 3032.86, "word": " it's", "probability": 0.945556640625 }, { "start": 3032.86, "end": 3032.94, "word": " going", "probability": 0.485107421875 }, { "start": 3032.94, "end": 3033.06, "word": " to", "probability": 0.90576171875 }, { "start": 3033.06, "end": 3033.26, "word": " print", "probability": 0.89013671875 }, { "start": 3033.26, "end": 3033.42, "word": " out", "probability": 0.80517578125 }, { "start": 3033.42, "end": 3033.58, "word": " all", "probability": 0.90234375 }, { "start": 3033.58, "end": 3033.76, "word": " the", "probability": 0.8046875 }, { "start": 3033.76, "end": 3034.06, "word": " stats", "probability": 0.8759765625 }, { "start": 3034.06, "end": 3034.26, "word": " that", "probability": 0.8779296875 }, { "start": 3034.26, "end": 3034.4, "word": " we", "probability": 0.90673828125 }, { "start": 3034.4, "end": 3034.72, "word": " need", "probability": 0.81298828125 }, { "start": 3034.72, "end": 3035.12, "word": ".", "probability": 0.99072265625 } ] }, { "id": 1280, "seek": 299842, "start": 3036.52, "end": 3039.86, "text": " So that hops us into task 6A,", "tokens": [ 50714, 407, 300, 47579, 505, 666, 5633, 1386, 32, 11, 50864 ], "temperature": 0.0, "avg_logprob": -0.1828750066757202, "compression_ratio": 1.8070866141732282, "no_speech_prob": 0.010986328125, "words": [ { "start": 3036.52, "end": 3036.92, "word": " So", "probability": 0.75146484375 }, { "start": 3036.92, "end": 3037.06, "word": " that", "probability": 0.7734375 }, { "start": 3037.06, "end": 3037.26, "word": " hops", "probability": 0.35791015625 }, { "start": 3037.26, "end": 3037.44, "word": " us", "probability": 0.8916015625 }, { "start": 3037.44, "end": 3037.98, "word": " into", "probability": 0.72314453125 }, { "start": 3037.98, "end": 3038.64, "word": " task", "probability": 0.640625 }, { "start": 3038.64, "end": 3039.58, "word": " 6A", "probability": 0.71484375 }, { "start": 3039.58, "end": 3039.86, "word": ",", "probability": 0.9150390625 } ] }, { "id": 1281, "seek": 299842, "start": 3039.86, "end": 3043.4, "text": " which is going to be training and evaluating our first model,", "tokens": [ 50864, 597, 307, 516, 281, 312, 3097, 293, 27479, 527, 700, 2316, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.1828750066757202, "compression_ratio": 1.8070866141732282, "no_speech_prob": 0.010986328125, "words": [ { "start": 3039.86, "end": 3040.22, "word": " which", "probability": 0.91796875 }, { "start": 3040.22, "end": 3040.34, "word": " is", "probability": 0.90673828125 }, { "start": 3040.34, "end": 3040.42, "word": " going", "probability": 0.82861328125 }, { "start": 3040.42, "end": 3040.46, "word": " to", "probability": 0.90673828125 }, { "start": 3040.46, "end": 3040.6, "word": " be", "probability": 0.90625 }, { "start": 3040.6, "end": 3040.96, "word": " training", "probability": 0.79150390625 }, { "start": 3040.96, "end": 3041.24, "word": " and", "probability": 0.8935546875 }, { "start": 3041.24, "end": 3041.76, "word": " evaluating", "probability": 0.77294921875 }, { "start": 3041.76, "end": 3042.16, "word": " our", "probability": 0.81787109375 }, { "start": 3042.16, "end": 3042.64, "word": " first", "probability": 0.814453125 }, { "start": 3042.64, "end": 3043.02, "word": " model", "probability": 0.80126953125 }, { "start": 3043.02, "end": 3043.4, "word": ",", "probability": 0.95556640625 } ] }, { "id": 1282, "seek": 299842, "start": 3043.4, "end": 3048.34, "text": " which is going to be multinomial Naive Bayesian using the TFIDF vectorizer.", "tokens": [ 51064, 597, 307, 516, 281, 312, 45872, 47429, 6056, 488, 7840, 42434, 1228, 264, 40964, 2777, 37, 8062, 6545, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.1828750066757202, "compression_ratio": 1.8070866141732282, "no_speech_prob": 0.010986328125, "words": [ { "start": 3043.4, "end": 3043.76, "word": " which", "probability": 0.92578125 }, { "start": 3043.76, "end": 3043.9, "word": " is", "probability": 0.90673828125 }, { "start": 3043.9, "end": 3043.98, "word": " going", "probability": 0.86181640625 }, { "start": 3043.98, "end": 3044.04, "word": " to", "probability": 0.90380859375 }, { "start": 3044.04, "end": 3044.16, "word": " be", "probability": 0.90576171875 }, { "start": 3044.16, "end": 3044.78, "word": " multinomial", "probability": 0.9111328125 }, { "start": 3044.78, "end": 3045.18, "word": " Naive", "probability": 0.680908203125 }, { "start": 3045.18, "end": 3045.52, "word": " Bayesian", "probability": 0.90869140625 }, { "start": 3045.52, "end": 3045.98, "word": " using", "probability": 0.6865234375 }, { "start": 3045.98, "end": 3046.28, "word": " the", "probability": 0.79541015625 }, { "start": 3046.28, "end": 3047.28, "word": " TFIDF", "probability": 0.5751953125 }, { "start": 3047.28, "end": 3047.94, "word": " vectorizer", "probability": 0.865234375 }, { "start": 3047.94, "end": 3048.34, "word": ".", "probability": 0.99169921875 } ] }, { "id": 1283, "seek": 299842, "start": 3049.98, "end": 3053.94, "text": " So there's a lot of steps to this, but we're going to walk through it step by step.", "tokens": [ 51414, 407, 456, 311, 257, 688, 295, 4439, 281, 341, 11, 457, 321, 434, 516, 281, 1792, 807, 309, 1823, 538, 1823, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.1828750066757202, "compression_ratio": 1.8070866141732282, "no_speech_prob": 0.010986328125, "words": [ { "start": 3049.98, "end": 3050.38, "word": " So", "probability": 0.8330078125 }, { "start": 3050.38, "end": 3050.54, "word": " there's", "probability": 0.90185546875 }, { "start": 3050.66, "end": 3050.74, "word": " a lot", "probability": 0.88720703125 }, { "start": 3050.74, "end": 3050.84, "word": " of", "probability": 0.9091796875 }, { "start": 3050.84, "end": 3051.04, "word": " steps", "probability": 0.72998046875 }, { "start": 3051.04, "end": 3051.18, "word": " to", "probability": 0.90234375 }, { "start": 3051.18, "end": 3051.4, "word": " this", "probability": 0.87890625 }, { "start": 3051.4, "end": 3051.46, "word": ",", "probability": 0.896484375 }, { "start": 3051.46, "end": 3051.58, "word": " but", "probability": 0.9072265625 }, { "start": 3051.58, "end": 3051.74, "word": " we're", "probability": 0.92822265625 }, { "start": 3051.74, "end": 3051.82, "word": " going", "probability": 0.78173828125 }, { "start": 3051.82, "end": 3052.0, "word": " to", "probability": 0.90478515625 }, { "start": 3052.0, "end": 3052.28, "word": " walk", "probability": 0.8115234375 }, { "start": 3052.28, "end": 3052.48, "word": " through", "probability": 0.791015625 }, { "start": 3052.48, "end": 3052.62, "word": " it", "probability": 0.90576171875 }, { "start": 3052.62, "end": 3052.9, "word": " step", "probability": 0.8046875 }, { "start": 3052.9, "end": 3053.14, "word": " by", "probability": 0.7119140625 }, { "start": 3053.14, "end": 3053.54, "word": " step", "probability": 0.8212890625 }, { "start": 3053.54, "end": 3053.94, "word": ".", "probability": 0.9931640625 } ] }, { "id": 1284, "seek": 299842, "start": 3054.2, "end": 3058.16, "text": " First, what we're going to do is create a multinomial Naive Bayesian constructor,", "tokens": [ 51614, 2386, 11, 437, 321, 434, 516, 281, 360, 307, 1884, 257, 45872, 47429, 6056, 488, 7840, 42434, 47479, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.1828750066757202, "compression_ratio": 1.8070866141732282, "no_speech_prob": 0.010986328125, "words": [ { "start": 3054.2, "end": 3054.6, "word": " First", "probability": 0.89111328125 }, { "start": 3054.6, "end": 3054.66, "word": ",", "probability": 0.72705078125 }, { "start": 3054.66, "end": 3054.72, "word": " what", "probability": 0.88525390625 }, { "start": 3054.72, "end": 3054.86, "word": " we're", "probability": 0.930419921875 }, { "start": 3054.86, "end": 3054.92, "word": " going", "probability": 0.8271484375 }, { "start": 3054.92, "end": 3054.96, "word": " to", "probability": 0.90673828125 }, { "start": 3054.96, "end": 3055.12, "word": " do", "probability": 0.9091796875 }, { "start": 3055.12, "end": 3055.34, "word": " is", "probability": 0.890625 }, { "start": 3055.34, "end": 3055.68, "word": " create", "probability": 0.82958984375 }, { "start": 3056.02, "end": 3056.66, "word": " a multinomial", "probability": 0.941162109375 }, { "start": 3056.66, "end": 3057.08, "word": " Naive", "probability": 0.898193359375 }, { "start": 3057.08, "end": 3057.38, "word": " Bayesian", "probability": 0.920654296875 }, { "start": 3057.38, "end": 3057.96, "word": " constructor", "probability": 0.70751953125 }, { "start": 3057.96, "end": 3058.16, "word": ",", "probability": 0.330322265625 } ] }, { "id": 1285, "seek": 302730, "start": 3058.16, "end": 3061.42, "text": " so that's going to look like mnb, tf, idf,", "tokens": [ 50364, 370, 300, 311, 516, 281, 574, 411, 275, 77, 65, 11, 256, 69, 11, 4496, 69, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.194021737575531, "compression_ratio": 1.651376146788991, "no_speech_prob": 0.00572967529296875, "words": [ { "start": 3058.16, "end": 3058.3, "word": " so", "probability": 0.2149658203125 }, { "start": 3058.3, "end": 3058.48, "word": " that's", "probability": 0.90625 }, { "start": 3058.48, "end": 3058.56, "word": " going", "probability": 0.427001953125 }, { "start": 3058.56, "end": 3058.62, "word": " to", "probability": 0.90283203125 }, { "start": 3058.62, "end": 3058.78, "word": " look", "probability": 0.92041015625 }, { "start": 3058.78, "end": 3059.22, "word": " like", "probability": 0.8662109375 }, { "start": 3059.22, "end": 3060.08, "word": " mnb", "probability": 0.78564453125 }, { "start": 3060.08, "end": 3060.26, "word": ",", "probability": 0.11077880859375 }, { "start": 3060.26, "end": 3060.7, "word": " tf", "probability": 0.959716796875 }, { "start": 3060.7, "end": 3060.82, "word": ",", "probability": 0.88232421875 }, { "start": 3060.82, "end": 3061.32, "word": " idf", "probability": 0.93212890625 }, { "start": 3061.32, "end": 3061.42, "word": ",", "probability": 0.334716796875 } ] }, { "id": 1286, "seek": 302730, "start": 3061.42, "end": 3064.16, "text": " and the names of these variables are very important", "tokens": [ 50514, 293, 264, 5288, 295, 613, 9102, 366, 588, 1021, 50664 ], "temperature": 0.0, "avg_logprob": -0.194021737575531, "compression_ratio": 1.651376146788991, "no_speech_prob": 0.00572967529296875, "words": [ { "start": 3061.42, "end": 3061.54, "word": " and", "probability": 0.87109375 }, { "start": 3061.54, "end": 3061.94, "word": " the", "probability": 0.80712890625 }, { "start": 3061.94, "end": 3062.54, "word": " names", "probability": 0.7998046875 }, { "start": 3062.54, "end": 3062.72, "word": " of", "probability": 0.90380859375 }, { "start": 3062.72, "end": 3062.88, "word": " these", "probability": 0.71142578125 }, { "start": 3062.88, "end": 3063.22, "word": " variables", "probability": 0.82861328125 }, { "start": 3063.22, "end": 3063.42, "word": " are", "probability": 0.89501953125 }, { "start": 3063.42, "end": 3063.74, "word": " very", "probability": 0.7470703125 }, { "start": 3063.74, "end": 3064.16, "word": " important", "probability": 0.76953125 } ] }, { "id": 1287, "seek": 302730, "start": 3064.16, "end": 3068.0, "text": " because that's what's being used in the generator function.", "tokens": [ 50664, 570, 300, 311, 437, 311, 885, 1143, 294, 264, 19265, 2445, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.194021737575531, "compression_ratio": 1.651376146788991, "no_speech_prob": 0.00572967529296875, "words": [ { "start": 3064.16, "end": 3064.5, "word": " because", "probability": 0.71533203125 }, { "start": 3064.5, "end": 3064.92, "word": " that's", "probability": 0.940673828125 }, { "start": 3064.92, "end": 3065.14, "word": " what's", "probability": 0.94091796875 }, { "start": 3065.14, "end": 3065.38, "word": " being", "probability": 0.8818359375 }, { "start": 3065.38, "end": 3065.86, "word": " used", "probability": 0.8095703125 }, { "start": 3065.86, "end": 3066.18, "word": " in", "probability": 0.90380859375 }, { "start": 3066.18, "end": 3066.4, "word": " the", "probability": 0.81591796875 }, { "start": 3066.4, "end": 3066.8, "word": " generator", "probability": 0.86865234375 }, { "start": 3066.8, "end": 3067.28, "word": " function", "probability": 0.8740234375 }, { "start": 3067.28, "end": 3068.0, "word": ".", "probability": 0.88037109375 } ] }, { "id": 1288, "seek": 302730, "start": 3068.98, "end": 3074.32, "text": " So I'm going to call this Numial Naive Bayesian,", "tokens": [ 50914, 407, 286, 478, 516, 281, 818, 341, 22592, 831, 6056, 488, 7840, 42434, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.194021737575531, "compression_ratio": 1.651376146788991, "no_speech_prob": 0.00572967529296875, "words": [ { "start": 3068.98, "end": 3069.34, "word": " So", "probability": 0.529296875 }, { "start": 3069.34, "end": 3069.46, "word": " I'm", "probability": 0.813720703125 }, { "start": 3069.46, "end": 3069.46, "word": " going", "probability": 0.80908203125 }, { "start": 3069.46, "end": 3069.52, "word": " to", "probability": 0.90576171875 }, { "start": 3069.52, "end": 3069.66, "word": " call", "probability": 0.80859375 }, { "start": 3069.66, "end": 3070.18, "word": " this", "probability": 0.88623046875 }, { "start": 3070.18, "end": 3072.52, "word": " Numial", "probability": 0.327392578125 }, { "start": 3072.52, "end": 3073.14, "word": " Naive", "probability": 0.5819091796875 }, { "start": 3073.14, "end": 3073.5, "word": " Bayesian", "probability": 0.92333984375 }, { "start": 3073.5, "end": 3074.32, "word": ",", "probability": 0.4736328125 } ] }, { "id": 1289, "seek": 302730, "start": 3074.84, "end": 3078.66, "text": " and then we're going to train the multinomial Naive Bayesian,", "tokens": [ 51214, 293, 550, 321, 434, 516, 281, 3847, 264, 45872, 47429, 6056, 488, 7840, 42434, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.194021737575531, "compression_ratio": 1.651376146788991, "no_speech_prob": 0.00572967529296875, "words": [ { "start": 3074.84, "end": 3075.2, "word": " and", "probability": 0.87744140625 }, { "start": 3075.2, "end": 3075.3, "word": " then", "probability": 0.7373046875 }, { "start": 3075.3, "end": 3075.4, "word": " we're", "probability": 0.927978515625 }, { "start": 3075.4, "end": 3075.54, "word": " going", "probability": 0.85498046875 }, { "start": 3075.54, "end": 3075.76, "word": " to", "probability": 0.904296875 }, { "start": 3075.76, "end": 3076.18, "word": " train", "probability": 0.81884765625 }, { "start": 3076.18, "end": 3076.34, "word": " the", "probability": 0.80322265625 }, { "start": 3076.34, "end": 3076.78, "word": " multinomial", "probability": 0.76220703125 }, { "start": 3076.78, "end": 3077.16, "word": " Naive", "probability": 0.81640625 }, { "start": 3077.16, "end": 3077.56, "word": " Bayesian", "probability": 0.9130859375 }, { "start": 3077.56, "end": 3078.66, "word": ",", "probability": 0.375244140625 } ] }, { "id": 1290, "seek": 302730, "start": 3078.66, "end": 3084.2, "text": " as I already misspelled something, mnb, tf, idf, .fit,", "tokens": [ 51414, 382, 286, 1217, 1713, 33000, 746, 11, 275, 77, 65, 11, 256, 69, 11, 4496, 69, 11, 2411, 6845, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.194021737575531, "compression_ratio": 1.651376146788991, "no_speech_prob": 0.00572967529296875, "words": [ { "start": 3078.66, "end": 3079.32, "word": " as", "probability": 0.87841796875 }, { "start": 3079.32, "end": 3079.48, "word": " I", "probability": 0.96337890625 }, { "start": 3079.48, "end": 3079.96, "word": " already", "probability": 0.8115234375 }, { "start": 3079.96, "end": 3080.38, "word": " misspelled", "probability": 0.834716796875 }, { "start": 3080.38, "end": 3080.82, "word": " something", "probability": 0.74462890625 }, { "start": 3080.82, "end": 3081.38, "word": ",", "probability": 0.72412109375 }, { "start": 3081.38, "end": 3081.88, "word": " mnb", "probability": 0.9396158854166666 }, { "start": 3081.88, "end": 3082.02, "word": ",", "probability": 0.6455078125 }, { "start": 3082.02, "end": 3082.54, "word": " tf", "probability": 0.97021484375 }, { "start": 3082.54, "end": 3082.6, "word": ",", "probability": 0.97216796875 }, { "start": 3082.6, "end": 3083.14, "word": " idf", "probability": 0.961669921875 }, { "start": 3083.14, "end": 3083.16, "word": ",", "probability": 0.70654296875 }, { "start": 3083.16, "end": 3083.82, "word": " .fit", "probability": 0.76220703125 }, { "start": 3083.82, "end": 3084.2, "word": ",", "probability": 0.84521484375 } ] }, { "id": 1291, "seek": 302730, "start": 3084.2, "end": 3087.04, "text": " which is scikit-learn's code for train,", "tokens": [ 51664, 597, 307, 2180, 22681, 12, 306, 1083, 311, 3089, 337, 3847, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.194021737575531, "compression_ratio": 1.651376146788991, "no_speech_prob": 0.00572967529296875, "words": [ { "start": 3084.2, "end": 3084.32, "word": " which", "probability": 0.91845703125 }, { "start": 3084.32, "end": 3084.58, "word": " is", "probability": 0.908203125 }, { "start": 3084.58, "end": 3085.26, "word": " scikit", "probability": 0.673828125 }, { "start": 3085.26, "end": 3085.74, "word": "-learn's", "probability": 0.923583984375 }, { "start": 3085.74, "end": 3086.4, "word": " code", "probability": 0.82080078125 }, { "start": 3086.4, "end": 3086.62, "word": " for", "probability": 0.9013671875 }, { "start": 3086.62, "end": 3086.92, "word": " train", "probability": 0.72412109375 }, { "start": 3086.92, "end": 3087.04, "word": ",", "probability": 0.72119140625 } ] }, { "id": 1292, "seek": 305066, "start": 3087.04, "end": 3091.3, "text": " and then we're going to use our TFIDF, our vectorized corpus,", "tokens": [ 50364, 293, 550, 321, 434, 516, 281, 764, 527, 40964, 2777, 37, 11, 527, 8062, 1602, 1181, 31624, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.18178764081770374, "compression_ratio": 1.5894039735099337, "no_speech_prob": 0.0021495819091796875, "words": [ { "start": 3087.04, "end": 3087.12, "word": " and", "probability": 0.36083984375 }, { "start": 3087.12, "end": 3087.22, "word": " then", "probability": 0.70849609375 }, { "start": 3087.22, "end": 3087.32, "word": " we're", "probability": 0.91357421875 }, { "start": 3087.32, "end": 3087.4, "word": " going", "probability": 0.32666015625 }, { "start": 3087.4, "end": 3087.44, "word": " to", "probability": 0.9052734375 }, { "start": 3087.44, "end": 3087.64, "word": " use", "probability": 0.830078125 }, { "start": 3087.64, "end": 3087.8, "word": " our", "probability": 0.787109375 }, { "start": 3087.8, "end": 3088.94, "word": " TFIDF", "probability": 0.5299886067708334 }, { "start": 3088.94, "end": 3089.08, "word": ",", "probability": 0.8193359375 }, { "start": 3089.08, "end": 3089.16, "word": " our", "probability": 0.79541015625 }, { "start": 3089.16, "end": 3090.18, "word": " vectorized", "probability": 0.88134765625 }, { "start": 3090.18, "end": 3091.0, "word": " corpus", "probability": 0.85107421875 }, { "start": 3091.0, "end": 3091.3, "word": ",", "probability": 0.2393798828125 } ] }, { "id": 1293, "seek": 305066, "start": 3091.3, "end": 3093.44, "text": " with the TFIDF array.", "tokens": [ 50564, 365, 264, 40964, 2777, 37, 10225, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.18178764081770374, "compression_ratio": 1.5894039735099337, "no_speech_prob": 0.0021495819091796875, "words": [ { "start": 3091.3, "end": 3091.48, "word": " with", "probability": 0.80419921875 }, { "start": 3091.48, "end": 3091.62, "word": " the", "probability": 0.79443359375 }, { "start": 3091.62, "end": 3092.42, "word": " TFIDF", "probability": 0.9143880208333334 }, { "start": 3092.42, "end": 3093.08, "word": " array", "probability": 0.72607421875 }, { "start": 3093.08, "end": 3093.44, "word": ".", "probability": 0.9755859375 } ] }, { "id": 1294, "seek": 305066, "start": 3095.36, "end": 3098.06, "text": " So now we're going to get a couple stats,", "tokens": [ 50764, 407, 586, 321, 434, 516, 281, 483, 257, 1916, 18152, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.18178764081770374, "compression_ratio": 1.5894039735099337, "no_speech_prob": 0.0021495819091796875, "words": [ { "start": 3095.36, "end": 3095.72, "word": " So", "probability": 0.67724609375 }, { "start": 3095.72, "end": 3095.94, "word": " now", "probability": 0.68310546875 }, { "start": 3095.94, "end": 3096.06, "word": " we're", "probability": 0.915771484375 }, { "start": 3096.06, "end": 3096.14, "word": " going", "probability": 0.814453125 }, { "start": 3096.14, "end": 3096.18, "word": " to", "probability": 0.9052734375 }, { "start": 3096.18, "end": 3096.3, "word": " get", "probability": 0.8955078125 }, { "start": 3096.52, "end": 3096.84, "word": " a couple", "probability": 0.7890625 }, { "start": 3096.84, "end": 3097.9, "word": " stats", "probability": 0.7880859375 }, { "start": 3097.9, "end": 3098.06, "word": ",", "probability": 0.3359375 } ] }, { "id": 1295, "seek": 305066, "start": 3098.06, "end": 3100.06, "text": " so we're going to get our score,", "tokens": [ 50914, 370, 321, 434, 516, 281, 483, 527, 6175, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.18178764081770374, "compression_ratio": 1.5894039735099337, "no_speech_prob": 0.0021495819091796875, "words": [ { "start": 3098.06, "end": 3098.14, "word": " so", "probability": 0.80908203125 }, { "start": 3098.14, "end": 3098.24, "word": " we're", "probability": 0.92724609375 }, { "start": 3098.24, "end": 3098.3, "word": " going", "probability": 0.82470703125 }, { "start": 3098.3, "end": 3098.34, "word": " to", "probability": 0.90576171875 }, { "start": 3098.34, "end": 3098.48, "word": " get", "probability": 0.89111328125 }, { "start": 3098.48, "end": 3098.68, "word": " our", "probability": 0.82763671875 }, { "start": 3098.68, "end": 3099.38, "word": " score", "probability": 0.76806640625 }, { "start": 3099.38, "end": 3100.06, "word": ",", "probability": 0.46337890625 } ] }, { "id": 1296, "seek": 305066, "start": 3100.06, "end": 3108.74, "text": " mnb, tf, idf, equals mnb, tf, idf, .score.", "tokens": [ 51014, 275, 77, 65, 11, 256, 69, 11, 4496, 69, 11, 6915, 275, 77, 65, 11, 256, 69, 11, 4496, 69, 11, 2411, 4417, 418, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.18178764081770374, "compression_ratio": 1.5894039735099337, "no_speech_prob": 0.0021495819091796875, "words": [ { "start": 3100.06, "end": 3100.6, "word": " mnb", "probability": 0.6399739583333334 }, { "start": 3100.6, "end": 3100.74, "word": ",", "probability": 0.0240631103515625 }, { "start": 3100.74, "end": 3101.44, "word": " tf", "probability": 0.7230224609375 }, { "start": 3101.44, "end": 3101.48, "word": ",", "probability": 0.11004638671875 }, { "start": 3101.48, "end": 3102.06, "word": " idf", "probability": 0.807861328125 }, { "start": 3102.06, "end": 3102.28, "word": ",", "probability": 0.4384765625 }, { "start": 3102.28, "end": 3103.48, "word": " equals", "probability": 0.8759765625 }, { "start": 3103.48, "end": 3104.16, "word": " mnb", "probability": 0.9267578125 }, { "start": 3104.16, "end": 3104.36, "word": ",", "probability": 0.75 }, { "start": 3104.36, "end": 3105.04, "word": " tf", "probability": 0.97216796875 }, { "start": 3105.04, "end": 3105.14, "word": ",", "probability": 0.96923828125 }, { "start": 3105.14, "end": 3105.66, "word": " idf", "probability": 0.953857421875 }, { "start": 3105.66, "end": 3105.82, "word": ",", "probability": 0.69384765625 }, { "start": 3105.82, "end": 3108.56, "word": " .score", "probability": 0.6038411458333334 }, { "start": 3108.56, "end": 3108.74, "word": ".", "probability": 0.51806640625 } ] }, { "id": 1297, "seek": 305066, "start": 3108.74, "end": 3110.4, "text": " This is going to give us our accuracy,", "tokens": [ 51464, 639, 307, 516, 281, 976, 505, 527, 14170, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.18178764081770374, "compression_ratio": 1.5894039735099337, "no_speech_prob": 0.0021495819091796875, "words": [ { "start": 3108.74, "end": 3109.0, "word": " This", "probability": 0.78955078125 }, { "start": 3109.0, "end": 3109.12, "word": " is", "probability": 0.90478515625 }, { "start": 3109.12, "end": 3109.2, "word": " going", "probability": 0.84619140625 }, { "start": 3109.2, "end": 3109.26, "word": " to", "probability": 0.90625 }, { "start": 3109.26, "end": 3109.38, "word": " give", "probability": 0.8232421875 }, { "start": 3109.38, "end": 3109.5, "word": " us", "probability": 0.9033203125 }, { "start": 3109.5, "end": 3109.68, "word": " our", "probability": 0.8076171875 }, { "start": 3109.68, "end": 3110.16, "word": " accuracy", "probability": 0.755859375 }, { "start": 3110.16, "end": 3110.4, "word": ",", "probability": 0.5849609375 } ] }, { "id": 1298, "seek": 307666, "start": 3110.4, "end": 3114.5, "text": " and we want to compare this against our test, tf, idf, x,", "tokens": [ 50364, 293, 321, 528, 281, 6794, 341, 1970, 527, 1500, 11, 256, 69, 11, 4496, 69, 11, 2031, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.17113095578693208, "compression_ratio": 1.7707006369426752, "no_speech_prob": 0.0592041015625, "words": [ { "start": 3110.4, "end": 3110.46, "word": " and", "probability": 0.2998046875 }, { "start": 3110.46, "end": 3110.54, "word": " we", "probability": 0.80859375 }, { "start": 3110.54, "end": 3110.66, "word": " want", "probability": 0.41259765625 }, { "start": 3110.66, "end": 3110.76, "word": " to", "probability": 0.8994140625 }, { "start": 3110.76, "end": 3111.06, "word": " compare", "probability": 0.89892578125 }, { "start": 3111.06, "end": 3111.38, "word": " this", "probability": 0.88037109375 }, { "start": 3111.38, "end": 3111.72, "word": " against", "probability": 0.8720703125 }, { "start": 3111.72, "end": 3112.0, "word": " our", "probability": 0.80908203125 }, { "start": 3112.0, "end": 3112.46, "word": " test", "probability": 0.6904296875 }, { "start": 3112.46, "end": 3112.5, "word": ",", "probability": 0.015380859375 }, { "start": 3112.5, "end": 3113.04, "word": " tf", "probability": 0.76953125 }, { "start": 3113.04, "end": 3113.14, "word": ",", "probability": 0.17919921875 }, { "start": 3113.14, "end": 3113.72, "word": " idf", "probability": 0.869140625 }, { "start": 3113.72, "end": 3113.94, "word": ",", "probability": 0.87646484375 }, { "start": 3113.94, "end": 3114.32, "word": " x", "probability": 0.9189453125 }, { "start": 3114.32, "end": 3114.5, "word": ",", "probability": 0.59716796875 } ] }, { "id": 1299, "seek": 307666, "start": 3114.5, "end": 3117.38, "text": " and our test labels.", "tokens": [ 50564, 293, 527, 1500, 16949, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.17113095578693208, "compression_ratio": 1.7707006369426752, "no_speech_prob": 0.0592041015625, "words": [ { "start": 3114.5, "end": 3114.8, "word": " and", "probability": 0.8974609375 }, { "start": 3114.8, "end": 3115.12, "word": " our", "probability": 0.80810546875 }, { "start": 3115.12, "end": 3115.8, "word": " test", "probability": 0.7939453125 }, { "start": 3115.8, "end": 3116.84, "word": " labels", "probability": 0.8486328125 }, { "start": 3116.84, "end": 3117.38, "word": ".", "probability": 0.921875 } ] }, { "id": 1300, "seek": 307666, "start": 3118.26, "end": 3121.14, "text": " And then we want to take a look at the raw predictions,", "tokens": [ 50764, 400, 550, 321, 528, 281, 747, 257, 574, 412, 264, 8936, 21264, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.17113095578693208, "compression_ratio": 1.7707006369426752, "no_speech_prob": 0.0592041015625, "words": [ { "start": 3118.26, "end": 3118.44, "word": " And", "probability": 0.69775390625 }, { "start": 3118.44, "end": 3118.5, "word": " then", "probability": 0.72998046875 }, { "start": 3118.5, "end": 3118.6, "word": " we", "probability": 0.873046875 }, { "start": 3118.6, "end": 3118.72, "word": " want", "probability": 0.74658203125 }, { "start": 3118.72, "end": 3118.8, "word": " to", "probability": 0.90087890625 }, { "start": 3118.8, "end": 3118.92, "word": " take", "probability": 0.802734375 }, { "start": 3119.02, "end": 3119.1, "word": " a look", "probability": 0.91162109375 }, { "start": 3119.1, "end": 3119.18, "word": " at", "probability": 0.9033203125 }, { "start": 3119.18, "end": 3119.34, "word": " the", "probability": 0.81494140625 }, { "start": 3119.34, "end": 3119.58, "word": " raw", "probability": 0.84423828125 }, { "start": 3119.58, "end": 3120.06, "word": " predictions", "probability": 0.7607421875 }, { "start": 3120.06, "end": 3121.14, "word": ",", "probability": 0.2060546875 } ] }, { "id": 1301, "seek": 307666, "start": 3121.14, "end": 3124.68, "text": " so we're going to have our predictions, mnb, tf, idf,", "tokens": [ 50914, 370, 321, 434, 516, 281, 362, 527, 21264, 11, 275, 77, 65, 11, 256, 69, 11, 4496, 69, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.17113095578693208, "compression_ratio": 1.7707006369426752, "no_speech_prob": 0.0592041015625, "words": [ { "start": 3121.14, "end": 3121.42, "word": " so", "probability": 0.86181640625 }, { "start": 3121.42, "end": 3121.56, "word": " we're", "probability": 0.91796875 }, { "start": 3121.56, "end": 3121.58, "word": " going", "probability": 0.5078125 }, { "start": 3121.58, "end": 3121.6, "word": " to", "probability": 0.89990234375 }, { "start": 3121.6, "end": 3121.72, "word": " have", "probability": 0.87890625 }, { "start": 3121.72, "end": 3121.86, "word": " our", "probability": 0.79345703125 }, { "start": 3121.86, "end": 3122.46, "word": " predictions", "probability": 0.7568359375 }, { "start": 3122.46, "end": 3122.72, "word": ",", "probability": 0.75244140625 }, { "start": 3122.72, "end": 3123.14, "word": " mnb", "probability": 0.8209635416666666 }, { "start": 3123.14, "end": 3123.28, "word": ",", "probability": 0.77685546875 }, { "start": 3123.28, "end": 3123.92, "word": " tf", "probability": 0.9755859375 }, { "start": 3123.92, "end": 3124.02, "word": ",", "probability": 0.9814453125 }, { "start": 3124.02, "end": 3124.64, "word": " idf", "probability": 0.94921875 }, { "start": 3124.64, "end": 3124.68, "word": ",", "probability": 0.59033203125 } ] }, { "id": 1302, "seek": 307666, "start": 3125.4, "end": 3131.6, "text": " equals mnb, tf, idf, .predict, using the predict function,", "tokens": [ 51114, 6915, 275, 77, 65, 11, 256, 69, 11, 4496, 69, 11, 2411, 79, 24945, 11, 1228, 264, 6069, 2445, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.17113095578693208, "compression_ratio": 1.7707006369426752, "no_speech_prob": 0.0592041015625, "words": [ { "start": 3125.4, "end": 3125.7, "word": " equals", "probability": 0.80126953125 }, { "start": 3125.7, "end": 3126.76, "word": " mnb", "probability": 0.8531901041666666 }, { "start": 3126.76, "end": 3126.96, "word": ",", "probability": 0.8486328125 }, { "start": 3126.96, "end": 3127.66, "word": " tf", "probability": 0.976806640625 }, { "start": 3127.66, "end": 3127.76, "word": ",", "probability": 0.98291015625 }, { "start": 3127.76, "end": 3128.2, "word": " idf", "probability": 0.962158203125 }, { "start": 3128.2, "end": 3128.22, "word": ",", "probability": 0.460205078125 }, { "start": 3128.22, "end": 3129.14, "word": " .predict", "probability": 0.5980224609375 }, { "start": 3129.14, "end": 3129.64, "word": ",", "probability": 0.71923828125 }, { "start": 3129.64, "end": 3129.9, "word": " using", "probability": 0.779296875 }, { "start": 3129.9, "end": 3130.06, "word": " the", "probability": 0.79296875 }, { "start": 3130.06, "end": 3130.28, "word": " predict", "probability": 0.80517578125 }, { "start": 3130.28, "end": 3130.66, "word": " function", "probability": 0.84033203125 }, { "start": 3130.66, "end": 3131.6, "word": ",", "probability": 0.8212890625 } ] }, { "id": 1303, "seek": 307666, "start": 3131.6, "end": 3134.76, "text": " on our test, tf, idf, x.", "tokens": [ 51414, 322, 527, 1500, 11, 256, 69, 11, 4496, 69, 11, 2031, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.17113095578693208, "compression_ratio": 1.7707006369426752, "no_speech_prob": 0.0592041015625, "words": [ { "start": 3131.6, "end": 3132.16, "word": " on", "probability": 0.908203125 }, { "start": 3132.16, "end": 3132.46, "word": " our", "probability": 0.81298828125 }, { "start": 3132.46, "end": 3132.84, "word": " test", "probability": 0.8017578125 }, { "start": 3132.84, "end": 3132.94, "word": ",", "probability": 0.85888671875 }, { "start": 3132.94, "end": 3133.38, "word": " tf", "probability": 0.977783203125 }, { "start": 3133.38, "end": 3133.46, "word": ",", "probability": 0.99560546875 }, { "start": 3133.46, "end": 3133.84, "word": " idf", "probability": 0.95068359375 }, { "start": 3133.84, "end": 3133.86, "word": ",", "probability": 0.99072265625 }, { "start": 3133.86, "end": 3134.22, "word": " x", "probability": 0.9970703125 }, { "start": 3134.22, "end": 3134.76, "word": ".", "probability": 0.9560546875 } ] }, { "id": 1304, "seek": 307666, "start": 3135.54, "end": 3136.4, "text": " Cool.", "tokens": [ 51614, 8561, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.17113095578693208, "compression_ratio": 1.7707006369426752, "no_speech_prob": 0.0592041015625, "words": [ { "start": 3135.54, "end": 3135.86, "word": " Cool", "probability": 0.685546875 }, { "start": 3135.86, "end": 3136.4, "word": ".", "probability": 0.83203125 } ] }, { "id": 1305, "seek": 310398, "start": 3136.4, "end": 3139.76, "text": " And with those results, what we are going to do", "tokens": [ 50364, 400, 365, 729, 3542, 11, 437, 321, 366, 516, 281, 360, 50514 ], "temperature": 0.0, "avg_logprob": -0.1996527777777778, "compression_ratio": 1.7073170731707317, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 3136.4, "end": 3137.62, "word": " And", "probability": 0.583984375 }, { "start": 3137.62, "end": 3138.02, "word": " with", "probability": 0.76806640625 }, { "start": 3138.02, "end": 3138.26, "word": " those", "probability": 0.85791015625 }, { "start": 3138.26, "end": 3138.68, "word": " results", "probability": 0.697265625 }, { "start": 3138.68, "end": 3138.8, "word": ",", "probability": 0.71630859375 }, { "start": 3138.8, "end": 3138.9, "word": " what", "probability": 0.88330078125 }, { "start": 3138.9, "end": 3139.02, "word": " we", "probability": 0.90576171875 }, { "start": 3139.02, "end": 3139.1, "word": " are", "probability": 0.591796875 }, { "start": 3139.1, "end": 3139.3, "word": " going", "probability": 0.8564453125 }, { "start": 3139.3, "end": 3139.46, "word": " to", "probability": 0.90625 }, { "start": 3139.46, "end": 3139.76, "word": " do", "probability": 0.90625 } ] }, { "id": 1306, "seek": 310398, "start": 3139.76, "end": 3143.7, "text": " is generate a classification, a confusion matrix,", "tokens": [ 50514, 307, 8460, 257, 21538, 11, 257, 15075, 8141, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.1996527777777778, "compression_ratio": 1.7073170731707317, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 3139.76, "end": 3140.26, "word": " is", "probability": 0.8681640625 }, { "start": 3140.26, "end": 3140.74, "word": " generate", "probability": 0.80712890625 }, { "start": 3141.28, "end": 3141.88, "word": " a classification", "probability": 0.62744140625 }, { "start": 3141.88, "end": 3142.44, "word": ",", "probability": 0.76123046875 }, { "start": 3142.88, "end": 3143.26, "word": " a confusion", "probability": 0.87255859375 }, { "start": 3143.26, "end": 3143.58, "word": " matrix", "probability": 0.85498046875 }, { "start": 3143.58, "end": 3143.7, "word": ",", "probability": 0.34765625 } ] }, { "id": 1307, "seek": 310398, "start": 3143.7, "end": 3145.9, "text": " so we can see our true positives, false positives,", "tokens": [ 50714, 370, 321, 393, 536, 527, 2074, 35127, 11, 7908, 35127, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.1996527777777778, "compression_ratio": 1.7073170731707317, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 3143.7, "end": 3143.8, "word": " so", "probability": 0.89111328125 }, { "start": 3143.8, "end": 3143.88, "word": " we", "probability": 0.89892578125 }, { "start": 3143.88, "end": 3144.0, "word": " can", "probability": 0.89794921875 }, { "start": 3144.0, "end": 3144.26, "word": " see", "probability": 0.81884765625 }, { "start": 3144.26, "end": 3144.5, "word": " our", "probability": 0.77392578125 }, { "start": 3144.5, "end": 3144.68, "word": " true", "probability": 0.904296875 }, { "start": 3144.68, "end": 3145.1, "word": " positives", "probability": 0.84521484375 }, { "start": 3145.1, "end": 3145.24, "word": ",", "probability": 0.982421875 }, { "start": 3145.24, "end": 3145.38, "word": " false", "probability": 0.865234375 }, { "start": 3145.38, "end": 3145.72, "word": " positives", "probability": 0.8740234375 }, { "start": 3145.72, "end": 3145.9, "word": ",", "probability": 0.99072265625 } ] }, { "id": 1308, "seek": 310398, "start": 3145.9, "end": 3147.54, "text": " true negatives, false negatives.", "tokens": [ 50814, 2074, 40019, 11, 7908, 40019, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.1996527777777778, "compression_ratio": 1.7073170731707317, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 3145.9, "end": 3146.0, "word": " true", "probability": 0.9150390625 }, { "start": 3146.0, "end": 3146.3, "word": " negatives", "probability": 0.80029296875 }, { "start": 3146.3, "end": 3146.42, "word": ",", "probability": 0.99462890625 }, { "start": 3146.42, "end": 3146.54, "word": " false", "probability": 0.83642578125 }, { "start": 3146.54, "end": 3146.9, "word": " negatives", "probability": 0.7958984375 }, { "start": 3146.9, "end": 3147.54, "word": ".", "probability": 0.88525390625 } ] }, { "id": 1309, "seek": 310398, "start": 3147.58, "end": 3159.78, "text": " So cmatrix, mnb, tf, idf, equals our confusion matrix,", "tokens": [ 50914, 407, 14668, 267, 6579, 11, 275, 77, 65, 11, 256, 69, 11, 4496, 69, 11, 6915, 527, 15075, 8141, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.1996527777777778, "compression_ratio": 1.7073170731707317, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 3147.58, "end": 3147.74, "word": " So", "probability": 0.87841796875 }, { "start": 3147.74, "end": 3148.84, "word": " cmatrix", "probability": 0.6410929361979166 }, { "start": 3148.84, "end": 3149.2, "word": ",", "probability": 0.466552734375 }, { "start": 3149.2, "end": 3150.08, "word": " mnb", "probability": 0.6586100260416666 }, { "start": 3150.08, "end": 3150.4, "word": ",", "probability": 0.94140625 }, { "start": 3150.4, "end": 3150.98, "word": " tf", "probability": 0.95166015625 }, { "start": 3150.98, "end": 3151.08, "word": ",", "probability": 0.91650390625 }, { "start": 3151.08, "end": 3151.6, "word": " idf", "probability": 0.925048828125 }, { "start": 3151.6, "end": 3152.04, "word": ",", "probability": 0.386474609375 }, { "start": 3152.04, "end": 3153.2, "word": " equals", "probability": 0.8623046875 }, { "start": 3153.2, "end": 3153.64, "word": " our", "probability": 0.80419921875 }, { "start": 3153.64, "end": 3155.36, "word": " confusion", "probability": 0.91015625 }, { "start": 3155.36, "end": 3159.3, "word": " matrix", "probability": 0.81591796875 }, { "start": 3159.3, "end": 3159.78, "word": ",", "probability": 0.31201171875 } ] }, { "id": 1310, "seek": 310398, "start": 3159.78, "end": 3163.72, "text": " and then we're going to use our test labels", "tokens": [ 51514, 293, 550, 321, 434, 516, 281, 764, 527, 1500, 16949, 51714 ], "temperature": 0.0, "avg_logprob": -0.1996527777777778, "compression_ratio": 1.7073170731707317, "no_speech_prob": 0.003124237060546875, "words": [ { "start": 3159.78, "end": 3160.32, "word": " and", "probability": 0.875 }, { "start": 3160.32, "end": 3160.44, "word": " then", "probability": 0.67333984375 }, { "start": 3160.44, "end": 3160.56, "word": " we're", "probability": 0.91943359375 }, { "start": 3160.56, "end": 3160.74, "word": " going", "probability": 0.85888671875 }, { "start": 3160.74, "end": 3160.9, "word": " to", "probability": 0.90380859375 }, { "start": 3160.9, "end": 3161.18, "word": " use", "probability": 0.830078125 }, { "start": 3161.18, "end": 3161.8, "word": " our", "probability": 0.81103515625 }, { "start": 3161.8, "end": 3163.28, "word": " test", "probability": 0.83447265625 }, { "start": 3163.28, "end": 3163.72, "word": " labels", "probability": 0.8330078125 } ] }, { "id": 1311, "seek": 312958, "start": 3163.72, "end": 3170.8, "text": " and our predictions, mnb, tf, idf, which is our raw predictions.", "tokens": [ 50364, 293, 527, 21264, 11, 275, 77, 65, 11, 256, 69, 11, 4496, 69, 11, 597, 307, 527, 8936, 21264, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.203488374692063, "compression_ratio": 1.8686131386861313, "no_speech_prob": 0.27490234375, "words": [ { "start": 3163.72, "end": 3164.02, "word": " and", "probability": 0.61474609375 }, { "start": 3164.02, "end": 3164.4, "word": " our", "probability": 0.78662109375 }, { "start": 3164.4, "end": 3166.86, "word": " predictions", "probability": 0.712890625 }, { "start": 3166.86, "end": 3167.6, "word": ",", "probability": 0.460693359375 }, { "start": 3167.6, "end": 3168.12, "word": " mnb", "probability": 0.5611979166666666 }, { "start": 3168.12, "end": 3168.24, "word": ",", "probability": 0.76416015625 }, { "start": 3168.24, "end": 3168.8, "word": " tf", "probability": 0.96875 }, { "start": 3168.8, "end": 3168.88, "word": ",", "probability": 0.96923828125 }, { "start": 3168.88, "end": 3169.16, "word": " idf", "probability": 0.929931640625 }, { "start": 3169.16, "end": 3169.22, "word": ",", "probability": 0.7255859375 }, { "start": 3169.22, "end": 3169.36, "word": " which", "probability": 0.9072265625 }, { "start": 3169.36, "end": 3169.46, "word": " is", "probability": 0.84375 }, { "start": 3169.46, "end": 3169.58, "word": " our", "probability": 0.81298828125 }, { "start": 3169.58, "end": 3169.88, "word": " raw", "probability": 0.83544921875 }, { "start": 3169.88, "end": 3170.34, "word": " predictions", "probability": 0.798828125 }, { "start": 3170.34, "end": 3170.8, "word": ".", "probability": 0.951171875 } ] }, { "id": 1312, "seek": 312958, "start": 3170.8, "end": 3173.22, "text": " We're going to do the same thing for our classification report,", "tokens": [ 50714, 492, 434, 516, 281, 360, 264, 912, 551, 337, 527, 21538, 2275, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.203488374692063, "compression_ratio": 1.8686131386861313, "no_speech_prob": 0.27490234375, "words": [ { "start": 3170.8, "end": 3171.1, "word": " We're", "probability": 0.747314453125 }, { "start": 3171.1, "end": 3171.16, "word": " going", "probability": 0.59375 }, { "start": 3171.16, "end": 3171.18, "word": " to", "probability": 0.904296875 }, { "start": 3171.18, "end": 3171.3, "word": " do", "probability": 0.8935546875 }, { "start": 3171.3, "end": 3171.42, "word": " the", "probability": 0.81103515625 }, { "start": 3171.42, "end": 3171.6, "word": " same", "probability": 0.814453125 }, { "start": 3171.6, "end": 3171.84, "word": " thing", "probability": 0.79541015625 }, { "start": 3171.84, "end": 3172.0, "word": " for", "probability": 0.8916015625 }, { "start": 3172.0, "end": 3172.12, "word": " our", "probability": 0.72802734375 }, { "start": 3172.12, "end": 3172.58, "word": " classification", "probability": 0.900390625 }, { "start": 3172.58, "end": 3173.06, "word": " report", "probability": 0.341796875 }, { "start": 3173.06, "end": 3173.22, "word": ",", "probability": 0.438720703125 } ] }, { "id": 1313, "seek": 312958, "start": 3173.22, "end": 3178.68, "text": " so we'll see report, mnb, tf, idf,", "tokens": [ 50814, 370, 321, 603, 536, 2275, 11, 275, 77, 65, 11, 256, 69, 11, 4496, 69, 11, 51164 ], "temperature": 0.0, "avg_logprob": -0.203488374692063, "compression_ratio": 1.8686131386861313, "no_speech_prob": 0.27490234375, "words": [ { "start": 3173.22, "end": 3173.34, "word": " so", "probability": 0.7900390625 }, { "start": 3173.34, "end": 3173.4, "word": " we'll", "probability": 0.41204833984375 }, { "start": 3173.4, "end": 3173.48, "word": " see", "probability": 0.654296875 }, { "start": 3173.48, "end": 3174.36, "word": " report", "probability": 0.6025390625 }, { "start": 3174.36, "end": 3175.04, "word": ",", "probability": 0.837890625 }, { "start": 3175.04, "end": 3175.64, "word": " mnb", "probability": 0.9560546875 }, { "start": 3175.64, "end": 3175.84, "word": ",", "probability": 0.9873046875 }, { "start": 3175.84, "end": 3176.32, "word": " tf", "probability": 0.974609375 }, { "start": 3176.32, "end": 3176.42, "word": ",", "probability": 0.9921875 }, { "start": 3176.42, "end": 3176.94, "word": " idf", "probability": 0.955078125 }, { "start": 3176.94, "end": 3178.68, "word": ",", "probability": 0.703125 } ] }, { "id": 1314, "seek": 312958, "start": 3179.94, "end": 3182.3, "text": " classification report, and in the same order,", "tokens": [ 51164, 21538, 2275, 11, 293, 294, 264, 912, 1668, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.203488374692063, "compression_ratio": 1.8686131386861313, "no_speech_prob": 0.27490234375, "words": [ { "start": 3179.94, "end": 3180.54, "word": " classification", "probability": 0.86279296875 }, { "start": 3180.54, "end": 3181.14, "word": " report", "probability": 0.82568359375 }, { "start": 3181.14, "end": 3181.24, "word": ",", "probability": 0.68017578125 }, { "start": 3181.24, "end": 3181.36, "word": " and", "probability": 0.84814453125 }, { "start": 3181.36, "end": 3181.46, "word": " in", "probability": 0.5322265625 }, { "start": 3181.46, "end": 3181.6, "word": " the", "probability": 0.8134765625 }, { "start": 3181.6, "end": 3181.8, "word": " same", "probability": 0.814453125 }, { "start": 3181.8, "end": 3182.14, "word": " order", "probability": 0.7958984375 }, { "start": 3182.14, "end": 3182.3, "word": ",", "probability": 0.7236328125 } ] }, { "id": 1315, "seek": 312958, "start": 3182.3, "end": 3189.32, "text": " test labels and our predictions, mnb, tf, idf.", "tokens": [ 51264, 1500, 16949, 293, 527, 21264, 11, 275, 77, 65, 11, 256, 69, 11, 4496, 69, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.203488374692063, "compression_ratio": 1.8686131386861313, "no_speech_prob": 0.27490234375, "words": [ { "start": 3182.3, "end": 3182.64, "word": " test", "probability": 0.75927734375 }, { "start": 3182.64, "end": 3183.2, "word": " labels", "probability": 0.67041015625 }, { "start": 3183.2, "end": 3184.46, "word": " and", "probability": 0.443115234375 }, { "start": 3184.46, "end": 3184.86, "word": " our", "probability": 0.7998046875 }, { "start": 3184.86, "end": 3186.04, "word": " predictions", "probability": 0.7421875 }, { "start": 3186.04, "end": 3187.12, "word": ",", "probability": 0.8837890625 }, { "start": 3187.12, "end": 3187.58, "word": " mnb", "probability": 0.94775390625 }, { "start": 3187.58, "end": 3187.78, "word": ",", "probability": 0.9931640625 }, { "start": 3187.78, "end": 3188.26, "word": " tf", "probability": 0.968994140625 }, { "start": 3188.26, "end": 3188.36, "word": ",", "probability": 0.99462890625 }, { "start": 3188.36, "end": 3188.72, "word": " idf", "probability": 0.96044921875 }, { "start": 3188.72, "end": 3189.32, "word": ".", "probability": 0.9873046875 } ] }, { "id": 1316, "seek": 315776, "start": 3190.68, "end": 3193.9, "text": " So I'm going to let this sit for a second,", "tokens": [ 50414, 407, 286, 478, 516, 281, 718, 341, 1394, 337, 257, 1150, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.17221101637809508, "compression_ratio": 1.547486033519553, "no_speech_prob": 0.005382537841796875, "words": [ { "start": 3190.68, "end": 3191.2, "word": " So", "probability": 0.52685546875 }, { "start": 3191.2, "end": 3191.34, "word": " I'm", "probability": 0.857421875 }, { "start": 3191.34, "end": 3191.34, "word": " going", "probability": 0.350830078125 }, { "start": 3191.34, "end": 3191.36, "word": " to", "probability": 0.89111328125 }, { "start": 3191.36, "end": 3191.48, "word": " let", "probability": 0.8876953125 }, { "start": 3191.48, "end": 3191.7, "word": " this", "probability": 0.875 }, { "start": 3191.7, "end": 3191.98, "word": " sit", "probability": 0.9091796875 }, { "start": 3191.98, "end": 3192.18, "word": " for", "probability": 0.89111328125 }, { "start": 3192.4, "end": 3192.66, "word": " a second", "probability": 0.79736328125 }, { "start": 3192.66, "end": 3193.9, "word": ",", "probability": 0.361083984375 } ] }, { "id": 1317, "seek": 315776, "start": 3194.58, "end": 3197.52, "text": " give you a chance to copy all of that down.", "tokens": [ 50614, 976, 291, 257, 2931, 281, 5055, 439, 295, 300, 760, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.17221101637809508, "compression_ratio": 1.547486033519553, "no_speech_prob": 0.005382537841796875, "words": [ { "start": 3194.58, "end": 3195.1, "word": " give", "probability": 0.74951171875 }, { "start": 3195.1, "end": 3195.16, "word": " you", "probability": 0.865234375 }, { "start": 3195.28, "end": 3195.48, "word": " a chance", "probability": 0.90625 }, { "start": 3195.48, "end": 3195.68, "word": " to", "probability": 0.9033203125 }, { "start": 3195.68, "end": 3195.98, "word": " copy", "probability": 0.791015625 }, { "start": 3195.98, "end": 3196.3, "word": " all", "probability": 0.90234375 }, { "start": 3196.3, "end": 3196.44, "word": " of", "probability": 0.89208984375 }, { "start": 3196.44, "end": 3196.62, "word": " that", "probability": 0.884765625 }, { "start": 3196.62, "end": 3197.0, "word": " down", "probability": 0.802734375 }, { "start": 3197.0, "end": 3197.52, "word": ".", "probability": 0.96875 } ] }, { "id": 1318, "seek": 315776, "start": 3199.58, "end": 3204.6, "text": " So what's really helpful here is seeing how", "tokens": [ 50864, 407, 437, 311, 534, 4961, 510, 307, 2577, 577, 51264 ], "temperature": 0.0, "avg_logprob": -0.17221101637809508, "compression_ratio": 1.547486033519553, "no_speech_prob": 0.005382537841796875, "words": [ { "start": 3199.58, "end": 3200.1, "word": " So", "probability": 0.85498046875 }, { "start": 3200.1, "end": 3200.62, "word": " what's", "probability": 0.898681640625 }, { "start": 3200.62, "end": 3201.44, "word": " really", "probability": 0.65185546875 }, { "start": 3201.44, "end": 3201.86, "word": " helpful", "probability": 0.83447265625 }, { "start": 3201.86, "end": 3202.32, "word": " here", "probability": 0.81640625 }, { "start": 3202.32, "end": 3202.98, "word": " is", "probability": 0.87548828125 }, { "start": 3202.98, "end": 3203.66, "word": " seeing", "probability": 0.80029296875 }, { "start": 3203.66, "end": 3204.6, "word": " how", "probability": 0.896484375 } ] }, { "id": 1319, "seek": 315776, "start": 3207.2, "end": 3210.72, "text": " at each of these tasks, 6a, 6b, 6c, and 6d,", "tokens": [ 51264, 412, 1184, 295, 613, 9608, 11, 1386, 64, 11, 1386, 65, 11, 1386, 66, 11, 293, 1386, 67, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.17221101637809508, "compression_ratio": 1.547486033519553, "no_speech_prob": 0.005382537841796875, "words": [ { "start": 3207.2, "end": 3207.72, "word": " at", "probability": 0.685546875 }, { "start": 3207.72, "end": 3207.94, "word": " each", "probability": 0.8642578125 }, { "start": 3207.94, "end": 3208.06, "word": " of", "probability": 0.90380859375 }, { "start": 3208.06, "end": 3208.24, "word": " these", "probability": 0.7021484375 }, { "start": 3208.24, "end": 3208.68, "word": " tasks", "probability": 0.87451171875 }, { "start": 3208.68, "end": 3208.76, "word": ",", "probability": 0.446533203125 }, { "start": 3208.76, "end": 3209.04, "word": " 6a", "probability": 0.69482421875 }, { "start": 3209.04, "end": 3209.12, "word": ",", "probability": 0.95751953125 }, { "start": 3209.12, "end": 3209.42, "word": " 6b", "probability": 0.993896484375 }, { "start": 3209.42, "end": 3209.54, "word": ",", "probability": 0.994140625 }, { "start": 3209.54, "end": 3209.84, "word": " 6c", "probability": 0.989501953125 }, { "start": 3209.84, "end": 3209.88, "word": ",", "probability": 0.61474609375 }, { "start": 3209.88, "end": 3209.96, "word": " and", "probability": 0.87646484375 }, { "start": 3209.96, "end": 3210.4, "word": " 6d", "probability": 0.99853515625 }, { "start": 3210.4, "end": 3210.72, "word": ",", "probability": 0.8359375 } ] }, { "id": 1320, "seek": 315776, "start": 3211.32, "end": 3214.24, "text": " we're only going to need to change very few things.", "tokens": [ 51464, 321, 434, 787, 516, 281, 643, 281, 1319, 588, 1326, 721, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.17221101637809508, "compression_ratio": 1.547486033519553, "no_speech_prob": 0.005382537841796875, "words": [ { "start": 3211.32, "end": 3211.6, "word": " we're", "probability": 0.917236328125 }, { "start": 3211.6, "end": 3211.74, "word": " only", "probability": 0.85009765625 }, { "start": 3211.74, "end": 3211.82, "word": " going", "probability": 0.8173828125 }, { "start": 3211.82, "end": 3211.9, "word": " to", "probability": 0.90283203125 }, { "start": 3211.9, "end": 3212.02, "word": " need", "probability": 0.78955078125 }, { "start": 3212.02, "end": 3212.18, "word": " to", "probability": 0.9033203125 }, { "start": 3212.18, "end": 3212.6, "word": " change", "probability": 0.849609375 }, { "start": 3212.6, "end": 3213.02, "word": " very", "probability": 0.73193359375 }, { "start": 3213.02, "end": 3213.44, "word": " few", "probability": 0.7841796875 }, { "start": 3213.44, "end": 3214.02, "word": " things", "probability": 0.73828125 }, { "start": 3214.02, "end": 3214.24, "word": ".", "probability": 0.3388671875 } ] }, { "id": 1321, "seek": 315776, "start": 3214.24, "end": 3217.5, "text": " We're going to need to change, instead of tf, idf,", "tokens": [ 51614, 492, 434, 516, 281, 643, 281, 1319, 11, 2602, 295, 256, 69, 11, 4496, 69, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.17221101637809508, "compression_ratio": 1.547486033519553, "no_speech_prob": 0.005382537841796875, "words": [ { "start": 3214.24, "end": 3214.5, "word": " We're", "probability": 0.837158203125 }, { "start": 3214.5, "end": 3214.68, "word": " going", "probability": 0.8564453125 }, { "start": 3214.68, "end": 3214.82, "word": " to", "probability": 0.90380859375 }, { "start": 3214.82, "end": 3214.96, "word": " need", "probability": 0.78125 }, { "start": 3214.96, "end": 3215.12, "word": " to", "probability": 0.90625 }, { "start": 3215.12, "end": 3215.56, "word": " change", "probability": 0.84765625 }, { "start": 3215.56, "end": 3215.62, "word": ",", "probability": 0.3671875 }, { "start": 3215.62, "end": 3215.94, "word": " instead", "probability": 0.85107421875 }, { "start": 3215.94, "end": 3216.38, "word": " of", "probability": 0.9013671875 }, { "start": 3216.38, "end": 3216.72, "word": " tf", "probability": 0.79833984375 }, { "start": 3216.72, "end": 3216.74, "word": ",", "probability": 0.0433349609375 }, { "start": 3216.74, "end": 3217.28, "word": " idf", "probability": 0.5814208984375 }, { "start": 3217.28, "end": 3217.5, "word": ",", "probability": 0.93212890625 } ] }, { "id": 1322, "seek": 318588, "start": 3217.5, "end": 3220.6, "text": " we're going to change this to count to do our train and evaluate", "tokens": [ 50364, 321, 434, 516, 281, 1319, 341, 281, 1207, 281, 360, 527, 3847, 293, 13059, 50514 ], "temperature": 0.0, "avg_logprob": -0.19767441860465115, "compression_ratio": 2.0277777777777777, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 3217.5, "end": 3217.86, "word": " we're", "probability": 0.586669921875 }, { "start": 3217.86, "end": 3217.94, "word": " going", "probability": 0.798828125 }, { "start": 3217.94, "end": 3218.02, "word": " to", "probability": 0.90576171875 }, { "start": 3218.02, "end": 3218.2, "word": " change", "probability": 0.8251953125 }, { "start": 3218.2, "end": 3218.38, "word": " this", "probability": 0.8798828125 }, { "start": 3218.38, "end": 3218.54, "word": " to", "probability": 0.8974609375 }, { "start": 3218.54, "end": 3218.9, "word": " count", "probability": 0.5537109375 }, { "start": 3218.9, "end": 3219.24, "word": " to", "probability": 0.7939453125 }, { "start": 3219.24, "end": 3219.56, "word": " do", "probability": 0.88037109375 }, { "start": 3219.56, "end": 3219.86, "word": " our", "probability": 0.80419921875 }, { "start": 3219.86, "end": 3220.12, "word": " train", "probability": 0.69384765625 }, { "start": 3220.12, "end": 3220.24, "word": " and", "probability": 0.85986328125 }, { "start": 3220.24, "end": 3220.6, "word": " evaluate", "probability": 0.77001953125 } ] }, { "id": 1323, "seek": 318588, "start": 3220.6, "end": 3223.5, "text": " the multinomial Naive Bayesian with the count model.", "tokens": [ 50514, 264, 45872, 47429, 6056, 488, 7840, 42434, 365, 264, 1207, 2316, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.19767441860465115, "compression_ratio": 2.0277777777777777, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 3220.6, "end": 3220.8, "word": " the", "probability": 0.8017578125 }, { "start": 3220.8, "end": 3221.36, "word": " multinomial", "probability": 0.93115234375 }, { "start": 3221.36, "end": 3221.74, "word": " Naive", "probability": 0.6260986328125 }, { "start": 3221.74, "end": 3222.06, "word": " Bayesian", "probability": 0.87744140625 }, { "start": 3222.06, "end": 3222.3, "word": " with", "probability": 0.78466796875 }, { "start": 3222.3, "end": 3222.44, "word": " the", "probability": 0.73583984375 }, { "start": 3222.44, "end": 3222.68, "word": " count", "probability": 0.7197265625 }, { "start": 3222.68, "end": 3223.06, "word": " model", "probability": 0.8232421875 }, { "start": 3223.06, "end": 3223.5, "word": ".", "probability": 0.331787109375 } ] }, { "id": 1324, "seek": 318588, "start": 3223.72, "end": 3226.62, "text": " And then we're going to change this from", "tokens": [ 50664, 400, 550, 321, 434, 516, 281, 1319, 341, 490, 50814 ], "temperature": 0.0, "avg_logprob": -0.19767441860465115, "compression_ratio": 2.0277777777777777, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 3223.72, "end": 3223.78, "word": " And", "probability": 0.5419921875 }, { "start": 3223.78, "end": 3224.06, "word": " then", "probability": 0.720703125 }, { "start": 3224.06, "end": 3224.98, "word": " we're", "probability": 0.887451171875 }, { "start": 3224.98, "end": 3225.14, "word": " going", "probability": 0.859375 }, { "start": 3225.14, "end": 3225.32, "word": " to", "probability": 0.90673828125 }, { "start": 3225.32, "end": 3225.8, "word": " change", "probability": 0.8310546875 }, { "start": 3225.8, "end": 3226.26, "word": " this", "probability": 0.873046875 }, { "start": 3226.26, "end": 3226.62, "word": " from", "probability": 0.798828125 } ] }, { "id": 1325, "seek": 318588, "start": 3226.62, "end": 3228.52, "text": " the multinomial Naive Bayesian constructor", "tokens": [ 50814, 264, 45872, 47429, 6056, 488, 7840, 42434, 47479, 50914 ], "temperature": 0.0, "avg_logprob": -0.19767441860465115, "compression_ratio": 2.0277777777777777, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 3226.62, "end": 3226.86, "word": " the", "probability": 0.810546875 }, { "start": 3226.86, "end": 3227.38, "word": " multinomial", "probability": 0.867431640625 }, { "start": 3227.38, "end": 3227.72, "word": " Naive", "probability": 0.872802734375 }, { "start": 3227.72, "end": 3228.02, "word": " Bayesian", "probability": 0.89892578125 }, { "start": 3228.02, "end": 3228.52, "word": " constructor", "probability": 0.6669921875 } ] }, { "id": 1326, "seek": 318588, "start": 3228.52, "end": 3231.28, "text": " to the logistic regression constructor.", "tokens": [ 50914, 281, 264, 3565, 3142, 24590, 47479, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.19767441860465115, "compression_ratio": 2.0277777777777777, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 3228.52, "end": 3228.96, "word": " to", "probability": 0.8798828125 }, { "start": 3228.96, "end": 3229.28, "word": " the", "probability": 0.8154296875 }, { "start": 3229.28, "end": 3229.78, "word": " logistic", "probability": 0.8896484375 }, { "start": 3229.78, "end": 3230.18, "word": " regression", "probability": 0.890625 }, { "start": 3230.18, "end": 3230.84, "word": " constructor", "probability": 0.69091796875 }, { "start": 3230.84, "end": 3231.28, "word": ".", "probability": 0.76806640625 } ] }, { "id": 1327, "seek": 318588, "start": 3231.4, "end": 3233.84, "text": " But other than that, the rest of our code is going to be identical.", "tokens": [ 51064, 583, 661, 813, 300, 11, 264, 1472, 295, 527, 3089, 307, 516, 281, 312, 14800, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.19767441860465115, "compression_ratio": 2.0277777777777777, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 3231.4, "end": 3231.58, "word": " But", "probability": 0.82958984375 }, { "start": 3231.58, "end": 3231.74, "word": " other", "probability": 0.76904296875 }, { "start": 3231.74, "end": 3231.9, "word": " than", "probability": 0.8857421875 }, { "start": 3231.9, "end": 3232.08, "word": " that", "probability": 0.87744140625 }, { "start": 3232.08, "end": 3232.12, "word": ",", "probability": 0.50927734375 }, { "start": 3232.12, "end": 3232.24, "word": " the", "probability": 0.81298828125 }, { "start": 3232.24, "end": 3232.42, "word": " rest", "probability": 0.7978515625 }, { "start": 3232.42, "end": 3232.54, "word": " of", "probability": 0.90673828125 }, { "start": 3232.54, "end": 3232.66, "word": " our", "probability": 0.8134765625 }, { "start": 3232.66, "end": 3232.84, "word": " code", "probability": 0.7353515625 }, { "start": 3232.84, "end": 3232.96, "word": " is", "probability": 0.89892578125 }, { "start": 3232.96, "end": 3233.08, "word": " going", "probability": 0.84814453125 }, { "start": 3233.08, "end": 3233.14, "word": " to", "probability": 0.90380859375 }, { "start": 3233.14, "end": 3233.26, "word": " be", "probability": 0.9072265625 }, { "start": 3233.26, "end": 3233.68, "word": " identical", "probability": 0.806640625 }, { "start": 3233.68, "end": 3233.84, "word": ".", "probability": 0.52880859375 } ] }, { "id": 1328, "seek": 318588, "start": 3233.84, "end": 3236.28, "text": " The rest of our preprocessing is going to be identical.", "tokens": [ 51164, 440, 1472, 295, 527, 2666, 340, 780, 278, 307, 516, 281, 312, 14800, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.19767441860465115, "compression_ratio": 2.0277777777777777, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 3233.84, "end": 3233.94, "word": " The", "probability": 0.79638671875 }, { "start": 3233.94, "end": 3234.14, "word": " rest", "probability": 0.787109375 }, { "start": 3234.14, "end": 3234.26, "word": " of", "probability": 0.9072265625 }, { "start": 3234.26, "end": 3234.38, "word": " our", "probability": 0.82080078125 }, { "start": 3234.38, "end": 3235.04, "word": " preprocessing", "probability": 0.81982421875 }, { "start": 3235.04, "end": 3235.18, "word": " is", "probability": 0.9052734375 }, { "start": 3235.18, "end": 3235.28, "word": " going", "probability": 0.85595703125 }, { "start": 3235.28, "end": 3235.32, "word": " to", "probability": 0.90673828125 }, { "start": 3235.32, "end": 3235.44, "word": " be", "probability": 0.90966796875 }, { "start": 3235.44, "end": 3235.84, "word": " identical", "probability": 0.80224609375 }, { "start": 3235.84, "end": 3236.28, "word": ".", "probability": 0.7919921875 } ] }, { "id": 1329, "seek": 318588, "start": 3236.48, "end": 3239.24, "text": " And so this will allow us to train a total of four algorithms", "tokens": [ 51314, 400, 370, 341, 486, 2089, 505, 281, 3847, 257, 3217, 295, 1451, 14642, 51464 ], "temperature": 0.0, "avg_logprob": -0.19767441860465115, "compression_ratio": 2.0277777777777777, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 3236.48, "end": 3236.56, "word": " And", "probability": 0.787109375 }, { "start": 3236.56, "end": 3236.68, "word": " so", "probability": 0.90185546875 }, { "start": 3236.68, "end": 3236.84, "word": " this", "probability": 0.83544921875 }, { "start": 3236.84, "end": 3237.0, "word": " will", "probability": 0.81591796875 }, { "start": 3237.0, "end": 3237.2, "word": " allow", "probability": 0.8740234375 }, { "start": 3237.2, "end": 3237.4, "word": " us", "probability": 0.9013671875 }, { "start": 3237.4, "end": 3237.56, "word": " to", "probability": 0.904296875 }, { "start": 3237.56, "end": 3237.84, "word": " train", "probability": 0.79443359375 }, { "start": 3238.04, "end": 3238.22, "word": " a total", "probability": 0.79833984375 }, { "start": 3238.22, "end": 3238.42, "word": " of", "probability": 0.90283203125 }, { "start": 3238.42, "end": 3238.68, "word": " four", "probability": 0.859375 }, { "start": 3238.68, "end": 3239.24, "word": " algorithms", "probability": 0.880859375 } ] }, { "id": 1330, "seek": 318588, "start": 3239.96, "end": 3243.86, "text": " using two separate machine learning algorithms", "tokens": [ 51464, 1228, 732, 4994, 3479, 2539, 14642, 51664 ], "temperature": 0.0, "avg_logprob": -0.19767441860465115, "compression_ratio": 2.0277777777777777, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 3239.96, "end": 3240.4, "word": " using", "probability": 0.70166015625 }, { "start": 3240.4, "end": 3240.78, "word": " two", "probability": 0.81494140625 }, { "start": 3240.78, "end": 3241.36, "word": " separate", "probability": 0.8623046875 }, { "start": 3241.36, "end": 3243.16, "word": " machine", "probability": 0.6591796875 }, { "start": 3243.16, "end": 3243.46, "word": " learning", "probability": 0.82958984375 }, { "start": 3243.46, "end": 3243.86, "word": " algorithms", "probability": 0.8818359375 } ] }, { "id": 1331, "seek": 318588, "start": 3243.86, "end": 3245.62, "text": " as well as two separate vectorizers.", "tokens": [ 51664, 382, 731, 382, 732, 4994, 8062, 22525, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.19767441860465115, "compression_ratio": 2.0277777777777777, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 3243.86, "end": 3244.12, "word": " as", "probability": 0.5732421875 }, { "start": 3244.12, "end": 3244.22, "word": " well", "probability": 0.87451171875 }, { "start": 3244.22, "end": 3244.34, "word": " as", "probability": 0.90234375 }, { "start": 3244.34, "end": 3244.52, "word": " two", "probability": 0.8212890625 }, { "start": 3244.52, "end": 3244.8, "word": " separate", "probability": 0.86962890625 }, { "start": 3244.8, "end": 3245.38, "word": " vectorizers", "probability": 0.930419921875 }, { "start": 3245.38, "end": 3245.62, "word": ".", "probability": 0.9833984375 } ] }, { "id": 1332, "seek": 321166, "start": 3246.34, "end": 3249.1, "text": " So this is going to be very helpful for us.", "tokens": [ 50414, 407, 341, 307, 516, 281, 312, 588, 4961, 337, 505, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.29581924548020233, "compression_ratio": 1.3642384105960266, "no_speech_prob": 0.0244140625, "words": [ { "start": 3246.34, "end": 3247.06, "word": " So", "probability": 0.49755859375 }, { "start": 3247.06, "end": 3247.16, "word": " this", "probability": 0.1046142578125 }, { "start": 3247.16, "end": 3247.2, "word": " is", "probability": 0.8662109375 }, { "start": 3247.2, "end": 3247.26, "word": " going", "probability": 0.365234375 }, { "start": 3247.26, "end": 3247.26, "word": " to", "probability": 0.90234375 }, { "start": 3247.26, "end": 3247.38, "word": " be", "probability": 0.9013671875 }, { "start": 3247.38, "end": 3247.66, "word": " very", "probability": 0.72705078125 }, { "start": 3247.66, "end": 3247.92, "word": " helpful", "probability": 0.8212890625 }, { "start": 3247.92, "end": 3248.14, "word": " for", "probability": 0.890625 }, { "start": 3248.14, "end": 3248.38, "word": " us", "probability": 0.9091796875 }, { "start": 3248.38, "end": 3249.1, "word": ".", "probability": 0.96826171875 } ] }, { "id": 1333, "seek": 321166, "start": 3250.4, "end": 3254.04, "text": " So I'm going to go ahead and run this.", "tokens": [ 50614, 407, 286, 478, 516, 281, 352, 2286, 293, 1190, 341, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.29581924548020233, "compression_ratio": 1.3642384105960266, "no_speech_prob": 0.0244140625, "words": [ { "start": 3250.4, "end": 3251.12, "word": " So", "probability": 0.7998046875 }, { "start": 3251.12, "end": 3251.26, "word": " I'm", "probability": 0.975830078125 }, { "start": 3251.26, "end": 3251.28, "word": " going", "probability": 0.6552734375 }, { "start": 3251.28, "end": 3251.3, "word": " to", "probability": 0.90478515625 }, { "start": 3251.3, "end": 3251.4, "word": " go", "probability": 0.89306640625 }, { "start": 3251.4, "end": 3251.84, "word": " ahead", "probability": 0.8466796875 }, { "start": 3251.84, "end": 3252.4, "word": " and", "probability": 0.89599609375 }, { "start": 3252.4, "end": 3253.1, "word": " run", "probability": 0.89404296875 }, { "start": 3253.1, "end": 3253.6, "word": " this", "probability": 0.88916015625 }, { "start": 3253.6, "end": 3254.04, "word": ".", "probability": 0.6650390625 } ] }, { "id": 1334, "seek": 321166, "start": 3254.04, "end": 3256.26, "text": " So shift-enter to run.", "tokens": [ 50764, 407, 5513, 12, 14278, 281, 1190, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.29581924548020233, "compression_ratio": 1.3642384105960266, "no_speech_prob": 0.0244140625, "words": [ { "start": 3254.04, "end": 3254.14, "word": " So", "probability": 0.88232421875 }, { "start": 3254.14, "end": 3254.6, "word": " shift", "probability": 0.5849609375 }, { "start": 3254.6, "end": 3254.94, "word": "-enter", "probability": 0.430999755859375 }, { "start": 3254.94, "end": 3255.3, "word": " to", "probability": 0.88916015625 }, { "start": 3255.3, "end": 3255.7, "word": " run", "probability": 0.91748046875 }, { "start": 3255.7, "end": 3256.26, "word": ".", "probability": 0.740234375 } ] }, { "id": 1335, "seek": 321166, "start": 3256.26, "end": 3260.24, "text": " It looks like I misspelled something.", "tokens": [ 50914, 467, 1542, 411, 286, 1713, 33000, 746, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.29581924548020233, "compression_ratio": 1.3642384105960266, "no_speech_prob": 0.0244140625, "words": [ { "start": 3256.26, "end": 3256.42, "word": " It", "probability": 0.51171875 }, { "start": 3256.42, "end": 3256.62, "word": " looks", "probability": 0.78271484375 }, { "start": 3256.62, "end": 3256.96, "word": " like", "probability": 0.8798828125 }, { "start": 3256.96, "end": 3257.66, "word": " I", "probability": 0.99365234375 }, { "start": 3257.66, "end": 3258.94, "word": " misspelled", "probability": 0.86962890625 }, { "start": 3258.94, "end": 3259.68, "word": " something", "probability": 0.74658203125 }, { "start": 3259.68, "end": 3260.24, "word": ".", "probability": 0.798828125 } ] }, { "id": 1336, "seek": 321166, "start": 3263.12, "end": 3264.56, "text": " Multinomial.", "tokens": [ 51064, 14665, 259, 298, 831, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.29581924548020233, "compression_ratio": 1.3642384105960266, "no_speech_prob": 0.0244140625, "words": [ { "start": 3263.12, "end": 3263.84, "word": " Multinomial", "probability": 0.57196044921875 }, { "start": 3263.84, "end": 3264.56, "word": ".", "probability": 0.6650390625 } ] }, { "id": 1337, "seek": 321166, "start": 3264.84, "end": 3266.66, "text": " There we go.", "tokens": [ 51314, 821, 321, 352, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.29581924548020233, "compression_ratio": 1.3642384105960266, "no_speech_prob": 0.0244140625, "words": [ { "start": 3264.84, "end": 3265.56, "word": " There", "probability": 0.7529296875 }, { "start": 3265.56, "end": 3265.68, "word": " we", "probability": 0.90087890625 }, { "start": 3265.68, "end": 3265.94, "word": " go", "probability": 0.8984375 }, { "start": 3265.94, "end": 3266.66, "word": ".", "probability": 0.96533203125 } ] }, { "id": 1338, "seek": 321166, "start": 3267.28, "end": 3269.44, "text": " Required argument y.", "tokens": [ 51414, 42029, 1824, 6770, 288, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.29581924548020233, "compression_ratio": 1.3642384105960266, "no_speech_prob": 0.0244140625, "words": [ { "start": 3267.28, "end": 3267.62, "word": " Required", "probability": 0.7034912109375 }, { "start": 3267.62, "end": 3268.04, "word": " argument", "probability": 0.7119140625 }, { "start": 3268.04, "end": 3268.72, "word": " y", "probability": 0.55224609375 }, { "start": 3268.72, "end": 3269.44, "word": ".", "probability": 0.78369140625 } ] }, { "id": 1339, "seek": 321166, "start": 3269.9, "end": 3271.4, "text": " That one's new.", "tokens": [ 51564, 663, 472, 311, 777, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.29581924548020233, "compression_ratio": 1.3642384105960266, "no_speech_prob": 0.0244140625, "words": [ { "start": 3269.9, "end": 3270.22, "word": " That", "probability": 0.79296875 }, { "start": 3270.22, "end": 3270.46, "word": " one's", "probability": 0.848876953125 }, { "start": 3270.46, "end": 3270.68, "word": " new", "probability": 0.7744140625 }, { "start": 3270.68, "end": 3271.4, "word": ".", "probability": 0.99755859375 } ] }, { "id": 1340, "seek": 323920, "start": 3272.98, "end": 3276.58, "text": " Give me one second.", "tokens": [ 50414, 5303, 385, 472, 1150, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.1933803827531876, "compression_ratio": 1.7173913043478262, "no_speech_prob": 0.005218505859375, "words": [ { "start": 3272.98, "end": 3273.52, "word": " Give", "probability": 0.56982421875 }, { "start": 3273.52, "end": 3273.68, "word": " me", "probability": 0.89794921875 }, { "start": 3273.68, "end": 3275.26, "word": " one", "probability": 0.80517578125 }, { "start": 3275.26, "end": 3276.04, "word": " second", "probability": 0.80322265625 }, { "start": 3276.04, "end": 3276.58, "word": ".", "probability": 0.8837890625 } ] }, { "id": 1341, "seek": 323920, "start": 3276.9, "end": 3279.32, "text": " Oh, that is what I forgot.", "tokens": [ 50614, 876, 11, 300, 307, 437, 286, 5298, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.1933803827531876, "compression_ratio": 1.7173913043478262, "no_speech_prob": 0.005218505859375, "words": [ { "start": 3276.9, "end": 3277.14, "word": " Oh", "probability": 0.82373046875 }, { "start": 3277.14, "end": 3277.68, "word": ",", "probability": 0.88671875 }, { "start": 3277.68, "end": 3278.16, "word": " that", "probability": 0.880859375 }, { "start": 3278.16, "end": 3278.28, "word": " is", "probability": 0.90380859375 }, { "start": 3278.28, "end": 3278.42, "word": " what", "probability": 0.89306640625 }, { "start": 3278.42, "end": 3278.54, "word": " I", "probability": 0.998046875 }, { "start": 3278.54, "end": 3278.78, "word": " forgot", "probability": 0.7939453125 }, { "start": 3278.78, "end": 3279.32, "word": ".", "probability": 0.9794921875 } ] }, { "id": 1342, "seek": 323920, "start": 3279.36, "end": 3282.5, "text": " So we want to train our multinomial Naive Bayesian", "tokens": [ 50764, 407, 321, 528, 281, 3847, 527, 45872, 47429, 6056, 488, 7840, 42434, 50914 ], "temperature": 0.0, "avg_logprob": -0.1933803827531876, "compression_ratio": 1.7173913043478262, "no_speech_prob": 0.005218505859375, "words": [ { "start": 3279.36, "end": 3279.74, "word": " So", "probability": 0.841796875 }, { "start": 3279.74, "end": 3280.0, "word": " we", "probability": 0.72265625 }, { "start": 3280.0, "end": 3280.22, "word": " want", "probability": 0.80908203125 }, { "start": 3280.22, "end": 3280.38, "word": " to", "probability": 0.90380859375 }, { "start": 3280.38, "end": 3280.7, "word": " train", "probability": 0.80126953125 }, { "start": 3280.7, "end": 3280.92, "word": " our", "probability": 0.81884765625 }, { "start": 3280.92, "end": 3281.66, "word": " multinomial", "probability": 0.512115478515625 }, { "start": 3281.66, "end": 3282.12, "word": " Naive", "probability": 0.6591796875 }, { "start": 3282.12, "end": 3282.5, "word": " Bayesian", "probability": 0.891845703125 } ] }, { "id": 1343, "seek": 323920, "start": 3282.5, "end": 3286.34, "text": " with our data as well as our labels", "tokens": [ 50914, 365, 527, 1412, 382, 731, 382, 527, 16949, 51114 ], "temperature": 0.0, "avg_logprob": -0.1933803827531876, "compression_ratio": 1.7173913043478262, "no_speech_prob": 0.005218505859375, "words": [ { "start": 3282.5, "end": 3283.02, "word": " with", "probability": 0.79052734375 }, { "start": 3283.02, "end": 3283.58, "word": " our", "probability": 0.8076171875 }, { "start": 3283.58, "end": 3284.42, "word": " data", "probability": 0.80810546875 }, { "start": 3284.42, "end": 3284.78, "word": " as", "probability": 0.6845703125 }, { "start": 3284.78, "end": 3285.18, "word": " well", "probability": 0.8837890625 }, { "start": 3285.18, "end": 3285.52, "word": " as", "probability": 0.908203125 }, { "start": 3285.52, "end": 3285.76, "word": " our", "probability": 0.82666015625 }, { "start": 3285.76, "end": 3286.34, "word": " labels", "probability": 0.85888671875 } ] }, { "id": 1344, "seek": 323920, "start": 3286.34, "end": 3290.12, "text": " so that it knows what belongs to spam,", "tokens": [ 51114, 370, 300, 309, 3255, 437, 12953, 281, 24028, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.1933803827531876, "compression_ratio": 1.7173913043478262, "no_speech_prob": 0.005218505859375, "words": [ { "start": 3286.34, "end": 3286.84, "word": " so", "probability": 0.61669921875 }, { "start": 3286.84, "end": 3286.98, "word": " that", "probability": 0.88037109375 }, { "start": 3286.98, "end": 3287.16, "word": " it", "probability": 0.8994140625 }, { "start": 3287.16, "end": 3287.68, "word": " knows", "probability": 0.72705078125 }, { "start": 3287.68, "end": 3288.98, "word": " what", "probability": 0.86962890625 }, { "start": 3288.98, "end": 3289.46, "word": " belongs", "probability": 0.662109375 }, { "start": 3289.46, "end": 3289.7, "word": " to", "probability": 0.88134765625 }, { "start": 3289.7, "end": 3289.98, "word": " spam", "probability": 0.765625 }, { "start": 3289.98, "end": 3290.12, "word": ",", "probability": 0.90283203125 } ] }, { "id": 1345, "seek": 323920, "start": 3290.12, "end": 3293.98, "text": " what belongs to ham, just kind of in our pen and paper example,", "tokens": [ 51264, 437, 12953, 281, 7852, 11, 445, 733, 295, 294, 527, 3435, 293, 3035, 1365, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.1933803827531876, "compression_ratio": 1.7173913043478262, "no_speech_prob": 0.005218505859375, "words": [ { "start": 3290.12, "end": 3290.28, "word": " what", "probability": 0.88330078125 }, { "start": 3290.28, "end": 3290.6, "word": " belongs", "probability": 0.68115234375 }, { "start": 3290.6, "end": 3290.8, "word": " to", "probability": 0.9033203125 }, { "start": 3290.8, "end": 3291.16, "word": " ham", "probability": 0.77197265625 }, { "start": 3291.16, "end": 3291.36, "word": ",", "probability": 0.70361328125 }, { "start": 3291.36, "end": 3291.46, "word": " just", "probability": 0.72607421875 }, { "start": 3291.46, "end": 3291.72, "word": " kind", "probability": 0.78076171875 }, { "start": 3291.72, "end": 3291.92, "word": " of", "probability": 0.90966796875 }, { "start": 3291.92, "end": 3292.12, "word": " in", "probability": 0.833984375 }, { "start": 3292.12, "end": 3292.38, "word": " our", "probability": 0.80908203125 }, { "start": 3292.38, "end": 3292.94, "word": " pen", "probability": 0.90625 }, { "start": 3292.94, "end": 3293.04, "word": " and", "probability": 0.87158203125 }, { "start": 3293.04, "end": 3293.26, "word": " paper", "probability": 0.80126953125 }, { "start": 3293.26, "end": 3293.72, "word": " example", "probability": 0.92236328125 }, { "start": 3293.72, "end": 3293.98, "word": ",", "probability": 0.75537109375 } ] }, { "id": 1346, "seek": 323920, "start": 3293.98, "end": 3296.56, "text": " what belonged to sports and what belonged to not sports.", "tokens": [ 51464, 437, 28611, 281, 6573, 293, 437, 28611, 281, 406, 6573, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.1933803827531876, "compression_ratio": 1.7173913043478262, "no_speech_prob": 0.005218505859375, "words": [ { "start": 3293.98, "end": 3294.1, "word": " what", "probability": 0.87548828125 }, { "start": 3294.1, "end": 3294.38, "word": " belonged", "probability": 0.4296875 }, { "start": 3294.38, "end": 3294.56, "word": " to", "probability": 0.90673828125 }, { "start": 3294.56, "end": 3294.84, "word": " sports", "probability": 0.78515625 }, { "start": 3294.84, "end": 3295.0, "word": " and", "probability": 0.85205078125 }, { "start": 3295.0, "end": 3295.14, "word": " what", "probability": 0.8798828125 }, { "start": 3295.14, "end": 3295.38, "word": " belonged", "probability": 0.607421875 }, { "start": 3295.38, "end": 3295.54, "word": " to", "probability": 0.89990234375 }, { "start": 3295.54, "end": 3295.72, "word": " not", "probability": 0.80029296875 }, { "start": 3295.72, "end": 3296.02, "word": " sports", "probability": 0.771484375 }, { "start": 3296.02, "end": 3296.56, "word": ".", "probability": 0.939453125 } ] }, { "id": 1347, "seek": 323920, "start": 3297.02, "end": 3298.94, "text": " So now I can run that.", "tokens": [ 51614, 407, 586, 286, 393, 1190, 300, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.1933803827531876, "compression_ratio": 1.7173913043478262, "no_speech_prob": 0.005218505859375, "words": [ { "start": 3297.02, "end": 3297.38, "word": " So", "probability": 0.89111328125 }, { "start": 3297.38, "end": 3297.68, "word": " now", "probability": 0.8447265625 }, { "start": 3297.68, "end": 3297.76, "word": " I", "probability": 0.97607421875 }, { "start": 3297.76, "end": 3297.9, "word": " can", "probability": 0.8955078125 }, { "start": 3297.9, "end": 3298.08, "word": " run", "probability": 0.90966796875 }, { "start": 3298.08, "end": 3298.4, "word": " that", "probability": 0.8896484375 }, { "start": 3298.4, "end": 3298.94, "word": ".", "probability": 0.5029296875 } ] }, { "id": 1348, "seek": 326510, "start": 3300.46, "end": 3304.36, "text": " And I see where we ran into that problem yesterday.", "tokens": [ 50414, 400, 286, 536, 689, 321, 5872, 666, 300, 1154, 5186, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.20211693612478113, "compression_ratio": 1.649214659685864, "no_speech_prob": 0.0005974769592285156, "words": [ { "start": 3300.46, "end": 3300.96, "word": " And", "probability": 0.410888671875 }, { "start": 3300.96, "end": 3301.46, "word": " I", "probability": 0.9208984375 }, { "start": 3301.46, "end": 3301.78, "word": " see", "probability": 0.8134765625 }, { "start": 3301.78, "end": 3301.96, "word": " where", "probability": 0.91357421875 }, { "start": 3301.96, "end": 3302.08, "word": " we", "probability": 0.90625 }, { "start": 3302.08, "end": 3302.26, "word": " ran", "probability": 0.86962890625 }, { "start": 3302.26, "end": 3302.44, "word": " into", "probability": 0.7294921875 }, { "start": 3302.44, "end": 3302.62, "word": " that", "probability": 0.8828125 }, { "start": 3302.62, "end": 3303.04, "word": " problem", "probability": 0.75244140625 }, { "start": 3303.04, "end": 3303.86, "word": " yesterday", "probability": 0.74560546875 }, { "start": 3303.86, "end": 3304.36, "word": ".", "probability": 0.86767578125 } ] }, { "id": 1349, "seek": 326510, "start": 3304.58, "end": 3305.26, "text": " Okay.", "tokens": [ 50614, 1033, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.20211693612478113, "compression_ratio": 1.649214659685864, "no_speech_prob": 0.0005974769592285156, "words": [ { "start": 3304.58, "end": 3304.76, "word": " Okay", "probability": 0.6484375 }, { "start": 3304.76, "end": 3305.26, "word": ".", "probability": 0.5908203125 } ] }, { "id": 1350, "seek": 326510, "start": 3306.6, "end": 3308.74, "text": " I need to swap.", "tokens": [ 50714, 286, 643, 281, 18135, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.20211693612478113, "compression_ratio": 1.649214659685864, "no_speech_prob": 0.0005974769592285156, "words": [ { "start": 3306.6, "end": 3306.9, "word": " I", "probability": 0.994140625 }, { "start": 3306.9, "end": 3307.2, "word": " need", "probability": 0.80322265625 }, { "start": 3307.2, "end": 3307.6, "word": " to", "probability": 0.90673828125 }, { "start": 3307.6, "end": 3308.5, "word": " swap", "probability": 0.9130859375 }, { "start": 3308.5, "end": 3308.74, "word": ".", "probability": 0.301513671875 } ] }, { "id": 1351, "seek": 326510, "start": 3308.74, "end": 3311.8, "text": " This is the problem that I had with scikit-learn earlier.", "tokens": [ 50864, 639, 307, 264, 1154, 300, 286, 632, 365, 2180, 22681, 12, 306, 1083, 3071, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.20211693612478113, "compression_ratio": 1.649214659685864, "no_speech_prob": 0.0005974769592285156, "words": [ { "start": 3308.74, "end": 3309.0, "word": " This", "probability": 0.79931640625 }, { "start": 3309.0, "end": 3309.12, "word": " is", "probability": 0.89990234375 }, { "start": 3309.12, "end": 3309.32, "word": " the", "probability": 0.81689453125 }, { "start": 3309.32, "end": 3309.72, "word": " problem", "probability": 0.77880859375 }, { "start": 3309.72, "end": 3309.88, "word": " that", "probability": 0.8671875 }, { "start": 3309.88, "end": 3309.96, "word": " I", "probability": 0.99853515625 }, { "start": 3309.96, "end": 3310.18, "word": " had", "probability": 0.80908203125 }, { "start": 3310.18, "end": 3310.34, "word": " with", "probability": 0.80859375 }, { "start": 3310.34, "end": 3310.62, "word": " scikit", "probability": 0.797607421875 }, { "start": 3310.62, "end": 3310.78, "word": "-learn", "probability": 0.9407552083333334 }, { "start": 3310.78, "end": 3311.3, "word": " earlier", "probability": 0.89599609375 }, { "start": 3311.3, "end": 3311.8, "word": ".", "probability": 0.658203125 } ] }, { "id": 1352, "seek": 326510, "start": 3313.14, "end": 3315.56, "text": " The test labels and the predictions.", "tokens": [ 51014, 440, 1500, 16949, 293, 264, 21264, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.20211693612478113, "compression_ratio": 1.649214659685864, "no_speech_prob": 0.0005974769592285156, "words": [ { "start": 3313.14, "end": 3313.64, "word": " The", "probability": 0.8037109375 }, { "start": 3313.64, "end": 3314.12, "word": " test", "probability": 0.798828125 }, { "start": 3314.12, "end": 3314.52, "word": " labels", "probability": 0.869140625 }, { "start": 3314.52, "end": 3314.8, "word": " and", "probability": 0.87548828125 }, { "start": 3314.8, "end": 3314.94, "word": " the", "probability": 0.79296875 }, { "start": 3314.94, "end": 3315.34, "word": " predictions", "probability": 0.744140625 }, { "start": 3315.34, "end": 3315.56, "word": ".", "probability": 0.791015625 } ] }, { "id": 1353, "seek": 326510, "start": 3315.56, "end": 3318.72, "text": " We start with the predictions and then we follow up with the test labels", "tokens": [ 51164, 492, 722, 365, 264, 21264, 293, 550, 321, 1524, 493, 365, 264, 1500, 16949, 51314 ], "temperature": 0.0, "avg_logprob": -0.20211693612478113, "compression_ratio": 1.649214659685864, "no_speech_prob": 0.0005974769592285156, "words": [ { "start": 3315.56, "end": 3315.62, "word": " We", "probability": 0.8642578125 }, { "start": 3315.62, "end": 3315.92, "word": " start", "probability": 0.8662109375 }, { "start": 3315.92, "end": 3316.06, "word": " with", "probability": 0.8056640625 }, { "start": 3316.06, "end": 3316.18, "word": " the", "probability": 0.81103515625 }, { "start": 3316.18, "end": 3316.5, "word": " predictions", "probability": 0.7353515625 }, { "start": 3316.5, "end": 3316.9, "word": " and", "probability": 0.5986328125 }, { "start": 3316.9, "end": 3317.02, "word": " then", "probability": 0.71484375 }, { "start": 3317.02, "end": 3317.2, "word": " we", "probability": 0.890625 }, { "start": 3317.2, "end": 3317.5, "word": " follow", "probability": 0.8525390625 }, { "start": 3317.5, "end": 3317.72, "word": " up", "probability": 0.87939453125 }, { "start": 3317.72, "end": 3317.86, "word": " with", "probability": 0.802734375 }, { "start": 3317.86, "end": 3317.98, "word": " the", "probability": 0.81494140625 }, { "start": 3317.98, "end": 3318.26, "word": " test", "probability": 0.80810546875 }, { "start": 3318.26, "end": 3318.72, "word": " labels", "probability": 0.85205078125 } ] }, { "id": 1354, "seek": 326510, "start": 3318.72, "end": 3320.5, "text": " instead of the other way around.", "tokens": [ 51314, 2602, 295, 264, 661, 636, 926, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.20211693612478113, "compression_ratio": 1.649214659685864, "no_speech_prob": 0.0005974769592285156, "words": [ { "start": 3318.72, "end": 3319.08, "word": " instead", "probability": 0.78662109375 }, { "start": 3319.08, "end": 3319.28, "word": " of", "probability": 0.90673828125 }, { "start": 3319.28, "end": 3319.38, "word": " the", "probability": 0.8134765625 }, { "start": 3319.38, "end": 3319.5, "word": " other", "probability": 0.78125 }, { "start": 3319.5, "end": 3319.66, "word": " way", "probability": 0.89404296875 }, { "start": 3319.66, "end": 3320.0, "word": " around", "probability": 0.880859375 }, { "start": 3320.0, "end": 3320.5, "word": ".", "probability": 0.99072265625 } ] }, { "id": 1355, "seek": 326510, "start": 3321.24, "end": 3323.1, "text": " So I go ahead and run that.", "tokens": [ 51464, 407, 286, 352, 2286, 293, 1190, 300, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.20211693612478113, "compression_ratio": 1.649214659685864, "no_speech_prob": 0.0005974769592285156, "words": [ { "start": 3321.24, "end": 3321.68, "word": " So", "probability": 0.857421875 }, { "start": 3321.68, "end": 3321.76, "word": " I", "probability": 0.830078125 }, { "start": 3321.76, "end": 3321.88, "word": " go", "probability": 0.8544921875 }, { "start": 3321.88, "end": 3322.04, "word": " ahead", "probability": 0.85791015625 }, { "start": 3322.04, "end": 3322.18, "word": " and", "probability": 0.89697265625 }, { "start": 3322.18, "end": 3322.34, "word": " run", "probability": 0.8974609375 }, { "start": 3322.34, "end": 3322.6, "word": " that", "probability": 0.88134765625 }, { "start": 3322.6, "end": 3323.1, "word": ".", "probability": 0.9501953125 } ] }, { "id": 1356, "seek": 326510, "start": 3323.8, "end": 3324.84, "text": " There we go.", "tokens": [ 51614, 821, 321, 352, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.20211693612478113, "compression_ratio": 1.649214659685864, "no_speech_prob": 0.0005974769592285156, "words": [ { "start": 3323.8, "end": 3324.26, "word": " There", "probability": 0.7861328125 }, { "start": 3324.26, "end": 3324.34, "word": " we", "probability": 0.9013671875 }, { "start": 3324.34, "end": 3324.56, "word": " go", "probability": 0.89599609375 }, { "start": 3324.56, "end": 3324.84, "word": ".", "probability": 0.96923828125 } ] }, { "id": 1357, "seek": 329176, "start": 3324.84, "end": 3329.2, "text": " So we know that we had 590 ham emails.", "tokens": [ 50364, 407, 321, 458, 300, 321, 632, 1025, 7771, 7852, 12524, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.16369743269180584, "compression_ratio": 1.7361111111111112, "no_speech_prob": 0.0191192626953125, "words": [ { "start": 3324.84, "end": 3325.06, "word": " So", "probability": 0.76025390625 }, { "start": 3325.06, "end": 3325.32, "word": " we", "probability": 0.76953125 }, { "start": 3325.32, "end": 3325.56, "word": " know", "probability": 0.81494140625 }, { "start": 3325.56, "end": 3325.7, "word": " that", "probability": 0.8701171875 }, { "start": 3325.7, "end": 3325.82, "word": " we", "probability": 0.89794921875 }, { "start": 3325.82, "end": 3326.3, "word": " had", "probability": 0.80615234375 }, { "start": 3326.3, "end": 3327.78, "word": " 590", "probability": 0.90869140625 }, { "start": 3327.78, "end": 3328.28, "word": " ham", "probability": 0.60546875 }, { "start": 3328.28, "end": 3328.8, "word": " emails", "probability": 0.76806640625 }, { "start": 3328.8, "end": 3329.2, "word": ".", "probability": 0.77294921875 } ] }, { "id": 1358, "seek": 329176, "start": 3329.2, "end": 3332.66, "text": " We know that we had, if we add these two numbers together,", "tokens": [ 50564, 492, 458, 300, 321, 632, 11, 498, 321, 909, 613, 732, 3547, 1214, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.16369743269180584, "compression_ratio": 1.7361111111111112, "no_speech_prob": 0.0191192626953125, "words": [ { "start": 3329.2, "end": 3329.48, "word": " We", "probability": 0.876953125 }, { "start": 3329.48, "end": 3329.62, "word": " know", "probability": 0.81787109375 }, { "start": 3329.62, "end": 3329.74, "word": " that", "probability": 0.8759765625 }, { "start": 3329.74, "end": 3329.88, "word": " we", "probability": 0.84033203125 }, { "start": 3329.88, "end": 3330.28, "word": " had", "probability": 0.81201171875 }, { "start": 3330.28, "end": 3330.58, "word": ",", "probability": 0.60107421875 }, { "start": 3330.58, "end": 3330.84, "word": " if", "probability": 0.8798828125 }, { "start": 3330.84, "end": 3330.94, "word": " we", "probability": 0.90087890625 }, { "start": 3330.94, "end": 3331.08, "word": " add", "probability": 0.79150390625 }, { "start": 3331.08, "end": 3331.28, "word": " these", "probability": 0.69580078125 }, { "start": 3331.28, "end": 3331.44, "word": " two", "probability": 0.79150390625 }, { "start": 3331.44, "end": 3331.68, "word": " numbers", "probability": 0.876953125 }, { "start": 3331.68, "end": 3332.14, "word": " together", "probability": 0.77978515625 }, { "start": 3332.14, "end": 3332.66, "word": ",", "probability": 0.923828125 } ] }, { "id": 1359, "seek": 329176, "start": 3333.44, "end": 3334.92, "text": " 276 spam emails.", "tokens": [ 50714, 7634, 21, 24028, 12524, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.16369743269180584, "compression_ratio": 1.7361111111111112, "no_speech_prob": 0.0191192626953125, "words": [ { "start": 3333.44, "end": 3333.9, "word": " 276", "probability": 0.905517578125 }, { "start": 3333.9, "end": 3334.32, "word": " spam", "probability": 0.92333984375 }, { "start": 3334.32, "end": 3334.8, "word": " emails", "probability": 0.77587890625 }, { "start": 3334.8, "end": 3334.92, "word": ".", "probability": 0.81201171875 } ] }, { "id": 1360, "seek": 329176, "start": 3334.92, "end": 3338.2, "text": " So we can see the actual number of ham emails, the actual number of spam emails", "tokens": [ 50864, 407, 321, 393, 536, 264, 3539, 1230, 295, 7852, 12524, 11, 264, 3539, 1230, 295, 24028, 12524, 51014 ], "temperature": 0.0, "avg_logprob": -0.16369743269180584, "compression_ratio": 1.7361111111111112, "no_speech_prob": 0.0191192626953125, "words": [ { "start": 3334.92, "end": 3335.02, "word": " So", "probability": 0.71826171875 }, { "start": 3335.02, "end": 3335.1, "word": " we", "probability": 0.8876953125 }, { "start": 3335.1, "end": 3335.2, "word": " can", "probability": 0.8935546875 }, { "start": 3335.2, "end": 3335.36, "word": " see", "probability": 0.80810546875 }, { "start": 3335.36, "end": 3335.52, "word": " the", "probability": 0.81884765625 }, { "start": 3335.52, "end": 3335.82, "word": " actual", "probability": 0.798828125 }, { "start": 3335.82, "end": 3336.08, "word": " number", "probability": 0.88232421875 }, { "start": 3336.08, "end": 3336.22, "word": " of", "probability": 0.908203125 }, { "start": 3336.22, "end": 3336.4, "word": " ham", "probability": 0.75439453125 }, { "start": 3336.4, "end": 3336.68, "word": " emails", "probability": 0.76708984375 }, { "start": 3336.68, "end": 3336.8, "word": ",", "probability": 0.943359375 }, { "start": 3336.8, "end": 3336.9, "word": " the", "probability": 0.81640625 }, { "start": 3336.9, "end": 3337.16, "word": " actual", "probability": 0.78173828125 }, { "start": 3337.16, "end": 3337.38, "word": " number", "probability": 0.87646484375 }, { "start": 3337.38, "end": 3337.52, "word": " of", "probability": 0.8974609375 }, { "start": 3337.52, "end": 3337.74, "word": " spam", "probability": 0.89404296875 }, { "start": 3337.74, "end": 3338.2, "word": " emails", "probability": 0.78173828125 } ] }, { "id": 1361, "seek": 329176, "start": 3338.2, "end": 3339.96, "text": " in those columns.", "tokens": [ 51014, 294, 729, 13766, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.16369743269180584, "compression_ratio": 1.7361111111111112, "no_speech_prob": 0.0191192626953125, "words": [ { "start": 3338.2, "end": 3338.92, "word": " in", "probability": 0.82470703125 }, { "start": 3338.92, "end": 3339.12, "word": " those", "probability": 0.84814453125 }, { "start": 3339.12, "end": 3339.5, "word": " columns", "probability": 0.89208984375 }, { "start": 3339.5, "end": 3339.96, "word": ".", "probability": 0.9228515625 } ] }, { "id": 1362, "seek": 329176, "start": 3340.8, "end": 3342.64, "text": " But let me scroll up real quick.", "tokens": [ 51164, 583, 718, 385, 11369, 493, 957, 1702, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.16369743269180584, "compression_ratio": 1.7361111111111112, "no_speech_prob": 0.0191192626953125, "words": [ { "start": 3340.8, "end": 3341.16, "word": " But", "probability": 0.87841796875 }, { "start": 3341.16, "end": 3341.32, "word": " let", "probability": 0.86572265625 }, { "start": 3341.32, "end": 3341.42, "word": " me", "probability": 0.89892578125 }, { "start": 3341.42, "end": 3341.62, "word": " scroll", "probability": 0.89892578125 }, { "start": 3341.62, "end": 3341.8, "word": " up", "probability": 0.90869140625 }, { "start": 3341.8, "end": 3341.96, "word": " real", "probability": 0.85888671875 }, { "start": 3341.96, "end": 3342.18, "word": " quick", "probability": 0.927734375 }, { "start": 3342.18, "end": 3342.64, "word": ".", "probability": 0.98583984375 } ] }, { "id": 1363, "seek": 329176, "start": 3342.76, "end": 3345.66, "text": " So this is our classification report.", "tokens": [ 51264, 407, 341, 307, 527, 21538, 2275, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.16369743269180584, "compression_ratio": 1.7361111111111112, "no_speech_prob": 0.0191192626953125, "words": [ { "start": 3342.76, "end": 3343.0, "word": " So", "probability": 0.89013671875 }, { "start": 3343.0, "end": 3343.28, "word": " this", "probability": 0.85791015625 }, { "start": 3343.28, "end": 3343.48, "word": " is", "probability": 0.90673828125 }, { "start": 3343.48, "end": 3344.14, "word": " our", "probability": 0.82177734375 }, { "start": 3344.14, "end": 3345.02, "word": " classification", "probability": 0.9072265625 }, { "start": 3345.02, "end": 3345.52, "word": " report", "probability": 0.86572265625 }, { "start": 3345.52, "end": 3345.66, "word": ".", "probability": 0.7802734375 } ] }, { "id": 1364, "seek": 329176, "start": 3345.7, "end": 3349.24, "text": " Classification report we're not really going to use in this example,", "tokens": [ 51414, 9471, 3774, 2275, 321, 434, 406, 534, 516, 281, 764, 294, 341, 1365, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.16369743269180584, "compression_ratio": 1.7361111111111112, "no_speech_prob": 0.0191192626953125, "words": [ { "start": 3345.7, "end": 3346.16, "word": " Classification", "probability": 0.9169921875 }, { "start": 3346.16, "end": 3346.52, "word": " report", "probability": 0.8408203125 }, { "start": 3346.52, "end": 3346.7, "word": " we're", "probability": 0.711181640625 }, { "start": 3346.7, "end": 3346.86, "word": " not", "probability": 0.8935546875 }, { "start": 3346.86, "end": 3347.08, "word": " really", "probability": 0.76708984375 }, { "start": 3347.08, "end": 3347.28, "word": " going", "probability": 0.8603515625 }, { "start": 3347.28, "end": 3347.5, "word": " to", "probability": 0.90673828125 }, { "start": 3347.5, "end": 3347.82, "word": " use", "probability": 0.822265625 }, { "start": 3347.82, "end": 3348.0, "word": " in", "probability": 0.90478515625 }, { "start": 3348.0, "end": 3348.16, "word": " this", "probability": 0.87939453125 }, { "start": 3348.16, "end": 3348.54, "word": " example", "probability": 0.92529296875 }, { "start": 3348.54, "end": 3349.24, "word": ",", "probability": 0.66845703125 } ] }, { "id": 1365, "seek": 329176, "start": 3349.24, "end": 3351.5, "text": " but it's good to know.", "tokens": [ 51564, 457, 309, 311, 665, 281, 458, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.16369743269180584, "compression_ratio": 1.7361111111111112, "no_speech_prob": 0.0191192626953125, "words": [ { "start": 3349.24, "end": 3349.9, "word": " but", "probability": 0.8876953125 }, { "start": 3349.9, "end": 3350.28, "word": " it's", "probability": 0.954345703125 }, { "start": 3350.28, "end": 3350.5, "word": " good", "probability": 0.88232421875 }, { "start": 3350.5, "end": 3350.7, "word": " to", "probability": 0.9013671875 }, { "start": 3350.7, "end": 3351.12, "word": " know", "probability": 0.81640625 }, { "start": 3351.12, "end": 3351.5, "word": ".", "probability": 0.75244140625 } ] }, { "id": 1366, "seek": 332012, "start": 3351.5, "end": 3354.98, "text": " There are other ways to measure how good a model is performing,", "tokens": [ 50364, 821, 366, 661, 2098, 281, 3481, 577, 665, 257, 2316, 307, 10205, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.20445165628532194, "compression_ratio": 1.4849785407725322, "no_speech_prob": 0.0233306884765625, "words": [ { "start": 3351.5, "end": 3351.74, "word": " There", "probability": 0.49658203125 }, { "start": 3351.74, "end": 3351.84, "word": " are", "probability": 0.89306640625 }, { "start": 3351.84, "end": 3352.02, "word": " other", "probability": 0.75732421875 }, { "start": 3352.02, "end": 3352.3, "word": " ways", "probability": 0.794921875 }, { "start": 3352.3, "end": 3352.5, "word": " to", "probability": 0.8984375 }, { "start": 3352.5, "end": 3352.84, "word": " measure", "probability": 0.80322265625 }, { "start": 3352.84, "end": 3353.26, "word": " how", "probability": 0.896484375 }, { "start": 3353.26, "end": 3353.5, "word": " good", "probability": 0.8623046875 }, { "start": 3353.64, "end": 3353.78, "word": " a model", "probability": 0.806640625 }, { "start": 3353.78, "end": 3353.94, "word": " is", "probability": 0.8662109375 }, { "start": 3353.94, "end": 3354.42, "word": " performing", "probability": 0.68994140625 }, { "start": 3354.42, "end": 3354.98, "word": ",", "probability": 0.428955078125 } ] }, { "id": 1367, "seek": 332012, "start": 3354.98, "end": 3356.8, "text": " beyond accuracy.", "tokens": [ 50514, 4399, 14170, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.20445165628532194, "compression_ratio": 1.4849785407725322, "no_speech_prob": 0.0233306884765625, "words": [ { "start": 3354.98, "end": 3355.4, "word": " beyond", "probability": 0.427001953125 }, { "start": 3355.4, "end": 3356.12, "word": " accuracy", "probability": 0.74072265625 }, { "start": 3356.12, "end": 3356.8, "word": ".", "probability": 0.7763671875 } ] }, { "id": 1368, "seek": 332012, "start": 3357.5, "end": 3360.4, "text": " Precision, recall, and F1 score", "tokens": [ 50664, 6001, 40832, 11, 9901, 11, 293, 479, 16, 6175, 50814 ], "temperature": 0.0, "avg_logprob": -0.20445165628532194, "compression_ratio": 1.4849785407725322, "no_speech_prob": 0.0233306884765625, "words": [ { "start": 3357.5, "end": 3358.18, "word": " Precision", "probability": 0.80859375 }, { "start": 3358.18, "end": 3358.58, "word": ",", "probability": 0.93505859375 }, { "start": 3358.58, "end": 3359.06, "word": " recall", "probability": 0.484619140625 }, { "start": 3359.06, "end": 3359.4, "word": ",", "probability": 0.76708984375 }, { "start": 3359.4, "end": 3359.58, "word": " and", "probability": 0.87353515625 }, { "start": 3359.58, "end": 3360.04, "word": " F1", "probability": 0.92431640625 }, { "start": 3360.04, "end": 3360.4, "word": " score", "probability": 0.69921875 } ] }, { "id": 1369, "seek": 332012, "start": 3360.4, "end": 3363.78, "text": " are all used in their own ways.", "tokens": [ 50814, 366, 439, 1143, 294, 641, 1065, 2098, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.20445165628532194, "compression_ratio": 1.4849785407725322, "no_speech_prob": 0.0233306884765625, "words": [ { "start": 3360.4, "end": 3360.66, "word": " are", "probability": 0.86865234375 }, { "start": 3360.66, "end": 3360.86, "word": " all", "probability": 0.75390625 }, { "start": 3360.86, "end": 3361.44, "word": " used", "probability": 0.7939453125 }, { "start": 3361.44, "end": 3362.38, "word": " in", "probability": 0.86181640625 }, { "start": 3362.38, "end": 3362.52, "word": " their", "probability": 0.89453125 }, { "start": 3362.52, "end": 3362.72, "word": " own", "probability": 0.82958984375 }, { "start": 3362.72, "end": 3363.1, "word": " ways", "probability": 0.7626953125 }, { "start": 3363.1, "end": 3363.78, "word": ".", "probability": 0.9296875 } ] }, { "id": 1370, "seek": 332012, "start": 3363.82, "end": 3367.7, "text": " I'm not going to go into that, but it's definitely worth understanding.", "tokens": [ 50964, 286, 478, 406, 516, 281, 352, 666, 300, 11, 457, 309, 311, 2138, 3163, 3701, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.20445165628532194, "compression_ratio": 1.4849785407725322, "no_speech_prob": 0.0233306884765625, "words": [ { "start": 3363.82, "end": 3363.9, "word": " I'm", "probability": 0.883544921875 }, { "start": 3363.9, "end": 3364.06, "word": " not", "probability": 0.9013671875 }, { "start": 3364.06, "end": 3364.18, "word": " going", "probability": 0.76513671875 }, { "start": 3364.18, "end": 3364.24, "word": " to", "probability": 0.8564453125 }, { "start": 3364.24, "end": 3364.34, "word": " go", "probability": 0.8798828125 }, { "start": 3364.34, "end": 3364.5, "word": " into", "probability": 0.72314453125 }, { "start": 3364.5, "end": 3364.78, "word": " that", "probability": 0.85693359375 }, { "start": 3364.78, "end": 3364.88, "word": ",", "probability": 0.70654296875 }, { "start": 3364.88, "end": 3365.02, "word": " but", "probability": 0.896484375 }, { "start": 3365.02, "end": 3365.26, "word": " it's", "probability": 0.9365234375 }, { "start": 3365.26, "end": 3365.64, "word": " definitely", "probability": 0.7548828125 }, { "start": 3365.64, "end": 3366.32, "word": " worth", "probability": 0.90185546875 }, { "start": 3366.32, "end": 3367.02, "word": " understanding", "probability": 0.69921875 }, { "start": 3367.02, "end": 3367.7, "word": ".", "probability": 0.974609375 } ] }, { "id": 1371, "seek": 332012, "start": 3368.04, "end": 3370.78, "text": " Instead, we're just going to look at the straight accuracy.", "tokens": [ 51114, 7156, 11, 321, 434, 445, 516, 281, 574, 412, 264, 2997, 14170, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.20445165628532194, "compression_ratio": 1.4849785407725322, "no_speech_prob": 0.0233306884765625, "words": [ { "start": 3368.04, "end": 3368.66, "word": " Instead", "probability": 0.89306640625 }, { "start": 3368.66, "end": 3368.74, "word": ",", "probability": 0.70849609375 }, { "start": 3368.74, "end": 3368.84, "word": " we're", "probability": 0.9072265625 }, { "start": 3368.84, "end": 3368.98, "word": " just", "probability": 0.791015625 }, { "start": 3368.98, "end": 3369.08, "word": " going", "probability": 0.82861328125 }, { "start": 3369.08, "end": 3369.14, "word": " to", "probability": 0.9013671875 }, { "start": 3369.14, "end": 3369.24, "word": " look", "probability": 0.91748046875 }, { "start": 3369.24, "end": 3369.32, "word": " at", "probability": 0.91357421875 }, { "start": 3369.32, "end": 3369.44, "word": " the", "probability": 0.77978515625 }, { "start": 3369.44, "end": 3369.7, "word": " straight", "probability": 0.73828125 }, { "start": 3369.7, "end": 3370.26, "word": " accuracy", "probability": 0.72412109375 }, { "start": 3370.26, "end": 3370.78, "word": ".", "probability": 0.90234375 } ] }, { "id": 1372, "seek": 332012, "start": 3370.78, "end": 3373.4, "text": " For this multinomial with TF-IDF,", "tokens": [ 51264, 1171, 341, 45872, 47429, 365, 40964, 12, 2777, 37, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.20445165628532194, "compression_ratio": 1.4849785407725322, "no_speech_prob": 0.0233306884765625, "words": [ { "start": 3370.78, "end": 3371.26, "word": " For", "probability": 0.6962890625 }, { "start": 3371.26, "end": 3371.42, "word": " this", "probability": 0.8720703125 }, { "start": 3371.42, "end": 3372.02, "word": " multinomial", "probability": 0.92041015625 }, { "start": 3372.02, "end": 3372.46, "word": " with", "probability": 0.7529296875 }, { "start": 3372.46, "end": 3372.8, "word": " TF", "probability": 0.76171875 }, { "start": 3372.8, "end": 3373.3, "word": "-IDF", "probability": 0.90625 }, { "start": 3373.3, "end": 3373.4, "word": ",", "probability": 0.7978515625 } ] }, { "id": 1373, "seek": 332012, "start": 3373.4, "end": 3375.94, "text": " we have a .875", "tokens": [ 51414, 321, 362, 257, 2411, 23, 11901, 51564 ], "temperature": 0.0, "avg_logprob": -0.20445165628532194, "compression_ratio": 1.4849785407725322, "no_speech_prob": 0.0233306884765625, "words": [ { "start": 3373.4, "end": 3373.54, "word": " we", "probability": 0.89892578125 }, { "start": 3373.54, "end": 3373.98, "word": " have", "probability": 0.87548828125 }, { "start": 3374.44, "end": 3375.94, "word": " a .875", "probability": 0.7454427083333334 } ] }, { "id": 1374, "seek": 332012, "start": 3375.94, "end": 3379.86, "text": " or a 87.5% accuracy.", "tokens": [ 51564, 420, 257, 27990, 13, 20, 4, 14170, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.20445165628532194, "compression_ratio": 1.4849785407725322, "no_speech_prob": 0.0233306884765625, "words": [ { "start": 3375.94, "end": 3376.92, "word": " or", "probability": 0.6064453125 }, { "start": 3377.28, "end": 3377.78, "word": " a 87", "probability": 0.9052734375 }, { "start": 3377.78, "end": 3378.6, "word": ".5", "probability": 0.996826171875 }, { "start": 3378.6, "end": 3378.86, "word": "%", "probability": 0.87939453125 }, { "start": 3378.86, "end": 3379.44, "word": " accuracy", "probability": 0.74462890625 }, { "start": 3379.44, "end": 3379.86, "word": ".", "probability": 0.9892578125 } ] }, { "id": 1375, "seek": 334998, "start": 3379.86, "end": 3383.0, "text": " If we look at our true positives and our true negatives,", "tokens": [ 50364, 759, 321, 574, 412, 527, 2074, 35127, 293, 527, 2074, 40019, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.17919481874586227, "compression_ratio": 1.8325991189427313, "no_speech_prob": 0.01016998291015625, "words": [ { "start": 3379.86, "end": 3380.84, "word": " If", "probability": 0.70654296875 }, { "start": 3380.84, "end": 3380.96, "word": " we", "probability": 0.89501953125 }, { "start": 3380.96, "end": 3381.1, "word": " look", "probability": 0.91259765625 }, { "start": 3381.1, "end": 3381.18, "word": " at", "probability": 0.90771484375 }, { "start": 3381.18, "end": 3381.3, "word": " our", "probability": 0.80126953125 }, { "start": 3381.3, "end": 3381.46, "word": " true", "probability": 0.81884765625 }, { "start": 3381.46, "end": 3381.88, "word": " positives", "probability": 0.837890625 }, { "start": 3381.88, "end": 3382.12, "word": " and", "probability": 0.87158203125 }, { "start": 3382.12, "end": 3382.26, "word": " our", "probability": 0.72216796875 }, { "start": 3382.26, "end": 3382.42, "word": " true", "probability": 0.93115234375 }, { "start": 3382.42, "end": 3382.86, "word": " negatives", "probability": 0.82666015625 }, { "start": 3382.86, "end": 3383.0, "word": ",", "probability": 0.73681640625 } ] }, { "id": 1376, "seek": 334998, "start": 3383.0, "end": 3386.5, "text": " it correctly classified or predicted all ham emails", "tokens": [ 50514, 309, 8944, 20627, 420, 19147, 439, 7852, 12524, 50664 ], "temperature": 0.0, "avg_logprob": -0.17919481874586227, "compression_ratio": 1.8325991189427313, "no_speech_prob": 0.01016998291015625, "words": [ { "start": 3383.0, "end": 3383.12, "word": " it", "probability": 0.86474609375 }, { "start": 3383.12, "end": 3383.52, "word": " correctly", "probability": 0.9140625 }, { "start": 3383.52, "end": 3384.26, "word": " classified", "probability": 0.86376953125 }, { "start": 3384.26, "end": 3384.98, "word": " or", "probability": 0.673828125 }, { "start": 3384.98, "end": 3385.36, "word": " predicted", "probability": 0.74462890625 }, { "start": 3385.36, "end": 3385.76, "word": " all", "probability": 0.87890625 }, { "start": 3385.76, "end": 3386.06, "word": " ham", "probability": 0.29736328125 }, { "start": 3386.06, "end": 3386.5, "word": " emails", "probability": 0.77783203125 } ] }, { "id": 1377, "seek": 334998, "start": 3386.5, "end": 3388.92, "text": " as being part of the ham class.", "tokens": [ 50664, 382, 885, 644, 295, 264, 7852, 1508, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.17919481874586227, "compression_ratio": 1.8325991189427313, "no_speech_prob": 0.01016998291015625, "words": [ { "start": 3386.5, "end": 3386.84, "word": " as", "probability": 0.8876953125 }, { "start": 3386.84, "end": 3387.06, "word": " being", "probability": 0.86669921875 }, { "start": 3387.06, "end": 3387.38, "word": " part", "probability": 0.80712890625 }, { "start": 3387.38, "end": 3387.48, "word": " of", "probability": 0.90673828125 }, { "start": 3387.48, "end": 3387.6, "word": " the", "probability": 0.80126953125 }, { "start": 3387.6, "end": 3387.78, "word": " ham", "probability": 0.7607421875 }, { "start": 3387.78, "end": 3388.4, "word": " class", "probability": 0.91748046875 }, { "start": 3388.4, "end": 3388.92, "word": ".", "probability": 0.76806640625 } ] }, { "id": 1378, "seek": 334998, "start": 3388.96, "end": 3392.46, "text": " So these are all of our true positives for what is ham.", "tokens": [ 50814, 407, 613, 366, 439, 295, 527, 2074, 35127, 337, 437, 307, 7852, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.17919481874586227, "compression_ratio": 1.8325991189427313, "no_speech_prob": 0.01016998291015625, "words": [ { "start": 3388.96, "end": 3389.06, "word": " So", "probability": 0.11273193359375 }, { "start": 3389.06, "end": 3389.26, "word": " these", "probability": 0.6337890625 }, { "start": 3389.26, "end": 3389.38, "word": " are", "probability": 0.8876953125 }, { "start": 3389.38, "end": 3389.54, "word": " all", "probability": 0.88037109375 }, { "start": 3389.54, "end": 3389.66, "word": " of", "probability": 0.8525390625 }, { "start": 3389.66, "end": 3390.0, "word": " our", "probability": 0.8134765625 }, { "start": 3390.0, "end": 3390.68, "word": " true", "probability": 0.9052734375 }, { "start": 3390.68, "end": 3391.12, "word": " positives", "probability": 0.7978515625 }, { "start": 3391.12, "end": 3391.38, "word": " for", "probability": 0.86865234375 }, { "start": 3391.38, "end": 3391.52, "word": " what", "probability": 0.82666015625 }, { "start": 3391.52, "end": 3391.66, "word": " is", "probability": 0.90283203125 }, { "start": 3391.66, "end": 3391.94, "word": " ham", "probability": 0.83447265625 }, { "start": 3391.94, "end": 3392.46, "word": ".", "probability": 0.65234375 } ] }, { "id": 1379, "seek": 334998, "start": 3392.54, "end": 3394.72, "text": " And then our true negatives, what is spam,", "tokens": [ 50964, 400, 550, 527, 2074, 40019, 11, 437, 307, 24028, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.17919481874586227, "compression_ratio": 1.8325991189427313, "no_speech_prob": 0.01016998291015625, "words": [ { "start": 3392.54, "end": 3392.7, "word": " And", "probability": 0.67724609375 }, { "start": 3392.7, "end": 3392.78, "word": " then", "probability": 0.5869140625 }, { "start": 3392.78, "end": 3392.88, "word": " our", "probability": 0.8056640625 }, { "start": 3392.88, "end": 3393.04, "word": " true", "probability": 0.92529296875 }, { "start": 3393.04, "end": 3393.52, "word": " negatives", "probability": 0.81689453125 }, { "start": 3393.52, "end": 3394.04, "word": ",", "probability": 0.8046875 }, { "start": 3394.04, "end": 3394.16, "word": " what", "probability": 0.86572265625 }, { "start": 3394.16, "end": 3394.32, "word": " is", "probability": 0.90185546875 }, { "start": 3394.32, "end": 3394.62, "word": " spam", "probability": 0.92529296875 }, { "start": 3394.62, "end": 3394.72, "word": ",", "probability": 0.7060546875 } ] }, { "id": 1380, "seek": 334998, "start": 3394.72, "end": 3400.28, "text": " it only classified 168 out of the 276 that we have.", "tokens": [ 51114, 309, 787, 20627, 3165, 23, 484, 295, 264, 7634, 21, 300, 321, 362, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.17919481874586227, "compression_ratio": 1.8325991189427313, "no_speech_prob": 0.01016998291015625, "words": [ { "start": 3394.72, "end": 3394.8, "word": " it", "probability": 0.888671875 }, { "start": 3394.8, "end": 3394.98, "word": " only", "probability": 0.859375 }, { "start": 3394.98, "end": 3395.58, "word": " classified", "probability": 0.91845703125 }, { "start": 3395.58, "end": 3397.12, "word": " 168", "probability": 0.873291015625 }, { "start": 3397.12, "end": 3397.7, "word": " out", "probability": 0.7841796875 }, { "start": 3397.7, "end": 3397.78, "word": " of", "probability": 0.9052734375 }, { "start": 3397.78, "end": 3397.9, "word": " the", "probability": 0.80712890625 }, { "start": 3397.9, "end": 3399.06, "word": " 276", "probability": 0.89990234375 }, { "start": 3399.06, "end": 3399.28, "word": " that", "probability": 0.87744140625 }, { "start": 3399.28, "end": 3399.42, "word": " we", "probability": 0.90673828125 }, { "start": 3399.42, "end": 3399.76, "word": " have", "probability": 0.8759765625 }, { "start": 3399.76, "end": 3400.28, "word": ".", "probability": 0.98974609375 } ] }, { "id": 1381, "seek": 334998, "start": 3400.72, "end": 3403.08, "text": " The other half of the spam emails", "tokens": [ 51364, 440, 661, 1922, 295, 264, 24028, 12524, 51514 ], "temperature": 0.0, "avg_logprob": -0.17919481874586227, "compression_ratio": 1.8325991189427313, "no_speech_prob": 0.01016998291015625, "words": [ { "start": 3400.72, "end": 3401.24, "word": " The", "probability": 0.8017578125 }, { "start": 3401.24, "end": 3401.46, "word": " other", "probability": 0.78759765625 }, { "start": 3401.46, "end": 3402.0, "word": " half", "probability": 0.82373046875 }, { "start": 3402.0, "end": 3402.24, "word": " of", "probability": 0.91162109375 }, { "start": 3402.24, "end": 3402.4, "word": " the", "probability": 0.810546875 }, { "start": 3402.4, "end": 3402.66, "word": " spam", "probability": 0.91455078125 }, { "start": 3402.66, "end": 3403.08, "word": " emails", "probability": 0.771484375 } ] }, { "id": 1382, "seek": 334998, "start": 3403.08, "end": 3406.66, "text": " it also thought were ham or regular emails.", "tokens": [ 51514, 309, 611, 1194, 645, 7852, 420, 3890, 12524, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.17919481874586227, "compression_ratio": 1.8325991189427313, "no_speech_prob": 0.01016998291015625, "words": [ { "start": 3403.08, "end": 3403.32, "word": " it", "probability": 0.611328125 }, { "start": 3403.32, "end": 3403.68, "word": " also", "probability": 0.8212890625 }, { "start": 3403.68, "end": 3404.34, "word": " thought", "probability": 0.8271484375 }, { "start": 3404.34, "end": 3404.98, "word": " were", "probability": 0.85009765625 }, { "start": 3404.98, "end": 3405.44, "word": " ham", "probability": 0.826171875 }, { "start": 3405.44, "end": 3405.6, "word": " or", "probability": 0.83544921875 }, { "start": 3405.6, "end": 3405.84, "word": " regular", "probability": 0.888671875 }, { "start": 3405.84, "end": 3406.28, "word": " emails", "probability": 0.7568359375 }, { "start": 3406.28, "end": 3406.66, "word": ".", "probability": 0.9326171875 } ] }, { "id": 1383, "seek": 334998, "start": 3406.66, "end": 3409.72, "text": " So our predictor is letting some spam through,", "tokens": [ 51664, 407, 527, 6069, 284, 307, 8295, 512, 24028, 807, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.17919481874586227, "compression_ratio": 1.8325991189427313, "no_speech_prob": 0.01016998291015625, "words": [ { "start": 3406.66, "end": 3406.86, "word": " So", "probability": 0.85791015625 }, { "start": 3406.86, "end": 3407.18, "word": " our", "probability": 0.78515625 }, { "start": 3407.18, "end": 3407.68, "word": " predictor", "probability": 0.854736328125 }, { "start": 3407.68, "end": 3407.9, "word": " is", "probability": 0.89794921875 }, { "start": 3407.9, "end": 3408.24, "word": " letting", "probability": 0.82373046875 }, { "start": 3408.24, "end": 3408.66, "word": " some", "probability": 0.8193359375 }, { "start": 3408.66, "end": 3409.04, "word": " spam", "probability": 0.91455078125 }, { "start": 3409.04, "end": 3409.52, "word": " through", "probability": 0.82080078125 }, { "start": 3409.52, "end": 3409.72, "word": ",", "probability": 0.86376953125 } ] }, { "id": 1384, "seek": 337790, "start": 3409.72, "end": 3412.88, "text": " but the good news is it's not blocking any of our", "tokens": [ 50364, 457, 264, 665, 2583, 307, 309, 311, 406, 17776, 604, 295, 527, 50514 ], "temperature": 0.0, "avg_logprob": -0.2515453427702516, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 3409.72, "end": 3409.8, "word": " but", "probability": 0.345947265625 }, { "start": 3409.8, "end": 3409.92, "word": " the", "probability": 0.81884765625 }, { "start": 3409.92, "end": 3410.04, "word": " good", "probability": 0.8681640625 }, { "start": 3410.04, "end": 3410.26, "word": " news", "probability": 0.74462890625 }, { "start": 3410.26, "end": 3410.42, "word": " is", "probability": 0.90576171875 }, { "start": 3410.42, "end": 3410.7, "word": " it's", "probability": 0.90234375 }, { "start": 3410.7, "end": 3411.04, "word": " not", "probability": 0.8984375 }, { "start": 3411.04, "end": 3411.5, "word": " blocking", "probability": 0.75732421875 }, { "start": 3411.5, "end": 3412.06, "word": " any", "probability": 0.82177734375 }, { "start": 3412.06, "end": 3412.32, "word": " of", "probability": 0.9111328125 }, { "start": 3412.32, "end": 3412.88, "word": " our", "probability": 0.81005859375 } ] }, { "id": 1385, "seek": 337790, "start": 3412.88, "end": 3414.92, "text": " legitimate emails.", "tokens": [ 50514, 17956, 12524, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.2515453427702516, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 3412.88, "end": 3413.92, "word": " legitimate", "probability": 0.75244140625 }, { "start": 3413.92, "end": 3414.4, "word": " emails", "probability": 0.7294921875 }, { "start": 3414.4, "end": 3414.92, "word": ".", "probability": 0.9921875 } ] }, { "id": 1386, "seek": 337790, "start": 3418.82, "end": 3422.66, "text": " Moving on to the next example, we're going to do the same thing.", "tokens": [ 50814, 14242, 322, 281, 264, 958, 1365, 11, 321, 434, 516, 281, 360, 264, 912, 551, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.2515453427702516, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 3418.82, "end": 3419.34, "word": " Moving", "probability": 0.0914306640625 }, { "start": 3419.34, "end": 3419.78, "word": " on", "probability": 0.84130859375 }, { "start": 3419.78, "end": 3420.02, "word": " to", "probability": 0.9052734375 }, { "start": 3420.02, "end": 3420.38, "word": " the", "probability": 0.81591796875 }, { "start": 3420.38, "end": 3420.62, "word": " next", "probability": 0.86669921875 }, { "start": 3420.62, "end": 3421.04, "word": " example", "probability": 0.9326171875 }, { "start": 3421.04, "end": 3421.2, "word": ",", "probability": 0.85986328125 }, { "start": 3421.2, "end": 3421.34, "word": " we're", "probability": 0.92822265625 }, { "start": 3421.34, "end": 3421.42, "word": " going", "probability": 0.306396484375 }, { "start": 3421.42, "end": 3421.48, "word": " to", "probability": 0.90234375 }, { "start": 3421.48, "end": 3421.58, "word": " do", "probability": 0.89697265625 }, { "start": 3421.58, "end": 3421.74, "word": " the", "probability": 0.80908203125 }, { "start": 3421.74, "end": 3422.02, "word": " same", "probability": 0.8134765625 }, { "start": 3422.02, "end": 3422.5, "word": " thing", "probability": 0.8134765625 }, { "start": 3422.5, "end": 3422.66, "word": ".", "probability": 0.90380859375 } ] }, { "id": 1387, "seek": 337790, "start": 3422.66, "end": 3423.98, "text": " We're going to use multinomial naivete", "tokens": [ 50964, 492, 434, 516, 281, 764, 45872, 47429, 1667, 592, 3498, 51114 ], "temperature": 0.0, "avg_logprob": -0.2515453427702516, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 3422.66, "end": 3422.78, "word": " We're", "probability": 0.928466796875 }, { "start": 3422.78, "end": 3422.86, "word": " going", "probability": 0.83984375 }, { "start": 3422.86, "end": 3422.9, "word": " to", "probability": 0.9072265625 }, { "start": 3422.9, "end": 3423.06, "word": " use", "probability": 0.8544921875 }, { "start": 3423.06, "end": 3423.64, "word": " multinomial", "probability": 0.86279296875 }, { "start": 3423.64, "end": 3423.98, "word": " naivete", "probability": 0.5189615885416666 } ] }, { "id": 1388, "seek": 337790, "start": 3424.54, "end": 3427.7, "text": " with count vectorizer.", "tokens": [ 51114, 365, 1207, 8062, 6545, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.2515453427702516, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 3424.54, "end": 3424.8, "word": " with", "probability": 0.54150390625 }, { "start": 3424.8, "end": 3426.54, "word": " count", "probability": 0.422119140625 }, { "start": 3426.54, "end": 3427.18, "word": " vectorizer", "probability": 0.900146484375 }, { "start": 3427.18, "end": 3427.7, "word": ".", "probability": 0.92333984375 } ] }, { "id": 1389, "seek": 337790, "start": 3427.7, "end": 3431.02, "text": " This is going to be the same, and then be count.", "tokens": [ 51264, 639, 307, 516, 281, 312, 264, 912, 11, 293, 550, 312, 1207, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.2515453427702516, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 3427.7, "end": 3428.08, "word": " This", "probability": 0.595703125 }, { "start": 3428.08, "end": 3428.22, "word": " is", "probability": 0.9072265625 }, { "start": 3428.22, "end": 3428.32, "word": " going", "probability": 0.8544921875 }, { "start": 3428.32, "end": 3428.34, "word": " to", "probability": 0.90234375 }, { "start": 3428.34, "end": 3428.44, "word": " be", "probability": 0.8974609375 }, { "start": 3428.44, "end": 3428.58, "word": " the", "probability": 0.80859375 }, { "start": 3428.58, "end": 3428.92, "word": " same", "probability": 0.81494140625 }, { "start": 3428.92, "end": 3429.34, "word": ",", "probability": 0.428955078125 }, { "start": 3429.34, "end": 3429.42, "word": " and", "probability": 0.76318359375 }, { "start": 3429.42, "end": 3429.54, "word": " then", "probability": 0.53857421875 }, { "start": 3429.54, "end": 3429.8, "word": " be", "probability": 0.5654296875 }, { "start": 3429.8, "end": 3430.5, "word": " count", "probability": 0.5546875 }, { "start": 3430.5, "end": 3431.02, "word": ".", "probability": 0.654296875 } ] }, { "id": 1390, "seek": 337790, "start": 3433.02, "end": 3435.66, "text": " I am actually a little lazy,", "tokens": [ 51414, 286, 669, 767, 257, 707, 14847, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.2515453427702516, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 3433.02, "end": 3433.54, "word": " I", "probability": 0.796875 }, { "start": 3433.54, "end": 3433.82, "word": " am", "probability": 0.80078125 }, { "start": 3433.82, "end": 3434.4, "word": " actually", "probability": 0.75244140625 }, { "start": 3434.7, "end": 3434.92, "word": " a little", "probability": 0.80029296875 }, { "start": 3434.92, "end": 3435.3, "word": " lazy", "probability": 0.73779296875 }, { "start": 3435.3, "end": 3435.66, "word": ",", "probability": 0.6103515625 } ] }, { "id": 1391, "seek": 337790, "start": 3435.66, "end": 3437.64, "text": " so what I'm going to do", "tokens": [ 51564, 370, 437, 286, 478, 516, 281, 360, 51714 ], "temperature": 0.0, "avg_logprob": -0.2515453427702516, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 3435.66, "end": 3435.92, "word": " so", "probability": 0.88037109375 }, { "start": 3435.92, "end": 3437.14, "word": " what", "probability": 0.859375 }, { "start": 3437.14, "end": 3437.26, "word": " I'm", "probability": 0.99462890625 }, { "start": 3437.26, "end": 3437.34, "word": " going", "probability": 0.85546875 }, { "start": 3437.34, "end": 3437.4, "word": " to", "probability": 0.90625 }, { "start": 3437.4, "end": 3437.64, "word": " do", "probability": 0.90869140625 } ] }, { "id": 1392, "seek": 340554, "start": 3437.64, "end": 3440.64, "text": " is just copy this", "tokens": [ 50364, 307, 445, 5055, 341, 50514 ], "temperature": 0.0, "avg_logprob": -0.22149884852546234, "compression_ratio": 1.7222222222222223, "no_speech_prob": 0.005817413330078125, "words": [ { "start": 3437.64, "end": 3437.9, "word": " is", "probability": 0.7685546875 }, { "start": 3437.9, "end": 3438.24, "word": " just", "probability": 0.8623046875 }, { "start": 3438.24, "end": 3439.16, "word": " copy", "probability": 0.8203125 }, { "start": 3439.16, "end": 3440.64, "word": " this", "probability": 0.86279296875 } ] }, { "id": 1393, "seek": 340554, "start": 3440.64, "end": 3442.46, "text": " and I can show you all you need to do", "tokens": [ 50514, 293, 286, 393, 855, 291, 439, 291, 643, 281, 360, 50664 ], "temperature": 0.0, "avg_logprob": -0.22149884852546234, "compression_ratio": 1.7222222222222223, "no_speech_prob": 0.005817413330078125, "words": [ { "start": 3440.64, "end": 3441.08, "word": " and", "probability": 0.47705078125 }, { "start": 3441.08, "end": 3441.2, "word": " I", "probability": 0.80078125 }, { "start": 3441.2, "end": 3441.34, "word": " can", "probability": 0.8896484375 }, { "start": 3441.34, "end": 3441.54, "word": " show", "probability": 0.88623046875 }, { "start": 3441.54, "end": 3441.68, "word": " you", "probability": 0.89892578125 }, { "start": 3441.68, "end": 3441.88, "word": " all", "probability": 0.75341796875 }, { "start": 3441.88, "end": 3442.0, "word": " you", "probability": 0.89794921875 }, { "start": 3442.0, "end": 3442.14, "word": " need", "probability": 0.81103515625 }, { "start": 3442.14, "end": 3442.26, "word": " to", "probability": 0.90576171875 }, { "start": 3442.26, "end": 3442.46, "word": " do", "probability": 0.90966796875 } ] }, { "id": 1394, "seek": 340554, "start": 3442.46, "end": 3447.02, "text": " is just change a few things around and you have a working model.", "tokens": [ 50664, 307, 445, 1319, 257, 1326, 721, 926, 293, 291, 362, 257, 1364, 2316, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.22149884852546234, "compression_ratio": 1.7222222222222223, "no_speech_prob": 0.005817413330078125, "words": [ { "start": 3442.46, "end": 3442.7, "word": " is", "probability": 0.89892578125 }, { "start": 3442.7, "end": 3442.96, "word": " just", "probability": 0.861328125 }, { "start": 3442.96, "end": 3443.38, "word": " change", "probability": 0.83837890625 }, { "start": 3443.62, "end": 3443.8, "word": " a few", "probability": 0.814453125 }, { "start": 3443.8, "end": 3444.1, "word": " things", "probability": 0.7421875 }, { "start": 3444.1, "end": 3444.44, "word": " around", "probability": 0.87158203125 }, { "start": 3444.44, "end": 3444.96, "word": " and", "probability": 0.8251953125 }, { "start": 3444.96, "end": 3445.68, "word": " you", "probability": 0.892578125 }, { "start": 3445.68, "end": 3445.9, "word": " have", "probability": 0.8828125 }, { "start": 3446.12, "end": 3446.4, "word": " a working", "probability": 0.73583984375 }, { "start": 3446.4, "end": 3446.72, "word": " model", "probability": 0.8251953125 }, { "start": 3446.72, "end": 3447.02, "word": ".", "probability": 0.8330078125 } ] }, { "id": 1395, "seek": 340554, "start": 3447.02, "end": 3449.06, "text": " So instead of multinomial tfidf,", "tokens": [ 50814, 407, 2602, 295, 45872, 47429, 256, 69, 327, 69, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.22149884852546234, "compression_ratio": 1.7222222222222223, "no_speech_prob": 0.005817413330078125, "words": [ { "start": 3447.02, "end": 3447.04, "word": " So", "probability": 0.74560546875 }, { "start": 3447.04, "end": 3447.3, "word": " instead", "probability": 0.7900390625 }, { "start": 3447.3, "end": 3447.62, "word": " of", "probability": 0.90673828125 }, { "start": 3447.62, "end": 3448.18, "word": " multinomial", "probability": 0.901611328125 }, { "start": 3448.18, "end": 3449.02, "word": " tfidf", "probability": 0.7293701171875 }, { "start": 3449.02, "end": 3449.06, "word": ",", "probability": 0.355712890625 } ] }, { "id": 1396, "seek": 340554, "start": 3449.06, "end": 3451.98, "text": " I'm going to be using multinomial count.", "tokens": [ 50964, 286, 478, 516, 281, 312, 1228, 45872, 47429, 1207, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.22149884852546234, "compression_ratio": 1.7222222222222223, "no_speech_prob": 0.005817413330078125, "words": [ { "start": 3449.06, "end": 3449.34, "word": " I'm", "probability": 0.977783203125 }, { "start": 3449.34, "end": 3449.5, "word": " going", "probability": 0.861328125 }, { "start": 3449.5, "end": 3449.6, "word": " to", "probability": 0.9072265625 }, { "start": 3449.6, "end": 3449.74, "word": " be", "probability": 0.90283203125 }, { "start": 3449.74, "end": 3449.98, "word": " using", "probability": 0.833984375 }, { "start": 3449.98, "end": 3450.78, "word": " multinomial", "probability": 0.936767578125 }, { "start": 3450.78, "end": 3451.74, "word": " count", "probability": 0.76123046875 }, { "start": 3451.74, "end": 3451.98, "word": ".", "probability": 0.73583984375 } ] }, { "id": 1397, "seek": 340554, "start": 3451.98, "end": 3453.8, "text": " We're going to use the same constructor.", "tokens": [ 51114, 492, 434, 516, 281, 764, 264, 912, 47479, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.22149884852546234, "compression_ratio": 1.7222222222222223, "no_speech_prob": 0.005817413330078125, "words": [ { "start": 3451.98, "end": 3452.26, "word": " We're", "probability": 0.9228515625 }, { "start": 3452.26, "end": 3452.32, "word": " going", "probability": 0.83544921875 }, { "start": 3452.32, "end": 3452.36, "word": " to", "probability": 0.908203125 }, { "start": 3452.36, "end": 3452.48, "word": " use", "probability": 0.83056640625 }, { "start": 3452.48, "end": 3452.6, "word": " the", "probability": 0.81201171875 }, { "start": 3452.6, "end": 3452.78, "word": " same", "probability": 0.81494140625 }, { "start": 3452.78, "end": 3453.32, "word": " constructor", "probability": 0.697265625 }, { "start": 3453.32, "end": 3453.8, "word": ".", "probability": 0.40478515625 } ] }, { "id": 1398, "seek": 340554, "start": 3454.78, "end": 3456.94, "text": " So in this case it's called count,", "tokens": [ 51264, 407, 294, 341, 1389, 309, 311, 1219, 1207, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.22149884852546234, "compression_ratio": 1.7222222222222223, "no_speech_prob": 0.005817413330078125, "words": [ { "start": 3454.78, "end": 3454.94, "word": " So", "probability": 0.7353515625 }, { "start": 3454.94, "end": 3455.04, "word": " in", "probability": 0.88916015625 }, { "start": 3455.04, "end": 3455.18, "word": " this", "probability": 0.88232421875 }, { "start": 3455.18, "end": 3455.42, "word": " case", "probability": 0.8046875 }, { "start": 3455.42, "end": 3455.78, "word": " it's", "probability": 0.842041015625 }, { "start": 3455.78, "end": 3456.42, "word": " called", "probability": 0.82421875 }, { "start": 3456.42, "end": 3456.82, "word": " count", "probability": 0.7060546875 }, { "start": 3456.82, "end": 3456.94, "word": ",", "probability": 0.15673828125 } ] }, { "id": 1399, "seek": 340554, "start": 3456.94, "end": 3461.58, "text": " and instead of using the tfidfx, we're going to use the countx.", "tokens": [ 51414, 293, 2602, 295, 1228, 264, 256, 69, 327, 69, 87, 11, 321, 434, 516, 281, 764, 264, 1207, 87, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.22149884852546234, "compression_ratio": 1.7222222222222223, "no_speech_prob": 0.005817413330078125, "words": [ { "start": 3456.94, "end": 3457.12, "word": " and", "probability": 0.89306640625 }, { "start": 3457.12, "end": 3457.38, "word": " instead", "probability": 0.849609375 }, { "start": 3457.38, "end": 3457.54, "word": " of", "probability": 0.90966796875 }, { "start": 3457.54, "end": 3457.82, "word": " using", "probability": 0.8134765625 }, { "start": 3457.82, "end": 3458.04, "word": " the", "probability": 0.77001953125 }, { "start": 3458.04, "end": 3459.08, "word": " tfidfx", "probability": 0.92236328125 }, { "start": 3459.08, "end": 3459.12, "word": ",", "probability": 0.44775390625 }, { "start": 3459.12, "end": 3459.26, "word": " we're", "probability": 0.929931640625 }, { "start": 3459.26, "end": 3459.44, "word": " going", "probability": 0.85400390625 }, { "start": 3459.44, "end": 3459.62, "word": " to", "probability": 0.904296875 }, { "start": 3459.62, "end": 3459.86, "word": " use", "probability": 0.82666015625 }, { "start": 3459.86, "end": 3460.28, "word": " the", "probability": 0.80615234375 }, { "start": 3460.28, "end": 3461.1, "word": " countx", "probability": 0.6455078125 }, { "start": 3461.1, "end": 3461.58, "word": ".", "probability": 0.751953125 } ] }, { "id": 1400, "seek": 340554, "start": 3464.32, "end": 3465.28, "text": " score,", "tokens": [ 51564, 6175, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.22149884852546234, "compression_ratio": 1.7222222222222223, "no_speech_prob": 0.005817413330078125, "words": [ { "start": 3464.32, "end": 3464.8, "word": " score", "probability": 0.4755859375 }, { "start": 3464.8, "end": 3465.28, "word": ",", "probability": 0.0985107421875 } ] }, { "id": 1401, "seek": 343136, "start": 3465.28, "end": 3466.76, "text": " count,", "tokens": [ 50364, 1207, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.23472222520245445, "compression_ratio": 1.511764705882353, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 3465.28, "end": 3466.06, "word": " count", "probability": 0.22265625 }, { "start": 3466.06, "end": 3466.76, "word": ",", "probability": 0.349609375 } ] }, { "id": 1402, "seek": 343136, "start": 3469.24, "end": 3470.14, "text": " mnb,", "tokens": [ 50514, 275, 77, 65, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.23472222520245445, "compression_ratio": 1.511764705882353, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 3469.24, "end": 3469.8, "word": " mnb", "probability": 0.555908203125 }, { "start": 3469.8, "end": 3470.14, "word": ",", "probability": 0.330810546875 } ] }, { "id": 1403, "seek": 343136, "start": 3470.14, "end": 3471.26, "text": " count,", "tokens": [ 50664, 1207, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.23472222520245445, "compression_ratio": 1.511764705882353, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 3470.14, "end": 3470.74, "word": " count", "probability": 0.71142578125 }, { "start": 3470.74, "end": 3471.26, "word": ",", "probability": 0.404296875 } ] }, { "id": 1404, "seek": 343136, "start": 3471.26, "end": 3476.68, "text": " and our test labels stay the same because we didn't vectorize those.", "tokens": [ 50814, 293, 527, 1500, 16949, 1754, 264, 912, 570, 321, 994, 380, 8062, 1125, 729, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.23472222520245445, "compression_ratio": 1.511764705882353, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 3471.26, "end": 3471.58, "word": " and", "probability": 0.03802490234375 }, { "start": 3471.58, "end": 3471.72, "word": " our", "probability": 0.501953125 }, { "start": 3471.72, "end": 3472.32, "word": " test", "probability": 0.81591796875 }, { "start": 3472.32, "end": 3474.5, "word": " labels", "probability": 0.55615234375 }, { "start": 3474.5, "end": 3474.76, "word": " stay", "probability": 0.8603515625 }, { "start": 3474.76, "end": 3474.92, "word": " the", "probability": 0.81494140625 }, { "start": 3474.92, "end": 3475.12, "word": " same", "probability": 0.8154296875 }, { "start": 3475.12, "end": 3475.38, "word": " because", "probability": 0.6044921875 }, { "start": 3475.38, "end": 3475.5, "word": " we", "probability": 0.90283203125 }, { "start": 3475.5, "end": 3475.72, "word": " didn't", "probability": 0.92431640625 }, { "start": 3475.72, "end": 3476.28, "word": " vectorize", "probability": 0.88037109375 }, { "start": 3476.28, "end": 3476.54, "word": " those", "probability": 0.8173828125 }, { "start": 3476.54, "end": 3476.68, "word": ".", "probability": 0.42724609375 } ] }, { "id": 1405, "seek": 343136, "start": 3476.68, "end": 3478.92, "text": " There's no reason for us to change this.", "tokens": [ 50964, 821, 311, 572, 1778, 337, 505, 281, 1319, 341, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.23472222520245445, "compression_ratio": 1.511764705882353, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 3476.68, "end": 3476.8, "word": " There's", "probability": 0.8017578125 }, { "start": 3476.8, "end": 3476.96, "word": " no", "probability": 0.89697265625 }, { "start": 3476.96, "end": 3477.24, "word": " reason", "probability": 0.9140625 }, { "start": 3477.24, "end": 3477.42, "word": " for", "probability": 0.8828125 }, { "start": 3477.42, "end": 3477.56, "word": " us", "probability": 0.90087890625 }, { "start": 3477.56, "end": 3477.7, "word": " to", "probability": 0.90673828125 }, { "start": 3477.7, "end": 3478.0, "word": " change", "probability": 0.83544921875 }, { "start": 3478.0, "end": 3478.36, "word": " this", "probability": 0.74169921875 }, { "start": 3478.36, "end": 3478.92, "word": ".", "probability": 0.9609375 } ] }, { "id": 1406, "seek": 343136, "start": 3480.12, "end": 3484.16, "text": " I'm just going to go ahead and ctrl-c and ctrl-v some stuff.", "tokens": [ 51114, 286, 478, 445, 516, 281, 352, 2286, 293, 269, 28269, 12, 66, 293, 269, 28269, 12, 85, 512, 1507, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.23472222520245445, "compression_ratio": 1.511764705882353, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 3480.12, "end": 3480.52, "word": " I'm", "probability": 0.84326171875 }, { "start": 3480.52, "end": 3480.62, "word": " just", "probability": 0.7978515625 }, { "start": 3480.62, "end": 3480.76, "word": " going", "probability": 0.56640625 }, { "start": 3480.76, "end": 3480.82, "word": " to", "probability": 0.892578125 }, { "start": 3480.82, "end": 3480.88, "word": " go", "probability": 0.8447265625 }, { "start": 3480.88, "end": 3481.22, "word": " ahead", "probability": 0.833984375 }, { "start": 3481.22, "end": 3481.78, "word": " and", "probability": 0.2578125 }, { "start": 3481.78, "end": 3481.96, "word": " ctrl", "probability": 0.38812255859375 }, { "start": 3481.96, "end": 3482.28, "word": "-c", "probability": 0.5745849609375 }, { "start": 3482.28, "end": 3482.56, "word": " and", "probability": 0.80126953125 }, { "start": 3482.56, "end": 3482.86, "word": " ctrl", "probability": 0.873779296875 }, { "start": 3482.86, "end": 3483.14, "word": "-v", "probability": 0.964111328125 }, { "start": 3483.14, "end": 3483.32, "word": " some", "probability": 0.525390625 }, { "start": 3483.32, "end": 3483.6, "word": " stuff", "probability": 0.791015625 }, { "start": 3483.6, "end": 3484.16, "word": ".", "probability": 0.912109375 } ] }, { "id": 1407, "seek": 343136, "start": 3485.9, "end": 3489.36, "text": " So all I'm doing is just changing the word tfidf", "tokens": [ 51414, 407, 439, 286, 478, 884, 307, 445, 4473, 264, 1349, 256, 69, 327, 69, 51564 ], "temperature": 0.0, "avg_logprob": -0.23472222520245445, "compression_ratio": 1.511764705882353, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 3485.9, "end": 3486.46, "word": " So", "probability": 0.52392578125 }, { "start": 3486.46, "end": 3486.72, "word": " all", "probability": 0.79150390625 }, { "start": 3486.72, "end": 3486.88, "word": " I'm", "probability": 0.95458984375 }, { "start": 3486.88, "end": 3487.2, "word": " doing", "probability": 0.9140625 }, { "start": 3487.2, "end": 3487.46, "word": " is", "probability": 0.9013671875 }, { "start": 3487.46, "end": 3487.66, "word": " just", "probability": 0.85791015625 }, { "start": 3487.66, "end": 3488.0, "word": " changing", "probability": 0.77294921875 }, { "start": 3488.0, "end": 3488.22, "word": " the", "probability": 0.80078125 }, { "start": 3488.22, "end": 3488.52, "word": " word", "probability": 0.7275390625 }, { "start": 3488.52, "end": 3489.36, "word": " tfidf", "probability": 0.7490234375 } ] }, { "id": 1408, "seek": 343136, "start": 3489.36, "end": 3491.1, "text": " to the word count.", "tokens": [ 51564, 281, 264, 1349, 1207, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.23472222520245445, "compression_ratio": 1.511764705882353, "no_speech_prob": 0.0004172325134277344, "words": [ { "start": 3489.36, "end": 3489.62, "word": " to", "probability": 0.89990234375 }, { "start": 3489.62, "end": 3489.84, "word": " the", "probability": 0.8046875 }, { "start": 3489.84, "end": 3490.08, "word": " word", "probability": 0.80615234375 }, { "start": 3490.08, "end": 3490.6, "word": " count", "probability": 0.6708984375 }, { "start": 3490.6, "end": 3491.1, "word": ".", "probability": 0.80908203125 } ] }, { "id": 1409, "seek": 345672, "start": 3491.1, "end": 3494.3, "text": " Everything else is staying the same.", "tokens": [ 50364, 5471, 1646, 307, 7939, 264, 912, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.23454671050166034, "compression_ratio": 1.5842696629213484, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 3491.1, "end": 3491.46, "word": " Everything", "probability": 0.3212890625 }, { "start": 3491.46, "end": 3491.76, "word": " else", "probability": 0.849609375 }, { "start": 3491.76, "end": 3492.12, "word": " is", "probability": 0.904296875 }, { "start": 3492.12, "end": 3492.72, "word": " staying", "probability": 0.765625 }, { "start": 3492.72, "end": 3493.26, "word": " the", "probability": 0.81591796875 }, { "start": 3493.26, "end": 3493.66, "word": " same", "probability": 0.8173828125 }, { "start": 3493.66, "end": 3494.3, "word": ".", "probability": 0.85693359375 } ] }, { "id": 1410, "seek": 345672, "start": 3495.04, "end": 3497.04, "text": " We have our predictions,", "tokens": [ 50514, 492, 362, 527, 21264, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.23454671050166034, "compression_ratio": 1.5842696629213484, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 3495.04, "end": 3495.68, "word": " We", "probability": 0.37744140625 }, { "start": 3495.68, "end": 3495.84, "word": " have", "probability": 0.88330078125 }, { "start": 3495.84, "end": 3496.02, "word": " our", "probability": 0.81005859375 }, { "start": 3496.02, "end": 3496.56, "word": " predictions", "probability": 0.73486328125 }, { "start": 3496.56, "end": 3497.04, "word": ",", "probability": 0.49072265625 } ] }, { "id": 1411, "seek": 345672, "start": 3497.04, "end": 3498.3, "text": " mnb, count,", "tokens": [ 50664, 275, 77, 65, 11, 1207, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.23454671050166034, "compression_ratio": 1.5842696629213484, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 3497.04, "end": 3497.4, "word": " mnb", "probability": 0.6578776041666666 }, { "start": 3497.4, "end": 3497.48, "word": ",", "probability": 0.01605224609375 }, { "start": 3497.48, "end": 3498.08, "word": " count", "probability": 0.7080078125 }, { "start": 3498.08, "end": 3498.3, "word": ",", "probability": 0.40869140625 } ] }, { "id": 1412, "seek": 345672, "start": 3498.3, "end": 3502.84, "text": " our test labels, that stays the same, we don't modify it.", "tokens": [ 50814, 527, 1500, 16949, 11, 300, 10834, 264, 912, 11, 321, 500, 380, 16927, 309, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.23454671050166034, "compression_ratio": 1.5842696629213484, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 3498.3, "end": 3498.8, "word": " our", "probability": 0.256591796875 }, { "start": 3498.8, "end": 3499.06, "word": " test", "probability": 0.8212890625 }, { "start": 3499.06, "end": 3499.5, "word": " labels", "probability": 0.8583984375 }, { "start": 3499.5, "end": 3499.74, "word": ",", "probability": 0.359619140625 }, { "start": 3499.74, "end": 3500.06, "word": " that", "probability": 0.7626953125 }, { "start": 3500.06, "end": 3500.28, "word": " stays", "probability": 0.80712890625 }, { "start": 3500.28, "end": 3500.5, "word": " the", "probability": 0.81591796875 }, { "start": 3500.5, "end": 3500.72, "word": " same", "probability": 0.810546875 }, { "start": 3500.72, "end": 3500.8, "word": ",", "probability": 0.49755859375 }, { "start": 3500.8, "end": 3500.88, "word": " we", "probability": 0.900390625 }, { "start": 3500.88, "end": 3501.04, "word": " don't", "probability": 0.9443359375 }, { "start": 3501.04, "end": 3501.44, "word": " modify", "probability": 0.869140625 }, { "start": 3501.44, "end": 3502.2, "word": " it", "probability": 0.89404296875 }, { "start": 3502.2, "end": 3502.84, "word": ".", "probability": 0.56689453125 } ] }, { "id": 1413, "seek": 345672, "start": 3502.9, "end": 3505.14, "text": " mnb, count,", "tokens": [ 50964, 275, 77, 65, 11, 1207, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.23454671050166034, "compression_ratio": 1.5842696629213484, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 3502.9, "end": 3503.36, "word": " mnb", "probability": 0.8277180989583334 }, { "start": 3503.36, "end": 3504.54, "word": ",", "probability": 0.361572265625 }, { "start": 3504.54, "end": 3504.86, "word": " count", "probability": 0.55224609375 }, { "start": 3504.86, "end": 3505.14, "word": ",", "probability": 0.71484375 } ] }, { "id": 1414, "seek": 345672, "start": 3505.14, "end": 3509.76, "text": " and then we change our predictions.", "tokens": [ 51114, 293, 550, 321, 1319, 527, 21264, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.23454671050166034, "compression_ratio": 1.5842696629213484, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 3505.14, "end": 3505.8, "word": " and", "probability": 0.00945281982421875 }, { "start": 3505.8, "end": 3507.8, "word": " then", "probability": 0.548828125 }, { "start": 3507.8, "end": 3507.9, "word": " we", "probability": 0.86474609375 }, { "start": 3507.9, "end": 3508.24, "word": " change", "probability": 0.83447265625 }, { "start": 3508.24, "end": 3508.52, "word": " our", "probability": 0.80712890625 }, { "start": 3508.52, "end": 3509.12, "word": " predictions", "probability": 0.77001953125 }, { "start": 3509.12, "end": 3509.76, "word": ".", "probability": 0.96240234375 } ] }, { "id": 1415, "seek": 345672, "start": 3510.6, "end": 3511.54, "text": " So I'm going to go ahead", "tokens": [ 51264, 407, 286, 478, 516, 281, 352, 2286, 51414 ], "temperature": 0.0, "avg_logprob": -0.23454671050166034, "compression_ratio": 1.5842696629213484, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 3510.6, "end": 3510.72, "word": " So", "probability": 0.67578125 }, { "start": 3510.72, "end": 3510.92, "word": " I'm", "probability": 0.86474609375 }, { "start": 3510.92, "end": 3510.98, "word": " going", "probability": 0.57861328125 }, { "start": 3510.98, "end": 3511.0, "word": " to", "probability": 0.90625 }, { "start": 3511.0, "end": 3511.1, "word": " go", "probability": 0.900390625 }, { "start": 3511.1, "end": 3511.54, "word": " ahead", "probability": 0.83837890625 } ] }, { "id": 1416, "seek": 345672, "start": 3511.54, "end": 3513.68, "text": " and let that sit for a moment.", "tokens": [ 51414, 293, 718, 300, 1394, 337, 257, 1623, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.23454671050166034, "compression_ratio": 1.5842696629213484, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 3511.54, "end": 3511.9, "word": " and", "probability": 0.72265625 }, { "start": 3511.9, "end": 3512.08, "word": " let", "probability": 0.89892578125 }, { "start": 3512.08, "end": 3512.44, "word": " that", "probability": 0.880859375 }, { "start": 3512.44, "end": 3512.68, "word": " sit", "probability": 0.91552734375 }, { "start": 3512.68, "end": 3512.86, "word": " for", "probability": 0.8974609375 }, { "start": 3513.02, "end": 3513.26, "word": " a moment", "probability": 0.91259765625 }, { "start": 3513.26, "end": 3513.68, "word": ".", "probability": 0.498046875 } ] }, { "id": 1417, "seek": 345672, "start": 3513.68, "end": 3516.46, "text": " I'll let you guys either manually type that in", "tokens": [ 51564, 286, 603, 718, 291, 1074, 2139, 16945, 2010, 300, 294, 51714 ], "temperature": 0.0, "avg_logprob": -0.23454671050166034, "compression_ratio": 1.5842696629213484, "no_speech_prob": 0.00225067138671875, "words": [ { "start": 3513.68, "end": 3513.7, "word": " I'll", "probability": 0.3802490234375 }, { "start": 3513.7, "end": 3513.76, "word": " let", "probability": 0.8701171875 }, { "start": 3513.76, "end": 3513.84, "word": " you", "probability": 0.89306640625 }, { "start": 3513.84, "end": 3514.26, "word": " guys", "probability": 0.84033203125 }, { "start": 3514.26, "end": 3515.18, "word": " either", "probability": 0.71630859375 }, { "start": 3515.18, "end": 3515.62, "word": " manually", "probability": 0.86865234375 }, { "start": 3515.62, "end": 3515.94, "word": " type", "probability": 0.9248046875 }, { "start": 3515.94, "end": 3516.14, "word": " that", "probability": 0.88037109375 }, { "start": 3516.14, "end": 3516.46, "word": " in", "probability": 0.9072265625 } ] }, { "id": 1418, "seek": 348378, "start": 3516.46, "end": 3520.94, "text": " or do the copy-and-paste track that I did,", "tokens": [ 50364, 420, 360, 264, 5055, 12, 474, 12, 79, 9079, 2837, 300, 286, 630, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.18936012188593546, "compression_ratio": 1.4631578947368422, "no_speech_prob": 0.009857177734375, "words": [ { "start": 3516.46, "end": 3516.84, "word": " or", "probability": 0.62939453125 }, { "start": 3516.84, "end": 3517.16, "word": " do", "probability": 0.8603515625 }, { "start": 3517.16, "end": 3517.42, "word": " the", "probability": 0.80908203125 }, { "start": 3517.42, "end": 3517.8, "word": " copy", "probability": 0.75341796875 }, { "start": 3517.8, "end": 3517.98, "word": "-and", "probability": 0.51519775390625 }, { "start": 3517.98, "end": 3518.38, "word": "-paste", "probability": 0.9430338541666666 }, { "start": 3518.38, "end": 3519.46, "word": " track", "probability": 0.83056640625 }, { "start": 3519.46, "end": 3519.68, "word": " that", "probability": 0.84375 }, { "start": 3519.68, "end": 3519.88, "word": " I", "probability": 0.97216796875 }, { "start": 3519.88, "end": 3520.2, "word": " did", "probability": 0.88720703125 }, { "start": 3520.2, "end": 3520.94, "word": ",", "probability": 0.478759765625 } ] }, { "id": 1419, "seek": 348378, "start": 3520.94, "end": 3522.7, "text": " which I highly recommend.", "tokens": [ 50514, 597, 286, 5405, 2748, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.18936012188593546, "compression_ratio": 1.4631578947368422, "no_speech_prob": 0.009857177734375, "words": [ { "start": 3520.94, "end": 3521.88, "word": " which", "probability": 0.90185546875 }, { "start": 3521.88, "end": 3521.96, "word": " I", "probability": 0.9814453125 }, { "start": 3521.96, "end": 3522.16, "word": " highly", "probability": 0.85546875 }, { "start": 3522.16, "end": 3522.6, "word": " recommend", "probability": 0.654296875 }, { "start": 3522.6, "end": 3522.7, "word": ".", "probability": 0.448486328125 } ] }, { "id": 1420, "seek": 348378, "start": 3522.7, "end": 3524.98, "text": " It just saves quite a bit of typing.", "tokens": [ 50664, 467, 445, 19155, 1596, 257, 857, 295, 18444, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.18936012188593546, "compression_ratio": 1.4631578947368422, "no_speech_prob": 0.009857177734375, "words": [ { "start": 3522.7, "end": 3522.78, "word": " It", "probability": 0.87646484375 }, { "start": 3522.78, "end": 3522.94, "word": " just", "probability": 0.83984375 }, { "start": 3522.94, "end": 3523.16, "word": " saves", "probability": 0.76220703125 }, { "start": 3523.16, "end": 3523.94, "word": " quite", "probability": 0.47607421875 }, { "start": 3524.06, "end": 3524.12, "word": " a bit", "probability": 0.90234375 }, { "start": 3524.12, "end": 3524.22, "word": " of", "probability": 0.90869140625 }, { "start": 3524.22, "end": 3524.46, "word": " typing", "probability": 0.64990234375 }, { "start": 3524.46, "end": 3524.98, "word": ".", "probability": 0.93798828125 } ] }, { "id": 1421, "seek": 348378, "start": 3526.28, "end": 3528.62, "text": " And then we'll type out the logistic regression", "tokens": [ 50814, 400, 550, 321, 603, 2010, 484, 264, 3565, 3142, 24590, 50964 ], "temperature": 0.0, "avg_logprob": -0.18936012188593546, "compression_ratio": 1.4631578947368422, "no_speech_prob": 0.009857177734375, "words": [ { "start": 3526.28, "end": 3526.8, "word": " And", "probability": 0.69677734375 }, { "start": 3526.8, "end": 3526.88, "word": " then", "probability": 0.55615234375 }, { "start": 3526.88, "end": 3526.98, "word": " we'll", "probability": 0.897705078125 }, { "start": 3526.98, "end": 3527.22, "word": " type", "probability": 0.89794921875 }, { "start": 3527.22, "end": 3527.44, "word": " out", "probability": 0.82080078125 }, { "start": 3527.44, "end": 3527.74, "word": " the", "probability": 0.8115234375 }, { "start": 3527.74, "end": 3528.2, "word": " logistic", "probability": 0.9130859375 }, { "start": 3528.2, "end": 3528.62, "word": " regression", "probability": 0.74560546875 } ] }, { "id": 1422, "seek": 348378, "start": 3528.62, "end": 3531.86, "text": " in a moment because that's the next model that we'll be making.", "tokens": [ 50964, 294, 257, 1623, 570, 300, 311, 264, 958, 2316, 300, 321, 603, 312, 1455, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.18936012188593546, "compression_ratio": 1.4631578947368422, "no_speech_prob": 0.009857177734375, "words": [ { "start": 3528.62, "end": 3529.24, "word": " in", "probability": 0.892578125 }, { "start": 3529.36, "end": 3529.54, "word": " a moment", "probability": 0.908203125 }, { "start": 3529.54, "end": 3529.78, "word": " because", "probability": 0.2841796875 }, { "start": 3529.78, "end": 3529.96, "word": " that's", "probability": 0.937744140625 }, { "start": 3529.96, "end": 3530.12, "word": " the", "probability": 0.8125 }, { "start": 3530.12, "end": 3530.38, "word": " next", "probability": 0.87255859375 }, { "start": 3530.38, "end": 3530.66, "word": " model", "probability": 0.81005859375 }, { "start": 3530.66, "end": 3530.82, "word": " that", "probability": 0.84326171875 }, { "start": 3530.82, "end": 3530.94, "word": " we'll", "probability": 0.919677734375 }, { "start": 3530.94, "end": 3531.08, "word": " be", "probability": 0.90478515625 }, { "start": 3531.08, "end": 3531.34, "word": " making", "probability": 0.79541015625 }, { "start": 3531.34, "end": 3531.86, "word": ".", "probability": 0.98681640625 } ] }, { "id": 1423, "seek": 348378, "start": 3534.78, "end": 3537.6, "text": " How are we doing on questions?", "tokens": [ 51264, 1012, 366, 321, 884, 322, 1651, 30, 51414 ], "temperature": 0.0, "avg_logprob": -0.18936012188593546, "compression_ratio": 1.4631578947368422, "no_speech_prob": 0.009857177734375, "words": [ { "start": 3534.78, "end": 3535.3, "word": " How", "probability": 0.83251953125 }, { "start": 3535.3, "end": 3535.56, "word": " are", "probability": 0.89697265625 }, { "start": 3535.56, "end": 3535.74, "word": " we", "probability": 0.90380859375 }, { "start": 3535.74, "end": 3536.08, "word": " doing", "probability": 0.92822265625 }, { "start": 3536.08, "end": 3536.48, "word": " on", "probability": 0.90771484375 }, { "start": 3536.48, "end": 3537.08, "word": " questions", "probability": 0.900390625 }, { "start": 3537.08, "end": 3537.6, "word": "?", "probability": 0.9775390625 } ] }, { "id": 1424, "seek": 348378, "start": 3541.16, "end": 3543.52, "text": " I think we're all doing well.", "tokens": [ 51564, 286, 519, 321, 434, 439, 884, 731, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.18936012188593546, "compression_ratio": 1.4631578947368422, "no_speech_prob": 0.009857177734375, "words": [ { "start": 3541.16, "end": 3541.68, "word": " I", "probability": 0.397705078125 }, { "start": 3541.68, "end": 3542.2, "word": " think", "probability": 0.8193359375 }, { "start": 3542.2, "end": 3542.36, "word": " we're", "probability": 0.921142578125 }, { "start": 3542.36, "end": 3542.48, "word": " all", "probability": 0.89501953125 }, { "start": 3542.48, "end": 3542.68, "word": " doing", "probability": 0.91357421875 }, { "start": 3542.68, "end": 3543.0, "word": " well", "probability": 0.87158203125 }, { "start": 3543.0, "end": 3543.52, "word": ".", "probability": 0.92919921875 } ] }, { "id": 1425, "seek": 350968, "start": 3544.3, "end": 3546.98, "text": " Everything's quiet on the Discord chat, too.", "tokens": [ 50364, 5471, 311, 5677, 322, 264, 32623, 5081, 11, 886, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.19100765154069785, "compression_ratio": 1.5242718446601942, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 3544.3, "end": 3544.88, "word": " Everything's", "probability": 0.4791259765625 }, { "start": 3544.88, "end": 3545.16, "word": " quiet", "probability": 0.83984375 }, { "start": 3545.16, "end": 3545.44, "word": " on", "probability": 0.900390625 }, { "start": 3545.44, "end": 3545.56, "word": " the", "probability": 0.80126953125 }, { "start": 3545.56, "end": 3545.84, "word": " Discord", "probability": 0.5927734375 }, { "start": 3545.84, "end": 3546.18, "word": " chat", "probability": 0.78466796875 }, { "start": 3546.18, "end": 3546.22, "word": ",", "probability": 0.343017578125 }, { "start": 3546.22, "end": 3546.4, "word": " too", "probability": 0.794921875 }, { "start": 3546.4, "end": 3546.98, "word": ".", "probability": 0.94873046875 } ] }, { "id": 1426, "seek": 350968, "start": 3551.58, "end": 3552.38, "text": " Awesome.", "tokens": [ 50514, 10391, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.19100765154069785, "compression_ratio": 1.5242718446601942, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 3551.58, "end": 3552.16, "word": " Awesome", "probability": 0.80322265625 }, { "start": 3552.16, "end": 3552.38, "word": ".", "probability": 0.5927734375 } ] }, { "id": 1427, "seek": 350968, "start": 3552.38, "end": 3554.04, "text": " So I'm going to go ahead and run this.", "tokens": [ 50664, 407, 286, 478, 516, 281, 352, 2286, 293, 1190, 341, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.19100765154069785, "compression_ratio": 1.5242718446601942, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 3552.38, "end": 3552.46, "word": " So", "probability": 0.85400390625 }, { "start": 3552.46, "end": 3552.56, "word": " I'm", "probability": 0.767333984375 }, { "start": 3552.56, "end": 3552.64, "word": " going", "probability": 0.5283203125 }, { "start": 3552.64, "end": 3552.66, "word": " to", "probability": 0.90087890625 }, { "start": 3552.66, "end": 3552.8, "word": " go", "probability": 0.896484375 }, { "start": 3552.8, "end": 3553.0, "word": " ahead", "probability": 0.853515625 }, { "start": 3553.0, "end": 3553.2, "word": " and", "probability": 0.896484375 }, { "start": 3553.2, "end": 3553.5, "word": " run", "probability": 0.90283203125 }, { "start": 3553.5, "end": 3553.86, "word": " this", "probability": 0.8837890625 }, { "start": 3553.86, "end": 3554.04, "word": ".", "probability": 0.8076171875 } ] }, { "id": 1428, "seek": 350968, "start": 3554.04, "end": 3556.34, "text": " I'm going to do Shift-Enter.", "tokens": [ 50814, 286, 478, 516, 281, 360, 28304, 12, 16257, 391, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.19100765154069785, "compression_ratio": 1.5242718446601942, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 3554.04, "end": 3554.08, "word": " I'm", "probability": 0.978759765625 }, { "start": 3554.08, "end": 3554.16, "word": " going", "probability": 0.80908203125 }, { "start": 3554.16, "end": 3554.18, "word": " to", "probability": 0.90625 }, { "start": 3554.18, "end": 3554.44, "word": " do", "probability": 0.90673828125 }, { "start": 3554.44, "end": 3555.2, "word": " Shift", "probability": 0.16943359375 }, { "start": 3555.2, "end": 3555.76, "word": "-Enter", "probability": 0.6529134114583334 }, { "start": 3555.76, "end": 3556.34, "word": ".", "probability": 0.7587890625 } ] }, { "id": 1429, "seek": 350968, "start": 3557.64, "end": 3560.28, "text": " And if we look at our accuracy, our multinomial", "tokens": [ 50964, 400, 498, 321, 574, 412, 527, 14170, 11, 527, 45872, 47429, 51114 ], "temperature": 0.0, "avg_logprob": -0.19100765154069785, "compression_ratio": 1.5242718446601942, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 3557.64, "end": 3558.1, "word": " And", "probability": 0.833984375 }, { "start": 3558.1, "end": 3558.26, "word": " if", "probability": 0.8837890625 }, { "start": 3558.26, "end": 3558.36, "word": " we", "probability": 0.90185546875 }, { "start": 3558.36, "end": 3558.5, "word": " look", "probability": 0.919921875 }, { "start": 3558.5, "end": 3558.58, "word": " at", "probability": 0.90283203125 }, { "start": 3558.58, "end": 3558.68, "word": " our", "probability": 0.7919921875 }, { "start": 3558.68, "end": 3559.08, "word": " accuracy", "probability": 0.71923828125 }, { "start": 3559.08, "end": 3559.38, "word": ",", "probability": 0.89013671875 }, { "start": 3559.38, "end": 3559.54, "word": " our", "probability": 0.80126953125 }, { "start": 3559.54, "end": 3560.28, "word": " multinomial", "probability": 0.89990234375 } ] }, { "id": 1430, "seek": 350968, "start": 3560.28, "end": 3565.22, "text": " with the count vectorizer, we have a 94% accuracy.", "tokens": [ 51114, 365, 264, 1207, 8062, 6545, 11, 321, 362, 257, 30849, 4, 14170, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.19100765154069785, "compression_ratio": 1.5242718446601942, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 3560.28, "end": 3560.6, "word": " with", "probability": 0.004497528076171875 }, { "start": 3560.6, "end": 3561.52, "word": " the", "probability": 0.6259765625 }, { "start": 3561.52, "end": 3561.74, "word": " count", "probability": 0.70849609375 }, { "start": 3561.74, "end": 3562.3, "word": " vectorizer", "probability": 0.933349609375 }, { "start": 3562.3, "end": 3562.44, "word": ",", "probability": 0.88427734375 }, { "start": 3562.44, "end": 3562.52, "word": " we", "probability": 0.8916015625 }, { "start": 3562.52, "end": 3562.78, "word": " have", "probability": 0.8828125 }, { "start": 3563.1, "end": 3563.74, "word": " a 94", "probability": 0.8935546875 }, { "start": 3563.74, "end": 3564.14, "word": "%", "probability": 0.89404296875 }, { "start": 3564.14, "end": 3564.64, "word": " accuracy", "probability": 0.74462890625 }, { "start": 3564.64, "end": 3565.22, "word": ".", "probability": 0.90869140625 } ] }, { "id": 1431, "seek": 350968, "start": 3565.38, "end": 3567.66, "text": " So quite a decent bump", "tokens": [ 51264, 407, 1596, 257, 8681, 9961, 51414 ], "temperature": 0.0, "avg_logprob": -0.19100765154069785, "compression_ratio": 1.5242718446601942, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 3565.38, "end": 3565.66, "word": " So", "probability": 0.88671875 }, { "start": 3565.66, "end": 3566.32, "word": " quite", "probability": 0.72998046875 }, { "start": 3566.92, "end": 3567.22, "word": " a decent", "probability": 0.72705078125 }, { "start": 3567.22, "end": 3567.66, "word": " bump", "probability": 0.81298828125 } ] }, { "id": 1432, "seek": 350968, "start": 3567.66, "end": 3569.92, "text": " compared to our tfidf vectorizer", "tokens": [ 51414, 5347, 281, 527, 256, 69, 327, 69, 8062, 6545, 51564 ], "temperature": 0.0, "avg_logprob": -0.19100765154069785, "compression_ratio": 1.5242718446601942, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 3567.66, "end": 3568.44, "word": " compared", "probability": 0.767578125 }, { "start": 3568.44, "end": 3568.62, "word": " to", "probability": 0.90625 }, { "start": 3568.62, "end": 3568.76, "word": " our", "probability": 0.80615234375 }, { "start": 3568.76, "end": 3569.34, "word": " tfidf", "probability": 0.568389892578125 }, { "start": 3569.34, "end": 3569.92, "word": " vectorizer", "probability": 0.9345703125 } ] }, { "id": 1433, "seek": 350968, "start": 3569.92, "end": 3572.7, "text": " using the same multinomial algorithm.", "tokens": [ 51564, 1228, 264, 912, 45872, 47429, 9284, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.19100765154069785, "compression_ratio": 1.5242718446601942, "no_speech_prob": 0.004070281982421875, "words": [ { "start": 3569.92, "end": 3570.34, "word": " using", "probability": 0.6025390625 }, { "start": 3570.34, "end": 3570.56, "word": " the", "probability": 0.810546875 }, { "start": 3570.56, "end": 3570.88, "word": " same", "probability": 0.83056640625 }, { "start": 3570.88, "end": 3571.6, "word": " multinomial", "probability": 0.938720703125 }, { "start": 3571.6, "end": 3572.12, "word": " algorithm", "probability": 0.8173828125 }, { "start": 3572.12, "end": 3572.7, "word": ".", "probability": 0.99267578125 } ] }, { "id": 1434, "seek": 353702, "start": 3572.7, "end": 3576.76, "text": " What we see is about 26 of our emails...", "tokens": [ 50364, 708, 321, 536, 307, 466, 7551, 295, 527, 12524, 485, 50514 ], "temperature": 0.0, "avg_logprob": -0.21619591417794043, "compression_ratio": 1.6495726495726495, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 3572.7, "end": 3573.14, "word": " What", "probability": 0.595703125 }, { "start": 3573.14, "end": 3573.28, "word": " we", "probability": 0.90625 }, { "start": 3573.28, "end": 3573.54, "word": " see", "probability": 0.8173828125 }, { "start": 3573.54, "end": 3574.1, "word": " is", "probability": 0.89990234375 }, { "start": 3574.1, "end": 3574.96, "word": " about", "probability": 0.6865234375 }, { "start": 3574.96, "end": 3575.54, "word": " 26", "probability": 0.88916015625 }, { "start": 3575.54, "end": 3575.7, "word": " of", "probability": 0.90771484375 }, { "start": 3575.7, "end": 3575.84, "word": " our", "probability": 0.81689453125 }, { "start": 3575.84, "end": 3576.76, "word": " emails...", "probability": 0.419464111328125 } ] }, { "id": 1435, "seek": 353702, "start": 3576.76, "end": 3579.62, "text": " not about, it's exactly 26 of our emails", "tokens": [ 50514, 406, 466, 11, 309, 311, 2293, 7551, 295, 527, 12524, 50664 ], "temperature": 0.0, "avg_logprob": -0.21619591417794043, "compression_ratio": 1.6495726495726495, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 3576.76, "end": 3577.5, "word": " not", "probability": 0.26318359375 }, { "start": 3577.5, "end": 3577.8, "word": " about", "probability": 0.6630859375 }, { "start": 3577.8, "end": 3577.92, "word": ",", "probability": 0.62646484375 }, { "start": 3577.92, "end": 3578.12, "word": " it's", "probability": 0.886474609375 }, { "start": 3578.12, "end": 3578.56, "word": " exactly", "probability": 0.78076171875 }, { "start": 3578.56, "end": 3579.04, "word": " 26", "probability": 0.91259765625 }, { "start": 3579.04, "end": 3579.22, "word": " of", "probability": 0.91064453125 }, { "start": 3579.22, "end": 3579.34, "word": " our", "probability": 0.82080078125 }, { "start": 3579.34, "end": 3579.62, "word": " emails", "probability": 0.7744140625 } ] }, { "id": 1436, "seek": 353702, "start": 3579.62, "end": 3581.9, "text": " in our test set got blocked.", "tokens": [ 50664, 294, 527, 1500, 992, 658, 15470, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.21619591417794043, "compression_ratio": 1.6495726495726495, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 3579.62, "end": 3579.78, "word": " in", "probability": 0.8056640625 }, { "start": 3579.78, "end": 3579.9, "word": " our", "probability": 0.81396484375 }, { "start": 3579.9, "end": 3580.16, "word": " test", "probability": 0.81298828125 }, { "start": 3580.16, "end": 3580.5, "word": " set", "probability": 0.88623046875 }, { "start": 3580.5, "end": 3581.4, "word": " got", "probability": 0.78515625 }, { "start": 3581.4, "end": 3581.78, "word": " blocked", "probability": 0.662109375 }, { "start": 3581.78, "end": 3581.9, "word": ".", "probability": 0.59814453125 } ] }, { "id": 1437, "seek": 353702, "start": 3581.9, "end": 3583.88, "text": " They were considered spam.", "tokens": [ 50814, 814, 645, 4888, 24028, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.21619591417794043, "compression_ratio": 1.6495726495726495, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 3581.9, "end": 3581.96, "word": " They", "probability": 0.728515625 }, { "start": 3581.96, "end": 3582.1, "word": " were", "probability": 0.88623046875 }, { "start": 3582.1, "end": 3582.58, "word": " considered", "probability": 0.64306640625 }, { "start": 3582.58, "end": 3583.44, "word": " spam", "probability": 0.8984375 }, { "start": 3583.44, "end": 3583.88, "word": ".", "probability": 0.56640625 } ] }, { "id": 1438, "seek": 353702, "start": 3584.48, "end": 3586.94, "text": " These are the regular ham emails.", "tokens": [ 50964, 1981, 366, 264, 3890, 7852, 12524, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.21619591417794043, "compression_ratio": 1.6495726495726495, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 3584.48, "end": 3584.92, "word": " These", "probability": 0.55908203125 }, { "start": 3584.92, "end": 3585.02, "word": " are", "probability": 0.8876953125 }, { "start": 3585.02, "end": 3585.18, "word": " the", "probability": 0.814453125 }, { "start": 3585.18, "end": 3585.52, "word": " regular", "probability": 0.88818359375 }, { "start": 3585.52, "end": 3585.88, "word": " ham", "probability": 0.57275390625 }, { "start": 3585.88, "end": 3586.52, "word": " emails", "probability": 0.82373046875 }, { "start": 3586.52, "end": 3586.94, "word": ".", "probability": 0.6083984375 } ] }, { "id": 1439, "seek": 353702, "start": 3586.94, "end": 3589.48, "text": " But we have significantly fewer spam emails", "tokens": [ 51114, 583, 321, 362, 10591, 13366, 24028, 12524, 51264 ], "temperature": 0.0, "avg_logprob": -0.21619591417794043, "compression_ratio": 1.6495726495726495, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 3586.94, "end": 3587.1, "word": " But", "probability": 0.74755859375 }, { "start": 3587.1, "end": 3587.18, "word": " we", "probability": 0.880859375 }, { "start": 3587.18, "end": 3587.24, "word": " have", "probability": 0.88037109375 }, { "start": 3587.24, "end": 3587.76, "word": " significantly", "probability": 0.392333984375 }, { "start": 3587.76, "end": 3588.58, "word": " fewer", "probability": 0.7294921875 }, { "start": 3588.58, "end": 3589.12, "word": " spam", "probability": 0.91455078125 }, { "start": 3589.12, "end": 3589.48, "word": " emails", "probability": 0.77880859375 } ] }, { "id": 1440, "seek": 353702, "start": 3589.48, "end": 3593.9, "text": " that are getting through our predictor.", "tokens": [ 51264, 300, 366, 1242, 807, 527, 6069, 284, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.21619591417794043, "compression_ratio": 1.6495726495726495, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 3589.48, "end": 3589.66, "word": " that", "probability": 0.86279296875 }, { "start": 3589.66, "end": 3589.74, "word": " are", "probability": 0.8935546875 }, { "start": 3589.74, "end": 3589.9, "word": " getting", "probability": 0.91259765625 }, { "start": 3589.9, "end": 3590.34, "word": " through", "probability": 0.7666015625 }, { "start": 3590.34, "end": 3591.56, "word": " our", "probability": 0.79541015625 }, { "start": 3591.56, "end": 3593.62, "word": " predictor", "probability": 0.7900390625 }, { "start": 3593.62, "end": 3593.9, "word": ".", "probability": 0.63818359375 } ] }, { "id": 1441, "seek": 353702, "start": 3593.9, "end": 3597.34, "text": " And so more of them are being classified as spam correctly.", "tokens": [ 51414, 400, 370, 544, 295, 552, 366, 885, 20627, 382, 24028, 8944, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.21619591417794043, "compression_ratio": 1.6495726495726495, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 3593.9, "end": 3593.9, "word": " And", "probability": 0.5654296875 }, { "start": 3593.9, "end": 3594.18, "word": " so", "probability": 0.88671875 }, { "start": 3594.18, "end": 3595.02, "word": " more", "probability": 0.71533203125 }, { "start": 3595.02, "end": 3595.22, "word": " of", "probability": 0.90625 }, { "start": 3595.22, "end": 3595.42, "word": " them", "probability": 0.74267578125 }, { "start": 3595.42, "end": 3595.6, "word": " are", "probability": 0.89794921875 }, { "start": 3595.6, "end": 3595.78, "word": " being", "probability": 0.88330078125 }, { "start": 3595.78, "end": 3596.2, "word": " classified", "probability": 0.92822265625 }, { "start": 3596.2, "end": 3596.44, "word": " as", "probability": 0.90869140625 }, { "start": 3596.44, "end": 3596.68, "word": " spam", "probability": 0.92724609375 }, { "start": 3596.68, "end": 3597.16, "word": " correctly", "probability": 0.81298828125 }, { "start": 3597.16, "end": 3597.34, "word": ".", "probability": 0.92578125 } ] }, { "id": 1442, "seek": 353702, "start": 3597.34, "end": 3600.04, "text": " And so this is what we want to see is a dark blue over in this corner.", "tokens": [ 51564, 400, 370, 341, 307, 437, 321, 528, 281, 536, 307, 257, 2877, 3344, 670, 294, 341, 4538, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.21619591417794043, "compression_ratio": 1.6495726495726495, "no_speech_prob": 0.00130462646484375, "words": [ { "start": 3597.34, "end": 3597.36, "word": " And", "probability": 0.3486328125 }, { "start": 3597.36, "end": 3597.44, "word": " so", "probability": 0.89404296875 }, { "start": 3597.44, "end": 3597.6, "word": " this", "probability": 0.857421875 }, { "start": 3597.6, "end": 3597.66, "word": " is", "probability": 0.90576171875 }, { "start": 3597.66, "end": 3597.76, "word": " what", "probability": 0.85693359375 }, { "start": 3597.76, "end": 3597.86, "word": " we", "probability": 0.87060546875 }, { "start": 3597.86, "end": 3597.96, "word": " want", "probability": 0.7861328125 }, { "start": 3597.96, "end": 3598.04, "word": " to", "probability": 0.90625 }, { "start": 3598.04, "end": 3598.18, "word": " see", "probability": 0.8134765625 }, { "start": 3598.18, "end": 3598.28, "word": " is", "probability": 0.6298828125 }, { "start": 3598.4, "end": 3598.58, "word": " a dark", "probability": 0.8330078125 }, { "start": 3598.58, "end": 3598.82, "word": " blue", "probability": 0.92333984375 }, { "start": 3598.82, "end": 3599.02, "word": " over", "probability": 0.8193359375 }, { "start": 3599.02, "end": 3599.16, "word": " in", "probability": 0.90625 }, { "start": 3599.16, "end": 3599.34, "word": " this", "probability": 0.88330078125 }, { "start": 3599.34, "end": 3599.62, "word": " corner", "probability": 0.837890625 }, { "start": 3599.62, "end": 3600.04, "word": ".", "probability": 0.412353515625 } ] }, { "id": 1443, "seek": 356384, "start": 3600.04, "end": 3603.72, "text": " And a darker blue", "tokens": [ 50364, 400, 257, 12741, 3344, 50514 ], "temperature": 0.0, "avg_logprob": -0.1944040637030158, "compression_ratio": 1.539906103286385, "no_speech_prob": 0.003429412841796875, "words": [ { "start": 3600.04, "end": 3600.18, "word": " And", "probability": 0.10821533203125 }, { "start": 3601.96, "end": 3603.22, "word": " a darker", "probability": 0.7626953125 }, { "start": 3603.22, "end": 3603.72, "word": " blue", "probability": 0.91748046875 } ] }, { "id": 1444, "seek": 356384, "start": 3603.72, "end": 3607.08, "text": " or this lighter blue given the count", "tokens": [ 50514, 420, 341, 11546, 3344, 2212, 264, 1207, 50664 ], "temperature": 0.0, "avg_logprob": -0.1944040637030158, "compression_ratio": 1.539906103286385, "no_speech_prob": 0.003429412841796875, "words": [ { "start": 3603.72, "end": 3604.08, "word": " or", "probability": 0.63330078125 }, { "start": 3604.08, "end": 3605.56, "word": " this", "probability": 0.1759033203125 }, { "start": 3605.56, "end": 3606.02, "word": " lighter", "probability": 0.78466796875 }, { "start": 3606.02, "end": 3606.36, "word": " blue", "probability": 0.916015625 }, { "start": 3606.36, "end": 3606.6, "word": " given", "probability": 0.38916015625 }, { "start": 3606.6, "end": 3606.74, "word": " the", "probability": 0.80859375 }, { "start": 3606.74, "end": 3607.08, "word": " count", "probability": 0.7880859375 } ] }, { "id": 1445, "seek": 356384, "start": 3607.08, "end": 3609.08, "text": " over in the bottom right corner.", "tokens": [ 50664, 670, 294, 264, 2767, 558, 4538, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.1944040637030158, "compression_ratio": 1.539906103286385, "no_speech_prob": 0.003429412841796875, "words": [ { "start": 3607.08, "end": 3607.66, "word": " over", "probability": 0.76318359375 }, { "start": 3607.66, "end": 3607.8, "word": " in", "probability": 0.88720703125 }, { "start": 3607.8, "end": 3607.88, "word": " the", "probability": 0.8134765625 }, { "start": 3607.88, "end": 3608.04, "word": " bottom", "probability": 0.7724609375 }, { "start": 3608.04, "end": 3608.24, "word": " right", "probability": 0.853515625 }, { "start": 3608.24, "end": 3608.52, "word": " corner", "probability": 0.8291015625 }, { "start": 3608.52, "end": 3609.08, "word": ".", "probability": 0.98779296875 } ] }, { "id": 1446, "seek": 356384, "start": 3609.56, "end": 3612.2, "text": " So this kind of hops into a conversation", "tokens": [ 50814, 407, 341, 733, 295, 47579, 666, 257, 3761, 50964 ], "temperature": 0.0, "avg_logprob": -0.1944040637030158, "compression_ratio": 1.539906103286385, "no_speech_prob": 0.003429412841796875, "words": [ { "start": 3609.56, "end": 3609.82, "word": " So", "probability": 0.81982421875 }, { "start": 3609.82, "end": 3610.04, "word": " this", "probability": 0.79150390625 }, { "start": 3610.04, "end": 3610.2, "word": " kind", "probability": 0.537109375 }, { "start": 3610.2, "end": 3610.34, "word": " of", "probability": 0.9140625 }, { "start": 3610.34, "end": 3610.62, "word": " hops", "probability": 0.70849609375 }, { "start": 3610.62, "end": 3610.98, "word": " into", "probability": 0.74560546875 }, { "start": 3611.76, "end": 3612.2, "word": " a conversation", "probability": 0.83349609375 } ] }, { "id": 1447, "seek": 356384, "start": 3612.2, "end": 3615.84, "text": " about false positives and false negatives.", "tokens": [ 50964, 466, 7908, 35127, 293, 7908, 40019, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.1944040637030158, "compression_ratio": 1.539906103286385, "no_speech_prob": 0.003429412841796875, "words": [ { "start": 3612.2, "end": 3612.86, "word": " about", "probability": 0.82861328125 }, { "start": 3612.86, "end": 3614.1, "word": " false", "probability": 0.83984375 }, { "start": 3614.1, "end": 3614.44, "word": " positives", "probability": 0.83837890625 }, { "start": 3614.44, "end": 3614.68, "word": " and", "probability": 0.8916015625 }, { "start": 3614.68, "end": 3614.88, "word": " false", "probability": 0.8544921875 }, { "start": 3614.88, "end": 3615.34, "word": " negatives", "probability": 0.796875 }, { "start": 3615.34, "end": 3615.84, "word": ".", "probability": 0.53955078125 } ] }, { "id": 1448, "seek": 356384, "start": 3615.84, "end": 3619.0, "text": " Which would you like to prioritize?", "tokens": [ 51114, 3013, 576, 291, 411, 281, 25164, 30, 51264 ], "temperature": 0.0, "avg_logprob": -0.1944040637030158, "compression_ratio": 1.539906103286385, "no_speech_prob": 0.003429412841796875, "words": [ { "start": 3615.84, "end": 3616.4, "word": " Which", "probability": 0.82666015625 }, { "start": 3616.4, "end": 3616.58, "word": " would", "probability": 0.86474609375 }, { "start": 3616.58, "end": 3616.68, "word": " you", "probability": 0.8896484375 }, { "start": 3616.68, "end": 3616.86, "word": " like", "probability": 0.88134765625 }, { "start": 3616.86, "end": 3617.16, "word": " to", "probability": 0.90576171875 }, { "start": 3617.16, "end": 3618.44, "word": " prioritize", "probability": 0.61572265625 }, { "start": 3618.44, "end": 3619.0, "word": "?", "probability": 0.97900390625 } ] }, { "id": 1449, "seek": 356384, "start": 3619.98, "end": 3622.34, "text": " And so it really depends on the model.", "tokens": [ 51264, 400, 370, 309, 534, 5946, 322, 264, 2316, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.1944040637030158, "compression_ratio": 1.539906103286385, "no_speech_prob": 0.003429412841796875, "words": [ { "start": 3619.98, "end": 3620.2, "word": " And", "probability": 0.8681640625 }, { "start": 3620.2, "end": 3620.48, "word": " so", "probability": 0.8984375 }, { "start": 3620.48, "end": 3620.72, "word": " it", "probability": 0.826171875 }, { "start": 3620.72, "end": 3620.94, "word": " really", "probability": 0.6318359375 }, { "start": 3620.94, "end": 3621.38, "word": " depends", "probability": 0.256591796875 }, { "start": 3621.38, "end": 3621.78, "word": " on", "probability": 0.90673828125 }, { "start": 3621.78, "end": 3621.92, "word": " the", "probability": 0.81396484375 }, { "start": 3621.92, "end": 3622.2, "word": " model", "probability": 0.8046875 }, { "start": 3622.2, "end": 3622.34, "word": ".", "probability": 0.9169921875 } ] }, { "id": 1450, "seek": 356384, "start": 3622.34, "end": 3625.22, "text": " In security, one of the things that we're concerned about", "tokens": [ 51414, 682, 3825, 11, 472, 295, 264, 721, 300, 321, 434, 5922, 466, 51564 ], "temperature": 0.0, "avg_logprob": -0.1944040637030158, "compression_ratio": 1.539906103286385, "no_speech_prob": 0.003429412841796875, "words": [ { "start": 3622.34, "end": 3622.44, "word": " In", "probability": 0.92529296875 }, { "start": 3622.44, "end": 3622.98, "word": " security", "probability": 0.91064453125 }, { "start": 3622.98, "end": 3623.6, "word": ",", "probability": 0.8701171875 }, { "start": 3623.6, "end": 3623.88, "word": " one", "probability": 0.8173828125 }, { "start": 3623.88, "end": 3623.96, "word": " of", "probability": 0.904296875 }, { "start": 3623.96, "end": 3624.04, "word": " the", "probability": 0.81494140625 }, { "start": 3624.04, "end": 3624.22, "word": " things", "probability": 0.73681640625 }, { "start": 3624.22, "end": 3624.34, "word": " that", "probability": 0.8740234375 }, { "start": 3624.34, "end": 3624.48, "word": " we're", "probability": 0.929931640625 }, { "start": 3624.48, "end": 3624.9, "word": " concerned", "probability": 0.8486328125 }, { "start": 3624.9, "end": 3625.22, "word": " about", "probability": 0.8203125 } ] }, { "id": 1451, "seek": 356384, "start": 3625.22, "end": 3626.86, "text": " is impacting the users.", "tokens": [ 51564, 307, 29963, 264, 5022, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.1944040637030158, "compression_ratio": 1.539906103286385, "no_speech_prob": 0.003429412841796875, "words": [ { "start": 3625.22, "end": 3625.44, "word": " is", "probability": 0.8876953125 }, { "start": 3625.44, "end": 3625.96, "word": " impacting", "probability": 0.73193359375 }, { "start": 3625.96, "end": 3626.2, "word": " the", "probability": 0.8046875 }, { "start": 3626.2, "end": 3626.56, "word": " users", "probability": 0.8388671875 }, { "start": 3626.56, "end": 3626.86, "word": ".", "probability": 0.99169921875 } ] }, { "id": 1452, "seek": 359092, "start": 3626.86, "end": 3630.98, "text": " So if you look at something like an antivirus,", "tokens": [ 50364, 407, 498, 291, 574, 412, 746, 411, 364, 2511, 592, 9619, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.19549419280401495, "compression_ratio": 1.5075376884422111, "no_speech_prob": 0.00307464599609375, "words": [ { "start": 3626.86, "end": 3627.04, "word": " So", "probability": 0.818359375 }, { "start": 3627.04, "end": 3627.24, "word": " if", "probability": 0.7822265625 }, { "start": 3627.24, "end": 3627.34, "word": " you", "probability": 0.892578125 }, { "start": 3627.34, "end": 3627.52, "word": " look", "probability": 0.91796875 }, { "start": 3627.52, "end": 3627.64, "word": " at", "probability": 0.9033203125 }, { "start": 3627.64, "end": 3628.06, "word": " something", "probability": 0.7373046875 }, { "start": 3628.06, "end": 3628.6, "word": " like", "probability": 0.8701171875 }, { "start": 3628.6, "end": 3630.0, "word": " an", "probability": 0.7890625 }, { "start": 3630.0, "end": 3630.76, "word": " antivirus", "probability": 0.84814453125 }, { "start": 3630.76, "end": 3630.98, "word": ",", "probability": 0.91357421875 } ] }, { "id": 1453, "seek": 359092, "start": 3630.98, "end": 3633.1, "text": " it looks for things that are probably", "tokens": [ 50514, 309, 1542, 337, 721, 300, 366, 1391, 50664 ], "temperature": 0.0, "avg_logprob": -0.19549419280401495, "compression_ratio": 1.5075376884422111, "no_speech_prob": 0.00307464599609375, "words": [ { "start": 3630.98, "end": 3631.88, "word": " it", "probability": 0.29150390625 }, { "start": 3631.88, "end": 3632.08, "word": " looks", "probability": 0.80078125 }, { "start": 3632.08, "end": 3632.24, "word": " for", "probability": 0.89697265625 }, { "start": 3632.24, "end": 3632.56, "word": " things", "probability": 0.73095703125 }, { "start": 3632.56, "end": 3632.76, "word": " that", "probability": 0.88232421875 }, { "start": 3632.76, "end": 3632.86, "word": " are", "probability": 0.89404296875 }, { "start": 3632.86, "end": 3633.1, "word": " probably", "probability": 0.8974609375 } ] }, { "id": 1454, "seek": 359092, "start": 3633.1, "end": 3636.28, "text": " talking out to the internet, trying to take over your webcam,", "tokens": [ 50664, 1417, 484, 281, 264, 4705, 11, 1382, 281, 747, 670, 428, 39490, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.19549419280401495, "compression_ratio": 1.5075376884422111, "no_speech_prob": 0.00307464599609375, "words": [ { "start": 3633.1, "end": 3633.4, "word": " talking", "probability": 0.77880859375 }, { "start": 3633.4, "end": 3633.52, "word": " out", "probability": 0.75048828125 }, { "start": 3633.52, "end": 3633.64, "word": " to", "probability": 0.9072265625 }, { "start": 3633.64, "end": 3633.76, "word": " the", "probability": 0.81884765625 }, { "start": 3633.76, "end": 3634.02, "word": " internet", "probability": 0.64111328125 }, { "start": 3634.02, "end": 3634.18, "word": ",", "probability": 0.8955078125 }, { "start": 3634.18, "end": 3634.38, "word": " trying", "probability": 0.7861328125 }, { "start": 3634.38, "end": 3634.5, "word": " to", "probability": 0.90283203125 }, { "start": 3634.5, "end": 3634.66, "word": " take", "probability": 0.8095703125 }, { "start": 3634.66, "end": 3634.78, "word": " over", "probability": 0.873046875 }, { "start": 3634.78, "end": 3634.96, "word": " your", "probability": 0.79931640625 }, { "start": 3634.96, "end": 3635.38, "word": " webcam", "probability": 0.876953125 }, { "start": 3635.38, "end": 3636.28, "word": ",", "probability": 0.97607421875 } ] }, { "id": 1455, "seek": 359092, "start": 3636.28, "end": 3638.66, "text": " uploading and downloading files.", "tokens": [ 50814, 27301, 293, 32529, 7098, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.19549419280401495, "compression_ratio": 1.5075376884422111, "no_speech_prob": 0.00307464599609375, "words": [ { "start": 3636.28, "end": 3636.78, "word": " uploading", "probability": 0.68115234375 }, { "start": 3636.78, "end": 3636.98, "word": " and", "probability": 0.88525390625 }, { "start": 3636.98, "end": 3637.34, "word": " downloading", "probability": 0.79931640625 }, { "start": 3637.34, "end": 3638.04, "word": " files", "probability": 0.82666015625 }, { "start": 3638.04, "end": 3638.66, "word": ".", "probability": 0.86083984375 } ] }, { "id": 1456, "seek": 359092, "start": 3638.72, "end": 3640.82, "text": " Well, what else does that?", "tokens": [ 50964, 1042, 11, 437, 1646, 775, 300, 30, 51114 ], "temperature": 0.0, "avg_logprob": -0.19549419280401495, "compression_ratio": 1.5075376884422111, "no_speech_prob": 0.00307464599609375, "words": [ { "start": 3638.72, "end": 3638.98, "word": " Well", "probability": 0.7470703125 }, { "start": 3638.98, "end": 3639.12, "word": ",", "probability": 0.94970703125 }, { "start": 3639.12, "end": 3639.54, "word": " what", "probability": 0.88671875 }, { "start": 3639.54, "end": 3639.72, "word": " else", "probability": 0.85888671875 }, { "start": 3639.72, "end": 3639.92, "word": " does", "probability": 0.92822265625 }, { "start": 3639.92, "end": 3640.2, "word": " that", "probability": 0.8876953125 }, { "start": 3640.2, "end": 3640.82, "word": "?", "probability": 0.93310546875 } ] }, { "id": 1457, "seek": 359092, "start": 3641.4, "end": 3644.98, "text": " Chrome, Internet Explorer, Firefox.", "tokens": [ 51114, 15327, 11, 7703, 31895, 11, 46613, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.19549419280401495, "compression_ratio": 1.5075376884422111, "no_speech_prob": 0.00307464599609375, "words": [ { "start": 3641.4, "end": 3641.8, "word": " Chrome", "probability": 0.75048828125 }, { "start": 3641.8, "end": 3642.58, "word": ",", "probability": 0.9853515625 }, { "start": 3642.58, "end": 3642.8, "word": " Internet", "probability": 0.74560546875 }, { "start": 3642.8, "end": 3643.36, "word": " Explorer", "probability": 0.8603515625 }, { "start": 3643.36, "end": 3644.04, "word": ",", "probability": 0.99365234375 }, { "start": 3644.04, "end": 3644.36, "word": " Firefox", "probability": 0.84423828125 }, { "start": 3644.36, "end": 3644.98, "word": ".", "probability": 0.93896484375 } ] }, { "id": 1458, "seek": 359092, "start": 3645.76, "end": 3648.1, "text": " So when you're building", "tokens": [ 51264, 407, 562, 291, 434, 2390, 51414 ], "temperature": 0.0, "avg_logprob": -0.19549419280401495, "compression_ratio": 1.5075376884422111, "no_speech_prob": 0.00307464599609375, "words": [ { "start": 3645.76, "end": 3646.12, "word": " So", "probability": 0.89208984375 }, { "start": 3646.12, "end": 3647.42, "word": " when", "probability": 0.783203125 }, { "start": 3647.42, "end": 3647.74, "word": " you're", "probability": 0.92236328125 }, { "start": 3647.74, "end": 3648.1, "word": " building", "probability": 0.794921875 } ] }, { "id": 1459, "seek": 359092, "start": 3649.26, "end": 3650.72, "text": " an antivirus,", "tokens": [ 51414, 364, 2511, 592, 9619, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.19549419280401495, "compression_ratio": 1.5075376884422111, "no_speech_prob": 0.00307464599609375, "words": [ { "start": 3649.26, "end": 3649.88, "word": " an", "probability": 0.8408203125 }, { "start": 3649.88, "end": 3650.5, "word": " antivirus", "probability": 0.89501953125 }, { "start": 3650.5, "end": 3650.72, "word": ",", "probability": 0.89111328125 } ] }, { "id": 1460, "seek": 359092, "start": 3650.72, "end": 3653.94, "text": " it's better to have", "tokens": [ 51564, 309, 311, 1101, 281, 362, 51714 ], "temperature": 0.0, "avg_logprob": -0.19549419280401495, "compression_ratio": 1.5075376884422111, "no_speech_prob": 0.00307464599609375, "words": [ { "start": 3650.72, "end": 3651.12, "word": " it's", "probability": 0.949951171875 }, { "start": 3651.12, "end": 3651.92, "word": " better", "probability": 0.82421875 }, { "start": 3651.92, "end": 3653.06, "word": " to", "probability": 0.9013671875 }, { "start": 3653.06, "end": 3653.94, "word": " have", "probability": 0.880859375 } ] }, { "id": 1461, "seek": 361810, "start": 3653.94, "end": 3656.66, "text": " what they consider false negatives.", "tokens": [ 50364, 437, 436, 1949, 7908, 40019, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.19762732060971083, "compression_ratio": 1.7125506072874495, "no_speech_prob": 0.050323486328125, "words": [ { "start": 3653.94, "end": 3654.62, "word": " what", "probability": 0.038604736328125 }, { "start": 3654.62, "end": 3655.06, "word": " they", "probability": 0.7314453125 }, { "start": 3655.06, "end": 3655.38, "word": " consider", "probability": 0.8037109375 }, { "start": 3655.38, "end": 3655.7, "word": " false", "probability": 0.7021484375 }, { "start": 3655.7, "end": 3656.1, "word": " negatives", "probability": 0.81103515625 }, { "start": 3656.1, "end": 3656.66, "word": ".", "probability": 0.26318359375 } ] }, { "id": 1462, "seek": 361810, "start": 3657.48, "end": 3660.54, "text": " Which is positive is", "tokens": [ 50514, 3013, 307, 3353, 307, 50664 ], "temperature": 0.0, "avg_logprob": -0.19762732060971083, "compression_ratio": 1.7125506072874495, "no_speech_prob": 0.050323486328125, "words": [ { "start": 3657.48, "end": 3657.74, "word": " Which", "probability": 0.447265625 }, { "start": 3657.74, "end": 3658.14, "word": " is", "probability": 0.89453125 }, { "start": 3658.14, "end": 3660.02, "word": " positive", "probability": 0.44677734375 }, { "start": 3660.02, "end": 3660.54, "word": " is", "probability": 0.80029296875 } ] }, { "id": 1463, "seek": 361810, "start": 3660.54, "end": 3663.18, "text": " it is malware and negative is it is not malware.", "tokens": [ 50664, 309, 307, 40747, 293, 3671, 307, 309, 307, 406, 40747, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.19762732060971083, "compression_ratio": 1.7125506072874495, "no_speech_prob": 0.050323486328125, "words": [ { "start": 3660.54, "end": 3660.76, "word": " it", "probability": 0.67919921875 }, { "start": 3660.76, "end": 3660.92, "word": " is", "probability": 0.8974609375 }, { "start": 3660.92, "end": 3661.24, "word": " malware", "probability": 0.865234375 }, { "start": 3661.24, "end": 3661.5, "word": " and", "probability": 0.5849609375 }, { "start": 3661.5, "end": 3661.78, "word": " negative", "probability": 0.90576171875 }, { "start": 3661.78, "end": 3662.16, "word": " is", "probability": 0.86865234375 }, { "start": 3662.16, "end": 3662.38, "word": " it", "probability": 0.58740234375 }, { "start": 3662.38, "end": 3662.5, "word": " is", "probability": 0.78857421875 }, { "start": 3662.5, "end": 3662.7, "word": " not", "probability": 0.89453125 }, { "start": 3662.7, "end": 3663.0, "word": " malware", "probability": 0.8896484375 }, { "start": 3663.0, "end": 3663.18, "word": ".", "probability": 0.3193359375 } ] }, { "id": 1464, "seek": 361810, "start": 3663.18, "end": 3665.92, "text": " It's benign. So it's better to allow", "tokens": [ 50814, 467, 311, 3271, 788, 13, 407, 309, 311, 1101, 281, 2089, 50964 ], "temperature": 0.0, "avg_logprob": -0.19762732060971083, "compression_ratio": 1.7125506072874495, "no_speech_prob": 0.050323486328125, "words": [ { "start": 3663.18, "end": 3663.24, "word": " It's", "probability": 0.90087890625 }, { "start": 3663.24, "end": 3663.64, "word": " benign", "probability": 0.93408203125 }, { "start": 3663.64, "end": 3664.2, "word": ".", "probability": 0.92431640625 }, { "start": 3664.22, "end": 3664.5, "word": " So", "probability": 0.8603515625 }, { "start": 3664.5, "end": 3664.68, "word": " it's", "probability": 0.912353515625 }, { "start": 3664.68, "end": 3664.94, "word": " better", "probability": 0.826171875 }, { "start": 3664.94, "end": 3665.4, "word": " to", "probability": 0.90380859375 }, { "start": 3665.4, "end": 3665.92, "word": " allow", "probability": 0.8798828125 } ] }, { "id": 1465, "seek": 361810, "start": 3665.92, "end": 3669.0, "text": " some viruses to run instead of", "tokens": [ 50964, 512, 21785, 281, 1190, 2602, 295, 51114 ], "temperature": 0.0, "avg_logprob": -0.19762732060971083, "compression_ratio": 1.7125506072874495, "no_speech_prob": 0.050323486328125, "words": [ { "start": 3665.92, "end": 3666.38, "word": " some", "probability": 0.81005859375 }, { "start": 3666.38, "end": 3666.82, "word": " viruses", "probability": 0.763671875 }, { "start": 3666.82, "end": 3667.26, "word": " to", "probability": 0.9033203125 }, { "start": 3667.26, "end": 3667.72, "word": " run", "probability": 0.90869140625 }, { "start": 3667.72, "end": 3668.16, "word": " instead", "probability": 0.79345703125 }, { "start": 3668.16, "end": 3669.0, "word": " of", "probability": 0.9033203125 } ] }, { "id": 1466, "seek": 361810, "start": 3669.82, "end": 3671.56, "text": " blocking legitimate applications.", "tokens": [ 51114, 17776, 17956, 5821, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.19762732060971083, "compression_ratio": 1.7125506072874495, "no_speech_prob": 0.050323486328125, "words": [ { "start": 3669.82, "end": 3670.38, "word": " blocking", "probability": 0.7041015625 }, { "start": 3670.38, "end": 3670.94, "word": " legitimate", "probability": 0.76611328125 }, { "start": 3670.94, "end": 3671.56, "word": " applications", "probability": 0.76806640625 }, { "start": 3671.56, "end": 3671.56, "word": ".", "probability": 0.2117919921875 } ] }, { "id": 1467, "seek": 361810, "start": 3671.56, "end": 3674.14, "text": " Because you don't want to impact the user experience.", "tokens": [ 51264, 1436, 291, 500, 380, 528, 281, 2712, 264, 4195, 1752, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.19762732060971083, "compression_ratio": 1.7125506072874495, "no_speech_prob": 0.050323486328125, "words": [ { "start": 3671.56, "end": 3671.92, "word": " Because", "probability": 0.87744140625 }, { "start": 3671.92, "end": 3672.04, "word": " you", "probability": 0.89453125 }, { "start": 3672.04, "end": 3672.16, "word": " don't", "probability": 0.946044921875 }, { "start": 3672.16, "end": 3672.3, "word": " want", "probability": 0.736328125 }, { "start": 3672.3, "end": 3672.42, "word": " to", "probability": 0.861328125 }, { "start": 3672.42, "end": 3672.88, "word": " impact", "probability": 0.86279296875 }, { "start": 3672.88, "end": 3673.12, "word": " the", "probability": 0.80126953125 }, { "start": 3673.12, "end": 3673.38, "word": " user", "probability": 0.7939453125 }, { "start": 3673.38, "end": 3674.06, "word": " experience", "probability": 0.80908203125 }, { "start": 3674.06, "end": 3674.14, "word": ".", "probability": 0.7001953125 } ] }, { "id": 1468, "seek": 361810, "start": 3674.14, "end": 3677.98, "text": " Because if you impact the user experience, it's just going to uninstall your antivirus software.", "tokens": [ 51414, 1436, 498, 291, 2712, 264, 4195, 1752, 11, 309, 311, 445, 516, 281, 517, 40166, 428, 2511, 592, 9619, 4722, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.19762732060971083, "compression_ratio": 1.7125506072874495, "no_speech_prob": 0.050323486328125, "words": [ { "start": 3674.14, "end": 3674.38, "word": " Because", "probability": 0.87744140625 }, { "start": 3674.38, "end": 3674.5, "word": " if", "probability": 0.8603515625 }, { "start": 3674.5, "end": 3674.58, "word": " you", "probability": 0.89599609375 }, { "start": 3674.58, "end": 3674.94, "word": " impact", "probability": 0.86962890625 }, { "start": 3674.94, "end": 3675.06, "word": " the", "probability": 0.65771484375 }, { "start": 3675.06, "end": 3675.22, "word": " user", "probability": 0.81298828125 }, { "start": 3675.22, "end": 3675.62, "word": " experience", "probability": 0.7998046875 }, { "start": 3675.62, "end": 3675.68, "word": ",", "probability": 0.5302734375 }, { "start": 3675.68, "end": 3675.8, "word": " it's", "probability": 0.886474609375 }, { "start": 3675.8, "end": 3675.92, "word": " just", "probability": 0.8642578125 }, { "start": 3675.92, "end": 3676.02, "word": " going", "probability": 0.58056640625 }, { "start": 3676.02, "end": 3676.12, "word": " to", "probability": 0.89794921875 }, { "start": 3676.12, "end": 3676.56, "word": " uninstall", "probability": 0.87646484375 }, { "start": 3676.56, "end": 3676.84, "word": " your", "probability": 0.80029296875 }, { "start": 3676.84, "end": 3677.38, "word": " antivirus", "probability": 0.8504231770833334 }, { "start": 3677.38, "end": 3677.8, "word": " software", "probability": 0.84912109375 }, { "start": 3677.8, "end": 3677.98, "word": ".", "probability": 0.478759765625 } ] }, { "id": 1469, "seek": 361810, "start": 3677.98, "end": 3681.12, "text": " And that leaves them unprotected and that's bad business for you", "tokens": [ 51564, 400, 300, 5510, 552, 517, 33629, 39963, 293, 300, 311, 1578, 1606, 337, 291, 51714 ], "temperature": 0.0, "avg_logprob": -0.19762732060971083, "compression_ratio": 1.7125506072874495, "no_speech_prob": 0.050323486328125, "words": [ { "start": 3677.98, "end": 3678.04, "word": " And", "probability": 0.83984375 }, { "start": 3678.04, "end": 3678.18, "word": " that", "probability": 0.8681640625 }, { "start": 3678.18, "end": 3678.36, "word": " leaves", "probability": 0.7080078125 }, { "start": 3678.36, "end": 3678.64, "word": " them", "probability": 0.7392578125 }, { "start": 3678.64, "end": 3679.32, "word": " unprotected", "probability": 0.8868815104166666 }, { "start": 3679.32, "end": 3679.96, "word": " and", "probability": 0.387939453125 }, { "start": 3679.96, "end": 3680.2, "word": " that's", "probability": 0.936767578125 }, { "start": 3680.2, "end": 3680.4, "word": " bad", "probability": 0.8759765625 }, { "start": 3680.4, "end": 3680.74, "word": " business", "probability": 0.87158203125 }, { "start": 3680.74, "end": 3680.92, "word": " for", "probability": 0.89697265625 }, { "start": 3680.92, "end": 3681.12, "word": " you", "probability": 0.896484375 } ] }, { "id": 1470, "seek": 364458, "start": 3681.12, "end": 3683.32, "text": " when people are uninstalling your software.", "tokens": [ 50364, 562, 561, 366, 517, 13911, 24021, 428, 4722, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.1801549186054458, "compression_ratio": 1.7296296296296296, "no_speech_prob": 0.02227783203125, "words": [ { "start": 3681.12, "end": 3681.26, "word": " when", "probability": 0.468994140625 }, { "start": 3681.26, "end": 3681.48, "word": " people", "probability": 0.8857421875 }, { "start": 3681.48, "end": 3681.62, "word": " are", "probability": 0.88720703125 }, { "start": 3681.62, "end": 3682.22, "word": " uninstalling", "probability": 0.9200846354166666 }, { "start": 3682.22, "end": 3682.42, "word": " your", "probability": 0.8095703125 }, { "start": 3682.42, "end": 3682.86, "word": " software", "probability": 0.830078125 }, { "start": 3682.86, "end": 3683.32, "word": ".", "probability": 0.89111328125 } ] }, { "id": 1471, "seek": 364458, "start": 3684.96, "end": 3687.3, "text": " So even for us, we want to consider", "tokens": [ 50514, 407, 754, 337, 505, 11, 321, 528, 281, 1949, 50664 ], "temperature": 0.0, "avg_logprob": -0.1801549186054458, "compression_ratio": 1.7296296296296296, "no_speech_prob": 0.02227783203125, "words": [ { "start": 3684.96, "end": 3685.42, "word": " So", "probability": 0.52392578125 }, { "start": 3685.42, "end": 3685.88, "word": " even", "probability": 0.60498046875 }, { "start": 3685.88, "end": 3686.08, "word": " for", "probability": 0.90087890625 }, { "start": 3686.08, "end": 3686.38, "word": " us", "probability": 0.90380859375 }, { "start": 3686.38, "end": 3686.46, "word": ",", "probability": 0.63916015625 }, { "start": 3686.46, "end": 3686.58, "word": " we", "probability": 0.90771484375 }, { "start": 3686.58, "end": 3686.74, "word": " want", "probability": 0.74853515625 }, { "start": 3686.74, "end": 3686.84, "word": " to", "probability": 0.90625 }, { "start": 3686.84, "end": 3687.3, "word": " consider", "probability": 0.80224609375 } ] }, { "id": 1472, "seek": 364458, "start": 3687.3, "end": 3689.46, "text": " and weigh the factors of", "tokens": [ 50664, 293, 13843, 264, 6771, 295, 50814 ], "temperature": 0.0, "avg_logprob": -0.1801549186054458, "compression_ratio": 1.7296296296296296, "no_speech_prob": 0.02227783203125, "words": [ { "start": 3687.3, "end": 3687.92, "word": " and", "probability": 0.8505859375 }, { "start": 3687.92, "end": 3688.32, "word": " weigh", "probability": 0.8056640625 }, { "start": 3688.32, "end": 3688.5, "word": " the", "probability": 0.8095703125 }, { "start": 3688.5, "end": 3688.94, "word": " factors", "probability": 0.83544921875 }, { "start": 3688.94, "end": 3689.46, "word": " of", "probability": 0.8837890625 } ] }, { "id": 1473, "seek": 364458, "start": 3689.46, "end": 3692.14, "text": " is it better for us to allow some spam to get through", "tokens": [ 50814, 307, 309, 1101, 337, 505, 281, 2089, 512, 24028, 281, 483, 807, 50964 ], "temperature": 0.0, "avg_logprob": -0.1801549186054458, "compression_ratio": 1.7296296296296296, "no_speech_prob": 0.02227783203125, "words": [ { "start": 3689.46, "end": 3689.72, "word": " is", "probability": 0.42822265625 }, { "start": 3689.72, "end": 3689.86, "word": " it", "probability": 0.9052734375 }, { "start": 3689.86, "end": 3690.12, "word": " better", "probability": 0.8125 }, { "start": 3690.12, "end": 3690.34, "word": " for", "probability": 0.888671875 }, { "start": 3690.34, "end": 3690.5, "word": " us", "probability": 0.8984375 }, { "start": 3690.5, "end": 3690.66, "word": " to", "probability": 0.908203125 }, { "start": 3690.66, "end": 3690.88, "word": " allow", "probability": 0.87939453125 }, { "start": 3690.88, "end": 3691.18, "word": " some", "probability": 0.814453125 }, { "start": 3691.18, "end": 3691.52, "word": " spam", "probability": 0.91748046875 }, { "start": 3691.52, "end": 3691.66, "word": " to", "probability": 0.904296875 }, { "start": 3691.66, "end": 3691.82, "word": " get", "probability": 0.89990234375 }, { "start": 3691.82, "end": 3692.14, "word": " through", "probability": 0.80126953125 } ] }, { "id": 1474, "seek": 364458, "start": 3692.14, "end": 3695.0, "text": " as long as we're not blocking any of the legitimate emails?", "tokens": [ 50964, 382, 938, 382, 321, 434, 406, 17776, 604, 295, 264, 17956, 12524, 30, 51114 ], "temperature": 0.0, "avg_logprob": -0.1801549186054458, "compression_ratio": 1.7296296296296296, "no_speech_prob": 0.02227783203125, "words": [ { "start": 3692.14, "end": 3692.44, "word": " as", "probability": 0.7275390625 }, { "start": 3692.44, "end": 3692.62, "word": " long", "probability": 0.88525390625 }, { "start": 3692.62, "end": 3692.72, "word": " as", "probability": 0.89990234375 }, { "start": 3692.72, "end": 3692.82, "word": " we're", "probability": 0.914306640625 }, { "start": 3692.82, "end": 3692.98, "word": " not", "probability": 0.89599609375 }, { "start": 3692.98, "end": 3693.34, "word": " blocking", "probability": 0.73193359375 }, { "start": 3693.34, "end": 3693.66, "word": " any", "probability": 0.8330078125 }, { "start": 3693.66, "end": 3693.78, "word": " of", "probability": 0.89892578125 }, { "start": 3693.78, "end": 3693.9, "word": " the", "probability": 0.80859375 }, { "start": 3693.9, "end": 3694.18, "word": " legitimate", "probability": 0.5361328125 }, { "start": 3694.18, "end": 3694.74, "word": " emails", "probability": 0.75048828125 }, { "start": 3694.74, "end": 3695.0, "word": "?", "probability": 0.34228515625 } ] }, { "id": 1475, "seek": 364458, "start": 3695.0, "end": 3698.18, "text": " Or do we want to make sure that absolutely no spam gets through", "tokens": [ 51114, 1610, 360, 321, 528, 281, 652, 988, 300, 3122, 572, 24028, 2170, 807, 51264 ], "temperature": 0.0, "avg_logprob": -0.1801549186054458, "compression_ratio": 1.7296296296296296, "no_speech_prob": 0.02227783203125, "words": [ { "start": 3695.0, "end": 3695.4, "word": " Or", "probability": 0.8828125 }, { "start": 3695.4, "end": 3695.52, "word": " do", "probability": 0.900390625 }, { "start": 3695.52, "end": 3695.64, "word": " we", "probability": 0.90087890625 }, { "start": 3695.64, "end": 3695.76, "word": " want", "probability": 0.8037109375 }, { "start": 3695.76, "end": 3695.84, "word": " to", "probability": 0.90673828125 }, { "start": 3695.84, "end": 3696.0, "word": " make", "probability": 0.873046875 }, { "start": 3696.0, "end": 3696.24, "word": " sure", "probability": 0.818359375 }, { "start": 3696.24, "end": 3696.46, "word": " that", "probability": 0.876953125 }, { "start": 3696.46, "end": 3696.9, "word": " absolutely", "probability": 0.71923828125 }, { "start": 3696.9, "end": 3697.24, "word": " no", "probability": 0.8935546875 }, { "start": 3697.24, "end": 3697.58, "word": " spam", "probability": 0.93798828125 }, { "start": 3697.58, "end": 3697.88, "word": " gets", "probability": 0.80908203125 }, { "start": 3697.88, "end": 3698.18, "word": " through", "probability": 0.80517578125 } ] }, { "id": 1476, "seek": 364458, "start": 3698.18, "end": 3702.48, "text": " and if we block legitimate emails, well that's just collateral damage.", "tokens": [ 51264, 293, 498, 321, 3461, 17956, 12524, 11, 731, 300, 311, 445, 41875, 4344, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.1801549186054458, "compression_ratio": 1.7296296296296296, "no_speech_prob": 0.02227783203125, "words": [ { "start": 3698.18, "end": 3698.42, "word": " and", "probability": 0.473388671875 }, { "start": 3698.42, "end": 3698.56, "word": " if", "probability": 0.91015625 }, { "start": 3698.56, "end": 3698.68, "word": " we", "probability": 0.90087890625 }, { "start": 3698.68, "end": 3698.98, "word": " block", "probability": 0.71484375 }, { "start": 3698.98, "end": 3699.4, "word": " legitimate", "probability": 0.75537109375 }, { "start": 3699.4, "end": 3700.0, "word": " emails", "probability": 0.775390625 }, { "start": 3700.0, "end": 3700.34, "word": ",", "probability": 0.8447265625 }, { "start": 3700.34, "end": 3700.7, "word": " well", "probability": 0.84521484375 }, { "start": 3700.7, "end": 3700.98, "word": " that's", "probability": 0.7464599609375 }, { "start": 3700.98, "end": 3701.14, "word": " just", "probability": 0.89453125 }, { "start": 3701.14, "end": 3701.5, "word": " collateral", "probability": 0.85595703125 }, { "start": 3701.5, "end": 3702.02, "word": " damage", "probability": 0.76806640625 }, { "start": 3702.02, "end": 3702.48, "word": ".", "probability": 0.81640625 } ] }, { "id": 1477, "seek": 364458, "start": 3702.56, "end": 3704.52, "text": " So these are considerations that you need to make", "tokens": [ 51414, 407, 613, 366, 24070, 300, 291, 643, 281, 652, 51564 ], "temperature": 0.0, "avg_logprob": -0.1801549186054458, "compression_ratio": 1.7296296296296296, "no_speech_prob": 0.02227783203125, "words": [ { "start": 3702.56, "end": 3702.86, "word": " So", "probability": 0.8857421875 }, { "start": 3702.86, "end": 3703.02, "word": " these", "probability": 0.69677734375 }, { "start": 3703.02, "end": 3703.12, "word": " are", "probability": 0.888671875 }, { "start": 3703.12, "end": 3703.66, "word": " considerations", "probability": 0.86279296875 }, { "start": 3703.66, "end": 3703.92, "word": " that", "probability": 0.8671875 }, { "start": 3703.92, "end": 3704.0, "word": " you", "probability": 0.89697265625 }, { "start": 3704.0, "end": 3704.14, "word": " need", "probability": 0.8154296875 }, { "start": 3704.14, "end": 3704.26, "word": " to", "probability": 0.9091796875 }, { "start": 3704.26, "end": 3704.52, "word": " make", "probability": 0.8828125 } ] }, { "id": 1478, "seek": 364458, "start": 3704.52, "end": 3707.6, "text": " when you're building models like these and as a data scientist.", "tokens": [ 51564, 562, 291, 434, 2390, 5245, 411, 613, 293, 382, 257, 1412, 12662, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.1801549186054458, "compression_ratio": 1.7296296296296296, "no_speech_prob": 0.02227783203125, "words": [ { "start": 3704.52, "end": 3704.7, "word": " when", "probability": 0.87890625 }, { "start": 3704.7, "end": 3704.84, "word": " you're", "probability": 0.91845703125 }, { "start": 3704.84, "end": 3705.06, "word": " building", "probability": 0.80908203125 }, { "start": 3705.06, "end": 3705.4, "word": " models", "probability": 0.81591796875 }, { "start": 3705.4, "end": 3705.62, "word": " like", "probability": 0.87939453125 }, { "start": 3705.62, "end": 3705.96, "word": " these", "probability": 0.69140625 }, { "start": 3705.96, "end": 3706.12, "word": " and", "probability": 0.75244140625 }, { "start": 3706.12, "end": 3706.34, "word": " as", "probability": 0.90283203125 }, { "start": 3706.48, "end": 3706.7, "word": " a data", "probability": 0.82861328125 }, { "start": 3706.7, "end": 3707.14, "word": " scientist", "probability": 0.7421875 }, { "start": 3707.14, "end": 3707.6, "word": ".", "probability": 0.98486328125 } ] }, { "id": 1479, "seek": 367334, "start": 3709.18, "end": 3712.18, "text": " So for the multinomial naïve Bayesian", "tokens": [ 50414, 407, 337, 264, 45872, 47429, 1667, 15487, 303, 7840, 42434, 50564 ], "temperature": 0.0, "avg_logprob": -0.17817539589539652, "compression_ratio": 1.7530864197530864, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 3709.18, "end": 3709.74, "word": " So", "probability": 0.56640625 }, { "start": 3709.74, "end": 3710.3, "word": " for", "probability": 0.64794921875 }, { "start": 3710.3, "end": 3710.72, "word": " the", "probability": 0.80322265625 }, { "start": 3710.72, "end": 3711.46, "word": " multinomial", "probability": 0.91357421875 }, { "start": 3711.46, "end": 3711.84, "word": " naïve", "probability": 0.5569661458333334 }, { "start": 3711.84, "end": 3712.18, "word": " Bayesian", "probability": 0.90185546875 } ] }, { "id": 1480, "seek": 367334, "start": 3712.18, "end": 3715.36, "text": " with the count vectorizer, we have 94% accuracy.", "tokens": [ 50564, 365, 264, 1207, 8062, 6545, 11, 321, 362, 30849, 4, 14170, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.17817539589539652, "compression_ratio": 1.7530864197530864, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 3712.18, "end": 3712.34, "word": " with", "probability": 0.75 }, { "start": 3712.34, "end": 3712.46, "word": " the", "probability": 0.45263671875 }, { "start": 3712.46, "end": 3712.64, "word": " count", "probability": 0.73681640625 }, { "start": 3712.64, "end": 3713.12, "word": " vectorizer", "probability": 0.93115234375 }, { "start": 3713.12, "end": 3713.22, "word": ",", "probability": 0.521484375 }, { "start": 3713.22, "end": 3713.28, "word": " we", "probability": 0.88671875 }, { "start": 3713.28, "end": 3713.4, "word": " have", "probability": 0.88720703125 }, { "start": 3713.4, "end": 3713.9, "word": " 94", "probability": 0.85888671875 }, { "start": 3713.9, "end": 3714.32, "word": "%", "probability": 0.82958984375 }, { "start": 3714.32, "end": 3714.8, "word": " accuracy", "probability": 0.75048828125 }, { "start": 3714.8, "end": 3715.36, "word": ".", "probability": 0.9677734375 } ] }, { "id": 1481, "seek": 367334, "start": 3715.74, "end": 3718.64, "text": " So let's try a different model.", "tokens": [ 50714, 407, 718, 311, 853, 257, 819, 2316, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.17817539589539652, "compression_ratio": 1.7530864197530864, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 3715.74, "end": 3716.02, "word": " So", "probability": 0.75634765625 }, { "start": 3716.02, "end": 3716.38, "word": " let's", "probability": 0.924072265625 }, { "start": 3716.38, "end": 3716.66, "word": " try", "probability": 0.8125 }, { "start": 3717.12, "end": 3717.88, "word": " a different", "probability": 0.6943359375 }, { "start": 3717.88, "end": 3718.48, "word": " model", "probability": 0.81103515625 }, { "start": 3718.48, "end": 3718.64, "word": ".", "probability": 0.814453125 } ] }, { "id": 1482, "seek": 367334, "start": 3718.64, "end": 3720.84, "text": " This one we're going to use the logistic regression.", "tokens": [ 50864, 639, 472, 321, 434, 516, 281, 764, 264, 3565, 3142, 24590, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.17817539589539652, "compression_ratio": 1.7530864197530864, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 3718.64, "end": 3718.8, "word": " This", "probability": 0.7890625 }, { "start": 3718.8, "end": 3718.92, "word": " one", "probability": 0.8046875 }, { "start": 3718.92, "end": 3719.08, "word": " we're", "probability": 0.783935546875 }, { "start": 3719.08, "end": 3719.18, "word": " going", "probability": 0.69384765625 }, { "start": 3719.18, "end": 3719.18, "word": " to", "probability": 0.9052734375 }, { "start": 3719.18, "end": 3719.44, "word": " use", "probability": 0.82568359375 }, { "start": 3719.44, "end": 3719.68, "word": " the", "probability": 0.78125 }, { "start": 3719.68, "end": 3720.12, "word": " logistic", "probability": 0.943115234375 }, { "start": 3720.12, "end": 3720.56, "word": " regression", "probability": 0.8857421875 }, { "start": 3720.56, "end": 3720.84, "word": ".", "probability": 0.94970703125 } ] }, { "id": 1483, "seek": 367334, "start": 3721.12, "end": 3723.6, "text": " So if we look at the instructions, we're going to use the", "tokens": [ 51014, 407, 498, 321, 574, 412, 264, 9415, 11, 321, 434, 516, 281, 764, 264, 51164 ], "temperature": 0.0, "avg_logprob": -0.17817539589539652, "compression_ratio": 1.7530864197530864, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 3721.12, "end": 3721.34, "word": " So", "probability": 0.8310546875 }, { "start": 3721.34, "end": 3721.44, "word": " if", "probability": 0.88818359375 }, { "start": 3721.44, "end": 3721.52, "word": " we", "probability": 0.900390625 }, { "start": 3721.52, "end": 3721.66, "word": " look", "probability": 0.91650390625 }, { "start": 3721.66, "end": 3721.74, "word": " at", "probability": 0.90673828125 }, { "start": 3721.74, "end": 3721.86, "word": " the", "probability": 0.818359375 }, { "start": 3721.86, "end": 3722.3, "word": " instructions", "probability": 0.77197265625 }, { "start": 3722.3, "end": 3722.3, "word": ",", "probability": 0.7998046875 }, { "start": 3722.3, "end": 3722.7, "word": " we're", "probability": 0.92041015625 }, { "start": 3722.7, "end": 3722.9, "word": " going", "probability": 0.8583984375 }, { "start": 3722.9, "end": 3723.1, "word": " to", "probability": 0.90673828125 }, { "start": 3723.1, "end": 3723.4, "word": " use", "probability": 0.82421875 }, { "start": 3723.4, "end": 3723.6, "word": " the", "probability": 0.81494140625 } ] }, { "id": 1484, "seek": 367334, "start": 3723.6, "end": 3726.78, "text": " logistic regression constructor, but we're going to use this", "tokens": [ 51164, 3565, 3142, 24590, 47479, 11, 457, 321, 434, 516, 281, 764, 341, 51314 ], "temperature": 0.0, "avg_logprob": -0.17817539589539652, "compression_ratio": 1.7530864197530864, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 3723.6, "end": 3724.0, "word": " logistic", "probability": 0.936767578125 }, { "start": 3724.0, "end": 3724.38, "word": " regression", "probability": 0.8720703125 }, { "start": 3724.38, "end": 3725.08, "word": " constructor", "probability": 0.72705078125 }, { "start": 3725.08, "end": 3725.4, "word": ",", "probability": 0.6845703125 }, { "start": 3725.4, "end": 3725.88, "word": " but", "probability": 0.89453125 }, { "start": 3725.88, "end": 3726.06, "word": " we're", "probability": 0.929443359375 }, { "start": 3726.06, "end": 3726.14, "word": " going", "probability": 0.84130859375 }, { "start": 3726.14, "end": 3726.22, "word": " to", "probability": 0.90625 }, { "start": 3726.22, "end": 3726.48, "word": " use", "probability": 0.8173828125 }, { "start": 3726.48, "end": 3726.78, "word": " this", "probability": 0.8779296875 } ] }, { "id": 1485, "seek": 367334, "start": 3727.58, "end": 3729.58, "text": " LBFGS solver. And this is one of the", "tokens": [ 51314, 441, 33, 37, 24446, 1404, 331, 13, 400, 341, 307, 472, 295, 264, 51464 ], "temperature": 0.0, "avg_logprob": -0.17817539589539652, "compression_ratio": 1.7530864197530864, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 3727.58, "end": 3728.14, "word": " LBFGS", "probability": 0.81744384765625 }, { "start": 3728.14, "end": 3728.7, "word": " solver", "probability": 0.9130859375 }, { "start": 3728.7, "end": 3728.96, "word": ".", "probability": 0.6533203125 }, { "start": 3728.96, "end": 3729.04, "word": " And", "probability": 0.767578125 }, { "start": 3729.04, "end": 3729.18, "word": " this", "probability": 0.8818359375 }, { "start": 3729.18, "end": 3729.3, "word": " is", "probability": 0.90771484375 }, { "start": 3729.3, "end": 3729.42, "word": " one", "probability": 0.8232421875 }, { "start": 3729.42, "end": 3729.48, "word": " of", "probability": 0.9013671875 }, { "start": 3729.48, "end": 3729.58, "word": " the", "probability": 0.8134765625 } ] }, { "id": 1486, "seek": 367334, "start": 3729.58, "end": 3732.9, "text": " hyperparameters, or at least I would consider it a hyperparameter", "tokens": [ 51464, 9848, 2181, 335, 6202, 11, 420, 412, 1935, 286, 576, 1949, 309, 257, 9848, 2181, 335, 2398, 51614 ], "temperature": 0.0, "avg_logprob": -0.17817539589539652, "compression_ratio": 1.7530864197530864, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 3729.58, "end": 3730.5, "word": " hyperparameters", "probability": 0.8671875 }, { "start": 3730.5, "end": 3730.84, "word": ",", "probability": 0.70263671875 }, { "start": 3730.84, "end": 3731.12, "word": " or", "probability": 0.8984375 }, { "start": 3731.12, "end": 3731.24, "word": " at", "probability": 0.90625 }, { "start": 3731.24, "end": 3731.34, "word": " least", "probability": 0.85546875 }, { "start": 3731.34, "end": 3731.52, "word": " I", "probability": 0.9423828125 }, { "start": 3731.52, "end": 3731.66, "word": " would", "probability": 0.83642578125 }, { "start": 3731.66, "end": 3731.98, "word": " consider", "probability": 0.8154296875 }, { "start": 3731.98, "end": 3732.1, "word": " it", "probability": 0.85986328125 }, { "start": 3732.16, "end": 3732.9, "word": " a hyperparameter", "probability": 0.9656982421875 } ] }, { "id": 1487, "seek": 367334, "start": 3733.66, "end": 3736.36, "text": " for logistic regression itself.", "tokens": [ 51614, 337, 3565, 3142, 24590, 2564, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.17817539589539652, "compression_ratio": 1.7530864197530864, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 3733.66, "end": 3734.22, "word": " for", "probability": 0.54443359375 }, { "start": 3734.22, "end": 3734.72, "word": " logistic", "probability": 0.93408203125 }, { "start": 3734.72, "end": 3735.12, "word": " regression", "probability": 0.87109375 }, { "start": 3735.12, "end": 3735.8, "word": " itself", "probability": 0.75537109375 }, { "start": 3735.8, "end": 3736.36, "word": ".", "probability": 0.99560546875 } ] }, { "id": 1488, "seek": 369966, "start": 3736.98, "end": 3739.42, "text": " There's a couple different solvers that you can use", "tokens": [ 50364, 821, 311, 257, 1916, 819, 1404, 840, 300, 291, 393, 764, 50514 ], "temperature": 0.0, "avg_logprob": -0.17581917765071092, "compression_ratio": 1.5763546798029557, "no_speech_prob": 0.002471923828125, "words": [ { "start": 3736.98, "end": 3737.38, "word": " There's", "probability": 0.65673828125 }, { "start": 3737.64, "end": 3737.88, "word": " a couple", "probability": 0.79638671875 }, { "start": 3737.88, "end": 3738.26, "word": " different", "probability": 0.52294921875 }, { "start": 3738.26, "end": 3738.64, "word": " solvers", "probability": 0.921142578125 }, { "start": 3738.64, "end": 3738.86, "word": " that", "probability": 0.828125 }, { "start": 3738.86, "end": 3738.98, "word": " you", "probability": 0.89501953125 }, { "start": 3738.98, "end": 3739.12, "word": " can", "probability": 0.89306640625 }, { "start": 3739.12, "end": 3739.42, "word": " use", "probability": 0.82373046875 } ] }, { "id": 1489, "seek": 369966, "start": 3739.42, "end": 3742.02, "text": " but in this case we're going to use the LBFGS.", "tokens": [ 50514, 457, 294, 341, 1389, 321, 434, 516, 281, 764, 264, 441, 33, 37, 24446, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.17581917765071092, "compression_ratio": 1.5763546798029557, "no_speech_prob": 0.002471923828125, "words": [ { "start": 3739.42, "end": 3739.64, "word": " but", "probability": 0.2237548828125 }, { "start": 3739.64, "end": 3739.78, "word": " in", "probability": 0.8759765625 }, { "start": 3739.78, "end": 3739.94, "word": " this", "probability": 0.875 }, { "start": 3739.94, "end": 3740.12, "word": " case", "probability": 0.8203125 }, { "start": 3740.12, "end": 3740.28, "word": " we're", "probability": 0.810302734375 }, { "start": 3740.28, "end": 3740.38, "word": " going", "probability": 0.495849609375 }, { "start": 3740.38, "end": 3740.4, "word": " to", "probability": 0.90673828125 }, { "start": 3740.4, "end": 3740.58, "word": " use", "probability": 0.82861328125 }, { "start": 3740.58, "end": 3740.72, "word": " the", "probability": 0.787109375 }, { "start": 3740.72, "end": 3741.62, "word": " LBFGS", "probability": 0.7996826171875 }, { "start": 3741.62, "end": 3742.02, "word": ".", "probability": 0.85498046875 } ] }, { "id": 1490, "seek": 369966, "start": 3742.36, "end": 3743.54, "text": " So what this is going to look like is", "tokens": [ 50664, 407, 437, 341, 307, 516, 281, 574, 411, 307, 50814 ], "temperature": 0.0, "avg_logprob": -0.17581917765071092, "compression_ratio": 1.5763546798029557, "no_speech_prob": 0.002471923828125, "words": [ { "start": 3742.36, "end": 3742.42, "word": " So", "probability": 0.7216796875 }, { "start": 3742.42, "end": 3742.5, "word": " what", "probability": 0.5546875 }, { "start": 3742.5, "end": 3742.6, "word": " this", "probability": 0.86083984375 }, { "start": 3742.6, "end": 3742.68, "word": " is", "probability": 0.90283203125 }, { "start": 3742.68, "end": 3742.76, "word": " going", "probability": 0.7890625 }, { "start": 3742.76, "end": 3742.8, "word": " to", "probability": 0.90576171875 }, { "start": 3742.8, "end": 3742.94, "word": " look", "probability": 0.91845703125 }, { "start": 3742.94, "end": 3743.2, "word": " like", "probability": 0.87890625 }, { "start": 3743.2, "end": 3743.54, "word": " is", "probability": 0.89208984375 } ] }, { "id": 1491, "seek": 369966, "start": 3743.54, "end": 3746.7, "text": " LGS TF IDF equals", "tokens": [ 50814, 441, 24446, 40964, 7348, 37, 6915, 50964 ], "temperature": 0.0, "avg_logprob": -0.17581917765071092, "compression_ratio": 1.5763546798029557, "no_speech_prob": 0.002471923828125, "words": [ { "start": 3743.54, "end": 3744.18, "word": " LGS", "probability": 0.722412109375 }, { "start": 3744.18, "end": 3745.38, "word": " TF", "probability": 0.302490234375 }, { "start": 3745.38, "end": 3746.04, "word": " IDF", "probability": 0.838623046875 }, { "start": 3746.04, "end": 3746.7, "word": " equals", "probability": 0.74267578125 } ] }, { "id": 1492, "seek": 369966, "start": 3750.34, "end": 3751.14, "text": " logistic regression", "tokens": [ 50964, 3565, 3142, 24590, 51114 ], "temperature": 0.0, "avg_logprob": -0.17581917765071092, "compression_ratio": 1.5763546798029557, "no_speech_prob": 0.002471923828125, "words": [ { "start": 3750.34, "end": 3750.74, "word": " logistic", "probability": 0.832763671875 }, { "start": 3750.74, "end": 3751.14, "word": " regression", "probability": 0.87109375 } ] }, { "id": 1493, "seek": 369966, "start": 3751.72, "end": 3753.8, "text": " and then we're going to set our solver", "tokens": [ 51114, 293, 550, 321, 434, 516, 281, 992, 527, 1404, 331, 51264 ], "temperature": 0.0, "avg_logprob": -0.17581917765071092, "compression_ratio": 1.5763546798029557, "no_speech_prob": 0.002471923828125, "words": [ { "start": 3751.72, "end": 3752.12, "word": " and", "probability": 0.1368408203125 }, { "start": 3752.12, "end": 3752.18, "word": " then", "probability": 0.42919921875 }, { "start": 3752.18, "end": 3752.28, "word": " we're", "probability": 0.927490234375 }, { "start": 3752.28, "end": 3752.32, "word": " going", "probability": 0.79052734375 }, { "start": 3752.32, "end": 3752.38, "word": " to", "probability": 0.89990234375 }, { "start": 3752.38, "end": 3752.56, "word": " set", "probability": 0.900390625 }, { "start": 3752.56, "end": 3752.88, "word": " our", "probability": 0.82763671875 }, { "start": 3752.88, "end": 3753.8, "word": " solver", "probability": 0.897705078125 } ] }, { "id": 1494, "seek": 369966, "start": 3754.34, "end": 3756.14, "text": " equals LBFGS", "tokens": [ 51264, 6915, 441, 33, 37, 24446, 51414 ], "temperature": 0.0, "avg_logprob": -0.17581917765071092, "compression_ratio": 1.5763546798029557, "no_speech_prob": 0.002471923828125, "words": [ { "start": 3754.34, "end": 3754.54, "word": " equals", "probability": 0.8662109375 }, { "start": 3754.54, "end": 3756.14, "word": " LBFGS", "probability": 0.940185546875 } ] }, { "id": 1495, "seek": 369966, "start": 3757.94, "end": 3760.2, "text": " and then of course, just like we did with the multinomial", "tokens": [ 51414, 293, 550, 295, 1164, 11, 445, 411, 321, 630, 365, 264, 45872, 47429, 51564 ], "temperature": 0.0, "avg_logprob": -0.17581917765071092, "compression_ratio": 1.5763546798029557, "no_speech_prob": 0.002471923828125, "words": [ { "start": 3757.94, "end": 3758.34, "word": " and", "probability": 0.3798828125 }, { "start": 3758.34, "end": 3758.46, "word": " then", "probability": 0.73095703125 }, { "start": 3758.46, "end": 3758.62, "word": " of", "probability": 0.87744140625 }, { "start": 3758.62, "end": 3758.86, "word": " course", "probability": 0.86328125 }, { "start": 3758.86, "end": 3759.02, "word": ",", "probability": 0.09295654296875 }, { "start": 3759.02, "end": 3759.16, "word": " just", "probability": 0.88232421875 }, { "start": 3759.16, "end": 3759.32, "word": " like", "probability": 0.88037109375 }, { "start": 3759.32, "end": 3759.42, "word": " we", "probability": 0.896484375 }, { "start": 3759.42, "end": 3759.54, "word": " did", "probability": 0.896484375 }, { "start": 3759.54, "end": 3759.62, "word": " with", "probability": 0.81201171875 }, { "start": 3759.62, "end": 3759.72, "word": " the", "probability": 0.7880859375 }, { "start": 3759.72, "end": 3760.2, "word": " multinomial", "probability": 0.927978515625 } ] }, { "id": 1496, "seek": 369966, "start": 3760.2, "end": 3762.68, "text": " naïve Bayesian, we're going to fit", "tokens": [ 51564, 1667, 15487, 303, 7840, 42434, 11, 321, 434, 516, 281, 3318, 51714 ], "temperature": 0.0, "avg_logprob": -0.17581917765071092, "compression_ratio": 1.5763546798029557, "no_speech_prob": 0.002471923828125, "words": [ { "start": 3760.2, "end": 3760.56, "word": " naïve", "probability": 0.3769734700520833 }, { "start": 3760.56, "end": 3760.9, "word": " Bayesian", "probability": 0.85888671875 }, { "start": 3760.9, "end": 3761.16, "word": ",", "probability": 0.65380859375 }, { "start": 3761.16, "end": 3761.28, "word": " we're", "probability": 0.9267578125 }, { "start": 3761.28, "end": 3761.58, "word": " going", "probability": 0.853515625 }, { "start": 3761.58, "end": 3762.1, "word": " to", "probability": 0.89794921875 }, { "start": 3762.1, "end": 3762.68, "word": " fit", "probability": 0.85009765625 } ] }, { "id": 1497, "seek": 372566, "start": 3762.68, "end": 3766.0, "text": " our train, our classifier", "tokens": [ 50364, 527, 3847, 11, 527, 1508, 9902, 50514 ], "temperature": 0.0, "avg_logprob": -0.19631806281533573, "compression_ratio": 2.0174418604651163, "no_speech_prob": 0.02001953125, "words": [ { "start": 3762.68, "end": 3763.36, "word": " our", "probability": 0.5771484375 }, { "start": 3763.36, "end": 3764.08, "word": " train", "probability": 0.78173828125 }, { "start": 3764.08, "end": 3764.7, "word": ",", "probability": 0.7919921875 }, { "start": 3764.7, "end": 3765.34, "word": " our", "probability": 0.80615234375 }, { "start": 3765.34, "end": 3766.0, "word": " classifier", "probability": 0.958984375 } ] }, { "id": 1498, "seek": 372566, "start": 3766.0, "end": 3768.6, "text": " we're going to use the TF IDF", "tokens": [ 50514, 321, 434, 516, 281, 764, 264, 40964, 7348, 37, 50664 ], "temperature": 0.0, "avg_logprob": -0.19631806281533573, "compression_ratio": 2.0174418604651163, "no_speech_prob": 0.02001953125, "words": [ { "start": 3766.0, "end": 3766.22, "word": " we're", "probability": 0.524200439453125 }, { "start": 3766.22, "end": 3766.42, "word": " going", "probability": 0.8466796875 }, { "start": 3766.42, "end": 3766.58, "word": " to", "probability": 0.90625 }, { "start": 3766.58, "end": 3766.9, "word": " use", "probability": 0.8193359375 }, { "start": 3766.9, "end": 3767.12, "word": " the", "probability": 0.77099609375 }, { "start": 3767.12, "end": 3767.62, "word": " TF", "probability": 0.560546875 }, { "start": 3767.62, "end": 3768.6, "word": " IDF", "probability": 0.6025390625 } ] }, { "id": 1499, "seek": 372566, "start": 3769.26, "end": 3771.86, "text": " X, which is our test data, and then we're going to", "tokens": [ 50664, 1783, 11, 597, 307, 527, 1500, 1412, 11, 293, 550, 321, 434, 516, 281, 50814 ], "temperature": 0.0, "avg_logprob": -0.19631806281533573, "compression_ratio": 2.0174418604651163, "no_speech_prob": 0.02001953125, "words": [ { "start": 3769.26, "end": 3769.72, "word": " X", "probability": 0.66748046875 }, { "start": 3769.72, "end": 3769.9, "word": ",", "probability": 0.60205078125 }, { "start": 3769.9, "end": 3770.06, "word": " which", "probability": 0.91796875 }, { "start": 3770.06, "end": 3770.18, "word": " is", "probability": 0.908203125 }, { "start": 3770.18, "end": 3770.32, "word": " our", "probability": 0.81787109375 }, { "start": 3770.32, "end": 3770.74, "word": " test", "probability": 0.81982421875 }, { "start": 3770.74, "end": 3771.04, "word": " data", "probability": 0.82177734375 }, { "start": 3771.04, "end": 3771.2, "word": ",", "probability": 0.25048828125 }, { "start": 3771.2, "end": 3771.26, "word": " and", "probability": 0.87939453125 }, { "start": 3771.26, "end": 3771.38, "word": " then", "probability": 0.73193359375 }, { "start": 3771.38, "end": 3771.5, "word": " we're", "probability": 0.92724609375 }, { "start": 3771.5, "end": 3771.66, "word": " going", "probability": 0.85498046875 }, { "start": 3771.66, "end": 3771.86, "word": " to", "probability": 0.908203125 } ] }, { "id": 1500, "seek": 372566, "start": 3771.86, "end": 3774.58, "text": " use our training data, sorry, and then we're going to use", "tokens": [ 50814, 764, 527, 3097, 1412, 11, 2597, 11, 293, 550, 321, 434, 516, 281, 764, 50964 ], "temperature": 0.0, "avg_logprob": -0.19631806281533573, "compression_ratio": 2.0174418604651163, "no_speech_prob": 0.02001953125, "words": [ { "start": 3771.86, "end": 3772.18, "word": " use", "probability": 0.83447265625 }, { "start": 3772.18, "end": 3772.6, "word": " our", "probability": 0.7802734375 }, { "start": 3772.6, "end": 3773.14, "word": " training", "probability": 0.74853515625 }, { "start": 3773.14, "end": 3773.48, "word": " data", "probability": 0.81396484375 }, { "start": 3773.48, "end": 3773.64, "word": ",", "probability": 0.74072265625 }, { "start": 3773.64, "end": 3773.84, "word": " sorry", "probability": 0.6494140625 }, { "start": 3773.84, "end": 3773.96, "word": ",", "probability": 0.6484375 }, { "start": 3773.96, "end": 3774.06, "word": " and", "probability": 0.8857421875 }, { "start": 3774.06, "end": 3774.14, "word": " then", "probability": 0.6982421875 }, { "start": 3774.14, "end": 3774.28, "word": " we're", "probability": 0.9296875 }, { "start": 3774.28, "end": 3774.32, "word": " going", "probability": 0.31787109375 }, { "start": 3774.32, "end": 3774.36, "word": " to", "probability": 0.90869140625 }, { "start": 3774.36, "end": 3774.58, "word": " use", "probability": 0.830078125 } ] }, { "id": 1501, "seek": 372566, "start": 3774.58, "end": 3775.98, "text": " our labels.", "tokens": [ 50964, 527, 16949, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.19631806281533573, "compression_ratio": 2.0174418604651163, "no_speech_prob": 0.02001953125, "words": [ { "start": 3774.58, "end": 3774.86, "word": " our", "probability": 0.81787109375 }, { "start": 3774.86, "end": 3775.52, "word": " labels", "probability": 0.85693359375 }, { "start": 3775.52, "end": 3775.98, "word": ".", "probability": 0.99609375 } ] }, { "id": 1502, "seek": 372566, "start": 3777.62, "end": 3780.08, "text": " Next we're going to hop in and do the score predictions", "tokens": [ 51114, 3087, 321, 434, 516, 281, 3818, 294, 293, 360, 264, 6175, 21264, 51264 ], "temperature": 0.0, "avg_logprob": -0.19631806281533573, "compression_ratio": 2.0174418604651163, "no_speech_prob": 0.02001953125, "words": [ { "start": 3777.62, "end": 3778.08, "word": " Next", "probability": 0.88818359375 }, { "start": 3778.08, "end": 3778.26, "word": " we're", "probability": 0.6697998046875 }, { "start": 3778.26, "end": 3778.28, "word": " going", "probability": 0.68505859375 }, { "start": 3778.28, "end": 3778.36, "word": " to", "probability": 0.90625 }, { "start": 3778.36, "end": 3778.56, "word": " hop", "probability": 0.884765625 }, { "start": 3778.56, "end": 3778.78, "word": " in", "probability": 0.90625 }, { "start": 3778.78, "end": 3778.98, "word": " and", "probability": 0.87158203125 }, { "start": 3778.98, "end": 3779.14, "word": " do", "probability": 0.90087890625 }, { "start": 3779.14, "end": 3779.38, "word": " the", "probability": 0.7626953125 }, { "start": 3779.38, "end": 3779.64, "word": " score", "probability": 0.79150390625 }, { "start": 3779.64, "end": 3780.08, "word": " predictions", "probability": 0.71923828125 } ] }, { "id": 1503, "seek": 372566, "start": 3780.53, "end": 3783.78, "text": " classification matrix and, sorry, confusion matrix", "tokens": [ 51264, 21538, 8141, 293, 11, 2597, 11, 15075, 8141, 51414 ], "temperature": 0.0, "avg_logprob": -0.19631806281533573, "compression_ratio": 2.0174418604651163, "no_speech_prob": 0.02001953125, "words": [ { "start": 3780.53, "end": 3780.76, "word": " classification", "probability": 0.4111328125 }, { "start": 3780.76, "end": 3781.36, "word": " matrix", "probability": 0.859375 }, { "start": 3781.36, "end": 3781.8, "word": " and", "probability": 0.64404296875 }, { "start": 3781.8, "end": 3782.5, "word": ",", "probability": 0.353271484375 }, { "start": 3782.5, "end": 3782.98, "word": " sorry", "probability": 0.72412109375 }, { "start": 3782.98, "end": 3783.08, "word": ",", "probability": 0.84814453125 }, { "start": 3783.08, "end": 3783.46, "word": " confusion", "probability": 0.90869140625 }, { "start": 3783.46, "end": 3783.78, "word": " matrix", "probability": 0.8505859375 } ] }, { "id": 1504, "seek": 372566, "start": 3783.78, "end": 3785.64, "text": " and classification reports. We're going to use", "tokens": [ 51414, 293, 21538, 7122, 13, 492, 434, 516, 281, 764, 51564 ], "temperature": 0.0, "avg_logprob": -0.19631806281533573, "compression_ratio": 2.0174418604651163, "no_speech_prob": 0.02001953125, "words": [ { "start": 3783.78, "end": 3784.04, "word": " and", "probability": 0.84228515625 }, { "start": 3784.04, "end": 3784.52, "word": " classification", "probability": 0.92919921875 }, { "start": 3784.52, "end": 3785.04, "word": " reports", "probability": 0.430908203125 }, { "start": 3785.04, "end": 3785.26, "word": ".", "probability": 0.87548828125 }, { "start": 3785.26, "end": 3785.34, "word": " We're", "probability": 0.888671875 }, { "start": 3785.34, "end": 3785.4, "word": " going", "probability": 0.68408203125 }, { "start": 3785.4, "end": 3785.42, "word": " to", "probability": 0.90625 }, { "start": 3785.42, "end": 3785.64, "word": " use", "probability": 0.81103515625 } ] }, { "id": 1505, "seek": 372566, "start": 3786.36, "end": 3788.68, "text": " score LGS TF IDF", "tokens": [ 51564, 6175, 441, 24446, 40964, 7348, 37, 51714 ], "temperature": 0.0, "avg_logprob": -0.19631806281533573, "compression_ratio": 2.0174418604651163, "no_speech_prob": 0.02001953125, "words": [ { "start": 3786.36, "end": 3786.82, "word": " score", "probability": 0.6533203125 }, { "start": 3786.82, "end": 3787.28, "word": " LGS", "probability": 0.67626953125 }, { "start": 3787.28, "end": 3787.96, "word": " TF", "probability": 0.4560546875 }, { "start": 3787.96, "end": 3788.68, "word": " IDF", "probability": 0.872802734375 } ] }, { "id": 1506, "seek": 375260, "start": 3788.68, "end": 3793.0, "text": " LGS TF IDF.score", "tokens": [ 50364, 441, 24446, 40964, 7348, 37, 13, 4417, 418, 50514 ], "temperature": 0.0, "avg_logprob": -0.18821957668191508, "compression_ratio": 1.5873015873015872, "no_speech_prob": 0.0384521484375, "words": [ { "start": 3788.68, "end": 3790.62, "word": " LGS", "probability": 0.34820556640625 }, { "start": 3790.62, "end": 3791.32, "word": " TF", "probability": 0.146240234375 }, { "start": 3791.32, "end": 3791.98, "word": " IDF", "probability": 0.923095703125 }, { "start": 3791.98, "end": 3793.0, "word": ".score", "probability": 0.546142578125 } ] }, { "id": 1507, "seek": 375260, "start": 3793.0, "end": 3795.0, "text": " We're just going to look at our", "tokens": [ 50514, 492, 434, 445, 516, 281, 574, 412, 527, 50664 ], "temperature": 0.0, "avg_logprob": -0.18821957668191508, "compression_ratio": 1.5873015873015872, "no_speech_prob": 0.0384521484375, "words": [ { "start": 3793.0, "end": 3794.24, "word": " We're", "probability": 0.5633544921875 }, { "start": 3794.24, "end": 3794.34, "word": " just", "probability": 0.82763671875 }, { "start": 3794.34, "end": 3794.44, "word": " going", "probability": 0.461669921875 }, { "start": 3794.44, "end": 3794.5, "word": " to", "probability": 0.904296875 }, { "start": 3794.5, "end": 3794.64, "word": " look", "probability": 0.919921875 }, { "start": 3794.64, "end": 3794.8, "word": " at", "probability": 0.9130859375 }, { "start": 3794.8, "end": 3795.0, "word": " our", "probability": 0.81640625 } ] }, { "id": 1508, "seek": 375260, "start": 3795.0, "end": 3797.8, "text": " test TF IDF X and our", "tokens": [ 50664, 1500, 40964, 7348, 37, 1783, 293, 527, 50814 ], "temperature": 0.0, "avg_logprob": -0.18821957668191508, "compression_ratio": 1.5873015873015872, "no_speech_prob": 0.0384521484375, "words": [ { "start": 3795.0, "end": 3795.48, "word": " test", "probability": 0.7021484375 }, { "start": 3795.48, "end": 3795.96, "word": " TF", "probability": 0.5751953125 }, { "start": 3795.96, "end": 3796.5, "word": " IDF", "probability": 0.866943359375 }, { "start": 3796.5, "end": 3796.94, "word": " X", "probability": 0.7080078125 }, { "start": 3796.94, "end": 3797.46, "word": " and", "probability": 0.865234375 }, { "start": 3797.46, "end": 3797.8, "word": " our", "probability": 0.80517578125 } ] }, { "id": 1509, "seek": 375260, "start": 3797.8, "end": 3800.92, "text": " test labels. We're going to have our", "tokens": [ 50814, 1500, 16949, 13, 492, 434, 516, 281, 362, 527, 50964 ], "temperature": 0.0, "avg_logprob": -0.18821957668191508, "compression_ratio": 1.5873015873015872, "no_speech_prob": 0.0384521484375, "words": [ { "start": 3797.8, "end": 3798.5, "word": " test", "probability": 0.8017578125 }, { "start": 3798.5, "end": 3799.2, "word": " labels", "probability": 0.83056640625 }, { "start": 3799.2, "end": 3799.46, "word": ".", "probability": 0.4814453125 }, { "start": 3799.46, "end": 3800.24, "word": " We're", "probability": 0.80908203125 }, { "start": 3800.24, "end": 3800.24, "word": " going", "probability": 0.46826171875 }, { "start": 3800.24, "end": 3800.24, "word": " to", "probability": 0.89697265625 }, { "start": 3800.24, "end": 3800.46, "word": " have", "probability": 0.8837890625 }, { "start": 3800.46, "end": 3800.92, "word": " our", "probability": 0.80029296875 } ] }, { "id": 1510, "seek": 375260, "start": 3800.92, "end": 3802.06, "text": " predictions", "tokens": [ 50964, 21264, 51114 ], "temperature": 0.0, "avg_logprob": -0.18821957668191508, "compression_ratio": 1.5873015873015872, "no_speech_prob": 0.0384521484375, "words": [ { "start": 3800.92, "end": 3802.06, "word": " predictions", "probability": 0.69921875 } ] }, { "id": 1511, "seek": 375260, "start": 3803.27, "end": 3805.94, "text": " LGS TF IDF equals", "tokens": [ 51114, 441, 24446, 40964, 7348, 37, 6915, 51264 ], "temperature": 0.0, "avg_logprob": -0.18821957668191508, "compression_ratio": 1.5873015873015872, "no_speech_prob": 0.0384521484375, "words": [ { "start": 3803.27, "end": 3803.78, "word": " LGS", "probability": 0.6641845703125 }, { "start": 3803.78, "end": 3804.22, "word": " TF", "probability": 0.7294921875 }, { "start": 3804.22, "end": 3805.0, "word": " IDF", "probability": 0.919189453125 }, { "start": 3805.0, "end": 3805.94, "word": " equals", "probability": 0.78515625 } ] }, { "id": 1512, "seek": 375260, "start": 3806.68, "end": 3810.12, "text": " LGS TF IDF.predict", "tokens": [ 51264, 441, 24446, 40964, 7348, 37, 13, 79, 24945, 51414 ], "temperature": 0.0, "avg_logprob": -0.18821957668191508, "compression_ratio": 1.5873015873015872, "no_speech_prob": 0.0384521484375, "words": [ { "start": 3806.68, "end": 3807.36, "word": " LGS", "probability": 0.82568359375 }, { "start": 3807.36, "end": 3808.16, "word": " TF", "probability": 0.70458984375 }, { "start": 3808.16, "end": 3808.84, "word": " IDF", "probability": 0.92822265625 }, { "start": 3808.84, "end": 3810.12, "word": ".predict", "probability": 0.7478841145833334 } ] }, { "id": 1513, "seek": 375260, "start": 3812.92, "end": 3814.52, "text": " That's going to give us our", "tokens": [ 51414, 663, 311, 516, 281, 976, 505, 527, 51564 ], "temperature": 0.0, "avg_logprob": -0.18821957668191508, "compression_ratio": 1.5873015873015872, "no_speech_prob": 0.0384521484375, "words": [ { "start": 3812.92, "end": 3813.94, "word": " That's", "probability": 0.7607421875 }, { "start": 3813.94, "end": 3814.0, "word": " going", "probability": 0.75341796875 }, { "start": 3814.0, "end": 3814.06, "word": " to", "probability": 0.8994140625 }, { "start": 3814.06, "end": 3814.16, "word": " give", "probability": 0.8232421875 }, { "start": 3814.16, "end": 3814.3, "word": " us", "probability": 0.89892578125 }, { "start": 3814.3, "end": 3814.52, "word": " our", "probability": 0.8134765625 } ] }, { "id": 1514, "seek": 375260, "start": 3814.52, "end": 3815.62, "text": " raw predictions", "tokens": [ 51564, 8936, 21264, 51714 ], "temperature": 0.0, "avg_logprob": -0.18821957668191508, "compression_ratio": 1.5873015873015872, "no_speech_prob": 0.0384521484375, "words": [ { "start": 3814.52, "end": 3815.12, "word": " raw", "probability": 0.80078125 }, { "start": 3815.12, "end": 3815.62, "word": " predictions", "probability": 0.7763671875 } ] }, { "id": 1515, "seek": 377996, "start": 3815.62, "end": 3818.74, "text": " and then I'm going to", "tokens": [ 50364, 293, 550, 286, 478, 516, 281, 50514 ], "temperature": 0.0, "avg_logprob": -0.17552760436937406, "compression_ratio": 1.497142857142857, "no_speech_prob": 0.0780029296875, "words": [ { "start": 3815.62, "end": 3816.36, "word": " and", "probability": 0.24169921875 }, { "start": 3816.36, "end": 3817.24, "word": " then", "probability": 0.693359375 }, { "start": 3817.24, "end": 3818.46, "word": " I'm", "probability": 0.871826171875 }, { "start": 3818.46, "end": 3818.56, "word": " going", "probability": 0.26123046875 }, { "start": 3818.56, "end": 3818.74, "word": " to", "probability": 0.89990234375 } ] }, { "id": 1516, "seek": 377996, "start": 3818.74, "end": 3820.54, "text": " stop saying exactly what I'm typing", "tokens": [ 50514, 1590, 1566, 2293, 437, 286, 478, 18444, 50664 ], "temperature": 0.0, "avg_logprob": -0.17552760436937406, "compression_ratio": 1.497142857142857, "no_speech_prob": 0.0780029296875, "words": [ { "start": 3818.74, "end": 3819.18, "word": " stop", "probability": 0.822265625 }, { "start": 3819.18, "end": 3819.56, "word": " saying", "probability": 0.7646484375 }, { "start": 3819.56, "end": 3819.98, "word": " exactly", "probability": 0.7890625 }, { "start": 3819.98, "end": 3820.12, "word": " what", "probability": 0.88330078125 }, { "start": 3820.12, "end": 3820.22, "word": " I'm", "probability": 0.9873046875 }, { "start": 3820.22, "end": 3820.54, "word": " typing", "probability": 0.76513671875 } ] }, { "id": 1517, "seek": 377996, "start": 3822.18, "end": 3824.36, "text": " but we're going to do our confusion matrix", "tokens": [ 50664, 457, 321, 434, 516, 281, 360, 527, 15075, 8141, 50814 ], "temperature": 0.0, "avg_logprob": -0.17552760436937406, "compression_ratio": 1.497142857142857, "no_speech_prob": 0.0780029296875, "words": [ { "start": 3822.18, "end": 3822.82, "word": " but", "probability": 0.35009765625 }, { "start": 3822.82, "end": 3822.98, "word": " we're", "probability": 0.912841796875 }, { "start": 3822.98, "end": 3823.06, "word": " going", "probability": 0.73583984375 }, { "start": 3823.06, "end": 3823.1, "word": " to", "probability": 0.9052734375 }, { "start": 3823.1, "end": 3823.28, "word": " do", "probability": 0.8720703125 }, { "start": 3823.28, "end": 3823.56, "word": " our", "probability": 0.78955078125 }, { "start": 3823.56, "end": 3823.96, "word": " confusion", "probability": 0.68994140625 }, { "start": 3823.96, "end": 3824.36, "word": " matrix", "probability": 0.8359375 } ] }, { "id": 1518, "seek": 377996, "start": 3839.66, "end": 3840.86, "text": " and our", "tokens": [ 50814, 293, 527, 50964 ], "temperature": 0.0, "avg_logprob": -0.17552760436937406, "compression_ratio": 1.497142857142857, "no_speech_prob": 0.0780029296875, "words": [ { "start": 3839.66, "end": 3840.3, "word": " and", "probability": 0.84326171875 }, { "start": 3840.3, "end": 3840.86, "word": " our", "probability": 0.81591796875 } ] }, { "id": 1519, "seek": 377996, "start": 3841.7, "end": 3842.82, "text": " classification report", "tokens": [ 50964, 21538, 2275, 51114 ], "temperature": 0.0, "avg_logprob": -0.17552760436937406, "compression_ratio": 1.497142857142857, "no_speech_prob": 0.0780029296875, "words": [ { "start": 3841.7, "end": 3842.34, "word": " classification", "probability": 0.90087890625 }, { "start": 3842.34, "end": 3842.82, "word": " report", "probability": 0.76708984375 } ] }, { "id": 1520, "seek": 377996, "start": 3857.28, "end": 3859.38, "text": " Awesome. So I'm going to let this sit", "tokens": [ 51114, 10391, 13, 407, 286, 478, 516, 281, 718, 341, 1394, 51264 ], "temperature": 0.0, "avg_logprob": -0.17552760436937406, "compression_ratio": 1.497142857142857, "no_speech_prob": 0.0780029296875, "words": [ { "start": 3857.28, "end": 3857.92, "word": " Awesome", "probability": 0.19873046875 }, { "start": 3857.92, "end": 3858.54, "word": ".", "probability": 0.369384765625 }, { "start": 3858.54, "end": 3858.76, "word": " So", "probability": 0.8076171875 }, { "start": 3858.76, "end": 3858.86, "word": " I'm", "probability": 0.860595703125 }, { "start": 3858.86, "end": 3858.9, "word": " going", "probability": 0.689453125 }, { "start": 3858.9, "end": 3858.9, "word": " to", "probability": 0.8828125 }, { "start": 3858.9, "end": 3859.02, "word": " let", "probability": 0.82958984375 }, { "start": 3859.02, "end": 3859.18, "word": " this", "probability": 0.86474609375 }, { "start": 3859.18, "end": 3859.38, "word": " sit", "probability": 0.908203125 } ] }, { "id": 1521, "seek": 377996, "start": 3859.38, "end": 3862.24, "text": " here for a little bit, let you guys", "tokens": [ 51264, 510, 337, 257, 707, 857, 11, 718, 291, 1074, 51414 ], "temperature": 0.0, "avg_logprob": -0.17552760436937406, "compression_ratio": 1.497142857142857, "no_speech_prob": 0.0780029296875, "words": [ { "start": 3859.38, "end": 3859.72, "word": " here", "probability": 0.79931640625 }, { "start": 3859.72, "end": 3859.94, "word": " for", "probability": 0.8994140625 }, { "start": 3860.24, "end": 3860.54, "word": " a little", "probability": 0.80419921875 }, { "start": 3860.54, "end": 3860.88, "word": " bit", "probability": 0.90234375 }, { "start": 3860.88, "end": 3861.3, "word": ",", "probability": 0.270263671875 }, { "start": 3861.3, "end": 3861.7, "word": " let", "probability": 0.7900390625 }, { "start": 3861.7, "end": 3861.84, "word": " you", "probability": 0.89892578125 }, { "start": 3861.84, "end": 3862.24, "word": " guys", "probability": 0.88037109375 } ] }, { "id": 1522, "seek": 377996, "start": 3862.24, "end": 3864.56, "text": " kind of copy and follow along", "tokens": [ 51414, 733, 295, 5055, 293, 1524, 2051, 51564 ], "temperature": 0.0, "avg_logprob": -0.17552760436937406, "compression_ratio": 1.497142857142857, "no_speech_prob": 0.0780029296875, "words": [ { "start": 3862.24, "end": 3863.0, "word": " kind", "probability": 0.69384765625 }, { "start": 3863.0, "end": 3863.12, "word": " of", "probability": 0.90576171875 }, { "start": 3863.12, "end": 3863.52, "word": " copy", "probability": 0.81201171875 }, { "start": 3863.52, "end": 3863.84, "word": " and", "probability": 0.83984375 }, { "start": 3863.84, "end": 3864.16, "word": " follow", "probability": 0.87890625 }, { "start": 3864.16, "end": 3864.56, "word": " along", "probability": 0.90185546875 } ] }, { "id": 1523, "seek": 377996, "start": 3867.12, "end": 3868.38, "text": " Hopefully we don't run into", "tokens": [ 51564, 10429, 321, 500, 380, 1190, 666, 51714 ], "temperature": 0.0, "avg_logprob": -0.17552760436937406, "compression_ratio": 1.497142857142857, "no_speech_prob": 0.0780029296875, "words": [ { "start": 3867.12, "end": 3867.76, "word": " Hopefully", "probability": 0.313232421875 }, { "start": 3867.76, "end": 3867.94, "word": " we", "probability": 0.7412109375 }, { "start": 3867.94, "end": 3868.08, "word": " don't", "probability": 0.94677734375 }, { "start": 3868.08, "end": 3868.24, "word": " run", "probability": 0.900390625 }, { "start": 3868.24, "end": 3868.38, "word": " into", "probability": 0.72021484375 } ] }, { "id": 1524, "seek": 380608, "start": 3868.38, "end": 3871.06, "text": " the same problems that we did last time", "tokens": [ 50364, 264, 912, 2740, 300, 321, 630, 1036, 565, 50514 ], "temperature": 0.0, "avg_logprob": -0.23576388425297207, "compression_ratio": 1.7, "no_speech_prob": 0.14404296875, "words": [ { "start": 3868.38, "end": 3868.48, "word": " the", "probability": 0.232177734375 }, { "start": 3868.48, "end": 3868.8, "word": " same", "probability": 0.79736328125 }, { "start": 3868.8, "end": 3869.18, "word": " problems", "probability": 0.70068359375 }, { "start": 3869.18, "end": 3869.32, "word": " that", "probability": 0.85498046875 }, { "start": 3869.32, "end": 3869.42, "word": " we", "probability": 0.90380859375 }, { "start": 3869.42, "end": 3869.76, "word": " did", "probability": 0.89453125 }, { "start": 3869.76, "end": 3870.52, "word": " last", "probability": 0.79833984375 }, { "start": 3870.52, "end": 3871.06, "word": " time", "probability": 0.8134765625 } ] }, { "id": 1525, "seek": 380608, "start": 3873.74, "end": 3875.14, "text": " Bender is fantastic", "tokens": [ 50514, 363, 3216, 307, 5456, 50664 ], "temperature": 0.0, "avg_logprob": -0.23576388425297207, "compression_ratio": 1.7, "no_speech_prob": 0.14404296875, "words": [ { "start": 3873.74, "end": 3874.26, "word": " Bender", "probability": 0.4335975646972656 }, { "start": 3874.26, "end": 3874.66, "word": " is", "probability": 0.55029296875 }, { "start": 3874.66, "end": 3875.14, "word": " fantastic", "probability": 0.91259765625 } ] }, { "id": 1526, "seek": 380608, "start": 3875.14, "end": 3877.26, "text": " I love it, but it will time out after about", "tokens": [ 50664, 286, 959, 309, 11, 457, 309, 486, 565, 484, 934, 466, 50814 ], "temperature": 0.0, "avg_logprob": -0.23576388425297207, "compression_ratio": 1.7, "no_speech_prob": 0.14404296875, "words": [ { "start": 3875.14, "end": 3875.44, "word": " I", "probability": 0.1856689453125 }, { "start": 3875.44, "end": 3875.66, "word": " love", "probability": 0.8837890625 }, { "start": 3875.66, "end": 3875.84, "word": " it", "probability": 0.90478515625 }, { "start": 3875.84, "end": 3875.96, "word": ",", "probability": 0.27783203125 }, { "start": 3875.96, "end": 3876.06, "word": " but", "probability": 0.8955078125 }, { "start": 3876.06, "end": 3876.24, "word": " it", "probability": 0.89306640625 }, { "start": 3876.24, "end": 3876.38, "word": " will", "probability": 0.81640625 }, { "start": 3876.38, "end": 3876.64, "word": " time", "probability": 0.80908203125 }, { "start": 3876.64, "end": 3876.78, "word": " out", "probability": 0.401123046875 }, { "start": 3876.78, "end": 3877.04, "word": " after", "probability": 0.7412109375 }, { "start": 3877.04, "end": 3877.26, "word": " about", "probability": 0.7978515625 } ] }, { "id": 1527, "seek": 380608, "start": 3877.26, "end": 3880.44, "text": " five minutes and once it", "tokens": [ 50814, 1732, 2077, 293, 1564, 309, 50964 ], "temperature": 0.0, "avg_logprob": -0.23576388425297207, "compression_ratio": 1.7, "no_speech_prob": 0.14404296875, "words": [ { "start": 3877.26, "end": 3877.58, "word": " five", "probability": 0.6240234375 }, { "start": 3877.58, "end": 3878.04, "word": " minutes", "probability": 0.87109375 }, { "start": 3878.04, "end": 3879.24, "word": " and", "probability": 0.452880859375 }, { "start": 3879.24, "end": 3880.32, "word": " once", "probability": 0.69970703125 }, { "start": 3880.32, "end": 3880.44, "word": " it", "probability": 0.85498046875 } ] }, { "id": 1528, "seek": 380608, "start": 3880.44, "end": 3882.4, "text": " times out you've got to kind of restart the whole thing", "tokens": [ 50964, 1413, 484, 291, 600, 658, 281, 733, 295, 21022, 264, 1379, 551, 51114 ], "temperature": 0.0, "avg_logprob": -0.23576388425297207, "compression_ratio": 1.7, "no_speech_prob": 0.14404296875, "words": [ { "start": 3880.44, "end": 3880.66, "word": " times", "probability": 0.72607421875 }, { "start": 3880.66, "end": 3880.84, "word": " out", "probability": 0.8076171875 }, { "start": 3880.84, "end": 3881.08, "word": " you've", "probability": 0.38140869140625 }, { "start": 3881.08, "end": 3881.1, "word": " got", "probability": 0.7314453125 }, { "start": 3881.1, "end": 3881.2, "word": " to", "probability": 0.86669921875 }, { "start": 3881.2, "end": 3881.32, "word": " kind", "probability": 0.446533203125 }, { "start": 3881.32, "end": 3881.38, "word": " of", "probability": 0.89599609375 }, { "start": 3881.38, "end": 3881.66, "word": " restart", "probability": 0.85546875 }, { "start": 3881.66, "end": 3881.86, "word": " the", "probability": 0.8076171875 }, { "start": 3881.86, "end": 3882.02, "word": " whole", "probability": 0.8134765625 }, { "start": 3882.02, "end": 3882.4, "word": " thing", "probability": 0.8232421875 } ] }, { "id": 1529, "seek": 380608, "start": 3883.44, "end": 3885.3, "text": " or at least you've got to restart the notebook", "tokens": [ 51114, 420, 412, 1935, 291, 600, 658, 281, 21022, 264, 21060, 51264 ], "temperature": 0.0, "avg_logprob": -0.23576388425297207, "compression_ratio": 1.7, "no_speech_prob": 0.14404296875, "words": [ { "start": 3883.44, "end": 3883.96, "word": " or", "probability": 0.59326171875 }, { "start": 3883.96, "end": 3884.08, "word": " at", "probability": 0.89599609375 }, { "start": 3884.08, "end": 3884.18, "word": " least", "probability": 0.8583984375 }, { "start": 3884.18, "end": 3884.4, "word": " you've", "probability": 0.851318359375 }, { "start": 3884.4, "end": 3884.48, "word": " got", "probability": 0.8779296875 }, { "start": 3884.48, "end": 3884.56, "word": " to", "probability": 0.89306640625 }, { "start": 3884.56, "end": 3884.82, "word": " restart", "probability": 0.8310546875 }, { "start": 3884.82, "end": 3885.0, "word": " the", "probability": 0.802734375 }, { "start": 3885.0, "end": 3885.3, "word": " notebook", "probability": 0.74658203125 } ] }, { "id": 1530, "seek": 380608, "start": 3885.3, "end": 3887.16, "text": " which is kind of annoying", "tokens": [ 51264, 597, 307, 733, 295, 11304, 51414 ], "temperature": 0.0, "avg_logprob": -0.23576388425297207, "compression_ratio": 1.7, "no_speech_prob": 0.14404296875, "words": [ { "start": 3885.3, "end": 3885.9, "word": " which", "probability": 0.57958984375 }, { "start": 3885.9, "end": 3886.14, "word": " is", "probability": 0.90478515625 }, { "start": 3886.14, "end": 3886.74, "word": " kind", "probability": 0.83203125 }, { "start": 3886.74, "end": 3886.84, "word": " of", "probability": 0.9091796875 }, { "start": 3886.84, "end": 3887.16, "word": " annoying", "probability": 0.75146484375 } ] }, { "id": 1531, "seek": 380608, "start": 3888.4, "end": 3891.22, "text": " Another thing you will notice is the logistic regression", "tokens": [ 51414, 3996, 551, 291, 486, 3449, 307, 264, 3565, 3142, 24590, 51564 ], "temperature": 0.0, "avg_logprob": -0.23576388425297207, "compression_ratio": 1.7, "no_speech_prob": 0.14404296875, "words": [ { "start": 3888.4, "end": 3888.92, "word": " Another", "probability": 0.1556396484375 }, { "start": 3888.92, "end": 3889.12, "word": " thing", "probability": 0.81884765625 }, { "start": 3889.12, "end": 3889.22, "word": " you", "probability": 0.513671875 }, { "start": 3889.22, "end": 3889.3, "word": " will", "probability": 0.705078125 }, { "start": 3889.3, "end": 3889.66, "word": " notice", "probability": 0.853515625 }, { "start": 3889.66, "end": 3890.1, "word": " is", "probability": 0.89697265625 }, { "start": 3890.1, "end": 3890.38, "word": " the", "probability": 0.77587890625 }, { "start": 3890.38, "end": 3890.8, "word": " logistic", "probability": 0.8974609375 }, { "start": 3890.8, "end": 3891.22, "word": " regression", "probability": 0.90625 } ] }, { "id": 1532, "seek": 380608, "start": 3892.02, "end": 3894.5, "text": " will take a little longer", "tokens": [ 51564, 486, 747, 257, 707, 2854, 51714 ], "temperature": 0.0, "avg_logprob": -0.23576388425297207, "compression_ratio": 1.7, "no_speech_prob": 0.14404296875, "words": [ { "start": 3892.02, "end": 3892.54, "word": " will", "probability": 0.224853515625 }, { "start": 3892.54, "end": 3892.9, "word": " take", "probability": 0.82275390625 }, { "start": 3893.52, "end": 3893.92, "word": " a little", "probability": 0.81396484375 }, { "start": 3893.92, "end": 3894.5, "word": " longer", "probability": 0.8408203125 } ] }, { "id": 1533, "seek": 383290, "start": 3896.06, "end": 3899.28, "text": " to train and give us our predictions", "tokens": [ 50364, 281, 3847, 293, 976, 505, 527, 21264, 50514 ], "temperature": 0.0, "avg_logprob": -0.20399306217829385, "compression_ratio": 1.6901408450704225, "no_speech_prob": 0.07696533203125, "words": [ { "start": 3896.06, "end": 3896.52, "word": " to", "probability": 0.57666015625 }, { "start": 3896.52, "end": 3896.98, "word": " train", "probability": 0.8056640625 }, { "start": 3896.98, "end": 3897.7, "word": " and", "probability": 0.87841796875 }, { "start": 3897.7, "end": 3898.48, "word": " give", "probability": 0.8291015625 }, { "start": 3898.48, "end": 3898.64, "word": " us", "probability": 0.90380859375 }, { "start": 3898.64, "end": 3898.88, "word": " our", "probability": 0.80908203125 }, { "start": 3898.88, "end": 3899.28, "word": " predictions", "probability": 0.69580078125 } ] }, { "id": 1534, "seek": 383290, "start": 3899.28, "end": 3901.76, "text": " and it's just the way that logistic regression operates", "tokens": [ 50514, 293, 309, 311, 445, 264, 636, 300, 3565, 3142, 24590, 22577, 50664 ], "temperature": 0.0, "avg_logprob": -0.20399306217829385, "compression_ratio": 1.6901408450704225, "no_speech_prob": 0.07696533203125, "words": [ { "start": 3899.28, "end": 3899.54, "word": " and", "probability": 0.17578125 }, { "start": 3899.54, "end": 3899.7, "word": " it's", "probability": 0.936279296875 }, { "start": 3899.7, "end": 3899.86, "word": " just", "probability": 0.88623046875 }, { "start": 3899.86, "end": 3900.0, "word": " the", "probability": 0.79541015625 }, { "start": 3900.0, "end": 3900.18, "word": " way", "probability": 0.89306640625 }, { "start": 3900.18, "end": 3900.36, "word": " that", "probability": 0.84619140625 }, { "start": 3900.36, "end": 3900.72, "word": " logistic", "probability": 0.870361328125 }, { "start": 3900.72, "end": 3901.16, "word": " regression", "probability": 0.89111328125 }, { "start": 3901.16, "end": 3901.76, "word": " operates", "probability": 0.7568359375 } ] }, { "id": 1535, "seek": 383290, "start": 3901.76, "end": 3903.14, "text": " it does a little bit more mathematical", "tokens": [ 50664, 309, 775, 257, 707, 857, 544, 18894, 50814 ], "temperature": 0.0, "avg_logprob": -0.20399306217829385, "compression_ratio": 1.6901408450704225, "no_speech_prob": 0.07696533203125, "words": [ { "start": 3901.76, "end": 3901.9, "word": " it", "probability": 0.2117919921875 }, { "start": 3901.9, "end": 3902.06, "word": " does", "probability": 0.91455078125 }, { "start": 3902.22, "end": 3902.32, "word": " a little", "probability": 0.802734375 }, { "start": 3902.32, "end": 3902.46, "word": " bit", "probability": 0.86279296875 }, { "start": 3902.46, "end": 3902.66, "word": " more", "probability": 0.88232421875 }, { "start": 3902.66, "end": 3903.14, "word": " mathematical", "probability": 0.75341796875 } ] }, { "id": 1536, "seek": 383290, "start": 3904.24, "end": 3906.22, "text": " or complicated mathematical formulas", "tokens": [ 50814, 420, 6179, 18894, 30546, 50964 ], "temperature": 0.0, "avg_logprob": -0.20399306217829385, "compression_ratio": 1.6901408450704225, "no_speech_prob": 0.07696533203125, "words": [ { "start": 3904.24, "end": 3904.7, "word": " or", "probability": 0.7734375 }, { "start": 3904.7, "end": 3905.16, "word": " complicated", "probability": 0.7431640625 }, { "start": 3905.16, "end": 3905.7, "word": " mathematical", "probability": 0.76806640625 }, { "start": 3905.7, "end": 3906.22, "word": " formulas", "probability": 0.87158203125 } ] }, { "id": 1537, "seek": 383290, "start": 3907.0, "end": 3908.92, "text": " than the multinomial Naive Bayesian", "tokens": [ 50964, 813, 264, 45872, 47429, 6056, 488, 7840, 42434, 51114 ], "temperature": 0.0, "avg_logprob": -0.20399306217829385, "compression_ratio": 1.6901408450704225, "no_speech_prob": 0.07696533203125, "words": [ { "start": 3907.0, "end": 3907.46, "word": " than", "probability": 0.81298828125 }, { "start": 3907.46, "end": 3907.64, "word": " the", "probability": 0.8095703125 }, { "start": 3907.64, "end": 3908.18, "word": " multinomial", "probability": 0.931640625 }, { "start": 3908.18, "end": 3908.52, "word": " Naive", "probability": 0.5380859375 }, { "start": 3908.52, "end": 3908.92, "word": " Bayesian", "probability": 0.856201171875 } ] }, { "id": 1538, "seek": 383290, "start": 3910.08, "end": 3912.22, "text": " so it just takes a little bit longer to train", "tokens": [ 51114, 370, 309, 445, 2516, 257, 707, 857, 2854, 281, 3847, 51264 ], "temperature": 0.0, "avg_logprob": -0.20399306217829385, "compression_ratio": 1.6901408450704225, "no_speech_prob": 0.07696533203125, "words": [ { "start": 3910.08, "end": 3910.54, "word": " so", "probability": 0.2069091796875 }, { "start": 3910.54, "end": 3910.64, "word": " it", "probability": 0.89453125 }, { "start": 3910.64, "end": 3910.78, "word": " just", "probability": 0.87890625 }, { "start": 3910.78, "end": 3910.96, "word": " takes", "probability": 0.7548828125 }, { "start": 3911.16, "end": 3911.34, "word": " a little", "probability": 0.8115234375 }, { "start": 3911.34, "end": 3911.5, "word": " bit", "probability": 0.8857421875 }, { "start": 3911.5, "end": 3911.72, "word": " longer", "probability": 0.8359375 }, { "start": 3911.72, "end": 3911.88, "word": " to", "probability": 0.89990234375 }, { "start": 3911.88, "end": 3912.22, "word": " train", "probability": 0.79345703125 } ] }, { "id": 1539, "seek": 383290, "start": 3912.22, "end": 3915.14, "text": " but not too much longer, so that's good", "tokens": [ 51264, 457, 406, 886, 709, 2854, 11, 370, 300, 311, 665, 51414 ], "temperature": 0.0, "avg_logprob": -0.20399306217829385, "compression_ratio": 1.6901408450704225, "no_speech_prob": 0.07696533203125, "words": [ { "start": 3912.22, "end": 3913.06, "word": " but", "probability": 0.7421875 }, { "start": 3913.06, "end": 3913.74, "word": " not", "probability": 0.89306640625 }, { "start": 3913.74, "end": 3913.96, "word": " too", "probability": 0.79052734375 }, { "start": 3913.96, "end": 3914.18, "word": " much", "probability": 0.8251953125 }, { "start": 3914.18, "end": 3914.48, "word": " longer", "probability": 0.849609375 }, { "start": 3914.48, "end": 3914.62, "word": ",", "probability": 0.136962890625 }, { "start": 3914.62, "end": 3914.7, "word": " so", "probability": 0.8955078125 }, { "start": 3914.7, "end": 3914.92, "word": " that's", "probability": 0.93798828125 }, { "start": 3914.92, "end": 3915.14, "word": " good", "probability": 0.88330078125 } ] }, { "id": 1540, "seek": 383290, "start": 3917.36, "end": 3919.18, "text": " One of them is matrix multiplication", "tokens": [ 51414, 1485, 295, 552, 307, 8141, 27290, 51564 ], "temperature": 0.0, "avg_logprob": -0.20399306217829385, "compression_ratio": 1.6901408450704225, "no_speech_prob": 0.07696533203125, "words": [ { "start": 3917.36, "end": 3917.82, "word": " One", "probability": 0.0341796875 }, { "start": 3917.82, "end": 3917.98, "word": " of", "probability": 0.8759765625 }, { "start": 3917.98, "end": 3918.14, "word": " them", "probability": 0.72998046875 }, { "start": 3918.14, "end": 3918.28, "word": " is", "probability": 0.6455078125 }, { "start": 3918.28, "end": 3918.7, "word": " matrix", "probability": 0.56494140625 }, { "start": 3918.7, "end": 3919.18, "word": " multiplication", "probability": 0.779296875 } ] }, { "id": 1541, "seek": 383290, "start": 3919.18, "end": 3921.32, "text": " which is a whole array of floats", "tokens": [ 51564, 597, 307, 257, 1379, 10225, 295, 37878, 51714 ], "temperature": 0.0, "avg_logprob": -0.20399306217829385, "compression_ratio": 1.6901408450704225, "no_speech_prob": 0.07696533203125, "words": [ { "start": 3919.18, "end": 3919.64, "word": " which", "probability": 0.64453125 }, { "start": 3919.64, "end": 3919.8, "word": " is", "probability": 0.88916015625 }, { "start": 3920.14, "end": 3920.42, "word": " a whole", "probability": 0.775390625 }, { "start": 3920.42, "end": 3920.74, "word": " array", "probability": 0.75390625 }, { "start": 3920.74, "end": 3920.94, "word": " of", "probability": 0.90625 }, { "start": 3920.94, "end": 3921.32, "word": " floats", "probability": 0.87744140625 } ] }, { "id": 1542, "seek": 385868, "start": 3921.32, "end": 3923.5, "text": " that you have to process versus", "tokens": [ 50364, 300, 291, 362, 281, 1399, 5717, 50514 ], "temperature": 0.0, "avg_logprob": -0.23217146729047483, "compression_ratio": 1.553072625698324, "no_speech_prob": 0.1732177734375, "words": [ { "start": 3921.32, "end": 3922.08, "word": " that", "probability": 0.4189453125 }, { "start": 3922.08, "end": 3922.22, "word": " you", "probability": 0.89453125 }, { "start": 3922.22, "end": 3922.38, "word": " have", "probability": 0.8779296875 }, { "start": 3922.38, "end": 3922.5, "word": " to", "probability": 0.9033203125 }, { "start": 3922.5, "end": 3922.98, "word": " process", "probability": 0.86962890625 }, { "start": 3922.98, "end": 3923.5, "word": " versus", "probability": 0.5673828125 } ] }, { "id": 1543, "seek": 385868, "start": 3923.5, "end": 3927.08, "text": " Naive Bayes is literally counting and some logs", "tokens": [ 50514, 6056, 488, 7840, 279, 307, 3736, 13251, 293, 512, 20820, 50664 ], "temperature": 0.0, "avg_logprob": -0.23217146729047483, "compression_ratio": 1.553072625698324, "no_speech_prob": 0.1732177734375, "words": [ { "start": 3923.5, "end": 3924.3, "word": " Naive", "probability": 0.629638671875 }, { "start": 3924.3, "end": 3924.68, "word": " Bayes", "probability": 0.83837890625 }, { "start": 3924.68, "end": 3924.84, "word": " is", "probability": 0.6689453125 }, { "start": 3924.84, "end": 3925.16, "word": " literally", "probability": 0.76611328125 }, { "start": 3925.16, "end": 3925.7, "word": " counting", "probability": 0.771484375 }, { "start": 3925.7, "end": 3926.22, "word": " and", "probability": 0.8447265625 }, { "start": 3926.22, "end": 3926.62, "word": " some", "probability": 0.80712890625 }, { "start": 3926.62, "end": 3927.08, "word": " logs", "probability": 0.6650390625 } ] }, { "id": 1544, "seek": 385868, "start": 3928.6, "end": 3930.34, "text": " when you're doing the math correctly", "tokens": [ 50664, 562, 291, 434, 884, 264, 5221, 8944, 50814 ], "temperature": 0.0, "avg_logprob": -0.23217146729047483, "compression_ratio": 1.553072625698324, "no_speech_prob": 0.1732177734375, "words": [ { "start": 3928.6, "end": 3929.36, "word": " when", "probability": 0.492431640625 }, { "start": 3929.36, "end": 3929.48, "word": " you're", "probability": 0.90234375 }, { "start": 3929.48, "end": 3929.66, "word": " doing", "probability": 0.908203125 }, { "start": 3929.66, "end": 3929.8, "word": " the", "probability": 0.81201171875 }, { "start": 3929.8, "end": 3929.98, "word": " math", "probability": 0.87646484375 }, { "start": 3929.98, "end": 3930.34, "word": " correctly", "probability": 0.8466796875 } ] }, { "id": 1545, "seek": 385868, "start": 3930.34, "end": 3931.64, "text": " which is very quick", "tokens": [ 50814, 597, 307, 588, 1702, 50964 ], "temperature": 0.0, "avg_logprob": -0.23217146729047483, "compression_ratio": 1.553072625698324, "no_speech_prob": 0.1732177734375, "words": [ { "start": 3930.34, "end": 3930.96, "word": " which", "probability": 0.1298828125 }, { "start": 3930.96, "end": 3931.12, "word": " is", "probability": 0.89501953125 }, { "start": 3931.12, "end": 3931.32, "word": " very", "probability": 0.69873046875 }, { "start": 3931.32, "end": 3931.64, "word": " quick", "probability": 0.43017578125 } ] }, { "id": 1546, "seek": 385868, "start": 3931.64, "end": 3934.54, "text": " It's just counting", "tokens": [ 50964, 467, 311, 445, 13251, 51114 ], "temperature": 0.0, "avg_logprob": -0.23217146729047483, "compression_ratio": 1.553072625698324, "no_speech_prob": 0.1732177734375, "words": [ { "start": 3931.64, "end": 3932.64, "word": " It's", "probability": 0.48497676849365234 }, { "start": 3932.64, "end": 3932.82, "word": " just", "probability": 0.86669921875 }, { "start": 3932.82, "end": 3934.54, "word": " counting", "probability": 0.484619140625 } ] }, { "id": 1547, "seek": 385868, "start": 3934.54, "end": 3936.96, "text": " Yeah, it's just counting", "tokens": [ 51114, 865, 11, 309, 311, 445, 13251, 51264 ], "temperature": 0.0, "avg_logprob": -0.23217146729047483, "compression_ratio": 1.553072625698324, "no_speech_prob": 0.1732177734375, "words": [ { "start": 3934.54, "end": 3935.86, "word": " Yeah", "probability": 0.03125 }, { "start": 3935.86, "end": 3936.34, "word": ",", "probability": 0.7685546875 }, { "start": 3936.34, "end": 3936.44, "word": " it's", "probability": 0.9365234375 }, { "start": 3936.44, "end": 3936.6, "word": " just", "probability": 0.89013671875 }, { "start": 3936.6, "end": 3936.96, "word": " counting", "probability": 0.74072265625 } ] }, { "id": 1548, "seek": 385868, "start": 3936.96, "end": 3942.82, "text": " and logs, the latest x86 stuff", "tokens": [ 51264, 293, 20820, 11, 264, 6792, 2031, 22193, 1507, 51414 ], "temperature": 0.0, "avg_logprob": -0.23217146729047483, "compression_ratio": 1.553072625698324, "no_speech_prob": 0.1732177734375, "words": [ { "start": 3936.96, "end": 3937.94, "word": " and", "probability": 0.48046875 }, { "start": 3937.94, "end": 3938.52, "word": " logs", "probability": 0.73486328125 }, { "start": 3938.52, "end": 3939.2, "word": ",", "probability": 0.293701171875 }, { "start": 3939.2, "end": 3940.34, "word": " the", "probability": 0.22021484375 }, { "start": 3940.34, "end": 3941.8, "word": " latest", "probability": 0.85302734375 }, { "start": 3941.8, "end": 3942.4, "word": " x86", "probability": 0.96826171875 }, { "start": 3942.4, "end": 3942.82, "word": " stuff", "probability": 0.80029296875 } ] }, { "id": 1549, "seek": 385868, "start": 3942.82, "end": 3945.06, "text": " have built-in processes", "tokens": [ 51414, 362, 3094, 12, 259, 7555, 51564 ], "temperature": 0.0, "avg_logprob": -0.23217146729047483, "compression_ratio": 1.553072625698324, "no_speech_prob": 0.1732177734375, "words": [ { "start": 3942.82, "end": 3943.26, "word": " have", "probability": 0.68017578125 }, { "start": 3943.26, "end": 3943.82, "word": " built", "probability": 0.9150390625 }, { "start": 3943.82, "end": 3944.26, "word": "-in", "probability": 0.840087890625 }, { "start": 3944.26, "end": 3945.06, "word": " processes", "probability": 0.80419921875 } ] }, { "id": 1550, "seek": 385868, "start": 3945.06, "end": 3947.1, "text": " for doing integer logs and stuff like that", "tokens": [ 51564, 337, 884, 24922, 20820, 293, 1507, 411, 300, 51714 ], "temperature": 0.0, "avg_logprob": -0.23217146729047483, "compression_ratio": 1.553072625698324, "no_speech_prob": 0.1732177734375, "words": [ { "start": 3945.06, "end": 3945.4, "word": " for", "probability": 0.8212890625 }, { "start": 3945.4, "end": 3945.64, "word": " doing", "probability": 0.927734375 }, { "start": 3945.64, "end": 3946.0, "word": " integer", "probability": 0.7001953125 }, { "start": 3946.0, "end": 3946.38, "word": " logs", "probability": 0.73291015625 }, { "start": 3946.38, "end": 3946.52, "word": " and", "probability": 0.841796875 }, { "start": 3946.52, "end": 3946.72, "word": " stuff", "probability": 0.79248046875 }, { "start": 3946.72, "end": 3946.88, "word": " like", "probability": 0.87841796875 }, { "start": 3946.88, "end": 3947.1, "word": " that", "probability": 0.88232421875 } ] }, { "id": 1551, "seek": 388270, "start": 3947.1, "end": 3948.4, "text": " because it's so common", "tokens": [ 50364, 570, 309, 311, 370, 2689, 50514 ], "temperature": 0.0, "avg_logprob": -0.22425426288761877, "compression_ratio": 1.655813953488372, "no_speech_prob": 0.034088134765625, "words": [ { "start": 3947.1, "end": 3947.42, "word": " because", "probability": 0.68115234375 }, { "start": 3947.42, "end": 3947.88, "word": " it's", "probability": 0.92138671875 }, { "start": 3947.88, "end": 3948.06, "word": " so", "probability": 0.8837890625 }, { "start": 3948.06, "end": 3948.4, "word": " common", "probability": 0.72412109375 } ] }, { "id": 1552, "seek": 388270, "start": 3948.4, "end": 3951.82, "text": " to use logs for numerical accuracy", "tokens": [ 50514, 281, 764, 20820, 337, 29054, 14170, 50664 ], "temperature": 0.0, "avg_logprob": -0.22425426288761877, "compression_ratio": 1.655813953488372, "no_speech_prob": 0.034088134765625, "words": [ { "start": 3948.4, "end": 3948.9, "word": " to", "probability": 0.12115478515625 }, { "start": 3948.9, "end": 3950.54, "word": " use", "probability": 0.75732421875 }, { "start": 3950.54, "end": 3950.88, "word": " logs", "probability": 0.69140625 }, { "start": 3950.88, "end": 3951.04, "word": " for", "probability": 0.8662109375 }, { "start": 3951.04, "end": 3951.36, "word": " numerical", "probability": 0.86328125 }, { "start": 3951.36, "end": 3951.82, "word": " accuracy", "probability": 0.7392578125 } ] }, { "id": 1553, "seek": 388270, "start": 3951.82, "end": 3953.34, "text": " in machine learning", "tokens": [ 50664, 294, 3479, 2539, 50814 ], "temperature": 0.0, "avg_logprob": -0.22425426288761877, "compression_ratio": 1.655813953488372, "no_speech_prob": 0.034088134765625, "words": [ { "start": 3951.82, "end": 3952.22, "word": " in", "probability": 0.85107421875 }, { "start": 3952.22, "end": 3952.92, "word": " machine", "probability": 0.68408203125 }, { "start": 3952.92, "end": 3953.34, "word": " learning", "probability": 0.85400390625 } ] }, { "id": 1554, "seek": 388270, "start": 3954.72, "end": 3957.38, "text": " You'll also notice the same thing with neural networks", "tokens": [ 50814, 509, 603, 611, 3449, 264, 912, 551, 365, 18161, 9590, 50964 ], "temperature": 0.0, "avg_logprob": -0.22425426288761877, "compression_ratio": 1.655813953488372, "no_speech_prob": 0.034088134765625, "words": [ { "start": 3954.72, "end": 3955.26, "word": " You'll", "probability": 0.405731201171875 }, { "start": 3955.26, "end": 3955.44, "word": " also", "probability": 0.7978515625 }, { "start": 3955.44, "end": 3955.7, "word": " notice", "probability": 0.78125 }, { "start": 3955.7, "end": 3955.82, "word": " the", "probability": 0.7958984375 }, { "start": 3955.82, "end": 3955.98, "word": " same", "probability": 0.83251953125 }, { "start": 3955.98, "end": 3956.22, "word": " thing", "probability": 0.79248046875 }, { "start": 3956.22, "end": 3956.52, "word": " with", "probability": 0.81298828125 }, { "start": 3956.52, "end": 3957.08, "word": " neural", "probability": 0.88134765625 }, { "start": 3957.08, "end": 3957.38, "word": " networks", "probability": 0.66943359375 } ] }, { "id": 1555, "seek": 388270, "start": 3957.38, "end": 3959.64, "text": " because neural networks do a lot of matrix multiplication", "tokens": [ 50964, 570, 18161, 9590, 360, 257, 688, 295, 8141, 27290, 51114 ], "temperature": 0.0, "avg_logprob": -0.22425426288761877, "compression_ratio": 1.655813953488372, "no_speech_prob": 0.034088134765625, "words": [ { "start": 3957.38, "end": 3957.64, "word": " because", "probability": 0.59423828125 }, { "start": 3957.64, "end": 3957.86, "word": " neural", "probability": 0.9140625 }, { "start": 3957.86, "end": 3958.12, "word": " networks", "probability": 0.69580078125 }, { "start": 3958.12, "end": 3958.28, "word": " do", "probability": 0.900390625 }, { "start": 3958.4, "end": 3958.52, "word": " a lot", "probability": 0.89208984375 }, { "start": 3958.52, "end": 3958.7, "word": " of", "probability": 0.896484375 }, { "start": 3958.7, "end": 3959.06, "word": " matrix", "probability": 0.84521484375 }, { "start": 3959.06, "end": 3959.64, "word": " multiplication", "probability": 0.78369140625 } ] }, { "id": 1556, "seek": 388270, "start": 3960.84, "end": 3963.94, "text": " which is why GPUs work really well for neural networks", "tokens": [ 51114, 597, 307, 983, 18407, 82, 589, 534, 731, 337, 18161, 9590, 51264 ], "temperature": 0.0, "avg_logprob": -0.22425426288761877, "compression_ratio": 1.655813953488372, "no_speech_prob": 0.034088134765625, "words": [ { "start": 3960.84, "end": 3961.38, "word": " which", "probability": 0.39404296875 }, { "start": 3961.38, "end": 3961.92, "word": " is", "probability": 0.89990234375 }, { "start": 3961.92, "end": 3962.16, "word": " why", "probability": 0.8154296875 }, { "start": 3962.16, "end": 3962.7, "word": " GPUs", "probability": 0.904052734375 }, { "start": 3962.7, "end": 3962.88, "word": " work", "probability": 0.80029296875 }, { "start": 3962.88, "end": 3963.08, "word": " really", "probability": 0.759765625 }, { "start": 3963.08, "end": 3963.24, "word": " well", "probability": 0.87646484375 }, { "start": 3963.24, "end": 3963.4, "word": " for", "probability": 0.888671875 }, { "start": 3963.4, "end": 3963.58, "word": " neural", "probability": 0.8984375 }, { "start": 3963.58, "end": 3963.94, "word": " networks", "probability": 0.669921875 } ] }, { "id": 1557, "seek": 388270, "start": 3963.94, "end": 3968.1, "text": " because you can parallelize matrix multiplications like that", "tokens": [ 51264, 570, 291, 393, 8952, 1125, 8141, 17596, 763, 411, 300, 51414 ], "temperature": 0.0, "avg_logprob": -0.22425426288761877, "compression_ratio": 1.655813953488372, "no_speech_prob": 0.034088134765625, "words": [ { "start": 3963.94, "end": 3964.24, "word": " because", "probability": 0.751953125 }, { "start": 3964.24, "end": 3964.56, "word": " you", "probability": 0.89453125 }, { "start": 3964.56, "end": 3964.74, "word": " can", "probability": 0.9150390625 }, { "start": 3964.74, "end": 3966.5, "word": " parallelize", "probability": 0.8466796875 }, { "start": 3966.5, "end": 3966.88, "word": " matrix", "probability": 0.81005859375 }, { "start": 3966.88, "end": 3967.6, "word": " multiplications", "probability": 0.7900390625 }, { "start": 3967.6, "end": 3967.82, "word": " like", "probability": 0.83837890625 }, { "start": 3967.82, "end": 3968.1, "word": " that", "probability": 0.88037109375 } ] }, { "id": 1558, "seek": 388270, "start": 3968.78, "end": 3970.22, "text": " So I'm going to go ahead and run this", "tokens": [ 51414, 407, 286, 478, 516, 281, 352, 2286, 293, 1190, 341, 51564 ], "temperature": 0.0, "avg_logprob": -0.22425426288761877, "compression_ratio": 1.655813953488372, "no_speech_prob": 0.034088134765625, "words": [ { "start": 3968.78, "end": 3969.32, "word": " So", "probability": 0.2379150390625 }, { "start": 3969.32, "end": 3969.52, "word": " I'm", "probability": 0.88037109375 }, { "start": 3969.52, "end": 3969.56, "word": " going", "probability": 0.5390625 }, { "start": 3969.56, "end": 3969.58, "word": " to", "probability": 0.90087890625 }, { "start": 3969.58, "end": 3969.66, "word": " go", "probability": 0.87744140625 }, { "start": 3969.66, "end": 3969.78, "word": " ahead", "probability": 0.853515625 }, { "start": 3969.78, "end": 3969.86, "word": " and", "probability": 0.89501953125 }, { "start": 3969.86, "end": 3970.0, "word": " run", "probability": 0.892578125 }, { "start": 3970.0, "end": 3970.22, "word": " this", "probability": 0.88427734375 } ] }, { "id": 1559, "seek": 388270, "start": 3970.22, "end": 3971.12, "text": " Shift-Enter", "tokens": [ 51564, 28304, 12, 16257, 391, 51714 ], "temperature": 0.0, "avg_logprob": -0.22425426288761877, "compression_ratio": 1.655813953488372, "no_speech_prob": 0.034088134765625, "words": [ { "start": 3970.22, "end": 3970.66, "word": " Shift", "probability": 0.031707763671875 }, { "start": 3970.66, "end": 3971.12, "word": "-Enter", "probability": 0.6376953125 } ] }, { "id": 1560, "seek": 390558, "start": 3973.32, "end": 3977.22, "text": " And it looks like it's running. Hopefully it doesn't take too long.", "tokens": [ 50414, 400, 309, 1542, 411, 309, 311, 2614, 13, 10429, 309, 1177, 380, 747, 886, 938, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.32770271679839574, "compression_ratio": 1.5953757225433527, "no_speech_prob": 0.64013671875, "words": [ { "start": 3973.32, "end": 3973.86, "word": " And", "probability": 0.33935546875 }, { "start": 3973.86, "end": 3974.4, "word": " it", "probability": 0.156005859375 }, { "start": 3974.4, "end": 3974.52, "word": " looks", "probability": 0.7802734375 }, { "start": 3974.52, "end": 3974.62, "word": " like", "probability": 0.8720703125 }, { "start": 3974.62, "end": 3974.74, "word": " it's", "probability": 0.945068359375 }, { "start": 3974.74, "end": 3974.94, "word": " running", "probability": 0.873046875 }, { "start": 3974.94, "end": 3975.1, "word": ".", "probability": 0.59423828125 }, { "start": 3975.1, "end": 3975.28, "word": " Hopefully", "probability": 0.72265625 }, { "start": 3975.28, "end": 3975.38, "word": " it", "probability": 0.55908203125 }, { "start": 3975.38, "end": 3975.54, "word": " doesn't", "probability": 0.924072265625 }, { "start": 3975.54, "end": 3975.78, "word": " take", "probability": 0.82470703125 }, { "start": 3975.78, "end": 3976.28, "word": " too", "probability": 0.787109375 }, { "start": 3976.28, "end": 3976.68, "word": " long", "probability": 0.89404296875 }, { "start": 3976.68, "end": 3977.22, "word": ".", "probability": 0.904296875 } ] }, { "id": 1561, "seek": 390558, "start": 3979.26, "end": 3983.92, "text": " Another comparison to make is a neural network versus a gradient-boosted tree.", "tokens": [ 50714, 3996, 9660, 281, 652, 307, 257, 18161, 3209, 5717, 257, 16235, 12, 1763, 555, 292, 4230, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.32770271679839574, "compression_ratio": 1.5953757225433527, "no_speech_prob": 0.64013671875, "words": [ { "start": 3979.26, "end": 3979.8, "word": " Another", "probability": 0.361572265625 }, { "start": 3979.8, "end": 3980.34, "word": " comparison", "probability": 0.705078125 }, { "start": 3980.34, "end": 3980.6, "word": " to", "probability": 0.8955078125 }, { "start": 3980.6, "end": 3980.86, "word": " make", "probability": 0.87841796875 }, { "start": 3980.86, "end": 3981.08, "word": " is", "probability": 0.89892578125 }, { "start": 3981.54, "end": 3981.82, "word": " a neural", "probability": 0.845703125 }, { "start": 3981.82, "end": 3982.18, "word": " network", "probability": 0.82763671875 }, { "start": 3982.18, "end": 3982.5, "word": " versus", "probability": 0.77294921875 }, { "start": 3983.02, "end": 3983.28, "word": " a gradient", "probability": 0.6162109375 }, { "start": 3983.28, "end": 3983.62, "word": "-boosted", "probability": 0.72674560546875 }, { "start": 3983.62, "end": 3983.8, "word": " tree", "probability": 0.77197265625 }, { "start": 3983.8, "end": 3983.92, "word": ".", "probability": 0.88818359375 } ] }, { "id": 1562, "seek": 390558, "start": 3983.92, "end": 3988.58, "text": " A gradient-boosted tree is all just if-then statements.", "tokens": [ 50964, 316, 16235, 12, 1763, 555, 292, 4230, 307, 439, 445, 498, 12, 19096, 12363, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.32770271679839574, "compression_ratio": 1.5953757225433527, "no_speech_prob": 0.64013671875, "words": [ { "start": 3983.92, "end": 3984.0, "word": " A", "probability": 0.64990234375 }, { "start": 3984.0, "end": 3984.2, "word": " gradient", "probability": 0.81591796875 }, { "start": 3984.2, "end": 3984.5, "word": "-boosted", "probability": 0.956298828125 }, { "start": 3984.5, "end": 3984.68, "word": " tree", "probability": 0.76806640625 }, { "start": 3984.68, "end": 3984.86, "word": " is", "probability": 0.8896484375 }, { "start": 3984.86, "end": 3985.24, "word": " all", "probability": 0.89208984375 }, { "start": 3985.24, "end": 3985.58, "word": " just", "probability": 0.8642578125 }, { "start": 3985.58, "end": 3986.68, "word": " if", "probability": 0.245849609375 }, { "start": 3986.68, "end": 3987.58, "word": "-then", "probability": 0.74658203125 }, { "start": 3987.58, "end": 3988.04, "word": " statements", "probability": 0.70068359375 }, { "start": 3988.04, "end": 3988.58, "word": ".", "probability": 0.2396240234375 } ] }, { "id": 1563, "seek": 390558, "start": 3989.46, "end": 3994.0, "text": " Versus a neural network is a huge pain in the ass to multiply everything.", "tokens": [ 51264, 12226, 301, 257, 18161, 3209, 307, 257, 2603, 1822, 294, 264, 1256, 281, 12972, 1203, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.32770271679839574, "compression_ratio": 1.5953757225433527, "no_speech_prob": 0.64013671875, "words": [ { "start": 3989.46, "end": 3990.0, "word": " Versus", "probability": 0.890380859375 }, { "start": 3990.12, "end": 3990.24, "word": " a neural", "probability": 0.89306640625 }, { "start": 3990.24, "end": 3990.54, "word": " network", "probability": 0.8310546875 }, { "start": 3990.54, "end": 3990.72, "word": " is", "probability": 0.58251953125 }, { "start": 3990.86, "end": 3991.16, "word": " a huge", "probability": 0.7646484375 }, { "start": 3991.16, "end": 3992.28, "word": " pain", "probability": 0.53125 }, { "start": 3992.28, "end": 3992.46, "word": " in", "probability": 0.87158203125 }, { "start": 3992.46, "end": 3992.5, "word": " the", "probability": 0.81884765625 }, { "start": 3992.5, "end": 3992.62, "word": " ass", "probability": 0.76708984375 }, { "start": 3992.62, "end": 3992.76, "word": " to", "probability": 0.90087890625 }, { "start": 3992.76, "end": 3993.04, "word": " multiply", "probability": 0.76318359375 }, { "start": 3993.04, "end": 3993.46, "word": " everything", "probability": 0.896484375 }, { "start": 3993.46, "end": 3994.0, "word": ".", "probability": 0.98388671875 } ] }, { "id": 1564, "seek": 393476, "start": 3994.0, "end": 3999.22, "text": " So a GBT could be run in milliseconds", "tokens": [ 50414, 407, 257, 26809, 51, 727, 312, 1190, 294, 34184, 50614 ], "temperature": 0.0, "avg_logprob": -0.2679924218341558, "compression_ratio": 1.6345381526104417, "no_speech_prob": 0.051055908203125, "words": [ { "start": 3994.0, "end": 3994.98, "word": " So", "probability": 0.455078125 }, { "start": 3995.9, "end": 3996.3, "word": " a GBT", "probability": 0.818359375 }, { "start": 3996.3, "end": 3996.72, "word": " could", "probability": 0.79638671875 }, { "start": 3996.72, "end": 3997.14, "word": " be", "probability": 0.85986328125 }, { "start": 3997.14, "end": 3998.26, "word": " run", "probability": 0.609375 }, { "start": 3998.26, "end": 3998.5, "word": " in", "probability": 0.87646484375 }, { "start": 3998.5, "end": 3999.22, "word": " milliseconds", "probability": 0.389404296875 } ] }, { "id": 1565, "seek": 393476, "start": 3999.22, "end": 4003.06, "text": " versus a neural network taking seconds in 100% of your CPU.", "tokens": [ 50614, 5717, 257, 18161, 3209, 1940, 3949, 294, 2319, 4, 295, 428, 13199, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.2679924218341558, "compression_ratio": 1.6345381526104417, "no_speech_prob": 0.051055908203125, "words": [ { "start": 3999.22, "end": 3999.82, "word": " versus", "probability": 0.64794921875 }, { "start": 4000.04, "end": 4000.2, "word": " a neural", "probability": 0.8212890625 }, { "start": 4000.2, "end": 4000.48, "word": " network", "probability": 0.8125 }, { "start": 4000.48, "end": 4000.78, "word": " taking", "probability": 0.7841796875 }, { "start": 4000.78, "end": 4001.26, "word": " seconds", "probability": 0.63232421875 }, { "start": 4001.26, "end": 4001.42, "word": " in", "probability": 0.40673828125 }, { "start": 4001.42, "end": 4001.66, "word": " 100", "probability": 0.6865234375 }, { "start": 4001.66, "end": 4001.92, "word": "%", "probability": 0.92333984375 }, { "start": 4001.92, "end": 4002.04, "word": " of", "probability": 0.875 }, { "start": 4002.04, "end": 4002.18, "word": " your", "probability": 0.7734375 }, { "start": 4002.18, "end": 4002.5, "word": " CPU", "probability": 0.88916015625 }, { "start": 4002.5, "end": 4003.06, "word": ".", "probability": 0.9716796875 } ] }, { "id": 1566, "seek": 393476, "start": 4005.0, "end": 4008.12, "text": " Actually, speaking of neural networks, I'm kind of curious about this.", "tokens": [ 50914, 5135, 11, 4124, 295, 18161, 9590, 11, 286, 478, 733, 295, 6369, 466, 341, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.2679924218341558, "compression_ratio": 1.6345381526104417, "no_speech_prob": 0.051055908203125, "words": [ { "start": 4005.0, "end": 4005.56, "word": " Actually", "probability": 0.12744140625 }, { "start": 4005.56, "end": 4005.72, "word": ",", "probability": 0.72509765625 }, { "start": 4005.72, "end": 4005.92, "word": " speaking", "probability": 0.80126953125 }, { "start": 4005.92, "end": 4006.08, "word": " of", "probability": 0.8994140625 }, { "start": 4006.08, "end": 4006.24, "word": " neural", "probability": 0.865234375 }, { "start": 4006.24, "end": 4006.56, "word": " networks", "probability": 0.67626953125 }, { "start": 4006.56, "end": 4006.66, "word": ",", "probability": 0.9013671875 }, { "start": 4006.66, "end": 4006.76, "word": " I'm", "probability": 0.9873046875 }, { "start": 4006.76, "end": 4006.88, "word": " kind", "probability": 0.5146484375 }, { "start": 4006.88, "end": 4006.96, "word": " of", "probability": 0.90625 }, { "start": 4006.96, "end": 4007.26, "word": " curious", "probability": 0.7861328125 }, { "start": 4007.26, "end": 4007.54, "word": " about", "probability": 0.8125 }, { "start": 4007.54, "end": 4007.86, "word": " this", "probability": 0.7158203125 }, { "start": 4007.86, "end": 4008.12, "word": ".", "probability": 0.255859375 } ] }, { "id": 1567, "seek": 393476, "start": 4008.12, "end": 4010.44, "text": " How well this would be received at DEF CON.", "tokens": [ 51064, 1012, 731, 341, 576, 312, 4613, 412, 10113, 37, 16596, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.2679924218341558, "compression_ratio": 1.6345381526104417, "no_speech_prob": 0.051055908203125, "words": [ { "start": 4008.12, "end": 4008.6, "word": " How", "probability": 0.875 }, { "start": 4008.6, "end": 4008.88, "word": " well", "probability": 0.87646484375 }, { "start": 4008.88, "end": 4009.1, "word": " this", "probability": 0.8564453125 }, { "start": 4009.1, "end": 4009.2, "word": " would", "probability": 0.78662109375 }, { "start": 4009.2, "end": 4009.3, "word": " be", "probability": 0.90283203125 }, { "start": 4009.3, "end": 4009.64, "word": " received", "probability": 0.7568359375 }, { "start": 4009.64, "end": 4009.8, "word": " at", "probability": 0.849609375 }, { "start": 4009.8, "end": 4009.98, "word": " DEF", "probability": 0.664794921875 }, { "start": 4009.98, "end": 4010.26, "word": " CON", "probability": 0.884765625 }, { "start": 4010.26, "end": 4010.44, "word": ".", "probability": 0.5458984375 } ] }, { "id": 1568, "seek": 393476, "start": 4010.44, "end": 4014.22, "text": " Would anybody be interested? And please vote in the Discord channel.", "tokens": [ 51164, 6068, 4472, 312, 3102, 30, 400, 1767, 4740, 294, 264, 32623, 2269, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.2679924218341558, "compression_ratio": 1.6345381526104417, "no_speech_prob": 0.051055908203125, "words": [ { "start": 4010.44, "end": 4010.56, "word": " Would", "probability": 0.8251953125 }, { "start": 4010.56, "end": 4010.92, "word": " anybody", "probability": 0.78125 }, { "start": 4010.92, "end": 4011.2, "word": " be", "probability": 0.8896484375 }, { "start": 4011.2, "end": 4011.64, "word": " interested", "probability": 0.693359375 }, { "start": 4011.64, "end": 4011.94, "word": "?", "probability": 0.320556640625 }, { "start": 4011.94, "end": 4012.06, "word": " And", "probability": 0.67822265625 }, { "start": 4012.06, "end": 4012.32, "word": " please", "probability": 0.70654296875 }, { "start": 4012.32, "end": 4012.66, "word": " vote", "probability": 0.857421875 }, { "start": 4012.66, "end": 4012.86, "word": " in", "probability": 0.900390625 }, { "start": 4012.86, "end": 4012.98, "word": " the", "probability": 0.80859375 }, { "start": 4012.98, "end": 4013.24, "word": " Discord", "probability": 0.689453125 }, { "start": 4013.24, "end": 4013.66, "word": " channel", "probability": 0.7490234375 }, { "start": 4013.66, "end": 4014.22, "word": ".", "probability": 0.54443359375 } ] }, { "id": 1569, "seek": 393476, "start": 4014.24, "end": 4018.4, "text": " If you would be interested in learning how to build neural networks from scratch", "tokens": [ 51364, 759, 291, 576, 312, 3102, 294, 2539, 577, 281, 1322, 18161, 9590, 490, 8459, 51564 ], "temperature": 0.0, "avg_logprob": -0.2679924218341558, "compression_ratio": 1.6345381526104417, "no_speech_prob": 0.051055908203125, "words": [ { "start": 4014.24, "end": 4014.58, "word": " If", "probability": 0.88525390625 }, { "start": 4014.58, "end": 4014.66, "word": " you", "probability": 0.892578125 }, { "start": 4014.66, "end": 4014.76, "word": " would", "probability": 0.74853515625 }, { "start": 4014.76, "end": 4014.88, "word": " be", "probability": 0.900390625 }, { "start": 4014.88, "end": 4015.16, "word": " interested", "probability": 0.6806640625 }, { "start": 4015.16, "end": 4015.5, "word": " in", "probability": 0.90478515625 }, { "start": 4015.5, "end": 4015.8, "word": " learning", "probability": 0.8544921875 }, { "start": 4015.8, "end": 4016.12, "word": " how", "probability": 0.8955078125 }, { "start": 4016.12, "end": 4016.5, "word": " to", "probability": 0.9033203125 }, { "start": 4016.5, "end": 4017.04, "word": " build", "probability": 0.87744140625 }, { "start": 4017.04, "end": 4017.36, "word": " neural", "probability": 0.89013671875 }, { "start": 4017.36, "end": 4017.64, "word": " networks", "probability": 0.6796875 }, { "start": 4017.64, "end": 4017.86, "word": " from", "probability": 0.8232421875 }, { "start": 4017.86, "end": 4018.4, "word": " scratch", "probability": 0.83251953125 } ] }, { "id": 1570, "seek": 393476, "start": 4018.4, "end": 4023.18, "text": " or how to build deep learning security tools", "tokens": [ 51564, 420, 577, 281, 1322, 2452, 2539, 3825, 3873, 51814 ], "temperature": 0.0, "avg_logprob": -0.2679924218341558, "compression_ratio": 1.6345381526104417, "no_speech_prob": 0.051055908203125, "words": [ { "start": 4018.4, "end": 4018.66, "word": " or", "probability": 0.59033203125 }, { "start": 4018.66, "end": 4018.82, "word": " how", "probability": 0.90283203125 }, { "start": 4018.82, "end": 4018.96, "word": " to", "probability": 0.90673828125 }, { "start": 4018.96, "end": 4019.32, "word": " build", "probability": 0.84716796875 }, { "start": 4019.32, "end": 4019.74, "word": " deep", "probability": 0.91259765625 }, { "start": 4019.74, "end": 4020.3, "word": " learning", "probability": 0.78271484375 }, { "start": 4020.3, "end": 4022.5, "word": " security", "probability": 0.90283203125 }, { "start": 4022.5, "end": 4023.18, "word": " tools", "probability": 0.80712890625 } ] }, { "id": 1571, "seek": 395904, "start": 4023.18, "end": 4025.92, "text": " I think both would be really interesting.", "tokens": [ 50364, 286, 519, 1293, 576, 312, 534, 1880, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.19513081152771794, "compression_ratio": 1.543103448275862, "no_speech_prob": 0.016143798828125, "words": [ { "start": 4023.18, "end": 4024.12, "word": " I", "probability": 0.677734375 }, { "start": 4024.12, "end": 4024.3, "word": " think", "probability": 0.81396484375 }, { "start": 4024.3, "end": 4024.54, "word": " both", "probability": 0.81689453125 }, { "start": 4024.54, "end": 4024.72, "word": " would", "probability": 0.85400390625 }, { "start": 4024.72, "end": 4024.84, "word": " be", "probability": 0.9033203125 }, { "start": 4024.84, "end": 4025.08, "word": " really", "probability": 0.76025390625 }, { "start": 4025.08, "end": 4025.64, "word": " interesting", "probability": 0.623046875 }, { "start": 4025.64, "end": 4025.92, "word": ".", "probability": 0.75537109375 } ] }, { "id": 1572, "seek": 395904, "start": 4025.92, "end": 4029.12, "text": " Neural networks from scratch is actually a lot easier than you would imagine.", "tokens": [ 50464, 1734, 1807, 9590, 490, 8459, 307, 767, 257, 688, 3571, 813, 291, 576, 3811, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.19513081152771794, "compression_ratio": 1.543103448275862, "no_speech_prob": 0.016143798828125, "words": [ { "start": 4025.92, "end": 4026.02, "word": " Neural", "probability": 0.9345703125 }, { "start": 4026.02, "end": 4026.32, "word": " networks", "probability": 0.57470703125 }, { "start": 4026.32, "end": 4026.5, "word": " from", "probability": 0.81982421875 }, { "start": 4026.5, "end": 4026.96, "word": " scratch", "probability": 0.8125 }, { "start": 4026.96, "end": 4027.18, "word": " is", "probability": 0.884765625 }, { "start": 4027.18, "end": 4027.48, "word": " actually", "probability": 0.7958984375 }, { "start": 4027.68, "end": 4027.9, "word": " a lot", "probability": 0.892578125 }, { "start": 4027.9, "end": 4028.26, "word": " easier", "probability": 0.92578125 }, { "start": 4028.26, "end": 4028.46, "word": " than", "probability": 0.87353515625 }, { "start": 4028.46, "end": 4028.58, "word": " you", "probability": 0.89794921875 }, { "start": 4028.58, "end": 4028.68, "word": " would", "probability": 0.8154296875 }, { "start": 4028.68, "end": 4029.0, "word": " imagine", "probability": 0.80810546875 }, { "start": 4029.0, "end": 4029.12, "word": ".", "probability": 0.73583984375 } ] }, { "id": 1573, "seek": 395904, "start": 4029.12, "end": 4031.48, "text": " You can do it in about 11 lines of Python code.", "tokens": [ 50614, 509, 393, 360, 309, 294, 466, 2975, 3876, 295, 15329, 3089, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.19513081152771794, "compression_ratio": 1.543103448275862, "no_speech_prob": 0.016143798828125, "words": [ { "start": 4029.12, "end": 4029.16, "word": " You", "probability": 0.88623046875 }, { "start": 4029.16, "end": 4029.28, "word": " can", "probability": 0.87451171875 }, { "start": 4029.28, "end": 4029.36, "word": " do", "probability": 0.9130859375 }, { "start": 4029.36, "end": 4029.44, "word": " it", "probability": 0.84912109375 }, { "start": 4029.44, "end": 4029.5, "word": " in", "probability": 0.82861328125 }, { "start": 4029.5, "end": 4029.64, "word": " about", "probability": 0.8203125 }, { "start": 4029.64, "end": 4029.88, "word": " 11", "probability": 0.81494140625 }, { "start": 4029.88, "end": 4030.18, "word": " lines", "probability": 0.89306640625 }, { "start": 4030.18, "end": 4030.3, "word": " of", "probability": 0.90234375 }, { "start": 4030.3, "end": 4030.58, "word": " Python", "probability": 0.83203125 }, { "start": 4030.58, "end": 4031.0, "word": " code", "probability": 0.810546875 }, { "start": 4031.0, "end": 4031.48, "word": ".", "probability": 0.81201171875 } ] }, { "id": 1574, "seek": 395904, "start": 4034.64, "end": 4038.36, "text": " Today we are able to simplify and easily explain the math", "tokens": [ 50914, 2692, 321, 366, 1075, 281, 20460, 293, 3612, 2903, 264, 5221, 51114 ], "temperature": 0.0, "avg_logprob": -0.19513081152771794, "compression_ratio": 1.543103448275862, "no_speech_prob": 0.016143798828125, "words": [ { "start": 4034.64, "end": 4035.12, "word": " Today", "probability": 0.376953125 }, { "start": 4035.12, "end": 4035.6, "word": " we", "probability": 0.60498046875 }, { "start": 4035.6, "end": 4035.72, "word": " are", "probability": 0.85888671875 }, { "start": 4035.72, "end": 4035.94, "word": " able", "probability": 0.8798828125 }, { "start": 4035.94, "end": 4036.18, "word": " to", "probability": 0.9091796875 }, { "start": 4036.18, "end": 4036.58, "word": " simplify", "probability": 0.91015625 }, { "start": 4036.58, "end": 4037.08, "word": " and", "probability": 0.8720703125 }, { "start": 4037.08, "end": 4037.44, "word": " easily", "probability": 0.87548828125 }, { "start": 4037.44, "end": 4037.82, "word": " explain", "probability": 0.83056640625 }, { "start": 4037.82, "end": 4038.0, "word": " the", "probability": 0.81494140625 }, { "start": 4038.0, "end": 4038.36, "word": " math", "probability": 0.90234375 } ] }, { "id": 1575, "seek": 395904, "start": 4038.36, "end": 4042.2, "text": " whereas a lot of these algorithms were invented in the 50s", "tokens": [ 51114, 9735, 257, 688, 295, 613, 14642, 645, 14479, 294, 264, 2625, 82, 51314 ], "temperature": 0.0, "avg_logprob": -0.19513081152771794, "compression_ratio": 1.543103448275862, "no_speech_prob": 0.016143798828125, "words": [ { "start": 4038.36, "end": 4038.66, "word": " whereas", "probability": 0.2076416015625 }, { "start": 4039.28, "end": 4039.44, "word": " a lot", "probability": 0.8857421875 }, { "start": 4039.44, "end": 4039.52, "word": " of", "probability": 0.9033203125 }, { "start": 4039.52, "end": 4039.68, "word": " these", "probability": 0.7177734375 }, { "start": 4039.68, "end": 4040.02, "word": " algorithms", "probability": 0.87451171875 }, { "start": 4040.02, "end": 4040.42, "word": " were", "probability": 0.85986328125 }, { "start": 4040.42, "end": 4041.3, "word": " invented", "probability": 0.57080078125 }, { "start": 4041.3, "end": 4041.56, "word": " in", "probability": 0.90625 }, { "start": 4041.56, "end": 4041.7, "word": " the", "probability": 0.8134765625 }, { "start": 4041.7, "end": 4042.2, "word": " 50s", "probability": 0.7158203125 } ] }, { "id": 1576, "seek": 395904, "start": 4043.02, "end": 4047.46, "text": " where the people who would do this kind of work were called statisticians", "tokens": [ 51314, 689, 264, 561, 567, 576, 360, 341, 733, 295, 589, 645, 1219, 29588, 2567, 51564 ], "temperature": 0.0, "avg_logprob": -0.19513081152771794, "compression_ratio": 1.543103448275862, "no_speech_prob": 0.016143798828125, "words": [ { "start": 4043.02, "end": 4043.5, "word": " where", "probability": 0.515625 }, { "start": 4043.5, "end": 4043.72, "word": " the", "probability": 0.7890625 }, { "start": 4043.72, "end": 4043.92, "word": " people", "probability": 0.92626953125 }, { "start": 4043.92, "end": 4044.08, "word": " who", "probability": 0.81201171875 }, { "start": 4044.08, "end": 4044.26, "word": " would", "probability": 0.84033203125 }, { "start": 4044.26, "end": 4044.58, "word": " do", "probability": 0.90234375 }, { "start": 4044.58, "end": 4045.14, "word": " this", "probability": 0.830078125 }, { "start": 4045.14, "end": 4045.74, "word": " kind", "probability": 0.74462890625 }, { "start": 4045.74, "end": 4045.88, "word": " of", "probability": 0.90087890625 }, { "start": 4045.88, "end": 4046.08, "word": " work", "probability": 0.81298828125 }, { "start": 4046.08, "end": 4046.24, "word": " were", "probability": 0.8544921875 }, { "start": 4046.24, "end": 4046.56, "word": " called", "probability": 0.77490234375 }, { "start": 4046.56, "end": 4047.46, "word": " statisticians", "probability": 0.86962890625 } ] }, { "id": 1577, "seek": 398656, "start": 4047.46, "end": 4053.52, "text": " or people who would apply these in business scenarios were called business intelligence.", "tokens": [ 50364, 420, 561, 567, 576, 3079, 613, 294, 1606, 15077, 645, 1219, 1606, 7599, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.24984829576270093, "compression_ratio": 1.5457875457875458, "no_speech_prob": 0.1275634765625, "words": [ { "start": 4047.46, "end": 4047.82, "word": " or", "probability": 0.81640625 }, { "start": 4047.82, "end": 4048.36, "word": " people", "probability": 0.89501953125 }, { "start": 4048.36, "end": 4048.48, "word": " who", "probability": 0.791015625 }, { "start": 4048.48, "end": 4048.6, "word": " would", "probability": 0.81201171875 }, { "start": 4048.6, "end": 4048.84, "word": " apply", "probability": 0.8505859375 }, { "start": 4048.84, "end": 4049.18, "word": " these", "probability": 0.703125 }, { "start": 4049.18, "end": 4049.48, "word": " in", "probability": 0.90478515625 }, { "start": 4049.48, "end": 4049.88, "word": " business", "probability": 0.9052734375 }, { "start": 4049.88, "end": 4050.3, "word": " scenarios", "probability": 0.82275390625 }, { "start": 4050.3, "end": 4050.46, "word": " were", "probability": 0.14208984375 }, { "start": 4050.46, "end": 4050.64, "word": " called", "probability": 0.7822265625 }, { "start": 4050.64, "end": 4051.06, "word": " business", "probability": 0.52978515625 }, { "start": 4051.06, "end": 4052.96, "word": " intelligence", "probability": 0.55810546875 }, { "start": 4052.96, "end": 4053.52, "word": ".", "probability": 0.720703125 } ] }, { "id": 1578, "seek": 398656, "start": 4053.96, "end": 4057.34, "text": " But today with computer science and these abstraction libraries", "tokens": [ 50664, 583, 965, 365, 3820, 3497, 293, 613, 37765, 15148, 50864 ], "temperature": 0.0, "avg_logprob": -0.24984829576270093, "compression_ratio": 1.5457875457875458, "no_speech_prob": 0.1275634765625, "words": [ { "start": 4053.96, "end": 4054.42, "word": " But", "probability": 0.830078125 }, { "start": 4054.42, "end": 4054.72, "word": " today", "probability": 0.77294921875 }, { "start": 4054.72, "end": 4054.94, "word": " with", "probability": 0.53173828125 }, { "start": 4054.94, "end": 4055.64, "word": " computer", "probability": 0.61865234375 }, { "start": 4055.64, "end": 4056.02, "word": " science", "probability": 0.86865234375 }, { "start": 4056.02, "end": 4056.14, "word": " and", "probability": 0.80517578125 }, { "start": 4056.14, "end": 4056.36, "word": " these", "probability": 0.68115234375 }, { "start": 4056.36, "end": 4056.78, "word": " abstraction", "probability": 0.58203125 }, { "start": 4056.78, "end": 4057.34, "word": " libraries", "probability": 0.89990234375 } ] }, { "id": 1579, "seek": 398656, "start": 4057.34, "end": 4059.56, "text": " it's a lot easier to understand.", "tokens": [ 50864, 309, 311, 257, 688, 3571, 281, 1223, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.24984829576270093, "compression_ratio": 1.5457875457875458, "no_speech_prob": 0.1275634765625, "words": [ { "start": 4057.34, "end": 4058.04, "word": " it's", "probability": 0.6099853515625 }, { "start": 4058.12, "end": 4058.2, "word": " a lot", "probability": 0.8896484375 }, { "start": 4058.2, "end": 4058.44, "word": " easier", "probability": 0.92431640625 }, { "start": 4058.44, "end": 4058.6, "word": " to", "probability": 0.9072265625 }, { "start": 4058.6, "end": 4059.0, "word": " understand", "probability": 0.740234375 }, { "start": 4059.0, "end": 4059.56, "word": ".", "probability": 0.88916015625 } ] }, { "id": 1580, "seek": 398656, "start": 4059.58, "end": 4063.76, "text": " So let me know in the Discord chat if there's any interest in either of those", "tokens": [ 50964, 407, 718, 385, 458, 294, 264, 32623, 5081, 498, 456, 311, 604, 1179, 294, 2139, 295, 729, 51164 ], "temperature": 0.0, "avg_logprob": -0.24984829576270093, "compression_ratio": 1.5457875457875458, "no_speech_prob": 0.1275634765625, "words": [ { "start": 4059.58, "end": 4059.68, "word": " So", "probability": 0.77197265625 }, { "start": 4059.68, "end": 4059.9, "word": " let", "probability": 0.78271484375 }, { "start": 4059.9, "end": 4059.94, "word": " me", "probability": 0.904296875 }, { "start": 4059.94, "end": 4060.14, "word": " know", "probability": 0.8154296875 }, { "start": 4060.14, "end": 4060.38, "word": " in", "probability": 0.90185546875 }, { "start": 4060.38, "end": 4060.5, "word": " the", "probability": 0.80908203125 }, { "start": 4060.5, "end": 4060.78, "word": " Discord", "probability": 0.5244140625 }, { "start": 4060.78, "end": 4061.24, "word": " chat", "probability": 0.787109375 }, { "start": 4061.24, "end": 4062.22, "word": " if", "probability": 0.8505859375 }, { "start": 4062.22, "end": 4062.38, "word": " there's", "probability": 0.92431640625 }, { "start": 4062.38, "end": 4062.56, "word": " any", "probability": 0.81494140625 }, { "start": 4062.56, "end": 4062.9, "word": " interest", "probability": 0.767578125 }, { "start": 4062.9, "end": 4063.08, "word": " in", "probability": 0.89404296875 }, { "start": 4063.08, "end": 4063.36, "word": " either", "probability": 0.8359375 }, { "start": 4063.36, "end": 4063.52, "word": " of", "probability": 0.90478515625 }, { "start": 4063.52, "end": 4063.76, "word": " those", "probability": 0.853515625 } ] }, { "id": 1581, "seek": 398656, "start": 4063.76, "end": 4067.2, "text": " as potentially future workshops for future DEF CON events.", "tokens": [ 51164, 382, 7263, 2027, 19162, 337, 2027, 10113, 37, 16596, 3931, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.24984829576270093, "compression_ratio": 1.5457875457875458, "no_speech_prob": 0.1275634765625, "words": [ { "start": 4063.76, "end": 4064.0, "word": " as", "probability": 0.783203125 }, { "start": 4064.0, "end": 4064.36, "word": " potentially", "probability": 0.61279296875 }, { "start": 4064.36, "end": 4064.68, "word": " future", "probability": 0.9443359375 }, { "start": 4064.68, "end": 4065.16, "word": " workshops", "probability": 0.5869140625 }, { "start": 4065.16, "end": 4065.62, "word": " for", "probability": 0.8818359375 }, { "start": 4065.62, "end": 4065.98, "word": " future", "probability": 0.9462890625 }, { "start": 4065.98, "end": 4066.22, "word": " DEF", "probability": 0.6396484375 }, { "start": 4066.22, "end": 4066.28, "word": " CON", "probability": 0.83447265625 }, { "start": 4066.28, "end": 4066.64, "word": " events", "probability": 0.78369140625 }, { "start": 4066.64, "end": 4067.2, "word": ".", "probability": 0.2117919921875 } ] }, { "id": 1582, "seek": 398656, "start": 4067.22, "end": 4069.28, "text": " Or even just AI Village events.", "tokens": [ 51314, 1610, 754, 445, 7318, 22651, 3931, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.24984829576270093, "compression_ratio": 1.5457875457875458, "no_speech_prob": 0.1275634765625, "words": [ { "start": 4067.22, "end": 4067.32, "word": " Or", "probability": 0.84521484375 }, { "start": 4067.32, "end": 4067.62, "word": " even", "probability": 0.77880859375 }, { "start": 4067.62, "end": 4067.82, "word": " just", "probability": 0.865234375 }, { "start": 4067.82, "end": 4068.12, "word": " AI", "probability": 0.556640625 }, { "start": 4068.12, "end": 4068.4, "word": " Village", "probability": 0.5107421875 }, { "start": 4068.4, "end": 4068.72, "word": " events", "probability": 0.74951171875 }, { "start": 4068.72, "end": 4069.28, "word": ".", "probability": 0.9482421875 } ] }, { "id": 1583, "seek": 398656, "start": 4069.84, "end": 4073.02, "text": " So KDAMinMax has a question on Twitch chat.", "tokens": [ 51464, 407, 591, 7509, 30031, 36025, 575, 257, 1168, 322, 22222, 5081, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.24984829576270093, "compression_ratio": 1.5457875457875458, "no_speech_prob": 0.1275634765625, "words": [ { "start": 4069.84, "end": 4070.32, "word": " So", "probability": 0.65673828125 }, { "start": 4070.32, "end": 4071.56, "word": " KDAMinMax", "probability": 0.442718505859375 }, { "start": 4071.56, "end": 4071.74, "word": " has", "probability": 0.8779296875 }, { "start": 4071.84, "end": 4072.08, "word": " a question", "probability": 0.796875 }, { "start": 4072.08, "end": 4072.26, "word": " on", "probability": 0.89501953125 }, { "start": 4072.26, "end": 4072.46, "word": " Twitch", "probability": 0.79638671875 }, { "start": 4072.46, "end": 4072.78, "word": " chat", "probability": 0.6640625 }, { "start": 4072.78, "end": 4073.02, "word": ".", "probability": 0.6748046875 } ] }, { "id": 1584, "seek": 398656, "start": 4073.02, "end": 4074.98, "text": " I'll just read it here.", "tokens": [ 51614, 286, 603, 445, 1401, 309, 510, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.24984829576270093, "compression_ratio": 1.5457875457875458, "no_speech_prob": 0.1275634765625, "words": [ { "start": 4073.02, "end": 4073.34, "word": " I'll", "probability": 0.959716796875 }, { "start": 4073.34, "end": 4073.58, "word": " just", "probability": 0.88232421875 }, { "start": 4073.58, "end": 4074.26, "word": " read", "probability": 0.9033203125 }, { "start": 4074.26, "end": 4074.42, "word": " it", "probability": 0.9013671875 }, { "start": 4074.42, "end": 4074.74, "word": " here", "probability": 0.8056640625 }, { "start": 4074.74, "end": 4074.98, "word": ".", "probability": 0.9560546875 } ] }, { "id": 1585, "seek": 401232, "start": 4074.98, "end": 4078.38, "text": " I have a possibly stupid question about input structures.", "tokens": [ 50364, 286, 362, 257, 6264, 6631, 1168, 466, 4846, 9227, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.23125000140246224, "compression_ratio": 1.6077586206896552, "no_speech_prob": 0.1600341796875, "words": [ { "start": 4074.98, "end": 4075.34, "word": " I", "probability": 0.8623046875 }, { "start": 4075.34, "end": 4075.5, "word": " have", "probability": 0.87255859375 }, { "start": 4075.62, "end": 4075.94, "word": " a possibly", "probability": 0.88623046875 }, { "start": 4075.94, "end": 4076.34, "word": " stupid", "probability": 0.77001953125 }, { "start": 4076.34, "end": 4076.68, "word": " question", "probability": 0.81103515625 }, { "start": 4076.68, "end": 4076.94, "word": " about", "probability": 0.806640625 }, { "start": 4076.94, "end": 4077.28, "word": " input", "probability": 0.344482421875 }, { "start": 4077.28, "end": 4077.98, "word": " structures", "probability": 0.66650390625 }, { "start": 4077.98, "end": 4078.38, "word": ".", "probability": 0.76611328125 } ] }, { "id": 1586, "seek": 401232, "start": 4078.38, "end": 4081.86, "text": " If you're learning, there's no real stupid questions.", "tokens": [ 50564, 759, 291, 434, 2539, 11, 456, 311, 572, 957, 6631, 1651, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.23125000140246224, "compression_ratio": 1.6077586206896552, "no_speech_prob": 0.1600341796875, "words": [ { "start": 4078.38, "end": 4078.62, "word": " If", "probability": 0.67529296875 }, { "start": 4078.62, "end": 4079.78, "word": " you're", "probability": 0.91064453125 }, { "start": 4079.78, "end": 4080.06, "word": " learning", "probability": 0.849609375 }, { "start": 4080.06, "end": 4080.24, "word": ",", "probability": 0.89697265625 }, { "start": 4080.24, "end": 4080.36, "word": " there's", "probability": 0.883056640625 }, { "start": 4080.36, "end": 4080.5, "word": " no", "probability": 0.9033203125 }, { "start": 4080.5, "end": 4080.64, "word": " real", "probability": 0.8349609375 }, { "start": 4080.64, "end": 4080.84, "word": " stupid", "probability": 0.82958984375 }, { "start": 4080.84, "end": 4081.3, "word": " questions", "probability": 0.8984375 }, { "start": 4081.3, "end": 4081.86, "word": ".", "probability": 0.98828125 } ] }, { "id": 1587, "seek": 401232, "start": 4084.72, "end": 4088.86, "text": " An email predictor acts on strings or a set of strings.", "tokens": [ 50864, 1107, 3796, 6069, 284, 10672, 322, 13985, 420, 257, 992, 295, 13985, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.23125000140246224, "compression_ratio": 1.6077586206896552, "no_speech_prob": 0.1600341796875, "words": [ { "start": 4084.72, "end": 4085.0, "word": " An", "probability": 0.13671875 }, { "start": 4085.0, "end": 4085.56, "word": " email", "probability": 0.85693359375 }, { "start": 4085.56, "end": 4086.22, "word": " predictor", "probability": 0.79443359375 }, { "start": 4086.22, "end": 4087.28, "word": " acts", "probability": 0.580078125 }, { "start": 4087.28, "end": 4087.4, "word": " on", "probability": 0.75 }, { "start": 4087.4, "end": 4087.8, "word": " strings", "probability": 0.85498046875 }, { "start": 4087.8, "end": 4088.02, "word": " or", "probability": 0.6455078125 }, { "start": 4088.16, "end": 4088.26, "word": " a set", "probability": 0.884765625 }, { "start": 4088.26, "end": 4088.4, "word": " of", "probability": 0.90576171875 }, { "start": 4088.4, "end": 4088.7, "word": " strings", "probability": 0.8486328125 }, { "start": 4088.7, "end": 4088.86, "word": ".", "probability": 0.86669921875 } ] }, { "id": 1588, "seek": 401232, "start": 4088.86, "end": 4092.6, "text": " Are there any machine learning approaches that act reasonably well on trees?", "tokens": [ 51064, 2014, 456, 604, 3479, 2539, 11587, 300, 605, 23551, 731, 322, 5852, 30, 51214 ], "temperature": 0.0, "avg_logprob": -0.23125000140246224, "compression_ratio": 1.6077586206896552, "no_speech_prob": 0.1600341796875, "words": [ { "start": 4088.86, "end": 4088.94, "word": " Are", "probability": 0.87841796875 }, { "start": 4088.94, "end": 4089.0, "word": " there", "probability": 0.8251953125 }, { "start": 4089.0, "end": 4089.2, "word": " any", "probability": 0.83349609375 }, { "start": 4089.2, "end": 4089.46, "word": " machine", "probability": 0.705078125 }, { "start": 4089.46, "end": 4089.68, "word": " learning", "probability": 0.796875 }, { "start": 4089.68, "end": 4090.0, "word": " approaches", "probability": 0.64111328125 }, { "start": 4090.0, "end": 4090.22, "word": " that", "probability": 0.88134765625 }, { "start": 4090.22, "end": 4090.58, "word": " act", "probability": 0.70166015625 }, { "start": 4090.58, "end": 4091.06, "word": " reasonably", "probability": 0.900390625 }, { "start": 4091.06, "end": 4091.34, "word": " well", "probability": 0.85107421875 }, { "start": 4091.34, "end": 4091.54, "word": " on", "probability": 0.89892578125 }, { "start": 4091.54, "end": 4092.04, "word": " trees", "probability": 0.79833984375 }, { "start": 4092.04, "end": 4092.6, "word": "?", "probability": 0.469482421875 } ] }, { "id": 1589, "seek": 401232, "start": 4092.64, "end": 4096.02, "text": " For example, abstract syntax tree representations of applications.", "tokens": [ 51214, 1171, 1365, 11, 12649, 28431, 4230, 33358, 295, 5821, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.23125000140246224, "compression_ratio": 1.6077586206896552, "no_speech_prob": 0.1600341796875, "words": [ { "start": 4092.64, "end": 4092.82, "word": " For", "probability": 0.82763671875 }, { "start": 4092.82, "end": 4093.14, "word": " example", "probability": 0.92724609375 }, { "start": 4093.14, "end": 4093.24, "word": ",", "probability": 0.95458984375 }, { "start": 4093.24, "end": 4093.5, "word": " abstract", "probability": 0.7001953125 }, { "start": 4093.5, "end": 4093.84, "word": " syntax", "probability": 0.830078125 }, { "start": 4093.84, "end": 4094.14, "word": " tree", "probability": 0.84912109375 }, { "start": 4094.14, "end": 4094.7, "word": " representations", "probability": 0.7802734375 }, { "start": 4094.7, "end": 4094.94, "word": " of", "probability": 0.90185546875 }, { "start": 4094.94, "end": 4095.46, "word": " applications", "probability": 0.7548828125 }, { "start": 4095.46, "end": 4096.02, "word": ".", "probability": 0.8759765625 } ] }, { "id": 1590, "seek": 401232, "start": 4096.6, "end": 4100.74, "text": " For that, you might want to use a graph convolutional network", "tokens": [ 51464, 1171, 300, 11, 291, 1062, 528, 281, 764, 257, 4295, 45216, 304, 3209, 51664 ], "temperature": 0.0, "avg_logprob": -0.23125000140246224, "compression_ratio": 1.6077586206896552, "no_speech_prob": 0.1600341796875, "words": [ { "start": 4096.6, "end": 4097.02, "word": " For", "probability": 0.88623046875 }, { "start": 4097.02, "end": 4097.32, "word": " that", "probability": 0.8818359375 }, { "start": 4097.32, "end": 4097.44, "word": ",", "probability": 0.86083984375 }, { "start": 4097.44, "end": 4097.54, "word": " you", "probability": 0.896484375 }, { "start": 4097.54, "end": 4097.74, "word": " might", "probability": 0.806640625 }, { "start": 4097.74, "end": 4097.92, "word": " want", "probability": 0.7001953125 }, { "start": 4097.92, "end": 4098.04, "word": " to", "probability": 0.90625 }, { "start": 4098.04, "end": 4098.38, "word": " use", "probability": 0.82861328125 }, { "start": 4099.54, "end": 4099.88, "word": " a graph", "probability": 0.78173828125 }, { "start": 4099.88, "end": 4100.52, "word": " convolutional", "probability": 0.927490234375 }, { "start": 4100.52, "end": 4100.74, "word": " network", "probability": 0.6474609375 } ] }, { "id": 1591, "seek": 404022, "start": 4100.74, "end": 4108.34, "text": " or, honestly, you can interpret language as an abstract syntax tree.", "tokens": [ 50364, 420, 11, 6095, 11, 291, 393, 7302, 2856, 382, 364, 12649, 28431, 4230, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.2560975555239654, "compression_ratio": 1.7512437810945274, "no_speech_prob": 0.122314453125, "words": [ { "start": 4100.74, "end": 4101.72, "word": " or", "probability": 0.18701171875 }, { "start": 4101.72, "end": 4101.98, "word": ",", "probability": 0.2166748046875 }, { "start": 4101.98, "end": 4103.66, "word": " honestly", "probability": 0.64501953125 }, { "start": 4103.66, "end": 4103.98, "word": ",", "probability": 0.876953125 }, { "start": 4103.98, "end": 4104.84, "word": " you", "probability": 0.216796875 }, { "start": 4104.84, "end": 4106.0, "word": " can", "probability": 0.88525390625 }, { "start": 4106.0, "end": 4106.42, "word": " interpret", "probability": 0.759765625 }, { "start": 4106.42, "end": 4106.82, "word": " language", "probability": 0.56884765625 }, { "start": 4106.82, "end": 4107.02, "word": " as", "probability": 0.8583984375 }, { "start": 4107.02, "end": 4107.14, "word": " an", "probability": 0.8564453125 }, { "start": 4107.14, "end": 4107.44, "word": " abstract", "probability": 0.6572265625 }, { "start": 4107.44, "end": 4107.78, "word": " syntax", "probability": 0.8017578125 }, { "start": 4107.78, "end": 4108.14, "word": " tree", "probability": 0.8056640625 }, { "start": 4108.14, "end": 4108.34, "word": ".", "probability": 0.38916015625 } ] }, { "id": 1592, "seek": 404022, "start": 4108.34, "end": 4111.02, "text": " So you might want to reach in and use some of the...", "tokens": [ 50714, 407, 291, 1062, 528, 281, 2524, 294, 293, 764, 512, 295, 264, 485, 50864 ], "temperature": 0.0, "avg_logprob": -0.2560975555239654, "compression_ratio": 1.7512437810945274, "no_speech_prob": 0.122314453125, "words": [ { "start": 4108.34, "end": 4108.36, "word": " So", "probability": 0.56884765625 }, { "start": 4108.36, "end": 4108.44, "word": " you", "probability": 0.6357421875 }, { "start": 4108.44, "end": 4108.62, "word": " might", "probability": 0.80859375 }, { "start": 4108.62, "end": 4108.8, "word": " want", "probability": 0.78125 }, { "start": 4108.8, "end": 4108.9, "word": " to", "probability": 0.8994140625 }, { "start": 4108.9, "end": 4109.22, "word": " reach", "probability": 0.85400390625 }, { "start": 4109.22, "end": 4109.56, "word": " in", "probability": 0.90283203125 }, { "start": 4109.56, "end": 4109.72, "word": " and", "probability": 0.83837890625 }, { "start": 4109.72, "end": 4109.96, "word": " use", "probability": 0.826171875 }, { "start": 4109.96, "end": 4110.16, "word": " some", "probability": 0.79541015625 }, { "start": 4110.16, "end": 4110.32, "word": " of", "probability": 0.896484375 }, { "start": 4110.32, "end": 4111.02, "word": " the...", "probability": 0.569091796875 } ] }, { "id": 1593, "seek": 404022, "start": 4111.02, "end": 4116.16, "text": " There's a huge backlog of literature that people largely ignore", "tokens": [ 50864, 821, 311, 257, 2603, 47364, 295, 10394, 300, 561, 11611, 11200, 51114 ], "temperature": 0.0, "avg_logprob": -0.2560975555239654, "compression_ratio": 1.7512437810945274, "no_speech_prob": 0.122314453125, "words": [ { "start": 4111.02, "end": 4111.5, "word": " There's", "probability": 0.78125 }, { "start": 4111.7, "end": 4112.78, "word": " a huge", "probability": 0.83349609375 }, { "start": 4112.78, "end": 4113.64, "word": " backlog", "probability": 0.74267578125 }, { "start": 4113.64, "end": 4114.02, "word": " of", "probability": 0.90576171875 }, { "start": 4114.02, "end": 4114.36, "word": " literature", "probability": 0.8291015625 }, { "start": 4114.36, "end": 4115.14, "word": " that", "probability": 0.814453125 }, { "start": 4115.14, "end": 4115.38, "word": " people", "probability": 0.9111328125 }, { "start": 4115.38, "end": 4115.8, "word": " largely", "probability": 0.6259765625 }, { "start": 4115.8, "end": 4116.16, "word": " ignore", "probability": 0.587890625 } ] }, { "id": 1594, "seek": 404022, "start": 4116.16, "end": 4119.02, "text": " because of the success of deep learning", "tokens": [ 51114, 570, 295, 264, 2245, 295, 2452, 2539, 51264 ], "temperature": 0.0, "avg_logprob": -0.2560975555239654, "compression_ratio": 1.7512437810945274, "no_speech_prob": 0.122314453125, "words": [ { "start": 4116.16, "end": 4116.44, "word": " because", "probability": 0.765625 }, { "start": 4116.44, "end": 4116.6, "word": " of", "probability": 0.8798828125 }, { "start": 4116.6, "end": 4116.78, "word": " the", "probability": 0.796875 }, { "start": 4116.78, "end": 4117.08, "word": " success", "probability": 0.55029296875 }, { "start": 4117.08, "end": 4118.22, "word": " of", "probability": 0.88330078125 }, { "start": 4118.22, "end": 4118.68, "word": " deep", "probability": 0.8779296875 }, { "start": 4118.68, "end": 4119.02, "word": " learning", "probability": 0.82275390625 } ] }, { "id": 1595, "seek": 404022, "start": 4119.02, "end": 4124.68, "text": " of how to do language processing using abstract syntax trees.", "tokens": [ 51264, 295, 577, 281, 360, 2856, 9007, 1228, 12649, 28431, 5852, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.2560975555239654, "compression_ratio": 1.7512437810945274, "no_speech_prob": 0.122314453125, "words": [ { "start": 4119.02, "end": 4119.66, "word": " of", "probability": 0.52880859375 }, { "start": 4119.66, "end": 4119.92, "word": " how", "probability": 0.89453125 }, { "start": 4119.92, "end": 4120.16, "word": " to", "probability": 0.9091796875 }, { "start": 4120.16, "end": 4120.6, "word": " do", "probability": 0.9013671875 }, { "start": 4120.6, "end": 4121.9, "word": " language", "probability": 0.6728515625 }, { "start": 4121.9, "end": 4122.38, "word": " processing", "probability": 0.810546875 }, { "start": 4122.38, "end": 4122.92, "word": " using", "probability": 0.830078125 }, { "start": 4122.92, "end": 4123.38, "word": " abstract", "probability": 0.64453125 }, { "start": 4123.38, "end": 4123.66, "word": " syntax", "probability": 0.8828125 }, { "start": 4123.66, "end": 4124.2, "word": " trees", "probability": 0.8056640625 }, { "start": 4124.2, "end": 4124.68, "word": ".", "probability": 0.982421875 } ] }, { "id": 1596, "seek": 404022, "start": 4124.9, "end": 4128.64, "text": " So you might want to reach into some old school machine learning", "tokens": [ 51564, 407, 291, 1062, 528, 281, 2524, 666, 512, 1331, 1395, 3479, 2539, 51764 ], "temperature": 0.0, "avg_logprob": -0.2560975555239654, "compression_ratio": 1.7512437810945274, "no_speech_prob": 0.122314453125, "words": [ { "start": 4124.9, "end": 4125.54, "word": " So", "probability": 0.869140625 }, { "start": 4125.54, "end": 4125.66, "word": " you", "probability": 0.8564453125 }, { "start": 4125.66, "end": 4125.8, "word": " might", "probability": 0.81640625 }, { "start": 4125.8, "end": 4125.94, "word": " want", "probability": 0.80126953125 }, { "start": 4125.94, "end": 4126.04, "word": " to", "probability": 0.90380859375 }, { "start": 4126.04, "end": 4126.28, "word": " reach", "probability": 0.8388671875 }, { "start": 4126.28, "end": 4126.58, "word": " into", "probability": 0.73046875 }, { "start": 4126.58, "end": 4127.32, "word": " some", "probability": 0.65625 }, { "start": 4127.32, "end": 4127.72, "word": " old", "probability": 0.8935546875 }, { "start": 4127.72, "end": 4128.0, "word": " school", "probability": 0.44775390625 }, { "start": 4128.0, "end": 4128.32, "word": " machine", "probability": 0.68505859375 }, { "start": 4128.32, "end": 4128.64, "word": " learning", "probability": 0.83837890625 } ] }, { "id": 1597, "seek": 406760, "start": 4128.64, "end": 4132.66, "text": " from before 2010 when neural networks destroyed the world.", "tokens": [ 50364, 490, 949, 9657, 562, 18161, 9590, 8937, 264, 1002, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.22216236283039226, "compression_ratio": 1.4761904761904763, "no_speech_prob": 0.034088134765625, "words": [ { "start": 4128.64, "end": 4128.96, "word": " from", "probability": 0.60888671875 }, { "start": 4128.96, "end": 4129.4, "word": " before", "probability": 0.79833984375 }, { "start": 4129.4, "end": 4130.14, "word": " 2010", "probability": 0.7431640625 }, { "start": 4130.14, "end": 4130.56, "word": " when", "probability": 0.65966796875 }, { "start": 4130.56, "end": 4130.76, "word": " neural", "probability": 0.8193359375 }, { "start": 4130.76, "end": 4131.14, "word": " networks", "probability": 0.63671875 }, { "start": 4131.14, "end": 4131.62, "word": " destroyed", "probability": 0.779296875 }, { "start": 4131.62, "end": 4131.78, "word": " the", "probability": 0.81298828125 }, { "start": 4131.78, "end": 4132.08, "word": " world", "probability": 0.88818359375 }, { "start": 4132.08, "end": 4132.66, "word": ".", "probability": 0.69970703125 } ] }, { "id": 1598, "seek": 406760, "start": 4133.96, "end": 4136.76, "text": " I mean, built our jobs.", "tokens": [ 50614, 286, 914, 11, 3094, 527, 4782, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.22216236283039226, "compression_ratio": 1.4761904761904763, "no_speech_prob": 0.034088134765625, "words": [ { "start": 4133.96, "end": 4133.96, "word": " I", "probability": 0.3349609375 }, { "start": 4133.96, "end": 4134.2, "word": " mean", "probability": 0.92236328125 }, { "start": 4134.2, "end": 4134.42, "word": ",", "probability": 0.6787109375 }, { "start": 4134.42, "end": 4135.2, "word": " built", "probability": 0.8232421875 }, { "start": 4135.2, "end": 4135.76, "word": " our", "probability": 0.8115234375 }, { "start": 4135.76, "end": 4136.18, "word": " jobs", "probability": 0.7763671875 }, { "start": 4136.18, "end": 4136.76, "word": ".", "probability": 0.97607421875 } ] }, { "id": 1599, "seek": 406760, "start": 4139.3, "end": 4141.42, "text": " That was a good answer. Thank you.", "tokens": [ 50914, 663, 390, 257, 665, 1867, 13, 1044, 291, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.22216236283039226, "compression_ratio": 1.4761904761904763, "no_speech_prob": 0.034088134765625, "words": [ { "start": 4139.3, "end": 4139.7, "word": " That", "probability": 0.143310546875 }, { "start": 4139.7, "end": 4139.8, "word": " was", "probability": 0.6123046875 }, { "start": 4139.86, "end": 4139.94, "word": " a good", "probability": 0.87939453125 }, { "start": 4139.94, "end": 4140.12, "word": " answer", "probability": 0.8984375 }, { "start": 4140.12, "end": 4140.5, "word": ".", "probability": 0.4853515625 }, { "start": 4140.5, "end": 4140.68, "word": " Thank", "probability": 0.77685546875 }, { "start": 4140.68, "end": 4140.84, "word": " you", "probability": 0.89404296875 }, { "start": 4140.84, "end": 4141.42, "word": ".", "probability": 0.9873046875 } ] }, { "id": 1600, "seek": 406760, "start": 4144.6, "end": 4149.66, "text": " So what we're looking at is logistic regression with TF-IDF vectorizer.", "tokens": [ 51164, 407, 437, 321, 434, 1237, 412, 307, 3565, 3142, 24590, 365, 40964, 12, 2777, 37, 8062, 6545, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.22216236283039226, "compression_ratio": 1.4761904761904763, "no_speech_prob": 0.034088134765625, "words": [ { "start": 4144.6, "end": 4145.18, "word": " So", "probability": 0.08575439453125 }, { "start": 4145.18, "end": 4145.76, "word": " what", "probability": 0.560546875 }, { "start": 4145.76, "end": 4145.86, "word": " we're", "probability": 0.912841796875 }, { "start": 4145.86, "end": 4146.1, "word": " looking", "probability": 0.806640625 }, { "start": 4146.1, "end": 4146.38, "word": " at", "probability": 0.9072265625 }, { "start": 4146.38, "end": 4146.68, "word": " is", "probability": 0.9033203125 }, { "start": 4146.68, "end": 4147.06, "word": " logistic", "probability": 0.920166015625 }, { "start": 4147.06, "end": 4147.5, "word": " regression", "probability": 0.89111328125 }, { "start": 4147.5, "end": 4148.04, "word": " with", "probability": 0.80615234375 }, { "start": 4148.04, "end": 4148.32, "word": " TF", "probability": 0.60400390625 }, { "start": 4148.32, "end": 4148.76, "word": "-IDF", "probability": 0.9119466145833334 }, { "start": 4148.76, "end": 4149.46, "word": " vectorizer", "probability": 0.805908203125 }, { "start": 4149.46, "end": 4149.66, "word": ".", "probability": 0.94921875 } ] }, { "id": 1601, "seek": 406760, "start": 4149.66, "end": 4151.54, "text": " We have a slightly better...", "tokens": [ 51414, 492, 362, 257, 4748, 1101, 485, 51514 ], "temperature": 0.0, "avg_logprob": -0.22216236283039226, "compression_ratio": 1.4761904761904763, "no_speech_prob": 0.034088134765625, "words": [ { "start": 4149.66, "end": 4149.68, "word": " We", "probability": 0.68408203125 }, { "start": 4149.68, "end": 4149.86, "word": " have", "probability": 0.87890625 }, { "start": 4150.28, "end": 4150.52, "word": " a slightly", "probability": 0.81591796875 }, { "start": 4150.52, "end": 4151.54, "word": " better...", "probability": 0.53302001953125 } ] }, { "id": 1602, "seek": 406760, "start": 4151.54, "end": 4153.64, "text": " It's a small bump, but it's slightly better", "tokens": [ 51514, 467, 311, 257, 1359, 9961, 11, 457, 309, 311, 4748, 1101, 51614 ], "temperature": 0.0, "avg_logprob": -0.22216236283039226, "compression_ratio": 1.4761904761904763, "no_speech_prob": 0.034088134765625, "words": [ { "start": 4151.54, "end": 4152.02, "word": " It's", "probability": 0.7548828125 }, { "start": 4152.14, "end": 4152.38, "word": " a small", "probability": 0.8671875 }, { "start": 4152.38, "end": 4152.66, "word": " bump", "probability": 0.80078125 }, { "start": 4152.66, "end": 4152.78, "word": ",", "probability": 0.78466796875 }, { "start": 4152.78, "end": 4152.84, "word": " but", "probability": 0.8974609375 }, { "start": 4152.84, "end": 4153.0, "word": " it's", "probability": 0.945068359375 }, { "start": 4153.0, "end": 4153.26, "word": " slightly", "probability": 0.78759765625 }, { "start": 4153.26, "end": 4153.64, "word": " better", "probability": 0.8232421875 } ] }, { "id": 1603, "seek": 406760, "start": 4153.64, "end": 4156.02, "text": " than the multinomial with the count vectorizer.", "tokens": [ 51614, 813, 264, 45872, 47429, 365, 264, 1207, 8062, 6545, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.22216236283039226, "compression_ratio": 1.4761904761904763, "no_speech_prob": 0.034088134765625, "words": [ { "start": 4153.64, "end": 4153.9, "word": " than", "probability": 0.875 }, { "start": 4153.9, "end": 4154.28, "word": " the", "probability": 0.8095703125 }, { "start": 4154.28, "end": 4154.92, "word": " multinomial", "probability": 0.8984375 }, { "start": 4154.92, "end": 4155.08, "word": " with", "probability": 0.75732421875 }, { "start": 4155.08, "end": 4155.16, "word": " the", "probability": 0.62939453125 }, { "start": 4155.16, "end": 4155.32, "word": " count", "probability": 0.7509765625 }, { "start": 4155.32, "end": 4155.88, "word": " vectorizer", "probability": 0.95556640625 }, { "start": 4155.88, "end": 4156.02, "word": ".", "probability": 0.96484375 } ] }, { "id": 1604, "seek": 409760, "start": 4156.02, "end": 4160.14, "text": " We have a 95.9% accuracy.", "tokens": [ 50364, 492, 362, 257, 13420, 13, 24, 4, 14170, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.19917384612149205, "compression_ratio": 1.6435185185185186, "no_speech_prob": 0.0004582405090332031, "words": [ { "start": 4156.02, "end": 4156.08, "word": " We", "probability": 0.498779296875 }, { "start": 4156.08, "end": 4156.22, "word": " have", "probability": 0.8857421875 }, { "start": 4156.48, "end": 4157.0, "word": " a 95", "probability": 0.8974609375 }, { "start": 4157.0, "end": 4158.12, "word": ".9", "probability": 0.99609375 }, { "start": 4158.12, "end": 4158.68, "word": "%", "probability": 0.943359375 }, { "start": 4158.68, "end": 4159.42, "word": " accuracy", "probability": 0.74072265625 }, { "start": 4159.42, "end": 4160.14, "word": ".", "probability": 0.91943359375 } ] }, { "id": 1605, "seek": 409760, "start": 4160.4, "end": 4164.88, "text": " We see that we have a little bit more than the 26 ham emails", "tokens": [ 50564, 492, 536, 300, 321, 362, 257, 707, 857, 544, 813, 264, 7551, 7852, 12524, 50764 ], "temperature": 0.0, "avg_logprob": -0.19917384612149205, "compression_ratio": 1.6435185185185186, "no_speech_prob": 0.0004582405090332031, "words": [ { "start": 4160.4, "end": 4160.88, "word": " We", "probability": 0.896484375 }, { "start": 4160.88, "end": 4161.04, "word": " see", "probability": 0.81298828125 }, { "start": 4161.04, "end": 4161.2, "word": " that", "probability": 0.88037109375 }, { "start": 4161.2, "end": 4161.34, "word": " we", "probability": 0.90625 }, { "start": 4161.34, "end": 4161.84, "word": " have", "probability": 0.8798828125 }, { "start": 4162.42, "end": 4162.52, "word": " a little", "probability": 0.8056640625 }, { "start": 4162.52, "end": 4162.64, "word": " bit", "probability": 0.89208984375 }, { "start": 4162.64, "end": 4162.84, "word": " more", "probability": 0.880859375 }, { "start": 4162.84, "end": 4163.0, "word": " than", "probability": 0.88427734375 }, { "start": 4163.0, "end": 4163.14, "word": " the", "probability": 0.81005859375 }, { "start": 4163.14, "end": 4163.78, "word": " 26", "probability": 0.89892578125 }, { "start": 4163.78, "end": 4164.48, "word": " ham", "probability": 0.428955078125 }, { "start": 4164.48, "end": 4164.88, "word": " emails", "probability": 0.79736328125 } ] }, { "id": 1606, "seek": 409760, "start": 4164.88, "end": 4167.28, "text": " that were incorrectly classified as spam.", "tokens": [ 50764, 300, 645, 42892, 20627, 382, 24028, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.19917384612149205, "compression_ratio": 1.6435185185185186, "no_speech_prob": 0.0004582405090332031, "words": [ { "start": 4164.88, "end": 4165.06, "word": " that", "probability": 0.8779296875 }, { "start": 4165.06, "end": 4165.24, "word": " were", "probability": 0.87353515625 }, { "start": 4165.24, "end": 4165.76, "word": " incorrectly", "probability": 0.8447265625 }, { "start": 4165.76, "end": 4166.28, "word": " classified", "probability": 0.931640625 }, { "start": 4166.28, "end": 4166.56, "word": " as", "probability": 0.91064453125 }, { "start": 4166.56, "end": 4166.9, "word": " spam", "probability": 0.92919921875 }, { "start": 4166.9, "end": 4167.28, "word": ".", "probability": 0.45849609375 } ] }, { "id": 1607, "seek": 409760, "start": 4167.28, "end": 4171.9, "text": " We have significantly fewer of the spam emails being classified as ham.", "tokens": [ 50914, 492, 362, 10591, 13366, 295, 264, 24028, 12524, 885, 20627, 382, 7852, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.19917384612149205, "compression_ratio": 1.6435185185185186, "no_speech_prob": 0.0004582405090332031, "words": [ { "start": 4167.28, "end": 4167.46, "word": " We", "probability": 0.326171875 }, { "start": 4167.46, "end": 4167.58, "word": " have", "probability": 0.88232421875 }, { "start": 4167.58, "end": 4168.06, "word": " significantly", "probability": 0.86328125 }, { "start": 4168.06, "end": 4168.76, "word": " fewer", "probability": 0.7412109375 }, { "start": 4168.76, "end": 4169.18, "word": " of", "probability": 0.89990234375 }, { "start": 4169.18, "end": 4169.32, "word": " the", "probability": 0.8125 }, { "start": 4169.32, "end": 4169.66, "word": " spam", "probability": 0.9052734375 }, { "start": 4169.66, "end": 4170.04, "word": " emails", "probability": 0.77099609375 }, { "start": 4170.04, "end": 4170.24, "word": " being", "probability": 0.86181640625 }, { "start": 4170.24, "end": 4170.58, "word": " classified", "probability": 0.93603515625 }, { "start": 4170.58, "end": 4170.88, "word": " as", "probability": 0.91357421875 }, { "start": 4170.88, "end": 4171.18, "word": " ham", "probability": 0.84130859375 }, { "start": 4171.18, "end": 4171.9, "word": ".", "probability": 0.8857421875 } ] }, { "id": 1608, "seek": 409760, "start": 4172.1, "end": 4176.26, "text": " So this would be a perfect instance of moving towards", "tokens": [ 51164, 407, 341, 576, 312, 257, 2176, 5197, 295, 2684, 3030, 51364 ], "temperature": 0.0, "avg_logprob": -0.19917384612149205, "compression_ratio": 1.6435185185185186, "no_speech_prob": 0.0004582405090332031, "words": [ { "start": 4172.1, "end": 4172.3, "word": " So", "probability": 0.87060546875 }, { "start": 4172.3, "end": 4172.44, "word": " this", "probability": 0.8173828125 }, { "start": 4172.44, "end": 4172.56, "word": " would", "probability": 0.83642578125 }, { "start": 4172.56, "end": 4172.66, "word": " be", "probability": 0.9033203125 }, { "start": 4172.8, "end": 4173.04, "word": " a perfect", "probability": 0.84716796875 }, { "start": 4173.04, "end": 4173.62, "word": " instance", "probability": 0.90966796875 }, { "start": 4173.62, "end": 4174.08, "word": " of", "probability": 0.8876953125 }, { "start": 4174.08, "end": 4175.9, "word": " moving", "probability": 0.422607421875 }, { "start": 4175.9, "end": 4176.26, "word": " towards", "probability": 0.6396484375 } ] }, { "id": 1609, "seek": 409760, "start": 4176.6, "end": 4179.9, "text": " having absolutely zero spam get through our filter", "tokens": [ 51364, 1419, 3122, 4018, 24028, 483, 807, 527, 6608, 51564 ], "temperature": 0.0, "avg_logprob": -0.19917384612149205, "compression_ratio": 1.6435185185185186, "no_speech_prob": 0.0004582405090332031, "words": [ { "start": 4176.6, "end": 4177.12, "word": " having", "probability": 0.78759765625 }, { "start": 4177.12, "end": 4177.52, "word": " absolutely", "probability": 0.7021484375 }, { "start": 4177.52, "end": 4178.02, "word": " zero", "probability": 0.8291015625 }, { "start": 4178.02, "end": 4178.7, "word": " spam", "probability": 0.8974609375 }, { "start": 4178.7, "end": 4179.12, "word": " get", "probability": 0.85107421875 }, { "start": 4179.12, "end": 4179.32, "word": " through", "probability": 0.79736328125 }, { "start": 4179.32, "end": 4179.54, "word": " our", "probability": 0.81494140625 }, { "start": 4179.54, "end": 4179.9, "word": " filter", "probability": 0.89404296875 } ] }, { "id": 1610, "seek": 409760, "start": 4179.9, "end": 4184.84, "text": " at the risk of losing some of our regular emails.", "tokens": [ 51564, 412, 264, 3148, 295, 7027, 512, 295, 527, 3890, 12524, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.19917384612149205, "compression_ratio": 1.6435185185185186, "no_speech_prob": 0.0004582405090332031, "words": [ { "start": 4179.9, "end": 4180.7, "word": " at", "probability": 0.7919921875 }, { "start": 4180.7, "end": 4181.06, "word": " the", "probability": 0.81591796875 }, { "start": 4181.06, "end": 4181.84, "word": " risk", "probability": 0.78759765625 }, { "start": 4181.84, "end": 4182.16, "word": " of", "probability": 0.90380859375 }, { "start": 4182.16, "end": 4182.7, "word": " losing", "probability": 0.8125 }, { "start": 4182.7, "end": 4183.34, "word": " some", "probability": 0.8134765625 }, { "start": 4183.34, "end": 4183.48, "word": " of", "probability": 0.90625 }, { "start": 4183.48, "end": 4183.64, "word": " our", "probability": 0.8134765625 }, { "start": 4183.64, "end": 4183.94, "word": " regular", "probability": 0.89404296875 }, { "start": 4183.94, "end": 4184.48, "word": " emails", "probability": 0.751953125 }, { "start": 4184.48, "end": 4184.84, "word": ".", "probability": 0.99658203125 } ] }, { "id": 1611, "seek": 412568, "start": 4186.02, "end": 4189.38, "text": " But what I want to show is how the accuracy improves", "tokens": [ 50364, 583, 437, 286, 528, 281, 855, 307, 577, 264, 14170, 24771, 50514 ], "temperature": 0.0, "avg_logprob": -0.17127975849878221, "compression_ratio": 1.65625, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4186.02, "end": 4186.34, "word": " But", "probability": 0.347412109375 }, { "start": 4186.34, "end": 4186.5, "word": " what", "probability": 0.84375 }, { "start": 4186.5, "end": 4186.58, "word": " I", "probability": 0.98828125 }, { "start": 4186.58, "end": 4186.68, "word": " want", "probability": 0.6953125 }, { "start": 4186.68, "end": 4186.78, "word": " to", "probability": 0.908203125 }, { "start": 4186.78, "end": 4186.96, "word": " show", "probability": 0.88134765625 }, { "start": 4186.96, "end": 4187.18, "word": " is", "probability": 0.88134765625 }, { "start": 4187.18, "end": 4187.36, "word": " how", "probability": 0.8984375 }, { "start": 4187.36, "end": 4187.66, "word": " the", "probability": 0.8076171875 }, { "start": 4187.66, "end": 4188.4, "word": " accuracy", "probability": 0.6787109375 }, { "start": 4188.4, "end": 4189.38, "word": " improves", "probability": 0.802734375 } ] }, { "id": 1612, "seek": 412568, "start": 4189.38, "end": 4192.88, "text": " just changing the algorithm itself.", "tokens": [ 50514, 445, 4473, 264, 9284, 2564, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.17127975849878221, "compression_ratio": 1.65625, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4189.38, "end": 4190.42, "word": " just", "probability": 0.430419921875 }, { "start": 4190.42, "end": 4190.96, "word": " changing", "probability": 0.80419921875 }, { "start": 4190.96, "end": 4191.38, "word": " the", "probability": 0.81005859375 }, { "start": 4191.38, "end": 4191.82, "word": " algorithm", "probability": 0.81591796875 }, { "start": 4191.82, "end": 4192.48, "word": " itself", "probability": 0.779296875 }, { "start": 4192.48, "end": 4192.88, "word": ".", "probability": 0.64111328125 } ] }, { "id": 1613, "seek": 412568, "start": 4192.88, "end": 4195.7, "text": " And then looking at multinomial Naive Bayesian", "tokens": [ 50664, 400, 550, 1237, 412, 45872, 47429, 6056, 488, 7840, 42434, 50814 ], "temperature": 0.0, "avg_logprob": -0.17127975849878221, "compression_ratio": 1.65625, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4192.88, "end": 4192.9, "word": " And", "probability": 0.6474609375 }, { "start": 4192.9, "end": 4193.16, "word": " then", "probability": 0.75 }, { "start": 4193.16, "end": 4193.86, "word": " looking", "probability": 0.736328125 }, { "start": 4193.86, "end": 4194.5, "word": " at", "probability": 0.69970703125 }, { "start": 4194.5, "end": 4194.96, "word": " multinomial", "probability": 0.908935546875 }, { "start": 4194.96, "end": 4195.36, "word": " Naive", "probability": 0.705078125 }, { "start": 4195.36, "end": 4195.7, "word": " Bayesian", "probability": 0.9130859375 } ] }, { "id": 1614, "seek": 412568, "start": 4195.7, "end": 4199.64, "text": " compared to logistic regression both using TF-IDF.", "tokens": [ 50814, 5347, 281, 3565, 3142, 24590, 1293, 1228, 40964, 12, 2777, 37, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.17127975849878221, "compression_ratio": 1.65625, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4195.7, "end": 4196.12, "word": " compared", "probability": 0.73828125 }, { "start": 4196.12, "end": 4197.14, "word": " to", "probability": 0.89990234375 }, { "start": 4197.14, "end": 4197.66, "word": " logistic", "probability": 0.888427734375 }, { "start": 4197.66, "end": 4198.06, "word": " regression", "probability": 0.91259765625 }, { "start": 4198.06, "end": 4198.48, "word": " both", "probability": 0.403076171875 }, { "start": 4198.48, "end": 4198.74, "word": " using", "probability": 0.794921875 }, { "start": 4198.74, "end": 4199.04, "word": " TF", "probability": 0.81689453125 }, { "start": 4199.04, "end": 4199.5, "word": "-IDF", "probability": 0.9371744791666666 }, { "start": 4199.5, "end": 4199.64, "word": ".", "probability": 0.11962890625 } ] }, { "id": 1615, "seek": 412568, "start": 4199.64, "end": 4202.32, "text": " We had 87.5% for the multinomial", "tokens": [ 51014, 492, 632, 27990, 13, 20, 4, 337, 264, 45872, 47429, 51164 ], "temperature": 0.0, "avg_logprob": -0.17127975849878221, "compression_ratio": 1.65625, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4199.64, "end": 4199.7, "word": " We", "probability": 0.8876953125 }, { "start": 4199.7, "end": 4199.96, "word": " had", "probability": 0.8154296875 }, { "start": 4199.96, "end": 4200.5, "word": " 87", "probability": 0.88623046875 }, { "start": 4200.5, "end": 4201.14, "word": ".5", "probability": 0.997314453125 }, { "start": 4201.14, "end": 4201.38, "word": "%", "probability": 0.86865234375 }, { "start": 4201.38, "end": 4201.72, "word": " for", "probability": 0.88720703125 }, { "start": 4201.72, "end": 4201.98, "word": " the", "probability": 0.8115234375 }, { "start": 4201.98, "end": 4202.32, "word": " multinomial", "probability": 0.938232421875 } ] }, { "id": 1616, "seek": 412568, "start": 4202.6, "end": 4206.72, "text": " and then we have 95.9% for the logistic regression.", "tokens": [ 51164, 293, 550, 321, 362, 13420, 13, 24, 4, 337, 264, 3565, 3142, 24590, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.17127975849878221, "compression_ratio": 1.65625, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4202.6, "end": 4202.98, "word": " and", "probability": 0.515625 }, { "start": 4202.98, "end": 4203.12, "word": " then", "probability": 0.724609375 }, { "start": 4203.12, "end": 4203.24, "word": " we", "probability": 0.89697265625 }, { "start": 4203.24, "end": 4203.5, "word": " have", "probability": 0.8876953125 }, { "start": 4203.5, "end": 4204.18, "word": " 95", "probability": 0.912109375 }, { "start": 4204.18, "end": 4204.84, "word": ".9", "probability": 0.998046875 }, { "start": 4204.84, "end": 4205.3, "word": "%", "probability": 0.98388671875 }, { "start": 4205.3, "end": 4205.68, "word": " for", "probability": 0.84375 }, { "start": 4205.68, "end": 4205.8, "word": " the", "probability": 0.8095703125 }, { "start": 4205.8, "end": 4206.08, "word": " logistic", "probability": 0.94189453125 }, { "start": 4206.08, "end": 4206.46, "word": " regression", "probability": 0.8671875 }, { "start": 4206.46, "end": 4206.72, "word": ".", "probability": 0.95947265625 } ] }, { "id": 1617, "seek": 412568, "start": 4206.72, "end": 4209.72, "text": " So far, logistic regression is kind of beating out multinomial", "tokens": [ 51364, 407, 1400, 11, 3565, 3142, 24590, 307, 733, 295, 13497, 484, 45872, 47429, 51514 ], "temperature": 0.0, "avg_logprob": -0.17127975849878221, "compression_ratio": 1.65625, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4206.72, "end": 4206.72, "word": " So", "probability": 0.896484375 }, { "start": 4206.72, "end": 4207.32, "word": " far", "probability": 0.83642578125 }, { "start": 4207.32, "end": 4207.46, "word": ",", "probability": 0.402587890625 }, { "start": 4207.46, "end": 4207.78, "word": " logistic", "probability": 0.899658203125 }, { "start": 4207.78, "end": 4208.12, "word": " regression", "probability": 0.890625 }, { "start": 4208.12, "end": 4208.36, "word": " is", "probability": 0.87841796875 }, { "start": 4208.36, "end": 4208.5, "word": " kind", "probability": 0.73291015625 }, { "start": 4208.5, "end": 4208.6, "word": " of", "probability": 0.9013671875 }, { "start": 4208.6, "end": 4208.84, "word": " beating", "probability": 0.8525390625 }, { "start": 4208.84, "end": 4209.1, "word": " out", "probability": 0.79052734375 }, { "start": 4209.1, "end": 4209.72, "word": " multinomial", "probability": 0.93505859375 } ] }, { "id": 1618, "seek": 412568, "start": 4209.72, "end": 4214.1, "text": " in the TF-IDF and the count metrics.", "tokens": [ 51514, 294, 264, 40964, 12, 2777, 37, 293, 264, 1207, 16367, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.17127975849878221, "compression_ratio": 1.65625, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4209.72, "end": 4210.24, "word": " in", "probability": 0.88330078125 }, { "start": 4210.24, "end": 4211.42, "word": " the", "probability": 0.7958984375 }, { "start": 4211.42, "end": 4211.74, "word": " TF", "probability": 0.91015625 }, { "start": 4211.74, "end": 4212.14, "word": "-IDF", "probability": 0.9910481770833334 }, { "start": 4212.14, "end": 4212.42, "word": " and", "probability": 0.8916015625 }, { "start": 4212.42, "end": 4212.64, "word": " the", "probability": 0.80322265625 }, { "start": 4212.64, "end": 4212.94, "word": " count", "probability": 0.7451171875 }, { "start": 4212.94, "end": 4213.42, "word": " metrics", "probability": 0.68408203125 }, { "start": 4213.42, "end": 4214.1, "word": ".", "probability": 0.99462890625 } ] }, { "id": 1619, "seek": 415130, "start": 4214.1, "end": 4216.68, "text": " So we're going to do our last one which is going to be", "tokens": [ 50364, 407, 321, 434, 516, 281, 360, 527, 1036, 472, 597, 307, 516, 281, 312, 50514 ], "temperature": 0.0, "avg_logprob": -0.21153845981909677, "compression_ratio": 1.7853658536585366, "no_speech_prob": 0.0009851455688476562, "words": [ { "start": 4214.1, "end": 4214.6, "word": " So", "probability": 0.31787109375 }, { "start": 4214.6, "end": 4214.76, "word": " we're", "probability": 0.8623046875 }, { "start": 4214.76, "end": 4214.76, "word": " going", "probability": 0.4619140625 }, { "start": 4214.76, "end": 4214.8, "word": " to", "probability": 0.90478515625 }, { "start": 4214.8, "end": 4214.9, "word": " do", "probability": 0.91015625 }, { "start": 4214.9, "end": 4215.0, "word": " our", "probability": 0.7919921875 }, { "start": 4215.0, "end": 4215.34, "word": " last", "probability": 0.81396484375 }, { "start": 4215.34, "end": 4215.66, "word": " one", "probability": 0.818359375 }, { "start": 4215.66, "end": 4215.94, "word": " which", "probability": 0.394287109375 }, { "start": 4215.94, "end": 4216.06, "word": " is", "probability": 0.91162109375 }, { "start": 4216.06, "end": 4216.2, "word": " going", "probability": 0.8466796875 }, { "start": 4216.2, "end": 4216.36, "word": " to", "probability": 0.908203125 }, { "start": 4216.36, "end": 4216.68, "word": " be", "probability": 0.91064453125 } ] }, { "id": 1620, "seek": 415130, "start": 4219.98, "end": 4223.76, "text": " logistic regression with count vectorizer.", "tokens": [ 50514, 3565, 3142, 24590, 365, 1207, 8062, 6545, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.21153845981909677, "compression_ratio": 1.7853658536585366, "no_speech_prob": 0.0009851455688476562, "words": [ { "start": 4219.98, "end": 4220.4, "word": " logistic", "probability": 0.60601806640625 }, { "start": 4220.4, "end": 4220.82, "word": " regression", "probability": 0.896484375 }, { "start": 4220.82, "end": 4222.16, "word": " with", "probability": 0.76611328125 }, { "start": 4222.16, "end": 4222.84, "word": " count", "probability": 0.7216796875 }, { "start": 4222.84, "end": 4223.48, "word": " vectorizer", "probability": 0.933837890625 }, { "start": 4223.48, "end": 4223.76, "word": ".", "probability": 0.84619140625 } ] }, { "id": 1621, "seek": 415130, "start": 4223.76, "end": 4225.84, "text": " Count vectorizer worked well for multinomial", "tokens": [ 50814, 5247, 8062, 6545, 2732, 731, 337, 45872, 47429, 50964 ], "temperature": 0.0, "avg_logprob": -0.21153845981909677, "compression_ratio": 1.7853658536585366, "no_speech_prob": 0.0009851455688476562, "words": [ { "start": 4223.76, "end": 4224.16, "word": " Count", "probability": 0.6875 }, { "start": 4224.16, "end": 4224.52, "word": " vectorizer", "probability": 0.94775390625 }, { "start": 4224.52, "end": 4224.76, "word": " worked", "probability": 0.72900390625 }, { "start": 4224.76, "end": 4224.94, "word": " well", "probability": 0.873046875 }, { "start": 4224.94, "end": 4225.18, "word": " for", "probability": 0.90380859375 }, { "start": 4225.18, "end": 4225.84, "word": " multinomial", "probability": 0.5311279296875 } ] }, { "id": 1622, "seek": 415130, "start": 4225.84, "end": 4228.86, "text": " so let's see if it works well for logistic regression.", "tokens": [ 50964, 370, 718, 311, 536, 498, 309, 1985, 731, 337, 3565, 3142, 24590, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.21153845981909677, "compression_ratio": 1.7853658536585366, "no_speech_prob": 0.0009851455688476562, "words": [ { "start": 4225.84, "end": 4226.06, "word": " so", "probability": 0.292236328125 }, { "start": 4226.06, "end": 4226.3, "word": " let's", "probability": 0.9267578125 }, { "start": 4226.3, "end": 4226.44, "word": " see", "probability": 0.8076171875 }, { "start": 4226.44, "end": 4226.56, "word": " if", "probability": 0.90576171875 }, { "start": 4226.56, "end": 4226.68, "word": " it", "probability": 0.89990234375 }, { "start": 4226.68, "end": 4226.86, "word": " works", "probability": 0.70654296875 }, { "start": 4226.86, "end": 4227.14, "word": " well", "probability": 0.8759765625 }, { "start": 4227.14, "end": 4227.54, "word": " for", "probability": 0.8984375 }, { "start": 4227.54, "end": 4228.22, "word": " logistic", "probability": 0.949462890625 }, { "start": 4228.22, "end": 4228.6, "word": " regression", "probability": 0.716796875 }, { "start": 4228.6, "end": 4228.86, "word": ".", "probability": 0.80810546875 } ] }, { "id": 1623, "seek": 415130, "start": 4228.86, "end": 4230.96, "text": " So we're going to do LGS count.", "tokens": [ 51114, 407, 321, 434, 516, 281, 360, 441, 24446, 1207, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.21153845981909677, "compression_ratio": 1.7853658536585366, "no_speech_prob": 0.0009851455688476562, "words": [ { "start": 4228.86, "end": 4228.9, "word": " So", "probability": 0.5166015625 }, { "start": 4228.9, "end": 4229.04, "word": " we're", "probability": 0.8818359375 }, { "start": 4229.04, "end": 4229.04, "word": " going", "probability": 0.69921875 }, { "start": 4229.04, "end": 4229.08, "word": " to", "probability": 0.90087890625 }, { "start": 4229.08, "end": 4229.2, "word": " do", "probability": 0.8876953125 }, { "start": 4229.2, "end": 4229.7, "word": " LGS", "probability": 0.590087890625 }, { "start": 4229.7, "end": 4230.54, "word": " count", "probability": 0.447998046875 }, { "start": 4230.54, "end": 4230.96, "word": ".", "probability": 0.5341796875 } ] }, { "id": 1624, "seek": 415130, "start": 4236.55, "end": 4238.07, "text": " And I'm just going to type this out", "tokens": [ 51264, 400, 286, 478, 445, 516, 281, 2010, 341, 484, 51414 ], "temperature": 0.0, "avg_logprob": -0.21153845981909677, "compression_ratio": 1.7853658536585366, "no_speech_prob": 0.0009851455688476562, "words": [ { "start": 4236.55, "end": 4236.97, "word": " And", "probability": 0.56787109375 }, { "start": 4236.97, "end": 4237.13, "word": " I'm", "probability": 0.982177734375 }, { "start": 4237.13, "end": 4237.27, "word": " just", "probability": 0.87841796875 }, { "start": 4237.27, "end": 4237.39, "word": " going", "probability": 0.81298828125 }, { "start": 4237.39, "end": 4237.47, "word": " to", "probability": 0.90576171875 }, { "start": 4237.47, "end": 4237.67, "word": " type", "probability": 0.904296875 }, { "start": 4237.67, "end": 4237.87, "word": " this", "probability": 0.88232421875 }, { "start": 4237.87, "end": 4238.07, "word": " out", "probability": 0.81640625 } ] }, { "id": 1625, "seek": 415130, "start": 4238.07, "end": 4241.31, "text": " but you can use the same copy-paste trick that I used for the multinomial", "tokens": [ 51414, 457, 291, 393, 764, 264, 912, 5055, 12, 79, 9079, 4282, 300, 286, 1143, 337, 264, 45872, 47429, 51564 ], "temperature": 0.0, "avg_logprob": -0.21153845981909677, "compression_ratio": 1.7853658536585366, "no_speech_prob": 0.0009851455688476562, "words": [ { "start": 4238.07, "end": 4238.21, "word": " but", "probability": 0.58349609375 }, { "start": 4238.21, "end": 4238.33, "word": " you", "probability": 0.892578125 }, { "start": 4238.33, "end": 4238.45, "word": " can", "probability": 0.89599609375 }, { "start": 4238.45, "end": 4238.63, "word": " use", "probability": 0.8076171875 }, { "start": 4238.63, "end": 4238.79, "word": " the", "probability": 0.81103515625 }, { "start": 4238.79, "end": 4238.99, "word": " same", "probability": 0.83544921875 }, { "start": 4238.99, "end": 4239.31, "word": " copy", "probability": 0.82568359375 }, { "start": 4239.31, "end": 4239.67, "word": "-paste", "probability": 0.6490071614583334 }, { "start": 4239.67, "end": 4239.91, "word": " trick", "probability": 0.8466796875 }, { "start": 4239.91, "end": 4240.17, "word": " that", "probability": 0.85888671875 }, { "start": 4240.17, "end": 4240.35, "word": " I", "probability": 0.98828125 }, { "start": 4240.35, "end": 4240.51, "word": " used", "probability": 0.7412109375 }, { "start": 4240.51, "end": 4240.65, "word": " for", "probability": 0.89453125 }, { "start": 4240.65, "end": 4240.75, "word": " the", "probability": 0.80859375 }, { "start": 4240.75, "end": 4241.31, "word": " multinomial", "probability": 0.9365234375 } ] }, { "id": 1626, "seek": 415130, "start": 4241.31, "end": 4242.81, "text": " with the count vectorizer.", "tokens": [ 51564, 365, 264, 1207, 8062, 6545, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.21153845981909677, "compression_ratio": 1.7853658536585366, "no_speech_prob": 0.0009851455688476562, "words": [ { "start": 4241.31, "end": 4241.55, "word": " with", "probability": 0.80029296875 }, { "start": 4241.55, "end": 4241.65, "word": " the", "probability": 0.7294921875 }, { "start": 4241.65, "end": 4241.85, "word": " count", "probability": 0.76904296875 }, { "start": 4241.85, "end": 4242.39, "word": " vectorizer", "probability": 0.951416015625 }, { "start": 4242.39, "end": 4242.81, "word": ".", "probability": 0.93359375 } ] }, { "id": 1627, "seek": 417922, "start": 4244.67, "end": 4248.03, "text": " I'm just doing this as a way to kind of slow myself down", "tokens": [ 50414, 286, 478, 445, 884, 341, 382, 257, 636, 281, 733, 295, 2964, 2059, 760, 50614 ], "temperature": 0.0, "avg_logprob": -0.2566964220214676, "compression_ratio": 1.4541062801932367, "no_speech_prob": 0.0015974044799804688, "words": [ { "start": 4244.67, "end": 4245.11, "word": " I'm", "probability": 0.760498046875 }, { "start": 4245.11, "end": 4245.27, "word": " just", "probability": 0.85888671875 }, { "start": 4245.27, "end": 4245.49, "word": " doing", "probability": 0.90673828125 }, { "start": 4245.49, "end": 4245.79, "word": " this", "probability": 0.880859375 }, { "start": 4245.79, "end": 4246.13, "word": " as", "probability": 0.896484375 }, { "start": 4246.47, "end": 4246.63, "word": " a way", "probability": 0.88818359375 }, { "start": 4246.63, "end": 4246.75, "word": " to", "probability": 0.9033203125 }, { "start": 4246.75, "end": 4246.87, "word": " kind", "probability": 0.52392578125 }, { "start": 4246.87, "end": 4246.95, "word": " of", "probability": 0.9052734375 }, { "start": 4246.95, "end": 4247.15, "word": " slow", "probability": 0.83251953125 }, { "start": 4247.15, "end": 4247.59, "word": " myself", "probability": 0.6884765625 }, { "start": 4247.59, "end": 4248.03, "word": " down", "probability": 0.82275390625 } ] }, { "id": 1628, "seek": 417922, "start": 4248.03, "end": 4252.13, "text": " so that you all have an opportunity to copy the code.", "tokens": [ 50614, 370, 300, 291, 439, 362, 364, 2650, 281, 5055, 264, 3089, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.2566964220214676, "compression_ratio": 1.4541062801932367, "no_speech_prob": 0.0015974044799804688, "words": [ { "start": 4248.03, "end": 4248.49, "word": " so", "probability": 0.64697265625 }, { "start": 4248.49, "end": 4248.59, "word": " that", "probability": 0.8544921875 }, { "start": 4248.59, "end": 4248.69, "word": " you", "probability": 0.89990234375 }, { "start": 4248.69, "end": 4248.83, "word": " all", "probability": 0.84912109375 }, { "start": 4248.83, "end": 4249.01, "word": " have", "probability": 0.86669921875 }, { "start": 4249.01, "end": 4249.15, "word": " an", "probability": 0.90234375 }, { "start": 4249.15, "end": 4249.59, "word": " opportunity", "probability": 0.81494140625 }, { "start": 4249.59, "end": 4250.29, "word": " to", "probability": 0.90625 }, { "start": 4250.29, "end": 4251.25, "word": " copy", "probability": 0.7802734375 }, { "start": 4251.25, "end": 4251.43, "word": " the", "probability": 0.76123046875 }, { "start": 4251.43, "end": 4251.69, "word": " code", "probability": 0.81982421875 }, { "start": 4251.69, "end": 4252.13, "word": ".", "probability": 0.8603515625 } ] }, { "id": 1629, "seek": 417922, "start": 4252.35, "end": 4254.15, "text": " So LBFGS.", "tokens": [ 50814, 407, 441, 33, 37, 24446, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.2566964220214676, "compression_ratio": 1.4541062801932367, "no_speech_prob": 0.0015974044799804688, "words": [ { "start": 4252.35, "end": 4252.47, "word": " So", "probability": 0.71728515625 }, { "start": 4252.47, "end": 4253.71, "word": " LBFGS", "probability": 0.677398681640625 }, { "start": 4253.71, "end": 4254.15, "word": ".", "probability": 0.260009765625 } ] }, { "id": 1630, "seek": 417922, "start": 4254.57, "end": 4263.5, "text": " We're going to fit our labels.", "tokens": [ 50964, 492, 434, 516, 281, 3318, 527, 16949, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.2566964220214676, "compression_ratio": 1.4541062801932367, "no_speech_prob": 0.0015974044799804688, "words": [ { "start": 4254.57, "end": 4255.01, "word": " We're", "probability": 0.7353515625 }, { "start": 4255.01, "end": 4255.07, "word": " going", "probability": 0.43115234375 }, { "start": 4255.07, "end": 4255.21, "word": " to", "probability": 0.896484375 }, { "start": 4255.21, "end": 4255.63, "word": " fit", "probability": 0.7587890625 }, { "start": 4255.63, "end": 4258.19, "word": " our", "probability": 0.38720703125 }, { "start": 4262.54, "end": 4263.1, "word": " labels", "probability": 0.83251953125 }, { "start": 4263.1, "end": 4263.5, "word": ".", "probability": 0.2318115234375 } ] }, { "id": 1631, "seek": 417922, "start": 4263.5, "end": 4266.5, "text": " And we got to do our scores, predictions,", "tokens": [ 51164, 400, 321, 658, 281, 360, 527, 13444, 11, 21264, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.2566964220214676, "compression_ratio": 1.4541062801932367, "no_speech_prob": 0.0015974044799804688, "words": [ { "start": 4263.5, "end": 4263.62, "word": " And", "probability": 0.441162109375 }, { "start": 4263.62, "end": 4263.72, "word": " we", "probability": 0.6552734375 }, { "start": 4263.72, "end": 4263.8, "word": " got", "probability": 0.453125 }, { "start": 4263.8, "end": 4263.86, "word": " to", "probability": 0.89501953125 }, { "start": 4263.86, "end": 4263.98, "word": " do", "probability": 0.91015625 }, { "start": 4263.98, "end": 4264.1, "word": " our", "probability": 0.818359375 }, { "start": 4264.1, "end": 4264.58, "word": " scores", "probability": 0.72705078125 }, { "start": 4264.58, "end": 4264.76, "word": ",", "probability": 0.865234375 }, { "start": 4264.76, "end": 4265.32, "word": " predictions", "probability": 0.7392578125 }, { "start": 4265.32, "end": 4266.5, "word": ",", "probability": 0.955078125 } ] }, { "id": 1632, "seek": 417922, "start": 4266.5, "end": 4268.94, "text": " confusion matrix, and classification report.", "tokens": [ 51314, 15075, 8141, 11, 293, 21538, 2275, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.2566964220214676, "compression_ratio": 1.4541062801932367, "no_speech_prob": 0.0015974044799804688, "words": [ { "start": 4266.5, "end": 4266.82, "word": " confusion", "probability": 0.83642578125 }, { "start": 4266.82, "end": 4267.18, "word": " matrix", "probability": 0.84130859375 }, { "start": 4267.18, "end": 4267.4, "word": ",", "probability": 0.681640625 }, { "start": 4267.4, "end": 4267.52, "word": " and", "probability": 0.8955078125 }, { "start": 4267.52, "end": 4268.04, "word": " classification", "probability": 0.93017578125 }, { "start": 4268.04, "end": 4268.5, "word": " report", "probability": 0.85400390625 }, { "start": 4268.5, "end": 4268.94, "word": ".", "probability": 0.99560546875 } ] }, { "id": 1633, "seek": 417922, "start": 4278.73, "end": 4279.99, "text": " Yeah, one of the things", "tokens": [ 51464, 865, 11, 472, 295, 264, 721, 51614 ], "temperature": 0.0, "avg_logprob": -0.2566964220214676, "compression_ratio": 1.4541062801932367, "no_speech_prob": 0.0015974044799804688, "words": [ { "start": 4278.73, "end": 4279.15, "word": " Yeah", "probability": 0.83984375 }, { "start": 4279.15, "end": 4279.21, "word": ",", "probability": 0.6943359375 }, { "start": 4279.21, "end": 4279.37, "word": " one", "probability": 0.80615234375 }, { "start": 4279.37, "end": 4279.47, "word": " of", "probability": 0.9072265625 }, { "start": 4279.47, "end": 4279.59, "word": " the", "probability": 0.81591796875 }, { "start": 4279.59, "end": 4279.99, "word": " things", "probability": 0.73291015625 } ] }, { "id": 1634, "seek": 417922, "start": 4281.09, "end": 4283.07, "text": " that you kind of reminded me of, Sven,", "tokens": [ 51614, 300, 291, 733, 295, 15920, 385, 295, 11, 49787, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.2566964220214676, "compression_ratio": 1.4541062801932367, "no_speech_prob": 0.0015974044799804688, "words": [ { "start": 4281.09, "end": 4281.53, "word": " that", "probability": 0.86474609375 }, { "start": 4281.53, "end": 4281.65, "word": " you", "probability": 0.8701171875 }, { "start": 4281.65, "end": 4281.79, "word": " kind", "probability": 0.8154296875 }, { "start": 4281.79, "end": 4281.87, "word": " of", "probability": 0.90380859375 }, { "start": 4281.87, "end": 4282.13, "word": " reminded", "probability": 0.796875 }, { "start": 4282.13, "end": 4282.37, "word": " me", "probability": 0.9052734375 }, { "start": 4282.37, "end": 4282.59, "word": " of", "probability": 0.89501953125 }, { "start": 4282.59, "end": 4282.85, "word": ",", "probability": 0.65380859375 }, { "start": 4282.85, "end": 4283.01, "word": " Sven", "probability": 0.94873046875 }, { "start": 4283.01, "end": 4283.07, "word": ",", "probability": 0.93408203125 } ] }, { "id": 1635, "seek": 420502, "start": 4283.07, "end": 4285.15, "text": " when you've been talking about the different trees and algorithms", "tokens": [ 50364, 562, 291, 600, 668, 1417, 466, 264, 819, 5852, 293, 14642, 50514 ], "temperature": 0.0, "avg_logprob": -0.24371603374247966, "compression_ratio": 1.6849315068493151, "no_speech_prob": 0.0433349609375, "words": [ { "start": 4283.07, "end": 4283.07, "word": " when", "probability": 0.005771636962890625 }, { "start": 4283.07, "end": 4283.11, "word": " you've", "probability": 0.05950164794921875 }, { "start": 4283.11, "end": 4283.11, "word": " been", "probability": 0.71337890625 }, { "start": 4283.11, "end": 4283.33, "word": " talking", "probability": 0.7607421875 }, { "start": 4283.33, "end": 4283.59, "word": " about", "probability": 0.82080078125 }, { "start": 4283.59, "end": 4283.71, "word": " the", "probability": 0.80322265625 }, { "start": 4283.71, "end": 4284.03, "word": " different", "probability": 0.6796875 }, { "start": 4284.03, "end": 4284.43, "word": " trees", "probability": 0.8310546875 }, { "start": 4284.43, "end": 4284.63, "word": " and", "probability": 0.86865234375 }, { "start": 4284.63, "end": 4285.15, "word": " algorithms", "probability": 0.8779296875 } ] }, { "id": 1636, "seek": 420502, "start": 4285.15, "end": 4288.23, "text": " that have been overtaken by", "tokens": [ 50514, 300, 362, 668, 17038, 9846, 538, 50664 ], "temperature": 0.0, "avg_logprob": -0.24371603374247966, "compression_ratio": 1.6849315068493151, "no_speech_prob": 0.0433349609375, "words": [ { "start": 4285.15, "end": 4285.79, "word": " that", "probability": 0.87060546875 }, { "start": 4285.79, "end": 4286.01, "word": " have", "probability": 0.8798828125 }, { "start": 4286.01, "end": 4286.21, "word": " been", "probability": 0.810546875 }, { "start": 4286.21, "end": 4287.03, "word": " overtaken", "probability": 0.896728515625 }, { "start": 4287.03, "end": 4288.23, "word": " by", "probability": 0.90625 } ] }, { "id": 1637, "seek": 420502, "start": 4290.49, "end": 4292.29, "text": " neural networks and deep neural networks", "tokens": [ 50664, 18161, 9590, 293, 2452, 18161, 9590, 50814 ], "temperature": 0.0, "avg_logprob": -0.24371603374247966, "compression_ratio": 1.6849315068493151, "no_speech_prob": 0.0433349609375, "words": [ { "start": 4290.49, "end": 4291.05, "word": " neural", "probability": 0.77880859375 }, { "start": 4291.05, "end": 4291.45, "word": " networks", "probability": 0.6416015625 }, { "start": 4291.45, "end": 4291.59, "word": " and", "probability": 0.7685546875 }, { "start": 4291.59, "end": 4291.73, "word": " deep", "probability": 0.9189453125 }, { "start": 4291.73, "end": 4291.89, "word": " neural", "probability": 0.91455078125 }, { "start": 4291.89, "end": 4292.29, "word": " networks", "probability": 0.66796875 } ] }, { "id": 1638, "seek": 420502, "start": 4292.29, "end": 4295.09, "text": " is random forests. Random forests operate very well", "tokens": [ 50814, 307, 4974, 21700, 13, 37603, 21700, 9651, 588, 731, 50964 ], "temperature": 0.0, "avg_logprob": -0.24371603374247966, "compression_ratio": 1.6849315068493151, "no_speech_prob": 0.0433349609375, "words": [ { "start": 4292.29, "end": 4292.67, "word": " is", "probability": 0.7939453125 }, { "start": 4292.67, "end": 4292.99, "word": " random", "probability": 0.64892578125 }, { "start": 4292.99, "end": 4293.31, "word": " forests", "probability": 0.287353515625 }, { "start": 4293.31, "end": 4293.37, "word": ".", "probability": 0.86376953125 }, { "start": 4293.37, "end": 4293.55, "word": " Random", "probability": 0.767578125 }, { "start": 4293.55, "end": 4293.87, "word": " forests", "probability": 0.67333984375 }, { "start": 4293.87, "end": 4294.29, "word": " operate", "probability": 0.76611328125 }, { "start": 4294.29, "end": 4294.69, "word": " very", "probability": 0.74267578125 }, { "start": 4294.69, "end": 4295.09, "word": " well", "probability": 0.8671875 } ] }, { "id": 1639, "seek": 420502, "start": 4295.09, "end": 4299.53, "text": " on a lot of different scenarios.", "tokens": [ 50964, 322, 257, 688, 295, 819, 15077, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.24371603374247966, "compression_ratio": 1.6849315068493151, "no_speech_prob": 0.0433349609375, "words": [ { "start": 4295.09, "end": 4296.07, "word": " on", "probability": 0.8955078125 }, { "start": 4296.43, "end": 4296.71, "word": " a lot", "probability": 0.8876953125 }, { "start": 4296.71, "end": 4296.97, "word": " of", "probability": 0.90576171875 }, { "start": 4296.97, "end": 4297.45, "word": " different", "probability": 0.66796875 }, { "start": 4297.45, "end": 4298.97, "word": " scenarios", "probability": 0.82861328125 }, { "start": 4298.97, "end": 4299.53, "word": ".", "probability": 0.30908203125 } ] }, { "id": 1640, "seek": 420502, "start": 4300.31, "end": 4301.35, "text": " But because", "tokens": [ 51114, 583, 570, 51264 ], "temperature": 0.0, "avg_logprob": -0.24371603374247966, "compression_ratio": 1.6849315068493151, "no_speech_prob": 0.0433349609375, "words": [ { "start": 4300.31, "end": 4300.39, "word": " But", "probability": 0.78564453125 }, { "start": 4300.39, "end": 4301.35, "word": " because", "probability": 0.7734375 } ] }, { "id": 1641, "seek": 420502, "start": 4301.35, "end": 4304.71, "text": " random forests are a cluster of decision trees", "tokens": [ 51264, 4974, 21700, 366, 257, 13630, 295, 3537, 5852, 51414 ], "temperature": 0.0, "avg_logprob": -0.24371603374247966, "compression_ratio": 1.6849315068493151, "no_speech_prob": 0.0433349609375, "words": [ { "start": 4301.35, "end": 4302.17, "word": " random", "probability": 0.693359375 }, { "start": 4302.17, "end": 4302.61, "word": " forests", "probability": 0.6337890625 }, { "start": 4302.61, "end": 4302.89, "word": " are", "probability": 0.176513671875 }, { "start": 4303.65, "end": 4303.95, "word": " a cluster", "probability": 0.7548828125 }, { "start": 4303.95, "end": 4304.11, "word": " of", "probability": 0.90771484375 }, { "start": 4304.11, "end": 4304.41, "word": " decision", "probability": 0.8359375 }, { "start": 4304.41, "end": 4304.71, "word": " trees", "probability": 0.83544921875 } ] }, { "id": 1642, "seek": 420502, "start": 4304.71, "end": 4306.81, "text": " people go, oh, they're just if-then statements.", "tokens": [ 51414, 561, 352, 11, 1954, 11, 436, 434, 445, 498, 12, 19096, 12363, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.24371603374247966, "compression_ratio": 1.6849315068493151, "no_speech_prob": 0.0433349609375, "words": [ { "start": 4304.71, "end": 4305.03, "word": " people", "probability": 0.12164306640625 }, { "start": 4305.03, "end": 4305.27, "word": " go", "probability": 0.8759765625 }, { "start": 4305.27, "end": 4305.37, "word": ",", "probability": 0.69140625 }, { "start": 4305.37, "end": 4305.49, "word": " oh", "probability": 0.31982421875 }, { "start": 4305.49, "end": 4305.51, "word": ",", "probability": 0.68505859375 }, { "start": 4305.51, "end": 4305.63, "word": " they're", "probability": 0.831787109375 }, { "start": 4305.63, "end": 4305.83, "word": " just", "probability": 0.8876953125 }, { "start": 4305.83, "end": 4306.05, "word": " if", "probability": 0.72314453125 }, { "start": 4306.05, "end": 4306.23, "word": "-then", "probability": 0.6505126953125 }, { "start": 4306.23, "end": 4306.71, "word": " statements", "probability": 0.703125 }, { "start": 4306.71, "end": 4306.81, "word": ".", "probability": 0.48388671875 } ] }, { "id": 1643, "seek": 420502, "start": 4306.81, "end": 4308.87, "text": " This is dumb. This isn't machine learning.", "tokens": [ 51564, 639, 307, 10316, 13, 639, 1943, 380, 3479, 2539, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.24371603374247966, "compression_ratio": 1.6849315068493151, "no_speech_prob": 0.0433349609375, "words": [ { "start": 4306.81, "end": 4306.95, "word": " This", "probability": 0.80712890625 }, { "start": 4306.95, "end": 4307.07, "word": " is", "probability": 0.890625 }, { "start": 4307.07, "end": 4307.29, "word": " dumb", "probability": 0.8505859375 }, { "start": 4307.29, "end": 4307.37, "word": ".", "probability": 0.50341796875 }, { "start": 4307.37, "end": 4307.49, "word": " This", "probability": 0.8095703125 }, { "start": 4307.49, "end": 4307.69, "word": " isn't", "probability": 0.9189453125 }, { "start": 4307.69, "end": 4307.97, "word": " machine", "probability": 0.7119140625 }, { "start": 4307.97, "end": 4308.31, "word": " learning", "probability": 0.845703125 }, { "start": 4308.31, "end": 4308.87, "word": ".", "probability": 0.990234375 } ] }, { "id": 1644, "seek": 423312, "start": 4309.67, "end": 4312.97, "text": " Yeah, but for us, we have", "tokens": [ 50414, 865, 11, 457, 337, 505, 11, 321, 362, 50564 ], "temperature": 0.0, "avg_logprob": -0.23611111376020644, "compression_ratio": 1.4881516587677726, "no_speech_prob": 0.09259033203125, "words": [ { "start": 4309.67, "end": 4309.99, "word": " Yeah", "probability": 0.1016845703125 }, { "start": 4309.99, "end": 4311.61, "word": ",", "probability": 0.80419921875 }, { "start": 4311.61, "end": 4311.91, "word": " but", "probability": 0.78369140625 }, { "start": 4311.91, "end": 4312.21, "word": " for", "probability": 0.87939453125 }, { "start": 4312.21, "end": 4312.51, "word": " us", "probability": 0.89794921875 }, { "start": 4312.51, "end": 4312.69, "word": ",", "probability": 0.47314453125 }, { "start": 4312.69, "end": 4312.79, "word": " we", "probability": 0.8984375 }, { "start": 4312.79, "end": 4312.97, "word": " have", "probability": 0.845703125 } ] }, { "id": 1645, "seek": 423312, "start": 4313.05, "end": 4315.81, "text": " a highly shared data where,", "tokens": [ 50564, 257, 5405, 5507, 1412, 689, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.23611111376020644, "compression_ratio": 1.4881516587677726, "no_speech_prob": 0.09259033203125, "words": [ { "start": 4313.05, "end": 4313.65, "word": " a highly", "probability": 0.80126953125 }, { "start": 4313.65, "end": 4313.97, "word": " shared", "probability": 0.17919921875 }, { "start": 4313.97, "end": 4314.59, "word": " data", "probability": 0.75048828125 }, { "start": 4314.59, "end": 4315.53, "word": " where", "probability": 0.58984375 }, { "start": 4315.53, "end": 4315.81, "word": ",", "probability": 0.60693359375 } ] }, { "id": 1646, "seek": 423312, "start": 4315.81, "end": 4318.87, "text": " for example, on the Ember malware dataset,", "tokens": [ 50714, 337, 1365, 11, 322, 264, 3968, 607, 40747, 28872, 11, 50864 ], "temperature": 0.0, "avg_logprob": -0.23611111376020644, "compression_ratio": 1.4881516587677726, "no_speech_prob": 0.09259033203125, "words": [ { "start": 4315.81, "end": 4316.15, "word": " for", "probability": 0.640625 }, { "start": 4316.15, "end": 4316.53, "word": " example", "probability": 0.93359375 }, { "start": 4316.53, "end": 4316.71, "word": ",", "probability": 0.82666015625 }, { "start": 4316.71, "end": 4316.79, "word": " on", "probability": 0.8505859375 }, { "start": 4316.79, "end": 4316.97, "word": " the", "probability": 0.80322265625 }, { "start": 4316.97, "end": 4317.35, "word": " Ember", "probability": 0.75 }, { "start": 4317.35, "end": 4317.81, "word": " malware", "probability": 0.68798828125 }, { "start": 4317.81, "end": 4318.35, "word": " dataset", "probability": 0.57568359375 }, { "start": 4318.35, "end": 4318.87, "word": ",", "probability": 0.7822265625 } ] }, { "id": 1647, "seek": 423312, "start": 4319.47, "end": 4322.33, "text": " the lightweight,", "tokens": [ 50864, 264, 22052, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.23611111376020644, "compression_ratio": 1.4881516587677726, "no_speech_prob": 0.09259033203125, "words": [ { "start": 4319.47, "end": 4319.77, "word": " the", "probability": 0.7021484375 }, { "start": 4319.77, "end": 4321.77, "word": " lightweight", "probability": 0.8447265625 }, { "start": 4321.77, "end": 4322.33, "word": ",", "probability": 0.9345703125 } ] }, { "id": 1648, "seek": 423312, "start": 4322.33, "end": 4323.25, "text": " incredibly cheap", "tokens": [ 51014, 6252, 7084, 51164 ], "temperature": 0.0, "avg_logprob": -0.23611111376020644, "compression_ratio": 1.4881516587677726, "no_speech_prob": 0.09259033203125, "words": [ { "start": 4322.33, "end": 4322.65, "word": " incredibly", "probability": 0.6708984375 }, { "start": 4322.65, "end": 4323.25, "word": " cheap", "probability": 0.841796875 } ] }, { "id": 1649, "seek": 423312, "start": 4325.09, "end": 4327.97, "text": " gradient decision tree built with LightGBM", "tokens": [ 51164, 16235, 3537, 4230, 3094, 365, 8279, 8769, 44, 51314 ], "temperature": 0.0, "avg_logprob": -0.23611111376020644, "compression_ratio": 1.4881516587677726, "no_speech_prob": 0.09259033203125, "words": [ { "start": 4325.09, "end": 4325.73, "word": " gradient", "probability": 0.1572265625 }, { "start": 4325.73, "end": 4326.37, "word": " decision", "probability": 0.484375 }, { "start": 4326.37, "end": 4326.69, "word": " tree", "probability": 0.84375 }, { "start": 4326.69, "end": 4326.95, "word": " built", "probability": 0.71728515625 }, { "start": 4326.95, "end": 4327.17, "word": " with", "probability": 0.802734375 }, { "start": 4327.17, "end": 4327.97, "word": " LightGBM", "probability": 0.66748046875 } ] }, { "id": 1650, "seek": 423312, "start": 4327.97, "end": 4331.19, "text": " outperformed any neural network you can throw at it.", "tokens": [ 51314, 484, 610, 22892, 604, 18161, 3209, 291, 393, 3507, 412, 309, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.23611111376020644, "compression_ratio": 1.4881516587677726, "no_speech_prob": 0.09259033203125, "words": [ { "start": 4327.97, "end": 4328.71, "word": " outperformed", "probability": 0.8102213541666666 }, { "start": 4328.71, "end": 4329.11, "word": " any", "probability": 0.8134765625 }, { "start": 4329.11, "end": 4329.37, "word": " neural", "probability": 0.88671875 }, { "start": 4329.37, "end": 4329.71, "word": " network", "probability": 0.83984375 }, { "start": 4329.71, "end": 4329.91, "word": " you", "probability": 0.8828125 }, { "start": 4329.91, "end": 4330.05, "word": " can", "probability": 0.814453125 }, { "start": 4330.05, "end": 4330.25, "word": " throw", "probability": 0.8203125 }, { "start": 4330.25, "end": 4330.39, "word": " at", "probability": 0.89697265625 }, { "start": 4330.39, "end": 4330.59, "word": " it", "probability": 0.900390625 }, { "start": 4330.59, "end": 4331.19, "word": ".", "probability": 0.93701171875 } ] }, { "id": 1651, "seek": 423312, "start": 4331.19, "end": 4333.91, "text": " So the LightGBM gets 99.8%", "tokens": [ 51464, 407, 264, 8279, 8769, 44, 2170, 11803, 13, 23, 4, 51614 ], "temperature": 0.0, "avg_logprob": -0.23611111376020644, "compression_ratio": 1.4881516587677726, "no_speech_prob": 0.09259033203125, "words": [ { "start": 4331.19, "end": 4331.29, "word": " So", "probability": 0.7607421875 }, { "start": 4331.29, "end": 4331.43, "word": " the", "probability": 0.658203125 }, { "start": 4331.43, "end": 4331.97, "word": " LightGBM", "probability": 0.9373372395833334 }, { "start": 4331.97, "end": 4332.19, "word": " gets", "probability": 0.80078125 }, { "start": 4332.19, "end": 4332.77, "word": " 99", "probability": 0.875 }, { "start": 4332.77, "end": 4333.59, "word": ".8", "probability": 0.99365234375 }, { "start": 4333.59, "end": 4333.91, "word": "%", "probability": 0.892578125 } ] }, { "id": 1652, "seek": 423312, "start": 4333.91, "end": 4336.97, "text": " accuracy or something like that, and the neural network gets", "tokens": [ 51614, 14170, 420, 746, 411, 300, 11, 293, 264, 18161, 3209, 2170, 51764 ], "temperature": 0.0, "avg_logprob": -0.23611111376020644, "compression_ratio": 1.4881516587677726, "no_speech_prob": 0.09259033203125, "words": [ { "start": 4333.91, "end": 4334.41, "word": " accuracy", "probability": 0.736328125 }, { "start": 4334.41, "end": 4334.77, "word": " or", "probability": 0.6328125 }, { "start": 4334.77, "end": 4334.97, "word": " something", "probability": 0.73681640625 }, { "start": 4334.97, "end": 4335.19, "word": " like", "probability": 0.87841796875 }, { "start": 4335.19, "end": 4335.55, "word": " that", "probability": 0.88232421875 }, { "start": 4335.55, "end": 4335.69, "word": ",", "probability": 0.490478515625 }, { "start": 4335.69, "end": 4336.13, "word": " and", "probability": 0.88671875 }, { "start": 4336.13, "end": 4336.23, "word": " the", "probability": 0.64794921875 }, { "start": 4336.23, "end": 4336.41, "word": " neural", "probability": 0.919921875 }, { "start": 4336.41, "end": 4336.77, "word": " network", "probability": 0.79443359375 }, { "start": 4336.77, "end": 4336.97, "word": " gets", "probability": 0.73876953125 } ] }, { "id": 1653, "seek": 426008, "start": 4336.97, "end": 4339.91, "text": " 98.7% accuracy, which is", "tokens": [ 50364, 20860, 13, 22, 4, 14170, 11, 597, 307, 50514 ], "temperature": 0.0, "avg_logprob": -0.1928308830541723, "compression_ratio": 1.7606382978723405, "no_speech_prob": 0.0330810546875, "words": [ { "start": 4336.97, "end": 4337.39, "word": " 98", "probability": 0.11358642578125 }, { "start": 4337.39, "end": 4338.73, "word": ".7", "probability": 0.979248046875 }, { "start": 4338.73, "end": 4338.95, "word": "%", "probability": 0.83984375 }, { "start": 4338.95, "end": 4339.33, "word": " accuracy", "probability": 0.76513671875 }, { "start": 4339.33, "end": 4339.63, "word": ",", "probability": 0.6396484375 }, { "start": 4339.63, "end": 4339.73, "word": " which", "probability": 0.89892578125 }, { "start": 4339.73, "end": 4339.91, "word": " is", "probability": 0.91015625 } ] }, { "id": 1654, "seek": 426008, "start": 4339.91, "end": 4341.87, "text": " significantly worse.", "tokens": [ 50514, 10591, 5324, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.1928308830541723, "compression_ratio": 1.7606382978723405, "no_speech_prob": 0.0330810546875, "words": [ { "start": 4339.91, "end": 4340.65, "word": " significantly", "probability": 0.8759765625 }, { "start": 4340.65, "end": 4341.23, "word": " worse", "probability": 0.931640625 }, { "start": 4341.23, "end": 4341.87, "word": ".", "probability": 0.85791015625 } ] }, { "id": 1655, "seek": 426008, "start": 4344.35, "end": 4346.23, "text": " For some tasks,", "tokens": [ 50664, 1171, 512, 9608, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.1928308830541723, "compression_ratio": 1.7606382978723405, "no_speech_prob": 0.0330810546875, "words": [ { "start": 4344.35, "end": 4344.99, "word": " For", "probability": 0.6337890625 }, { "start": 4344.99, "end": 4345.31, "word": " some", "probability": 0.80517578125 }, { "start": 4345.31, "end": 4345.85, "word": " tasks", "probability": 0.8525390625 }, { "start": 4345.85, "end": 4346.23, "word": ",", "probability": 0.77587890625 } ] }, { "id": 1656, "seek": 426008, "start": 4346.41, "end": 4349.65, "text": " a gradient-based decision tree or something like that", "tokens": [ 50814, 257, 16235, 12, 6032, 3537, 4230, 420, 746, 411, 300, 50964 ], "temperature": 0.0, "avg_logprob": -0.1928308830541723, "compression_ratio": 1.7606382978723405, "no_speech_prob": 0.0330810546875, "words": [ { "start": 4346.41, "end": 4346.81, "word": " a gradient", "probability": 0.285400390625 }, { "start": 4346.81, "end": 4347.05, "word": "-based", "probability": 0.641357421875 }, { "start": 4347.05, "end": 4347.47, "word": " decision", "probability": 0.8037109375 }, { "start": 4347.47, "end": 4347.87, "word": " tree", "probability": 0.85791015625 }, { "start": 4347.87, "end": 4348.49, "word": " or", "probability": 0.68701171875 }, { "start": 4348.49, "end": 4348.81, "word": " something", "probability": 0.73291015625 }, { "start": 4348.81, "end": 4349.21, "word": " like", "probability": 0.87548828125 }, { "start": 4349.21, "end": 4349.65, "word": " that", "probability": 0.8798828125 } ] }, { "id": 1657, "seek": 426008, "start": 4349.65, "end": 4352.17, "text": " is the correct thing mathematically", "tokens": [ 50964, 307, 264, 3006, 551, 44003, 51114 ], "temperature": 0.0, "avg_logprob": -0.1928308830541723, "compression_ratio": 1.7606382978723405, "no_speech_prob": 0.0330810546875, "words": [ { "start": 4349.65, "end": 4350.25, "word": " is", "probability": 0.79541015625 }, { "start": 4350.25, "end": 4350.47, "word": " the", "probability": 0.80419921875 }, { "start": 4350.47, "end": 4351.09, "word": " correct", "probability": 0.86083984375 }, { "start": 4351.09, "end": 4351.85, "word": " thing", "probability": 0.802734375 }, { "start": 4351.85, "end": 4352.17, "word": " mathematically", "probability": 0.64794921875 } ] }, { "id": 1658, "seek": 426008, "start": 4352.59, "end": 4354.29, "text": " because neural networks have biases", "tokens": [ 51114, 570, 18161, 9590, 362, 32152, 51264 ], "temperature": 0.0, "avg_logprob": -0.1928308830541723, "compression_ratio": 1.7606382978723405, "no_speech_prob": 0.0330810546875, "words": [ { "start": 4352.59, "end": 4352.97, "word": " because", "probability": 0.48486328125 }, { "start": 4352.97, "end": 4353.25, "word": " neural", "probability": 0.8837890625 }, { "start": 4353.25, "end": 4353.51, "word": " networks", "probability": 0.7021484375 }, { "start": 4353.51, "end": 4353.81, "word": " have", "probability": 0.8828125 }, { "start": 4353.81, "end": 4354.29, "word": " biases", "probability": 0.88671875 } ] }, { "id": 1659, "seek": 426008, "start": 4354.97, "end": 4358.07, "text": " because it's easier for them to learn some things than others", "tokens": [ 51264, 570, 309, 311, 3571, 337, 552, 281, 1466, 512, 721, 813, 2357, 51414 ], "temperature": 0.0, "avg_logprob": -0.1928308830541723, "compression_ratio": 1.7606382978723405, "no_speech_prob": 0.0330810546875, "words": [ { "start": 4354.97, "end": 4355.33, "word": " because", "probability": 0.037994384765625 }, { "start": 4355.33, "end": 4356.09, "word": " it's", "probability": 0.906005859375 }, { "start": 4356.09, "end": 4356.41, "word": " easier", "probability": 0.9345703125 }, { "start": 4356.41, "end": 4356.59, "word": " for", "probability": 0.87255859375 }, { "start": 4356.59, "end": 4356.71, "word": " them", "probability": 0.75146484375 }, { "start": 4356.71, "end": 4356.83, "word": " to", "probability": 0.9033203125 }, { "start": 4356.83, "end": 4356.99, "word": " learn", "probability": 0.919921875 }, { "start": 4356.99, "end": 4357.29, "word": " some", "probability": 0.822265625 }, { "start": 4357.29, "end": 4357.61, "word": " things", "probability": 0.734375 }, { "start": 4357.61, "end": 4357.75, "word": " than", "probability": 0.83447265625 }, { "start": 4357.75, "end": 4358.07, "word": " others", "probability": 0.7744140625 } ] }, { "id": 1660, "seek": 426008, "start": 4358.07, "end": 4361.05, "text": " and GBTs have biases where", "tokens": [ 51414, 293, 26809, 33424, 362, 32152, 689, 51564 ], "temperature": 0.0, "avg_logprob": -0.1928308830541723, "compression_ratio": 1.7606382978723405, "no_speech_prob": 0.0330810546875, "words": [ { "start": 4358.07, "end": 4359.09, "word": " and", "probability": 0.253662109375 }, { "start": 4359.09, "end": 4359.99, "word": " GBTs", "probability": 0.78271484375 }, { "start": 4359.99, "end": 4360.41, "word": " have", "probability": 0.8876953125 }, { "start": 4360.41, "end": 4360.77, "word": " biases", "probability": 0.8369140625 }, { "start": 4360.77, "end": 4361.05, "word": " where", "probability": 0.77587890625 } ] }, { "id": 1661, "seek": 426008, "start": 4361.05, "end": 4363.93, "text": " it's easier for them to learn some things than others.", "tokens": [ 51564, 309, 311, 3571, 337, 552, 281, 1466, 512, 721, 813, 2357, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.1928308830541723, "compression_ratio": 1.7606382978723405, "no_speech_prob": 0.0330810546875, "words": [ { "start": 4361.05, "end": 4361.27, "word": " it's", "probability": 0.919921875 }, { "start": 4361.27, "end": 4361.47, "word": " easier", "probability": 0.72216796875 }, { "start": 4361.47, "end": 4362.01, "word": " for", "probability": 0.6630859375 }, { "start": 4362.01, "end": 4362.21, "word": " them", "probability": 0.7451171875 }, { "start": 4362.21, "end": 4362.33, "word": " to", "probability": 0.90283203125 }, { "start": 4362.33, "end": 4362.49, "word": " learn", "probability": 0.92333984375 }, { "start": 4362.49, "end": 4362.73, "word": " some", "probability": 0.7783203125 }, { "start": 4362.73, "end": 4362.91, "word": " things", "probability": 0.7294921875 }, { "start": 4362.91, "end": 4363.03, "word": " than", "probability": 0.87646484375 }, { "start": 4363.03, "end": 4363.29, "word": " others", "probability": 0.787109375 }, { "start": 4363.29, "end": 4363.93, "word": ".", "probability": 0.63671875 } ] }, { "id": 1662, "seek": 428718, "start": 4363.93, "end": 4366.55, "text": " And one of the great secrets", "tokens": [ 50364, 400, 472, 295, 264, 869, 14093, 50514 ], "temperature": 0.0, "avg_logprob": -0.21191406827419995, "compression_ratio": 1.5157894736842106, "no_speech_prob": 0.1275634765625, "words": [ { "start": 4363.93, "end": 4364.15, "word": " And", "probability": 0.1097412109375 }, { "start": 4364.15, "end": 4364.47, "word": " one", "probability": 0.75927734375 }, { "start": 4364.47, "end": 4364.61, "word": " of", "probability": 0.892578125 }, { "start": 4364.61, "end": 4364.75, "word": " the", "probability": 0.810546875 }, { "start": 4364.75, "end": 4366.21, "word": " great", "probability": 0.64501953125 }, { "start": 4366.21, "end": 4366.55, "word": " secrets", "probability": 0.72216796875 } ] }, { "id": 1663, "seek": 428718, "start": 4366.55, "end": 4368.51, "text": " of machine learning is", "tokens": [ 50514, 295, 3479, 2539, 307, 50664 ], "temperature": 0.0, "avg_logprob": -0.21191406827419995, "compression_ratio": 1.5157894736842106, "no_speech_prob": 0.1275634765625, "words": [ { "start": 4366.55, "end": 4366.77, "word": " of", "probability": 0.8896484375 }, { "start": 4366.77, "end": 4367.91, "word": " machine", "probability": 0.4306640625 }, { "start": 4367.91, "end": 4368.21, "word": " learning", "probability": 0.84130859375 }, { "start": 4368.21, "end": 4368.51, "word": " is", "probability": 0.88525390625 } ] }, { "id": 1664, "seek": 428718, "start": 4369.19, "end": 4372.29, "text": " match up your problem with both", "tokens": [ 50664, 2995, 493, 428, 1154, 365, 1293, 50814 ], "temperature": 0.0, "avg_logprob": -0.21191406827419995, "compression_ratio": 1.5157894736842106, "no_speech_prob": 0.1275634765625, "words": [ { "start": 4369.19, "end": 4369.81, "word": " match", "probability": 0.46630859375 }, { "start": 4369.81, "end": 4370.09, "word": " up", "probability": 0.88720703125 }, { "start": 4370.09, "end": 4370.25, "word": " your", "probability": 0.80126953125 }, { "start": 4370.25, "end": 4370.63, "word": " problem", "probability": 0.72314453125 }, { "start": 4370.63, "end": 4370.97, "word": " with", "probability": 0.810546875 }, { "start": 4370.97, "end": 4372.29, "word": " both", "probability": 0.66064453125 } ] }, { "id": 1665, "seek": 428718, "start": 4372.64, "end": 4375.85, "text": " the requirements, how powerful your predictor", "tokens": [ 50814, 264, 7728, 11, 577, 4005, 428, 6069, 284, 50964 ], "temperature": 0.0, "avg_logprob": -0.21191406827419995, "compression_ratio": 1.5157894736842106, "no_speech_prob": 0.1275634765625, "words": [ { "start": 4372.64, "end": 4372.95, "word": " the", "probability": 0.5244140625 }, { "start": 4372.95, "end": 4373.51, "word": " requirements", "probability": 0.85693359375 }, { "start": 4373.51, "end": 4374.01, "word": ",", "probability": 0.5712890625 }, { "start": 4374.01, "end": 4374.21, "word": " how", "probability": 0.796875 }, { "start": 4374.21, "end": 4374.65, "word": " powerful", "probability": 0.84375 }, { "start": 4374.65, "end": 4375.07, "word": " your", "probability": 0.779296875 }, { "start": 4375.07, "end": 4375.85, "word": " predictor", "probability": 0.768310546875 } ] }, { "id": 1666, "seek": 428718, "start": 4375.85, "end": 4378.01, "text": " needs to be, and the inherent biases", "tokens": [ 50964, 2203, 281, 312, 11, 293, 264, 26387, 32152, 51114 ], "temperature": 0.0, "avg_logprob": -0.21191406827419995, "compression_ratio": 1.5157894736842106, "no_speech_prob": 0.1275634765625, "words": [ { "start": 4375.85, "end": 4376.05, "word": " needs", "probability": 0.7626953125 }, { "start": 4376.05, "end": 4376.15, "word": " to", "probability": 0.90380859375 }, { "start": 4376.15, "end": 4376.37, "word": " be", "probability": 0.90673828125 }, { "start": 4376.37, "end": 4376.51, "word": ",", "probability": 0.7568359375 }, { "start": 4376.51, "end": 4376.89, "word": " and", "probability": 0.8916015625 }, { "start": 4376.89, "end": 4377.09, "word": " the", "probability": 0.80078125 }, { "start": 4377.09, "end": 4377.47, "word": " inherent", "probability": 0.7978515625 }, { "start": 4377.47, "end": 4378.01, "word": " biases", "probability": 0.89013671875 } ] }, { "id": 1667, "seek": 428718, "start": 4378.01, "end": 4380.81, "text": " of those predictors.", "tokens": [ 51114, 295, 729, 6069, 830, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.21191406827419995, "compression_ratio": 1.5157894736842106, "no_speech_prob": 0.1275634765625, "words": [ { "start": 4378.01, "end": 4378.77, "word": " of", "probability": 0.90478515625 }, { "start": 4378.77, "end": 4379.59, "word": " those", "probability": 0.84765625 }, { "start": 4379.59, "end": 4380.19, "word": " predictors", "probability": 0.88623046875 }, { "start": 4380.19, "end": 4380.81, "word": ".", "probability": 0.9677734375 } ] }, { "id": 1668, "seek": 428718, "start": 4382.13, "end": 4382.91, "text": " Yeah.", "tokens": [ 51264, 865, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.21191406827419995, "compression_ratio": 1.5157894736842106, "no_speech_prob": 0.1275634765625, "words": [ { "start": 4382.13, "end": 4382.55, "word": " Yeah", "probability": 0.6533203125 }, { "start": 4382.55, "end": 4382.91, "word": ".", "probability": 0.3251953125 } ] }, { "id": 1669, "seek": 428718, "start": 4386.48, "end": 4389.3, "text": " Yeah, that's pretty interesting. I didn't know that.", "tokens": [ 51414, 865, 11, 300, 311, 1238, 1880, 13, 286, 994, 380, 458, 300, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.21191406827419995, "compression_ratio": 1.5157894736842106, "no_speech_prob": 0.1275634765625, "words": [ { "start": 4386.48, "end": 4387.1, "word": " Yeah", "probability": 0.394287109375 }, { "start": 4387.1, "end": 4387.22, "word": ",", "probability": 0.72509765625 }, { "start": 4387.22, "end": 4387.48, "word": " that's", "probability": 0.9404296875 }, { "start": 4387.48, "end": 4387.64, "word": " pretty", "probability": 0.8828125 }, { "start": 4387.64, "end": 4387.96, "word": " interesting", "probability": 0.65771484375 }, { "start": 4387.96, "end": 4388.12, "word": ".", "probability": 0.734375 }, { "start": 4388.12, "end": 4388.16, "word": " I", "probability": 0.86328125 }, { "start": 4388.16, "end": 4388.3, "word": " didn't", "probability": 0.92724609375 }, { "start": 4388.3, "end": 4388.48, "word": " know", "probability": 0.82568359375 }, { "start": 4388.48, "end": 4388.68, "word": " that", "probability": 0.880859375 }, { "start": 4388.68, "end": 4389.3, "word": ".", "probability": 0.95166015625 } ] }, { "id": 1670, "seek": 428718, "start": 4390.7, "end": 4392.78, "text": " But that also reminds me of another thing", "tokens": [ 51564, 583, 300, 611, 12025, 385, 295, 1071, 551, 51714 ], "temperature": 0.0, "avg_logprob": -0.21191406827419995, "compression_ratio": 1.5157894736842106, "no_speech_prob": 0.1275634765625, "words": [ { "start": 4390.7, "end": 4391.32, "word": " But", "probability": 0.78564453125 }, { "start": 4391.32, "end": 4391.44, "word": " that", "probability": 0.876953125 }, { "start": 4391.44, "end": 4391.62, "word": " also", "probability": 0.8447265625 }, { "start": 4391.62, "end": 4391.9, "word": " reminds", "probability": 0.767578125 }, { "start": 4391.9, "end": 4392.02, "word": " me", "probability": 0.90673828125 }, { "start": 4392.02, "end": 4392.1, "word": " of", "probability": 0.90673828125 }, { "start": 4392.1, "end": 4392.3, "word": " another", "probability": 0.7998046875 }, { "start": 4392.3, "end": 4392.78, "word": " thing", "probability": 0.81396484375 } ] }, { "id": 1671, "seek": 431454, "start": 4392.78, "end": 4396.72, "text": " with neural networks. Neural networks are really good at learning superstitions.", "tokens": [ 50364, 365, 18161, 9590, 13, 1734, 1807, 9590, 366, 534, 665, 412, 2539, 29423, 2451, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.2154314138193046, "compression_ratio": 1.7874015748031495, "no_speech_prob": 0.366455078125, "words": [ { "start": 4392.78, "end": 4393.24, "word": " with", "probability": 0.238525390625 }, { "start": 4393.24, "end": 4393.86, "word": " neural", "probability": 0.82177734375 }, { "start": 4393.86, "end": 4394.18, "word": " networks", "probability": 0.6533203125 }, { "start": 4394.18, "end": 4394.26, "word": ".", "probability": 0.57861328125 }, { "start": 4394.26, "end": 4394.36, "word": " Neural", "probability": 0.868896484375 }, { "start": 4394.36, "end": 4394.66, "word": " networks", "probability": 0.66943359375 }, { "start": 4394.66, "end": 4394.8, "word": " are", "probability": 0.89013671875 }, { "start": 4394.8, "end": 4394.94, "word": " really", "probability": 0.75537109375 }, { "start": 4394.94, "end": 4395.12, "word": " good", "probability": 0.880859375 }, { "start": 4395.12, "end": 4395.26, "word": " at", "probability": 0.908203125 }, { "start": 4395.26, "end": 4395.46, "word": " learning", "probability": 0.875 }, { "start": 4395.46, "end": 4396.2, "word": " superstitions", "probability": 0.8701171875 }, { "start": 4396.2, "end": 4396.72, "word": ".", "probability": 0.8662109375 } ] }, { "id": 1672, "seek": 431454, "start": 4397.06, "end": 4399.52, "text": " I don't know if that's a machine learning as a whole thing", "tokens": [ 50514, 286, 500, 380, 458, 498, 300, 311, 257, 3479, 2539, 382, 257, 1379, 551, 50664 ], "temperature": 0.0, "avg_logprob": -0.2154314138193046, "compression_ratio": 1.7874015748031495, "no_speech_prob": 0.366455078125, "words": [ { "start": 4397.06, "end": 4397.26, "word": " I", "probability": 0.951171875 }, { "start": 4397.26, "end": 4397.36, "word": " don't", "probability": 0.945556640625 }, { "start": 4397.36, "end": 4397.46, "word": " know", "probability": 0.82080078125 }, { "start": 4397.46, "end": 4397.56, "word": " if", "probability": 0.90283203125 }, { "start": 4397.56, "end": 4397.72, "word": " that's", "probability": 0.932861328125 }, { "start": 4397.8, "end": 4398.08, "word": " a machine", "probability": 0.70947265625 }, { "start": 4398.08, "end": 4398.4, "word": " learning", "probability": 0.85546875 }, { "start": 4398.4, "end": 4398.64, "word": " as", "probability": 0.88525390625 }, { "start": 4398.82, "end": 4399.1, "word": " a whole", "probability": 0.80029296875 }, { "start": 4399.1, "end": 4399.52, "word": " thing", "probability": 0.798828125 } ] }, { "id": 1673, "seek": 431454, "start": 4399.52, "end": 4401.78, "text": " or specifically in neural networks", "tokens": [ 50664, 420, 4682, 294, 18161, 9590, 50814 ], "temperature": 0.0, "avg_logprob": -0.2154314138193046, "compression_ratio": 1.7874015748031495, "no_speech_prob": 0.366455078125, "words": [ { "start": 4399.52, "end": 4400.18, "word": " or", "probability": 0.55517578125 }, { "start": 4400.18, "end": 4400.94, "word": " specifically", "probability": 0.14697265625 }, { "start": 4400.94, "end": 4401.18, "word": " in", "probability": 0.5693359375 }, { "start": 4401.18, "end": 4401.32, "word": " neural", "probability": 0.88671875 }, { "start": 4401.32, "end": 4401.78, "word": " networks", "probability": 0.65380859375 } ] }, { "id": 1674, "seek": 431454, "start": 4401.78, "end": 4404.96, "text": " but I remember there was a dataset that they were using to identify", "tokens": [ 50814, 457, 286, 1604, 456, 390, 257, 28872, 300, 436, 645, 1228, 281, 5876, 50964 ], "temperature": 0.0, "avg_logprob": -0.2154314138193046, "compression_ratio": 1.7874015748031495, "no_speech_prob": 0.366455078125, "words": [ { "start": 4401.78, "end": 4402.34, "word": " but", "probability": 0.208740234375 }, { "start": 4402.34, "end": 4402.54, "word": " I", "probability": 0.89208984375 }, { "start": 4402.54, "end": 4402.78, "word": " remember", "probability": 0.78955078125 }, { "start": 4402.78, "end": 4403.08, "word": " there", "probability": 0.845703125 }, { "start": 4403.08, "end": 4403.22, "word": " was", "probability": 0.89599609375 }, { "start": 4403.48, "end": 4403.8, "word": " a dataset", "probability": 0.325439453125 }, { "start": 4403.8, "end": 4404.0, "word": " that", "probability": 0.85595703125 }, { "start": 4404.0, "end": 4404.12, "word": " they", "probability": 0.7353515625 }, { "start": 4404.12, "end": 4404.22, "word": " were", "probability": 0.8857421875 }, { "start": 4404.22, "end": 4404.44, "word": " using", "probability": 0.82666015625 }, { "start": 4404.44, "end": 4404.6, "word": " to", "probability": 0.90625 }, { "start": 4404.6, "end": 4404.96, "word": " identify", "probability": 0.8916015625 } ] }, { "id": 1675, "seek": 431454, "start": 4404.96, "end": 4408.04, "text": " skin cancer cells. They used a convolutional", "tokens": [ 50964, 3178, 5592, 5438, 13, 814, 1143, 257, 45216, 304, 51114 ], "temperature": 0.0, "avg_logprob": -0.2154314138193046, "compression_ratio": 1.7874015748031495, "no_speech_prob": 0.366455078125, "words": [ { "start": 4404.96, "end": 4405.3, "word": " skin", "probability": 0.8251953125 }, { "start": 4405.3, "end": 4405.62, "word": " cancer", "probability": 0.85205078125 }, { "start": 4405.62, "end": 4406.18, "word": " cells", "probability": 0.71875 }, { "start": 4406.18, "end": 4406.7, "word": ".", "probability": 0.70263671875 }, { "start": 4406.94, "end": 4407.16, "word": " They", "probability": 0.712890625 }, { "start": 4407.16, "end": 4407.32, "word": " used", "probability": 0.8193359375 }, { "start": 4407.44, "end": 4408.04, "word": " a convolutional", "probability": 0.9013671875 } ] }, { "id": 1676, "seek": 431454, "start": 4408.04, "end": 4411.18, "text": " neural network and based off of that it was learning", "tokens": [ 51114, 18161, 3209, 293, 2361, 766, 295, 300, 309, 390, 2539, 51264 ], "temperature": 0.0, "avg_logprob": -0.2154314138193046, "compression_ratio": 1.7874015748031495, "no_speech_prob": 0.366455078125, "words": [ { "start": 4408.04, "end": 4408.2, "word": " neural", "probability": 0.90283203125 }, { "start": 4408.2, "end": 4408.62, "word": " network", "probability": 0.82275390625 }, { "start": 4408.62, "end": 4409.26, "word": " and", "probability": 0.81884765625 }, { "start": 4409.26, "end": 4409.92, "word": " based", "probability": 0.828125 }, { "start": 4409.92, "end": 4410.1, "word": " off", "probability": 0.806640625 }, { "start": 4410.1, "end": 4410.22, "word": " of", "probability": 0.90478515625 }, { "start": 4410.22, "end": 4410.48, "word": " that", "probability": 0.88134765625 }, { "start": 4410.48, "end": 4410.66, "word": " it", "probability": 0.6845703125 }, { "start": 4410.66, "end": 4410.8, "word": " was", "probability": 0.90185546875 }, { "start": 4410.8, "end": 4411.18, "word": " learning", "probability": 0.8662109375 } ] }, { "id": 1677, "seek": 431454, "start": 4411.18, "end": 4414.64, "text": " that if there was a... it was performing too well.", "tokens": [ 51264, 300, 498, 456, 390, 257, 485, 309, 390, 10205, 886, 731, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.2154314138193046, "compression_ratio": 1.7874015748031495, "no_speech_prob": 0.366455078125, "words": [ { "start": 4411.18, "end": 4411.6, "word": " that", "probability": 0.86474609375 }, { "start": 4411.6, "end": 4411.8, "word": " if", "probability": 0.84375 }, { "start": 4411.8, "end": 4411.98, "word": " there", "probability": 0.818359375 }, { "start": 4411.98, "end": 4412.18, "word": " was", "probability": 0.89501953125 }, { "start": 4412.18, "end": 4413.16, "word": " a...", "probability": 0.5946044921875 }, { "start": 4413.16, "end": 4413.22, "word": " it", "probability": 0.51611328125 }, { "start": 4413.22, "end": 4413.3, "word": " was", "probability": 0.85107421875 }, { "start": 4413.3, "end": 4413.64, "word": " performing", "probability": 0.71337890625 }, { "start": 4413.64, "end": 4413.98, "word": " too", "probability": 0.7890625 }, { "start": 4413.98, "end": 4414.32, "word": " well", "probability": 0.8779296875 }, { "start": 4414.32, "end": 4414.64, "word": ".", "probability": 0.55029296875 } ] }, { "id": 1678, "seek": 431454, "start": 4414.64, "end": 4416.96, "text": " It got nearly 100% and they", "tokens": [ 51414, 467, 658, 6217, 2319, 4, 293, 436, 51564 ], "temperature": 0.0, "avg_logprob": -0.2154314138193046, "compression_ratio": 1.7874015748031495, "no_speech_prob": 0.366455078125, "words": [ { "start": 4414.64, "end": 4414.7, "word": " It", "probability": 0.8759765625 }, { "start": 4414.7, "end": 4415.12, "word": " got", "probability": 0.83056640625 }, { "start": 4415.12, "end": 4415.42, "word": " nearly", "probability": 0.802734375 }, { "start": 4415.42, "end": 4415.72, "word": " 100", "probability": 0.490966796875 }, { "start": 4415.72, "end": 4416.0, "word": "%", "probability": 0.57275390625 }, { "start": 4416.0, "end": 4416.7, "word": " and", "probability": 0.876953125 }, { "start": 4416.7, "end": 4416.96, "word": " they", "probability": 0.73974609375 } ] }, { "id": 1679, "seek": 431454, "start": 4417.54, "end": 4420.14, "text": " kind of dug into what it was doing", "tokens": [ 51564, 733, 295, 22954, 666, 437, 309, 390, 884, 51714 ], "temperature": 0.0, "avg_logprob": -0.2154314138193046, "compression_ratio": 1.7874015748031495, "no_speech_prob": 0.366455078125, "words": [ { "start": 4417.54, "end": 4418.06, "word": " kind", "probability": 0.7119140625 }, { "start": 4418.06, "end": 4418.16, "word": " of", "probability": 0.90673828125 }, { "start": 4418.16, "end": 4418.32, "word": " dug", "probability": 0.88037109375 }, { "start": 4418.32, "end": 4418.72, "word": " into", "probability": 0.716796875 }, { "start": 4418.72, "end": 4419.58, "word": " what", "probability": 0.8837890625 }, { "start": 4419.58, "end": 4419.66, "word": " it", "probability": 0.9013671875 }, { "start": 4419.66, "end": 4419.8, "word": " was", "probability": 0.896484375 }, { "start": 4419.8, "end": 4420.14, "word": " doing", "probability": 0.91357421875 } ] }, { "id": 1680, "seek": 434214, "start": 4420.14, "end": 4422.8, "text": " and it said, OK, well if I see a ruler in the picture", "tokens": [ 50364, 293, 309, 848, 11, 2264, 11, 731, 498, 286, 536, 257, 19661, 294, 264, 3036, 50514 ], "temperature": 0.0, "avg_logprob": -0.19987500524520874, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.206787109375, "words": [ { "start": 4420.14, "end": 4420.48, "word": " and", "probability": 0.413818359375 }, { "start": 4420.48, "end": 4420.64, "word": " it", "probability": 0.83203125 }, { "start": 4420.64, "end": 4420.9, "word": " said", "probability": 0.87890625 }, { "start": 4420.9, "end": 4421.04, "word": ",", "probability": 0.45703125 }, { "start": 4421.04, "end": 4421.18, "word": " OK", "probability": 0.100830078125 }, { "start": 4421.18, "end": 4421.28, "word": ",", "probability": 0.89599609375 }, { "start": 4421.28, "end": 4421.38, "word": " well", "probability": 0.84130859375 }, { "start": 4421.38, "end": 4421.5, "word": " if", "probability": 0.272705078125 }, { "start": 4421.5, "end": 4421.58, "word": " I", "probability": 0.990234375 }, { "start": 4421.58, "end": 4421.72, "word": " see", "probability": 0.80126953125 }, { "start": 4421.96, "end": 4422.2, "word": " a ruler", "probability": 0.7431640625 }, { "start": 4422.2, "end": 4422.4, "word": " in", "probability": 0.90380859375 }, { "start": 4422.4, "end": 4422.5, "word": " the", "probability": 0.81494140625 }, { "start": 4422.5, "end": 4422.8, "word": " picture", "probability": 0.7724609375 } ] }, { "id": 1681, "seek": 434214, "start": 4422.8, "end": 4425.78, "text": " which the scientists, how they were collecting the images, they had a ruler", "tokens": [ 50514, 597, 264, 7708, 11, 577, 436, 645, 12510, 264, 5267, 11, 436, 632, 257, 19661, 50664 ], "temperature": 0.0, "avg_logprob": -0.19987500524520874, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.206787109375, "words": [ { "start": 4422.8, "end": 4423.06, "word": " which", "probability": 0.176513671875 }, { "start": 4423.06, "end": 4423.34, "word": " the", "probability": 0.7919921875 }, { "start": 4423.34, "end": 4423.96, "word": " scientists", "probability": 0.63818359375 }, { "start": 4423.96, "end": 4424.1, "word": ",", "probability": 0.421630859375 }, { "start": 4424.1, "end": 4424.18, "word": " how", "probability": 0.87451171875 }, { "start": 4424.18, "end": 4424.26, "word": " they", "probability": 0.74560546875 }, { "start": 4424.26, "end": 4424.36, "word": " were", "probability": 0.87353515625 }, { "start": 4424.36, "end": 4424.68, "word": " collecting", "probability": 0.73046875 }, { "start": 4424.68, "end": 4424.86, "word": " the", "probability": 0.53955078125 }, { "start": 4424.86, "end": 4425.04, "word": " images", "probability": 0.828125 }, { "start": 4425.04, "end": 4425.2, "word": ",", "probability": 0.63720703125 }, { "start": 4425.2, "end": 4425.24, "word": " they", "probability": 0.73291015625 }, { "start": 4425.24, "end": 4425.34, "word": " had", "probability": 0.8134765625 }, { "start": 4425.54, "end": 4425.78, "word": " a ruler", "probability": 0.740234375 } ] }, { "id": 1682, "seek": 434214, "start": 4425.78, "end": 4428.86, "text": " next to the skin cancer cells. If I see a ruler in the picture", "tokens": [ 50664, 958, 281, 264, 3178, 5592, 5438, 13, 759, 286, 536, 257, 19661, 294, 264, 3036, 50814 ], "temperature": 0.0, "avg_logprob": -0.19987500524520874, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.206787109375, "words": [ { "start": 4425.78, "end": 4426.16, "word": " next", "probability": 0.84716796875 }, { "start": 4426.16, "end": 4426.46, "word": " to", "probability": 0.90380859375 }, { "start": 4426.46, "end": 4426.74, "word": " the", "probability": 0.80859375 }, { "start": 4426.74, "end": 4426.96, "word": " skin", "probability": 0.8251953125 }, { "start": 4426.96, "end": 4427.28, "word": " cancer", "probability": 0.849609375 }, { "start": 4427.28, "end": 4427.58, "word": " cells", "probability": 0.73095703125 }, { "start": 4427.58, "end": 4427.64, "word": ".", "probability": 0.67529296875 }, { "start": 4427.64, "end": 4427.72, "word": " If", "probability": 0.8583984375 }, { "start": 4427.72, "end": 4427.78, "word": " I", "probability": 0.98974609375 }, { "start": 4427.78, "end": 4427.88, "word": " see", "probability": 0.80712890625 }, { "start": 4428.04, "end": 4428.28, "word": " a ruler", "probability": 0.7197265625 }, { "start": 4428.28, "end": 4428.44, "word": " in", "probability": 0.90771484375 }, { "start": 4428.44, "end": 4428.54, "word": " the", "probability": 0.814453125 }, { "start": 4428.54, "end": 4428.86, "word": " picture", "probability": 0.77587890625 } ] }, { "id": 1683, "seek": 434214, "start": 4428.86, "end": 4432.38, "text": " that's how I know it's cancer. Not the little blob", "tokens": [ 50814, 300, 311, 577, 286, 458, 309, 311, 5592, 13, 1726, 264, 707, 46115, 50964 ], "temperature": 0.0, "avg_logprob": -0.19987500524520874, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.206787109375, "words": [ { "start": 4428.86, "end": 4429.62, "word": " that's", "probability": 0.59979248046875 }, { "start": 4429.62, "end": 4429.76, "word": " how", "probability": 0.89501953125 }, { "start": 4429.76, "end": 4429.88, "word": " I", "probability": 0.99462890625 }, { "start": 4429.88, "end": 4430.02, "word": " know", "probability": 0.81201171875 }, { "start": 4430.02, "end": 4430.24, "word": " it's", "probability": 0.947998046875 }, { "start": 4430.24, "end": 4430.64, "word": " cancer", "probability": 0.83984375 }, { "start": 4430.64, "end": 4431.08, "word": ".", "probability": 0.234375 }, { "start": 4431.2, "end": 4431.46, "word": " Not", "probability": 0.89501953125 }, { "start": 4431.46, "end": 4431.84, "word": " the", "probability": 0.806640625 }, { "start": 4431.84, "end": 4432.04, "word": " little", "probability": 0.791015625 }, { "start": 4432.04, "end": 4432.38, "word": " blob", "probability": 0.81787109375 } ] }, { "id": 1684, "seek": 434214, "start": 4432.38, "end": 4433.48, "text": " next to it.", "tokens": [ 50964, 958, 281, 309, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.19987500524520874, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.206787109375, "words": [ { "start": 4432.38, "end": 4432.7, "word": " next", "probability": 0.84033203125 }, { "start": 4432.7, "end": 4432.86, "word": " to", "probability": 0.90673828125 }, { "start": 4432.86, "end": 4433.04, "word": " it", "probability": 0.90380859375 }, { "start": 4433.04, "end": 4433.48, "word": ".", "probability": 0.97216796875 } ] }, { "id": 1685, "seek": 434214, "start": 4435.1, "end": 4437.64, "text": " So I don't know if that's a whole machine learning problem", "tokens": [ 51114, 407, 286, 500, 380, 458, 498, 300, 311, 257, 1379, 3479, 2539, 1154, 51264 ], "temperature": 0.0, "avg_logprob": -0.19987500524520874, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.206787109375, "words": [ { "start": 4435.1, "end": 4435.54, "word": " So", "probability": 0.7861328125 }, { "start": 4435.54, "end": 4435.76, "word": " I", "probability": 0.82568359375 }, { "start": 4435.76, "end": 4435.84, "word": " don't", "probability": 0.9462890625 }, { "start": 4435.84, "end": 4436.02, "word": " know", "probability": 0.77001953125 }, { "start": 4436.02, "end": 4436.16, "word": " if", "probability": 0.71484375 }, { "start": 4436.16, "end": 4436.32, "word": " that's", "probability": 0.74462890625 }, { "start": 4436.6, "end": 4436.8, "word": " a whole", "probability": 0.7578125 }, { "start": 4436.8, "end": 4437.1, "word": " machine", "probability": 0.70068359375 }, { "start": 4437.1, "end": 4437.32, "word": " learning", "probability": 0.767578125 }, { "start": 4437.32, "end": 4437.64, "word": " problem", "probability": 0.77490234375 } ] }, { "id": 1686, "seek": 434214, "start": 4437.64, "end": 4439.14, "text": " or specifically a neural net problem", "tokens": [ 51264, 420, 4682, 257, 18161, 2533, 1154, 51414 ], "temperature": 0.0, "avg_logprob": -0.19987500524520874, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.206787109375, "words": [ { "start": 4437.64, "end": 4437.8, "word": " or", "probability": 0.83447265625 }, { "start": 4437.8, "end": 4438.24, "word": " specifically", "probability": 0.7216796875 }, { "start": 4438.46, "end": 4438.6, "word": " a neural", "probability": 0.84375 }, { "start": 4438.6, "end": 4438.78, "word": " net", "probability": 0.7724609375 }, { "start": 4438.78, "end": 4439.14, "word": " problem", "probability": 0.7744140625 } ] }, { "id": 1687, "seek": 434214, "start": 4439.14, "end": 4443.14, "text": " but it's just kind of an interesting anecdote.", "tokens": [ 51414, 457, 309, 311, 445, 733, 295, 364, 1880, 49845, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.19987500524520874, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.206787109375, "words": [ { "start": 4439.14, "end": 4439.94, "word": " but", "probability": 0.31298828125 }, { "start": 4439.94, "end": 4440.2, "word": " it's", "probability": 0.94677734375 }, { "start": 4440.2, "end": 4440.34, "word": " just", "probability": 0.87939453125 }, { "start": 4440.34, "end": 4440.58, "word": " kind", "probability": 0.76611328125 }, { "start": 4440.58, "end": 4440.78, "word": " of", "probability": 0.90673828125 }, { "start": 4440.78, "end": 4441.22, "word": " an", "probability": 0.478515625 }, { "start": 4441.22, "end": 4441.98, "word": " interesting", "probability": 0.62744140625 }, { "start": 4441.98, "end": 4442.7, "word": " anecdote", "probability": 0.66162109375 }, { "start": 4442.7, "end": 4443.14, "word": ".", "probability": 0.87451171875 } ] }, { "id": 1688, "seek": 434214, "start": 4444.06, "end": 4447.74, "text": " Be careful how you collect and preprocess and use your data.", "tokens": [ 51564, 879, 5026, 577, 291, 2500, 293, 2666, 340, 780, 293, 764, 428, 1412, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.19987500524520874, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.206787109375, "words": [ { "start": 4444.06, "end": 4444.5, "word": " Be", "probability": 0.8896484375 }, { "start": 4444.5, "end": 4444.72, "word": " careful", "probability": 0.900390625 }, { "start": 4444.72, "end": 4444.9, "word": " how", "probability": 0.90283203125 }, { "start": 4444.9, "end": 4445.04, "word": " you", "probability": 0.8994140625 }, { "start": 4445.04, "end": 4445.48, "word": " collect", "probability": 0.79443359375 }, { "start": 4445.48, "end": 4445.9, "word": " and", "probability": 0.86474609375 }, { "start": 4445.9, "end": 4446.6, "word": " preprocess", "probability": 0.7708333333333334 }, { "start": 4446.6, "end": 4446.78, "word": " and", "probability": 0.884765625 }, { "start": 4446.78, "end": 4446.94, "word": " use", "probability": 0.8095703125 }, { "start": 4446.94, "end": 4447.08, "word": " your", "probability": 0.80029296875 }, { "start": 4447.08, "end": 4447.3, "word": " data", "probability": 0.8017578125 }, { "start": 4447.3, "end": 4447.74, "word": ".", "probability": 0.99560546875 } ] }, { "id": 1689, "seek": 437008, "start": 4449.06, "end": 4451.64, "text": " A friend of mine did his PhD.", "tokens": [ 50414, 316, 1277, 295, 3892, 630, 702, 14476, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.27991617016675996, "compression_ratio": 1.5333333333333334, "no_speech_prob": 0.14794921875, "words": [ { "start": 4449.06, "end": 4449.84, "word": " A", "probability": 0.338134765625 }, { "start": 4449.84, "end": 4450.02, "word": " friend", "probability": 0.60498046875 }, { "start": 4450.02, "end": 4450.12, "word": " of", "probability": 0.90966796875 }, { "start": 4450.12, "end": 4450.3, "word": " mine", "probability": 0.84326171875 }, { "start": 4450.3, "end": 4450.52, "word": " did", "probability": 0.67138671875 }, { "start": 4450.52, "end": 4450.7, "word": " his", "probability": 0.83154296875 }, { "start": 4450.7, "end": 4451.14, "word": " PhD", "probability": 0.77734375 }, { "start": 4451.14, "end": 4451.64, "word": ".", "probability": 0.33251953125 } ] }, { "id": 1690, "seek": 437008, "start": 4451.64, "end": 4454.34, "text": " His PhD thesis was inducing the", "tokens": [ 50564, 2812, 14476, 22288, 390, 13716, 2175, 264, 50714 ], "temperature": 0.0, "avg_logprob": -0.27991617016675996, "compression_ratio": 1.5333333333333334, "no_speech_prob": 0.14794921875, "words": [ { "start": 4451.64, "end": 4452.0, "word": " His", "probability": 0.7880859375 }, { "start": 4452.0, "end": 4452.4, "word": " PhD", "probability": 0.87109375 }, { "start": 4452.4, "end": 4452.74, "word": " thesis", "probability": 0.84326171875 }, { "start": 4452.74, "end": 4453.02, "word": " was", "probability": 0.8916015625 }, { "start": 4453.02, "end": 4453.72, "word": " inducing", "probability": 0.775146484375 }, { "start": 4453.72, "end": 4454.34, "word": " the", "probability": 0.8125 } ] }, { "id": 1691, "seek": 437008, "start": 4455.22, "end": 4457.56, "text": " bias that's sort of like the inherent", "tokens": [ 50714, 272, 654, 82, 300, 311, 1333, 295, 411, 264, 26387, 50864 ], "temperature": 0.0, "avg_logprob": -0.27991617016675996, "compression_ratio": 1.5333333333333334, "no_speech_prob": 0.14794921875, "words": [ { "start": 4455.22, "end": 4456.0, "word": " bias", "probability": 0.5618489583333334 }, { "start": 4456.0, "end": 4456.34, "word": " that's", "probability": 0.694580078125 }, { "start": 4456.34, "end": 4456.62, "word": " sort", "probability": 0.66650390625 }, { "start": 4456.62, "end": 4456.76, "word": " of", "probability": 0.89892578125 }, { "start": 4456.76, "end": 4457.0, "word": " like", "probability": 0.76171875 }, { "start": 4457.0, "end": 4457.14, "word": " the", "probability": 0.59619140625 }, { "start": 4457.14, "end": 4457.56, "word": " inherent", "probability": 0.72802734375 } ] }, { "id": 1692, "seek": 437008, "start": 4458.36, "end": 4461.14, "text": " model bias that's in convolutional", "tokens": [ 50864, 2316, 12577, 300, 311, 294, 45216, 304, 51014 ], "temperature": 0.0, "avg_logprob": -0.27991617016675996, "compression_ratio": 1.5333333333333334, "no_speech_prob": 0.14794921875, "words": [ { "start": 4458.36, "end": 4459.14, "word": " model", "probability": 0.83642578125 }, { "start": 4459.14, "end": 4459.64, "word": " bias", "probability": 0.75927734375 }, { "start": 4459.64, "end": 4460.08, "word": " that's", "probability": 0.8759765625 }, { "start": 4460.08, "end": 4460.44, "word": " in", "probability": 0.8798828125 }, { "start": 4460.44, "end": 4461.14, "word": " convolutional", "probability": 0.82373046875 } ] }, { "id": 1693, "seek": 437008, "start": 4461.14, "end": 4463.98, "text": " neural networks into other models", "tokens": [ 51014, 18161, 9590, 666, 661, 5245, 51164 ], "temperature": 0.0, "avg_logprob": -0.27991617016675996, "compression_ratio": 1.5333333333333334, "no_speech_prob": 0.14794921875, "words": [ { "start": 4461.14, "end": 4461.28, "word": " neural", "probability": 0.89111328125 }, { "start": 4461.28, "end": 4461.7, "word": " networks", "probability": 0.68017578125 }, { "start": 4461.7, "end": 4463.12, "word": " into", "probability": 0.62060546875 }, { "start": 4463.12, "end": 4463.5, "word": " other", "probability": 0.78564453125 }, { "start": 4463.5, "end": 4463.98, "word": " models", "probability": 0.81005859375 } ] }, { "id": 1694, "seek": 437008, "start": 4463.98, "end": 4466.14, "text": " and it slightly improved.", "tokens": [ 51164, 293, 309, 4748, 9689, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.27991617016675996, "compression_ratio": 1.5333333333333334, "no_speech_prob": 0.14794921875, "words": [ { "start": 4463.98, "end": 4464.24, "word": " and", "probability": 0.373779296875 }, { "start": 4464.24, "end": 4464.36, "word": " it", "probability": 0.83935546875 }, { "start": 4464.36, "end": 4464.6, "word": " slightly", "probability": 0.401123046875 }, { "start": 4464.6, "end": 4465.36, "word": " improved", "probability": 0.79541015625 }, { "start": 4465.36, "end": 4466.14, "word": ".", "probability": 0.65966796875 } ] }, { "id": 1695, "seek": 437008, "start": 4469.2, "end": 4471.62, "text": " By inducing a bias?", "tokens": [ 51314, 3146, 13716, 2175, 257, 12577, 30, 51464 ], "temperature": 0.0, "avg_logprob": -0.27991617016675996, "compression_ratio": 1.5333333333333334, "no_speech_prob": 0.14794921875, "words": [ { "start": 4469.2, "end": 4469.76, "word": " By", "probability": 0.69091796875 }, { "start": 4469.76, "end": 4470.36, "word": " inducing", "probability": 0.810302734375 }, { "start": 4470.52, "end": 4470.84, "word": " a bias", "probability": 0.82421875 }, { "start": 4470.84, "end": 4471.62, "word": "?", "probability": 0.95654296875 } ] }, { "id": 1696, "seek": 437008, "start": 4471.84, "end": 4475.34, "text": " Yeah, you can induce a pixel", "tokens": [ 51464, 865, 11, 291, 393, 41263, 257, 19261, 51614 ], "temperature": 0.0, "avg_logprob": -0.27991617016675996, "compression_ratio": 1.5333333333333334, "no_speech_prob": 0.14794921875, "words": [ { "start": 4471.84, "end": 4472.14, "word": " Yeah", "probability": 0.89208984375 }, { "start": 4472.14, "end": 4472.3, "word": ",", "probability": 0.693359375 }, { "start": 4472.3, "end": 4472.42, "word": " you", "probability": 0.888671875 }, { "start": 4472.42, "end": 4472.58, "word": " can", "probability": 0.892578125 }, { "start": 4472.58, "end": 4473.24, "word": " induce", "probability": 0.73974609375 }, { "start": 4474.12, "end": 4475.34, "word": " a pixel", "probability": 0.61865234375 } ] }, { "id": 1697, "seek": 437008, "start": 4475.34, "end": 4478.1, "text": " locality bias like a great green", "tokens": [ 51614, 1628, 1860, 12577, 411, 257, 869, 3092, 51764 ], "temperature": 0.0, "avg_logprob": -0.27991617016675996, "compression_ratio": 1.5333333333333334, "no_speech_prob": 0.14794921875, "words": [ { "start": 4475.34, "end": 4475.96, "word": " locality", "probability": 0.946533203125 }, { "start": 4475.96, "end": 4476.44, "word": " bias", "probability": 0.85205078125 }, { "start": 4476.44, "end": 4477.14, "word": " like", "probability": 0.205322265625 }, { "start": 4477.48, "end": 4477.9, "word": " a great", "probability": 0.2919921875 }, { "start": 4477.9, "end": 4478.1, "word": " green", "probability": 0.11676025390625 } ] }, { "id": 1698, "seek": 439756, "start": 4478.1, "end": 4482.14, "text": " tree or a support vector machine", "tokens": [ 50364, 4230, 420, 257, 1406, 8062, 3479, 50514 ], "temperature": 0.0, "avg_logprob": -0.25661058227221173, "compression_ratio": 1.57, "no_speech_prob": 0.052581787109375, "words": [ { "start": 4478.1, "end": 4478.52, "word": " tree", "probability": 0.0253753662109375 }, { "start": 4478.52, "end": 4479.18, "word": " or", "probability": 0.751953125 }, { "start": 4480.06, "end": 4481.44, "word": " a support", "probability": 0.83203125 }, { "start": 4481.44, "end": 4481.68, "word": " vector", "probability": 0.91552734375 }, { "start": 4481.68, "end": 4482.14, "word": " machine", "probability": 0.72802734375 } ] }, { "id": 1699, "seek": 439756, "start": 4483.26, "end": 4484.78, "text": " and it improves", "tokens": [ 50514, 293, 309, 24771, 50664 ], "temperature": 0.0, "avg_logprob": -0.25661058227221173, "compression_ratio": 1.57, "no_speech_prob": 0.052581787109375, "words": [ { "start": 4483.26, "end": 4483.86, "word": " and", "probability": 0.2115478515625 }, { "start": 4483.86, "end": 4484.1, "word": " it", "probability": 0.67333984375 }, { "start": 4484.1, "end": 4484.78, "word": " improves", "probability": 0.67822265625 } ] }, { "id": 1700, "seek": 439756, "start": 4485.7, "end": 4487.74, "text": " that's one of the assumptions that people make", "tokens": [ 50664, 300, 311, 472, 295, 264, 17695, 300, 561, 652, 50814 ], "temperature": 0.0, "avg_logprob": -0.25661058227221173, "compression_ratio": 1.57, "no_speech_prob": 0.052581787109375, "words": [ { "start": 4485.7, "end": 4486.3, "word": " that's", "probability": 0.148773193359375 }, { "start": 4486.3, "end": 4486.48, "word": " one", "probability": 0.818359375 }, { "start": 4486.48, "end": 4486.58, "word": " of", "probability": 0.9013671875 }, { "start": 4486.58, "end": 4486.7, "word": " the", "probability": 0.8173828125 }, { "start": 4486.7, "end": 4487.08, "word": " assumptions", "probability": 0.900390625 }, { "start": 4487.08, "end": 4487.32, "word": " that", "probability": 0.828125 }, { "start": 4487.32, "end": 4487.48, "word": " people", "probability": 0.92724609375 }, { "start": 4487.48, "end": 4487.74, "word": " make", "probability": 0.880859375 } ] }, { "id": 1701, "seek": 439756, "start": 4487.74, "end": 4490.92, "text": " about convolutional neural networks is it allows you to make", "tokens": [ 50814, 466, 45216, 304, 18161, 9590, 307, 309, 4045, 291, 281, 652, 50964 ], "temperature": 0.0, "avg_logprob": -0.25661058227221173, "compression_ratio": 1.57, "no_speech_prob": 0.052581787109375, "words": [ { "start": 4487.74, "end": 4487.96, "word": " about", "probability": 0.81884765625 }, { "start": 4487.96, "end": 4488.84, "word": " convolutional", "probability": 0.849853515625 }, { "start": 4488.84, "end": 4489.46, "word": " neural", "probability": 0.53515625 }, { "start": 4489.46, "end": 4489.8, "word": " networks", "probability": 0.53466796875 }, { "start": 4489.8, "end": 4489.98, "word": " is", "probability": 0.369140625 }, { "start": 4489.98, "end": 4490.08, "word": " it", "probability": 0.36474609375 }, { "start": 4490.08, "end": 4490.32, "word": " allows", "probability": 0.73583984375 }, { "start": 4490.32, "end": 4490.58, "word": " you", "probability": 0.888671875 }, { "start": 4490.58, "end": 4490.7, "word": " to", "probability": 0.90283203125 }, { "start": 4490.7, "end": 4490.92, "word": " make", "probability": 0.87451171875 } ] }, { "id": 1702, "seek": 439756, "start": 4490.92, "end": 4493.9, "text": " small pixel local decisions", "tokens": [ 50964, 1359, 19261, 2654, 5327, 51114 ], "temperature": 0.0, "avg_logprob": -0.25661058227221173, "compression_ratio": 1.57, "no_speech_prob": 0.052581787109375, "words": [ { "start": 4490.92, "end": 4491.98, "word": " small", "probability": 0.4033203125 }, { "start": 4491.98, "end": 4492.4, "word": " pixel", "probability": 0.71484375 }, { "start": 4492.4, "end": 4493.34, "word": " local", "probability": 0.611328125 }, { "start": 4493.34, "end": 4493.9, "word": " decisions", "probability": 0.5791015625 } ] }, { "id": 1703, "seek": 439756, "start": 4494.88, "end": 4496.88, "text": " and then those can get glued together", "tokens": [ 51114, 293, 550, 729, 393, 483, 28008, 1214, 51264 ], "temperature": 0.0, "avg_logprob": -0.25661058227221173, "compression_ratio": 1.57, "no_speech_prob": 0.052581787109375, "words": [ { "start": 4494.88, "end": 4495.48, "word": " and", "probability": 0.73046875 }, { "start": 4495.48, "end": 4495.62, "word": " then", "probability": 0.68359375 }, { "start": 4495.62, "end": 4495.88, "word": " those", "probability": 0.85546875 }, { "start": 4495.88, "end": 4496.08, "word": " can", "probability": 0.88916015625 }, { "start": 4496.08, "end": 4496.26, "word": " get", "probability": 0.87744140625 }, { "start": 4496.26, "end": 4496.5, "word": " glued", "probability": 0.673828125 }, { "start": 4496.5, "end": 4496.88, "word": " together", "probability": 0.77978515625 } ] }, { "id": 1704, "seek": 439756, "start": 4496.88, "end": 4498.5, "text": " in the right way.", "tokens": [ 51264, 294, 264, 558, 636, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.25661058227221173, "compression_ratio": 1.57, "no_speech_prob": 0.052581787109375, "words": [ { "start": 4496.88, "end": 4497.14, "word": " in", "probability": 0.8984375 }, { "start": 4497.14, "end": 4497.26, "word": " the", "probability": 0.81591796875 }, { "start": 4497.26, "end": 4497.48, "word": " right", "probability": 0.88623046875 }, { "start": 4497.48, "end": 4497.9, "word": " way", "probability": 0.89599609375 }, { "start": 4497.9, "end": 4498.5, "word": ".", "probability": 0.56884765625 } ] }, { "id": 1705, "seek": 439756, "start": 4500.16, "end": 4502.9, "text": " And so he went and built little modifications", "tokens": [ 51414, 400, 370, 415, 1437, 293, 3094, 707, 26881, 51564 ], "temperature": 0.0, "avg_logprob": -0.25661058227221173, "compression_ratio": 1.57, "no_speech_prob": 0.052581787109375, "words": [ { "start": 4500.16, "end": 4500.2, "word": " And", "probability": 0.55078125 }, { "start": 4500.2, "end": 4500.4, "word": " so", "probability": 0.88818359375 }, { "start": 4500.4, "end": 4500.62, "word": " he", "probability": 0.85498046875 }, { "start": 4500.62, "end": 4501.1, "word": " went", "probability": 0.477294921875 }, { "start": 4501.1, "end": 4501.54, "word": " and", "probability": 0.8876953125 }, { "start": 4501.54, "end": 4501.78, "word": " built", "probability": 0.9150390625 }, { "start": 4501.78, "end": 4502.3, "word": " little", "probability": 0.7529296875 }, { "start": 4502.3, "end": 4502.9, "word": " modifications", "probability": 0.681640625 } ] }, { "id": 1706, "seek": 439756, "start": 4502.9, "end": 4505.58, "text": " to a dozen other algorithms", "tokens": [ 51564, 281, 257, 16654, 661, 14642, 51714 ], "temperature": 0.0, "avg_logprob": -0.25661058227221173, "compression_ratio": 1.57, "no_speech_prob": 0.052581787109375, "words": [ { "start": 4502.9, "end": 4503.3, "word": " to", "probability": 0.9033203125 }, { "start": 4503.6, "end": 4503.9, "word": " a dozen", "probability": 0.81591796875 }, { "start": 4503.9, "end": 4505.04, "word": " other", "probability": 0.6552734375 }, { "start": 4505.04, "end": 4505.58, "word": " algorithms", "probability": 0.8828125 } ] }, { "id": 1707, "seek": 442460, "start": 4505.58, "end": 4507.26, "text": " that have sort of fallen out of favor", "tokens": [ 50364, 300, 362, 1333, 295, 11547, 484, 295, 2294, 50514 ], "temperature": 0.0, "avg_logprob": -0.25485641690524846, "compression_ratio": 1.4858757062146892, "no_speech_prob": 0.2017822265625, "words": [ { "start": 4505.58, "end": 4505.88, "word": " that", "probability": 0.6357421875 }, { "start": 4505.88, "end": 4506.12, "word": " have", "probability": 0.6962890625 }, { "start": 4506.12, "end": 4506.36, "word": " sort", "probability": 0.430908203125 }, { "start": 4506.36, "end": 4506.44, "word": " of", "probability": 0.89892578125 }, { "start": 4506.44, "end": 4506.62, "word": " fallen", "probability": 0.7255859375 }, { "start": 4506.62, "end": 4506.82, "word": " out", "probability": 0.81982421875 }, { "start": 4506.82, "end": 4507.0, "word": " of", "probability": 0.89111328125 }, { "start": 4507.0, "end": 4507.26, "word": " favor", "probability": 0.7490234375 } ] }, { "id": 1708, "seek": 442460, "start": 4507.26, "end": 4511.4, "text": " and all of them improved slightly on images", "tokens": [ 50514, 293, 439, 295, 552, 9689, 4748, 322, 5267, 50664 ], "temperature": 0.0, "avg_logprob": -0.25485641690524846, "compression_ratio": 1.4858757062146892, "no_speech_prob": 0.2017822265625, "words": [ { "start": 4507.26, "end": 4508.44, "word": " and", "probability": 0.37353515625 }, { "start": 4508.44, "end": 4509.26, "word": " all", "probability": 0.85546875 }, { "start": 4509.26, "end": 4509.38, "word": " of", "probability": 0.8955078125 }, { "start": 4509.38, "end": 4509.5, "word": " them", "probability": 0.72412109375 }, { "start": 4509.5, "end": 4509.88, "word": " improved", "probability": 0.5712890625 }, { "start": 4509.88, "end": 4510.28, "word": " slightly", "probability": 0.779296875 }, { "start": 4510.28, "end": 4511.02, "word": " on", "probability": 0.701171875 }, { "start": 4511.02, "end": 4511.4, "word": " images", "probability": 0.79638671875 } ] }, { "id": 1709, "seek": 442460, "start": 4511.4, "end": 4514.5, "text": " when you induced a pixel local bias.", "tokens": [ 50664, 562, 291, 33991, 257, 19261, 2654, 12577, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.25485641690524846, "compression_ratio": 1.4858757062146892, "no_speech_prob": 0.2017822265625, "words": [ { "start": 4511.4, "end": 4511.68, "word": " when", "probability": 0.8564453125 }, { "start": 4511.68, "end": 4511.84, "word": " you", "probability": 0.8876953125 }, { "start": 4511.84, "end": 4512.52, "word": " induced", "probability": 0.42431640625 }, { "start": 4512.8, "end": 4513.16, "word": " a pixel", "probability": 0.7216796875 }, { "start": 4513.16, "end": 4513.44, "word": " local", "probability": 0.53466796875 }, { "start": 4513.44, "end": 4513.9, "word": " bias", "probability": 0.72412109375 }, { "start": 4513.9, "end": 4514.5, "word": ".", "probability": 0.955078125 } ] }, { "id": 1710, "seek": 442460, "start": 4514.98, "end": 4517.16, "text": " Okay, interesting.", "tokens": [ 50814, 1033, 11, 1880, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.25485641690524846, "compression_ratio": 1.4858757062146892, "no_speech_prob": 0.2017822265625, "words": [ { "start": 4514.98, "end": 4515.58, "word": " Okay", "probability": 0.431396484375 }, { "start": 4515.58, "end": 4516.08, "word": ",", "probability": 0.59228515625 }, { "start": 4516.08, "end": 4516.58, "word": " interesting", "probability": 0.63720703125 }, { "start": 4516.58, "end": 4517.16, "word": ".", "probability": 0.8974609375 } ] }, { "id": 1711, "seek": 442460, "start": 4517.16, "end": 4520.2, "text": " Yeah, that's", "tokens": [ 50964, 865, 11, 300, 311, 51114 ], "temperature": 0.0, "avg_logprob": -0.25485641690524846, "compression_ratio": 1.4858757062146892, "no_speech_prob": 0.2017822265625, "words": [ { "start": 4517.16, "end": 4517.16, "word": " Yeah", "probability": 0.5517578125 }, { "start": 4517.16, "end": 4519.78, "word": ",", "probability": 0.44140625 }, { "start": 4519.78, "end": 4520.2, "word": " that's", "probability": 0.900634765625 } ] }, { "id": 1712, "seek": 442460, "start": 4523.14, "end": 4523.92, "text": " that's actually", "tokens": [ 51114, 300, 311, 767, 51264 ], "temperature": 0.0, "avg_logprob": -0.25485641690524846, "compression_ratio": 1.4858757062146892, "no_speech_prob": 0.2017822265625, "words": [ { "start": 4523.14, "end": 4523.74, "word": " that's", "probability": 0.5204925537109375 }, { "start": 4523.74, "end": 4523.92, "word": " actually", "probability": 0.771484375 } ] }, { "id": 1713, "seek": 442460, "start": 4523.92, "end": 4524.9, "text": " really interesting.", "tokens": [ 51264, 534, 1880, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.25485641690524846, "compression_ratio": 1.4858757062146892, "no_speech_prob": 0.2017822265625, "words": [ { "start": 4523.92, "end": 4524.16, "word": " really", "probability": 0.76220703125 }, { "start": 4524.16, "end": 4524.56, "word": " interesting", "probability": 0.72119140625 }, { "start": 4524.56, "end": 4524.9, "word": ".", "probability": 0.70703125 } ] }, { "id": 1714, "seek": 442460, "start": 4527.48, "end": 4528.92, "text": " Alright, so", "tokens": [ 51414, 2798, 11, 370, 51564 ], "temperature": 0.0, "avg_logprob": -0.25485641690524846, "compression_ratio": 1.4858757062146892, "no_speech_prob": 0.2017822265625, "words": [ { "start": 4527.48, "end": 4528.08, "word": " Alright", "probability": 0.0965576171875 }, { "start": 4528.08, "end": 4528.68, "word": ",", "probability": 0.69580078125 }, { "start": 4528.68, "end": 4528.92, "word": " so", "probability": 0.87890625 } ] }, { "id": 1715, "seek": 442460, "start": 4529.52, "end": 4532.62, "text": " hopefully I gave you guys enough time to make sure that this got", "tokens": [ 51564, 4696, 286, 2729, 291, 1074, 1547, 565, 281, 652, 988, 300, 341, 658, 51714 ], "temperature": 0.0, "avg_logprob": -0.25485641690524846, "compression_ratio": 1.4858757062146892, "no_speech_prob": 0.2017822265625, "words": [ { "start": 4529.52, "end": 4530.12, "word": " hopefully", "probability": 0.607421875 }, { "start": 4530.12, "end": 4530.28, "word": " I", "probability": 0.9482421875 }, { "start": 4530.28, "end": 4530.42, "word": " gave", "probability": 0.7734375 }, { "start": 4530.42, "end": 4530.52, "word": " you", "probability": 0.89599609375 }, { "start": 4530.52, "end": 4530.72, "word": " guys", "probability": 0.8818359375 }, { "start": 4530.72, "end": 4530.98, "word": " enough", "probability": 0.78369140625 }, { "start": 4530.98, "end": 4531.32, "word": " time", "probability": 0.81787109375 }, { "start": 4531.32, "end": 4531.7, "word": " to", "probability": 0.90576171875 }, { "start": 4531.7, "end": 4532.0, "word": " make", "probability": 0.88232421875 }, { "start": 4532.0, "end": 4532.12, "word": " sure", "probability": 0.81982421875 }, { "start": 4532.12, "end": 4532.28, "word": " that", "probability": 0.8671875 }, { "start": 4532.28, "end": 4532.42, "word": " this", "probability": 0.88623046875 }, { "start": 4532.42, "end": 4532.62, "word": " got", "probability": 0.8994140625 } ] }, { "id": 1716, "seek": 445014, "start": 4532.62, "end": 4534.98, "text": " copied down. I'm going to go ahead and run it", "tokens": [ 50364, 25365, 760, 13, 286, 478, 516, 281, 352, 2286, 293, 1190, 309, 50514 ], "temperature": 0.0, "avg_logprob": -0.2149234637618065, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.31396484375, "words": [ { "start": 4532.62, "end": 4532.96, "word": " copied", "probability": 0.01507568359375 }, { "start": 4532.96, "end": 4533.42, "word": " down", "probability": 0.80517578125 }, { "start": 4533.42, "end": 4533.84, "word": ".", "probability": 0.3671875 }, { "start": 4533.84, "end": 4533.96, "word": " I'm", "probability": 0.58642578125 }, { "start": 4533.96, "end": 4533.96, "word": " going", "probability": 0.5009765625 }, { "start": 4533.96, "end": 4533.98, "word": " to", "probability": 0.90625 }, { "start": 4533.98, "end": 4534.08, "word": " go", "probability": 0.89306640625 }, { "start": 4534.08, "end": 4534.4, "word": " ahead", "probability": 0.85986328125 }, { "start": 4534.4, "end": 4534.56, "word": " and", "probability": 0.892578125 }, { "start": 4534.56, "end": 4534.84, "word": " run", "probability": 0.8798828125 }, { "start": 4534.84, "end": 4534.98, "word": " it", "probability": 0.8994140625 } ] }, { "id": 1717, "seek": 445014, "start": 4534.98, "end": 4538.22, "text": " and shift enter. This is going to take a little bit because it's going through", "tokens": [ 50514, 293, 5513, 3242, 13, 639, 307, 516, 281, 747, 257, 707, 857, 570, 309, 311, 516, 807, 50664 ], "temperature": 0.0, "avg_logprob": -0.2149234637618065, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.31396484375, "words": [ { "start": 4534.98, "end": 4535.1, "word": " and", "probability": 0.126708984375 }, { "start": 4535.1, "end": 4535.34, "word": " shift", "probability": 0.67236328125 }, { "start": 4535.34, "end": 4535.76, "word": " enter", "probability": 0.46484375 }, { "start": 4535.76, "end": 4536.2, "word": ".", "probability": 0.82958984375 }, { "start": 4536.36, "end": 4536.72, "word": " This", "probability": 0.5029296875 }, { "start": 4536.72, "end": 4536.76, "word": " is", "probability": 0.9033203125 }, { "start": 4536.76, "end": 4536.84, "word": " going", "probability": 0.80322265625 }, { "start": 4536.84, "end": 4536.9, "word": " to", "probability": 0.9052734375 }, { "start": 4536.9, "end": 4537.04, "word": " take", "probability": 0.814453125 }, { "start": 4537.14, "end": 4537.24, "word": " a little", "probability": 0.81201171875 }, { "start": 4537.24, "end": 4537.46, "word": " bit", "probability": 0.8955078125 }, { "start": 4537.46, "end": 4537.64, "word": " because", "probability": 0.7490234375 }, { "start": 4537.64, "end": 4537.8, "word": " it's", "probability": 0.943115234375 }, { "start": 4537.8, "end": 4537.98, "word": " going", "probability": 0.845703125 }, { "start": 4537.98, "end": 4538.22, "word": " through", "probability": 0.787109375 } ] }, { "id": 1718, "seek": 445014, "start": 4538.22, "end": 4540.32, "text": " its matrix multiplications", "tokens": [ 50664, 1080, 8141, 17596, 763, 50814 ], "temperature": 0.0, "avg_logprob": -0.2149234637618065, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.31396484375, "words": [ { "start": 4538.22, "end": 4538.52, "word": " its", "probability": 0.7509765625 }, { "start": 4538.52, "end": 4539.24, "word": " matrix", "probability": 0.83544921875 }, { "start": 4539.24, "end": 4540.32, "word": " multiplications", "probability": 0.79296875 } ] }, { "id": 1719, "seek": 445014, "start": 4541.2, "end": 4544.1, "text": " but in the meantime, we're about to hop into", "tokens": [ 50814, 457, 294, 264, 14991, 11, 321, 434, 466, 281, 3818, 666, 50964 ], "temperature": 0.0, "avg_logprob": -0.2149234637618065, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.31396484375, "words": [ { "start": 4541.2, "end": 4541.64, "word": " but", "probability": 0.1744384765625 }, { "start": 4541.64, "end": 4541.84, "word": " in", "probability": 0.8876953125 }, { "start": 4541.84, "end": 4542.06, "word": " the", "probability": 0.8095703125 }, { "start": 4542.06, "end": 4542.48, "word": " meantime", "probability": 0.8671875 }, { "start": 4542.48, "end": 4543.16, "word": ",", "probability": 0.22998046875 }, { "start": 4543.16, "end": 4543.34, "word": " we're", "probability": 0.927490234375 }, { "start": 4543.34, "end": 4543.48, "word": " about", "probability": 0.82177734375 }, { "start": 4543.48, "end": 4543.62, "word": " to", "probability": 0.904296875 }, { "start": 4543.62, "end": 4543.78, "word": " hop", "probability": 0.90869140625 }, { "start": 4543.78, "end": 4544.1, "word": " into", "probability": 0.7314453125 } ] }, { "id": 1720, "seek": 445014, "start": 4544.62, "end": 4546.78, "text": " our final task", "tokens": [ 50964, 527, 2572, 5633, 51114 ], "temperature": 0.0, "avg_logprob": -0.2149234637618065, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.31396484375, "words": [ { "start": 4544.62, "end": 4544.84, "word": " our", "probability": 0.82666015625 }, { "start": 4544.84, "end": 4546.02, "word": " final", "probability": 0.8740234375 }, { "start": 4546.02, "end": 4546.78, "word": " task", "probability": 0.81005859375 } ] }, { "id": 1721, "seek": 445014, "start": 4546.78, "end": 4549.96, "text": " and what we have is a real spam email", "tokens": [ 51114, 293, 437, 321, 362, 307, 257, 957, 24028, 3796, 51264 ], "temperature": 0.0, "avg_logprob": -0.2149234637618065, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.31396484375, "words": [ { "start": 4546.78, "end": 4547.62, "word": " and", "probability": 0.491943359375 }, { "start": 4547.62, "end": 4548.66, "word": " what", "probability": 0.8203125 }, { "start": 4548.66, "end": 4548.8, "word": " we", "probability": 0.90673828125 }, { "start": 4548.8, "end": 4548.98, "word": " have", "probability": 0.87353515625 }, { "start": 4548.98, "end": 4549.06, "word": " is", "probability": 0.9033203125 }, { "start": 4549.18, "end": 4549.38, "word": " a real", "probability": 0.875 }, { "start": 4549.38, "end": 4549.68, "word": " spam", "probability": 0.94287109375 }, { "start": 4549.68, "end": 4549.96, "word": " email", "probability": 0.90380859375 } ] }, { "id": 1722, "seek": 445014, "start": 4549.96, "end": 4552.58, "text": " I pulled this out of my inbox or my spam folder", "tokens": [ 51264, 286, 7373, 341, 484, 295, 452, 35067, 420, 452, 24028, 10820, 51414 ], "temperature": 0.0, "avg_logprob": -0.2149234637618065, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.31396484375, "words": [ { "start": 4549.96, "end": 4550.12, "word": " I", "probability": 0.0946044921875 }, { "start": 4550.12, "end": 4550.32, "word": " pulled", "probability": 0.8466796875 }, { "start": 4550.32, "end": 4550.52, "word": " this", "probability": 0.87060546875 }, { "start": 4550.52, "end": 4550.64, "word": " out", "probability": 0.8291015625 }, { "start": 4550.64, "end": 4550.74, "word": " of", "probability": 0.90673828125 }, { "start": 4550.74, "end": 4550.86, "word": " my", "probability": 0.91650390625 }, { "start": 4550.86, "end": 4551.32, "word": " inbox", "probability": 0.78955078125 }, { "start": 4551.32, "end": 4551.52, "word": " or", "probability": 0.87939453125 }, { "start": 4551.52, "end": 4551.68, "word": " my", "probability": 0.9033203125 }, { "start": 4551.68, "end": 4551.98, "word": " spam", "probability": 0.92919921875 }, { "start": 4551.98, "end": 4552.58, "word": " folder", "probability": 0.7666015625 } ] }, { "id": 1723, "seek": 445014, "start": 4554.22, "end": 4555.1, "text": " last May", "tokens": [ 51414, 1036, 1891, 51564 ], "temperature": 0.0, "avg_logprob": -0.2149234637618065, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.31396484375, "words": [ { "start": 4554.22, "end": 4554.66, "word": " last", "probability": 0.69873046875 }, { "start": 4554.66, "end": 4555.1, "word": " May", "probability": 0.78955078125 } ] }, { "id": 1724, "seek": 445014, "start": 4555.86, "end": 4558.16, "text": " but we see your latest issue is available now", "tokens": [ 51564, 457, 321, 536, 428, 6792, 2734, 307, 2435, 586, 51714 ], "temperature": 0.0, "avg_logprob": -0.2149234637618065, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.31396484375, "words": [ { "start": 4555.86, "end": 4556.3, "word": " but", "probability": 0.52490234375 }, { "start": 4556.3, "end": 4556.48, "word": " we", "probability": 0.89990234375 }, { "start": 4556.48, "end": 4556.7, "word": " see", "probability": 0.8154296875 }, { "start": 4556.7, "end": 4556.92, "word": " your", "probability": 0.66064453125 }, { "start": 4556.92, "end": 4557.14, "word": " latest", "probability": 0.841796875 }, { "start": 4557.14, "end": 4557.38, "word": " issue", "probability": 0.81640625 }, { "start": 4557.38, "end": 4557.5, "word": " is", "probability": 0.904296875 }, { "start": 4557.5, "end": 4557.74, "word": " available", "probability": 0.72314453125 }, { "start": 4557.74, "end": 4558.16, "word": " now", "probability": 0.880859375 } ] }, { "id": 1725, "seek": 447684, "start": 4558.16, "end": 4560.94, "text": " if you don't want issue notifications, click here to unsubscribe", "tokens": [ 50364, 498, 291, 500, 380, 528, 2734, 13426, 11, 2052, 510, 281, 2693, 9493, 50514 ], "temperature": 0.0, "avg_logprob": -0.19385162771232728, "compression_ratio": 1.6702127659574468, "no_speech_prob": 0.08880615234375, "words": [ { "start": 4558.16, "end": 4558.4, "word": " if", "probability": 0.29345703125 }, { "start": 4558.4, "end": 4558.52, "word": " you", "probability": 0.90185546875 }, { "start": 4558.52, "end": 4558.7, "word": " don't", "probability": 0.94482421875 }, { "start": 4558.7, "end": 4558.96, "word": " want", "probability": 0.80615234375 }, { "start": 4558.96, "end": 4559.26, "word": " issue", "probability": 0.5087890625 }, { "start": 4559.26, "end": 4559.8, "word": " notifications", "probability": 0.77587890625 }, { "start": 4559.8, "end": 4560.02, "word": ",", "probability": 0.476318359375 }, { "start": 4560.02, "end": 4560.16, "word": " click", "probability": 0.828125 }, { "start": 4560.16, "end": 4560.3, "word": " here", "probability": 0.8017578125 }, { "start": 4560.3, "end": 4560.4, "word": " to", "probability": 0.9052734375 }, { "start": 4560.4, "end": 4560.94, "word": " unsubscribe", "probability": 0.822021484375 } ] }, { "id": 1726, "seek": 447684, "start": 4561.66, "end": 4563.84, "text": " Hi George. My name is not George", "tokens": [ 50514, 2421, 7136, 13, 1222, 1315, 307, 406, 7136, 50664 ], "temperature": 0.0, "avg_logprob": -0.19385162771232728, "compression_ratio": 1.6702127659574468, "no_speech_prob": 0.08880615234375, "words": [ { "start": 4561.66, "end": 4562.06, "word": " Hi", "probability": 0.0307159423828125 }, { "start": 4562.06, "end": 4562.46, "word": " George", "probability": 0.62109375 }, { "start": 4562.46, "end": 4562.86, "word": ".", "probability": 0.2171630859375 }, { "start": 4562.9, "end": 4563.1, "word": " My", "probability": 0.810546875 }, { "start": 4563.1, "end": 4563.2, "word": " name", "probability": 0.8173828125 }, { "start": 4563.2, "end": 4563.28, "word": " is", "probability": 0.90185546875 }, { "start": 4563.28, "end": 4563.46, "word": " not", "probability": 0.875 }, { "start": 4563.46, "end": 4563.84, "word": " George", "probability": 0.8720703125 } ] }, { "id": 1727, "seek": 447684, "start": 4565.18, "end": 4567.4, "text": " but we're going to look at this email", "tokens": [ 50664, 457, 321, 434, 516, 281, 574, 412, 341, 3796, 50814 ], "temperature": 0.0, "avg_logprob": -0.19385162771232728, "compression_ratio": 1.6702127659574468, "no_speech_prob": 0.08880615234375, "words": [ { "start": 4565.18, "end": 4565.58, "word": " but", "probability": 0.1607666015625 }, { "start": 4565.58, "end": 4565.98, "word": " we're", "probability": 0.776123046875 }, { "start": 4565.98, "end": 4566.04, "word": " going", "probability": 0.479736328125 }, { "start": 4566.04, "end": 4566.1, "word": " to", "probability": 0.90234375 }, { "start": 4566.1, "end": 4566.2, "word": " look", "probability": 0.9140625 }, { "start": 4566.2, "end": 4566.32, "word": " at", "probability": 0.9091796875 }, { "start": 4566.32, "end": 4566.72, "word": " this", "probability": 0.87939453125 }, { "start": 4566.72, "end": 4567.4, "word": " email", "probability": 0.8515625 } ] }, { "id": 1728, "seek": 447684, "start": 4567.4, "end": 4570.26, "text": " and we're going to try it against all four of our spam classifiers", "tokens": [ 50814, 293, 321, 434, 516, 281, 853, 309, 1970, 439, 1451, 295, 527, 24028, 1508, 23463, 50964 ], "temperature": 0.0, "avg_logprob": -0.19385162771232728, "compression_ratio": 1.6702127659574468, "no_speech_prob": 0.08880615234375, "words": [ { "start": 4567.4, "end": 4567.62, "word": " and", "probability": 0.399658203125 }, { "start": 4567.62, "end": 4567.74, "word": " we're", "probability": 0.8974609375 }, { "start": 4567.74, "end": 4567.78, "word": " going", "probability": 0.8193359375 }, { "start": 4567.78, "end": 4567.8, "word": " to", "probability": 0.90087890625 }, { "start": 4567.8, "end": 4567.94, "word": " try", "probability": 0.8271484375 }, { "start": 4567.94, "end": 4568.04, "word": " it", "probability": 0.88232421875 }, { "start": 4568.04, "end": 4568.24, "word": " against", "probability": 0.8603515625 }, { "start": 4568.24, "end": 4568.52, "word": " all", "probability": 0.90771484375 }, { "start": 4568.52, "end": 4568.98, "word": " four", "probability": 0.87109375 }, { "start": 4568.98, "end": 4569.22, "word": " of", "probability": 0.9052734375 }, { "start": 4569.22, "end": 4569.36, "word": " our", "probability": 0.8330078125 }, { "start": 4569.36, "end": 4569.64, "word": " spam", "probability": 0.912109375 }, { "start": 4569.64, "end": 4570.26, "word": " classifiers", "probability": 0.9228515625 } ] }, { "id": 1729, "seek": 447684, "start": 4570.26, "end": 4573.36, "text": " and see how well they do. But what's also good about this exercise", "tokens": [ 50964, 293, 536, 577, 731, 436, 360, 13, 583, 437, 311, 611, 665, 466, 341, 5380, 51114 ], "temperature": 0.0, "avg_logprob": -0.19385162771232728, "compression_ratio": 1.6702127659574468, "no_speech_prob": 0.08880615234375, "words": [ { "start": 4570.26, "end": 4570.44, "word": " and", "probability": 0.86328125 }, { "start": 4570.44, "end": 4570.6, "word": " see", "probability": 0.81787109375 }, { "start": 4570.6, "end": 4570.76, "word": " how", "probability": 0.90087890625 }, { "start": 4570.76, "end": 4570.96, "word": " well", "probability": 0.88037109375 }, { "start": 4570.96, "end": 4571.1, "word": " they", "probability": 0.7392578125 }, { "start": 4571.1, "end": 4571.44, "word": " do", "probability": 0.904296875 }, { "start": 4571.44, "end": 4571.84, "word": ".", "probability": 0.48193359375 }, { "start": 4572.08, "end": 4572.18, "word": " But", "probability": 0.76611328125 }, { "start": 4572.18, "end": 4572.32, "word": " what's", "probability": 0.92919921875 }, { "start": 4572.32, "end": 4572.48, "word": " also", "probability": 0.81689453125 }, { "start": 4572.48, "end": 4572.66, "word": " good", "probability": 0.8828125 }, { "start": 4572.66, "end": 4572.82, "word": " about", "probability": 0.8203125 }, { "start": 4572.82, "end": 4573.02, "word": " this", "probability": 0.8818359375 }, { "start": 4573.02, "end": 4573.36, "word": " exercise", "probability": 0.861328125 } ] }, { "id": 1730, "seek": 447684, "start": 4573.36, "end": 4576.4, "text": " is it doesn't really hold your hand. This is usually something", "tokens": [ 51114, 307, 309, 1177, 380, 534, 1797, 428, 1011, 13, 639, 307, 2673, 746, 51264 ], "temperature": 0.0, "avg_logprob": -0.19385162771232728, "compression_ratio": 1.6702127659574468, "no_speech_prob": 0.08880615234375, "words": [ { "start": 4573.36, "end": 4574.02, "word": " is", "probability": 0.8916015625 }, { "start": 4574.02, "end": 4574.22, "word": " it", "probability": 0.85888671875 }, { "start": 4574.22, "end": 4574.46, "word": " doesn't", "probability": 0.9326171875 }, { "start": 4574.46, "end": 4574.66, "word": " really", "probability": 0.775390625 }, { "start": 4574.66, "end": 4574.94, "word": " hold", "probability": 0.82275390625 }, { "start": 4574.94, "end": 4575.08, "word": " your", "probability": 0.80517578125 }, { "start": 4575.08, "end": 4575.44, "word": " hand", "probability": 0.8330078125 }, { "start": 4575.44, "end": 4575.56, "word": ".", "probability": 0.76806640625 }, { "start": 4575.56, "end": 4575.72, "word": " This", "probability": 0.80419921875 }, { "start": 4575.72, "end": 4575.84, "word": " is", "probability": 0.90673828125 }, { "start": 4575.84, "end": 4576.06, "word": " usually", "probability": 0.8349609375 }, { "start": 4576.06, "end": 4576.4, "word": " something", "probability": 0.73193359375 } ] }, { "id": 1731, "seek": 447684, "start": 4576.4, "end": 4579.5, "text": " that I give plenty of time in a classroom", "tokens": [ 51264, 300, 286, 976, 7140, 295, 565, 294, 257, 7419, 51414 ], "temperature": 0.0, "avg_logprob": -0.19385162771232728, "compression_ratio": 1.6702127659574468, "no_speech_prob": 0.08880615234375, "words": [ { "start": 4576.4, "end": 4576.74, "word": " that", "probability": 0.8759765625 }, { "start": 4576.74, "end": 4577.02, "word": " I", "probability": 0.97119140625 }, { "start": 4577.02, "end": 4577.36, "word": " give", "probability": 0.78662109375 }, { "start": 4577.36, "end": 4577.68, "word": " plenty", "probability": 0.90576171875 }, { "start": 4577.68, "end": 4577.9, "word": " of", "probability": 0.904296875 }, { "start": 4577.9, "end": 4578.34, "word": " time", "probability": 0.796875 }, { "start": 4578.34, "end": 4578.96, "word": " in", "probability": 0.8720703125 }, { "start": 4579.1, "end": 4579.5, "word": " a classroom", "probability": 0.95068359375 } ] }, { "id": 1732, "seek": 447684, "start": 4579.5, "end": 4581.48, "text": " setting. This allows people to ask questions", "tokens": [ 51414, 3287, 13, 639, 4045, 561, 281, 1029, 1651, 51564 ], "temperature": 0.0, "avg_logprob": -0.19385162771232728, "compression_ratio": 1.6702127659574468, "no_speech_prob": 0.08880615234375, "words": [ { "start": 4579.5, "end": 4579.86, "word": " setting", "probability": 0.83154296875 }, { "start": 4579.86, "end": 4579.98, "word": ".", "probability": 0.72509765625 }, { "start": 4579.98, "end": 4580.06, "word": " This", "probability": 0.8076171875 }, { "start": 4580.06, "end": 4580.3, "word": " allows", "probability": 0.7958984375 }, { "start": 4580.3, "end": 4580.58, "word": " people", "probability": 0.9267578125 }, { "start": 4580.58, "end": 4580.72, "word": " to", "probability": 0.9072265625 }, { "start": 4580.72, "end": 4580.96, "word": " ask", "probability": 0.81591796875 }, { "start": 4580.96, "end": 4581.48, "word": " questions", "probability": 0.9130859375 } ] }, { "id": 1733, "seek": 447684, "start": 4582.1, "end": 4584.86, "text": " as I go through. But this last task is going to say", "tokens": [ 51564, 382, 286, 352, 807, 13, 583, 341, 1036, 5633, 307, 516, 281, 584, 51714 ], "temperature": 0.0, "avg_logprob": -0.19385162771232728, "compression_ratio": 1.6702127659574468, "no_speech_prob": 0.08880615234375, "words": [ { "start": 4582.1, "end": 4582.5, "word": " as", "probability": 0.8662109375 }, { "start": 4582.5, "end": 4582.62, "word": " I", "probability": 0.60986328125 }, { "start": 4582.62, "end": 4582.74, "word": " go", "probability": 0.904296875 }, { "start": 4582.74, "end": 4583.06, "word": " through", "probability": 0.79052734375 }, { "start": 4583.06, "end": 4583.22, "word": ".", "probability": 0.368896484375 }, { "start": 4583.22, "end": 4583.38, "word": " But", "probability": 0.873046875 }, { "start": 4583.38, "end": 4583.6, "word": " this", "probability": 0.876953125 }, { "start": 4583.6, "end": 4583.84, "word": " last", "probability": 0.81298828125 }, { "start": 4583.84, "end": 4584.2, "word": " task", "probability": 0.81494140625 }, { "start": 4584.2, "end": 4584.38, "word": " is", "probability": 0.9033203125 }, { "start": 4584.38, "end": 4584.54, "word": " going", "probability": 0.8662109375 }, { "start": 4584.54, "end": 4584.7, "word": " to", "probability": 0.904296875 }, { "start": 4584.7, "end": 4584.86, "word": " say", "probability": 0.8935546875 } ] }, { "id": 1734, "seek": 450330, "start": 4584.86, "end": 4587.36, "text": " OK, we have a new email we've never seen before", "tokens": [ 50364, 2264, 11, 321, 362, 257, 777, 3796, 321, 600, 1128, 1612, 949, 50514 ], "temperature": 0.0, "avg_logprob": -0.20801767345630762, "compression_ratio": 1.7104072398190044, "no_speech_prob": 0.029296875, "words": [ { "start": 4584.86, "end": 4585.06, "word": " OK", "probability": 0.0292510986328125 }, { "start": 4585.06, "end": 4585.16, "word": ",", "probability": 0.8017578125 }, { "start": 4585.16, "end": 4585.28, "word": " we", "probability": 0.8974609375 }, { "start": 4585.28, "end": 4585.48, "word": " have", "probability": 0.8759765625 }, { "start": 4585.66, "end": 4585.84, "word": " a new", "probability": 0.82470703125 }, { "start": 4585.84, "end": 4586.26, "word": " email", "probability": 0.85107421875 }, { "start": 4586.26, "end": 4586.52, "word": " we've", "probability": 0.861328125 }, { "start": 4586.52, "end": 4586.68, "word": " never", "probability": 0.8623046875 }, { "start": 4586.68, "end": 4586.94, "word": " seen", "probability": 0.88427734375 }, { "start": 4586.94, "end": 4587.36, "word": " before", "probability": 0.806640625 } ] }, { "id": 1735, "seek": 450330, "start": 4589.54, "end": 4591.16, "text": " run it against our classifiers", "tokens": [ 50514, 1190, 309, 1970, 527, 1508, 23463, 50664 ], "temperature": 0.0, "avg_logprob": -0.20801767345630762, "compression_ratio": 1.7104072398190044, "no_speech_prob": 0.029296875, "words": [ { "start": 4589.54, "end": 4589.98, "word": " run", "probability": 0.043609619140625 }, { "start": 4589.98, "end": 4590.14, "word": " it", "probability": 0.880859375 }, { "start": 4590.14, "end": 4590.4, "word": " against", "probability": 0.853515625 }, { "start": 4590.4, "end": 4590.58, "word": " our", "probability": 0.7685546875 }, { "start": 4590.58, "end": 4591.16, "word": " classifiers", "probability": 0.871826171875 } ] }, { "id": 1736, "seek": 450330, "start": 4591.16, "end": 4593.96, "text": " that we trained. And so you have to go through", "tokens": [ 50664, 300, 321, 8895, 13, 400, 370, 291, 362, 281, 352, 807, 50814 ], "temperature": 0.0, "avg_logprob": -0.20801767345630762, "compression_ratio": 1.7104072398190044, "no_speech_prob": 0.029296875, "words": [ { "start": 4591.16, "end": 4591.32, "word": " that", "probability": 0.82666015625 }, { "start": 4591.32, "end": 4591.44, "word": " we", "probability": 0.900390625 }, { "start": 4591.44, "end": 4591.74, "word": " trained", "probability": 0.77001953125 }, { "start": 4591.74, "end": 4592.18, "word": ".", "probability": 0.82470703125 }, { "start": 4593.18, "end": 4593.26, "word": " And", "probability": 0.8515625 }, { "start": 4593.26, "end": 4593.38, "word": " so", "probability": 0.89697265625 }, { "start": 4593.38, "end": 4593.46, "word": " you", "probability": 0.82470703125 }, { "start": 4593.46, "end": 4593.58, "word": " have", "probability": 0.88232421875 }, { "start": 4593.58, "end": 4593.66, "word": " to", "probability": 0.9072265625 }, { "start": 4593.66, "end": 4593.8, "word": " go", "probability": 0.90380859375 }, { "start": 4593.8, "end": 4593.96, "word": " through", "probability": 0.8037109375 } ] }, { "id": 1737, "seek": 450330, "start": 4593.96, "end": 4597.08, "text": " the whole process of using the", "tokens": [ 50814, 264, 1379, 1399, 295, 1228, 264, 50964 ], "temperature": 0.0, "avg_logprob": -0.20801767345630762, "compression_ratio": 1.7104072398190044, "no_speech_prob": 0.029296875, "words": [ { "start": 4593.96, "end": 4594.1, "word": " the", "probability": 0.81591796875 }, { "start": 4594.1, "end": 4594.26, "word": " whole", "probability": 0.7939453125 }, { "start": 4594.26, "end": 4594.94, "word": " process", "probability": 0.8583984375 }, { "start": 4594.94, "end": 4595.56, "word": " of", "probability": 0.8779296875 }, { "start": 4595.56, "end": 4596.78, "word": " using", "probability": 0.7900390625 }, { "start": 4596.78, "end": 4597.08, "word": " the", "probability": 0.8037109375 } ] }, { "id": 1738, "seek": 450330, "start": 4597.08, "end": 4600.0, "text": " vectorizers to vectorize the tokens", "tokens": [ 50964, 8062, 22525, 281, 8062, 1125, 264, 22667, 51114 ], "temperature": 0.0, "avg_logprob": -0.20801767345630762, "compression_ratio": 1.7104072398190044, "no_speech_prob": 0.029296875, "words": [ { "start": 4597.08, "end": 4597.72, "word": " vectorizers", "probability": 0.85546875 }, { "start": 4597.72, "end": 4598.08, "word": " to", "probability": 0.87646484375 }, { "start": 4598.08, "end": 4598.74, "word": " vectorize", "probability": 0.869384765625 }, { "start": 4598.74, "end": 4599.12, "word": " the", "probability": 0.78857421875 }, { "start": 4599.12, "end": 4600.0, "word": " tokens", "probability": 0.69287109375 } ] }, { "id": 1739, "seek": 450330, "start": 4600.0, "end": 4602.94, "text": " or the words in the email and then putting them through the predict", "tokens": [ 51114, 420, 264, 2283, 294, 264, 3796, 293, 550, 3372, 552, 807, 264, 6069, 51264 ], "temperature": 0.0, "avg_logprob": -0.20801767345630762, "compression_ratio": 1.7104072398190044, "no_speech_prob": 0.029296875, "words": [ { "start": 4600.0, "end": 4600.16, "word": " or", "probability": 0.46875 }, { "start": 4600.16, "end": 4600.28, "word": " the", "probability": 0.8046875 }, { "start": 4600.28, "end": 4600.58, "word": " words", "probability": 0.7109375 }, { "start": 4600.58, "end": 4600.7, "word": " in", "probability": 0.8876953125 }, { "start": 4600.7, "end": 4600.84, "word": " the", "probability": 0.81103515625 }, { "start": 4600.84, "end": 4601.14, "word": " email", "probability": 0.9091796875 }, { "start": 4601.14, "end": 4601.86, "word": " and", "probability": 0.55712890625 }, { "start": 4601.86, "end": 4602.02, "word": " then", "probability": 0.73095703125 }, { "start": 4602.02, "end": 4602.28, "word": " putting", "probability": 0.9033203125 }, { "start": 4602.28, "end": 4602.46, "word": " them", "probability": 0.74267578125 }, { "start": 4602.46, "end": 4602.6, "word": " through", "probability": 0.7841796875 }, { "start": 4602.6, "end": 4602.74, "word": " the", "probability": 0.80517578125 }, { "start": 4602.74, "end": 4602.94, "word": " predict", "probability": 0.78564453125 } ] }, { "id": 1740, "seek": 450330, "start": 4602.94, "end": 4605.88, "text": " function and then printing out the prediction", "tokens": [ 51264, 2445, 293, 550, 14699, 484, 264, 17630, 51414 ], "temperature": 0.0, "avg_logprob": -0.20801767345630762, "compression_ratio": 1.7104072398190044, "no_speech_prob": 0.029296875, "words": [ { "start": 4602.94, "end": 4603.36, "word": " function", "probability": 0.884765625 }, { "start": 4603.36, "end": 4603.62, "word": " and", "probability": 0.810546875 }, { "start": 4603.62, "end": 4603.98, "word": " then", "probability": 0.7265625 }, { "start": 4603.98, "end": 4604.82, "word": " printing", "probability": 0.6240234375 }, { "start": 4604.82, "end": 4605.14, "word": " out", "probability": 0.8125 }, { "start": 4605.14, "end": 4605.56, "word": " the", "probability": 0.81103515625 }, { "start": 4605.56, "end": 4605.88, "word": " prediction", "probability": 0.8642578125 } ] }, { "id": 1741, "seek": 450330, "start": 4605.88, "end": 4608.96, "text": " that it gives. So before", "tokens": [ 51414, 300, 309, 2709, 13, 407, 949, 51564 ], "temperature": 0.0, "avg_logprob": -0.20801767345630762, "compression_ratio": 1.7104072398190044, "no_speech_prob": 0.029296875, "words": [ { "start": 4605.88, "end": 4606.1, "word": " that", "probability": 0.88330078125 }, { "start": 4606.1, "end": 4606.24, "word": " it", "probability": 0.8876953125 }, { "start": 4606.24, "end": 4606.56, "word": " gives", "probability": 0.8359375 }, { "start": 4606.56, "end": 4607.0, "word": ".", "probability": 0.9755859375 }, { "start": 4607.96, "end": 4608.34, "word": " So", "probability": 0.87353515625 }, { "start": 4608.34, "end": 4608.96, "word": " before", "probability": 0.630859375 } ] }, { "id": 1742, "seek": 450330, "start": 4608.96, "end": 4611.32, "text": " we hop into that, I really want this to finish", "tokens": [ 51564, 321, 3818, 666, 300, 11, 286, 534, 528, 341, 281, 2413, 51714 ], "temperature": 0.0, "avg_logprob": -0.20801767345630762, "compression_ratio": 1.7104072398190044, "no_speech_prob": 0.029296875, "words": [ { "start": 4608.96, "end": 4609.14, "word": " we", "probability": 0.91357421875 }, { "start": 4609.14, "end": 4609.32, "word": " hop", "probability": 0.88525390625 }, { "start": 4609.32, "end": 4609.5, "word": " into", "probability": 0.736328125 }, { "start": 4609.5, "end": 4609.76, "word": " that", "probability": 0.884765625 }, { "start": 4609.76, "end": 4609.82, "word": ",", "probability": 0.79931640625 }, { "start": 4609.82, "end": 4609.92, "word": " I", "probability": 0.99609375 }, { "start": 4609.92, "end": 4610.16, "word": " really", "probability": 0.77685546875 }, { "start": 4610.16, "end": 4610.4, "word": " want", "probability": 0.81201171875 }, { "start": 4610.4, "end": 4610.58, "word": " this", "probability": 0.87841796875 }, { "start": 4610.58, "end": 4610.78, "word": " to", "probability": 0.9033203125 }, { "start": 4610.78, "end": 4611.32, "word": " finish", "probability": 0.8916015625 } ] }, { "id": 1743, "seek": 452944, "start": 4611.32, "end": 4614.62, "text": " I want it to just be on its own time", "tokens": [ 50364, 286, 528, 309, 281, 445, 312, 322, 1080, 1065, 565, 50514 ], "temperature": 0.0, "avg_logprob": -0.2534246608002545, "compression_ratio": 1.6129032258064515, "no_speech_prob": 0.057464599609375, "words": [ { "start": 4611.32, "end": 4611.76, "word": " I", "probability": 0.07855224609375 }, { "start": 4611.76, "end": 4611.94, "word": " want", "probability": 0.60546875 }, { "start": 4611.94, "end": 4612.1, "word": " it", "probability": 0.84130859375 }, { "start": 4612.1, "end": 4612.3, "word": " to", "probability": 0.5966796875 }, { "start": 4612.3, "end": 4612.48, "word": " just", "probability": 0.80029296875 }, { "start": 4612.48, "end": 4613.54, "word": " be", "probability": 0.8671875 }, { "start": 4613.54, "end": 4613.74, "word": " on", "probability": 0.91455078125 }, { "start": 4613.74, "end": 4613.88, "word": " its", "probability": 0.74853515625 }, { "start": 4613.88, "end": 4614.18, "word": " own", "probability": 0.82421875 }, { "start": 4614.18, "end": 4614.62, "word": " time", "probability": 0.8017578125 } ] }, { "id": 1744, "seek": 452944, "start": 4615.78, "end": 4616.38, "text": " but", "tokens": [ 50514, 457, 50664 ], "temperature": 0.0, "avg_logprob": -0.2534246608002545, "compression_ratio": 1.6129032258064515, "no_speech_prob": 0.057464599609375, "words": [ { "start": 4615.78, "end": 4616.38, "word": " but", "probability": 0.097412109375 } ] }, { "id": 1745, "seek": 452944, "start": 4619.6, "end": 4621.24, "text": " we're going to", "tokens": [ 50664, 321, 434, 516, 281, 50814 ], "temperature": 0.0, "avg_logprob": -0.2534246608002545, "compression_ratio": 1.6129032258064515, "no_speech_prob": 0.057464599609375, "words": [ { "start": 4619.6, "end": 4620.2, "word": " we're", "probability": 0.54278564453125 }, { "start": 4620.2, "end": 4620.38, "word": " going", "probability": 0.8583984375 }, { "start": 4620.38, "end": 4621.24, "word": " to", "probability": 0.90576171875 } ] }, { "id": 1746, "seek": 452944, "start": 4621.24, "end": 4623.86, "text": " compare how well these models did", "tokens": [ 50814, 6794, 577, 731, 613, 5245, 630, 50964 ], "temperature": 0.0, "avg_logprob": -0.2534246608002545, "compression_ratio": 1.6129032258064515, "no_speech_prob": 0.057464599609375, "words": [ { "start": 4621.24, "end": 4621.76, "word": " compare", "probability": 0.74560546875 }, { "start": 4621.76, "end": 4622.18, "word": " how", "probability": 0.9091796875 }, { "start": 4622.18, "end": 4622.36, "word": " well", "probability": 0.87890625 }, { "start": 4622.36, "end": 4622.7, "word": " these", "probability": 0.6953125 }, { "start": 4622.7, "end": 4623.38, "word": " models", "probability": 0.7880859375 }, { "start": 4623.38, "end": 4623.86, "word": " did", "probability": 0.89208984375 } ] }, { "id": 1747, "seek": 452944, "start": 4625.04, "end": 4626.76, "text": " once this last one is complete", "tokens": [ 50964, 1564, 341, 1036, 472, 307, 3566, 51114 ], "temperature": 0.0, "avg_logprob": -0.2534246608002545, "compression_ratio": 1.6129032258064515, "no_speech_prob": 0.057464599609375, "words": [ { "start": 4625.04, "end": 4625.64, "word": " once", "probability": 0.77978515625 }, { "start": 4625.64, "end": 4625.8, "word": " this", "probability": 0.87353515625 }, { "start": 4625.8, "end": 4626.04, "word": " last", "probability": 0.8212890625 }, { "start": 4626.04, "end": 4626.2, "word": " one", "probability": 0.81884765625 }, { "start": 4626.2, "end": 4626.32, "word": " is", "probability": 0.90380859375 }, { "start": 4626.32, "end": 4626.76, "word": " complete", "probability": 0.66064453125 } ] }, { "id": 1748, "seek": 452944, "start": 4626.76, "end": 4629.52, "text": " and we're going to see if or how much", "tokens": [ 51114, 293, 321, 434, 516, 281, 536, 498, 420, 577, 709, 51264 ], "temperature": 0.0, "avg_logprob": -0.2534246608002545, "compression_ratio": 1.6129032258064515, "no_speech_prob": 0.057464599609375, "words": [ { "start": 4626.76, "end": 4627.44, "word": " and", "probability": 0.2056884765625 }, { "start": 4627.44, "end": 4627.58, "word": " we're", "probability": 0.6903076171875 }, { "start": 4627.58, "end": 4627.64, "word": " going", "probability": 0.611328125 }, { "start": 4627.64, "end": 4627.68, "word": " to", "probability": 0.90478515625 }, { "start": 4627.68, "end": 4627.94, "word": " see", "probability": 0.79638671875 }, { "start": 4627.94, "end": 4628.34, "word": " if", "probability": 0.529296875 }, { "start": 4628.34, "end": 4628.96, "word": " or", "probability": 0.73876953125 }, { "start": 4628.96, "end": 4629.22, "word": " how", "probability": 0.9033203125 }, { "start": 4629.22, "end": 4629.52, "word": " much", "probability": 0.8154296875 } ] }, { "id": 1749, "seek": 452944, "start": 4629.52, "end": 4632.66, "text": " that comparison has an influence on our test email", "tokens": [ 51264, 300, 9660, 575, 364, 6503, 322, 527, 1500, 3796, 51414 ], "temperature": 0.0, "avg_logprob": -0.2534246608002545, "compression_ratio": 1.6129032258064515, "no_speech_prob": 0.057464599609375, "words": [ { "start": 4629.52, "end": 4629.7, "word": " that", "probability": 0.87255859375 }, { "start": 4629.7, "end": 4630.22, "word": " comparison", "probability": 0.67431640625 }, { "start": 4630.22, "end": 4630.52, "word": " has", "probability": 0.89501953125 }, { "start": 4630.52, "end": 4630.66, "word": " an", "probability": 0.8759765625 }, { "start": 4630.66, "end": 4631.04, "word": " influence", "probability": 0.7998046875 }, { "start": 4631.04, "end": 4631.5, "word": " on", "probability": 0.908203125 }, { "start": 4631.5, "end": 4631.82, "word": " our", "probability": 0.81787109375 }, { "start": 4631.82, "end": 4632.26, "word": " test", "probability": 0.798828125 }, { "start": 4632.26, "end": 4632.66, "word": " email", "probability": 0.900390625 } ] }, { "id": 1750, "seek": 452944, "start": 4635.18, "end": 4637.46, "text": " So we're just going to give this another", "tokens": [ 51564, 407, 321, 434, 445, 516, 281, 976, 341, 1071, 51714 ], "temperature": 0.0, "avg_logprob": -0.2534246608002545, "compression_ratio": 1.6129032258064515, "no_speech_prob": 0.057464599609375, "words": [ { "start": 4635.18, "end": 4635.78, "word": " So", "probability": 0.0243988037109375 }, { "start": 4635.78, "end": 4635.86, "word": " we're", "probability": 0.7353515625 }, { "start": 4635.86, "end": 4635.96, "word": " just", "probability": 0.8505859375 }, { "start": 4635.96, "end": 4636.1, "word": " going", "probability": 0.66943359375 }, { "start": 4636.1, "end": 4636.18, "word": " to", "probability": 0.9052734375 }, { "start": 4636.18, "end": 4636.36, "word": " give", "probability": 0.826171875 }, { "start": 4636.36, "end": 4636.8, "word": " this", "probability": 0.8759765625 }, { "start": 4636.8, "end": 4637.46, "word": " another", "probability": 0.720703125 } ] }, { "id": 1751, "seek": 455806, "start": 4638.58, "end": 4641.18, "text": " Probably be another 30 seconds or so.", "tokens": [ 50414, 9210, 312, 1071, 2217, 3949, 420, 370, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.2815170797527346, "compression_ratio": 1.5934065934065933, "no_speech_prob": 0.460205078125, "words": [ { "start": 4638.58, "end": 4638.98, "word": " Probably", "probability": 0.03778076171875 }, { "start": 4638.98, "end": 4639.38, "word": " be", "probability": 0.491943359375 }, { "start": 4639.38, "end": 4639.56, "word": " another", "probability": 0.828125 }, { "start": 4639.56, "end": 4639.92, "word": " 30", "probability": 0.845703125 }, { "start": 4639.92, "end": 4640.26, "word": " seconds", "probability": 0.7177734375 }, { "start": 4640.26, "end": 4640.4, "word": " or", "probability": 0.88330078125 }, { "start": 4640.4, "end": 4640.82, "word": " so", "probability": 0.9072265625 }, { "start": 4640.82, "end": 4641.18, "word": ".", "probability": 0.66845703125 } ] }, { "id": 1752, "seek": 455806, "start": 4641.18, "end": 4642.86, "text": " So it's not too long.", "tokens": [ 50514, 407, 309, 311, 406, 886, 938, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.2815170797527346, "compression_ratio": 1.5934065934065933, "no_speech_prob": 0.460205078125, "words": [ { "start": 4641.18, "end": 4641.42, "word": " So", "probability": 0.5205078125 }, { "start": 4641.42, "end": 4641.52, "word": " it's", "probability": 0.895751953125 }, { "start": 4641.52, "end": 4641.7, "word": " not", "probability": 0.89892578125 }, { "start": 4641.7, "end": 4642.1, "word": " too", "probability": 0.80908203125 }, { "start": 4642.1, "end": 4642.54, "word": " long", "probability": 0.89111328125 }, { "start": 4642.54, "end": 4642.86, "word": ".", "probability": 0.85595703125 } ] }, { "id": 1753, "seek": 455806, "start": 4642.86, "end": 4644.0, "text": " How's the Discord chat?", "tokens": [ 50614, 1012, 311, 264, 32623, 5081, 30, 50664 ], "temperature": 0.0, "avg_logprob": -0.2815170797527346, "compression_ratio": 1.5934065934065933, "no_speech_prob": 0.460205078125, "words": [ { "start": 4642.86, "end": 4643.0, "word": " How's", "probability": 0.916015625 }, { "start": 4643.0, "end": 4643.08, "word": " the", "probability": 0.77978515625 }, { "start": 4643.08, "end": 4643.32, "word": " Discord", "probability": 0.52587890625 }, { "start": 4643.32, "end": 4643.6, "word": " chat", "probability": 0.71875 }, { "start": 4643.6, "end": 4644.0, "word": "?", "probability": 0.9482421875 } ] }, { "id": 1754, "seek": 455806, "start": 4647.82, "end": 4649.46, "text": " Discord chat's doing well.", "tokens": [ 50764, 32623, 5081, 311, 884, 731, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.2815170797527346, "compression_ratio": 1.5934065934065933, "no_speech_prob": 0.460205078125, "words": [ { "start": 4647.82, "end": 4648.22, "word": " Discord", "probability": 0.212646484375 }, { "start": 4648.22, "end": 4648.6, "word": " chat's", "probability": 0.690185546875 }, { "start": 4648.6, "end": 4648.76, "word": " doing", "probability": 0.9033203125 }, { "start": 4648.76, "end": 4649.06, "word": " well", "probability": 0.8740234375 }, { "start": 4649.06, "end": 4649.46, "word": ".", "probability": 0.94384765625 } ] }, { "id": 1755, "seek": 455806, "start": 4656.56, "end": 4660.94, "text": " I really appreciate how much discussion we have in this version of the workshop.", "tokens": [ 50964, 286, 534, 4449, 577, 709, 5017, 321, 362, 294, 341, 3037, 295, 264, 13541, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.2815170797527346, "compression_ratio": 1.5934065934065933, "no_speech_prob": 0.460205078125, "words": [ { "start": 4656.56, "end": 4656.96, "word": " I", "probability": 0.708984375 }, { "start": 4656.96, "end": 4657.36, "word": " really", "probability": 0.78173828125 }, { "start": 4657.36, "end": 4657.82, "word": " appreciate", "probability": 0.8583984375 }, { "start": 4657.82, "end": 4658.02, "word": " how", "probability": 0.89111328125 }, { "start": 4658.02, "end": 4658.18, "word": " much", "probability": 0.818359375 }, { "start": 4658.18, "end": 4658.64, "word": " discussion", "probability": 0.76025390625 }, { "start": 4658.64, "end": 4658.82, "word": " we", "probability": 0.8642578125 }, { "start": 4658.82, "end": 4658.94, "word": " have", "probability": 0.87646484375 }, { "start": 4658.94, "end": 4659.04, "word": " in", "probability": 0.884765625 }, { "start": 4659.04, "end": 4659.28, "word": " this", "probability": 0.88037109375 }, { "start": 4659.28, "end": 4660.0, "word": " version", "probability": 0.5830078125 }, { "start": 4660.0, "end": 4660.14, "word": " of", "probability": 0.89990234375 }, { "start": 4660.14, "end": 4660.24, "word": " the", "probability": 0.80322265625 }, { "start": 4660.24, "end": 4660.54, "word": " workshop", "probability": 0.6845703125 }, { "start": 4660.54, "end": 4660.94, "word": ".", "probability": 0.95751953125 } ] }, { "id": 1756, "seek": 455806, "start": 4661.18, "end": 4665.0, "text": " Also, and this is something that I want to note for people who are seeing this for the first time.", "tokens": [ 51164, 2743, 11, 293, 341, 307, 746, 300, 286, 528, 281, 3637, 337, 561, 567, 366, 2577, 341, 337, 264, 700, 565, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.2815170797527346, "compression_ratio": 1.5934065934065933, "no_speech_prob": 0.460205078125, "words": [ { "start": 4661.18, "end": 4661.52, "word": " Also", "probability": 0.87353515625 }, { "start": 4661.52, "end": 4661.64, "word": ",", "probability": 0.85205078125 }, { "start": 4661.64, "end": 4661.74, "word": " and", "probability": 0.87060546875 }, { "start": 4661.74, "end": 4661.88, "word": " this", "probability": 0.8876953125 }, { "start": 4661.88, "end": 4661.98, "word": " is", "probability": 0.90478515625 }, { "start": 4661.98, "end": 4662.14, "word": " something", "probability": 0.7392578125 }, { "start": 4662.14, "end": 4662.3, "word": " that", "probability": 0.8291015625 }, { "start": 4662.3, "end": 4662.38, "word": " I", "probability": 0.99853515625 }, { "start": 4662.38, "end": 4662.48, "word": " want", "probability": 0.67041015625 }, { "start": 4662.48, "end": 4662.58, "word": " to", "probability": 0.90625 }, { "start": 4662.58, "end": 4662.8, "word": " note", "probability": 0.67529296875 }, { "start": 4662.8, "end": 4663.18, "word": " for", "probability": 0.85693359375 }, { "start": 4663.18, "end": 4663.74, "word": " people", "probability": 0.9033203125 }, { "start": 4663.74, "end": 4663.88, "word": " who", "probability": 0.81005859375 }, { "start": 4663.88, "end": 4663.98, "word": " are", "probability": 0.88916015625 }, { "start": 4663.98, "end": 4664.16, "word": " seeing", "probability": 0.78857421875 }, { "start": 4664.16, "end": 4664.36, "word": " this", "probability": 0.87548828125 }, { "start": 4664.36, "end": 4664.46, "word": " for", "probability": 0.89306640625 }, { "start": 4664.46, "end": 4664.58, "word": " the", "probability": 0.81884765625 }, { "start": 4664.58, "end": 4664.74, "word": " first", "probability": 0.8115234375 }, { "start": 4664.74, "end": 4664.92, "word": " time", "probability": 0.81201171875 }, { "start": 4664.92, "end": 4665.0, "word": ".", "probability": 0.71923828125 } ] }, { "id": 1757, "seek": 455806, "start": 4665.0, "end": 4667.82, "text": " So the last time I did my workshop on Friday,", "tokens": [ 51364, 407, 264, 1036, 565, 286, 630, 452, 13541, 322, 6984, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.2815170797527346, "compression_ratio": 1.5934065934065933, "no_speech_prob": 0.460205078125, "words": [ { "start": 4665.0, "end": 4665.08, "word": " So", "probability": 0.830078125 }, { "start": 4665.08, "end": 4665.2, "word": " the", "probability": 0.705078125 }, { "start": 4665.2, "end": 4665.34, "word": " last", "probability": 0.8056640625 }, { "start": 4665.34, "end": 4665.46, "word": " time", "probability": 0.806640625 }, { "start": 4665.46, "end": 4665.54, "word": " I", "probability": 0.99755859375 }, { "start": 4665.54, "end": 4665.64, "word": " did", "probability": 0.9013671875 }, { "start": 4665.64, "end": 4665.8, "word": " my", "probability": 0.9033203125 }, { "start": 4665.8, "end": 4666.1, "word": " workshop", "probability": 0.677734375 }, { "start": 4666.1, "end": 4667.12, "word": " on", "probability": 0.83203125 }, { "start": 4667.12, "end": 4667.62, "word": " Friday", "probability": 0.8359375 }, { "start": 4667.62, "end": 4667.82, "word": ",", "probability": 0.912109375 } ] }, { "id": 1758, "seek": 455806, "start": 4667.82, "end": 4671.28, "text": " unfortunately my webcam froze in a very unflattering position,", "tokens": [ 51514, 7015, 452, 39490, 46077, 294, 257, 588, 517, 3423, 14849, 2535, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.2815170797527346, "compression_ratio": 1.5934065934065933, "no_speech_prob": 0.460205078125, "words": [ { "start": 4667.82, "end": 4668.3, "word": " unfortunately", "probability": 0.8193359375 }, { "start": 4668.3, "end": 4668.6, "word": " my", "probability": 0.50830078125 }, { "start": 4668.6, "end": 4668.96, "word": " webcam", "probability": 0.86767578125 }, { "start": 4668.96, "end": 4669.46, "word": " froze", "probability": 0.77294921875 }, { "start": 4669.46, "end": 4669.58, "word": " in", "probability": 0.892578125 }, { "start": 4669.68, "end": 4669.86, "word": " a very", "probability": 0.70751953125 }, { "start": 4669.86, "end": 4670.58, "word": " unflattering", "probability": 0.923828125 }, { "start": 4670.58, "end": 4671.08, "word": " position", "probability": 0.8134765625 }, { "start": 4671.08, "end": 4671.28, "word": ",", "probability": 0.24072265625 } ] }, { "id": 1759, "seek": 455806, "start": 4671.28, "end": 4673.14, "text": " so I just had my mouth gaping open.", "tokens": [ 51664, 370, 286, 445, 632, 452, 4525, 7417, 278, 1269, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.2815170797527346, "compression_ratio": 1.5934065934065933, "no_speech_prob": 0.460205078125, "words": [ { "start": 4671.28, "end": 4671.4, "word": " so", "probability": 0.8935546875 }, { "start": 4671.4, "end": 4671.52, "word": " I", "probability": 0.9951171875 }, { "start": 4671.52, "end": 4671.68, "word": " just", "probability": 0.8876953125 }, { "start": 4671.68, "end": 4671.86, "word": " had", "probability": 0.79931640625 }, { "start": 4671.86, "end": 4672.02, "word": " my", "probability": 0.90380859375 }, { "start": 4672.02, "end": 4672.26, "word": " mouth", "probability": 0.8515625 }, { "start": 4672.26, "end": 4672.62, "word": " gaping", "probability": 0.81884765625 }, { "start": 4672.62, "end": 4672.9, "word": " open", "probability": 0.81640625 }, { "start": 4672.9, "end": 4673.14, "word": ".", "probability": 0.277099609375 } ] }, { "id": 1760, "seek": 458602, "start": 4674.54, "end": 4679.6, "text": " So for this one I just put a static image of myself today.", "tokens": [ 50414, 407, 337, 341, 472, 286, 445, 829, 257, 13437, 3256, 295, 2059, 965, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.17601103321009992, "compression_ratio": 1.5514018691588785, "no_speech_prob": 0.00475311279296875, "words": [ { "start": 4674.54, "end": 4675.0, "word": " So", "probability": 0.0718994140625 }, { "start": 4675.0, "end": 4675.46, "word": " for", "probability": 0.5078125 }, { "start": 4675.46, "end": 4675.66, "word": " this", "probability": 0.88427734375 }, { "start": 4675.66, "end": 4675.86, "word": " one", "probability": 0.8095703125 }, { "start": 4675.86, "end": 4675.98, "word": " I", "probability": 0.63623046875 }, { "start": 4675.98, "end": 4676.18, "word": " just", "probability": 0.8408203125 }, { "start": 4676.18, "end": 4676.42, "word": " put", "probability": 0.88671875 }, { "start": 4676.68, "end": 4677.08, "word": " a static", "probability": 0.82958984375 }, { "start": 4677.08, "end": 4677.38, "word": " image", "probability": 0.828125 }, { "start": 4677.38, "end": 4677.52, "word": " of", "probability": 0.900390625 }, { "start": 4677.52, "end": 4678.6, "word": " myself", "probability": 0.313232421875 }, { "start": 4678.6, "end": 4679.14, "word": " today", "probability": 0.734375 }, { "start": 4679.14, "end": 4679.6, "word": ".", "probability": 0.4833984375 } ] }, { "id": 1761, "seek": 458602, "start": 4679.94, "end": 4681.74, "text": " That way you can still see my beautiful face,", "tokens": [ 50664, 663, 636, 291, 393, 920, 536, 452, 2238, 1851, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.17601103321009992, "compression_ratio": 1.5514018691588785, "no_speech_prob": 0.00475311279296875, "words": [ { "start": 4679.94, "end": 4680.1, "word": " That", "probability": 0.64697265625 }, { "start": 4680.1, "end": 4680.2, "word": " way", "probability": 0.8740234375 }, { "start": 4680.2, "end": 4680.28, "word": " you", "probability": 0.8623046875 }, { "start": 4680.28, "end": 4680.4, "word": " can", "probability": 0.88916015625 }, { "start": 4680.4, "end": 4680.6, "word": " still", "probability": 0.9052734375 }, { "start": 4680.6, "end": 4680.76, "word": " see", "probability": 0.80908203125 }, { "start": 4680.76, "end": 4680.9, "word": " my", "probability": 0.9111328125 }, { "start": 4680.9, "end": 4681.16, "word": " beautiful", "probability": 0.896484375 }, { "start": 4681.16, "end": 4681.62, "word": " face", "probability": 0.8232421875 }, { "start": 4681.62, "end": 4681.74, "word": ",", "probability": 0.397705078125 } ] }, { "id": 1762, "seek": 458602, "start": 4681.74, "end": 4684.94, "text": " but you don't get a very unflattering image of it.", "tokens": [ 50764, 457, 291, 500, 380, 483, 257, 588, 517, 3423, 14849, 3256, 295, 309, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.17601103321009992, "compression_ratio": 1.5514018691588785, "no_speech_prob": 0.00475311279296875, "words": [ { "start": 4681.74, "end": 4681.94, "word": " but", "probability": 0.8837890625 }, { "start": 4681.94, "end": 4682.54, "word": " you", "probability": 0.85986328125 }, { "start": 4682.54, "end": 4682.66, "word": " don't", "probability": 0.9375 }, { "start": 4682.66, "end": 4682.9, "word": " get", "probability": 0.88916015625 }, { "start": 4683.06, "end": 4683.24, "word": " a very", "probability": 0.71142578125 }, { "start": 4683.24, "end": 4683.8, "word": " unflattering", "probability": 0.91015625 }, { "start": 4683.8, "end": 4684.2, "word": " image", "probability": 0.822265625 }, { "start": 4684.2, "end": 4684.34, "word": " of", "probability": 0.87939453125 }, { "start": 4684.34, "end": 4684.48, "word": " it", "probability": 0.8974609375 }, { "start": 4684.48, "end": 4684.94, "word": ".", "probability": 0.9814453125 } ] }, { "id": 1763, "seek": 458602, "start": 4685.78, "end": 4688.32, "text": " Alright, so this one is complete.", "tokens": [ 50964, 2798, 11, 370, 341, 472, 307, 3566, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.17601103321009992, "compression_ratio": 1.5514018691588785, "no_speech_prob": 0.00475311279296875, "words": [ { "start": 4685.78, "end": 4686.24, "word": " Alright", "probability": 0.4248046875 }, { "start": 4686.24, "end": 4686.4, "word": ",", "probability": 0.68115234375 }, { "start": 4686.4, "end": 4686.52, "word": " so", "probability": 0.89013671875 }, { "start": 4686.52, "end": 4686.7, "word": " this", "probability": 0.8798828125 }, { "start": 4686.7, "end": 4686.88, "word": " one", "probability": 0.82275390625 }, { "start": 4686.88, "end": 4687.2, "word": " is", "probability": 0.90869140625 }, { "start": 4687.2, "end": 4687.86, "word": " complete", "probability": 0.673828125 }, { "start": 4687.86, "end": 4688.32, "word": ".", "probability": 0.865234375 } ] }, { "id": 1764, "seek": 458602, "start": 4688.32, "end": 4693.78, "text": " We are now at the best model that we have of the ones that we've trained.", "tokens": [ 51064, 492, 366, 586, 412, 264, 1151, 2316, 300, 321, 362, 295, 264, 2306, 300, 321, 600, 8895, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.17601103321009992, "compression_ratio": 1.5514018691588785, "no_speech_prob": 0.00475311279296875, "words": [ { "start": 4688.32, "end": 4688.5, "word": " We", "probability": 0.9033203125 }, { "start": 4688.5, "end": 4688.96, "word": " are", "probability": 0.88818359375 }, { "start": 4688.96, "end": 4689.36, "word": " now", "probability": 0.8994140625 }, { "start": 4689.36, "end": 4689.6, "word": " at", "probability": 0.9033203125 }, { "start": 4689.6, "end": 4689.74, "word": " the", "probability": 0.81494140625 }, { "start": 4689.74, "end": 4690.16, "word": " best", "probability": 0.81884765625 }, { "start": 4690.16, "end": 4690.46, "word": " model", "probability": 0.79443359375 }, { "start": 4690.46, "end": 4690.64, "word": " that", "probability": 0.78759765625 }, { "start": 4690.64, "end": 4690.82, "word": " we", "probability": 0.90576171875 }, { "start": 4690.82, "end": 4691.24, "word": " have", "probability": 0.88330078125 }, { "start": 4691.24, "end": 4692.28, "word": " of", "probability": 0.68408203125 }, { "start": 4692.28, "end": 4692.46, "word": " the", "probability": 0.8193359375 }, { "start": 4692.46, "end": 4692.76, "word": " ones", "probability": 0.80322265625 }, { "start": 4692.76, "end": 4692.92, "word": " that", "probability": 0.837890625 }, { "start": 4692.92, "end": 4693.14, "word": " we've", "probability": 0.845947265625 }, { "start": 4693.14, "end": 4693.54, "word": " trained", "probability": 0.822265625 }, { "start": 4693.54, "end": 4693.78, "word": ".", "probability": 0.85498046875 } ] }, { "id": 1765, "seek": 458602, "start": 4693.78, "end": 4698.2, "text": " We have a 97.69% accuracy.", "tokens": [ 51364, 492, 362, 257, 23399, 13, 30908, 4, 14170, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.17601103321009992, "compression_ratio": 1.5514018691588785, "no_speech_prob": 0.00475311279296875, "words": [ { "start": 4693.78, "end": 4693.88, "word": " We", "probability": 0.88623046875 }, { "start": 4693.88, "end": 4693.98, "word": " have", "probability": 0.87548828125 }, { "start": 4694.14, "end": 4694.78, "word": " a 97", "probability": 0.8349609375 }, { "start": 4694.78, "end": 4696.34, "word": ".69", "probability": 0.9853515625 }, { "start": 4696.34, "end": 4697.16, "word": "%", "probability": 0.8427734375 }, { "start": 4697.16, "end": 4697.82, "word": " accuracy", "probability": 0.7353515625 }, { "start": 4697.82, "end": 4698.2, "word": ".", "probability": 0.81689453125 } ] }, { "id": 1766, "seek": 458602, "start": 4698.2, "end": 4701.1, "text": " We can round that up to a 97.7% accuracy.", "tokens": [ 51564, 492, 393, 3098, 300, 493, 281, 257, 23399, 13, 22, 4, 14170, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.17601103321009992, "compression_ratio": 1.5514018691588785, "no_speech_prob": 0.00475311279296875, "words": [ { "start": 4698.2, "end": 4698.36, "word": " We", "probability": 0.69873046875 }, { "start": 4698.36, "end": 4698.42, "word": " can", "probability": 0.77099609375 }, { "start": 4698.42, "end": 4698.58, "word": " round", "probability": 0.88037109375 }, { "start": 4698.58, "end": 4698.74, "word": " that", "probability": 0.88037109375 }, { "start": 4698.74, "end": 4698.86, "word": " up", "probability": 0.896484375 }, { "start": 4698.86, "end": 4698.96, "word": " to", "probability": 0.90185546875 }, { "start": 4699.06, "end": 4699.4, "word": " a 97", "probability": 0.908203125 }, { "start": 4699.4, "end": 4699.98, "word": ".7", "probability": 0.9892578125 }, { "start": 4699.98, "end": 4700.24, "word": "%", "probability": 0.98828125 }, { "start": 4700.24, "end": 4700.64, "word": " accuracy", "probability": 0.71923828125 }, { "start": 4700.64, "end": 4701.1, "word": ".", "probability": 0.96484375 } ] }, { "id": 1767, "seek": 461478, "start": 4701.1, "end": 4708.18, "text": " We see that only 8 out of our 582 ham emails were misclassified as spam,", "tokens": [ 50364, 492, 536, 300, 787, 1649, 484, 295, 527, 21786, 17, 7852, 12524, 645, 3346, 11665, 2587, 382, 24028, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.21110734003393547, "compression_ratio": 1.7195767195767195, "no_speech_prob": 0.048126220703125, "words": [ { "start": 4701.1, "end": 4701.44, "word": " We", "probability": 0.496826171875 }, { "start": 4701.44, "end": 4701.62, "word": " see", "probability": 0.81787109375 }, { "start": 4701.62, "end": 4701.8, "word": " that", "probability": 0.8701171875 }, { "start": 4701.8, "end": 4702.1, "word": " only", "probability": 0.8330078125 }, { "start": 4702.1, "end": 4702.56, "word": " 8", "probability": 0.71875 }, { "start": 4702.56, "end": 4702.82, "word": " out", "probability": 0.775390625 }, { "start": 4702.82, "end": 4702.94, "word": " of", "probability": 0.904296875 }, { "start": 4702.94, "end": 4703.14, "word": " our", "probability": 0.7685546875 }, { "start": 4703.14, "end": 4704.68, "word": " 582", "probability": 0.902099609375 }, { "start": 4704.68, "end": 4705.46, "word": " ham", "probability": 0.337890625 }, { "start": 4705.46, "end": 4705.94, "word": " emails", "probability": 0.78076171875 }, { "start": 4705.94, "end": 4706.62, "word": " were", "probability": 0.77490234375 }, { "start": 4706.62, "end": 4707.32, "word": " misclassified", "probability": 0.93603515625 }, { "start": 4707.32, "end": 4707.52, "word": " as", "probability": 0.91064453125 }, { "start": 4707.52, "end": 4707.86, "word": " spam", "probability": 0.91259765625 }, { "start": 4707.86, "end": 4708.18, "word": ",", "probability": 0.311279296875 } ] }, { "id": 1768, "seek": 461478, "start": 4708.18, "end": 4714.72, "text": " and then only 12 out of our 264 spam emails were misclassified as ham,", "tokens": [ 50714, 293, 550, 787, 2272, 484, 295, 527, 7551, 19, 24028, 12524, 645, 3346, 11665, 2587, 382, 7852, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.21110734003393547, "compression_ratio": 1.7195767195767195, "no_speech_prob": 0.048126220703125, "words": [ { "start": 4708.18, "end": 4708.3, "word": " and", "probability": 0.80517578125 }, { "start": 4708.3, "end": 4708.4, "word": " then", "probability": 0.45703125 }, { "start": 4708.4, "end": 4708.64, "word": " only", "probability": 0.82958984375 }, { "start": 4708.64, "end": 4709.18, "word": " 12", "probability": 0.8955078125 }, { "start": 4709.18, "end": 4709.4, "word": " out", "probability": 0.78564453125 }, { "start": 4709.4, "end": 4709.46, "word": " of", "probability": 0.90380859375 }, { "start": 4709.46, "end": 4709.6, "word": " our", "probability": 0.80078125 }, { "start": 4709.6, "end": 4710.74, "word": " 264", "probability": 0.9111328125 }, { "start": 4710.74, "end": 4712.38, "word": " spam", "probability": 0.923828125 }, { "start": 4712.38, "end": 4712.82, "word": " emails", "probability": 0.74267578125 }, { "start": 4712.82, "end": 4713.02, "word": " were", "probability": 0.8564453125 }, { "start": 4713.02, "end": 4713.68, "word": " misclassified", "probability": 0.9459635416666666 }, { "start": 4713.68, "end": 4713.88, "word": " as", "probability": 0.9169921875 }, { "start": 4713.88, "end": 4714.16, "word": " ham", "probability": 0.83837890625 }, { "start": 4714.16, "end": 4714.72, "word": ",", "probability": 0.494384765625 } ] }, { "id": 1769, "seek": 461478, "start": 4714.72, "end": 4719.68, "text": " making this the best model that we have out of the 4 that we've trained.", "tokens": [ 51014, 1455, 341, 264, 1151, 2316, 300, 321, 362, 484, 295, 264, 1017, 300, 321, 600, 8895, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.21110734003393547, "compression_ratio": 1.7195767195767195, "no_speech_prob": 0.048126220703125, "words": [ { "start": 4714.72, "end": 4715.14, "word": " making", "probability": 0.76611328125 }, { "start": 4715.14, "end": 4715.44, "word": " this", "probability": 0.873046875 }, { "start": 4715.44, "end": 4715.72, "word": " the", "probability": 0.806640625 }, { "start": 4715.72, "end": 4716.18, "word": " best", "probability": 0.8046875 }, { "start": 4716.18, "end": 4716.64, "word": " model", "probability": 0.80322265625 }, { "start": 4716.64, "end": 4717.32, "word": " that", "probability": 0.83447265625 }, { "start": 4717.32, "end": 4717.44, "word": " we", "probability": 0.90380859375 }, { "start": 4717.44, "end": 4717.92, "word": " have", "probability": 0.8759765625 }, { "start": 4717.92, "end": 4718.12, "word": " out", "probability": 0.77880859375 }, { "start": 4718.12, "end": 4718.18, "word": " of", "probability": 0.90283203125 }, { "start": 4718.18, "end": 4718.3, "word": " the", "probability": 0.81298828125 }, { "start": 4718.3, "end": 4718.5, "word": " 4", "probability": 0.6123046875 }, { "start": 4718.5, "end": 4718.64, "word": " that", "probability": 0.859375 }, { "start": 4718.64, "end": 4718.84, "word": " we've", "probability": 0.90283203125 }, { "start": 4718.84, "end": 4719.1, "word": " trained", "probability": 0.8037109375 }, { "start": 4719.1, "end": 4719.68, "word": ".", "probability": 0.98046875 } ] }, { "id": 1770, "seek": 461478, "start": 4721.4, "end": 4723.98, "text": " So that's pretty solid.", "tokens": [ 51364, 407, 300, 311, 1238, 5100, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.21110734003393547, "compression_ratio": 1.7195767195767195, "no_speech_prob": 0.048126220703125, "words": [ { "start": 4721.4, "end": 4721.76, "word": " So", "probability": 0.783203125 }, { "start": 4721.76, "end": 4722.46, "word": " that's", "probability": 0.8076171875 }, { "start": 4722.46, "end": 4723.0, "word": " pretty", "probability": 0.88525390625 }, { "start": 4723.0, "end": 4723.4, "word": " solid", "probability": 0.83984375 }, { "start": 4723.4, "end": 4723.98, "word": ".", "probability": 0.93212890625 } ] }, { "id": 1771, "seek": 461478, "start": 4724.96, "end": 4729.86, "text": " So moving forward, what I would do is take this as kind of the better of the models,", "tokens": [ 51564, 407, 2684, 2128, 11, 437, 286, 576, 360, 307, 747, 341, 382, 733, 295, 264, 1101, 295, 264, 5245, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.21110734003393547, "compression_ratio": 1.7195767195767195, "no_speech_prob": 0.048126220703125, "words": [ { "start": 4724.96, "end": 4725.46, "word": " So", "probability": 0.72314453125 }, { "start": 4725.46, "end": 4725.68, "word": " moving", "probability": 0.80078125 }, { "start": 4725.68, "end": 4725.96, "word": " forward", "probability": 0.84228515625 }, { "start": 4725.96, "end": 4726.02, "word": ",", "probability": 0.58056640625 }, { "start": 4726.02, "end": 4726.1, "word": " what", "probability": 0.8759765625 }, { "start": 4726.1, "end": 4726.18, "word": " I", "probability": 0.9951171875 }, { "start": 4726.18, "end": 4726.28, "word": " would", "probability": 0.84375 }, { "start": 4726.28, "end": 4726.52, "word": " do", "probability": 0.89697265625 }, { "start": 4726.52, "end": 4726.96, "word": " is", "probability": 0.8828125 }, { "start": 4726.96, "end": 4727.3, "word": " take", "probability": 0.79736328125 }, { "start": 4727.3, "end": 4727.78, "word": " this", "probability": 0.87890625 }, { "start": 4727.78, "end": 4728.16, "word": " as", "probability": 0.86962890625 }, { "start": 4728.16, "end": 4728.38, "word": " kind", "probability": 0.5048828125 }, { "start": 4728.38, "end": 4728.52, "word": " of", "probability": 0.90283203125 }, { "start": 4728.52, "end": 4728.86, "word": " the", "probability": 0.80419921875 }, { "start": 4728.86, "end": 4729.18, "word": " better", "probability": 0.79150390625 }, { "start": 4729.18, "end": 4729.34, "word": " of", "probability": 0.8740234375 }, { "start": 4729.34, "end": 4729.42, "word": " the", "probability": 0.8173828125 }, { "start": 4729.42, "end": 4729.76, "word": " models", "probability": 0.79736328125 }, { "start": 4729.76, "end": 4729.86, "word": ",", "probability": 0.521484375 } ] }, { "id": 1772, "seek": 463822, "start": 4729.86, "end": 4733.14, "text": " and I would go ahead and deploy this in production,", "tokens": [ 50364, 293, 286, 576, 352, 2286, 293, 7274, 341, 294, 4265, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.19550539829112865, "compression_ratio": 1.7027027027027026, "no_speech_prob": 0.0010814666748046875, "words": [ { "start": 4729.86, "end": 4729.94, "word": " and", "probability": 0.273193359375 }, { "start": 4729.94, "end": 4730.02, "word": " I", "probability": 0.931640625 }, { "start": 4730.02, "end": 4730.18, "word": " would", "probability": 0.8505859375 }, { "start": 4730.18, "end": 4731.1, "word": " go", "probability": 0.8876953125 }, { "start": 4731.1, "end": 4731.5, "word": " ahead", "probability": 0.84619140625 }, { "start": 4731.5, "end": 4731.92, "word": " and", "probability": 0.89208984375 }, { "start": 4731.92, "end": 4732.38, "word": " deploy", "probability": 0.72412109375 }, { "start": 4732.38, "end": 4732.6, "word": " this", "probability": 0.876953125 }, { "start": 4732.6, "end": 4732.74, "word": " in", "probability": 0.908203125 }, { "start": 4732.74, "end": 4733.02, "word": " production", "probability": 0.849609375 }, { "start": 4733.02, "end": 4733.14, "word": ",", "probability": 0.1790771484375 } ] }, { "id": 1773, "seek": 463822, "start": 4733.14, "end": 4740.44, "text": " or add this model into an application that's designed to kind of wrap around the idea of spam and ham.", "tokens": [ 50514, 420, 909, 341, 2316, 666, 364, 3861, 300, 311, 4761, 281, 733, 295, 7019, 926, 264, 1558, 295, 24028, 293, 7852, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.19550539829112865, "compression_ratio": 1.7027027027027026, "no_speech_prob": 0.0010814666748046875, "words": [ { "start": 4733.14, "end": 4733.22, "word": " or", "probability": 0.89013671875 }, { "start": 4733.22, "end": 4733.46, "word": " add", "probability": 0.80517578125 }, { "start": 4733.46, "end": 4733.68, "word": " this", "probability": 0.87744140625 }, { "start": 4733.68, "end": 4734.08, "word": " model", "probability": 0.8115234375 }, { "start": 4734.08, "end": 4734.7, "word": " into", "probability": 0.72705078125 }, { "start": 4734.7, "end": 4735.68, "word": " an", "probability": 0.8994140625 }, { "start": 4735.68, "end": 4736.18, "word": " application", "probability": 0.77734375 }, { "start": 4736.18, "end": 4736.56, "word": " that's", "probability": 0.9228515625 }, { "start": 4736.56, "end": 4736.96, "word": " designed", "probability": 0.79296875 }, { "start": 4736.96, "end": 4737.42, "word": " to", "probability": 0.90478515625 }, { "start": 4737.42, "end": 4737.88, "word": " kind", "probability": 0.53076171875 }, { "start": 4737.88, "end": 4737.98, "word": " of", "probability": 0.9130859375 }, { "start": 4737.98, "end": 4738.22, "word": " wrap", "probability": 0.77587890625 }, { "start": 4738.22, "end": 4738.5, "word": " around", "probability": 0.87255859375 }, { "start": 4738.5, "end": 4738.66, "word": " the", "probability": 0.8173828125 }, { "start": 4738.66, "end": 4738.98, "word": " idea", "probability": 0.77294921875 }, { "start": 4738.98, "end": 4739.16, "word": " of", "probability": 0.89990234375 }, { "start": 4739.16, "end": 4739.46, "word": " spam", "probability": 0.6494140625 }, { "start": 4739.46, "end": 4739.64, "word": " and", "probability": 0.87841796875 }, { "start": 4739.64, "end": 4739.9, "word": " ham", "probability": 0.71044921875 }, { "start": 4739.9, "end": 4740.44, "word": ".", "probability": 0.97119140625 } ] }, { "id": 1774, "seek": 463822, "start": 4740.96, "end": 4745.52, "text": " So if you are simply an email provider, you can use this to filter email,", "tokens": [ 50864, 407, 498, 291, 366, 2935, 364, 3796, 12398, 11, 291, 393, 764, 341, 281, 6608, 3796, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.19550539829112865, "compression_ratio": 1.7027027027027026, "no_speech_prob": 0.0010814666748046875, "words": [ { "start": 4740.96, "end": 4741.26, "word": " So", "probability": 0.8681640625 }, { "start": 4741.26, "end": 4741.52, "word": " if", "probability": 0.7314453125 }, { "start": 4741.52, "end": 4741.8, "word": " you", "probability": 0.896484375 }, { "start": 4741.8, "end": 4742.24, "word": " are", "probability": 0.89697265625 }, { "start": 4742.24, "end": 4742.92, "word": " simply", "probability": 0.84228515625 }, { "start": 4742.92, "end": 4743.08, "word": " an", "probability": 0.900390625 }, { "start": 4743.08, "end": 4743.28, "word": " email", "probability": 0.85986328125 }, { "start": 4743.28, "end": 4743.66, "word": " provider", "probability": 0.83935546875 }, { "start": 4743.66, "end": 4743.7, "word": ",", "probability": 0.8642578125 }, { "start": 4743.7, "end": 4743.86, "word": " you", "probability": 0.896484375 }, { "start": 4743.86, "end": 4743.98, "word": " can", "probability": 0.88818359375 }, { "start": 4743.98, "end": 4744.16, "word": " use", "probability": 0.8212890625 }, { "start": 4744.16, "end": 4744.3, "word": " this", "probability": 0.87890625 }, { "start": 4744.3, "end": 4744.44, "word": " to", "probability": 0.90234375 }, { "start": 4744.44, "end": 4744.66, "word": " filter", "probability": 0.8916015625 }, { "start": 4744.66, "end": 4745.16, "word": " email", "probability": 0.90283203125 }, { "start": 4745.16, "end": 4745.52, "word": ",", "probability": 0.59716796875 } ] }, { "id": 1775, "seek": 463822, "start": 4745.52, "end": 4753.3, "text": " or if you are a spam company, or not a spam company, but like a spam research company,", "tokens": [ 51114, 420, 498, 291, 366, 257, 24028, 2237, 11, 420, 406, 257, 24028, 2237, 11, 457, 411, 257, 24028, 2132, 2237, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.19550539829112865, "compression_ratio": 1.7027027027027026, "no_speech_prob": 0.0010814666748046875, "words": [ { "start": 4745.52, "end": 4746.02, "word": " or", "probability": 0.90283203125 }, { "start": 4746.02, "end": 4746.28, "word": " if", "probability": 0.90625 }, { "start": 4746.28, "end": 4746.54, "word": " you", "probability": 0.8935546875 }, { "start": 4746.54, "end": 4747.06, "word": " are", "probability": 0.89404296875 }, { "start": 4749.24, "end": 4749.52, "word": " a spam", "probability": 0.89501953125 }, { "start": 4749.52, "end": 4749.9, "word": " company", "probability": 0.80224609375 }, { "start": 4749.9, "end": 4749.98, "word": ",", "probability": 0.802734375 }, { "start": 4749.98, "end": 4750.04, "word": " or", "probability": 0.673828125 }, { "start": 4750.04, "end": 4750.14, "word": " not", "probability": 0.876953125 }, { "start": 4750.26, "end": 4750.46, "word": " a spam", "probability": 0.892578125 }, { "start": 4750.46, "end": 4750.78, "word": " company", "probability": 0.810546875 }, { "start": 4750.78, "end": 4750.92, "word": ",", "probability": 0.88916015625 }, { "start": 4750.92, "end": 4751.0, "word": " but", "probability": 0.87255859375 }, { "start": 4751.0, "end": 4751.44, "word": " like", "probability": 0.71142578125 }, { "start": 4751.58, "end": 4751.92, "word": " a spam", "probability": 0.91064453125 }, { "start": 4751.92, "end": 4752.4, "word": " research", "probability": 0.77880859375 }, { "start": 4752.4, "end": 4752.9, "word": " company", "probability": 0.8037109375 }, { "start": 4752.9, "end": 4753.3, "word": ",", "probability": 0.974609375 } ] }, { "id": 1776, "seek": 466728, "start": 4753.3, "end": 4760.92, "text": " you would use this to grab the spam messages and then collect that as data,", "tokens": [ 50364, 291, 576, 764, 341, 281, 4444, 264, 24028, 7897, 293, 550, 2500, 300, 382, 1412, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.17020715622419721, "compression_ratio": 1.703883495145631, "no_speech_prob": 0.00035691261291503906, "words": [ { "start": 4753.3, "end": 4753.56, "word": " you", "probability": 0.50390625 }, { "start": 4753.56, "end": 4753.7, "word": " would", "probability": 0.81640625 }, { "start": 4753.7, "end": 4753.98, "word": " use", "probability": 0.8154296875 }, { "start": 4753.98, "end": 4754.28, "word": " this", "probability": 0.8759765625 }, { "start": 4754.28, "end": 4754.72, "word": " to", "probability": 0.90283203125 }, { "start": 4754.72, "end": 4755.66, "word": " grab", "probability": 0.78955078125 }, { "start": 4755.66, "end": 4755.84, "word": " the", "probability": 0.80615234375 }, { "start": 4755.84, "end": 4756.06, "word": " spam", "probability": 0.923828125 }, { "start": 4756.06, "end": 4756.5, "word": " messages", "probability": 0.84228515625 }, { "start": 4756.5, "end": 4757.12, "word": " and", "probability": 0.755859375 }, { "start": 4757.12, "end": 4757.56, "word": " then", "probability": 0.69677734375 }, { "start": 4757.56, "end": 4759.98, "word": " collect", "probability": 0.73583984375 }, { "start": 4759.98, "end": 4760.26, "word": " that", "probability": 0.88330078125 }, { "start": 4760.26, "end": 4760.5, "word": " as", "probability": 0.91845703125 }, { "start": 4760.5, "end": 4760.78, "word": " data", "probability": 0.8212890625 }, { "start": 4760.78, "end": 4760.92, "word": ",", "probability": 0.237060546875 } ] }, { "id": 1777, "seek": 466728, "start": 4760.92, "end": 4765.54, "text": " and then you can use that to be training the next version of your spam filter.", "tokens": [ 50714, 293, 550, 291, 393, 764, 300, 281, 312, 3097, 264, 958, 3037, 295, 428, 24028, 6608, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.17020715622419721, "compression_ratio": 1.703883495145631, "no_speech_prob": 0.00035691261291503906, "words": [ { "start": 4760.92, "end": 4760.96, "word": " and", "probability": 0.787109375 }, { "start": 4760.96, "end": 4761.06, "word": " then", "probability": 0.7158203125 }, { "start": 4761.06, "end": 4761.16, "word": " you", "probability": 0.87451171875 }, { "start": 4761.16, "end": 4761.3, "word": " can", "probability": 0.8916015625 }, { "start": 4761.3, "end": 4761.54, "word": " use", "probability": 0.8125 }, { "start": 4761.54, "end": 4761.94, "word": " that", "probability": 0.8818359375 }, { "start": 4761.94, "end": 4762.9, "word": " to", "probability": 0.8955078125 }, { "start": 4762.9, "end": 4763.06, "word": " be", "probability": 0.88134765625 }, { "start": 4763.06, "end": 4763.36, "word": " training", "probability": 0.8330078125 }, { "start": 4763.36, "end": 4763.78, "word": " the", "probability": 0.80908203125 }, { "start": 4763.78, "end": 4764.14, "word": " next", "probability": 0.865234375 }, { "start": 4764.14, "end": 4764.44, "word": " version", "probability": 0.7197265625 }, { "start": 4764.44, "end": 4764.6, "word": " of", "probability": 0.90966796875 }, { "start": 4764.6, "end": 4764.72, "word": " your", "probability": 0.7958984375 }, { "start": 4764.72, "end": 4764.92, "word": " spam", "probability": 0.9072265625 }, { "start": 4764.92, "end": 4765.24, "word": " filter", "probability": 0.92236328125 }, { "start": 4765.24, "end": 4765.54, "word": ".", "probability": 0.97900390625 } ] }, { "id": 1778, "seek": 466728, "start": 4767.68, "end": 4771.58, "text": " So let's take a look at our test spam email.", "tokens": [ 51064, 407, 718, 311, 747, 257, 574, 412, 527, 1500, 24028, 3796, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.17020715622419721, "compression_ratio": 1.703883495145631, "no_speech_prob": 0.00035691261291503906, "words": [ { "start": 4767.68, "end": 4768.28, "word": " So", "probability": 0.456298828125 }, { "start": 4768.28, "end": 4768.88, "word": " let's", "probability": 0.816650390625 }, { "start": 4768.88, "end": 4769.02, "word": " take", "probability": 0.818359375 }, { "start": 4769.1, "end": 4769.22, "word": " a look", "probability": 0.9150390625 }, { "start": 4769.22, "end": 4769.56, "word": " at", "probability": 0.90380859375 }, { "start": 4769.56, "end": 4769.84, "word": " our", "probability": 0.8173828125 }, { "start": 4769.84, "end": 4770.36, "word": " test", "probability": 0.73583984375 }, { "start": 4770.36, "end": 4770.9, "word": " spam", "probability": 0.884765625 }, { "start": 4770.9, "end": 4771.28, "word": " email", "probability": 0.90478515625 }, { "start": 4771.28, "end": 4771.58, "word": ".", "probability": 0.92626953125 } ] }, { "id": 1779, "seek": 466728, "start": 4772.18, "end": 4776.9, "text": " We have our final task, which is to use the vectorizer and the models that we created", "tokens": [ 51314, 492, 362, 527, 2572, 5633, 11, 597, 307, 281, 764, 264, 8062, 6545, 293, 264, 5245, 300, 321, 2942, 51564 ], "temperature": 0.0, "avg_logprob": -0.17020715622419721, "compression_ratio": 1.703883495145631, "no_speech_prob": 0.00035691261291503906, "words": [ { "start": 4772.18, "end": 4772.78, "word": " We", "probability": 0.8994140625 }, { "start": 4772.78, "end": 4772.88, "word": " have", "probability": 0.88037109375 }, { "start": 4772.88, "end": 4773.0, "word": " our", "probability": 0.82080078125 }, { "start": 4773.0, "end": 4773.2, "word": " final", "probability": 0.880859375 }, { "start": 4773.2, "end": 4773.68, "word": " task", "probability": 0.80859375 }, { "start": 4773.68, "end": 4773.98, "word": ",", "probability": 0.71923828125 }, { "start": 4773.98, "end": 4774.22, "word": " which", "probability": 0.92138671875 }, { "start": 4774.22, "end": 4774.5, "word": " is", "probability": 0.9072265625 }, { "start": 4774.5, "end": 4774.74, "word": " to", "probability": 0.9052734375 }, { "start": 4774.74, "end": 4775.02, "word": " use", "probability": 0.81591796875 }, { "start": 4775.02, "end": 4775.16, "word": " the", "probability": 0.80810546875 }, { "start": 4775.16, "end": 4775.62, "word": " vectorizer", "probability": 0.888427734375 }, { "start": 4775.62, "end": 4775.82, "word": " and", "probability": 0.88720703125 }, { "start": 4775.82, "end": 4775.94, "word": " the", "probability": 0.81494140625 }, { "start": 4775.94, "end": 4776.24, "word": " models", "probability": 0.79736328125 }, { "start": 4776.24, "end": 4776.36, "word": " that", "probability": 0.8759765625 }, { "start": 4776.36, "end": 4776.46, "word": " we", "probability": 0.9072265625 }, { "start": 4776.46, "end": 4776.9, "word": " created", "probability": 0.72802734375 } ] }, { "id": 1780, "seek": 466728, "start": 4776.9, "end": 4782.36, "text": " to perform predictions on our test email and our test spam email.", "tokens": [ 51564, 281, 2042, 21264, 322, 527, 1500, 3796, 293, 527, 1500, 24028, 3796, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.17020715622419721, "compression_ratio": 1.703883495145631, "no_speech_prob": 0.00035691261291503906, "words": [ { "start": 4776.9, "end": 4777.6, "word": " to", "probability": 0.8818359375 }, { "start": 4777.6, "end": 4777.98, "word": " perform", "probability": 0.77734375 }, { "start": 4777.98, "end": 4778.58, "word": " predictions", "probability": 0.70458984375 }, { "start": 4778.58, "end": 4779.14, "word": " on", "probability": 0.9091796875 }, { "start": 4779.14, "end": 4779.4, "word": " our", "probability": 0.810546875 }, { "start": 4779.4, "end": 4779.72, "word": " test", "probability": 0.830078125 }, { "start": 4779.72, "end": 4780.1, "word": " email", "probability": 0.90966796875 }, { "start": 4780.1, "end": 4780.38, "word": " and", "probability": 0.8671875 }, { "start": 4780.38, "end": 4780.54, "word": " our", "probability": 0.81396484375 }, { "start": 4780.54, "end": 4780.88, "word": " test", "probability": 0.7958984375 }, { "start": 4780.88, "end": 4781.38, "word": " spam", "probability": 0.91064453125 }, { "start": 4781.38, "end": 4781.76, "word": " email", "probability": 0.91845703125 }, { "start": 4781.76, "end": 4782.36, "word": ".", "probability": 0.9794921875 } ] }, { "id": 1781, "seek": 468554, "start": 4782.36, "end": 4789.5, "text": " So to make things easier, what I'm going to do is use a variable, I'll call this working email,", "tokens": [ 50364, 407, 281, 652, 721, 3571, 11, 437, 286, 478, 516, 281, 360, 307, 764, 257, 7006, 11, 286, 603, 818, 341, 1364, 3796, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.22963626951467794, "compression_ratio": 1.4797297297297298, "no_speech_prob": 0.0012063980102539062, "words": [ { "start": 4782.36, "end": 4783.02, "word": " So", "probability": 0.73291015625 }, { "start": 4783.02, "end": 4783.42, "word": " to", "probability": 0.609375 }, { "start": 4783.42, "end": 4783.6, "word": " make", "probability": 0.87890625 }, { "start": 4783.6, "end": 4783.86, "word": " things", "probability": 0.748046875 }, { "start": 4783.86, "end": 4784.46, "word": " easier", "probability": 0.91748046875 }, { "start": 4784.46, "end": 4784.74, "word": ",", "probability": 0.701171875 }, { "start": 4784.74, "end": 4784.92, "word": " what", "probability": 0.83447265625 }, { "start": 4784.92, "end": 4785.18, "word": " I'm", "probability": 0.982666015625 }, { "start": 4785.18, "end": 4785.24, "word": " going", "probability": 0.58154296875 }, { "start": 4785.24, "end": 4785.26, "word": " to", "probability": 0.9052734375 }, { "start": 4785.26, "end": 4785.52, "word": " do", "probability": 0.90380859375 }, { "start": 4785.52, "end": 4785.88, "word": " is", "probability": 0.89404296875 }, { "start": 4785.88, "end": 4786.46, "word": " use", "probability": 0.82080078125 }, { "start": 4787.68, "end": 4787.92, "word": " a variable", "probability": 0.775390625 }, { "start": 4787.92, "end": 4788.12, "word": ",", "probability": 0.227294921875 }, { "start": 4788.12, "end": 4788.16, "word": " I'll", "probability": 0.9521484375 }, { "start": 4788.16, "end": 4788.28, "word": " call", "probability": 0.81005859375 }, { "start": 4788.28, "end": 4788.46, "word": " this", "probability": 0.88232421875 }, { "start": 4788.46, "end": 4788.9, "word": " working", "probability": 0.444580078125 }, { "start": 4788.9, "end": 4789.22, "word": " email", "probability": 0.72998046875 }, { "start": 4789.22, "end": 4789.5, "word": ",", "probability": 0.237548828125 } ] }, { "id": 1782, "seek": 468554, "start": 4790.34, "end": 4793.42, "text": " and this will allow us to switch pretty quickly.", "tokens": [ 50764, 293, 341, 486, 2089, 505, 281, 3679, 1238, 2661, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.22963626951467794, "compression_ratio": 1.4797297297297298, "no_speech_prob": 0.0012063980102539062, "words": [ { "start": 4790.34, "end": 4790.8, "word": " and", "probability": 0.85205078125 }, { "start": 4790.8, "end": 4790.92, "word": " this", "probability": 0.87841796875 }, { "start": 4790.92, "end": 4791.12, "word": " will", "probability": 0.82080078125 }, { "start": 4791.12, "end": 4791.5, "word": " allow", "probability": 0.86669921875 }, { "start": 4791.5, "end": 4791.72, "word": " us", "probability": 0.90771484375 }, { "start": 4791.72, "end": 4791.9, "word": " to", "probability": 0.90625 }, { "start": 4791.9, "end": 4792.3, "word": " switch", "probability": 0.94091796875 }, { "start": 4792.3, "end": 4792.58, "word": " pretty", "probability": 0.86376953125 }, { "start": 4792.58, "end": 4792.86, "word": " quickly", "probability": 0.876953125 }, { "start": 4792.86, "end": 4793.42, "word": ".", "probability": 0.93017578125 } ] }, { "id": 1783, "seek": 468554, "start": 4794.18, "end": 4800.62, "text": " So I have test email, and then we're going to want to vectorize our email,", "tokens": [ 50964, 407, 286, 362, 1500, 3796, 11, 293, 550, 321, 434, 516, 281, 528, 281, 8062, 1125, 527, 3796, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.22963626951467794, "compression_ratio": 1.4797297297297298, "no_speech_prob": 0.0012063980102539062, "words": [ { "start": 4794.18, "end": 4794.46, "word": " So", "probability": 0.8837890625 }, { "start": 4794.46, "end": 4794.62, "word": " I", "probability": 0.97314453125 }, { "start": 4794.62, "end": 4794.98, "word": " have", "probability": 0.8662109375 }, { "start": 4794.98, "end": 4795.78, "word": " test", "probability": 0.75927734375 }, { "start": 4795.78, "end": 4796.14, "word": " email", "probability": 0.83056640625 }, { "start": 4796.14, "end": 4796.68, "word": ",", "probability": 0.5732421875 }, { "start": 4796.68, "end": 4797.02, "word": " and", "probability": 0.8095703125 }, { "start": 4797.02, "end": 4797.16, "word": " then", "probability": 0.634765625 }, { "start": 4797.16, "end": 4797.4, "word": " we're", "probability": 0.919677734375 }, { "start": 4797.4, "end": 4797.6, "word": " going", "probability": 0.8525390625 }, { "start": 4797.6, "end": 4797.94, "word": " to", "probability": 0.8984375 }, { "start": 4797.94, "end": 4798.16, "word": " want", "probability": 0.822265625 }, { "start": 4798.16, "end": 4798.42, "word": " to", "probability": 0.89990234375 }, { "start": 4798.42, "end": 4799.36, "word": " vectorize", "probability": 0.89013671875 }, { "start": 4799.36, "end": 4799.96, "word": " our", "probability": 0.80810546875 }, { "start": 4799.96, "end": 4800.32, "word": " email", "probability": 0.89697265625 }, { "start": 4800.32, "end": 4800.62, "word": ",", "probability": 0.494873046875 } ] }, { "id": 1784, "seek": 471554, "start": 4800.62, "end": 4804.96, "text": " so we're going to use our test email tfidf,", "tokens": [ 50364, 370, 321, 434, 516, 281, 764, 527, 1500, 3796, 256, 69, 327, 69, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.28897057561313405, "compression_ratio": 1.6794871794871795, "no_speech_prob": 0.2042236328125, "words": [ { "start": 4800.62, "end": 4800.8, "word": " so", "probability": 0.19482421875 }, { "start": 4800.8, "end": 4801.02, "word": " we're", "probability": 0.868408203125 }, { "start": 4801.02, "end": 4801.14, "word": " going", "probability": 0.30517578125 }, { "start": 4801.14, "end": 4801.18, "word": " to", "probability": 0.90673828125 }, { "start": 4801.18, "end": 4801.48, "word": " use", "probability": 0.83251953125 }, { "start": 4801.48, "end": 4801.82, "word": " our", "probability": 0.822265625 }, { "start": 4801.82, "end": 4802.26, "word": " test", "probability": 0.7783203125 }, { "start": 4802.26, "end": 4802.7, "word": " email", "probability": 0.76904296875 }, { "start": 4802.7, "end": 4803.96, "word": " tfidf", "probability": 0.6800537109375 }, { "start": 4803.96, "end": 4804.96, "word": ",", "probability": 0.2364501953125 } ] }, { "id": 1785, "seek": 471554, "start": 4807.64, "end": 4811.62, "text": " yes, tvec.transform,", "tokens": [ 50664, 2086, 11, 256, 303, 66, 13, 24999, 837, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.28897057561313405, "compression_ratio": 1.6794871794871795, "no_speech_prob": 0.2042236328125, "words": [ { "start": 4807.64, "end": 4808.12, "word": " yes", "probability": 0.75927734375 }, { "start": 4808.12, "end": 4808.6, "word": ",", "probability": 0.7265625 }, { "start": 4808.6, "end": 4809.68, "word": " tvec", "probability": 0.8819986979166666 }, { "start": 4809.68, "end": 4811.34, "word": ".transform", "probability": 0.9029947916666666 }, { "start": 4811.34, "end": 4811.62, "word": ",", "probability": 0.416015625 } ] }, { "id": 1786, "seek": 471554, "start": 4812.52, "end": 4815.94, "text": " and this is going to be, remember it needs to be in a list,", "tokens": [ 50964, 293, 341, 307, 516, 281, 312, 11, 1604, 309, 2203, 281, 312, 294, 257, 1329, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.28897057561313405, "compression_ratio": 1.6794871794871795, "no_speech_prob": 0.2042236328125, "words": [ { "start": 4812.52, "end": 4812.82, "word": " and", "probability": 0.58740234375 }, { "start": 4812.82, "end": 4813.0, "word": " this", "probability": 0.82666015625 }, { "start": 4813.0, "end": 4813.12, "word": " is", "probability": 0.9013671875 }, { "start": 4813.12, "end": 4813.2, "word": " going", "probability": 0.82958984375 }, { "start": 4813.2, "end": 4813.28, "word": " to", "probability": 0.90576171875 }, { "start": 4813.28, "end": 4813.64, "word": " be", "probability": 0.9033203125 }, { "start": 4813.64, "end": 4814.4, "word": ",", "probability": 0.54443359375 }, { "start": 4814.4, "end": 4814.74, "word": " remember", "probability": 0.7314453125 }, { "start": 4814.74, "end": 4814.96, "word": " it", "probability": 0.5498046875 }, { "start": 4814.96, "end": 4815.14, "word": " needs", "probability": 0.74365234375 }, { "start": 4815.14, "end": 4815.22, "word": " to", "probability": 0.90576171875 }, { "start": 4815.22, "end": 4815.3, "word": " be", "probability": 0.89697265625 }, { "start": 4815.3, "end": 4815.4, "word": " in", "probability": 0.8544921875 }, { "start": 4815.54, "end": 4815.84, "word": " a list", "probability": 0.87841796875 }, { "start": 4815.84, "end": 4815.94, "word": ",", "probability": 0.572265625 } ] }, { "id": 1787, "seek": 471554, "start": 4815.94, "end": 4819.62, "text": " so we've got to use these square brackets, our working email,", "tokens": [ 51114, 370, 321, 600, 658, 281, 764, 613, 3732, 26179, 11, 527, 1364, 3796, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.28897057561313405, "compression_ratio": 1.6794871794871795, "no_speech_prob": 0.2042236328125, "words": [ { "start": 4815.94, "end": 4816.04, "word": " so", "probability": 0.89892578125 }, { "start": 4816.04, "end": 4816.18, "word": " we've", "probability": 0.6766357421875 }, { "start": 4816.18, "end": 4816.2, "word": " got", "probability": 0.892578125 }, { "start": 4816.2, "end": 4816.26, "word": " to", "probability": 0.90087890625 }, { "start": 4816.26, "end": 4816.38, "word": " use", "probability": 0.81103515625 }, { "start": 4816.38, "end": 4816.54, "word": " these", "probability": 0.6142578125 }, { "start": 4816.54, "end": 4816.72, "word": " square", "probability": 0.8828125 }, { "start": 4816.72, "end": 4817.18, "word": " brackets", "probability": 0.83056640625 }, { "start": 4817.18, "end": 4817.4, "word": ",", "probability": 0.82177734375 }, { "start": 4817.4, "end": 4817.66, "word": " our", "probability": 0.78662109375 }, { "start": 4817.66, "end": 4818.6, "word": " working", "probability": 0.720703125 }, { "start": 4818.6, "end": 4819.0, "word": " email", "probability": 0.90869140625 }, { "start": 4819.0, "end": 4819.62, "word": ",", "probability": 0.65185546875 } ] }, { "id": 1788, "seek": 471554, "start": 4820.28, "end": 4827.66, "text": " and then we'll do the same thing with our test email count, tvec.transform,", "tokens": [ 51364, 293, 550, 321, 603, 360, 264, 912, 551, 365, 527, 1500, 3796, 1207, 11, 256, 303, 66, 13, 24999, 837, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.28897057561313405, "compression_ratio": 1.6794871794871795, "no_speech_prob": 0.2042236328125, "words": [ { "start": 4820.28, "end": 4820.66, "word": " and", "probability": 0.88818359375 }, { "start": 4820.66, "end": 4820.74, "word": " then", "probability": 0.70556640625 }, { "start": 4820.74, "end": 4820.84, "word": " we'll", "probability": 0.925537109375 }, { "start": 4820.84, "end": 4820.94, "word": " do", "probability": 0.9052734375 }, { "start": 4820.94, "end": 4821.1, "word": " the", "probability": 0.8115234375 }, { "start": 4821.1, "end": 4821.3, "word": " same", "probability": 0.8056640625 }, { "start": 4821.3, "end": 4821.56, "word": " thing", "probability": 0.80615234375 }, { "start": 4821.56, "end": 4821.76, "word": " with", "probability": 0.802734375 }, { "start": 4821.76, "end": 4821.96, "word": " our", "probability": 0.81494140625 }, { "start": 4821.96, "end": 4822.4, "word": " test", "probability": 0.7978515625 }, { "start": 4822.4, "end": 4822.94, "word": " email", "probability": 0.923828125 }, { "start": 4822.94, "end": 4823.84, "word": " count", "probability": 0.65185546875 }, { "start": 4823.84, "end": 4824.5, "word": ",", "probability": 0.9033203125 }, { "start": 4824.5, "end": 4825.44, "word": " tvec", "probability": 0.9527994791666666 }, { "start": 4825.44, "end": 4826.84, "word": ".transform", "probability": 0.92626953125 }, { "start": 4826.84, "end": 4827.66, "word": ",", "probability": 0.64208984375 } ] }, { "id": 1789, "seek": 474554, "start": 4830.76, "end": 4832.18, "text": " working email.", "tokens": [ 50364, 1364, 3796, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.21730323922302988, "compression_ratio": 1.661904761904762, "no_speech_prob": 0.004329681396484375, "words": [ { "start": 4830.76, "end": 4831.26, "word": " working", "probability": 0.19580078125 }, { "start": 4831.26, "end": 4831.68, "word": " email", "probability": 0.8515625 }, { "start": 4831.68, "end": 4832.18, "word": ".", "probability": 0.662109375 } ] }, { "id": 1790, "seek": 474554, "start": 4833.18, "end": 4836.52, "text": " Now we need to get the raw predictions for every single one of them.", "tokens": [ 50514, 823, 321, 643, 281, 483, 264, 8936, 21264, 337, 633, 2167, 472, 295, 552, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.21730323922302988, "compression_ratio": 1.661904761904762, "no_speech_prob": 0.004329681396484375, "words": [ { "start": 4833.18, "end": 4833.68, "word": " Now", "probability": 0.2113037109375 }, { "start": 4833.68, "end": 4834.1, "word": " we", "probability": 0.85009765625 }, { "start": 4834.1, "end": 4834.22, "word": " need", "probability": 0.80908203125 }, { "start": 4834.22, "end": 4834.28, "word": " to", "probability": 0.900390625 }, { "start": 4834.28, "end": 4834.4, "word": " get", "probability": 0.88427734375 }, { "start": 4834.4, "end": 4834.58, "word": " the", "probability": 0.8115234375 }, { "start": 4834.58, "end": 4834.82, "word": " raw", "probability": 0.80908203125 }, { "start": 4834.82, "end": 4835.18, "word": " predictions", "probability": 0.73974609375 }, { "start": 4835.18, "end": 4835.56, "word": " for", "probability": 0.892578125 }, { "start": 4835.56, "end": 4835.82, "word": " every", "probability": 0.7353515625 }, { "start": 4835.82, "end": 4836.06, "word": " single", "probability": 0.88671875 }, { "start": 4836.06, "end": 4836.22, "word": " one", "probability": 0.81787109375 }, { "start": 4836.22, "end": 4836.34, "word": " of", "probability": 0.892578125 }, { "start": 4836.34, "end": 4836.46, "word": " them", "probability": 0.736328125 }, { "start": 4836.46, "end": 4836.52, "word": ".", "probability": 0.9033203125 } ] }, { "id": 1791, "seek": 474554, "start": 4836.52, "end": 4840.88, "text": " The raw predictions, we already have the variable names here, kind of at the bottom,", "tokens": [ 50664, 440, 8936, 21264, 11, 321, 1217, 362, 264, 7006, 5288, 510, 11, 733, 295, 412, 264, 2767, 11, 50864 ], "temperature": 0.0, "avg_logprob": -0.21730323922302988, "compression_ratio": 1.661904761904762, "no_speech_prob": 0.004329681396484375, "words": [ { "start": 4836.52, "end": 4836.62, "word": " The", "probability": 0.468505859375 }, { "start": 4836.62, "end": 4836.88, "word": " raw", "probability": 0.77294921875 }, { "start": 4836.88, "end": 4837.28, "word": " predictions", "probability": 0.73828125 }, { "start": 4837.28, "end": 4837.42, "word": ",", "probability": 0.52294921875 }, { "start": 4837.42, "end": 4837.5, "word": " we", "probability": 0.90234375 }, { "start": 4837.5, "end": 4837.78, "word": " already", "probability": 0.81494140625 }, { "start": 4837.78, "end": 4838.08, "word": " have", "probability": 0.8759765625 }, { "start": 4838.08, "end": 4838.26, "word": " the", "probability": 0.80224609375 }, { "start": 4838.26, "end": 4838.58, "word": " variable", "probability": 0.7412109375 }, { "start": 4838.58, "end": 4839.1, "word": " names", "probability": 0.80908203125 }, { "start": 4839.1, "end": 4840.02, "word": " here", "probability": 0.76904296875 }, { "start": 4840.02, "end": 4840.12, "word": ",", "probability": 0.42919921875 }, { "start": 4840.12, "end": 4840.28, "word": " kind", "probability": 0.73486328125 }, { "start": 4840.28, "end": 4840.36, "word": " of", "probability": 0.9091796875 }, { "start": 4840.36, "end": 4840.46, "word": " at", "probability": 0.78857421875 }, { "start": 4840.46, "end": 4840.54, "word": " the", "probability": 0.818359375 }, { "start": 4840.54, "end": 4840.78, "word": " bottom", "probability": 0.7685546875 }, { "start": 4840.78, "end": 4840.88, "word": ",", "probability": 0.45849609375 } ] }, { "id": 1792, "seek": 474554, "start": 4840.88, "end": 4842.96, "text": " so I'm just going to go ahead and write them out.", "tokens": [ 50864, 370, 286, 478, 445, 516, 281, 352, 2286, 293, 2464, 552, 484, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.21730323922302988, "compression_ratio": 1.661904761904762, "no_speech_prob": 0.004329681396484375, "words": [ { "start": 4840.88, "end": 4840.96, "word": " so", "probability": 0.89111328125 }, { "start": 4840.96, "end": 4841.06, "word": " I'm", "probability": 0.9365234375 }, { "start": 4841.06, "end": 4841.16, "word": " just", "probability": 0.8701171875 }, { "start": 4841.16, "end": 4841.28, "word": " going", "probability": 0.492431640625 }, { "start": 4841.28, "end": 4841.32, "word": " to", "probability": 0.9033203125 }, { "start": 4841.32, "end": 4841.42, "word": " go", "probability": 0.876953125 }, { "start": 4841.42, "end": 4841.86, "word": " ahead", "probability": 0.84912109375 }, { "start": 4841.86, "end": 4842.32, "word": " and", "probability": 0.890625 }, { "start": 4842.32, "end": 4842.52, "word": " write", "probability": 0.79296875 }, { "start": 4842.52, "end": 4842.66, "word": " them", "probability": 0.73681640625 }, { "start": 4842.66, "end": 4842.84, "word": " out", "probability": 0.8095703125 }, { "start": 4842.84, "end": 4842.96, "word": ".", "probability": 0.87744140625 } ] }, { "id": 1793, "seek": 474554, "start": 4842.96, "end": 4846.66, "text": " So we have test email mnb with tfidf,", "tokens": [ 50964, 407, 321, 362, 1500, 3796, 275, 77, 65, 365, 256, 69, 327, 69, 11, 51164 ], "temperature": 0.0, "avg_logprob": -0.21730323922302988, "compression_ratio": 1.661904761904762, "no_speech_prob": 0.004329681396484375, "words": [ { "start": 4842.96, "end": 4843.02, "word": " So", "probability": 0.630859375 }, { "start": 4843.02, "end": 4843.1, "word": " we", "probability": 0.83349609375 }, { "start": 4843.1, "end": 4843.2, "word": " have", "probability": 0.880859375 }, { "start": 4843.2, "end": 4843.64, "word": " test", "probability": 0.5810546875 }, { "start": 4843.64, "end": 4844.18, "word": " email", "probability": 0.6025390625 }, { "start": 4844.18, "end": 4844.82, "word": " mnb", "probability": 0.74658203125 }, { "start": 4844.82, "end": 4845.16, "word": " with", "probability": 0.67822265625 }, { "start": 4845.16, "end": 4846.3, "word": " tfidf", "probability": 0.8118896484375 }, { "start": 4846.3, "end": 4846.66, "word": ",", "probability": 0.7626953125 } ] }, { "id": 1794, "seek": 474554, "start": 4847.84, "end": 4852.6, "text": " which is going to be our mnbtfidf.predict,", "tokens": [ 51214, 597, 307, 516, 281, 312, 527, 275, 77, 4517, 69, 327, 69, 13, 79, 24945, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.21730323922302988, "compression_ratio": 1.661904761904762, "no_speech_prob": 0.004329681396484375, "words": [ { "start": 4847.84, "end": 4848.34, "word": " which", "probability": 0.91455078125 }, { "start": 4848.34, "end": 4848.48, "word": " is", "probability": 0.90625 }, { "start": 4848.48, "end": 4848.62, "word": " going", "probability": 0.8603515625 }, { "start": 4848.62, "end": 4848.76, "word": " to", "probability": 0.90380859375 }, { "start": 4848.76, "end": 4848.98, "word": " be", "probability": 0.90771484375 }, { "start": 4848.98, "end": 4849.3, "word": " our", "probability": 0.806640625 }, { "start": 4849.3, "end": 4850.88, "word": " mnbtfidf", "probability": 0.8975423177083334 }, { "start": 4850.88, "end": 4851.64, "word": ".predict", "probability": 0.8190104166666666 }, { "start": 4851.64, "end": 4852.6, "word": ",", "probability": 0.1171875 } ] }, { "id": 1795, "seek": 474554, "start": 4852.6, "end": 4859.84, "text": " on our test email with the tfidf vectorized info,", "tokens": [ 51464, 322, 527, 1500, 3796, 365, 264, 256, 69, 327, 69, 8062, 1602, 13614, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.21730323922302988, "compression_ratio": 1.661904761904762, "no_speech_prob": 0.004329681396484375, "words": [ { "start": 4852.6, "end": 4853.24, "word": " on", "probability": 0.86328125 }, { "start": 4853.24, "end": 4853.6, "word": " our", "probability": 0.8203125 }, { "start": 4853.6, "end": 4854.18, "word": " test", "probability": 0.8193359375 }, { "start": 4854.18, "end": 4854.84, "word": " email", "probability": 0.916015625 }, { "start": 4854.84, "end": 4856.6, "word": " with", "probability": 0.716796875 }, { "start": 4856.6, "end": 4856.88, "word": " the", "probability": 0.75 }, { "start": 4856.88, "end": 4858.2, "word": " tfidf", "probability": 0.97021484375 }, { "start": 4858.2, "end": 4859.06, "word": " vectorized", "probability": 0.795654296875 }, { "start": 4859.06, "end": 4859.56, "word": " info", "probability": 0.70263671875 }, { "start": 4859.56, "end": 4859.84, "word": ",", "probability": 0.24072265625 } ] }, { "id": 1796, "seek": 477212, "start": 4860.62, "end": 4864.52, "text": " we're going to do the same thing for count,", "tokens": [ 50364, 321, 434, 516, 281, 360, 264, 912, 551, 337, 1207, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.2585827590714038, "compression_ratio": 1.5478260869565217, "no_speech_prob": 0.0012645721435546875, "words": [ { "start": 4860.62, "end": 4861.14, "word": " we're", "probability": 0.4599456787109375 }, { "start": 4861.14, "end": 4861.14, "word": " going", "probability": 0.513671875 }, { "start": 4861.14, "end": 4861.2, "word": " to", "probability": 0.904296875 }, { "start": 4861.2, "end": 4861.28, "word": " do", "probability": 0.90234375 }, { "start": 4861.28, "end": 4861.46, "word": " the", "probability": 0.81005859375 }, { "start": 4861.46, "end": 4861.68, "word": " same", "probability": 0.81787109375 }, { "start": 4861.68, "end": 4862.14, "word": " thing", "probability": 0.81005859375 }, { "start": 4862.14, "end": 4863.26, "word": " for", "probability": 0.8935546875 }, { "start": 4863.26, "end": 4864.12, "word": " count", "probability": 0.62744140625 }, { "start": 4864.12, "end": 4864.52, "word": ",", "probability": 0.302490234375 } ] }, { "id": 1797, "seek": 477212, "start": 4864.52, "end": 4866.8, "text": " using our count.predict,", "tokens": [ 50564, 1228, 527, 1207, 13, 79, 24945, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.2585827590714038, "compression_ratio": 1.5478260869565217, "no_speech_prob": 0.0012645721435546875, "words": [ { "start": 4864.52, "end": 4864.92, "word": " using", "probability": 0.611328125 }, { "start": 4864.92, "end": 4865.1, "word": " our", "probability": 0.79541015625 }, { "start": 4865.1, "end": 4865.56, "word": " count", "probability": 0.62646484375 }, { "start": 4865.56, "end": 4866.34, "word": ".predict", "probability": 0.5963541666666666 }, { "start": 4866.34, "end": 4866.8, "word": ",", "probability": 0.183837890625 } ] }, { "id": 1798, "seek": 477212, "start": 4874.49, "end": 4877.83, "text": " with our count vectorized,", "tokens": [ 50864, 365, 527, 1207, 8062, 1602, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.2585827590714038, "compression_ratio": 1.5478260869565217, "no_speech_prob": 0.0012645721435546875, "words": [ { "start": 4874.49, "end": 4875.41, "word": " with", "probability": 0.09906005859375 }, { "start": 4875.41, "end": 4876.33, "word": " our", "probability": 0.77734375 }, { "start": 4876.33, "end": 4876.59, "word": " count", "probability": 0.783203125 }, { "start": 4876.59, "end": 4877.35, "word": " vectorized", "probability": 0.8583984375 }, { "start": 4877.35, "end": 4877.83, "word": ",", "probability": 0.492919921875 } ] }, { "id": 1799, "seek": 477212, "start": 4878.39, "end": 4883.85, "text": " test email lgs, tfidf.predict,", "tokens": [ 50964, 1500, 3796, 287, 21559, 11, 256, 69, 327, 69, 13, 79, 24945, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.2585827590714038, "compression_ratio": 1.5478260869565217, "no_speech_prob": 0.0012645721435546875, "words": [ { "start": 4878.39, "end": 4878.69, "word": " test", "probability": 0.77197265625 }, { "start": 4878.69, "end": 4879.19, "word": " email", "probability": 0.54150390625 }, { "start": 4879.19, "end": 4880.67, "word": " lgs", "probability": 0.69189453125 }, { "start": 4880.67, "end": 4881.03, "word": ",", "probability": 0.12744140625 }, { "start": 4881.03, "end": 4882.43, "word": " tfidf", "probability": 0.7475433349609375 }, { "start": 4882.43, "end": 4883.39, "word": ".predict", "probability": 0.6956380208333334 }, { "start": 4883.39, "end": 4883.85, "word": ",", "probability": 0.82177734375 } ] }, { "id": 1800, "seek": 477212, "start": 4892.02, "end": 4895.22, "text": " tfidf.data, and our last one,", "tokens": [ 51364, 256, 69, 327, 69, 13, 67, 3274, 11, 293, 527, 1036, 472, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.2585827590714038, "compression_ratio": 1.5478260869565217, "no_speech_prob": 0.0012645721435546875, "words": [ { "start": 4892.02, "end": 4892.94, "word": " tfidf", "probability": 0.9488525390625 }, { "start": 4892.94, "end": 4893.22, "word": ".data", "probability": 0.7421875 }, { "start": 4893.22, "end": 4893.36, "word": ",", "probability": 0.66845703125 }, { "start": 4893.36, "end": 4893.6, "word": " and", "probability": 0.8896484375 }, { "start": 4893.6, "end": 4893.84, "word": " our", "probability": 0.82763671875 }, { "start": 4893.84, "end": 4894.18, "word": " last", "probability": 0.82568359375 }, { "start": 4894.18, "end": 4894.74, "word": " one", "probability": 0.81103515625 }, { "start": 4894.74, "end": 4895.22, "word": ",", "probability": 0.7861328125 } ] }, { "id": 1801, "seek": 477212, "start": 4895.22, "end": 4898.48, "text": " test email lgs.count,", "tokens": [ 51514, 1500, 3796, 287, 21559, 13, 26050, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.2585827590714038, "compression_ratio": 1.5478260869565217, "no_speech_prob": 0.0012645721435546875, "words": [ { "start": 4895.22, "end": 4895.82, "word": " test", "probability": 0.826171875 }, { "start": 4895.82, "end": 4896.18, "word": " email", "probability": 0.84326171875 }, { "start": 4896.18, "end": 4897.0, "word": " lgs", "probability": 0.96484375 }, { "start": 4897.0, "end": 4898.04, "word": ".count", "probability": 0.5076904296875 }, { "start": 4898.04, "end": 4898.48, "word": ",", "probability": 0.298095703125 } ] }, { "id": 1802, "seek": 480108, "start": 4904.52, "end": 4905.56, "text": " count.", "tokens": [ 50414, 1207, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.20986520177593418, "compression_ratio": 1.6069651741293531, "no_speech_prob": 0.0022869110107421875, "words": [ { "start": 4904.52, "end": 4905.04, "word": " count", "probability": 0.0267486572265625 }, { "start": 4905.04, "end": 4905.56, "word": ".", "probability": 0.388916015625 } ] }, { "id": 1803, "seek": 480108, "start": 4907.04, "end": 4909.56, "text": " And then, just for fun and games,", "tokens": [ 50564, 400, 550, 11, 445, 337, 1019, 293, 2813, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.20986520177593418, "compression_ratio": 1.6069651741293531, "no_speech_prob": 0.0022869110107421875, "words": [ { "start": 4907.04, "end": 4907.38, "word": " And", "probability": 0.7119140625 }, { "start": 4907.38, "end": 4907.64, "word": " then", "probability": 0.7119140625 }, { "start": 4907.64, "end": 4907.86, "word": ",", "probability": 0.320556640625 }, { "start": 4907.86, "end": 4907.98, "word": " just", "probability": 0.892578125 }, { "start": 4907.98, "end": 4908.28, "word": " for", "probability": 0.8994140625 }, { "start": 4908.28, "end": 4909.02, "word": " fun", "probability": 0.9208984375 }, { "start": 4909.02, "end": 4909.12, "word": " and", "probability": 0.865234375 }, { "start": 4909.12, "end": 4909.38, "word": " games", "probability": 0.78857421875 }, { "start": 4909.38, "end": 4909.56, "word": ",", "probability": 0.87744140625 } ] }, { "id": 1804, "seek": 480108, "start": 4909.56, "end": 4912.8, "text": " we can print out our working email.", "tokens": [ 50664, 321, 393, 4482, 484, 527, 1364, 3796, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.20986520177593418, "compression_ratio": 1.6069651741293531, "no_speech_prob": 0.0022869110107421875, "words": [ { "start": 4909.56, "end": 4909.64, "word": " we", "probability": 0.904296875 }, { "start": 4909.64, "end": 4909.94, "word": " can", "probability": 0.896484375 }, { "start": 4909.94, "end": 4910.36, "word": " print", "probability": 0.87744140625 }, { "start": 4910.36, "end": 4910.6, "word": " out", "probability": 0.7900390625 }, { "start": 4910.6, "end": 4911.06, "word": " our", "probability": 0.81787109375 }, { "start": 4911.06, "end": 4911.9, "word": " working", "probability": 0.68017578125 }, { "start": 4911.9, "end": 4912.28, "word": " email", "probability": 0.88330078125 }, { "start": 4912.28, "end": 4912.8, "word": ".", "probability": 0.974609375 } ] }, { "id": 1805, "seek": 480108, "start": 4913.02, "end": 4915.24, "text": " So this is going to print our test email.", "tokens": [ 50814, 407, 341, 307, 516, 281, 4482, 527, 1500, 3796, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.20986520177593418, "compression_ratio": 1.6069651741293531, "no_speech_prob": 0.0022869110107421875, "words": [ { "start": 4913.02, "end": 4913.2, "word": " So", "probability": 0.76123046875 }, { "start": 4913.2, "end": 4913.32, "word": " this", "probability": 0.6962890625 }, { "start": 4913.32, "end": 4913.44, "word": " is", "probability": 0.9013671875 }, { "start": 4913.44, "end": 4913.52, "word": " going", "probability": 0.6240234375 }, { "start": 4913.52, "end": 4913.62, "word": " to", "probability": 0.90869140625 }, { "start": 4913.62, "end": 4913.8, "word": " print", "probability": 0.86474609375 }, { "start": 4913.8, "end": 4913.98, "word": " our", "probability": 0.763671875 }, { "start": 4913.98, "end": 4914.5, "word": " test", "probability": 0.80615234375 }, { "start": 4914.5, "end": 4914.92, "word": " email", "probability": 0.9296875 }, { "start": 4914.92, "end": 4915.24, "word": ".", "probability": 0.85107421875 } ] }, { "id": 1806, "seek": 480108, "start": 4915.24, "end": 4917.4, "text": " Our test email was the one that we saw,", "tokens": [ 50964, 2621, 1500, 3796, 390, 264, 472, 300, 321, 1866, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.20986520177593418, "compression_ratio": 1.6069651741293531, "no_speech_prob": 0.0022869110107421875, "words": [ { "start": 4915.24, "end": 4915.4, "word": " Our", "probability": 0.88916015625 }, { "start": 4915.4, "end": 4915.66, "word": " test", "probability": 0.8056640625 }, { "start": 4915.66, "end": 4916.0, "word": " email", "probability": 0.91455078125 }, { "start": 4916.0, "end": 4916.2, "word": " was", "probability": 0.69970703125 }, { "start": 4916.2, "end": 4916.32, "word": " the", "probability": 0.81103515625 }, { "start": 4916.32, "end": 4916.42, "word": " one", "probability": 0.81494140625 }, { "start": 4916.42, "end": 4916.52, "word": " that", "probability": 0.734375 }, { "start": 4916.52, "end": 4916.62, "word": " we", "probability": 0.8994140625 }, { "start": 4916.62, "end": 4916.98, "word": " saw", "probability": 0.8095703125 }, { "start": 4916.98, "end": 4917.4, "word": ",", "probability": 0.28173828125 } ] }, { "id": 1807, "seek": 480108, "start": 4917.4, "end": 4919.94, "text": " EastAsianFonts and Lenny, thanks for your support.", "tokens": [ 51064, 6747, 10884, 952, 37, 896, 82, 293, 23009, 1634, 11, 3231, 337, 428, 1406, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.20986520177593418, "compression_ratio": 1.6069651741293531, "no_speech_prob": 0.0022869110107421875, "words": [ { "start": 4917.4, "end": 4918.18, "word": " EastAsianFonts", "probability": 0.7585042317708334 }, { "start": 4918.18, "end": 4918.28, "word": " and", "probability": 0.45263671875 }, { "start": 4918.28, "end": 4918.52, "word": " Lenny", "probability": 0.8818359375 }, { "start": 4918.52, "end": 4918.58, "word": ",", "probability": 0.6640625 }, { "start": 4918.58, "end": 4918.78, "word": " thanks", "probability": 0.7001953125 }, { "start": 4918.78, "end": 4918.9, "word": " for", "probability": 0.89697265625 }, { "start": 4918.9, "end": 4919.02, "word": " your", "probability": 0.80712890625 }, { "start": 4919.02, "end": 4919.42, "word": " support", "probability": 0.935546875 }, { "start": 4919.42, "end": 4919.94, "word": ".", "probability": 0.94091796875 } ] }, { "id": 1808, "seek": 480108, "start": 4922.5, "end": 4926.64, "text": " So you can go ahead and copy this down.", "tokens": [ 51314, 407, 291, 393, 352, 2286, 293, 5055, 341, 760, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.20986520177593418, "compression_ratio": 1.6069651741293531, "no_speech_prob": 0.0022869110107421875, "words": [ { "start": 4922.5, "end": 4923.02, "word": " So", "probability": 0.77685546875 }, { "start": 4923.02, "end": 4923.54, "word": " you", "probability": 0.64208984375 }, { "start": 4923.54, "end": 4923.74, "word": " can", "probability": 0.89794921875 }, { "start": 4923.74, "end": 4923.92, "word": " go", "probability": 0.892578125 }, { "start": 4923.92, "end": 4924.36, "word": " ahead", "probability": 0.85107421875 }, { "start": 4924.36, "end": 4924.94, "word": " and", "probability": 0.88623046875 }, { "start": 4924.94, "end": 4925.86, "word": " copy", "probability": 0.80908203125 }, { "start": 4925.86, "end": 4926.16, "word": " this", "probability": 0.88525390625 }, { "start": 4926.16, "end": 4926.5, "word": " down", "probability": 0.8046875 }, { "start": 4926.5, "end": 4926.64, "word": ".", "probability": 0.79931640625 } ] }, { "id": 1809, "seek": 480108, "start": 4926.64, "end": 4929.22, "text": " I'm going to go ahead and run this,", "tokens": [ 51514, 286, 478, 516, 281, 352, 2286, 293, 1190, 341, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.20986520177593418, "compression_ratio": 1.6069651741293531, "no_speech_prob": 0.0022869110107421875, "words": [ { "start": 4926.64, "end": 4926.82, "word": " I'm", "probability": 0.990478515625 }, { "start": 4926.82, "end": 4926.9, "word": " going", "probability": 0.7626953125 }, { "start": 4926.9, "end": 4926.94, "word": " to", "probability": 0.90283203125 }, { "start": 4926.94, "end": 4927.06, "word": " go", "probability": 0.89013671875 }, { "start": 4927.06, "end": 4927.52, "word": " ahead", "probability": 0.861328125 }, { "start": 4927.52, "end": 4928.1, "word": " and", "probability": 0.89501953125 }, { "start": 4928.1, "end": 4928.6, "word": " run", "probability": 0.90185546875 }, { "start": 4928.6, "end": 4929.06, "word": " this", "probability": 0.87890625 }, { "start": 4929.06, "end": 4929.22, "word": ",", "probability": 0.476318359375 } ] }, { "id": 1810, "seek": 480108, "start": 4929.22, "end": 4931.78, "text": " because we are running close to time.", "tokens": [ 51664, 570, 321, 366, 2614, 1998, 281, 565, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.20986520177593418, "compression_ratio": 1.6069651741293531, "no_speech_prob": 0.0022869110107421875, "words": [ { "start": 4929.22, "end": 4929.4, "word": " because", "probability": 0.7353515625 }, { "start": 4929.4, "end": 4929.54, "word": " we", "probability": 0.90478515625 }, { "start": 4929.54, "end": 4929.78, "word": " are", "probability": 0.7255859375 }, { "start": 4929.78, "end": 4930.26, "word": " running", "probability": 0.8798828125 }, { "start": 4930.26, "end": 4930.72, "word": " close", "probability": 0.8486328125 }, { "start": 4930.72, "end": 4930.92, "word": " to", "probability": 0.90087890625 }, { "start": 4930.92, "end": 4931.26, "word": " time", "probability": 0.7958984375 }, { "start": 4931.26, "end": 4931.78, "word": ".", "probability": 0.96630859375 } ] }, { "id": 1811, "seek": 482880, "start": 4931.78, "end": 4933.82, "text": " So this is going to be our test email,", "tokens": [ 50364, 407, 341, 307, 516, 281, 312, 527, 1500, 3796, 11, 50464 ], "temperature": 0.0, "avg_logprob": -0.19791666432111352, "compression_ratio": 1.70935960591133, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 4931.78, "end": 4932.06, "word": " So", "probability": 0.6259765625 }, { "start": 4932.06, "end": 4932.22, "word": " this", "probability": 0.7939453125 }, { "start": 4932.22, "end": 4932.32, "word": " is", "probability": 0.91259765625 }, { "start": 4932.32, "end": 4932.42, "word": " going", "probability": 0.76904296875 }, { "start": 4932.42, "end": 4932.46, "word": " to", "probability": 0.9033203125 }, { "start": 4932.46, "end": 4932.54, "word": " be", "probability": 0.90625 }, { "start": 4932.54, "end": 4932.7, "word": " our", "probability": 0.62744140625 }, { "start": 4932.7, "end": 4933.0, "word": " test", "probability": 0.79736328125 }, { "start": 4933.0, "end": 4933.28, "word": " email", "probability": 0.8916015625 }, { "start": 4933.28, "end": 4933.82, "word": ",", "probability": 0.332275390625 } ] }, { "id": 1812, "seek": 482880, "start": 4933.82, "end": 4935.84, "text": " and ideally, this should say that", "tokens": [ 50464, 293, 22915, 11, 341, 820, 584, 300, 50564 ], "temperature": 0.0, "avg_logprob": -0.19791666432111352, "compression_ratio": 1.70935960591133, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 4933.82, "end": 4934.02, "word": " and", "probability": 0.88134765625 }, { "start": 4934.02, "end": 4934.48, "word": " ideally", "probability": 0.7119140625 }, { "start": 4934.48, "end": 4934.7, "word": ",", "probability": 0.21044921875 }, { "start": 4934.7, "end": 4934.86, "word": " this", "probability": 0.87158203125 }, { "start": 4934.86, "end": 4935.1, "word": " should", "probability": 0.9248046875 }, { "start": 4935.1, "end": 4935.5, "word": " say", "probability": 0.8837890625 }, { "start": 4935.5, "end": 4935.84, "word": " that", "probability": 0.86279296875 } ] }, { "id": 1813, "seek": 482880, "start": 4935.84, "end": 4938.14, "text": " it is a regular email, not spam.", "tokens": [ 50564, 309, 307, 257, 3890, 3796, 11, 406, 24028, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.19791666432111352, "compression_ratio": 1.70935960591133, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 4935.84, "end": 4936.02, "word": " it", "probability": 0.892578125 }, { "start": 4936.02, "end": 4936.26, "word": " is", "probability": 0.89404296875 }, { "start": 4936.6, "end": 4936.9, "word": " a regular", "probability": 0.88671875 }, { "start": 4936.9, "end": 4937.28, "word": " email", "probability": 0.90771484375 }, { "start": 4937.28, "end": 4937.42, "word": ",", "probability": 0.744140625 }, { "start": 4937.42, "end": 4937.64, "word": " not", "probability": 0.865234375 }, { "start": 4937.64, "end": 4938.0, "word": " spam", "probability": 0.91650390625 }, { "start": 4938.0, "end": 4938.14, "word": ".", "probability": 0.88330078125 } ] }, { "id": 1814, "seek": 482880, "start": 4938.14, "end": 4941.1, "text": " It's going to label all four of these as ham.", "tokens": [ 50664, 467, 311, 516, 281, 7645, 439, 1451, 295, 613, 382, 7852, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.19791666432111352, "compression_ratio": 1.70935960591133, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 4938.14, "end": 4938.22, "word": " It's", "probability": 0.9228515625 }, { "start": 4938.22, "end": 4938.38, "word": " going", "probability": 0.82373046875 }, { "start": 4938.38, "end": 4938.5, "word": " to", "probability": 0.90576171875 }, { "start": 4938.5, "end": 4938.7, "word": " label", "probability": 0.81005859375 }, { "start": 4938.7, "end": 4939.06, "word": " all", "probability": 0.90576171875 }, { "start": 4939.06, "end": 4939.32, "word": " four", "probability": 0.86865234375 }, { "start": 4939.32, "end": 4939.46, "word": " of", "probability": 0.9091796875 }, { "start": 4939.46, "end": 4939.7, "word": " these", "probability": 0.7041015625 }, { "start": 4939.7, "end": 4940.06, "word": " as", "probability": 0.91357421875 }, { "start": 4940.06, "end": 4940.58, "word": " ham", "probability": 0.325927734375 }, { "start": 4940.58, "end": 4941.1, "word": ".", "probability": 0.9658203125 } ] }, { "id": 1815, "seek": 482880, "start": 4941.12, "end": 4942.62, "text": " So let's run it.", "tokens": [ 50814, 407, 718, 311, 1190, 309, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.19791666432111352, "compression_ratio": 1.70935960591133, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 4941.12, "end": 4941.52, "word": " So", "probability": 0.8466796875 }, { "start": 4941.52, "end": 4941.72, "word": " let's", "probability": 0.933349609375 }, { "start": 4941.72, "end": 4941.9, "word": " run", "probability": 0.90283203125 }, { "start": 4941.9, "end": 4942.1, "word": " it", "probability": 0.9052734375 }, { "start": 4942.1, "end": 4942.62, "word": ".", "probability": 0.7705078125 } ] }, { "id": 1816, "seek": 482880, "start": 4942.92, "end": 4944.78, "text": " Working is not defined,", "tokens": [ 50914, 18337, 307, 406, 7642, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.19791666432111352, "compression_ratio": 1.70935960591133, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 4942.92, "end": 4943.26, "word": " Working", "probability": 0.69189453125 }, { "start": 4943.26, "end": 4943.62, "word": " is", "probability": 0.90283203125 }, { "start": 4943.62, "end": 4943.8, "word": " not", "probability": 0.904296875 }, { "start": 4943.8, "end": 4944.36, "word": " defined", "probability": 0.74560546875 }, { "start": 4944.36, "end": 4944.78, "word": ",", "probability": 0.260986328125 } ] }, { "id": 1817, "seek": 482880, "start": 4946.54, "end": 4949.54, "text": " because I forgot to call this working email.", "tokens": [ 51114, 570, 286, 5298, 281, 818, 341, 1364, 3796, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.19791666432111352, "compression_ratio": 1.70935960591133, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 4946.54, "end": 4947.06, "word": " because", "probability": 0.7548828125 }, { "start": 4947.06, "end": 4947.34, "word": " I", "probability": 0.95849609375 }, { "start": 4947.34, "end": 4947.66, "word": " forgot", "probability": 0.76513671875 }, { "start": 4947.66, "end": 4947.88, "word": " to", "probability": 0.90673828125 }, { "start": 4947.88, "end": 4948.02, "word": " call", "probability": 0.818359375 }, { "start": 4948.02, "end": 4948.24, "word": " this", "probability": 0.88671875 }, { "start": 4948.24, "end": 4948.56, "word": " working", "probability": 0.486083984375 }, { "start": 4948.56, "end": 4949.02, "word": " email", "probability": 0.89208984375 }, { "start": 4949.02, "end": 4949.54, "word": ".", "probability": 0.9384765625 } ] }, { "id": 1818, "seek": 482880, "start": 4950.2, "end": 4951.56, "text": " So we're going to run it.", "tokens": [ 51264, 407, 321, 434, 516, 281, 1190, 309, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.19791666432111352, "compression_ratio": 1.70935960591133, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 4950.2, "end": 4950.48, "word": " So", "probability": 0.85400390625 }, { "start": 4950.48, "end": 4950.6, "word": " we're", "probability": 0.90771484375 }, { "start": 4950.6, "end": 4950.62, "word": " going", "probability": 0.759765625 }, { "start": 4950.62, "end": 4950.68, "word": " to", "probability": 0.90576171875 }, { "start": 4950.68, "end": 4950.82, "word": " run", "probability": 0.90234375 }, { "start": 4950.82, "end": 4951.04, "word": " it", "probability": 0.9052734375 }, { "start": 4951.04, "end": 4951.56, "word": ".", "probability": 0.89990234375 } ] }, { "id": 1819, "seek": 482880, "start": 4952.28, "end": 4953.72, "text": " Here's our email.", "tokens": [ 51364, 1692, 311, 527, 3796, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.19791666432111352, "compression_ratio": 1.70935960591133, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 4952.28, "end": 4952.8, "word": " Here's", "probability": 0.827880859375 }, { "start": 4952.8, "end": 4952.94, "word": " our", "probability": 0.81103515625 }, { "start": 4952.94, "end": 4953.2, "word": " email", "probability": 0.9130859375 }, { "start": 4953.2, "end": 4953.72, "word": ".", "probability": 0.474609375 } ] }, { "id": 1820, "seek": 482880, "start": 4954.38, "end": 4956.14, "text": " And all four of our classifiers", "tokens": [ 51464, 400, 439, 1451, 295, 527, 1508, 23463, 51564 ], "temperature": 0.0, "avg_logprob": -0.19791666432111352, "compression_ratio": 1.70935960591133, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 4954.38, "end": 4954.9, "word": " And", "probability": 0.85791015625 }, { "start": 4954.9, "end": 4955.16, "word": " all", "probability": 0.90234375 }, { "start": 4955.16, "end": 4955.38, "word": " four", "probability": 0.89306640625 }, { "start": 4955.38, "end": 4955.48, "word": " of", "probability": 0.89990234375 }, { "start": 4955.48, "end": 4955.56, "word": " our", "probability": 0.83056640625 }, { "start": 4955.56, "end": 4956.14, "word": " classifiers", "probability": 0.927978515625 } ] }, { "id": 1821, "seek": 482880, "start": 4956.14, "end": 4959.5, "text": " correctly classified this as ham.", "tokens": [ 51564, 8944, 20627, 341, 382, 7852, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.19791666432111352, "compression_ratio": 1.70935960591133, "no_speech_prob": 0.00045108795166015625, "words": [ { "start": 4956.14, "end": 4956.74, "word": " correctly", "probability": 0.8857421875 }, { "start": 4956.74, "end": 4957.36, "word": " classified", "probability": 0.82958984375 }, { "start": 4957.36, "end": 4957.88, "word": " this", "probability": 0.8798828125 }, { "start": 4957.88, "end": 4958.42, "word": " as", "probability": 0.91064453125 }, { "start": 4958.42, "end": 4958.98, "word": " ham", "probability": 0.8447265625 }, { "start": 4958.98, "end": 4959.5, "word": ".", "probability": 0.96484375 } ] }, { "id": 1822, "seek": 485878, "start": 4960.36, "end": 4962.22, "text": " I'm going to scroll back up,", "tokens": [ 50414, 286, 478, 516, 281, 11369, 646, 493, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.2295454590158029, "compression_ratio": 1.5045454545454546, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 4960.36, "end": 4960.96, "word": " I'm", "probability": 0.6795654296875 }, { "start": 4960.96, "end": 4960.98, "word": " going", "probability": 0.447509765625 }, { "start": 4960.98, "end": 4961.02, "word": " to", "probability": 0.90966796875 }, { "start": 4961.02, "end": 4961.24, "word": " scroll", "probability": 0.91015625 }, { "start": 4961.24, "end": 4961.5, "word": " back", "probability": 0.81201171875 }, { "start": 4961.5, "end": 4961.78, "word": " up", "probability": 0.90283203125 }, { "start": 4961.78, "end": 4962.22, "word": ",", "probability": 0.286376953125 } ] }, { "id": 1823, "seek": 485878, "start": 4962.22, "end": 4968.28, "text": " and we saved our email as our test spam email.", "tokens": [ 50514, 293, 321, 6624, 527, 3796, 382, 527, 1500, 24028, 3796, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.2295454590158029, "compression_ratio": 1.5045454545454546, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 4962.22, "end": 4962.38, "word": " and", "probability": 0.87548828125 }, { "start": 4962.38, "end": 4962.6, "word": " we", "probability": 0.8916015625 }, { "start": 4962.6, "end": 4963.34, "word": " saved", "probability": 0.70458984375 }, { "start": 4963.34, "end": 4964.56, "word": " our", "probability": 0.8056640625 }, { "start": 4964.56, "end": 4965.64, "word": " email", "probability": 0.81591796875 }, { "start": 4965.64, "end": 4966.06, "word": " as", "probability": 0.8955078125 }, { "start": 4966.06, "end": 4966.36, "word": " our", "probability": 0.7880859375 }, { "start": 4966.36, "end": 4966.76, "word": " test", "probability": 0.63427734375 }, { "start": 4966.76, "end": 4967.3, "word": " spam", "probability": 0.86279296875 }, { "start": 4967.3, "end": 4967.72, "word": " email", "probability": 0.91162109375 }, { "start": 4967.72, "end": 4968.28, "word": ".", "probability": 0.76904296875 } ] }, { "id": 1824, "seek": 485878, "start": 4968.28, "end": 4970.78, "text": " So I'm going to grab that,", "tokens": [ 50764, 407, 286, 478, 516, 281, 4444, 300, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.2295454590158029, "compression_ratio": 1.5045454545454546, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 4968.28, "end": 4968.58, "word": " So", "probability": 0.6376953125 }, { "start": 4968.58, "end": 4968.68, "word": " I'm", "probability": 0.844970703125 }, { "start": 4968.68, "end": 4968.72, "word": " going", "probability": 0.75146484375 }, { "start": 4968.72, "end": 4968.82, "word": " to", "probability": 0.90478515625 }, { "start": 4968.82, "end": 4969.2, "word": " grab", "probability": 0.78271484375 }, { "start": 4969.2, "end": 4970.06, "word": " that", "probability": 0.884765625 }, { "start": 4970.06, "end": 4970.78, "word": ",", "probability": 0.368408203125 } ] }, { "id": 1825, "seek": 485878, "start": 4970.78, "end": 4972.52, "text": " and I'll run it.", "tokens": [ 50914, 293, 286, 603, 1190, 309, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.2295454590158029, "compression_ratio": 1.5045454545454546, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 4970.78, "end": 4971.42, "word": " and", "probability": 0.51708984375 }, { "start": 4971.42, "end": 4971.56, "word": " I'll", "probability": 0.735595703125 }, { "start": 4971.56, "end": 4971.74, "word": " run", "probability": 0.904296875 }, { "start": 4971.74, "end": 4971.92, "word": " it", "probability": 0.90625 }, { "start": 4971.92, "end": 4972.52, "word": ".", "probability": 0.94970703125 } ] }, { "id": 1826, "seek": 485878, "start": 4973.26, "end": 4975.52, "text": " Oh, I forgot to run the code block", "tokens": [ 51014, 876, 11, 286, 5298, 281, 1190, 264, 3089, 3461, 51164 ], "temperature": 0.0, "avg_logprob": -0.2295454590158029, "compression_ratio": 1.5045454545454546, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 4973.26, "end": 4973.52, "word": " Oh", "probability": 0.407470703125 }, { "start": 4973.52, "end": 4973.82, "word": ",", "probability": 0.90185546875 }, { "start": 4973.82, "end": 4974.02, "word": " I", "probability": 0.9814453125 }, { "start": 4974.02, "end": 4974.16, "word": " forgot", "probability": 0.77294921875 }, { "start": 4974.16, "end": 4974.34, "word": " to", "probability": 0.9052734375 }, { "start": 4974.34, "end": 4974.56, "word": " run", "probability": 0.8916015625 }, { "start": 4974.56, "end": 4974.86, "word": " the", "probability": 0.81298828125 }, { "start": 4974.86, "end": 4975.32, "word": " code", "probability": 0.8486328125 }, { "start": 4975.32, "end": 4975.52, "word": " block", "probability": 0.80078125 } ] }, { "id": 1827, "seek": 485878, "start": 4975.52, "end": 4978.2, "text": " that actually defined our test spam email.", "tokens": [ 51164, 300, 767, 7642, 527, 1500, 24028, 3796, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.2295454590158029, "compression_ratio": 1.5045454545454546, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 4975.52, "end": 4975.7, "word": " that", "probability": 0.8818359375 }, { "start": 4975.7, "end": 4976.06, "word": " actually", "probability": 0.77392578125 }, { "start": 4976.06, "end": 4976.56, "word": " defined", "probability": 0.7216796875 }, { "start": 4976.56, "end": 4976.82, "word": " our", "probability": 0.82470703125 }, { "start": 4976.82, "end": 4977.04, "word": " test", "probability": 0.7744140625 }, { "start": 4977.04, "end": 4977.32, "word": " spam", "probability": 0.89599609375 }, { "start": 4977.32, "end": 4977.6, "word": " email", "probability": 0.9140625 }, { "start": 4977.6, "end": 4978.2, "word": ".", "probability": 0.92919921875 } ] }, { "id": 1828, "seek": 485878, "start": 4979.12, "end": 4980.96, "text": " And now we can run this.", "tokens": [ 51314, 400, 586, 321, 393, 1190, 341, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.2295454590158029, "compression_ratio": 1.5045454545454546, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 4979.12, "end": 4979.68, "word": " And", "probability": 0.7548828125 }, { "start": 4979.68, "end": 4979.8, "word": " now", "probability": 0.88525390625 }, { "start": 4979.8, "end": 4979.88, "word": " we", "probability": 0.86474609375 }, { "start": 4979.88, "end": 4979.98, "word": " can", "probability": 0.89453125 }, { "start": 4979.98, "end": 4980.12, "word": " run", "probability": 0.91015625 }, { "start": 4980.12, "end": 4980.36, "word": " this", "probability": 0.87890625 }, { "start": 4980.36, "end": 4980.96, "word": ".", "probability": 0.95654296875 } ] }, { "id": 1829, "seek": 485878, "start": 4981.56, "end": 4983.06, "text": " And we see something interesting here.", "tokens": [ 51414, 400, 321, 536, 746, 1880, 510, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.2295454590158029, "compression_ratio": 1.5045454545454546, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 4981.56, "end": 4981.7, "word": " And", "probability": 0.5537109375 }, { "start": 4981.7, "end": 4981.76, "word": " we", "probability": 0.8935546875 }, { "start": 4981.76, "end": 4981.86, "word": " see", "probability": 0.81396484375 }, { "start": 4981.86, "end": 4982.08, "word": " something", "probability": 0.74072265625 }, { "start": 4982.08, "end": 4982.42, "word": " interesting", "probability": 0.63623046875 }, { "start": 4982.42, "end": 4982.74, "word": " here", "probability": 0.81298828125 }, { "start": 4982.74, "end": 4983.06, "word": ".", "probability": 0.401611328125 } ] }, { "id": 1830, "seek": 485878, "start": 4983.06, "end": 4984.76, "text": " Our worst performing model,", "tokens": [ 51514, 2621, 5855, 10205, 2316, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.2295454590158029, "compression_ratio": 1.5045454545454546, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 4983.06, "end": 4983.42, "word": " Our", "probability": 0.6904296875 }, { "start": 4983.42, "end": 4983.92, "word": " worst", "probability": 0.892578125 }, { "start": 4983.92, "end": 4984.3, "word": " performing", "probability": 0.57568359375 }, { "start": 4984.3, "end": 4984.62, "word": " model", "probability": 0.8056640625 }, { "start": 4984.62, "end": 4984.76, "word": ",", "probability": 0.9365234375 } ] }, { "id": 1831, "seek": 485878, "start": 4984.76, "end": 4986.72, "text": " our MNB TF-IDF,", "tokens": [ 51614, 527, 376, 45, 33, 40964, 12, 2777, 37, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.2295454590158029, "compression_ratio": 1.5045454545454546, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 4984.76, "end": 4984.84, "word": " our", "probability": 0.77099609375 }, { "start": 4984.84, "end": 4985.26, "word": " MNB", "probability": 0.7923177083333334 }, { "start": 4985.26, "end": 4985.62, "word": " TF", "probability": 0.521484375 }, { "start": 4985.62, "end": 4986.12, "word": "-IDF", "probability": 0.85400390625 }, { "start": 4986.12, "end": 4986.72, "word": ",", "probability": 0.93408203125 } ] }, { "id": 1832, "seek": 485878, "start": 4986.72, "end": 4989.48, "text": " which was 87.5% accurate,", "tokens": [ 51714, 597, 390, 27990, 13, 20, 4, 8559, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.2295454590158029, "compression_ratio": 1.5045454545454546, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 4986.72, "end": 4987.5, "word": " which", "probability": 0.9111328125 }, { "start": 4987.5, "end": 4987.64, "word": " was", "probability": 0.865234375 }, { "start": 4987.64, "end": 4988.04, "word": " 87", "probability": 0.86865234375 }, { "start": 4988.04, "end": 4988.62, "word": ".5", "probability": 0.997802734375 }, { "start": 4988.62, "end": 4988.86, "word": "%", "probability": 0.916015625 }, { "start": 4988.86, "end": 4989.34, "word": " accurate", "probability": 0.6943359375 }, { "start": 4989.34, "end": 4989.48, "word": ",", "probability": 0.88037109375 } ] }, { "id": 1833, "seek": 488804, "start": 4990.52, "end": 4992.9, "text": " misclassified this email as being legitimate,", "tokens": [ 50364, 3346, 11665, 2587, 341, 3796, 382, 885, 17956, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.1794610437059748, "compression_ratio": 1.739622641509434, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 4990.52, "end": 4990.96, "word": " misclassified", "probability": 0.7059733072916666 }, { "start": 4990.96, "end": 4991.22, "word": " this", "probability": 0.8427734375 }, { "start": 4991.22, "end": 4991.54, "word": " email", "probability": 0.84033203125 }, { "start": 4991.54, "end": 4992.02, "word": " as", "probability": 0.9072265625 }, { "start": 4992.02, "end": 4992.34, "word": " being", "probability": 0.78955078125 }, { "start": 4992.34, "end": 4992.76, "word": " legitimate", "probability": 0.70361328125 }, { "start": 4992.76, "end": 4992.9, "word": ",", "probability": 0.4658203125 } ] }, { "id": 1834, "seek": 488804, "start": 4992.9, "end": 4994.0, "text": " as a ham email.", "tokens": [ 50514, 382, 257, 7852, 3796, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.1794610437059748, "compression_ratio": 1.739622641509434, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 4992.9, "end": 4993.0, "word": " as", "probability": 0.818359375 }, { "start": 4993.12, "end": 4993.36, "word": " a ham", "probability": 0.488525390625 }, { "start": 4993.36, "end": 4993.78, "word": " email", "probability": 0.89111328125 }, { "start": 4993.78, "end": 4994.0, "word": ".", "probability": 0.63818359375 } ] }, { "id": 1835, "seek": 488804, "start": 4994.24, "end": 4995.6, "text": " But the other three of ours", "tokens": [ 50614, 583, 264, 661, 1045, 295, 11896, 50664 ], "temperature": 0.0, "avg_logprob": -0.1794610437059748, "compression_ratio": 1.739622641509434, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 4994.24, "end": 4994.68, "word": " But", "probability": 0.7763671875 }, { "start": 4994.68, "end": 4994.76, "word": " the", "probability": 0.7919921875 }, { "start": 4994.76, "end": 4994.92, "word": " other", "probability": 0.7919921875 }, { "start": 4994.92, "end": 4995.18, "word": " three", "probability": 0.68798828125 }, { "start": 4995.18, "end": 4995.32, "word": " of", "probability": 0.9013671875 }, { "start": 4995.32, "end": 4995.6, "word": " ours", "probability": 0.6865234375 } ] }, { "id": 1836, "seek": 488804, "start": 4995.6, "end": 4998.1, "text": " classified this correctly as a spam email.", "tokens": [ 50664, 20627, 341, 8944, 382, 257, 24028, 3796, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.1794610437059748, "compression_ratio": 1.739622641509434, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 4995.6, "end": 4996.06, "word": " classified", "probability": 0.7451171875 }, { "start": 4996.06, "end": 4996.34, "word": " this", "probability": 0.8701171875 }, { "start": 4996.34, "end": 4996.74, "word": " correctly", "probability": 0.8203125 }, { "start": 4996.74, "end": 4996.92, "word": " as", "probability": 0.86962890625 }, { "start": 4997.06, "end": 4997.3, "word": " a spam", "probability": 0.9091796875 }, { "start": 4997.3, "end": 4997.66, "word": " email", "probability": 0.90087890625 }, { "start": 4997.66, "end": 4998.1, "word": ".", "probability": 0.94677734375 } ] }, { "id": 1837, "seek": 488804, "start": 4998.74, "end": 5000.7, "text": " So there's a couple things we can do with this.", "tokens": [ 50814, 407, 456, 311, 257, 1916, 721, 321, 393, 360, 365, 341, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.1794610437059748, "compression_ratio": 1.739622641509434, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 4998.74, "end": 4999.18, "word": " So", "probability": 0.64208984375 }, { "start": 4999.18, "end": 4999.44, "word": " there's", "probability": 0.791748046875 }, { "start": 4999.52, "end": 4999.62, "word": " a couple", "probability": 0.791015625 }, { "start": 4999.62, "end": 4999.82, "word": " things", "probability": 0.5302734375 }, { "start": 4999.82, "end": 4999.9, "word": " we", "probability": 0.89892578125 }, { "start": 4999.9, "end": 5000.0, "word": " can", "probability": 0.8916015625 }, { "start": 5000.0, "end": 5000.12, "word": " do", "probability": 0.9033203125 }, { "start": 5000.12, "end": 5000.24, "word": " with", "probability": 0.81005859375 }, { "start": 5000.24, "end": 5000.52, "word": " this", "probability": 0.8798828125 }, { "start": 5000.52, "end": 5000.7, "word": ".", "probability": 0.79052734375 } ] }, { "id": 1838, "seek": 488804, "start": 5000.7, "end": 5002.38, "text": " If we were so inclined,", "tokens": [ 50914, 759, 321, 645, 370, 28173, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.1794610437059748, "compression_ratio": 1.739622641509434, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 5000.7, "end": 5001.08, "word": " If", "probability": 0.8642578125 }, { "start": 5001.08, "end": 5001.24, "word": " we", "probability": 0.8994140625 }, { "start": 5001.24, "end": 5001.44, "word": " were", "probability": 0.861328125 }, { "start": 5001.44, "end": 5001.7, "word": " so", "probability": 0.8896484375 }, { "start": 5001.7, "end": 5002.14, "word": " inclined", "probability": 0.80322265625 }, { "start": 5002.14, "end": 5002.38, "word": ",", "probability": 0.72412109375 } ] }, { "id": 1839, "seek": 488804, "start": 5002.38, "end": 5004.54, "text": " we can use what's called ensemble learning,", "tokens": [ 51014, 321, 393, 764, 437, 311, 1219, 19492, 2539, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.1794610437059748, "compression_ratio": 1.739622641509434, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 5002.38, "end": 5002.5, "word": " we", "probability": 0.900390625 }, { "start": 5002.5, "end": 5002.7, "word": " can", "probability": 0.875 }, { "start": 5002.7, "end": 5003.02, "word": " use", "probability": 0.8115234375 }, { "start": 5003.02, "end": 5003.22, "word": " what's", "probability": 0.923095703125 }, { "start": 5003.22, "end": 5003.46, "word": " called", "probability": 0.81982421875 }, { "start": 5003.46, "end": 5003.88, "word": " ensemble", "probability": 0.4404296875 }, { "start": 5003.88, "end": 5004.22, "word": " learning", "probability": 0.83203125 }, { "start": 5004.22, "end": 5004.54, "word": ",", "probability": 0.7021484375 } ] }, { "id": 1840, "seek": 488804, "start": 5004.54, "end": 5007.38, "text": " which we use all four algorithms.", "tokens": [ 51114, 597, 321, 764, 439, 1451, 14642, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.1794610437059748, "compression_ratio": 1.739622641509434, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 5004.54, "end": 5004.8, "word": " which", "probability": 0.85107421875 }, { "start": 5004.8, "end": 5006.0, "word": " we", "probability": 0.7861328125 }, { "start": 5006.0, "end": 5006.16, "word": " use", "probability": 0.81494140625 }, { "start": 5006.16, "end": 5006.36, "word": " all", "probability": 0.89990234375 }, { "start": 5006.36, "end": 5006.66, "word": " four", "probability": 0.87109375 }, { "start": 5006.66, "end": 5007.16, "word": " algorithms", "probability": 0.873046875 }, { "start": 5007.16, "end": 5007.38, "word": ".", "probability": 0.41162109375 } ] }, { "id": 1841, "seek": 488804, "start": 5007.38, "end": 5009.12, "text": " We take the average of them,", "tokens": [ 51264, 492, 747, 264, 4274, 295, 552, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.1794610437059748, "compression_ratio": 1.739622641509434, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 5007.38, "end": 5007.4, "word": " We", "probability": 0.89306640625 }, { "start": 5007.4, "end": 5007.58, "word": " take", "probability": 0.81591796875 }, { "start": 5007.58, "end": 5007.74, "word": " the", "probability": 0.81103515625 }, { "start": 5007.74, "end": 5008.04, "word": " average", "probability": 0.6806640625 }, { "start": 5008.04, "end": 5008.24, "word": " of", "probability": 0.89697265625 }, { "start": 5008.24, "end": 5008.58, "word": " them", "probability": 0.74072265625 }, { "start": 5008.58, "end": 5009.12, "word": ",", "probability": 0.34228515625 } ] }, { "id": 1842, "seek": 488804, "start": 5009.12, "end": 5011.24, "text": " or in other words,", "tokens": [ 51364, 420, 294, 661, 2283, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.1794610437059748, "compression_ratio": 1.739622641509434, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 5009.12, "end": 5009.52, "word": " or", "probability": 0.417236328125 }, { "start": 5009.52, "end": 5010.78, "word": " in", "probability": 0.7822265625 }, { "start": 5010.78, "end": 5010.96, "word": " other", "probability": 0.783203125 }, { "start": 5010.96, "end": 5011.16, "word": " words", "probability": 0.72265625 }, { "start": 5011.16, "end": 5011.24, "word": ",", "probability": 0.8720703125 } ] }, { "id": 1843, "seek": 488804, "start": 5011.24, "end": 5014.82, "text": " they give a vote on what they think the class is.", "tokens": [ 51464, 436, 976, 257, 4740, 322, 437, 436, 519, 264, 1508, 307, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.1794610437059748, "compression_ratio": 1.739622641509434, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 5011.24, "end": 5011.46, "word": " they", "probability": 0.73193359375 }, { "start": 5011.46, "end": 5011.62, "word": " give", "probability": 0.8193359375 }, { "start": 5011.78, "end": 5012.08, "word": " a vote", "probability": 0.87646484375 }, { "start": 5012.08, "end": 5012.72, "word": " on", "probability": 0.88671875 }, { "start": 5012.72, "end": 5013.02, "word": " what", "probability": 0.88525390625 }, { "start": 5013.02, "end": 5013.22, "word": " they", "probability": 0.732421875 }, { "start": 5013.22, "end": 5013.5, "word": " think", "probability": 0.802734375 }, { "start": 5013.5, "end": 5013.66, "word": " the", "probability": 0.81201171875 }, { "start": 5013.66, "end": 5013.96, "word": " class", "probability": 0.90966796875 }, { "start": 5013.96, "end": 5014.38, "word": " is", "probability": 0.908203125 }, { "start": 5014.38, "end": 5014.82, "word": ".", "probability": 0.6064453125 } ] }, { "id": 1844, "seek": 488804, "start": 5014.82, "end": 5016.42, "text": " And then in this case,", "tokens": [ 51614, 400, 550, 294, 341, 1389, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.1794610437059748, "compression_ratio": 1.739622641509434, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 5014.82, "end": 5014.88, "word": " And", "probability": 0.7724609375 }, { "start": 5014.88, "end": 5015.2, "word": " then", "probability": 0.716796875 }, { "start": 5015.2, "end": 5015.98, "word": " in", "probability": 0.712890625 }, { "start": 5015.98, "end": 5016.14, "word": " this", "probability": 0.87939453125 }, { "start": 5016.14, "end": 5016.36, "word": " case", "probability": 0.81005859375 }, { "start": 5016.36, "end": 5016.42, "word": ",", "probability": 0.8681640625 } ] }, { "id": 1845, "seek": 488804, "start": 5016.42, "end": 5017.82, "text": " three out of the four say it's spam,", "tokens": [ 51714, 1045, 484, 295, 264, 1451, 584, 309, 311, 24028, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.1794610437059748, "compression_ratio": 1.739622641509434, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 5016.42, "end": 5016.58, "word": " three", "probability": 0.802734375 }, { "start": 5016.58, "end": 5016.7, "word": " out", "probability": 0.77587890625 }, { "start": 5016.7, "end": 5016.76, "word": " of", "probability": 0.90283203125 }, { "start": 5016.76, "end": 5016.88, "word": " the", "probability": 0.80859375 }, { "start": 5016.88, "end": 5017.08, "word": " four", "probability": 0.8876953125 }, { "start": 5017.08, "end": 5017.28, "word": " say", "probability": 0.8076171875 }, { "start": 5017.28, "end": 5017.42, "word": " it's", "probability": 0.925537109375 }, { "start": 5017.42, "end": 5017.72, "word": " spam", "probability": 0.90625 }, { "start": 5017.72, "end": 5017.82, "word": ",", "probability": 0.7294921875 } ] }, { "id": 1846, "seek": 488804, "start": 5017.82, "end": 5018.74, "text": " so it would be spam.", "tokens": [ 51764, 370, 309, 576, 312, 24028, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.1794610437059748, "compression_ratio": 1.739622641509434, "no_speech_prob": 0.00039196014404296875, "words": [ { "start": 5017.82, "end": 5017.9, "word": " so", "probability": 0.888671875 }, { "start": 5017.9, "end": 5017.98, "word": " it", "probability": 0.8984375 }, { "start": 5017.98, "end": 5018.06, "word": " would", "probability": 0.83154296875 }, { "start": 5018.06, "end": 5018.2, "word": " be", "probability": 0.89111328125 }, { "start": 5018.2, "end": 5018.52, "word": " spam", "probability": 0.90576171875 }, { "start": 5018.52, "end": 5018.74, "word": ".", "probability": 0.82177734375 } ] }, { "id": 1847, "seek": 491604, "start": 5018.74, "end": 5022.24, "text": " Or we can use this as an example and say,", "tokens": [ 50364, 1610, 321, 393, 764, 341, 382, 364, 1365, 293, 584, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.16032986525032256, "compression_ratio": 1.3763440860215055, "no_speech_prob": 0.00022339820861816406, "words": [ { "start": 5018.74, "end": 5019.26, "word": " Or", "probability": 0.491455078125 }, { "start": 5019.26, "end": 5019.36, "word": " we", "probability": 0.84912109375 }, { "start": 5019.36, "end": 5019.48, "word": " can", "probability": 0.890625 }, { "start": 5019.48, "end": 5019.68, "word": " use", "probability": 0.81494140625 }, { "start": 5019.68, "end": 5019.9, "word": " this", "probability": 0.87744140625 }, { "start": 5019.9, "end": 5020.32, "word": " as", "probability": 0.8955078125 }, { "start": 5020.32, "end": 5021.16, "word": " an", "probability": 0.8037109375 }, { "start": 5021.16, "end": 5021.58, "word": " example", "probability": 0.9267578125 }, { "start": 5021.58, "end": 5021.86, "word": " and", "probability": 0.82080078125 }, { "start": 5021.86, "end": 5022.08, "word": " say", "probability": 0.90234375 }, { "start": 5022.08, "end": 5022.24, "word": ",", "probability": 0.6875 } ] }, { "id": 1848, "seek": 491604, "start": 5022.24, "end": 5024.42, "text": " hey, the MNB TF-IDF,", "tokens": [ 50514, 4177, 11, 264, 376, 45, 33, 40964, 12, 2777, 37, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.16032986525032256, "compression_ratio": 1.3763440860215055, "no_speech_prob": 0.00022339820861816406, "words": [ { "start": 5022.24, "end": 5022.46, "word": " hey", "probability": 0.345703125 }, { "start": 5022.46, "end": 5022.96, "word": ",", "probability": 0.8037109375 }, { "start": 5022.96, "end": 5023.16, "word": " the", "probability": 0.7978515625 }, { "start": 5023.16, "end": 5023.58, "word": " MNB", "probability": 0.6079915364583334 }, { "start": 5023.58, "end": 5023.9, "word": " TF", "probability": 0.37255859375 }, { "start": 5023.9, "end": 5024.34, "word": "-IDF", "probability": 0.82080078125 }, { "start": 5024.34, "end": 5024.42, "word": ",", "probability": 0.73388671875 } ] }, { "id": 1849, "seek": 491604, "start": 5024.42, "end": 5025.68, "text": " we probably shouldn't use that", "tokens": [ 50614, 321, 1391, 4659, 380, 764, 300, 50714 ], "temperature": 0.0, "avg_logprob": -0.16032986525032256, "compression_ratio": 1.3763440860215055, "no_speech_prob": 0.00022339820861816406, "words": [ { "start": 5024.42, "end": 5024.5, "word": " we", "probability": 0.859375 }, { "start": 5024.5, "end": 5024.7, "word": " probably", "probability": 0.90234375 }, { "start": 5024.7, "end": 5025.06, "word": " shouldn't", "probability": 0.92822265625 }, { "start": 5025.06, "end": 5025.34, "word": " use", "probability": 0.82275390625 }, { "start": 5025.34, "end": 5025.68, "word": " that", "probability": 0.87744140625 } ] }, { "id": 1850, "seek": 491604, "start": 5025.68, "end": 5027.78, "text": " simply because it's misclassifying", "tokens": [ 50714, 2935, 570, 309, 311, 3346, 11665, 5489, 50814 ], "temperature": 0.0, "avg_logprob": -0.16032986525032256, "compression_ratio": 1.3763440860215055, "no_speech_prob": 0.00022339820861816406, "words": [ { "start": 5025.68, "end": 5026.26, "word": " simply", "probability": 0.630859375 }, { "start": 5026.26, "end": 5026.6, "word": " because", "probability": 0.8349609375 }, { "start": 5026.6, "end": 5026.84, "word": " it's", "probability": 0.94873046875 }, { "start": 5026.84, "end": 5027.78, "word": " misclassifying", "probability": 0.95166015625 } ] }, { "id": 1851, "seek": 491604, "start": 5027.78, "end": 5029.68, "text": " known spam emails", "tokens": [ 50814, 2570, 24028, 12524, 50914 ], "temperature": 0.0, "avg_logprob": -0.16032986525032256, "compression_ratio": 1.3763440860215055, "no_speech_prob": 0.00022339820861816406, "words": [ { "start": 5027.78, "end": 5028.82, "word": " known", "probability": 0.7333984375 }, { "start": 5028.82, "end": 5029.22, "word": " spam", "probability": 0.958984375 }, { "start": 5029.22, "end": 5029.68, "word": " emails", "probability": 0.7578125 } ] }, { "id": 1852, "seek": 491604, "start": 5030.42, "end": 5032.34, "text": " at a high rate.", "tokens": [ 50914, 412, 257, 1090, 3314, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.16032986525032256, "compression_ratio": 1.3763440860215055, "no_speech_prob": 0.00022339820861816406, "words": [ { "start": 5030.42, "end": 5031.14, "word": " at", "probability": 0.85205078125 }, { "start": 5031.34, "end": 5031.58, "word": " a high", "probability": 0.86083984375 }, { "start": 5031.58, "end": 5031.94, "word": " rate", "probability": 0.904296875 }, { "start": 5031.94, "end": 5032.34, "word": ".", "probability": 0.4521484375 } ] }, { "id": 1853, "seek": 491604, "start": 5032.34, "end": 5035.18, "text": " 87% means that we have", "tokens": [ 51014, 27990, 4, 1355, 300, 321, 362, 51164 ], "temperature": 0.0, "avg_logprob": -0.16032986525032256, "compression_ratio": 1.3763440860215055, "no_speech_prob": 0.00022339820861816406, "words": [ { "start": 5032.34, "end": 5032.78, "word": " 87", "probability": 0.673828125 }, { "start": 5032.78, "end": 5033.22, "word": "%", "probability": 0.9599609375 }, { "start": 5033.22, "end": 5034.54, "word": " means", "probability": 0.8701171875 }, { "start": 5034.54, "end": 5034.7, "word": " that", "probability": 0.8759765625 }, { "start": 5034.7, "end": 5034.82, "word": " we", "probability": 0.90380859375 }, { "start": 5034.82, "end": 5035.18, "word": " have", "probability": 0.8818359375 } ] }, { "id": 1854, "seek": 491604, "start": 5035.18, "end": 5038.84, "text": " about a 12.5%", "tokens": [ 51164, 466, 257, 2272, 13, 20, 4, 51364 ], "temperature": 0.0, "avg_logprob": -0.16032986525032256, "compression_ratio": 1.3763440860215055, "no_speech_prob": 0.00022339820861816406, "words": [ { "start": 5035.18, "end": 5036.44, "word": " about", "probability": 0.65966796875 }, { "start": 5036.88, "end": 5037.6, "word": " a 12", "probability": 0.927734375 }, { "start": 5037.6, "end": 5038.18, "word": ".5", "probability": 0.752197265625 }, { "start": 5038.18, "end": 5038.84, "word": "%", "probability": 0.99169921875 } ] }, { "id": 1855, "seek": 491604, "start": 5040.64, "end": 5043.76, "text": " chance of misclassifying spam emails.", "tokens": [ 51464, 2931, 295, 3346, 11665, 5489, 24028, 12524, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.16032986525032256, "compression_ratio": 1.3763440860215055, "no_speech_prob": 0.00022339820861816406, "words": [ { "start": 5040.64, "end": 5041.36, "word": " chance", "probability": 0.908203125 }, { "start": 5041.36, "end": 5041.58, "word": " of", "probability": 0.91162109375 }, { "start": 5041.58, "end": 5042.32, "word": " misclassifying", "probability": 0.9446614583333334 }, { "start": 5042.32, "end": 5042.66, "word": " spam", "probability": 0.9287109375 }, { "start": 5042.66, "end": 5043.04, "word": " emails", "probability": 0.79638671875 }, { "start": 5043.04, "end": 5043.76, "word": ".", "probability": 0.99609375 } ] }, { "id": 1856, "seek": 491604, "start": 5045.02, "end": 5046.74, "text": " So this is kind of", "tokens": [ 51664, 407, 341, 307, 733, 295, 51764 ], "temperature": 0.0, "avg_logprob": -0.16032986525032256, "compression_ratio": 1.3763440860215055, "no_speech_prob": 0.00022339820861816406, "words": [ { "start": 5045.02, "end": 5045.24, "word": " So", "probability": 0.78125 }, { "start": 5045.24, "end": 5046.12, "word": " this", "probability": 0.69970703125 }, { "start": 5046.12, "end": 5046.26, "word": " is", "probability": 0.90966796875 }, { "start": 5046.26, "end": 5046.46, "word": " kind", "probability": 0.576171875 }, { "start": 5046.46, "end": 5046.74, "word": " of", "probability": 0.9091796875 } ] }, { "id": 1857, "seek": 494426, "start": 5046.74, "end": 5048.96, "text": " pretty close to the conclusion of the workshop.", "tokens": [ 50364, 1238, 1998, 281, 264, 10063, 295, 264, 13541, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.19274808750807784, "compression_ratio": 1.754863813229572, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 5046.74, "end": 5047.44, "word": " pretty", "probability": 0.1033935546875 }, { "start": 5047.44, "end": 5047.68, "word": " close", "probability": 0.8310546875 }, { "start": 5047.68, "end": 5047.78, "word": " to", "probability": 0.9013671875 }, { "start": 5047.78, "end": 5047.88, "word": " the", "probability": 0.8125 }, { "start": 5047.88, "end": 5048.2, "word": " conclusion", "probability": 0.81103515625 }, { "start": 5048.2, "end": 5048.32, "word": " of", "probability": 0.869140625 }, { "start": 5048.32, "end": 5048.42, "word": " the", "probability": 0.81298828125 }, { "start": 5048.42, "end": 5048.72, "word": " workshop", "probability": 0.68017578125 }, { "start": 5048.72, "end": 5048.96, "word": ".", "probability": 0.7001953125 } ] }, { "id": 1858, "seek": 494426, "start": 5048.96, "end": 5050.38, "text": " This shows how you can take", "tokens": [ 50464, 639, 3110, 577, 291, 393, 747, 50564 ], "temperature": 0.0, "avg_logprob": -0.19274808750807784, "compression_ratio": 1.754863813229572, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 5048.96, "end": 5049.08, "word": " This", "probability": 0.79248046875 }, { "start": 5049.08, "end": 5049.38, "word": " shows", "probability": 0.79833984375 }, { "start": 5049.38, "end": 5049.62, "word": " how", "probability": 0.8828125 }, { "start": 5049.62, "end": 5049.76, "word": " you", "probability": 0.89697265625 }, { "start": 5049.76, "end": 5049.9, "word": " can", "probability": 0.89453125 }, { "start": 5049.9, "end": 5050.38, "word": " take", "probability": 0.794921875 } ] }, { "id": 1859, "seek": 494426, "start": 5050.38, "end": 5052.54, "text": " raw emails, raw data,", "tokens": [ 50564, 8936, 12524, 11, 8936, 1412, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.19274808750807784, "compression_ratio": 1.754863813229572, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 5050.38, "end": 5051.12, "word": " raw", "probability": 0.72802734375 }, { "start": 5051.12, "end": 5051.44, "word": " emails", "probability": 0.50341796875 }, { "start": 5051.44, "end": 5051.58, "word": ",", "probability": 0.81787109375 }, { "start": 5051.58, "end": 5051.76, "word": " raw", "probability": 0.765625 }, { "start": 5051.76, "end": 5052.2, "word": " data", "probability": 0.79931640625 }, { "start": 5052.2, "end": 5052.54, "word": ",", "probability": 0.90283203125 } ] }, { "id": 1860, "seek": 494426, "start": 5052.54, "end": 5054.1, "text": " transform it in a way", "tokens": [ 50614, 4088, 309, 294, 257, 636, 50714 ], "temperature": 0.0, "avg_logprob": -0.19274808750807784, "compression_ratio": 1.754863813229572, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 5052.54, "end": 5053.04, "word": " transform", "probability": 0.85791015625 }, { "start": 5053.04, "end": 5053.52, "word": " it", "probability": 0.89794921875 }, { "start": 5053.52, "end": 5053.72, "word": " in", "probability": 0.88330078125 }, { "start": 5053.84, "end": 5054.1, "word": " a way", "probability": 0.90087890625 } ] }, { "id": 1861, "seek": 494426, "start": 5054.1, "end": 5055.3, "text": " that can be used in", "tokens": [ 50714, 300, 393, 312, 1143, 294, 50814 ], "temperature": 0.0, "avg_logprob": -0.19274808750807784, "compression_ratio": 1.754863813229572, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 5054.1, "end": 5054.34, "word": " that", "probability": 0.87939453125 }, { "start": 5054.34, "end": 5054.48, "word": " can", "probability": 0.82177734375 }, { "start": 5054.48, "end": 5054.6, "word": " be", "probability": 0.90576171875 }, { "start": 5054.6, "end": 5054.88, "word": " used", "probability": 0.8203125 }, { "start": 5054.88, "end": 5055.3, "word": " in", "probability": 0.89697265625 } ] }, { "id": 1862, "seek": 494426, "start": 5055.78, "end": 5057.52, "text": " machine learning models.", "tokens": [ 50814, 3479, 2539, 5245, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.19274808750807784, "compression_ratio": 1.754863813229572, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 5055.78, "end": 5056.26, "word": " machine", "probability": 0.67236328125 }, { "start": 5056.26, "end": 5056.58, "word": " learning", "probability": 0.81396484375 }, { "start": 5056.58, "end": 5057.04, "word": " models", "probability": 0.78271484375 }, { "start": 5057.04, "end": 5057.52, "word": ".", "probability": 0.4375 } ] }, { "id": 1863, "seek": 494426, "start": 5057.72, "end": 5059.8, "text": " And then we build out our machine learning models,", "tokens": [ 50914, 400, 550, 321, 1322, 484, 527, 3479, 2539, 5245, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.19274808750807784, "compression_ratio": 1.754863813229572, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 5057.72, "end": 5057.88, "word": " And", "probability": 0.80224609375 }, { "start": 5057.88, "end": 5058.08, "word": " then", "probability": 0.72314453125 }, { "start": 5058.08, "end": 5058.28, "word": " we", "probability": 0.84814453125 }, { "start": 5058.28, "end": 5058.48, "word": " build", "probability": 0.833984375 }, { "start": 5058.48, "end": 5058.62, "word": " out", "probability": 0.80322265625 }, { "start": 5058.62, "end": 5058.72, "word": " our", "probability": 0.8125 }, { "start": 5058.72, "end": 5058.96, "word": " machine", "probability": 0.724609375 }, { "start": 5058.96, "end": 5059.22, "word": " learning", "probability": 0.82958984375 }, { "start": 5059.22, "end": 5059.62, "word": " models", "probability": 0.791015625 }, { "start": 5059.62, "end": 5059.8, "word": ",", "probability": 0.6708984375 } ] }, { "id": 1864, "seek": 494426, "start": 5059.8, "end": 5060.88, "text": " we evaluate them,", "tokens": [ 51014, 321, 13059, 552, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.19274808750807784, "compression_ratio": 1.754863813229572, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 5059.8, "end": 5059.92, "word": " we", "probability": 0.8955078125 }, { "start": 5059.92, "end": 5060.32, "word": " evaluate", "probability": 0.76171875 }, { "start": 5060.32, "end": 5060.8, "word": " them", "probability": 0.74658203125 }, { "start": 5060.8, "end": 5060.88, "word": ",", "probability": 0.66357421875 } ] }, { "id": 1865, "seek": 494426, "start": 5060.88, "end": 5062.66, "text": " and we can test them.", "tokens": [ 51064, 293, 321, 393, 1500, 552, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.19274808750807784, "compression_ratio": 1.754863813229572, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 5060.88, "end": 5061.18, "word": " and", "probability": 0.8916015625 }, { "start": 5061.18, "end": 5061.4, "word": " we", "probability": 0.90185546875 }, { "start": 5061.4, "end": 5061.56, "word": " can", "probability": 0.84521484375 }, { "start": 5061.56, "end": 5061.84, "word": " test", "probability": 0.82421875 }, { "start": 5061.84, "end": 5062.18, "word": " them", "probability": 0.74365234375 }, { "start": 5062.18, "end": 5062.66, "word": ".", "probability": 0.91796875 } ] }, { "id": 1866, "seek": 494426, "start": 5062.66, "end": 5064.02, "text": " And this last task shows you", "tokens": [ 51164, 400, 341, 1036, 5633, 3110, 291, 51214 ], "temperature": 0.0, "avg_logprob": -0.19274808750807784, "compression_ratio": 1.754863813229572, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 5062.66, "end": 5062.78, "word": " And", "probability": 0.80224609375 }, { "start": 5062.78, "end": 5062.94, "word": " this", "probability": 0.87255859375 }, { "start": 5062.94, "end": 5063.2, "word": " last", "probability": 0.8173828125 }, { "start": 5063.2, "end": 5063.5, "word": " task", "probability": 0.82177734375 }, { "start": 5063.5, "end": 5063.8, "word": " shows", "probability": 0.802734375 }, { "start": 5063.8, "end": 5064.02, "word": " you", "probability": 0.8935546875 } ] }, { "id": 1867, "seek": 494426, "start": 5064.02, "end": 5066.22, "text": " how we can properly deploy them.", "tokens": [ 51214, 577, 321, 393, 6108, 7274, 552, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.19274808750807784, "compression_ratio": 1.754863813229572, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 5064.02, "end": 5064.38, "word": " how", "probability": 0.90283203125 }, { "start": 5064.38, "end": 5064.76, "word": " we", "probability": 0.90234375 }, { "start": 5064.76, "end": 5065.06, "word": " can", "probability": 0.89453125 }, { "start": 5065.06, "end": 5065.44, "word": " properly", "probability": 0.8369140625 }, { "start": 5065.44, "end": 5065.82, "word": " deploy", "probability": 0.72412109375 }, { "start": 5065.82, "end": 5066.08, "word": " them", "probability": 0.74072265625 }, { "start": 5066.08, "end": 5066.22, "word": ".", "probability": 0.888671875 } ] }, { "id": 1868, "seek": 494426, "start": 5066.22, "end": 5068.08, "text": " So we can build a piece of software", "tokens": [ 51314, 407, 321, 393, 1322, 257, 2522, 295, 4722, 51414 ], "temperature": 0.0, "avg_logprob": -0.19274808750807784, "compression_ratio": 1.754863813229572, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 5066.22, "end": 5066.42, "word": " So", "probability": 0.85205078125 }, { "start": 5066.42, "end": 5067.22, "word": " we", "probability": 0.72705078125 }, { "start": 5067.22, "end": 5067.32, "word": " can", "probability": 0.87353515625 }, { "start": 5067.32, "end": 5067.44, "word": " build", "probability": 0.86328125 }, { "start": 5067.54, "end": 5067.66, "word": " a piece", "probability": 0.8134765625 }, { "start": 5067.66, "end": 5067.8, "word": " of", "probability": 0.9033203125 }, { "start": 5067.8, "end": 5068.08, "word": " software", "probability": 0.845703125 } ] }, { "id": 1869, "seek": 494426, "start": 5068.08, "end": 5069.24, "text": " or an application around it", "tokens": [ 51414, 420, 364, 3861, 926, 309, 51464 ], "temperature": 0.0, "avg_logprob": -0.19274808750807784, "compression_ratio": 1.754863813229572, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 5068.08, "end": 5068.24, "word": " or", "probability": 0.1317138671875 }, { "start": 5068.24, "end": 5068.32, "word": " an", "probability": 0.87548828125 }, { "start": 5068.32, "end": 5068.72, "word": " application", "probability": 0.76220703125 }, { "start": 5068.72, "end": 5069.08, "word": " around", "probability": 0.87548828125 }, { "start": 5069.08, "end": 5069.24, "word": " it", "probability": 0.8955078125 } ] }, { "id": 1870, "seek": 494426, "start": 5069.24, "end": 5070.82, "text": " and say every time we get an email,", "tokens": [ 51464, 293, 584, 633, 565, 321, 483, 364, 3796, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.19274808750807784, "compression_ratio": 1.754863813229572, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 5069.24, "end": 5069.34, "word": " and", "probability": 0.6083984375 }, { "start": 5069.34, "end": 5069.48, "word": " say", "probability": 0.8671875 }, { "start": 5069.48, "end": 5069.64, "word": " every", "probability": 0.53564453125 }, { "start": 5069.64, "end": 5069.78, "word": " time", "probability": 0.8076171875 }, { "start": 5069.78, "end": 5069.9, "word": " we", "probability": 0.900390625 }, { "start": 5069.9, "end": 5070.0, "word": " get", "probability": 0.9072265625 }, { "start": 5070.0, "end": 5070.18, "word": " an", "probability": 0.896484375 }, { "start": 5070.18, "end": 5070.58, "word": " email", "probability": 0.91162109375 }, { "start": 5070.58, "end": 5070.82, "word": ",", "probability": 0.794921875 } ] }, { "id": 1871, "seek": 494426, "start": 5072.18, "end": 5073.5, "text": " just swap out", "tokens": [ 51564, 445, 18135, 484, 51714 ], "temperature": 0.0, "avg_logprob": -0.19274808750807784, "compression_ratio": 1.754863813229572, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 5072.18, "end": 5072.66, "word": " just", "probability": 0.87646484375 }, { "start": 5072.66, "end": 5073.14, "word": " swap", "probability": 0.92041015625 }, { "start": 5073.14, "end": 5073.5, "word": " out", "probability": 0.82177734375 } ] }, { "id": 1872, "seek": 494426, "start": 5073.5, "end": 5074.96, "text": " this working email,", "tokens": [ 51714, 341, 1364, 3796, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.19274808750807784, "compression_ratio": 1.754863813229572, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 5073.5, "end": 5074.18, "word": " this", "probability": 0.884765625 }, { "start": 5074.18, "end": 5074.52, "word": " working", "probability": 0.68408203125 }, { "start": 5074.52, "end": 5074.88, "word": " email", "probability": 0.91259765625 }, { "start": 5074.88, "end": 5074.96, "word": ",", "probability": 0.355712890625 } ] }, { "id": 1873, "seek": 497266, "start": 5074.96, "end": 5077.58, "text": " and then you can leave everything else the same.", "tokens": [ 50364, 293, 550, 291, 393, 1856, 1203, 1646, 264, 912, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.1956623065382687, "compression_ratio": 1.6785714285714286, "no_speech_prob": 0.0083160400390625, "words": [ { "start": 5074.96, "end": 5075.12, "word": " and", "probability": 0.6650390625 }, { "start": 5075.12, "end": 5075.24, "word": " then", "probability": 0.65673828125 }, { "start": 5075.24, "end": 5075.34, "word": " you", "probability": 0.87841796875 }, { "start": 5075.34, "end": 5075.44, "word": " can", "probability": 0.892578125 }, { "start": 5075.44, "end": 5075.7, "word": " leave", "probability": 0.89501953125 }, { "start": 5075.7, "end": 5076.14, "word": " everything", "probability": 0.8779296875 }, { "start": 5076.14, "end": 5076.46, "word": " else", "probability": 0.84228515625 }, { "start": 5076.46, "end": 5076.86, "word": " the", "probability": 0.802734375 }, { "start": 5076.86, "end": 5077.18, "word": " same", "probability": 0.81787109375 }, { "start": 5077.18, "end": 5077.58, "word": ".", "probability": 0.96533203125 } ] }, { "id": 1874, "seek": 497266, "start": 5078.8, "end": 5079.96, "text": " Now, before I let you go,", "tokens": [ 50514, 823, 11, 949, 286, 718, 291, 352, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.1956623065382687, "compression_ratio": 1.6785714285714286, "no_speech_prob": 0.0083160400390625, "words": [ { "start": 5078.8, "end": 5078.94, "word": " Now", "probability": 0.63330078125 }, { "start": 5078.94, "end": 5079.12, "word": ",", "probability": 0.4814453125 }, { "start": 5079.12, "end": 5079.42, "word": " before", "probability": 0.79833984375 }, { "start": 5079.42, "end": 5079.52, "word": " I", "probability": 0.97314453125 }, { "start": 5079.52, "end": 5079.62, "word": " let", "probability": 0.900390625 }, { "start": 5079.62, "end": 5079.7, "word": " you", "probability": 0.90185546875 }, { "start": 5079.7, "end": 5079.88, "word": " go", "probability": 0.90869140625 }, { "start": 5079.88, "end": 5079.96, "word": ",", "probability": 0.7666015625 } ] }, { "id": 1875, "seek": 497266, "start": 5079.96, "end": 5081.9, "text": " there's one more thing that I want to show you.", "tokens": [ 50614, 456, 311, 472, 544, 551, 300, 286, 528, 281, 855, 291, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.1956623065382687, "compression_ratio": 1.6785714285714286, "no_speech_prob": 0.0083160400390625, "words": [ { "start": 5079.96, "end": 5080.12, "word": " there's", "probability": 0.902587890625 }, { "start": 5080.12, "end": 5080.3, "word": " one", "probability": 0.8271484375 }, { "start": 5080.3, "end": 5080.44, "word": " more", "probability": 0.875 }, { "start": 5080.44, "end": 5080.64, "word": " thing", "probability": 0.8134765625 }, { "start": 5080.64, "end": 5080.76, "word": " that", "probability": 0.7900390625 }, { "start": 5080.76, "end": 5080.84, "word": " I", "probability": 0.9951171875 }, { "start": 5080.84, "end": 5080.96, "word": " want", "probability": 0.716796875 }, { "start": 5080.96, "end": 5081.06, "word": " to", "probability": 0.90869140625 }, { "start": 5081.06, "end": 5081.26, "word": " show", "probability": 0.87646484375 }, { "start": 5081.26, "end": 5081.52, "word": " you", "probability": 0.89208984375 }, { "start": 5081.52, "end": 5081.9, "word": ".", "probability": 0.95166015625 } ] }, { "id": 1876, "seek": 497266, "start": 5082.26, "end": 5084.44, "text": " I mentioned hyperparameter tuning.", "tokens": [ 50714, 286, 2835, 9848, 2181, 335, 2398, 15164, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.1956623065382687, "compression_ratio": 1.6785714285714286, "no_speech_prob": 0.0083160400390625, "words": [ { "start": 5082.26, "end": 5082.66, "word": " I", "probability": 0.99169921875 }, { "start": 5082.66, "end": 5082.94, "word": " mentioned", "probability": 0.75439453125 }, { "start": 5082.94, "end": 5083.8, "word": " hyperparameter", "probability": 0.9315185546875 }, { "start": 5083.8, "end": 5084.14, "word": " tuning", "probability": 0.8115234375 }, { "start": 5084.14, "end": 5084.44, "word": ".", "probability": 0.413818359375 } ] }, { "id": 1877, "seek": 497266, "start": 5084.44, "end": 5086.0, "text": " So let's take a look and see", "tokens": [ 50814, 407, 718, 311, 747, 257, 574, 293, 536, 50914 ], "temperature": 0.0, "avg_logprob": -0.1956623065382687, "compression_ratio": 1.6785714285714286, "no_speech_prob": 0.0083160400390625, "words": [ { "start": 5084.44, "end": 5084.6, "word": " So", "probability": 0.2088623046875 }, { "start": 5084.6, "end": 5084.9, "word": " let's", "probability": 0.849853515625 }, { "start": 5084.9, "end": 5085.1, "word": " take", "probability": 0.8095703125 }, { "start": 5085.24, "end": 5085.44, "word": " a look", "probability": 0.91552734375 }, { "start": 5085.44, "end": 5085.64, "word": " and", "probability": 0.8623046875 }, { "start": 5085.64, "end": 5086.0, "word": " see", "probability": 0.810546875 } ] }, { "id": 1878, "seek": 497266, "start": 5086.0, "end": 5088.62, "text": " what hyperparameter tuning can do.", "tokens": [ 50914, 437, 9848, 2181, 335, 2398, 15164, 393, 360, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.1956623065382687, "compression_ratio": 1.6785714285714286, "no_speech_prob": 0.0083160400390625, "words": [ { "start": 5086.0, "end": 5086.36, "word": " what", "probability": 0.88330078125 }, { "start": 5086.36, "end": 5087.14, "word": " hyperparameter", "probability": 0.9771728515625 }, { "start": 5087.14, "end": 5087.5, "word": " tuning", "probability": 0.828125 }, { "start": 5087.5, "end": 5087.82, "word": " can", "probability": 0.89453125 }, { "start": 5087.82, "end": 5088.22, "word": " do", "probability": 0.904296875 }, { "start": 5088.22, "end": 5088.62, "word": ".", "probability": 0.98876953125 } ] }, { "id": 1879, "seek": 497266, "start": 5088.98, "end": 5090.06, "text": " So when we were talking about", "tokens": [ 51014, 407, 562, 321, 645, 1417, 466, 51114 ], "temperature": 0.0, "avg_logprob": -0.1956623065382687, "compression_ratio": 1.6785714285714286, "no_speech_prob": 0.0083160400390625, "words": [ { "start": 5088.98, "end": 5089.14, "word": " So", "probability": 0.69482421875 }, { "start": 5089.14, "end": 5089.32, "word": " when", "probability": 0.81689453125 }, { "start": 5089.32, "end": 5089.42, "word": " we", "probability": 0.8955078125 }, { "start": 5089.42, "end": 5089.48, "word": " were", "probability": 0.65673828125 }, { "start": 5089.48, "end": 5089.8, "word": " talking", "probability": 0.75634765625 }, { "start": 5089.8, "end": 5090.06, "word": " about", "probability": 0.82373046875 } ] }, { "id": 1880, "seek": 497266, "start": 5090.06, "end": 5091.72, "text": " the multinomial Naive Bayesian,", "tokens": [ 51114, 264, 45872, 47429, 6056, 488, 7840, 42434, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.1956623065382687, "compression_ratio": 1.6785714285714286, "no_speech_prob": 0.0083160400390625, "words": [ { "start": 5090.06, "end": 5090.26, "word": " the", "probability": 0.79931640625 }, { "start": 5090.26, "end": 5090.84, "word": " multinomial", "probability": 0.931884765625 }, { "start": 5090.84, "end": 5091.2, "word": " Naive", "probability": 0.673828125 }, { "start": 5091.2, "end": 5091.6, "word": " Bayesian", "probability": 0.901123046875 }, { "start": 5091.6, "end": 5091.72, "word": ",", "probability": 0.755859375 } ] }, { "id": 1881, "seek": 497266, "start": 5091.72, "end": 5093.56, "text": " we saw that we had that smoothing function,", "tokens": [ 51214, 321, 1866, 300, 321, 632, 300, 899, 6259, 571, 2445, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.1956623065382687, "compression_ratio": 1.6785714285714286, "no_speech_prob": 0.0083160400390625, "words": [ { "start": 5091.72, "end": 5091.82, "word": " we", "probability": 0.8916015625 }, { "start": 5091.82, "end": 5091.96, "word": " saw", "probability": 0.806640625 }, { "start": 5091.96, "end": 5092.06, "word": " that", "probability": 0.833984375 }, { "start": 5092.06, "end": 5092.14, "word": " we", "probability": 0.8935546875 }, { "start": 5092.14, "end": 5092.26, "word": " had", "probability": 0.64892578125 }, { "start": 5092.26, "end": 5092.46, "word": " that", "probability": 0.859375 }, { "start": 5092.46, "end": 5092.98, "word": " smoothing", "probability": 0.9114583333333334 }, { "start": 5092.98, "end": 5093.42, "word": " function", "probability": 0.8759765625 }, { "start": 5093.42, "end": 5093.56, "word": ",", "probability": 0.71728515625 } ] }, { "id": 1882, "seek": 497266, "start": 5093.56, "end": 5095.62, "text": " the alpha, right?", "tokens": [ 51314, 264, 8961, 11, 558, 30, 51414 ], "temperature": 0.0, "avg_logprob": -0.1956623065382687, "compression_ratio": 1.6785714285714286, "no_speech_prob": 0.0083160400390625, "words": [ { "start": 5093.56, "end": 5094.26, "word": " the", "probability": 0.25048828125 }, { "start": 5094.26, "end": 5094.72, "word": " alpha", "probability": 0.69482421875 }, { "start": 5094.72, "end": 5095.04, "word": ",", "probability": 0.6455078125 }, { "start": 5095.04, "end": 5095.22, "word": " right", "probability": 0.6201171875 }, { "start": 5095.22, "end": 5095.62, "word": "?", "probability": 0.791015625 } ] }, { "id": 1883, "seek": 497266, "start": 5096.0, "end": 5098.28, "text": " And it was normally 1.", "tokens": [ 51414, 400, 309, 390, 5646, 502, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.1956623065382687, "compression_ratio": 1.6785714285714286, "no_speech_prob": 0.0083160400390625, "words": [ { "start": 5096.0, "end": 5096.4, "word": " And", "probability": 0.685546875 }, { "start": 5096.4, "end": 5096.56, "word": " it", "probability": 0.89990234375 }, { "start": 5096.56, "end": 5096.7, "word": " was", "probability": 0.89599609375 }, { "start": 5096.7, "end": 5097.22, "word": " normally", "probability": 0.83544921875 }, { "start": 5097.22, "end": 5097.88, "word": " 1", "probability": 0.521484375 }, { "start": 5097.88, "end": 5098.28, "word": ".", "probability": 0.794921875 } ] }, { "id": 1884, "seek": 497266, "start": 5098.58, "end": 5100.98, "text": " So we can add that in here.", "tokens": [ 51514, 407, 321, 393, 909, 300, 294, 510, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.1956623065382687, "compression_ratio": 1.6785714285714286, "no_speech_prob": 0.0083160400390625, "words": [ { "start": 5098.58, "end": 5098.9, "word": " So", "probability": 0.763671875 }, { "start": 5098.9, "end": 5100.06, "word": " we", "probability": 0.76806640625 }, { "start": 5100.06, "end": 5100.18, "word": " can", "probability": 0.8955078125 }, { "start": 5100.18, "end": 5100.36, "word": " add", "probability": 0.80810546875 }, { "start": 5100.36, "end": 5100.5, "word": " that", "probability": 0.880859375 }, { "start": 5100.5, "end": 5100.66, "word": " in", "probability": 0.908203125 }, { "start": 5100.66, "end": 5100.86, "word": " here", "probability": 0.814453125 }, { "start": 5100.86, "end": 5100.98, "word": ".", "probability": 0.76513671875 } ] }, { "id": 1885, "seek": 497266, "start": 5100.98, "end": 5103.36, "text": " So we have alpha equals 1.", "tokens": [ 51664, 407, 321, 362, 8961, 6915, 502, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.1956623065382687, "compression_ratio": 1.6785714285714286, "no_speech_prob": 0.0083160400390625, "words": [ { "start": 5100.98, "end": 5101.06, "word": " So", "probability": 0.77734375 }, { "start": 5101.06, "end": 5101.16, "word": " we", "probability": 0.87841796875 }, { "start": 5101.16, "end": 5101.38, "word": " have", "probability": 0.87255859375 }, { "start": 5101.38, "end": 5101.76, "word": " alpha", "probability": 0.73095703125 }, { "start": 5101.76, "end": 5102.26, "word": " equals", "probability": 0.6416015625 }, { "start": 5102.26, "end": 5102.96, "word": " 1", "probability": 0.9521484375 }, { "start": 5102.96, "end": 5103.36, "word": ".", "probability": 0.77490234375 } ] }, { "id": 1886, "seek": 499960, "start": 5103.36, "end": 5107.9, "text": " We see that an 87.5% accuracy.", "tokens": [ 50364, 492, 536, 300, 364, 27990, 13, 20, 4, 14170, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.18825000524520874, "compression_ratio": 1.5573122529644268, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 5103.36, "end": 5104.22, "word": " We", "probability": 0.167236328125 }, { "start": 5104.22, "end": 5104.54, "word": " see", "probability": 0.71337890625 }, { "start": 5104.54, "end": 5104.96, "word": " that", "probability": 0.5712890625 }, { "start": 5104.96, "end": 5105.48, "word": " an", "probability": 0.5048828125 }, { "start": 5105.48, "end": 5105.86, "word": " 87", "probability": 0.88525390625 }, { "start": 5105.86, "end": 5106.5, "word": ".5", "probability": 0.991943359375 }, { "start": 5106.5, "end": 5106.78, "word": "%", "probability": 0.8583984375 }, { "start": 5106.78, "end": 5107.4, "word": " accuracy", "probability": 0.7060546875 }, { "start": 5107.4, "end": 5107.9, "word": ".", "probability": 0.5546875 } ] }, { "id": 1887, "seek": 499960, "start": 5108.28, "end": 5109.72, "text": " We go ahead and run that.", "tokens": [ 50564, 492, 352, 2286, 293, 1190, 300, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.18825000524520874, "compression_ratio": 1.5573122529644268, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 5108.28, "end": 5108.6, "word": " We", "probability": 0.7939453125 }, { "start": 5108.6, "end": 5108.76, "word": " go", "probability": 0.88330078125 }, { "start": 5108.76, "end": 5108.98, "word": " ahead", "probability": 0.865234375 }, { "start": 5108.98, "end": 5109.14, "word": " and", "probability": 0.892578125 }, { "start": 5109.14, "end": 5109.34, "word": " run", "probability": 0.9052734375 }, { "start": 5109.34, "end": 5109.58, "word": " that", "probability": 0.869140625 }, { "start": 5109.58, "end": 5109.72, "word": ".", "probability": 0.7841796875 } ] }, { "id": 1888, "seek": 499960, "start": 5109.72, "end": 5110.8, "text": " I'm just doing this to show you", "tokens": [ 50664, 286, 478, 445, 884, 341, 281, 855, 291, 50714 ], "temperature": 0.0, "avg_logprob": -0.18825000524520874, "compression_ratio": 1.5573122529644268, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 5109.72, "end": 5109.8, "word": " I'm", "probability": 0.921875 }, { "start": 5109.8, "end": 5109.96, "word": " just", "probability": 0.880859375 }, { "start": 5109.96, "end": 5110.16, "word": " doing", "probability": 0.8984375 }, { "start": 5110.16, "end": 5110.36, "word": " this", "probability": 0.86328125 }, { "start": 5110.36, "end": 5110.52, "word": " to", "probability": 0.89990234375 }, { "start": 5110.52, "end": 5110.7, "word": " show", "probability": 0.88818359375 }, { "start": 5110.7, "end": 5110.8, "word": " you", "probability": 0.86669921875 } ] }, { "id": 1889, "seek": 499960, "start": 5110.8, "end": 5112.26, "text": " that there are no tricks up my sleeve.", "tokens": [ 50714, 300, 456, 366, 572, 11733, 493, 452, 21138, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.18825000524520874, "compression_ratio": 1.5573122529644268, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 5110.8, "end": 5110.92, "word": " that", "probability": 0.8349609375 }, { "start": 5110.92, "end": 5111.04, "word": " there", "probability": 0.8515625 }, { "start": 5111.04, "end": 5111.12, "word": " are", "probability": 0.88623046875 }, { "start": 5111.12, "end": 5111.34, "word": " no", "probability": 0.90966796875 }, { "start": 5111.34, "end": 5111.56, "word": " tricks", "probability": 0.78759765625 }, { "start": 5111.56, "end": 5111.66, "word": " up", "probability": 0.89208984375 }, { "start": 5111.66, "end": 5111.84, "word": " my", "probability": 0.90771484375 }, { "start": 5111.84, "end": 5112.12, "word": " sleeve", "probability": 0.77294921875 }, { "start": 5112.12, "end": 5112.26, "word": ".", "probability": 0.83447265625 } ] }, { "id": 1890, "seek": 499960, "start": 5112.26, "end": 5115.46, "text": " Alpha is by default 1 for this model.", "tokens": [ 50814, 20588, 307, 538, 7576, 502, 337, 341, 2316, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.18825000524520874, "compression_ratio": 1.5573122529644268, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 5112.26, "end": 5112.52, "word": " Alpha", "probability": 0.91064453125 }, { "start": 5112.52, "end": 5112.84, "word": " is", "probability": 0.8984375 }, { "start": 5112.84, "end": 5113.02, "word": " by", "probability": 0.83154296875 }, { "start": 5113.52, "end": 5114.06, "word": " default 1", "probability": 0.327392578125 }, { "start": 5114.06, "end": 5114.4, "word": " for", "probability": 0.84423828125 }, { "start": 5114.4, "end": 5114.62, "word": " this", "probability": 0.88330078125 }, { "start": 5114.62, "end": 5114.96, "word": " model", "probability": 0.8095703125 }, { "start": 5114.96, "end": 5115.46, "word": ".", "probability": 0.93212890625 } ] }, { "id": 1891, "seek": 499960, "start": 5116.24, "end": 5117.74, "text": " But what if we change that", "tokens": [ 50964, 583, 437, 498, 321, 1319, 300, 51064 ], "temperature": 0.0, "avg_logprob": -0.18825000524520874, "compression_ratio": 1.5573122529644268, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 5116.24, "end": 5116.38, "word": " But", "probability": 0.78857421875 }, { "start": 5116.38, "end": 5116.6, "word": " what", "probability": 0.8564453125 }, { "start": 5116.6, "end": 5116.72, "word": " if", "probability": 0.9052734375 }, { "start": 5116.72, "end": 5116.84, "word": " we", "probability": 0.9033203125 }, { "start": 5116.84, "end": 5117.38, "word": " change", "probability": 0.6162109375 }, { "start": 5117.38, "end": 5117.74, "word": " that", "probability": 0.8720703125 } ] }, { "id": 1892, "seek": 499960, "start": 5117.74, "end": 5120.06, "text": " to maybe something a little smaller, right?", "tokens": [ 51064, 281, 1310, 746, 257, 707, 4356, 11, 558, 30, 51164 ], "temperature": 0.0, "avg_logprob": -0.18825000524520874, "compression_ratio": 1.5573122529644268, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 5117.74, "end": 5118.18, "word": " to", "probability": 0.89111328125 }, { "start": 5118.18, "end": 5118.66, "word": " maybe", "probability": 0.67236328125 }, { "start": 5118.66, "end": 5118.96, "word": " something", "probability": 0.7392578125 }, { "start": 5119.1, "end": 5119.18, "word": " a little", "probability": 0.79833984375 }, { "start": 5119.18, "end": 5119.6, "word": " smaller", "probability": 0.724609375 }, { "start": 5119.6, "end": 5119.78, "word": ",", "probability": 0.70263671875 }, { "start": 5119.78, "end": 5119.9, "word": " right", "probability": 0.7041015625 }, { "start": 5119.9, "end": 5120.06, "word": "?", "probability": 0.90625 } ] }, { "id": 1893, "seek": 499960, "start": 5120.06, "end": 5121.48, "text": " Maybe a 0.1.", "tokens": [ 51164, 2704, 257, 1958, 13, 16, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.18825000524520874, "compression_ratio": 1.5573122529644268, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 5120.06, "end": 5120.34, "word": " Maybe", "probability": 0.91943359375 }, { "start": 5120.58, "end": 5120.9, "word": " a 0", "probability": 0.595703125 }, { "start": 5120.9, "end": 5121.3, "word": ".1", "probability": 0.996826171875 }, { "start": 5121.3, "end": 5121.48, "word": ".", "probability": 0.6806640625 } ] }, { "id": 1894, "seek": 499960, "start": 5121.48, "end": 5124.2, "text": " Let's reduce the impact of that smoothing filter.", "tokens": [ 51264, 961, 311, 5407, 264, 2712, 295, 300, 899, 6259, 571, 6608, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.18825000524520874, "compression_ratio": 1.5573122529644268, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 5121.48, "end": 5121.8, "word": " Let's", "probability": 0.931884765625 }, { "start": 5121.8, "end": 5122.3, "word": " reduce", "probability": 0.74365234375 }, { "start": 5122.3, "end": 5122.5, "word": " the", "probability": 0.81494140625 }, { "start": 5122.5, "end": 5122.78, "word": " impact", "probability": 0.859375 }, { "start": 5122.78, "end": 5122.92, "word": " of", "probability": 0.89306640625 }, { "start": 5122.92, "end": 5123.06, "word": " that", "probability": 0.87548828125 }, { "start": 5123.06, "end": 5123.4, "word": " smoothing", "probability": 0.9088541666666666 }, { "start": 5123.4, "end": 5123.74, "word": " filter", "probability": 0.888671875 }, { "start": 5123.74, "end": 5124.2, "word": ".", "probability": 0.88427734375 } ] }, { "id": 1895, "seek": 499960, "start": 5124.2, "end": 5125.28, "text": " So I'm going to go ahead", "tokens": [ 51364, 407, 286, 478, 516, 281, 352, 2286, 51464 ], "temperature": 0.0, "avg_logprob": -0.18825000524520874, "compression_ratio": 1.5573122529644268, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 5124.2, "end": 5124.2, "word": " So", "probability": 0.45166015625 }, { "start": 5124.2, "end": 5124.74, "word": " I'm", "probability": 0.8447265625 }, { "start": 5124.74, "end": 5124.74, "word": " going", "probability": 0.5322265625 }, { "start": 5124.74, "end": 5124.76, "word": " to", "probability": 0.8994140625 }, { "start": 5124.76, "end": 5124.86, "word": " go", "probability": 0.892578125 }, { "start": 5124.86, "end": 5125.28, "word": " ahead", "probability": 0.8525390625 } ] }, { "id": 1896, "seek": 499960, "start": 5125.28, "end": 5128.2, "text": " and press Shift-Enter and run that.", "tokens": [ 51464, 293, 1886, 28304, 12, 16257, 391, 293, 1190, 300, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.18825000524520874, "compression_ratio": 1.5573122529644268, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 5125.28, "end": 5125.7, "word": " and", "probability": 0.888671875 }, { "start": 5125.7, "end": 5126.04, "word": " press", "probability": 0.70654296875 }, { "start": 5126.04, "end": 5126.54, "word": " Shift", "probability": 0.341796875 }, { "start": 5126.54, "end": 5126.9, "word": "-Enter", "probability": 0.6742350260416666 }, { "start": 5126.9, "end": 5127.14, "word": " and", "probability": 0.828125 }, { "start": 5127.14, "end": 5127.4, "word": " run", "probability": 0.90771484375 }, { "start": 5127.4, "end": 5127.7, "word": " that", "probability": 0.88037109375 }, { "start": 5127.7, "end": 5128.2, "word": ".", "probability": 0.94287109375 } ] }, { "id": 1897, "seek": 499960, "start": 5128.86, "end": 5130.3, "text": " And we see something interesting.", "tokens": [ 51614, 400, 321, 536, 746, 1880, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.18825000524520874, "compression_ratio": 1.5573122529644268, "no_speech_prob": 0.00028228759765625, "words": [ { "start": 5128.86, "end": 5129.06, "word": " And", "probability": 0.360595703125 }, { "start": 5129.06, "end": 5129.14, "word": " we", "probability": 0.86279296875 }, { "start": 5129.14, "end": 5129.22, "word": " see", "probability": 0.81640625 }, { "start": 5129.22, "end": 5129.44, "word": " something", "probability": 0.7353515625 }, { "start": 5129.44, "end": 5129.8, "word": " interesting", "probability": 0.62841796875 }, { "start": 5129.8, "end": 5130.3, "word": ".", "probability": 0.974609375 } ] }, { "id": 1898, "seek": 502956, "start": 5130.3, "end": 5134.16, "text": " So this went from our worst model,", "tokens": [ 50364, 407, 341, 1437, 490, 527, 5855, 2316, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.22316176751080682, "compression_ratio": 1.481283422459893, "no_speech_prob": 0.0012254714965820312, "words": [ { "start": 5130.3, "end": 5131.82, "word": " So", "probability": 0.759765625 }, { "start": 5131.82, "end": 5131.98, "word": " this", "probability": 0.7998046875 }, { "start": 5131.98, "end": 5132.18, "word": " went", "probability": 0.7734375 }, { "start": 5132.18, "end": 5132.92, "word": " from", "probability": 0.81005859375 }, { "start": 5132.92, "end": 5133.26, "word": " our", "probability": 0.79345703125 }, { "start": 5133.26, "end": 5133.52, "word": " worst", "probability": 0.9140625 }, { "start": 5133.52, "end": 5133.88, "word": " model", "probability": 0.79833984375 }, { "start": 5133.88, "end": 5134.16, "word": ",", "probability": 0.6650390625 } ] }, { "id": 1899, "seek": 502956, "start": 5134.16, "end": 5136.34, "text": " 87.5% accuracy,", "tokens": [ 50514, 27990, 13, 20, 4, 14170, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.22316176751080682, "compression_ratio": 1.481283422459893, "no_speech_prob": 0.0012254714965820312, "words": [ { "start": 5134.16, "end": 5134.54, "word": " 87", "probability": 0.888671875 }, { "start": 5134.54, "end": 5135.14, "word": ".5", "probability": 0.996826171875 }, { "start": 5135.14, "end": 5135.36, "word": "%", "probability": 0.92822265625 }, { "start": 5135.36, "end": 5135.8, "word": " accuracy", "probability": 0.72119140625 }, { "start": 5135.8, "end": 5136.34, "word": ",", "probability": 0.6337890625 } ] }, { "id": 1900, "seek": 502956, "start": 5136.34, "end": 5140.14, "text": " to actually our second best model,", "tokens": [ 50614, 281, 767, 527, 1150, 1151, 2316, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.22316176751080682, "compression_ratio": 1.481283422459893, "no_speech_prob": 0.0012254714965820312, "words": [ { "start": 5136.34, "end": 5136.68, "word": " to", "probability": 0.90283203125 }, { "start": 5136.68, "end": 5137.82, "word": " actually", "probability": 0.6982421875 }, { "start": 5137.82, "end": 5138.04, "word": " our", "probability": 0.73388671875 }, { "start": 5138.04, "end": 5138.46, "word": " second", "probability": 0.77685546875 }, { "start": 5138.46, "end": 5139.0, "word": " best", "probability": 0.7353515625 }, { "start": 5139.0, "end": 5139.46, "word": " model", "probability": 0.806640625 }, { "start": 5139.46, "end": 5140.14, "word": ",", "probability": 0.953125 } ] }, { "id": 1901, "seek": 502956, "start": 5140.14, "end": 5143.06, "text": " 96.5% accuracy.", "tokens": [ 50814, 24124, 13, 20, 4, 14170, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.22316176751080682, "compression_ratio": 1.481283422459893, "no_speech_prob": 0.0012254714965820312, "words": [ { "start": 5140.14, "end": 5140.56, "word": " 96", "probability": 0.89599609375 }, { "start": 5140.56, "end": 5141.46, "word": ".5", "probability": 0.99951171875 }, { "start": 5141.46, "end": 5141.78, "word": "%", "probability": 0.9970703125 }, { "start": 5141.78, "end": 5142.3, "word": " accuracy", "probability": 0.69921875 }, { "start": 5142.3, "end": 5143.06, "word": ".", "probability": 0.91552734375 } ] }, { "id": 1902, "seek": 502956, "start": 5143.74, "end": 5147.3, "text": " And so it slightly misclassified", "tokens": [ 50964, 400, 370, 309, 4748, 3346, 11665, 2587, 51214 ], "temperature": 0.0, "avg_logprob": -0.22316176751080682, "compression_ratio": 1.481283422459893, "no_speech_prob": 0.0012254714965820312, "words": [ { "start": 5143.74, "end": 5143.86, "word": " And", "probability": 0.84375 }, { "start": 5143.86, "end": 5144.24, "word": " so", "probability": 0.90185546875 }, { "start": 5144.24, "end": 5145.08, "word": " it", "probability": 0.7314453125 }, { "start": 5145.08, "end": 5146.3, "word": " slightly", "probability": 0.1680908203125 }, { "start": 5146.3, "end": 5147.3, "word": " misclassified", "probability": 0.8268229166666666 } ] }, { "id": 1903, "seek": 502956, "start": 5148.38, "end": 5150.72, "text": " some of the legitimate ham emails as spam.", "tokens": [ 51214, 512, 295, 264, 17956, 7852, 12524, 382, 24028, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.22316176751080682, "compression_ratio": 1.481283422459893, "no_speech_prob": 0.0012254714965820312, "words": [ { "start": 5148.38, "end": 5148.6, "word": " some", "probability": 0.8115234375 }, { "start": 5148.6, "end": 5148.7, "word": " of", "probability": 0.90478515625 }, { "start": 5148.7, "end": 5148.86, "word": " the", "probability": 0.8134765625 }, { "start": 5148.86, "end": 5149.2, "word": " legitimate", "probability": 0.7294921875 }, { "start": 5149.2, "end": 5149.54, "word": " ham", "probability": 0.64013671875 }, { "start": 5149.54, "end": 5149.92, "word": " emails", "probability": 0.75732421875 }, { "start": 5149.92, "end": 5150.16, "word": " as", "probability": 0.86181640625 }, { "start": 5150.16, "end": 5150.46, "word": " spam", "probability": 0.939453125 }, { "start": 5150.46, "end": 5150.72, "word": ".", "probability": 0.1822509765625 } ] }, { "id": 1904, "seek": 502956, "start": 5150.72, "end": 5152.78, "text": " But it drastically reduced the,", "tokens": [ 51364, 583, 309, 29673, 9212, 264, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.22316176751080682, "compression_ratio": 1.481283422459893, "no_speech_prob": 0.0012254714965820312, "words": [ { "start": 5150.72, "end": 5151.0, "word": " But", "probability": 0.89208984375 }, { "start": 5151.0, "end": 5151.12, "word": " it", "probability": 0.884765625 }, { "start": 5151.12, "end": 5151.66, "word": " drastically", "probability": 0.82568359375 }, { "start": 5151.66, "end": 5152.32, "word": " reduced", "probability": 0.81201171875 }, { "start": 5152.32, "end": 5152.72, "word": " the", "probability": 0.77734375 }, { "start": 5152.72, "end": 5152.78, "word": ",", "probability": 0.74658203125 } ] }, { "id": 1905, "seek": 502956, "start": 5152.78, "end": 5156.3, "text": " I think it was 108 spam emails", "tokens": [ 51464, 286, 519, 309, 390, 41342, 24028, 12524, 51664 ], "temperature": 0.0, "avg_logprob": -0.22316176751080682, "compression_ratio": 1.481283422459893, "no_speech_prob": 0.0012254714965820312, "words": [ { "start": 5152.78, "end": 5152.9, "word": " I", "probability": 0.9970703125 }, { "start": 5152.9, "end": 5153.0, "word": " think", "probability": 0.806640625 }, { "start": 5153.0, "end": 5153.08, "word": " it", "probability": 0.88623046875 }, { "start": 5153.08, "end": 5153.14, "word": " was", "probability": 0.90576171875 }, { "start": 5153.14, "end": 5153.72, "word": " 108", "probability": 0.68408203125 }, { "start": 5153.72, "end": 5154.48, "word": " spam", "probability": 0.4814453125 }, { "start": 5154.48, "end": 5156.3, "word": " emails", "probability": 0.7587890625 } ] }, { "id": 1906, "seek": 502956, "start": 5157.16, "end": 5160.26, "text": " being misclassified down to just 22.", "tokens": [ 51664, 885, 3346, 11665, 2587, 760, 281, 445, 5853, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.22316176751080682, "compression_ratio": 1.481283422459893, "no_speech_prob": 0.0012254714965820312, "words": [ { "start": 5157.16, "end": 5157.84, "word": " being", "probability": 0.8564453125 }, { "start": 5157.84, "end": 5158.64, "word": " misclassified", "probability": 0.9519856770833334 }, { "start": 5158.64, "end": 5158.88, "word": " down", "probability": 0.5458984375 }, { "start": 5158.88, "end": 5159.04, "word": " to", "probability": 0.90771484375 }, { "start": 5159.04, "end": 5159.24, "word": " just", "probability": 0.88671875 }, { "start": 5159.24, "end": 5159.78, "word": " 22", "probability": 0.9052734375 }, { "start": 5159.78, "end": 5160.26, "word": ".", "probability": 0.9521484375 } ] }, { "id": 1907, "seek": 505836, "start": 5161.74, "end": 5164.24, "text": " So this is the power of hyperparameter tuning.", "tokens": [ 50414, 407, 341, 307, 264, 1347, 295, 9848, 2181, 335, 2398, 15164, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.16545542635658914, "compression_ratio": 1.6349809885931559, "no_speech_prob": 0.0008692741394042969, "words": [ { "start": 5161.74, "end": 5162.14, "word": " So", "probability": 0.75732421875 }, { "start": 5162.14, "end": 5162.32, "word": " this", "probability": 0.79541015625 }, { "start": 5162.32, "end": 5162.46, "word": " is", "probability": 0.89892578125 }, { "start": 5162.46, "end": 5162.6, "word": " the", "probability": 0.8125 }, { "start": 5162.6, "end": 5162.92, "word": " power", "probability": 0.8173828125 }, { "start": 5162.92, "end": 5163.1, "word": " of", "probability": 0.90478515625 }, { "start": 5163.1, "end": 5163.7, "word": " hyperparameter", "probability": 0.88525390625 }, { "start": 5163.7, "end": 5164.08, "word": " tuning", "probability": 0.78662109375 }, { "start": 5164.08, "end": 5164.24, "word": ".", "probability": 0.724609375 } ] }, { "id": 1908, "seek": 505836, "start": 5164.24, "end": 5165.4, "text": " And if we go all the way back down", "tokens": [ 50564, 400, 498, 321, 352, 439, 264, 636, 646, 760, 50614 ], "temperature": 0.0, "avg_logprob": -0.16545542635658914, "compression_ratio": 1.6349809885931559, "no_speech_prob": 0.0008692741394042969, "words": [ { "start": 5164.24, "end": 5164.3, "word": " And", "probability": 0.70361328125 }, { "start": 5164.3, "end": 5164.4, "word": " if", "probability": 0.90185546875 }, { "start": 5164.4, "end": 5164.48, "word": " we", "probability": 0.9052734375 }, { "start": 5164.48, "end": 5164.62, "word": " go", "probability": 0.9013671875 }, { "start": 5164.62, "end": 5164.78, "word": " all", "probability": 0.89501953125 }, { "start": 5164.78, "end": 5164.84, "word": " the", "probability": 0.81640625 }, { "start": 5164.84, "end": 5164.94, "word": " way", "probability": 0.8955078125 }, { "start": 5164.94, "end": 5165.14, "word": " back", "probability": 0.8076171875 }, { "start": 5165.14, "end": 5165.4, "word": " down", "probability": 0.814453125 } ] }, { "id": 1909, "seek": 505836, "start": 5165.4, "end": 5167.72, "text": " to our final task, task 7,", "tokens": [ 50614, 281, 527, 2572, 5633, 11, 5633, 1614, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.16545542635658914, "compression_ratio": 1.6349809885931559, "no_speech_prob": 0.0008692741394042969, "words": [ { "start": 5165.4, "end": 5165.56, "word": " to", "probability": 0.90087890625 }, { "start": 5165.56, "end": 5165.7, "word": " our", "probability": 0.83544921875 }, { "start": 5165.7, "end": 5165.96, "word": " final", "probability": 0.87158203125 }, { "start": 5165.96, "end": 5166.32, "word": " task", "probability": 0.7734375 }, { "start": 5166.32, "end": 5166.4, "word": ",", "probability": 0.88525390625 }, { "start": 5166.4, "end": 5166.56, "word": " task", "probability": 0.6875 }, { "start": 5166.56, "end": 5166.96, "word": " 7", "probability": 0.133544921875 }, { "start": 5166.96, "end": 5167.72, "word": ",", "probability": 0.8076171875 } ] }, { "id": 1910, "seek": 505836, "start": 5167.72, "end": 5169.64, "text": " and we run this,", "tokens": [ 50714, 293, 321, 1190, 341, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.16545542635658914, "compression_ratio": 1.6349809885931559, "no_speech_prob": 0.0008692741394042969, "words": [ { "start": 5167.72, "end": 5168.24, "word": " and", "probability": 0.8857421875 }, { "start": 5168.24, "end": 5168.6, "word": " we", "probability": 0.9033203125 }, { "start": 5168.6, "end": 5169.1, "word": " run", "probability": 0.90380859375 }, { "start": 5169.1, "end": 5169.5, "word": " this", "probability": 0.88427734375 }, { "start": 5169.5, "end": 5169.64, "word": ",", "probability": 0.388427734375 } ] }, { "id": 1911, "seek": 505836, "start": 5169.64, "end": 5172.64, "text": " where the multinomial manipulation with TF-IDF", "tokens": [ 50814, 689, 264, 45872, 47429, 26475, 365, 40964, 12, 2777, 37, 50964 ], "temperature": 0.0, "avg_logprob": -0.16545542635658914, "compression_ratio": 1.6349809885931559, "no_speech_prob": 0.0008692741394042969, "words": [ { "start": 5169.64, "end": 5169.84, "word": " where", "probability": 0.89111328125 }, { "start": 5169.84, "end": 5170.42, "word": " the", "probability": 0.8095703125 }, { "start": 5170.42, "end": 5171.08, "word": " multinomial", "probability": 0.926513671875 }, { "start": 5171.08, "end": 5171.78, "word": " manipulation", "probability": 0.285400390625 }, { "start": 5171.78, "end": 5172.02, "word": " with", "probability": 0.77490234375 }, { "start": 5172.02, "end": 5172.24, "word": " TF", "probability": 0.5390625 }, { "start": 5172.24, "end": 5172.64, "word": "-IDF", "probability": 0.8507486979166666 } ] }, { "id": 1912, "seek": 505836, "start": 5173.24, "end": 5174.84, "text": " incorrectly classified that as ham,", "tokens": [ 50964, 42892, 20627, 300, 382, 7852, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.16545542635658914, "compression_ratio": 1.6349809885931559, "no_speech_prob": 0.0008692741394042969, "words": [ { "start": 5173.24, "end": 5173.64, "word": " incorrectly", "probability": 0.82763671875 }, { "start": 5173.64, "end": 5174.04, "word": " classified", "probability": 0.90673828125 }, { "start": 5174.04, "end": 5174.26, "word": " that", "probability": 0.8798828125 }, { "start": 5174.26, "end": 5174.44, "word": " as", "probability": 0.9072265625 }, { "start": 5174.44, "end": 5174.72, "word": " ham", "probability": 0.33203125 }, { "start": 5174.72, "end": 5174.84, "word": ",", "probability": 0.74072265625 } ] }, { "id": 1913, "seek": 505836, "start": 5174.84, "end": 5176.44, "text": " we go ahead and rerun it.", "tokens": [ 51064, 321, 352, 2286, 293, 43819, 409, 309, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.16545542635658914, "compression_ratio": 1.6349809885931559, "no_speech_prob": 0.0008692741394042969, "words": [ { "start": 5174.84, "end": 5174.96, "word": " we", "probability": 0.70166015625 }, { "start": 5174.96, "end": 5175.06, "word": " go", "probability": 0.8876953125 }, { "start": 5175.06, "end": 5175.18, "word": " ahead", "probability": 0.8642578125 }, { "start": 5175.18, "end": 5175.3, "word": " and", "probability": 0.89501953125 }, { "start": 5175.3, "end": 5175.84, "word": " rerun", "probability": 0.87548828125 }, { "start": 5175.84, "end": 5176.04, "word": " it", "probability": 0.90380859375 }, { "start": 5176.04, "end": 5176.44, "word": ".", "probability": 0.62255859375 } ] }, { "id": 1914, "seek": 505836, "start": 5176.76, "end": 5178.86, "text": " Now it's correctly classifying it as spam", "tokens": [ 51164, 823, 309, 311, 8944, 1508, 5489, 309, 382, 24028, 51264 ], "temperature": 0.0, "avg_logprob": -0.16545542635658914, "compression_ratio": 1.6349809885931559, "no_speech_prob": 0.0008692741394042969, "words": [ { "start": 5176.76, "end": 5177.16, "word": " Now", "probability": 0.89892578125 }, { "start": 5177.16, "end": 5177.46, "word": " it's", "probability": 0.87744140625 }, { "start": 5177.46, "end": 5177.76, "word": " correctly", "probability": 0.84130859375 }, { "start": 5177.76, "end": 5178.34, "word": " classifying", "probability": 0.915283203125 }, { "start": 5178.34, "end": 5178.44, "word": " it", "probability": 0.8876953125 }, { "start": 5178.44, "end": 5178.58, "word": " as", "probability": 0.8818359375 }, { "start": 5178.58, "end": 5178.86, "word": " spam", "probability": 0.9208984375 } ] }, { "id": 1915, "seek": 505836, "start": 5178.86, "end": 5180.5, "text": " because its accuracy is much better.", "tokens": [ 51264, 570, 1080, 14170, 307, 709, 1101, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.16545542635658914, "compression_ratio": 1.6349809885931559, "no_speech_prob": 0.0008692741394042969, "words": [ { "start": 5178.86, "end": 5179.14, "word": " because", "probability": 0.607421875 }, { "start": 5179.14, "end": 5179.34, "word": " its", "probability": 0.6826171875 }, { "start": 5179.34, "end": 5179.7, "word": " accuracy", "probability": 0.77197265625 }, { "start": 5179.7, "end": 5179.98, "word": " is", "probability": 0.90576171875 }, { "start": 5179.98, "end": 5180.16, "word": " much", "probability": 0.80908203125 }, { "start": 5180.16, "end": 5180.42, "word": " better", "probability": 0.81982421875 }, { "start": 5180.42, "end": 5180.5, "word": ".", "probability": 0.89404296875 } ] }, { "id": 1916, "seek": 505836, "start": 5180.5, "end": 5182.04, "text": " And the only thing that we did to change it", "tokens": [ 51364, 400, 264, 787, 551, 300, 321, 630, 281, 1319, 309, 51464 ], "temperature": 0.0, "avg_logprob": -0.16545542635658914, "compression_ratio": 1.6349809885931559, "no_speech_prob": 0.0008692741394042969, "words": [ { "start": 5180.5, "end": 5180.58, "word": " And", "probability": 0.87158203125 }, { "start": 5180.58, "end": 5180.68, "word": " the", "probability": 0.8203125 }, { "start": 5180.68, "end": 5180.8, "word": " only", "probability": 0.86083984375 }, { "start": 5180.8, "end": 5180.98, "word": " thing", "probability": 0.8017578125 }, { "start": 5180.98, "end": 5181.1, "word": " that", "probability": 0.86474609375 }, { "start": 5181.1, "end": 5181.2, "word": " we", "probability": 0.90185546875 }, { "start": 5181.2, "end": 5181.42, "word": " did", "probability": 0.8974609375 }, { "start": 5181.42, "end": 5181.58, "word": " to", "probability": 0.904296875 }, { "start": 5181.58, "end": 5181.92, "word": " change", "probability": 0.83984375 }, { "start": 5181.92, "end": 5182.04, "word": " it", "probability": 0.8994140625 } ] }, { "id": 1917, "seek": 505836, "start": 5182.04, "end": 5183.84, "text": " was that hyperparameter tuning.", "tokens": [ 51464, 390, 300, 9848, 2181, 335, 2398, 15164, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.16545542635658914, "compression_ratio": 1.6349809885931559, "no_speech_prob": 0.0008692741394042969, "words": [ { "start": 5182.04, "end": 5182.2, "word": " was", "probability": 0.8779296875 }, { "start": 5182.2, "end": 5182.38, "word": " that", "probability": 0.875 }, { "start": 5182.38, "end": 5183.18, "word": " hyperparameter", "probability": 0.9781494140625 }, { "start": 5183.18, "end": 5183.44, "word": " tuning", "probability": 0.83203125 }, { "start": 5183.44, "end": 5183.84, "word": ".", "probability": 0.99755859375 } ] }, { "id": 1918, "seek": 505836, "start": 5186.92, "end": 5189.06, "text": " So that's all I have for you guys today.", "tokens": [ 51664, 407, 300, 311, 439, 286, 362, 337, 291, 1074, 965, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.16545542635658914, "compression_ratio": 1.6349809885931559, "no_speech_prob": 0.0008692741394042969, "words": [ { "start": 5186.92, "end": 5187.32, "word": " So", "probability": 0.890625 }, { "start": 5187.32, "end": 5187.72, "word": " that's", "probability": 0.890625 }, { "start": 5187.72, "end": 5187.9, "word": " all", "probability": 0.90185546875 }, { "start": 5187.9, "end": 5188.02, "word": " I", "probability": 0.9990234375 }, { "start": 5188.02, "end": 5188.18, "word": " have", "probability": 0.876953125 }, { "start": 5188.18, "end": 5188.3, "word": " for", "probability": 0.8955078125 }, { "start": 5188.3, "end": 5188.4, "word": " you", "probability": 0.89599609375 }, { "start": 5188.4, "end": 5188.58, "word": " guys", "probability": 0.88427734375 }, { "start": 5188.58, "end": 5189.06, "word": " today", "probability": 0.79296875 }, { "start": 5189.06, "end": 5189.06, "word": ".", "probability": 0.955078125 } ] }, { "id": 1919, "seek": 508836, "start": 5189.06, "end": 5192.44, "text": " I have a couple good resources,", "tokens": [ 50414, 286, 362, 257, 1916, 665, 3593, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.1612215962148074, "compression_ratio": 1.6557377049180328, "no_speech_prob": 0.010009765625, "words": [ { "start": 5189.06, "end": 5189.5, "word": " I", "probability": 0.732421875 }, { "start": 5189.5, "end": 5191.08, "word": " have", "probability": 0.8466796875 }, { "start": 5191.18, "end": 5191.3, "word": " a couple", "probability": 0.7861328125 }, { "start": 5191.3, "end": 5191.48, "word": " good", "probability": 0.6650390625 }, { "start": 5191.48, "end": 5192.02, "word": " resources", "probability": 0.78369140625 }, { "start": 5192.02, "end": 5192.44, "word": ",", "probability": 0.5791015625 } ] }, { "id": 1920, "seek": 508836, "start": 5192.44, "end": 5194.32, "text": " but the biggest one that's going to be helpful", "tokens": [ 50514, 457, 264, 3880, 472, 300, 311, 516, 281, 312, 4961, 50614 ], "temperature": 0.0, "avg_logprob": -0.1612215962148074, "compression_ratio": 1.6557377049180328, "no_speech_prob": 0.010009765625, "words": [ { "start": 5192.44, "end": 5192.48, "word": " but", "probability": 0.88623046875 }, { "start": 5192.48, "end": 5192.82, "word": " the", "probability": 0.8017578125 }, { "start": 5192.82, "end": 5193.22, "word": " biggest", "probability": 0.6318359375 }, { "start": 5193.22, "end": 5193.5, "word": " one", "probability": 0.80322265625 }, { "start": 5193.5, "end": 5193.7, "word": " that's", "probability": 0.909912109375 }, { "start": 5193.7, "end": 5193.8, "word": " going", "probability": 0.5693359375 }, { "start": 5193.8, "end": 5193.84, "word": " to", "probability": 0.90283203125 }, { "start": 5193.84, "end": 5193.98, "word": " be", "probability": 0.9072265625 }, { "start": 5193.98, "end": 5194.32, "word": " helpful", "probability": 0.82373046875 } ] }, { "id": 1921, "seek": 508836, "start": 5195.16, "end": 5196.76, "text": " is if you have any questions,", "tokens": [ 50614, 307, 498, 291, 362, 604, 1651, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.1612215962148074, "compression_ratio": 1.6557377049180328, "no_speech_prob": 0.010009765625, "words": [ { "start": 5195.16, "end": 5195.56, "word": " is", "probability": 0.818359375 }, { "start": 5195.56, "end": 5195.96, "word": " if", "probability": 0.45556640625 }, { "start": 5195.96, "end": 5196.04, "word": " you", "probability": 0.8955078125 }, { "start": 5196.04, "end": 5196.12, "word": " have", "probability": 0.884765625 }, { "start": 5196.12, "end": 5196.26, "word": " any", "probability": 0.83056640625 }, { "start": 5196.26, "end": 5196.66, "word": " questions", "probability": 0.9091796875 }, { "start": 5196.66, "end": 5196.76, "word": ",", "probability": 0.68359375 } ] }, { "id": 1922, "seek": 508836, "start": 5196.76, "end": 5197.72, "text": " feel free to reach out to me.", "tokens": [ 50714, 841, 1737, 281, 2524, 484, 281, 385, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.1612215962148074, "compression_ratio": 1.6557377049180328, "no_speech_prob": 0.010009765625, "words": [ { "start": 5196.76, "end": 5196.88, "word": " feel", "probability": 0.89208984375 }, { "start": 5196.88, "end": 5197.0, "word": " free", "probability": 0.87255859375 }, { "start": 5197.0, "end": 5197.12, "word": " to", "probability": 0.900390625 }, { "start": 5197.12, "end": 5197.26, "word": " reach", "probability": 0.84814453125 }, { "start": 5197.26, "end": 5197.4, "word": " out", "probability": 0.8203125 }, { "start": 5197.4, "end": 5197.5, "word": " to", "probability": 0.90234375 }, { "start": 5197.5, "end": 5197.62, "word": " me", "probability": 0.904296875 }, { "start": 5197.62, "end": 5197.72, "word": ".", "probability": 0.8134765625 } ] }, { "id": 1923, "seek": 508836, "start": 5197.72, "end": 5199.54, "text": " I am gtklondike on Gmail.", "tokens": [ 50764, 286, 669, 290, 83, 7837, 684, 1123, 322, 36732, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.1612215962148074, "compression_ratio": 1.6557377049180328, "no_speech_prob": 0.010009765625, "words": [ { "start": 5197.72, "end": 5197.8, "word": " I", "probability": 0.99365234375 }, { "start": 5197.8, "end": 5197.96, "word": " am", "probability": 0.828125 }, { "start": 5197.96, "end": 5198.74, "word": " gtklondike", "probability": 0.82509765625 }, { "start": 5198.74, "end": 5199.08, "word": " on", "probability": 0.83544921875 }, { "start": 5199.08, "end": 5199.36, "word": " Gmail", "probability": 0.66357421875 }, { "start": 5199.36, "end": 5199.54, "word": ".", "probability": 0.75439453125 } ] }, { "id": 1924, "seek": 508836, "start": 5199.54, "end": 5201.76, "text": " I'm also gtklondike on Twitter.", "tokens": [ 50864, 286, 478, 611, 290, 83, 7837, 684, 1123, 322, 5794, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.1612215962148074, "compression_ratio": 1.6557377049180328, "no_speech_prob": 0.010009765625, "words": [ { "start": 5199.54, "end": 5199.64, "word": " I'm", "probability": 0.958984375 }, { "start": 5199.64, "end": 5199.82, "word": " also", "probability": 0.8212890625 }, { "start": 5199.82, "end": 5200.6, "word": " gtklondike", "probability": 0.9478515625 }, { "start": 5200.6, "end": 5200.96, "word": " on", "probability": 0.89599609375 }, { "start": 5200.96, "end": 5201.36, "word": " Twitter", "probability": 0.86083984375 }, { "start": 5201.36, "end": 5201.76, "word": ".", "probability": 0.96337890625 } ] }, { "id": 1925, "seek": 508836, "start": 5202.02, "end": 5203.4, "text": " I'm not as active on Twitter,", "tokens": [ 50964, 286, 478, 406, 382, 4967, 322, 5794, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.1612215962148074, "compression_ratio": 1.6557377049180328, "no_speech_prob": 0.010009765625, "words": [ { "start": 5202.02, "end": 5202.38, "word": " I'm", "probability": 0.96630859375 }, { "start": 5202.38, "end": 5202.52, "word": " not", "probability": 0.8974609375 }, { "start": 5202.52, "end": 5202.66, "word": " as", "probability": 0.904296875 }, { "start": 5202.66, "end": 5202.9, "word": " active", "probability": 0.86865234375 }, { "start": 5202.9, "end": 5203.1, "word": " on", "probability": 0.89794921875 }, { "start": 5203.1, "end": 5203.3, "word": " Twitter", "probability": 0.8779296875 }, { "start": 5203.3, "end": 5203.4, "word": ",", "probability": 0.89306640625 } ] }, { "id": 1926, "seek": 508836, "start": 5203.4, "end": 5204.78, "text": " but I will see your direct messages", "tokens": [ 51064, 457, 286, 486, 536, 428, 2047, 7897, 51114 ], "temperature": 0.0, "avg_logprob": -0.1612215962148074, "compression_ratio": 1.6557377049180328, "no_speech_prob": 0.010009765625, "words": [ { "start": 5203.4, "end": 5203.46, "word": " but", "probability": 0.89794921875 }, { "start": 5203.46, "end": 5203.58, "word": " I", "probability": 0.99609375 }, { "start": 5203.58, "end": 5203.72, "word": " will", "probability": 0.8134765625 }, { "start": 5203.72, "end": 5203.92, "word": " see", "probability": 0.8154296875 }, { "start": 5203.92, "end": 5204.1, "word": " your", "probability": 0.80859375 }, { "start": 5204.1, "end": 5204.38, "word": " direct", "probability": 0.7890625 }, { "start": 5204.38, "end": 5204.78, "word": " messages", "probability": 0.8427734375 } ] }, { "id": 1927, "seek": 508836, "start": 5204.78, "end": 5207.54, "text": " or any at mentions.", "tokens": [ 51114, 420, 604, 412, 23844, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.1612215962148074, "compression_ratio": 1.6557377049180328, "no_speech_prob": 0.010009765625, "words": [ { "start": 5204.78, "end": 5205.06, "word": " or", "probability": 0.86865234375 }, { "start": 5205.06, "end": 5205.28, "word": " any", "probability": 0.79833984375 }, { "start": 5205.28, "end": 5205.64, "word": " at", "probability": 0.212158203125 }, { "start": 5205.64, "end": 5207.14, "word": " mentions", "probability": 0.6337890625 }, { "start": 5207.14, "end": 5207.54, "word": ".", "probability": 0.7490234375 } ] }, { "id": 1928, "seek": 508836, "start": 5208.34, "end": 5210.12, "text": " And then the GitHub code", "tokens": [ 51264, 400, 550, 264, 23331, 3089, 51414 ], "temperature": 0.0, "avg_logprob": -0.1612215962148074, "compression_ratio": 1.6557377049180328, "no_speech_prob": 0.010009765625, "words": [ { "start": 5208.34, "end": 5208.44, "word": " And", "probability": 0.74609375 }, { "start": 5208.44, "end": 5208.72, "word": " then", "probability": 0.71728515625 }, { "start": 5208.72, "end": 5209.4, "word": " the", "probability": 0.75537109375 }, { "start": 5209.4, "end": 5209.92, "word": " GitHub", "probability": 0.85205078125 }, { "start": 5209.92, "end": 5210.12, "word": " code", "probability": 0.81982421875 } ] }, { "id": 1929, "seek": 508836, "start": 5210.92, "end": 5212.36, "text": " for all of these workbooks,", "tokens": [ 51414, 337, 439, 295, 613, 589, 15170, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.1612215962148074, "compression_ratio": 1.6557377049180328, "no_speech_prob": 0.010009765625, "words": [ { "start": 5210.92, "end": 5211.32, "word": " for", "probability": 0.89892578125 }, { "start": 5211.32, "end": 5211.58, "word": " all", "probability": 0.89794921875 }, { "start": 5211.58, "end": 5211.7, "word": " of", "probability": 0.8828125 }, { "start": 5211.7, "end": 5211.84, "word": " these", "probability": 0.69873046875 }, { "start": 5211.84, "end": 5212.26, "word": " workbooks", "probability": 0.87744140625 }, { "start": 5212.26, "end": 5212.36, "word": ",", "probability": 0.7333984375 } ] }, { "id": 1930, "seek": 508836, "start": 5212.36, "end": 5214.06, "text": " this and all the workbooks,", "tokens": [ 51514, 341, 293, 439, 264, 589, 15170, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.1612215962148074, "compression_ratio": 1.6557377049180328, "no_speech_prob": 0.010009765625, "words": [ { "start": 5212.36, "end": 5212.5, "word": " this", "probability": 0.8720703125 }, { "start": 5212.5, "end": 5212.64, "word": " and", "probability": 0.85302734375 }, { "start": 5212.64, "end": 5212.82, "word": " all", "probability": 0.8974609375 }, { "start": 5212.82, "end": 5212.94, "word": " the", "probability": 0.58349609375 }, { "start": 5212.94, "end": 5213.44, "word": " workbooks", "probability": 0.883544921875 }, { "start": 5213.44, "end": 5214.06, "word": ",", "probability": 0.281982421875 } ] }, { "id": 1931, "seek": 508836, "start": 5214.06, "end": 5217.0, "text": " are on github.com slash netsecexplained.", "tokens": [ 51564, 366, 322, 290, 355, 836, 13, 1112, 17330, 2533, 8159, 23040, 3563, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.1612215962148074, "compression_ratio": 1.6557377049180328, "no_speech_prob": 0.010009765625, "words": [ { "start": 5214.06, "end": 5214.12, "word": " are", "probability": 0.88232421875 }, { "start": 5214.12, "end": 5214.54, "word": " on", "probability": 0.91064453125 }, { "start": 5214.54, "end": 5214.98, "word": " github", "probability": 0.8821614583333334 }, { "start": 5214.98, "end": 5215.44, "word": ".com", "probability": 0.949462890625 }, { "start": 5215.44, "end": 5215.76, "word": " slash", "probability": 0.009735107421875 }, { "start": 5215.76, "end": 5216.8, "word": " netsecexplained", "probability": 0.7137451171875 }, { "start": 5216.8, "end": 5217.0, "word": ".", "probability": 0.9921875 } ] }, { "id": 1932, "seek": 511532, "start": 5219.06, "end": 5221.54, "text": " So that is all I have for you guys.", "tokens": [ 50364, 407, 300, 307, 439, 286, 362, 337, 291, 1074, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.17708332992735362, "compression_ratio": 1.6581632653061225, "no_speech_prob": 0.003940582275390625, "words": [ { "start": 5219.06, "end": 5219.38, "word": " So", "probability": 0.7490234375 }, { "start": 5219.38, "end": 5220.0, "word": " that", "probability": 0.6806640625 }, { "start": 5220.0, "end": 5220.22, "word": " is", "probability": 0.89501953125 }, { "start": 5220.22, "end": 5220.46, "word": " all", "probability": 0.9072265625 }, { "start": 5220.46, "end": 5220.62, "word": " I", "probability": 0.9658203125 }, { "start": 5220.62, "end": 5220.86, "word": " have", "probability": 0.88037109375 }, { "start": 5220.86, "end": 5221.0, "word": " for", "probability": 0.8994140625 }, { "start": 5221.0, "end": 5221.14, "word": " you", "probability": 0.8935546875 }, { "start": 5221.14, "end": 5221.42, "word": " guys", "probability": 0.87548828125 }, { "start": 5221.42, "end": 5221.54, "word": ".", "probability": 0.607421875 } ] }, { "id": 1933, "seek": 511532, "start": 5221.54, "end": 5224.66, "text": " It looks like we just barely made it.", "tokens": [ 50464, 467, 1542, 411, 321, 445, 10268, 1027, 309, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.17708332992735362, "compression_ratio": 1.6581632653061225, "no_speech_prob": 0.003940582275390625, "words": [ { "start": 5221.54, "end": 5221.62, "word": " It", "probability": 0.8896484375 }, { "start": 5221.62, "end": 5221.8, "word": " looks", "probability": 0.8125 }, { "start": 5221.8, "end": 5222.14, "word": " like", "probability": 0.873046875 }, { "start": 5222.14, "end": 5222.6, "word": " we", "probability": 0.89453125 }, { "start": 5222.6, "end": 5223.2, "word": " just", "probability": 0.875 }, { "start": 5223.2, "end": 5223.92, "word": " barely", "probability": 0.888671875 }, { "start": 5223.92, "end": 5224.28, "word": " made", "probability": 0.81787109375 }, { "start": 5224.28, "end": 5224.5, "word": " it", "probability": 0.9013671875 }, { "start": 5224.5, "end": 5224.66, "word": ".", "probability": 0.2166748046875 } ] }, { "id": 1934, "seek": 511532, "start": 5224.78, "end": 5225.74, "text": " 1231.", "tokens": [ 50614, 2272, 12967, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.17708332992735362, "compression_ratio": 1.6581632653061225, "no_speech_prob": 0.003940582275390625, "words": [ { "start": 5224.78, "end": 5225.26, "word": " 1231", "probability": 0.5899658203125 }, { "start": 5225.26, "end": 5225.74, "word": ".", "probability": 0.69775390625 } ] }, { "id": 1935, "seek": 511532, "start": 5226.96, "end": 5229.16, "text": " And I will let you go.", "tokens": [ 50714, 400, 286, 486, 718, 291, 352, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.17708332992735362, "compression_ratio": 1.6581632653061225, "no_speech_prob": 0.003940582275390625, "words": [ { "start": 5226.96, "end": 5227.44, "word": " And", "probability": 0.81787109375 }, { "start": 5227.44, "end": 5227.92, "word": " I", "probability": 0.9462890625 }, { "start": 5227.92, "end": 5228.34, "word": " will", "probability": 0.8056640625 }, { "start": 5228.34, "end": 5228.5, "word": " let", "probability": 0.8994140625 }, { "start": 5228.5, "end": 5228.6, "word": " you", "probability": 0.89404296875 }, { "start": 5228.6, "end": 5228.86, "word": " go", "probability": 0.90673828125 }, { "start": 5228.86, "end": 5229.16, "word": ".", "probability": 0.96044921875 } ] }, { "id": 1936, "seek": 511532, "start": 5229.16, "end": 5232.42, "text": " I will stay in the chat channel", "tokens": [ 50864, 286, 486, 1754, 294, 264, 5081, 2269, 51014 ], "temperature": 0.0, "avg_logprob": -0.17708332992735362, "compression_ratio": 1.6581632653061225, "no_speech_prob": 0.003940582275390625, "words": [ { "start": 5229.16, "end": 5229.42, "word": " I", "probability": 0.98779296875 }, { "start": 5229.42, "end": 5229.58, "word": " will", "probability": 0.814453125 }, { "start": 5229.58, "end": 5229.92, "word": " stay", "probability": 0.9208984375 }, { "start": 5229.92, "end": 5230.3, "word": " in", "probability": 0.9033203125 }, { "start": 5230.3, "end": 5230.94, "word": " the", "probability": 0.810546875 }, { "start": 5230.94, "end": 5232.08, "word": " chat", "probability": 0.7353515625 }, { "start": 5232.08, "end": 5232.42, "word": " channel", "probability": 0.791015625 } ] }, { "id": 1937, "seek": 511532, "start": 5232.42, "end": 5233.24, "text": " for a little bit", "tokens": [ 51014, 337, 257, 707, 857, 51064 ], "temperature": 0.0, "avg_logprob": -0.17708332992735362, "compression_ratio": 1.6581632653061225, "no_speech_prob": 0.003940582275390625, "words": [ { "start": 5232.42, "end": 5232.7, "word": " for", "probability": 0.892578125 }, { "start": 5232.86, "end": 5232.96, "word": " a little", "probability": 0.8115234375 }, { "start": 5232.96, "end": 5233.24, "word": " bit", "probability": 0.8916015625 } ] }, { "id": 1938, "seek": 511532, "start": 5233.24, "end": 5236.14, "text": " in case any of you would like to continue to discuss.", "tokens": [ 51064, 294, 1389, 604, 295, 291, 576, 411, 281, 2354, 281, 2248, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.17708332992735362, "compression_ratio": 1.6581632653061225, "no_speech_prob": 0.003940582275390625, "words": [ { "start": 5233.24, "end": 5233.86, "word": " in", "probability": 0.485595703125 }, { "start": 5233.86, "end": 5234.1, "word": " case", "probability": 0.791015625 }, { "start": 5234.1, "end": 5234.32, "word": " any", "probability": 0.81494140625 }, { "start": 5234.32, "end": 5234.5, "word": " of", "probability": 0.90625 }, { "start": 5234.5, "end": 5234.64, "word": " you", "probability": 0.89404296875 }, { "start": 5234.64, "end": 5234.8, "word": " would", "probability": 0.83642578125 }, { "start": 5234.8, "end": 5234.96, "word": " like", "probability": 0.87744140625 }, { "start": 5234.96, "end": 5235.12, "word": " to", "probability": 0.9052734375 }, { "start": 5235.12, "end": 5235.42, "word": " continue", "probability": 0.82861328125 }, { "start": 5235.42, "end": 5235.6, "word": " to", "probability": 0.90380859375 }, { "start": 5235.6, "end": 5236.02, "word": " discuss", "probability": 0.814453125 }, { "start": 5236.02, "end": 5236.14, "word": ".", "probability": 0.2269287109375 } ] }, { "id": 1939, "seek": 511532, "start": 5236.14, "end": 5237.48, "text": " And I'll also stay in the voice channel", "tokens": [ 51214, 400, 286, 603, 611, 1754, 294, 264, 3177, 2269, 51264 ], "temperature": 0.0, "avg_logprob": -0.17708332992735362, "compression_ratio": 1.6581632653061225, "no_speech_prob": 0.003940582275390625, "words": [ { "start": 5236.14, "end": 5236.18, "word": " And", "probability": 0.73876953125 }, { "start": 5236.18, "end": 5236.3, "word": " I'll", "probability": 0.88134765625 }, { "start": 5236.3, "end": 5236.46, "word": " also", "probability": 0.82080078125 }, { "start": 5236.46, "end": 5236.74, "word": " stay", "probability": 0.93017578125 }, { "start": 5236.74, "end": 5236.86, "word": " in", "probability": 0.89892578125 }, { "start": 5236.86, "end": 5236.98, "word": " the", "probability": 0.8017578125 }, { "start": 5236.98, "end": 5237.2, "word": " voice", "probability": 0.8505859375 }, { "start": 5237.2, "end": 5237.48, "word": " channel", "probability": 0.7900390625 } ] }, { "id": 1940, "seek": 511532, "start": 5237.48, "end": 5240.1, "text": " for a little bit for the same reason.", "tokens": [ 51264, 337, 257, 707, 857, 337, 264, 912, 1778, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.17708332992735362, "compression_ratio": 1.6581632653061225, "no_speech_prob": 0.003940582275390625, "words": [ { "start": 5237.48, "end": 5237.7, "word": " for", "probability": 0.88671875 }, { "start": 5237.84, "end": 5237.98, "word": " a little", "probability": 0.80908203125 }, { "start": 5237.98, "end": 5238.28, "word": " bit", "probability": 0.88818359375 }, { "start": 5238.28, "end": 5239.02, "word": " for", "probability": 0.80908203125 }, { "start": 5239.02, "end": 5239.18, "word": " the", "probability": 0.80908203125 }, { "start": 5239.18, "end": 5239.34, "word": " same", "probability": 0.80322265625 }, { "start": 5239.34, "end": 5239.62, "word": " reason", "probability": 0.91796875 }, { "start": 5239.62, "end": 5240.1, "word": ".", "probability": 0.97509765625 } ] }, { "id": 1941, "seek": 511532, "start": 5240.22, "end": 5242.48, "text": " So I will see you there.", "tokens": [ 51414, 407, 286, 486, 536, 291, 456, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.17708332992735362, "compression_ratio": 1.6581632653061225, "no_speech_prob": 0.003940582275390625, "words": [ { "start": 5240.22, "end": 5240.5, "word": " So", "probability": 0.90087890625 }, { "start": 5240.5, "end": 5240.82, "word": " I", "probability": 0.943359375 }, { "start": 5240.82, "end": 5241.0, "word": " will", "probability": 0.81494140625 }, { "start": 5241.0, "end": 5241.28, "word": " see", "probability": 0.8134765625 }, { "start": 5241.28, "end": 5241.5, "word": " you", "probability": 0.89306640625 }, { "start": 5241.5, "end": 5242.0, "word": " there", "probability": 0.8564453125 }, { "start": 5242.0, "end": 5242.48, "word": ".", "probability": 0.95703125 } ] }, { "id": 1942, "seek": 511532, "start": 5242.72, "end": 5243.9, "text": " Have a good day.", "tokens": [ 51514, 3560, 257, 665, 786, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.17708332992735362, "compression_ratio": 1.6581632653061225, "no_speech_prob": 0.003940582275390625, "words": [ { "start": 5242.72, "end": 5243.06, "word": " Have", "probability": 0.87109375 }, { "start": 5243.14, "end": 5243.22, "word": " a good", "probability": 0.888671875 }, { "start": 5243.22, "end": 5243.42, "word": " day", "probability": 0.8984375 }, { "start": 5243.42, "end": 5243.9, "word": ".", "probability": 0.91796875 } ] } ], "text": " I just want to double check this. Alright, cool. I have all my stuff muted and we are good to go. Hello and welcome to Machine Learning for Security Analysts. This is going to be our final workshop for the AI village. This is going to be a beginner and interactive workshop for all those who are interested in machine learning and security and what this whole crazy AI thing is. So really, the major motivation for this workshop was that we're seeing a lot of buzz in the security community around AI and machine learning. But for many of us, it's not really clear what that is. So... oh, sorry. If you want to participate and ask questions, head over to the DevSchool channel and join the AIVillage-General-Voice, AIV-General-Voice. And you'll be able to ask us questions. If there's too many people joining and it gets unorganized, we're going to switch to Zoom. But it's sort of more open than it was before. Sorry, Gavin. Just needed to say that. No worries. Last line of this statement is I wanted to take, for the security community, the idea of machine learning and AI out of the buzzword and into the mainstream. So, my name is Gavin. I go by the pseudonym GT Klondike. I'm an independent security researcher and a security consultant. I'm very passionate about network attack and defense. And through that passion, I run a project called NetSecExplain, which is a blog and a YouTube channel, where I explain intermediate and advanced level computer networking concepts and security concepts in an easy-to-understand way. So, before I get started, usually in person, this is where I ask people, what are your thoughts when you hear the word machine learning? Right? And I've gotten a range of answers in the past that range from, oh, Skynet's going to take over the world, to you need a PhD in multivariable calculus and linear algebra. And while there is a mild amount of truth to the math background that you should have, neither of those are really true. Instead, machine learning is really a form of pattern matching. It's applied statistics. And with the increase in power behind the computer memory and behind the CPU, we're able to use these statistics in a much quicker, more processed way. So, first I want to kind of cover this idea of machine learning, artificial intelligence, and deep learning. In a lot of areas, it's being used interchangeably, and that's not really correct. First, what we have is this large umbrella of artificial intelligence. And artificial intelligence is kind of a philosophy, in my opinion. Artificial intelligence used to be, when the first digital calculators came out, that was considered artificial intelligence. A computer can do math. As things became more advanced, different concepts were considered artificial intelligence. There's video game artificial intelligence, rule-based artificial intelligence, classical image recognition. But today we're talking about machine learning, which is a subset of artificial intelligence. And it's focused a lot more on grabbing inferences from data and making statistical patterns. And then inside of machine learning, we have a concept called deep learning. Deep learning is specifically deep neural networks. And so neural networks is a machine learning algorithm that's pretty popular. But deep learning allows us to take that a little bit further. And so usually we see this in the form of convolutional neural networks, which are primarily used for image recognition, or recurrent neural networks, which are used for cyclical pattern recognition. So think of things such as a heartbeat monitor, where there's a pattern involved that you kind of need to match up. And if there's any sort of heart irregularities, the pattern will diverge from predicted patterns. So if we wanted to formally define machine learning, I would say that it's a set of statistical techniques that enable the process of information mining, pattern discovery, and drawing inferences from data. So the idea is that the algorithms learn from past data to predict future outcomes, instead of creating a different algorithm for a different scenario. And we'll see that as we go through the workbooks, how we're able to create multiple different types of algorithms around the same set of data, or how we can use the same algorithms with different types of data. So some key examples, especially in the security sphere, is domain generation algorithms. Domain generation algorithms are heavily used by botnets so that the bot herder can stay in contact with the botnet itself, while government agencies or ISPs are taking down the domains that they use to communicate. We also see this with web application firewalls. We can perform anomaly detection to identify normal web traffic, normal parameters that are sent by a web client, versus potentially malicious parameters. In this example here, it's showing a possible SQL injection, and it's calling that out. And then, of course, network anomaly detection, where what we can do is predict how the network will operate over a period of time, and then keep track of how it is actually operating. And if it's beyond a certain delta or a difference, then we can flag that and send it off to a security analyst. So why is this important for security analysts, and also important for hackers? Well, today, over a quarter of security products for detection have some form of machine learning. So from an analyst's perspective, what you want to do is understand how these machines work, so that you can ensure that they operate efficiently and are working effectively. Machine learning isn't this magical black box that just solves all of our problems. And I want to share a story with you, and this is what really made the idea of machine learning and the value of machine learning really stick out to me. So a number of years ago, a friend of mine was approached by a non-profit. And what this non-profit did was track cheetah population out in Africa. So they set up a bunch of different cameras, and they would take a picture at different intervals, and it would be sent off to a human analyst to identify whether or not there's a cheetah in the picture. Not a job I would want to do, but it needs done, and it's really important. So they approached my friend, and they were saying, hey, is there a way that we can increase our efficiency? Something that we can use to kind of automate some of the manual labor that we're doing. And so what he did was spend about a week, and he used a very simple machine learning model to identify images. And what he told this model was, hey, if you see an image, and you are at least 5% confident that there's a cheetah in the picture, send it off to an analyst. If you're less than 5% confident, just throw it away. Now 5%, that doesn't really sound like a lot, and to be honest, it's not. But what this non-profit was able to do with this simple model was what would normally take them a year of labor they were able to complete in one month. That is a 1200% increase in productivity by just implementing a little bit of machine learning and that fuzzy logic into their process to kind of help automate it. So this is what I want to do to kind of push for the security analysts and for the hacker community to get a little bit more involved in AI and machine learning so that we can see and identify ways that we can improve our own processes, especially ones that require a little bit of fuzzy logic, things that traditional signatures or scripting aren't sufficient in. So the 7-step machine learning process generally looks like this. And this isn't a list so much as a cycle, right? So first we're going to start with gathering the data. We want to identify what it is we want our machine learning algorithm to classify. So first we're going to gather the data and then we're going to prepare the data in such a way that is easy for machine learning models to understand. And in this case, it's usually turning it into some form of number or some form of signal. Most of our time is spent gathering the data and preparing the data. The rest of this tends to be a little bit quicker. So first, based on the data that we have and the problem set that were presented, we choose a model. So some models perform better than others in certain tasks. And sometimes you just got to kind of figure out maybe neural nets isn't the best model for you. Maybe logistic regression or SVM or random forest classifier is better for you. But once we've identified the model or models, then we go ahead and train it. And so what we'll usually do is perform what's called a training testing split. And in this case, we have a series or a lot of clean labeled data. And we take that data, we separate 80% of it and 20% of it. 80% of it is what we use to train the model. And then the other 20% is what is used to evaluate the model to see how well the model is performing. And so it's kind of like how we teach students in elementary school, right? We train them on the bulk of information and then we test them to see how well they're understanding the material. And so some of our models will perform very well. Some of our models may not. And so if we have a model that performs fairly well, but we think it could do better, then we hop into what is called hyperparameter tuning. And we're going to see what a hyperparameter looks like in a little bit. But hyperparameter tuning, think of it as little knobs and levers and switches that we can use to kind of tweak our model and tune it in such a way that it is better at a certain type of problem. And then once we've completed all this, we're ready to deploy. Now the reason why this is cyclical, right? We want to gather more data, prepare the data, and use the same model that we're already using after deploy is because machine learning stops learning as soon as it's trained. So to kind of give you an idea, I know that certain spam filters like Facebook's Facebook spam filter, they retrain it and rebuild it every one to three days because that's how quickly spam is being processed through their pipelines and through their networks. And so it's a way for them to kind of stay on top of that. So we're going to hop into understanding how machine learning works, especially in the security space. And the easiest example, in my opinion, is building a spam filter. Now spam filters, we already know how they operate conceptually. So it's a lower barrier of entry. We're going to see specifically how the machine learning fits in. But before I hop into that, are there any questions on how machine learning, AI, and deep learning kind of intermingle and why it's important to understand machine learning from a security standpoint or in the hacking community? I see on the Twitch chat, reinforcement learning, reinforcement learning, self-learning, contextual regret minimization, what differences between them? I'm not familiar with counterfactual, not familiar with counterfactual regret minimization, but typically you'll see three types of machine learning. You'll see classification or supervised learning, which is what we're going to be covering. You'll see unsupervised learning, which is very good for data exploration. And unsupervised learning uses a whole different set of algorithms. And then there's reinforcement learning, where we embed in a model different rewards and punishments based on how it's performing. And so these are all different ways of training the model, and then we can make decisions off of those. Hey, Sven, are there any questions in the Discord chat before I move on? Okay, I'm going to assume not. So before we look at a full spam filter, we want to kind of look at a smaller example. So in this case, we have a series of sentences talking about sports or not sports, which are really elections. So here we have a couple sentences. A, great games. Sorry. Yes. Well, I think you got this one. But there was a question from Norwin. I fell asleep on the job. No worries. It has been a long weekend. So what was the question? Norwin kindly repeated Glucorio's question. So you already answered it. Okay, okay. So kind of going back, we have a great game, which is talking about sports. We have the election was over, which is talking about not sports. Very clean match, talking about sports. Clean but forgettable game, talking about sports. So if we wanted to take this idea and specify a sentence that we've never seen before about sports and not sports, how would we do this? We would want to look at keywords. So in this case, we can see that it's talking about games. We know it's probably about sports. If it's talking about elections, it's probably not talking about sports. And so what we want to really hone in on are keywords. But to put this into a machine learning model, we need to find a way to turn this into numbers. So the way that we're going to do this is Bayes' Theorem. Bayes' Theorem is... it may look complex at first, but it's actually a really easy to understand probability theorem. And in this case, we see the probability of A given B equals probability of B given A times the probability of A divided by the probability of B. So in this case, we want to see what is the probability that this sentence is talking about sports given that the sentence is A very close game. So we don't know the probability of sports given A very close game, but we can easily plug that into this formula and say, well, we know the probability of sports. We saw three out of our five sentences were talking about sports. And we can figure out the probability of A very close game given sports and the probability of A very close game. But how do we do that? How do we get a sentence like this? Well, with Bayes theorem, we can actually, or with probability, actually, we can split this up. So instead of A very close game as a whole sentence, we can look at the probability of A times the probability of very times close times game. And so what this turns into in our A very close game given sports is probability of A in sports, probability of very in sports, and so on. And of course, we're going to want to do is say, okay, whichever is highest, sports or not sports, that's the one that we're going to classify this sentence as being part of. So at this point, it becomes a simple counting game, right? So how many times does the word A show up in sports? Well, we see that it shows up twice, once in the first sentence and once in the fourth sentence. And then how many times does it show up in not sports? Once, right there in the fifth sentence. So A does not show up in sports. It only shows up in not sports. And then we see the word game show up twice in sports. So we just take those numbers and we plug them in and we say, okay, A showed up in sports twice, very showed up once, close showed up zero times, and game showed up twice. And if we counted the number of unique words, we would have had 11 unique words across all of our sentences talking about sports. But we run into a problem and the problem is that what we want our machine learning model to do is identify and classify sentences that it has never seen before. Unfortunately, it's never seen close and so that winds up being a zero, zero times everything is zero. And we see that that easily cascades down and just ruins our model. So it's because we've never seen the word close, there's a zero probability that this exists in our sentence. So that's a problem, but we can get around that. There's another algorithm called multinomial Naive Bayes. And so this is just a small modification and what it does is add what is called a smoothing filter. And we can see this alpha here. It's added to the numerator and the denominator. And usually this alpha is one, but this is going to be our hyperparameter for Naive Bayesian, multinomial Naive Bayesian that we can tweak, right? We can set it to one, we can set it to two, we can set it to 0.1. And so this is a thing that we can tweak to see if we can get our model to work for us. So we take the same idea. We do the word counts. We saw that a showed up in sports twice, very showed up once, close to zero. But now we have this plus one. So the probability of close given sports is never going to reach zero. And then of course, as I mentioned earlier, we need to do the same thing for not sports. And the total number of unique words in not sports is nine. The total number of unique words in sports is 11. And the total number of unique words across both classes is 14. So we plug in our answers and we do our calculations and we get 0.0000461 for sports and 0.0000143 for non-sports. Classifying the sentence, a very close game being about sports. So that was a lot that I just kind of laid on you. If you have any questions, type them in the chat. While you're doing that, I'm going to show you how we can take our raw emails and transform them into these types of counts and these types of numbers in a very clean and effective way. So the five things we need to keep track of are the total number of unique words, the total number of words in spam, the total number of words in ham, or regular emails, the count of each word in spam, and the count of each word in ham. So let's take a look at one of our emails. We see here, East Asian fonts in Lenny. Thanks for your support. Installing Unifonts did it well for me. Now we want to take a sentence like this and find a way to classify it as being spam or ham. But before we do that, we want to kind of point out a couple things. So we see here kind of towards the bottom, we have the word unsubscribe, all capitalized, and then unsubscribe lowercase. What we want to do is look at keywords. And so in context, it doesn't matter if unsubscribe is capitalized or the first letter is capitalized or it's all lowercase. It means the same thing. And so to kind of reduce our problem set, what we're going to do is set everything to lowercase. The other thing we want to do is remove what are called stop words. Stop words are words like the, in, of, on, or... They don't add any context to the sentence. And we're going to do the same thing for punctuation. So we're going to remove those. We're going to keep our keywords. And then one more thing that we're going to do is called stemming. So if we have something like the word congrats or congratulations, in the English language, they mean the same thing. So if we're looking at keywords, we want to treat them the same. And so what stemming does is shrink those words down to their base form or the root form. And then we can count them the same. Another really good example is the word thanks, thank you, where it's a just singular thank. And I thanked somebody today with an ed at the end. As a keyword, they all mean the same thing. And so stemming will reduce them all down to thank. And so instead of three separate words, it's going to be counted as one word. And so that's going to drastically reduce our dimension space. So after our preprocessing, which is what this is known as, we're going to see East Asian fonts in Lenny, or East Asian fonts Lenny, thanks support installing Unifonts, well me. And then what isn't shown here is what the stemming looks like. So as we go through the workbook, we'll take this exact same email and see how it's transformed at every step of our preprocessing. So are there any questions so far? I don't think so. There's none on Twitch chat, and there's none in the Discord. Perfect. So what we're going to have are a series of workbooks. We're going to use MyBender. MyBender is really awesome. TAs, if you don't mind sharing this link. What it will do is spin up a Docker container with the workbook linked to my GitHub so that you can kind of code with me as we walk through and build our own machine learning classifiers. While this is starting up, what we're going to be using is instead of coding everything raw and doing the raw numbers like we did on our pen and paper, we're going to be using the abstraction library Scikit-learn. Scikit-learn is very useful and it allows us to treat things kind of like Legos, where, OK, maybe I don't want multinomial Naive Bayesian, maybe I want logistic regression or random forest. We can just swap that out. So once it's loaded, and I'm going to give you a moment to get this loaded up. If it takes a little bit longer than it should, then you'll easily be able to catch up to me and I'll show you how. So we're going to click on workbooks spam filter sklearn. If you're not very familiar with Python, you can still follow along. We have a completed workbook, which is the workbook complete spam filter sklearn. And these are Jupyter notebooks. If you've never used Jupyter notebooks, I think they're the best thing since sliced bread, especially when it comes to data science. But it allows us to interact with code blocks and visualize things in line. And I think they work fantastic together. So let's go ahead, scroll down. We're going to run this first code block. And so what this is going to do is install a couple of libraries that we need, as well as set our data directory to where the data directory is in the GitHub project. So to run these, you can click run up at the top, or you can press shift enter, which is what I'm pressing now. And then you can see that it's running. A star in the upper corner means that it's currently running. And then a number in the upper corner means that that was the order that code block was ran in. So while that is going, I'm going to let it go until it stops scrolling my thing. So we're just going to import a couple libraries. We're going to import numpy, matplotlib for graphs, regular expressions we'll be using and NLTK. NLTK stands for Natural Language Toolkit. This will allow us to identify and collect a list of stop words to remove those things. And it will also allow us to use a stemmer function to stem the words and reduce our problem space. Train test split, I don't believe we're actually using that in here. The data directories I have are already split into 80% training, 20% testing. And then we're going to use our vectorizers. And we'll explain what the vectorizers do, but we're going to take a look at both of the TF-IDF vectorizer and the count vectorizer because they operate slightly different. Count vectorizer just takes a straight word count like we did with our pen and paper example. And then TF-IDF actually takes all of the words into account and gives them a weight. Scikit-learn, we're going to use logistic regression and multinomial naivetation. And the reason why we're going to use both of these is because we don't actually know which one's going to perform best. And so like good data scientists, we're going to try a couple different models and take the one that performs best with the problem set that we have. And then for a couple metric and visualizations, we're going to use the Scikit-learn confusion matrix and classification report. So I'm going to go ahead and press Shift-Enter and that's going to run. You will see libraries imported once that's complete. And we can move on to the next thing. So this is our test email. This is the exact same email that we saw in the slides. So as I mentioned earlier, we're going to use this email to see how it's transformed at every step of preprocessing. So I'm going to go ahead and run that. And then this is our tokenizer function. Tokenizer functions will allow us to pull out the keywords in the way that we would like them to be extracted. So in this case, we're going to grab all the punctuation, all the stop words, and we're going to create a stemmer constructor. We're going to use these to remove the stop words from the email. We're going to use these to remove punctuation from the email, and then we're going to stem the words. We're going to move all the words to lowercase so that they are treated exactly the same. So we're just going to go ahead and run this, shift enter, and our tokenizer is defined. And this is where we run into our first task, which is to tokenize an email. So our task says that we want to print the full email, test email, and then we're going to print the results of the tokenized version of that email. So here I'm just going to do print tokenizer test email. And we can go ahead and run that, shift enter. We can see the original email that we have, East Asian Fonts and Lenny, thanks for your support. We can see, just like in our slides, we have East Asian Font Lenny, slightly changed, thank instead of thanks, support install, because we can have installing installed with an ed at the end, or I will install this software, which is just a standard install. We see unsubscribe has been changed. And two of the things that I want to point out is every single word in here is unique, except for the word unsubscribe, which shows up twice, and list.deviant.org, which shows up twice. So we're going to take a look at our training data. What this is going to do is identify the directories where our spam files are, our ham files are, and our test files are. We're going to get a count, because that's one of the five things that we needed to keep track of, was the count of, actually we want to keep track of the count of words, we don't care how many emails we have. So I'm going to go ahead and run this, and what we're going to do is put those emails into what is known as a corpus. So we're going to create two list arrays, so corpus and labels. Corpus is going to hold all of our emails for spam and ham, and then the labels is going to be each label for our data. So the first thing we're going to do is corpus equals a new list, labels equals a new list, and then we're going to do the same thing for spam and ham. We're going to load the email bodies from the ham directories and the spam directory into the corpus array, and then we're going to load the labels for each email into the labels array. So what that's going to look like is we're going to use a for loop here, so we can say for each in os.listdir, and then we have our data directory, which is defined above. We're going to look at our ham directory for this first round. With each open file, we're going to look at our data directory plus ham plus os.listdir. We're going to look at each, because each is the name of our file, and we're going to want to read those as the file descriptor f. So for our corpus, we can do an append and then f.read. So this will read each email into our corpus and then labels.append ham, because we know that all of the emails in the ham directory are part of the ham data set. And so we can easily do the same thing for spam which is we need to be careful on how we change this. So instead of slash ham, it's going to be slash spam, and then of course our label is also going to be spam. So I'm going to let this sit for a minute and let you guys go ahead and make sure that you copy this down correctly. This bit is pretty easy if you're familiar with Python. It might be a little confusing if you are not, but that's okay. If you ever get lost at any point, just remember that there are a completed solutions manual in the workbooks directory. So I'm going to go ahead and run this. So shift enter to run. And I spelled labels wrong. Labels, shift enter to run. Loading ham, loading spam, done. So what this is going to do is graphically load or graphically visualize how many ham emails we have versus how many spam emails we have. And this is something we want to generally do with our data just to see if there's any sort of imbalanced data sets. This one we have about 50% spam per ham. It's like 2 to 1 ratio of ham to spam. And so this I'm not going to consider an imbalanced data set for this example, but if we have something such as like credit card fraud where it happens less than a fraction of a percent of the time, that's something that we really want to dive into simply because if we try and use this exact example on credit card fraud, it's not going to work because what we will do is create a model that is 99% accurate because it just classifies all credit card transactions as legitimate. Now if we want to identify credit card fraud, that's not very helpful for us. So this just allows us to kind of explore the data and see how much of what we have. So in this case we have 2,359 ham emails and about 1,100 spam emails. So task 2A, we're going to view our training data. So this one's just to kind of see what our data looks like. We generally have an idea, but we just kind of want to play around with it. And this is another thing that you would want to do in a data discovery process is just kind of see, okay, what is it that we're actually working with? So in this case, I'm going to pick an email ID, just email ID 5. You can pick 5 or you can pick any other. And then I'm going to grab the email, which is part of the corpus array. Corpus and then our email ID. And then I'm going to print that email, and then I'm going to do the same thing and print the tokenized version using a tokenizer function of that email. So we can see how it's transformed. So just so I don't go too fast, I want to make sure that you're able to follow along and copy this down. It's fairly simple. So I will wait just a few seconds. How are we doing on questions? No one has been posting some helpful links, but hasn't had too many questions so far. So thank you very much. No winner. Okay. So when we run that, what we have is the email body. We see product review, vert tools, dev, 2.0 URL, and then this URL. We see product review, vert tool, dev, 2.0 URL as one word, HTTP, and then the full URL. So this is how we can identify and kind of track our data as it's being transformed over time. So task 3 is where we're going to start using our vectorizers. What we want to do is get a count of each unique word, and we want to get a count of each unique word per class so that we can use that in our classification. So there's two ways we can do that. We can use the straight count vectorizer, which will get the count of our words, and we can use a TF-IDF vectorizer, which will give us a weight of each count. So no winner says he's behind. He's catching up and he'll catch up later and follow along. I can try to figure out a system of helping the winner. I can send you a Zoom link or something and look over your shoulder metaphorically. Also, in the workbooks, you can just open up the... that's the wrong one... you can just open up the completed spam filter SK Learn, and it's completely filled out for you. So if you ever do fall behind and you would like to catch up, you can look at the answers there. There is a way to follow along and make sure your code works. Yeah, absolutely. And I like using the completed workbook. You can just run everything and see how things are supposed to be at each step of the process. So we're going to go ahead and train our vectorizers. And the instructions tell us exactly how to do this. So we're going to use the vectorizer. We're going to call it cvec for the count vectorizer, tvec for the tfidf vectorizer, and we're going to perform fit transform. Fit in scikit-learn world is code for train. So this is going to, quote unquote, train our vectorizers so they can get the count of each words. And then we're going to save the results as count x and tfidf x. So what that looks like is cvec equals count vectorizer. And then we want to use our tokenizer that we defined above. So the tokenizer that we're going to use is called tokenizer. I know, not confusing at all. But we're going to use our count x. And pay attention to your capitals. Scikit-learn is very picky and so is my workbook. We're going to use cvec.fit transform. And then we're going to train transform or count the words for our corpus. And then we're going to do the same thing with our tfidf vectorizer. tvec equals tfidf vectorizer. And we're going to use our tokenizer called tokenizer. And then our tfidf x equals tvec.fit transform. And it's also going to be on our corpus. So I'm going to let this sit for a minute and let you guys be able to catch up. And this takes a little bit. This takes about two minutes to run because what it's doing is it's reading every single email and it is counting the words in those emails in order to get the number of unique words. So I'm going to go ahead and run this because it's going to take a little bit. But in case you need, here is the code while this is operating. And so we can see that it is currently training the count vectorizer, kind of down here at the bottom. And then once the count vectorizer is complete, it will start training the tfidf vectorizer. And then it will let us know when that is complete. So while this is going, I'm going to go ahead and move on to the next code block. We can write the code while this is still training, but we won't be able to run it because it can run only one code block at a time. So in this case, we have task 3a, which is to count the test email tokens. So we're going to manually count out each of the tokens. So what we're going to do is say for i in and this is a bit of a trick so that we can keep the count as well as the words in order. So we're going to use a list of a dictionary and we're going to want to grab the tokenized version of our email. So let's call this tokenized email equals tokenizer test email. And then our from keys we're going to have tokenized email which we saw above is going to be a list. So we'll just call that tokenized email and then we're going to count the words. So print, do some Python format, And then we're going to look at our tokenized email.count of each word, and then the word itself. So we see our vectorizing is complete, so we are ready to run this. I'm going to let this sit for about 30 more seconds and let you guys catch up. And then, of course, after this workshop, I have a whole series of workbooks, as well as their solutions. So if you're interested in other ways to apply machine learning and security to different problems, and using different algorithms, don't forget to take a look at those. So I'm going to go ahead and run this, Shift-Enter, and we can see the counts. So we have East Asian font, Lenny, thanks, support. Each of these, we have our unique words, they only show up once in our email. The only two that are outliers is unsubscribe, or unsubscrib, after our stemmer. And this list.debian.org, they show up twice in our email. So this is if we manually counted these, but what if we used our vectorizers? So what we're going to do here in Task 3B is create new vectorizers, the count vectorizer and TF-IDF vectorizer, and then we're going to print out the counts that each of them represent. So in the first one here, I'll just call this example-cvec, and then we're going to define a new vectorizer. And I'll just call this example-x equals example-cvec.fit-transform. And then it expects a list, our email is a string, so we're going to wrap it in these square brackets. And we're just going to use our raw test email. And then we're going to want to print our example-x. And we can easily just copy and paste, do the same thing for our TF-IDF code. We'll just call this example-tvec, we'll use the TF-IDF vectorizer, tokenizer is tokenizer, we change this to tvec, and then we're already done with our example-x, so we don't need to change the name, we can just leave it as is. Example-tvec, fit-transform, and then square brackets, test-email, so that it's a list. Yes. Oh, it sounded like there was possibly a question. So Voto on the stream is asking, where are those workbooks again? Can one of the TAs post in the stream? There you go, perfect. Machine learning for a security analyst. Okay, so I'm going to go ahead and run this. Scroll up, let's take a look at the count vectorizer. So instead of seeing the words, we see these numbers, and that's exactly what we want. We've created what are called tokens. So the words themselves, the tokenizers will be able, or the vectorizers will be able to match them together. So all of them are one in their count, all of them are unique, except for token 16 and token 9. We don't know which one, either unsubscribe or list.wn.org, maps to 16 or 9, but what we do know is that both of them show up twice. So given that, list.wn.org is either 16 or 9, and then the other one belongs to unsubscribe, or the word unsubscribe. So this looks exactly the same as if we had done our raw count. If we look at our TF-IDF vectorizer, though, we see something a little differently. TF-IDF, what it does is use term frequency to give each term or token a weight. And so in this case, we see all of the ones that showed up once have a weight of 0.204, token 9 and token 16 have a weight of 0.408. So you don't really need to understand the underlying math, you just need to know that there are different ways to vectorize your data. So there's TF-IDF, count vectorizer, word2vec, and a couple others, bag of words. And so there's different ones that we can try and see which one works better for us. So let's hop down and start to load our testing data. So loading our testing data, what this is going to do is just show us the names of each of our files in our testing directory. And we have train email.txt, and then at the end we have the class that it belongs to. So we have ham, we have spam. So what we're going to want to do as part of loading our testing data is we're going to want to strip off these labels. So we're going to read the full email into our corpus, and we're going to strip off these labels, and those are going to be the new labels for our testing data. So that hops us into task 4 to load the testing data. Just like loading the training data, we're going to create two list arrays, our corpus, we're going to call this test corpus, and our test labels. And then we're going to load each email body, and then strip off the label and throw that into the test labels array. So what that's going to look like is... So we're going to look at... what was the name of that? Test corpus. And we're just going to set that as a blank list, and then test labels as a blank list. For loading each of the emails, we're going to do just like we did before, filename in ls.listdir, and then our data directory plus the test directory. So we're going to look at each filename, we're going to open each file, so data.dir plus test plus filename, and then we want to read those as the file descriptor F. So our test corpus, we're going to append F.read, which is going to read that email into our test corpus array, and then we want to grab the label. And in this case, I'm just going to use a simple regular expression. We're going to use txt, and then this is a backslash period, and filename 1. I'm going to scroll up real quick, because the reason why I want to do that is what this is saying is, where we see txt.period, we're going to split, so we have this full train txt.period, and then we have ham. And then the bracket 1, what that is going to do is say, this is bracket 0 once it's split, and then this is bracket 1, so we're just going to keep our labels, which are at the end of that split. And then with that label, or each label that we grab from the filename, we're going to append it to our labels directory, or our labels array. So this is what our code looks like. Double checking for errors, looks good to me. And I'm going to let this sit for a little bit, so you guys can go ahead and copy that down. How are we doing? No questions in Twitch stream, are there any questions in the Discord channel? Okay, I'm going to go ahead, shift, enter, and run. So this is going to quickly load the emails. And then let's run this next code block. So what this is going to do is allow us to visualize our data, just like we did before. So we see in our testing set, we have 590 ham emails, 276 spam emails, and the graph itself looks nearly identical to the one above, and that's because we did a random 80-20 split for our training and testing. And that was already done beforehand. So the next thing we want to do is use the vectorizers that we created, the cvec and the tvec vectorizer, and take a look at the test corpus, and get our counts of each word in the new emails. So let's go ahead, testCountX equals, and we're already going to use cvec, we're not going to use fitTransform, instead we're going to use transform, because we're not trying to train it, we're just trying to save the words themselves. We'll do testCorpus, and then testTFIDFX equals tvec.transform testCorpus. And that's all we need to do when we're using a piece of testing data. So I'm going to let that sit for a second, actually I'm going to run it because this is going to take a little bit as well. Slightly shorter than when we were training it, but it still needs to go through all the emails and apply the counts, and then the TFIDF, it needs to apply the weights. We already know what the counts are, we already know what the weights are, we just need to apply them to each token. So vectorizing is complete. And now we're finally on to testing and evaluating our model. So you remember how I said data collection and preprocessing is what's going to take the most amount of time? Well, that was about 80% of this workbook. If not, maybe a little more, maybe 85%. But yeah, data science in a nutshell. So here we have a very helpful report generator function. It's not important to know what's going on in this, it's just going to be a helper function, but we do need to know that it's going to take in our confusion matrix, our score, which is our accuracy, and the classification report, and then it's going to print out all the stats that we need. So that hops us into task 6A, which is going to be training and evaluating our first model, which is going to be multinomial Naive Bayesian using the TFIDF vectorizer. So there's a lot of steps to this, but we're going to walk through it step by step. First, what we're going to do is create a multinomial Naive Bayesian constructor, so that's going to look like mnb, tf, idf, and the names of these variables are very important because that's what's being used in the generator function. So I'm going to call this Numial Naive Bayesian, and then we're going to train the multinomial Naive Bayesian, as I already misspelled something, mnb, tf, idf, .fit, which is scikit-learn's code for train, and then we're going to use our TFIDF, our vectorized corpus, with the TFIDF array. So now we're going to get a couple stats, so we're going to get our score, mnb, tf, idf, equals mnb, tf, idf, .score. This is going to give us our accuracy, and we want to compare this against our test, tf, idf, x, and our test labels. And then we want to take a look at the raw predictions, so we're going to have our predictions, mnb, tf, idf, equals mnb, tf, idf, .predict, using the predict function, on our test, tf, idf, x. Cool. And with those results, what we are going to do is generate a classification, a confusion matrix, so we can see our true positives, false positives, true negatives, false negatives. So cmatrix, mnb, tf, idf, equals our confusion matrix, and then we're going to use our test labels and our predictions, mnb, tf, idf, which is our raw predictions. We're going to do the same thing for our classification report, so we'll see report, mnb, tf, idf, classification report, and in the same order, test labels and our predictions, mnb, tf, idf. So I'm going to let this sit for a second, give you a chance to copy all of that down. So what's really helpful here is seeing how at each of these tasks, 6a, 6b, 6c, and 6d, we're only going to need to change very few things. We're going to need to change, instead of tf, idf, we're going to change this to count to do our train and evaluate the multinomial Naive Bayesian with the count model. And then we're going to change this from the multinomial Naive Bayesian constructor to the logistic regression constructor. But other than that, the rest of our code is going to be identical. The rest of our preprocessing is going to be identical. And so this will allow us to train a total of four algorithms using two separate machine learning algorithms as well as two separate vectorizers. So this is going to be very helpful for us. So I'm going to go ahead and run this. So shift-enter to run. It looks like I misspelled something. Multinomial. There we go. Required argument y. That one's new. Give me one second. Oh, that is what I forgot. So we want to train our multinomial Naive Bayesian with our data as well as our labels so that it knows what belongs to spam, what belongs to ham, just kind of in our pen and paper example, what belonged to sports and what belonged to not sports. So now I can run that. And I see where we ran into that problem yesterday. Okay. I need to swap. This is the problem that I had with scikit-learn earlier. The test labels and the predictions. We start with the predictions and then we follow up with the test labels instead of the other way around. So I go ahead and run that. There we go. So we know that we had 590 ham emails. We know that we had, if we add these two numbers together, 276 spam emails. So we can see the actual number of ham emails, the actual number of spam emails in those columns. But let me scroll up real quick. So this is our classification report. Classification report we're not really going to use in this example, but it's good to know. There are other ways to measure how good a model is performing, beyond accuracy. Precision, recall, and F1 score are all used in their own ways. I'm not going to go into that, but it's definitely worth understanding. Instead, we're just going to look at the straight accuracy. For this multinomial with TF-IDF, we have a .875 or a 87.5% accuracy. If we look at our true positives and our true negatives, it correctly classified or predicted all ham emails as being part of the ham class. So these are all of our true positives for what is ham. And then our true negatives, what is spam, it only classified 168 out of the 276 that we have. The other half of the spam emails it also thought were ham or regular emails. So our predictor is letting some spam through, but the good news is it's not blocking any of our legitimate emails. Moving on to the next example, we're going to do the same thing. We're going to use multinomial naivete with count vectorizer. This is going to be the same, and then be count. I am actually a little lazy, so what I'm going to do is just copy this and I can show you all you need to do is just change a few things around and you have a working model. So instead of multinomial tfidf, I'm going to be using multinomial count. We're going to use the same constructor. So in this case it's called count, and instead of using the tfidfx, we're going to use the countx. score, count, mnb, count, and our test labels stay the same because we didn't vectorize those. There's no reason for us to change this. I'm just going to go ahead and ctrl-c and ctrl-v some stuff. So all I'm doing is just changing the word tfidf to the word count. Everything else is staying the same. We have our predictions, mnb, count, our test labels, that stays the same, we don't modify it. mnb, count, and then we change our predictions. So I'm going to go ahead and let that sit for a moment. I'll let you guys either manually type that in or do the copy-and-paste track that I did, which I highly recommend. It just saves quite a bit of typing. And then we'll type out the logistic regression in a moment because that's the next model that we'll be making. How are we doing on questions? I think we're all doing well. Everything's quiet on the Discord chat, too. Awesome. So I'm going to go ahead and run this. I'm going to do Shift-Enter. And if we look at our accuracy, our multinomial with the count vectorizer, we have a 94% accuracy. So quite a decent bump compared to our tfidf vectorizer using the same multinomial algorithm. What we see is about 26 of our emails... not about, it's exactly 26 of our emails in our test set got blocked. They were considered spam. These are the regular ham emails. But we have significantly fewer spam emails that are getting through our predictor. And so more of them are being classified as spam correctly. And so this is what we want to see is a dark blue over in this corner. And a darker blue or this lighter blue given the count over in the bottom right corner. So this kind of hops into a conversation about false positives and false negatives. Which would you like to prioritize? And so it really depends on the model. In security, one of the things that we're concerned about is impacting the users. So if you look at something like an antivirus, it looks for things that are probably talking out to the internet, trying to take over your webcam, uploading and downloading files. Well, what else does that? Chrome, Internet Explorer, Firefox. So when you're building an antivirus, it's better to have what they consider false negatives. Which is positive is it is malware and negative is it is not malware. It's benign. So it's better to allow some viruses to run instead of blocking legitimate applications. Because you don't want to impact the user experience. Because if you impact the user experience, it's just going to uninstall your antivirus software. And that leaves them unprotected and that's bad business for you when people are uninstalling your software. So even for us, we want to consider and weigh the factors of is it better for us to allow some spam to get through as long as we're not blocking any of the legitimate emails? Or do we want to make sure that absolutely no spam gets through and if we block legitimate emails, well that's just collateral damage. So these are considerations that you need to make when you're building models like these and as a data scientist. So for the multinomial naïve Bayesian with the count vectorizer, we have 94% accuracy. So let's try a different model. This one we're going to use the logistic regression. So if we look at the instructions, we're going to use the logistic regression constructor, but we're going to use this LBFGS solver. And this is one of the hyperparameters, or at least I would consider it a hyperparameter for logistic regression itself. There's a couple different solvers that you can use but in this case we're going to use the LBFGS. So what this is going to look like is LGS TF IDF equals logistic regression and then we're going to set our solver equals LBFGS and then of course, just like we did with the multinomial naïve Bayesian, we're going to fit our train, our classifier we're going to use the TF IDF X, which is our test data, and then we're going to use our training data, sorry, and then we're going to use our labels. Next we're going to hop in and do the score predictions classification matrix and, sorry, confusion matrix and classification reports. We're going to use score LGS TF IDF LGS TF IDF.score We're just going to look at our test TF IDF X and our test labels. We're going to have our predictions LGS TF IDF equals LGS TF IDF.predict That's going to give us our raw predictions and then I'm going to stop saying exactly what I'm typing but we're going to do our confusion matrix and our classification report Awesome. So I'm going to let this sit here for a little bit, let you guys kind of copy and follow along Hopefully we don't run into the same problems that we did last time Bender is fantastic I love it, but it will time out after about five minutes and once it times out you've got to kind of restart the whole thing or at least you've got to restart the notebook which is kind of annoying Another thing you will notice is the logistic regression will take a little longer to train and give us our predictions and it's just the way that logistic regression operates it does a little bit more mathematical or complicated mathematical formulas than the multinomial Naive Bayesian so it just takes a little bit longer to train but not too much longer, so that's good One of them is matrix multiplication which is a whole array of floats that you have to process versus Naive Bayes is literally counting and some logs when you're doing the math correctly which is very quick It's just counting Yeah, it's just counting and logs, the latest x86 stuff have built-in processes for doing integer logs and stuff like that because it's so common to use logs for numerical accuracy in machine learning You'll also notice the same thing with neural networks because neural networks do a lot of matrix multiplication which is why GPUs work really well for neural networks because you can parallelize matrix multiplications like that So I'm going to go ahead and run this Shift-Enter And it looks like it's running. Hopefully it doesn't take too long. Another comparison to make is a neural network versus a gradient-boosted tree. A gradient-boosted tree is all just if-then statements. Versus a neural network is a huge pain in the ass to multiply everything. So a GBT could be run in milliseconds versus a neural network taking seconds in 100% of your CPU. Actually, speaking of neural networks, I'm kind of curious about this. How well this would be received at DEF CON. Would anybody be interested? And please vote in the Discord channel. If you would be interested in learning how to build neural networks from scratch or how to build deep learning security tools I think both would be really interesting. Neural networks from scratch is actually a lot easier than you would imagine. You can do it in about 11 lines of Python code. Today we are able to simplify and easily explain the math whereas a lot of these algorithms were invented in the 50s where the people who would do this kind of work were called statisticians or people who would apply these in business scenarios were called business intelligence. But today with computer science and these abstraction libraries it's a lot easier to understand. So let me know in the Discord chat if there's any interest in either of those as potentially future workshops for future DEF CON events. Or even just AI Village events. So KDAMinMax has a question on Twitch chat. I'll just read it here. I have a possibly stupid question about input structures. If you're learning, there's no real stupid questions. An email predictor acts on strings or a set of strings. Are there any machine learning approaches that act reasonably well on trees? For example, abstract syntax tree representations of applications. For that, you might want to use a graph convolutional network or, honestly, you can interpret language as an abstract syntax tree. So you might want to reach in and use some of the... There's a huge backlog of literature that people largely ignore because of the success of deep learning of how to do language processing using abstract syntax trees. So you might want to reach into some old school machine learning from before 2010 when neural networks destroyed the world. I mean, built our jobs. That was a good answer. Thank you. So what we're looking at is logistic regression with TF-IDF vectorizer. We have a slightly better... It's a small bump, but it's slightly better than the multinomial with the count vectorizer. We have a 95.9% accuracy. We see that we have a little bit more than the 26 ham emails that were incorrectly classified as spam. We have significantly fewer of the spam emails being classified as ham. So this would be a perfect instance of moving towards having absolutely zero spam get through our filter at the risk of losing some of our regular emails. But what I want to show is how the accuracy improves just changing the algorithm itself. And then looking at multinomial Naive Bayesian compared to logistic regression both using TF-IDF. We had 87.5% for the multinomial and then we have 95.9% for the logistic regression. So far, logistic regression is kind of beating out multinomial in the TF-IDF and the count metrics. So we're going to do our last one which is going to be logistic regression with count vectorizer. Count vectorizer worked well for multinomial so let's see if it works well for logistic regression. So we're going to do LGS count. And I'm just going to type this out but you can use the same copy-paste trick that I used for the multinomial with the count vectorizer. I'm just doing this as a way to kind of slow myself down so that you all have an opportunity to copy the code. So LBFGS. We're going to fit our labels. And we got to do our scores, predictions, confusion matrix, and classification report. Yeah, one of the things that you kind of reminded me of, Sven, when you've been talking about the different trees and algorithms that have been overtaken by neural networks and deep neural networks is random forests. Random forests operate very well on a lot of different scenarios. But because random forests are a cluster of decision trees people go, oh, they're just if-then statements. This is dumb. This isn't machine learning. Yeah, but for us, we have a highly shared data where, for example, on the Ember malware dataset, the lightweight, incredibly cheap gradient decision tree built with LightGBM outperformed any neural network you can throw at it. So the LightGBM gets 99.8% accuracy or something like that, and the neural network gets 98.7% accuracy, which is significantly worse. For some tasks, a gradient-based decision tree or something like that is the correct thing mathematically because neural networks have biases because it's easier for them to learn some things than others and GBTs have biases where it's easier for them to learn some things than others. And one of the great secrets of machine learning is match up your problem with both the requirements, how powerful your predictor needs to be, and the inherent biases of those predictors. Yeah. Yeah, that's pretty interesting. I didn't know that. But that also reminds me of another thing with neural networks. Neural networks are really good at learning superstitions. I don't know if that's a machine learning as a whole thing or specifically in neural networks but I remember there was a dataset that they were using to identify skin cancer cells. They used a convolutional neural network and based off of that it was learning that if there was a... it was performing too well. It got nearly 100% and they kind of dug into what it was doing and it said, OK, well if I see a ruler in the picture which the scientists, how they were collecting the images, they had a ruler next to the skin cancer cells. If I see a ruler in the picture that's how I know it's cancer. Not the little blob next to it. So I don't know if that's a whole machine learning problem or specifically a neural net problem but it's just kind of an interesting anecdote. Be careful how you collect and preprocess and use your data. A friend of mine did his PhD. His PhD thesis was inducing the bias that's sort of like the inherent model bias that's in convolutional neural networks into other models and it slightly improved. By inducing a bias? Yeah, you can induce a pixel locality bias like a great green tree or a support vector machine and it improves that's one of the assumptions that people make about convolutional neural networks is it allows you to make small pixel local decisions and then those can get glued together in the right way. And so he went and built little modifications to a dozen other algorithms that have sort of fallen out of favor and all of them improved slightly on images when you induced a pixel local bias. Okay, interesting. Yeah, that's that's actually really interesting. Alright, so hopefully I gave you guys enough time to make sure that this got copied down. I'm going to go ahead and run it and shift enter. This is going to take a little bit because it's going through its matrix multiplications but in the meantime, we're about to hop into our final task and what we have is a real spam email I pulled this out of my inbox or my spam folder last May but we see your latest issue is available now if you don't want issue notifications, click here to unsubscribe Hi George. My name is not George but we're going to look at this email and we're going to try it against all four of our spam classifiers and see how well they do. But what's also good about this exercise is it doesn't really hold your hand. This is usually something that I give plenty of time in a classroom setting. This allows people to ask questions as I go through. But this last task is going to say OK, we have a new email we've never seen before run it against our classifiers that we trained. And so you have to go through the whole process of using the vectorizers to vectorize the tokens or the words in the email and then putting them through the predict function and then printing out the prediction that it gives. So before we hop into that, I really want this to finish I want it to just be on its own time but we're going to compare how well these models did once this last one is complete and we're going to see if or how much that comparison has an influence on our test email So we're just going to give this another Probably be another 30 seconds or so. So it's not too long. How's the Discord chat? Discord chat's doing well. I really appreciate how much discussion we have in this version of the workshop. Also, and this is something that I want to note for people who are seeing this for the first time. So the last time I did my workshop on Friday, unfortunately my webcam froze in a very unflattering position, so I just had my mouth gaping open. So for this one I just put a static image of myself today. That way you can still see my beautiful face, but you don't get a very unflattering image of it. Alright, so this one is complete. We are now at the best model that we have of the ones that we've trained. We have a 97.69% accuracy. We can round that up to a 97.7% accuracy. We see that only 8 out of our 582 ham emails were misclassified as spam, and then only 12 out of our 264 spam emails were misclassified as ham, making this the best model that we have out of the 4 that we've trained. So that's pretty solid. So moving forward, what I would do is take this as kind of the better of the models, and I would go ahead and deploy this in production, or add this model into an application that's designed to kind of wrap around the idea of spam and ham. So if you are simply an email provider, you can use this to filter email, or if you are a spam company, or not a spam company, but like a spam research company, you would use this to grab the spam messages and then collect that as data, and then you can use that to be training the next version of your spam filter. So let's take a look at our test spam email. We have our final task, which is to use the vectorizer and the models that we created to perform predictions on our test email and our test spam email. So to make things easier, what I'm going to do is use a variable, I'll call this working email, and this will allow us to switch pretty quickly. So I have test email, and then we're going to want to vectorize our email, so we're going to use our test email tfidf, yes, tvec.transform, and this is going to be, remember it needs to be in a list, so we've got to use these square brackets, our working email, and then we'll do the same thing with our test email count, tvec.transform, working email. Now we need to get the raw predictions for every single one of them. The raw predictions, we already have the variable names here, kind of at the bottom, so I'm just going to go ahead and write them out. So we have test email mnb with tfidf, which is going to be our mnbtfidf.predict, on our test email with the tfidf vectorized info, we're going to do the same thing for count, using our count.predict, with our count vectorized, test email lgs, tfidf.predict, tfidf.data, and our last one, test email lgs.count, count. And then, just for fun and games, we can print out our working email. So this is going to print our test email. Our test email was the one that we saw, EastAsianFonts and Lenny, thanks for your support. So you can go ahead and copy this down. I'm going to go ahead and run this, because we are running close to time. So this is going to be our test email, and ideally, this should say that it is a regular email, not spam. It's going to label all four of these as ham. So let's run it. Working is not defined, because I forgot to call this working email. So we're going to run it. Here's our email. And all four of our classifiers correctly classified this as ham. I'm going to scroll back up, and we saved our email as our test spam email. So I'm going to grab that, and I'll run it. Oh, I forgot to run the code block that actually defined our test spam email. And now we can run this. And we see something interesting here. Our worst performing model, our MNB TF-IDF, which was 87.5% accurate, misclassified this email as being legitimate, as a ham email. But the other three of ours classified this correctly as a spam email. So there's a couple things we can do with this. If we were so inclined, we can use what's called ensemble learning, which we use all four algorithms. We take the average of them, or in other words, they give a vote on what they think the class is. And then in this case, three out of the four say it's spam, so it would be spam. Or we can use this as an example and say, hey, the MNB TF-IDF, we probably shouldn't use that simply because it's misclassifying known spam emails at a high rate. 87% means that we have about a 12.5% chance of misclassifying spam emails. So this is kind of pretty close to the conclusion of the workshop. This shows how you can take raw emails, raw data, transform it in a way that can be used in machine learning models. And then we build out our machine learning models, we evaluate them, and we can test them. And this last task shows you how we can properly deploy them. So we can build a piece of software or an application around it and say every time we get an email, just swap out this working email, and then you can leave everything else the same. Now, before I let you go, there's one more thing that I want to show you. I mentioned hyperparameter tuning. So let's take a look and see what hyperparameter tuning can do. So when we were talking about the multinomial Naive Bayesian, we saw that we had that smoothing function, the alpha, right? And it was normally 1. So we can add that in here. So we have alpha equals 1. We see that an 87.5% accuracy. We go ahead and run that. I'm just doing this to show you that there are no tricks up my sleeve. Alpha is by default 1 for this model. But what if we change that to maybe something a little smaller, right? Maybe a 0.1. Let's reduce the impact of that smoothing filter. So I'm going to go ahead and press Shift-Enter and run that. And we see something interesting. So this went from our worst model, 87.5% accuracy, to actually our second best model, 96.5% accuracy. And so it slightly misclassified some of the legitimate ham emails as spam. But it drastically reduced the, I think it was 108 spam emails being misclassified down to just 22. So this is the power of hyperparameter tuning. And if we go all the way back down to our final task, task 7, and we run this, where the multinomial manipulation with TF-IDF incorrectly classified that as ham, we go ahead and rerun it. Now it's correctly classifying it as spam because its accuracy is much better. And the only thing that we did to change it was that hyperparameter tuning. So that's all I have for you guys today. I have a couple good resources, but the biggest one that's going to be helpful is if you have any questions, feel free to reach out to me. I am gtklondike on Gmail. I'm also gtklondike on Twitter. I'm not as active on Twitter, but I will see your direct messages or any at mentions. And then the GitHub code for all of these workbooks, this and all the workbooks, are on github.com slash netsecexplained. So that is all I have for you guys. It looks like we just barely made it. 1231. And I will let you go. I will stay in the chat channel for a little bit in case any of you would like to continue to discuss. And I'll also stay in the voice channel for a little bit for the same reason. So I will see you there. Have a good day." }