{ "segments": [ { "id": 1, "seek": 2676, "start": 3.8, "end": 6.2, "text": " Are we ready to go?", "tokens": [ 50414, 2014, 321, 1919, 281, 352, 30, 50464 ], "temperature": 0.0, "avg_logprob": -0.29800258715128164, "compression_ratio": 1.5384615384615385, "no_speech_prob": 0.3203125, "words": [ { "start": 3.8, "end": 4.68, "word": " Are", "probability": 0.059814453125 }, { "start": 4.68, "end": 5.24, "word": " we", "probability": 0.80078125 }, { "start": 5.24, "end": 5.4, "word": " ready", "probability": 0.78173828125 }, { "start": 5.4, "end": 5.5, "word": " to", "probability": 0.892578125 }, { "start": 5.5, "end": 5.66, "word": " go", "probability": 0.90283203125 }, { "start": 5.66, "end": 6.2, "word": "?", "probability": 0.97314453125 } ] }, { "id": 2, "seek": 2676, "start": 7.32, "end": 8.58, "text": " We are.", "tokens": [ 50514, 492, 366, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.29800258715128164, "compression_ratio": 1.5384615384615385, "no_speech_prob": 0.3203125, "words": [ { "start": 7.32, "end": 7.72, "word": " We", "probability": 0.61328125 }, { "start": 7.72, "end": 8.04, "word": " are", "probability": 0.880859375 }, { "start": 8.04, "end": 8.58, "word": ".", "probability": 0.775390625 } ] }, { "id": 3, "seek": 2676, "start": 8.7, "end": 9.74, "text": " Perfect.", "tokens": [ 50614, 10246, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.29800258715128164, "compression_ratio": 1.5384615384615385, "no_speech_prob": 0.3203125, "words": [ { "start": 8.7, "end": 9.24, "word": " Perfect", "probability": 0.755859375 }, { "start": 9.24, "end": 9.74, "word": ".", "probability": 0.9560546875 } ] }, { "id": 4, "seek": 2676, "start": 10.34, "end": 14.28, "text": " Hello and welcome to Machine Learning for Security Analysts.", "tokens": [ 50664, 2425, 293, 2928, 281, 22155, 15205, 337, 11164, 1107, 19530, 82, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.29800258715128164, "compression_ratio": 1.5384615384615385, "no_speech_prob": 0.3203125, "words": [ { "start": 10.34, "end": 10.88, "word": " Hello", "probability": 0.6044921875 }, { "start": 10.88, "end": 11.42, "word": " and", "probability": 0.6484375 }, { "start": 11.42, "end": 11.9, "word": " welcome", "probability": 0.7548828125 }, { "start": 11.9, "end": 12.44, "word": " to", "probability": 0.8955078125 }, { "start": 12.44, "end": 12.84, "word": " Machine", "probability": 0.3388671875 }, { "start": 12.84, "end": 13.12, "word": " Learning", "probability": 0.84375 }, { "start": 13.12, "end": 13.32, "word": " for", "probability": 0.8779296875 }, { "start": 13.32, "end": 13.7, "word": " Security", "probability": 0.80322265625 }, { "start": 13.7, "end": 14.26, "word": " Analysts", "probability": 0.8595377604166666 }, { "start": 14.26, "end": 14.28, "word": ".", "probability": 0.9453125 } ] }, { "id": 5, "seek": 2676, "start": 14.28, "end": 19.2, "text": " This is our first workshop here at the AI village, DEF CON Safe Mode.", "tokens": [ 50864, 639, 307, 527, 700, 13541, 510, 412, 264, 7318, 7288, 11, 10113, 37, 16596, 27030, 20500, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.29800258715128164, "compression_ratio": 1.5384615384615385, "no_speech_prob": 0.3203125, "words": [ { "start": 14.28, "end": 14.4, "word": " This", "probability": 0.81591796875 }, { "start": 14.4, "end": 14.52, "word": " is", "probability": 0.9052734375 }, { "start": 14.52, "end": 14.72, "word": " our", "probability": 0.81201171875 }, { "start": 14.72, "end": 15.08, "word": " first", "probability": 0.8125 }, { "start": 15.08, "end": 15.68, "word": " workshop", "probability": 0.697265625 }, { "start": 15.68, "end": 16.1, "word": " here", "probability": 0.79638671875 }, { "start": 16.1, "end": 16.5, "word": " at", "probability": 0.90576171875 }, { "start": 16.5, "end": 16.7, "word": " the", "probability": 0.8046875 }, { "start": 16.7, "end": 17.02, "word": " AI", "probability": 0.86279296875 }, { "start": 17.02, "end": 17.44, "word": " village", "probability": 0.4267578125 }, { "start": 17.44, "end": 17.6, "word": ",", "probability": 0.5166015625 }, { "start": 17.6, "end": 17.76, "word": " DEF", "probability": 0.642578125 }, { "start": 17.76, "end": 17.98, "word": " CON", "probability": 0.8818359375 }, { "start": 17.98, "end": 18.34, "word": " Safe", "probability": 0.323486328125 }, { "start": 18.34, "end": 18.66, "word": " Mode", "probability": 0.66064453125 }, { "start": 18.66, "end": 19.2, "word": ".", "probability": 0.9755859375 } ] }, { "id": 6, "seek": 2676, "start": 19.62, "end": 24.52, "text": " So the goal here is to kind of take machine learning out of the buzzword and into the mainstream.", "tokens": [ 51114, 407, 264, 3387, 510, 307, 281, 733, 295, 747, 3479, 2539, 484, 295, 264, 13036, 7462, 293, 666, 264, 15960, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.29800258715128164, "compression_ratio": 1.5384615384615385, "no_speech_prob": 0.3203125, "words": [ { "start": 19.62, "end": 19.8, "word": " So", "probability": 0.69287109375 }, { "start": 19.8, "end": 19.92, "word": " the", "probability": 0.71533203125 }, { "start": 19.92, "end": 20.06, "word": " goal", "probability": 0.90234375 }, { "start": 20.06, "end": 20.26, "word": " here", "probability": 0.8037109375 }, { "start": 20.26, "end": 20.38, "word": " is", "probability": 0.9052734375 }, { "start": 20.38, "end": 20.48, "word": " to", "probability": 0.90087890625 }, { "start": 20.48, "end": 20.62, "word": " kind", "probability": 0.6904296875 }, { "start": 20.62, "end": 20.72, "word": " of", "probability": 0.90380859375 }, { "start": 20.72, "end": 20.9, "word": " take", "probability": 0.8154296875 }, { "start": 20.9, "end": 21.3, "word": " machine", "probability": 0.70166015625 }, { "start": 21.3, "end": 21.72, "word": " learning", "probability": 0.8427734375 }, { "start": 21.72, "end": 22.4, "word": " out", "probability": 0.81201171875 }, { "start": 22.4, "end": 22.52, "word": " of", "probability": 0.90380859375 }, { "start": 22.52, "end": 22.66, "word": " the", "probability": 0.81005859375 }, { "start": 22.66, "end": 23.02, "word": " buzzword", "probability": 0.874755859375 }, { "start": 23.02, "end": 23.28, "word": " and", "probability": 0.8857421875 }, { "start": 23.28, "end": 23.48, "word": " into", "probability": 0.720703125 }, { "start": 23.48, "end": 23.6, "word": " the", "probability": 0.81640625 }, { "start": 23.6, "end": 23.98, "word": " mainstream", "probability": 0.85986328125 }, { "start": 23.98, "end": 24.52, "word": ".", "probability": 0.99072265625 } ] }, { "id": 7, "seek": 2676, "start": 25.2, "end": 30.56, "text": " So buzzwords like machine learning and AI have been in the industry for a couple of years now,", "tokens": [ 51414, 407, 13036, 13832, 411, 3479, 2539, 293, 7318, 362, 668, 294, 264, 3518, 337, 257, 1916, 295, 924, 586, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.29800258715128164, "compression_ratio": 1.5384615384615385, "no_speech_prob": 0.3203125, "words": [ { "start": 25.2, "end": 25.38, "word": " So", "probability": 0.8369140625 }, { "start": 25.38, "end": 26.38, "word": " buzzwords", "probability": 0.857177734375 }, { "start": 26.38, "end": 26.58, "word": " like", "probability": 0.849609375 }, { "start": 26.58, "end": 26.9, "word": " machine", "probability": 0.67919921875 }, { "start": 26.9, "end": 27.18, "word": " learning", "probability": 0.849609375 }, { "start": 27.18, "end": 27.34, "word": " and", "probability": 0.88525390625 }, { "start": 27.34, "end": 27.64, "word": " AI", "probability": 0.9111328125 }, { "start": 27.64, "end": 28.26, "word": " have", "probability": 0.8642578125 }, { "start": 28.26, "end": 28.48, "word": " been", "probability": 0.818359375 }, { "start": 28.48, "end": 28.58, "word": " in", "probability": 0.9091796875 }, { "start": 28.58, "end": 28.7, "word": " the", "probability": 0.81298828125 }, { "start": 28.7, "end": 28.96, "word": " industry", "probability": 0.734375 }, { "start": 28.96, "end": 29.36, "word": " for", "probability": 0.89501953125 }, { "start": 29.56, "end": 29.68, "word": " a couple", "probability": 0.79833984375 }, { "start": 29.68, "end": 29.8, "word": " of", "probability": 0.8662109375 }, { "start": 29.8, "end": 30.02, "word": " years", "probability": 0.87890625 }, { "start": 30.02, "end": 30.36, "word": " now", "probability": 0.89599609375 }, { "start": 30.36, "end": 30.56, "word": ",", "probability": 0.74560546875 } ] }, { "id": 8, "seek": 5220, "start": 30.56, "end": 36.62, "text": " but for most people, it's not really well understood what these actually mean.", "tokens": [ 50364, 457, 337, 881, 561, 11, 309, 311, 406, 534, 731, 7320, 437, 613, 767, 914, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.18847656901925802, "compression_ratio": 1.7665198237885462, "no_speech_prob": 0.09661865234375, "words": [ { "start": 30.56, "end": 30.72, "word": " but", "probability": 0.50048828125 }, { "start": 30.72, "end": 31.08, "word": " for", "probability": 0.884765625 }, { "start": 31.08, "end": 31.58, "word": " most", "probability": 0.80908203125 }, { "start": 31.58, "end": 31.98, "word": " people", "probability": 0.92578125 }, { "start": 31.98, "end": 32.32, "word": ",", "probability": 0.5361328125 }, { "start": 32.32, "end": 32.62, "word": " it's", "probability": 0.941162109375 }, { "start": 32.62, "end": 32.96, "word": " not", "probability": 0.89111328125 }, { "start": 32.96, "end": 33.22, "word": " really", "probability": 0.75732421875 }, { "start": 33.22, "end": 33.48, "word": " well", "probability": 0.88623046875 }, { "start": 33.48, "end": 33.94, "word": " understood", "probability": 0.79931640625 }, { "start": 33.94, "end": 35.1, "word": " what", "probability": 0.84130859375 }, { "start": 35.1, "end": 35.36, "word": " these", "probability": 0.71435546875 }, { "start": 35.36, "end": 35.68, "word": " actually", "probability": 0.78662109375 }, { "start": 35.68, "end": 36.02, "word": " mean", "probability": 0.92626953125 }, { "start": 36.02, "end": 36.62, "word": ".", "probability": 0.98583984375 } ] }, { "id": 9, "seek": 5220, "start": 36.9, "end": 39.66, "text": " So my goal is to kind of introduce you to machine learning,", "tokens": [ 50664, 407, 452, 3387, 307, 281, 733, 295, 5366, 291, 281, 3479, 2539, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.18847656901925802, "compression_ratio": 1.7665198237885462, "no_speech_prob": 0.09661865234375, "words": [ { "start": 36.9, "end": 37.16, "word": " So", "probability": 0.8642578125 }, { "start": 37.16, "end": 37.34, "word": " my", "probability": 0.8154296875 }, { "start": 37.34, "end": 37.56, "word": " goal", "probability": 0.9111328125 }, { "start": 37.56, "end": 37.9, "word": " is", "probability": 0.90283203125 }, { "start": 37.9, "end": 38.14, "word": " to", "probability": 0.91064453125 }, { "start": 38.14, "end": 38.32, "word": " kind", "probability": 0.5458984375 }, { "start": 38.32, "end": 38.4, "word": " of", "probability": 0.90625 }, { "start": 38.4, "end": 38.72, "word": " introduce", "probability": 0.6748046875 }, { "start": 38.72, "end": 38.94, "word": " you", "probability": 0.89599609375 }, { "start": 38.94, "end": 39.08, "word": " to", "probability": 0.90380859375 }, { "start": 39.08, "end": 39.36, "word": " machine", "probability": 0.6796875 }, { "start": 39.36, "end": 39.66, "word": " learning", "probability": 0.8466796875 }, { "start": 39.66, "end": 39.66, "word": ",", "probability": 0.427490234375 } ] }, { "id": 10, "seek": 5220, "start": 39.66, "end": 43.88, "text": " and we're going to do this by kind of going over what machine learning is,", "tokens": [ 50814, 293, 321, 434, 516, 281, 360, 341, 538, 733, 295, 516, 670, 437, 3479, 2539, 307, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.18847656901925802, "compression_ratio": 1.7665198237885462, "no_speech_prob": 0.09661865234375, "words": [ { "start": 39.66, "end": 40.02, "word": " and", "probability": 0.89501953125 }, { "start": 40.02, "end": 40.16, "word": " we're", "probability": 0.92724609375 }, { "start": 40.16, "end": 40.24, "word": " going", "probability": 0.266845703125 }, { "start": 40.24, "end": 40.32, "word": " to", "probability": 0.9033203125 }, { "start": 40.32, "end": 40.46, "word": " do", "probability": 0.90869140625 }, { "start": 40.46, "end": 40.74, "word": " this", "probability": 0.88134765625 }, { "start": 40.74, "end": 41.04, "word": " by", "probability": 0.90673828125 }, { "start": 41.04, "end": 41.3, "word": " kind", "probability": 0.720703125 }, { "start": 41.3, "end": 41.38, "word": " of", "probability": 0.904296875 }, { "start": 41.38, "end": 41.6, "word": " going", "probability": 0.86279296875 }, { "start": 41.6, "end": 41.96, "word": " over", "probability": 0.87890625 }, { "start": 41.96, "end": 42.92, "word": " what", "probability": 0.861328125 }, { "start": 42.92, "end": 43.2, "word": " machine", "probability": 0.7236328125 }, { "start": 43.2, "end": 43.44, "word": " learning", "probability": 0.849609375 }, { "start": 43.44, "end": 43.8, "word": " is", "probability": 0.90185546875 }, { "start": 43.8, "end": 43.88, "word": ",", "probability": 0.97314453125 } ] }, { "id": 11, "seek": 5220, "start": 43.88, "end": 46.86, "text": " how it fits in the broader concept of AI,", "tokens": [ 51014, 577, 309, 9001, 294, 264, 13227, 3410, 295, 7318, 11, 51164 ], "temperature": 0.0, "avg_logprob": -0.18847656901925802, "compression_ratio": 1.7665198237885462, "no_speech_prob": 0.09661865234375, "words": [ { "start": 43.88, "end": 44.0, "word": " how", "probability": 0.89453125 }, { "start": 44.0, "end": 44.16, "word": " it", "probability": 0.90673828125 }, { "start": 44.16, "end": 44.42, "word": " fits", "probability": 0.89013671875 }, { "start": 44.42, "end": 44.6, "word": " in", "probability": 0.88037109375 }, { "start": 44.6, "end": 44.74, "word": " the", "probability": 0.7451171875 }, { "start": 44.74, "end": 45.04, "word": " broader", "probability": 0.74072265625 }, { "start": 45.04, "end": 46.02, "word": " concept", "probability": 0.77490234375 }, { "start": 46.02, "end": 46.24, "word": " of", "probability": 0.90283203125 }, { "start": 46.24, "end": 46.56, "word": " AI", "probability": 0.76806640625 }, { "start": 46.56, "end": 46.86, "word": ",", "probability": 0.791015625 } ] }, { "id": 12, "seek": 5220, "start": 47.08, "end": 52.34, "text": " and why it's important for security analysts and hackers to understand machine learning,", "tokens": [ 51164, 293, 983, 309, 311, 1021, 337, 3825, 31388, 293, 39766, 281, 1223, 3479, 2539, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.18847656901925802, "compression_ratio": 1.7665198237885462, "no_speech_prob": 0.09661865234375, "words": [ { "start": 47.08, "end": 47.64, "word": " and", "probability": 0.896484375 }, { "start": 47.64, "end": 48.14, "word": " why", "probability": 0.81787109375 }, { "start": 48.14, "end": 48.32, "word": " it's", "probability": 0.95263671875 }, { "start": 48.32, "end": 48.66, "word": " important", "probability": 0.78125 }, { "start": 48.66, "end": 48.9, "word": " for", "probability": 0.86572265625 }, { "start": 48.9, "end": 49.28, "word": " security", "probability": 0.8662109375 }, { "start": 49.28, "end": 49.58, "word": " analysts", "probability": 0.6640625 }, { "start": 49.58, "end": 49.94, "word": " and", "probability": 0.884765625 }, { "start": 49.94, "end": 50.3, "word": " hackers", "probability": 0.73681640625 }, { "start": 50.3, "end": 51.06, "word": " to", "probability": 0.8916015625 }, { "start": 51.06, "end": 51.5, "word": " understand", "probability": 0.74560546875 }, { "start": 51.5, "end": 51.82, "word": " machine", "probability": 0.7109375 }, { "start": 51.82, "end": 52.24, "word": " learning", "probability": 0.84130859375 }, { "start": 52.24, "end": 52.34, "word": ",", "probability": 0.57177734375 } ] }, { "id": 13, "seek": 5220, "start": 52.34, "end": 56.0, "text": " as well as what the machine learning process looks like.", "tokens": [ 51414, 382, 731, 382, 437, 264, 3479, 2539, 1399, 1542, 411, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.18847656901925802, "compression_ratio": 1.7665198237885462, "no_speech_prob": 0.09661865234375, "words": [ { "start": 52.34, "end": 52.62, "word": " as", "probability": 0.904296875 }, { "start": 52.62, "end": 52.94, "word": " well", "probability": 0.87744140625 }, { "start": 52.94, "end": 53.56, "word": " as", "probability": 0.9052734375 }, { "start": 53.56, "end": 54.5, "word": " what", "probability": 0.8642578125 }, { "start": 54.5, "end": 54.62, "word": " the", "probability": 0.814453125 }, { "start": 54.62, "end": 54.8, "word": " machine", "probability": 0.72802734375 }, { "start": 54.8, "end": 55.0, "word": " learning", "probability": 0.8330078125 }, { "start": 55.0, "end": 55.34, "word": " process", "probability": 0.85888671875 }, { "start": 55.34, "end": 55.64, "word": " looks", "probability": 0.79296875 }, { "start": 55.64, "end": 55.96, "word": " like", "probability": 0.8837890625 }, { "start": 55.96, "end": 56.0, "word": ".", "probability": 0.640625 } ] }, { "id": 14, "seek": 8008, "start": 56.0, "end": 61.34, "text": " And then we're going to take all of that and put that into building our first machine learning model,", "tokens": [ 50364, 400, 550, 321, 434, 516, 281, 747, 439, 295, 300, 293, 829, 300, 666, 2390, 527, 700, 3479, 2539, 2316, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.1751358661962592, "compression_ratio": 1.5365853658536586, "no_speech_prob": 0.02886962890625, "words": [ { "start": 56.0, "end": 56.1, "word": " And", "probability": 0.30322265625 }, { "start": 56.1, "end": 56.18, "word": " then", "probability": 0.67578125 }, { "start": 56.18, "end": 56.3, "word": " we're", "probability": 0.89990234375 }, { "start": 56.3, "end": 56.38, "word": " going", "probability": 0.47314453125 }, { "start": 56.38, "end": 56.44, "word": " to", "probability": 0.8994140625 }, { "start": 56.44, "end": 56.6, "word": " take", "probability": 0.80615234375 }, { "start": 56.6, "end": 56.88, "word": " all", "probability": 0.89697265625 }, { "start": 56.88, "end": 57.04, "word": " of", "probability": 0.9013671875 }, { "start": 57.04, "end": 57.36, "word": " that", "probability": 0.88330078125 }, { "start": 57.36, "end": 57.62, "word": " and", "probability": 0.845703125 }, { "start": 57.62, "end": 57.88, "word": " put", "probability": 0.89208984375 }, { "start": 57.88, "end": 58.14, "word": " that", "probability": 0.8740234375 }, { "start": 58.14, "end": 58.64, "word": " into", "probability": 0.734375 }, { "start": 58.64, "end": 59.14, "word": " building", "probability": 0.79931640625 }, { "start": 59.14, "end": 59.36, "word": " our", "probability": 0.81494140625 }, { "start": 59.36, "end": 59.84, "word": " first", "probability": 0.8134765625 }, { "start": 59.84, "end": 60.2, "word": " machine", "probability": 0.7001953125 }, { "start": 60.2, "end": 60.46, "word": " learning", "probability": 0.7958984375 }, { "start": 60.46, "end": 60.84, "word": " model", "probability": 0.80419921875 }, { "start": 60.84, "end": 61.34, "word": ",", "probability": 0.744140625 } ] }, { "id": 15, "seek": 8008, "start": 61.34, "end": 63.38, "text": " which will be something very familiar.", "tokens": [ 50614, 597, 486, 312, 746, 588, 4963, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.1751358661962592, "compression_ratio": 1.5365853658536586, "no_speech_prob": 0.02886962890625, "words": [ { "start": 61.34, "end": 61.56, "word": " which", "probability": 0.91162109375 }, { "start": 61.56, "end": 61.64, "word": " will", "probability": 0.8017578125 }, { "start": 61.64, "end": 61.78, "word": " be", "probability": 0.90673828125 }, { "start": 61.78, "end": 62.06, "word": " something", "probability": 0.72265625 }, { "start": 62.06, "end": 62.5, "word": " very", "probability": 0.7314453125 }, { "start": 62.5, "end": 62.86, "word": " familiar", "probability": 0.7587890625 }, { "start": 62.86, "end": 63.38, "word": ".", "probability": 0.9931640625 } ] }, { "id": 16, "seek": 8008, "start": 63.82, "end": 66.02, "text": " So let's go ahead and get started.", "tokens": [ 50764, 407, 718, 311, 352, 2286, 293, 483, 1409, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.1751358661962592, "compression_ratio": 1.5365853658536586, "no_speech_prob": 0.02886962890625, "words": [ { "start": 63.82, "end": 64.34, "word": " So", "probability": 0.85888671875 }, { "start": 64.34, "end": 64.68, "word": " let's", "probability": 0.857421875 }, { "start": 64.68, "end": 64.84, "word": " go", "probability": 0.89599609375 }, { "start": 64.84, "end": 65.0, "word": " ahead", "probability": 0.8515625 }, { "start": 65.0, "end": 65.1, "word": " and", "probability": 0.89599609375 }, { "start": 65.1, "end": 65.24, "word": " get", "probability": 0.90234375 }, { "start": 65.24, "end": 65.5, "word": " started", "probability": 0.80615234375 }, { "start": 65.5, "end": 66.02, "word": ".", "probability": 0.9873046875 } ] }, { "id": 17, "seek": 8008, "start": 67.6, "end": 71.94, "text": " So who am I? My name is Gavin. I go by the pseudonym GT Klondike.", "tokens": [ 50964, 407, 567, 669, 286, 30, 1222, 1315, 307, 24020, 13, 286, 352, 538, 264, 25505, 532, 12732, 17530, 16053, 684, 1123, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.1751358661962592, "compression_ratio": 1.5365853658536586, "no_speech_prob": 0.02886962890625, "words": [ { "start": 67.6, "end": 68.12, "word": " So", "probability": 0.84130859375 }, { "start": 68.12, "end": 68.38, "word": " who", "probability": 0.6650390625 }, { "start": 68.38, "end": 68.48, "word": " am", "probability": 0.8974609375 }, { "start": 68.48, "end": 68.62, "word": " I", "probability": 0.9931640625 }, { "start": 68.62, "end": 68.7, "word": "?", "probability": 0.89501953125 }, { "start": 68.7, "end": 68.8, "word": " My", "probability": 0.90771484375 }, { "start": 68.8, "end": 68.94, "word": " name", "probability": 0.8134765625 }, { "start": 68.94, "end": 69.06, "word": " is", "probability": 0.9091796875 }, { "start": 69.06, "end": 69.32, "word": " Gavin", "probability": 0.79345703125 }, { "start": 69.32, "end": 69.52, "word": ".", "probability": 0.8623046875 }, { "start": 69.52, "end": 69.98, "word": " I", "probability": 0.9609375 }, { "start": 69.98, "end": 70.14, "word": " go", "probability": 0.8974609375 }, { "start": 70.14, "end": 70.32, "word": " by", "probability": 0.90380859375 }, { "start": 70.32, "end": 70.56, "word": " the", "probability": 0.8134765625 }, { "start": 70.56, "end": 70.9, "word": " pseudonym", "probability": 0.95556640625 }, { "start": 70.9, "end": 71.26, "word": " GT", "probability": 0.5947265625 }, { "start": 71.26, "end": 71.78, "word": " Klondike", "probability": 0.8251953125 }, { "start": 71.78, "end": 71.94, "word": ".", "probability": 0.912109375 } ] }, { "id": 18, "seek": 8008, "start": 71.94, "end": 75.22, "text": " I'm an independent security researcher and a security consultant.", "tokens": [ 51164, 286, 478, 364, 6695, 3825, 21751, 293, 257, 3825, 24676, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.1751358661962592, "compression_ratio": 1.5365853658536586, "no_speech_prob": 0.02886962890625, "words": [ { "start": 71.94, "end": 72.06, "word": " I'm", "probability": 0.98828125 }, { "start": 72.06, "end": 72.26, "word": " an", "probability": 0.89599609375 }, { "start": 72.26, "end": 72.6, "word": " independent", "probability": 0.779296875 }, { "start": 72.6, "end": 72.96, "word": " security", "probability": 0.89453125 }, { "start": 72.96, "end": 73.38, "word": " researcher", "probability": 0.7548828125 }, { "start": 73.38, "end": 73.86, "word": " and", "probability": 0.8876953125 }, { "start": 74.16, "end": 74.4, "word": " a security", "probability": 0.9248046875 }, { "start": 74.4, "end": 74.82, "word": " consultant", "probability": 0.84326171875 }, { "start": 74.82, "end": 75.22, "word": ".", "probability": 0.99365234375 } ] }, { "id": 19, "seek": 8008, "start": 75.22, "end": 79.98, "text": " I have a passion for network security, both attack and defense.", "tokens": [ 51314, 286, 362, 257, 5418, 337, 3209, 3825, 11, 1293, 2690, 293, 7654, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.1751358661962592, "compression_ratio": 1.5365853658536586, "no_speech_prob": 0.02886962890625, "words": [ { "start": 75.22, "end": 75.46, "word": " I", "probability": 0.99951171875 }, { "start": 75.46, "end": 75.6, "word": " have", "probability": 0.88037109375 }, { "start": 75.86, "end": 76.2, "word": " a passion", "probability": 0.8505859375 }, { "start": 76.2, "end": 76.76, "word": " for", "probability": 0.8955078125 }, { "start": 76.76, "end": 77.24, "word": " network", "probability": 0.810546875 }, { "start": 77.24, "end": 77.68, "word": " security", "probability": 0.9267578125 }, { "start": 77.68, "end": 77.94, "word": ",", "probability": 0.90576171875 }, { "start": 77.94, "end": 78.18, "word": " both", "probability": 0.8115234375 }, { "start": 78.18, "end": 78.68, "word": " attack", "probability": 0.80615234375 }, { "start": 78.68, "end": 79.02, "word": " and", "probability": 0.8974609375 }, { "start": 79.02, "end": 79.46, "word": " defense", "probability": 0.83447265625 }, { "start": 79.46, "end": 79.98, "word": ".", "probability": 0.91552734375 } ] }, { "id": 20, "seek": 8008, "start": 80.08, "end": 83.88, "text": " And so through that passion, I run a project called NetSec Explained,", "tokens": [ 51564, 400, 370, 807, 300, 5418, 11, 286, 1190, 257, 1716, 1219, 6188, 29511, 12514, 3563, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.1751358661962592, "compression_ratio": 1.5365853658536586, "no_speech_prob": 0.02886962890625, "words": [ { "start": 80.08, "end": 80.2, "word": " And", "probability": 0.8779296875 }, { "start": 80.2, "end": 80.44, "word": " so", "probability": 0.9033203125 }, { "start": 80.44, "end": 80.66, "word": " through", "probability": 0.7490234375 }, { "start": 80.66, "end": 80.86, "word": " that", "probability": 0.87841796875 }, { "start": 80.86, "end": 81.26, "word": " passion", "probability": 0.85302734375 }, { "start": 81.26, "end": 81.38, "word": ",", "probability": 0.89697265625 }, { "start": 81.38, "end": 81.54, "word": " I", "probability": 0.99951171875 }, { "start": 81.54, "end": 81.72, "word": " run", "probability": 0.87646484375 }, { "start": 81.84, "end": 82.12, "word": " a project", "probability": 0.8359375 }, { "start": 82.12, "end": 82.48, "word": " called", "probability": 0.78759765625 }, { "start": 82.48, "end": 82.86, "word": " NetSec", "probability": 0.6546630859375 }, { "start": 82.86, "end": 83.5, "word": " Explained", "probability": 0.834228515625 }, { "start": 83.5, "end": 83.88, "word": ",", "probability": 0.9267578125 } ] }, { "id": 21, "seek": 10842, "start": 83.88, "end": 89.42, "text": " which is a blog and a YouTube channel where I use intermediate and advanced-level concepts", "tokens": [ 50364, 597, 307, 257, 6968, 293, 257, 3088, 2269, 689, 286, 764, 19376, 293, 7339, 12, 12418, 10392, 50614 ], "temperature": 0.0, "avg_logprob": -0.17693866209851372, "compression_ratio": 1.5475285171102662, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 83.88, "end": 84.08, "word": " which", "probability": 0.49951171875 }, { "start": 84.08, "end": 84.22, "word": " is", "probability": 0.90234375 }, { "start": 84.44, "end": 84.8, "word": " a blog", "probability": 0.80078125 }, { "start": 84.8, "end": 84.96, "word": " and", "probability": 0.87353515625 }, { "start": 85.08, "end": 85.3, "word": " a YouTube", "probability": 0.6962890625 }, { "start": 85.3, "end": 85.78, "word": " channel", "probability": 0.78662109375 }, { "start": 85.78, "end": 86.46, "word": " where", "probability": 0.64599609375 }, { "start": 86.46, "end": 86.96, "word": " I", "probability": 0.99267578125 }, { "start": 86.96, "end": 87.72, "word": " use", "probability": 0.80712890625 }, { "start": 87.72, "end": 88.16, "word": " intermediate", "probability": 0.78271484375 }, { "start": 88.16, "end": 88.48, "word": " and", "probability": 0.8662109375 }, { "start": 88.48, "end": 88.76, "word": " advanced", "probability": 0.85107421875 }, { "start": 88.76, "end": 88.98, "word": "-level", "probability": 0.509490966796875 }, { "start": 88.98, "end": 89.42, "word": " concepts", "probability": 0.744140625 } ] }, { "id": 22, "seek": 10842, "start": 89.42, "end": 93.02, "text": " and try to explain them in a very easy-to-understand way.", "tokens": [ 50614, 293, 853, 281, 2903, 552, 294, 257, 588, 1858, 12, 1353, 12, 6617, 1115, 636, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.17693866209851372, "compression_ratio": 1.5475285171102662, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 89.42, "end": 89.68, "word": " and", "probability": 0.8076171875 }, { "start": 89.68, "end": 89.8, "word": " try", "probability": 0.8037109375 }, { "start": 89.8, "end": 89.9, "word": " to", "probability": 0.8994140625 }, { "start": 89.9, "end": 90.22, "word": " explain", "probability": 0.81884765625 }, { "start": 90.22, "end": 90.52, "word": " them", "probability": 0.73486328125 }, { "start": 90.52, "end": 90.88, "word": " in", "probability": 0.904296875 }, { "start": 90.96, "end": 91.16, "word": " a very", "probability": 0.73681640625 }, { "start": 91.16, "end": 91.5, "word": " easy", "probability": 0.826171875 }, { "start": 91.5, "end": 91.64, "word": "-to", "probability": 0.741943359375 }, { "start": 91.64, "end": 92.1, "word": "-understand", "probability": 0.9080403645833334 }, { "start": 92.1, "end": 92.46, "word": " way", "probability": 0.8935546875 }, { "start": 92.46, "end": 93.02, "word": ".", "probability": 0.96142578125 } ] }, { "id": 23, "seek": 10842, "start": 95.26, "end": 99.6, "text": " So it's usually at this point where, in person, I would kind of ask the audience,", "tokens": [ 50914, 407, 309, 311, 2673, 412, 341, 935, 689, 11, 294, 954, 11, 286, 576, 733, 295, 1029, 264, 4034, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.17693866209851372, "compression_ratio": 1.5475285171102662, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 95.26, "end": 95.82, "word": " So", "probability": 0.6630859375 }, { "start": 95.82, "end": 95.98, "word": " it's", "probability": 0.852783203125 }, { "start": 95.98, "end": 96.18, "word": " usually", "probability": 0.82568359375 }, { "start": 96.18, "end": 96.32, "word": " at", "probability": 0.89208984375 }, { "start": 96.32, "end": 96.44, "word": " this", "probability": 0.8798828125 }, { "start": 96.44, "end": 96.68, "word": " point", "probability": 0.85888671875 }, { "start": 96.68, "end": 97.0, "word": " where", "probability": 0.8583984375 }, { "start": 97.0, "end": 97.18, "word": ",", "probability": 0.473876953125 }, { "start": 97.18, "end": 97.3, "word": " in", "probability": 0.90478515625 }, { "start": 97.3, "end": 97.66, "word": " person", "probability": 0.744140625 }, { "start": 97.66, "end": 97.84, "word": ",", "probability": 0.939453125 }, { "start": 97.84, "end": 97.94, "word": " I", "probability": 0.99658203125 }, { "start": 97.94, "end": 98.06, "word": " would", "probability": 0.83740234375 }, { "start": 98.06, "end": 98.2, "word": " kind", "probability": 0.53955078125 }, { "start": 98.2, "end": 98.28, "word": " of", "probability": 0.90869140625 }, { "start": 98.28, "end": 98.44, "word": " ask", "probability": 0.822265625 }, { "start": 98.44, "end": 98.62, "word": " the", "probability": 0.81103515625 }, { "start": 98.62, "end": 99.04, "word": " audience", "probability": 0.8134765625 }, { "start": 99.04, "end": 99.6, "word": ",", "probability": 0.79150390625 } ] }, { "id": 24, "seek": 10842, "start": 99.6, "end": 103.1, "text": " when you hear the word machine learning, what comes to mind?", "tokens": [ 51114, 562, 291, 1568, 264, 1349, 3479, 2539, 11, 437, 1487, 281, 1575, 30, 51314 ], "temperature": 0.0, "avg_logprob": -0.17693866209851372, "compression_ratio": 1.5475285171102662, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 99.6, "end": 99.88, "word": " when", "probability": 0.1849365234375 }, { "start": 99.88, "end": 100.0, "word": " you", "probability": 0.89404296875 }, { "start": 100.0, "end": 100.14, "word": " hear", "probability": 0.859375 }, { "start": 100.14, "end": 100.26, "word": " the", "probability": 0.80615234375 }, { "start": 100.26, "end": 100.42, "word": " word", "probability": 0.7958984375 }, { "start": 100.42, "end": 100.74, "word": " machine", "probability": 0.178955078125 }, { "start": 100.74, "end": 101.12, "word": " learning", "probability": 0.81298828125 }, { "start": 101.12, "end": 101.54, "word": ",", "probability": 0.9169921875 }, { "start": 101.54, "end": 101.88, "word": " what", "probability": 0.8642578125 }, { "start": 101.88, "end": 102.14, "word": " comes", "probability": 0.80712890625 }, { "start": 102.14, "end": 102.3, "word": " to", "probability": 0.90673828125 }, { "start": 102.3, "end": 102.54, "word": " mind", "probability": 0.8076171875 }, { "start": 102.54, "end": 103.1, "word": "?", "probability": 0.9765625 } ] }, { "id": 25, "seek": 10842, "start": 103.26, "end": 106.66, "text": " Some of the common answers that I get are,", "tokens": [ 51314, 2188, 295, 264, 2689, 6338, 300, 286, 483, 366, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.17693866209851372, "compression_ratio": 1.5475285171102662, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 103.26, "end": 103.6, "word": " Some", "probability": 0.87890625 }, { "start": 103.6, "end": 103.72, "word": " of", "probability": 0.90380859375 }, { "start": 103.72, "end": 104.02, "word": " the", "probability": 0.81396484375 }, { "start": 104.02, "end": 104.5, "word": " common", "probability": 0.703125 }, { "start": 104.5, "end": 104.86, "word": " answers", "probability": 0.81787109375 }, { "start": 104.86, "end": 105.06, "word": " that", "probability": 0.8681640625 }, { "start": 105.06, "end": 105.18, "word": " I", "probability": 0.9990234375 }, { "start": 105.18, "end": 105.46, "word": " get", "probability": 0.9013671875 }, { "start": 105.46, "end": 106.14, "word": " are", "probability": 0.89697265625 }, { "start": 106.14, "end": 106.66, "word": ",", "probability": 0.83837890625 } ] }, { "id": 26, "seek": 10842, "start": 106.66, "end": 112.22, "text": " oh, you need to have a PhD in multivariable calculus and linear algebra,", "tokens": [ 51464, 1954, 11, 291, 643, 281, 362, 257, 14476, 294, 2120, 592, 3504, 712, 33400, 293, 8213, 21989, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.17693866209851372, "compression_ratio": 1.5475285171102662, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 106.66, "end": 106.92, "word": " oh", "probability": 0.292724609375 }, { "start": 106.92, "end": 107.02, "word": ",", "probability": 0.92578125 }, { "start": 107.02, "end": 107.26, "word": " you", "probability": 0.890625 }, { "start": 107.26, "end": 107.58, "word": " need", "probability": 0.8125 }, { "start": 107.58, "end": 107.7, "word": " to", "probability": 0.89990234375 }, { "start": 107.7, "end": 108.08, "word": " have", "probability": 0.88623046875 }, { "start": 108.52, "end": 108.98, "word": " a PhD", "probability": 0.65673828125 }, { "start": 108.98, "end": 109.46, "word": " in", "probability": 0.90185546875 }, { "start": 109.46, "end": 110.26, "word": " multivariable", "probability": 0.9185791015625 }, { "start": 110.26, "end": 110.82, "word": " calculus", "probability": 0.8017578125 }, { "start": 110.82, "end": 111.14, "word": " and", "probability": 0.8388671875 }, { "start": 111.14, "end": 111.36, "word": " linear", "probability": 0.76611328125 }, { "start": 111.36, "end": 111.72, "word": " algebra", "probability": 0.72998046875 }, { "start": 111.72, "end": 112.22, "word": ",", "probability": 0.6044921875 } ] }, { "id": 27, "seek": 13572, "start": 112.22, "end": 118.58, "text": " or Skynet's going to take over the world, or pattern matching.", "tokens": [ 50364, 420, 7324, 2534, 302, 311, 516, 281, 747, 670, 264, 1002, 11, 420, 5102, 14324, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.18458945464854146, "compression_ratio": 1.5252918287937742, "no_speech_prob": 0.00023412704467773438, "words": [ { "start": 112.22, "end": 112.54, "word": " or", "probability": 0.3828125 }, { "start": 112.54, "end": 113.42, "word": " Skynet's", "probability": 0.830078125 }, { "start": 113.42, "end": 113.52, "word": " going", "probability": 0.468017578125 }, { "start": 113.52, "end": 113.62, "word": " to", "probability": 0.9013671875 }, { "start": 113.62, "end": 113.78, "word": " take", "probability": 0.7978515625 }, { "start": 113.78, "end": 113.96, "word": " over", "probability": 0.853515625 }, { "start": 113.96, "end": 114.08, "word": " the", "probability": 0.8046875 }, { "start": 114.08, "end": 114.48, "word": " world", "probability": 0.77001953125 }, { "start": 114.48, "end": 116.82, "word": ",", "probability": 0.71142578125 }, { "start": 116.82, "end": 116.84, "word": " or", "probability": 0.890625 }, { "start": 116.84, "end": 117.68, "word": " pattern", "probability": 0.72265625 }, { "start": 117.68, "end": 118.02, "word": " matching", "probability": 0.6728515625 }, { "start": 118.02, "end": 118.58, "word": ".", "probability": 0.701171875 } ] }, { "id": 28, "seek": 13572, "start": 119.98, "end": 123.46, "text": " So these are all pretty interesting answers,", "tokens": [ 50714, 407, 613, 366, 439, 1238, 1880, 6338, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.18458945464854146, "compression_ratio": 1.5252918287937742, "no_speech_prob": 0.00023412704467773438, "words": [ { "start": 119.98, "end": 120.54, "word": " So", "probability": 0.495361328125 }, { "start": 120.54, "end": 121.1, "word": " these", "probability": 0.456298828125 }, { "start": 121.1, "end": 121.24, "word": " are", "probability": 0.89208984375 }, { "start": 121.24, "end": 121.58, "word": " all", "probability": 0.89501953125 }, { "start": 121.58, "end": 122.18, "word": " pretty", "probability": 0.87548828125 }, { "start": 122.18, "end": 122.56, "word": " interesting", "probability": 0.66552734375 }, { "start": 122.56, "end": 123.12, "word": " answers", "probability": 0.833984375 }, { "start": 123.12, "end": 123.46, "word": ",", "probability": 0.55029296875 } ] }, { "id": 29, "seek": 13572, "start": 123.46, "end": 126.5, "text": " but what we're going to walk through in this workshop is kind of show you that", "tokens": [ 50914, 457, 437, 321, 434, 516, 281, 1792, 807, 294, 341, 13541, 307, 733, 295, 855, 291, 300, 51064 ], "temperature": 0.0, "avg_logprob": -0.18458945464854146, "compression_ratio": 1.5252918287937742, "no_speech_prob": 0.00023412704467773438, "words": [ { "start": 123.46, "end": 123.64, "word": " but", "probability": 0.8955078125 }, { "start": 123.64, "end": 124.32, "word": " what", "probability": 0.87451171875 }, { "start": 124.32, "end": 124.46, "word": " we're", "probability": 0.924560546875 }, { "start": 124.46, "end": 124.54, "word": " going", "probability": 0.82958984375 }, { "start": 124.54, "end": 124.62, "word": " to", "probability": 0.9052734375 }, { "start": 124.62, "end": 124.78, "word": " walk", "probability": 0.80517578125 }, { "start": 124.78, "end": 124.94, "word": " through", "probability": 0.794921875 }, { "start": 124.94, "end": 125.06, "word": " in", "probability": 0.90380859375 }, { "start": 125.06, "end": 125.2, "word": " this", "probability": 0.8798828125 }, { "start": 125.2, "end": 125.56, "word": " workshop", "probability": 0.681640625 }, { "start": 125.56, "end": 125.72, "word": " is", "probability": 0.88818359375 }, { "start": 125.72, "end": 125.86, "word": " kind", "probability": 0.478515625 }, { "start": 125.86, "end": 125.92, "word": " of", "probability": 0.9013671875 }, { "start": 125.92, "end": 126.06, "word": " show", "probability": 0.873046875 }, { "start": 126.06, "end": 126.22, "word": " you", "probability": 0.888671875 }, { "start": 126.22, "end": 126.5, "word": " that", "probability": 0.87939453125 } ] }, { "id": 30, "seek": 13572, "start": 126.5, "end": 128.6, "text": " not all of that is necessary.", "tokens": [ 51064, 406, 439, 295, 300, 307, 4818, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.18458945464854146, "compression_ratio": 1.5252918287937742, "no_speech_prob": 0.00023412704467773438, "words": [ { "start": 126.5, "end": 127.16, "word": " not", "probability": 0.8720703125 }, { "start": 127.16, "end": 127.34, "word": " all", "probability": 0.8974609375 }, { "start": 127.34, "end": 127.44, "word": " of", "probability": 0.88720703125 }, { "start": 127.44, "end": 127.56, "word": " that", "probability": 0.87890625 }, { "start": 127.56, "end": 127.72, "word": " is", "probability": 0.90869140625 }, { "start": 127.72, "end": 128.18, "word": " necessary", "probability": 0.89111328125 }, { "start": 128.18, "end": 128.6, "word": ".", "probability": 0.94140625 } ] }, { "id": 31, "seek": 13572, "start": 128.6, "end": 132.2, "text": " You don't need a PhD in multivariable calculus or linear algebra,", "tokens": [ 51164, 509, 500, 380, 643, 257, 14476, 294, 2120, 592, 3504, 712, 33400, 420, 8213, 21989, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.18458945464854146, "compression_ratio": 1.5252918287937742, "no_speech_prob": 0.00023412704467773438, "words": [ { "start": 128.6, "end": 128.84, "word": " You", "probability": 0.890625 }, { "start": 128.84, "end": 129.02, "word": " don't", "probability": 0.947998046875 }, { "start": 129.02, "end": 129.16, "word": " need", "probability": 0.81494140625 }, { "start": 129.28, "end": 129.62, "word": " a PhD", "probability": 0.7607421875 }, { "start": 129.62, "end": 129.88, "word": " in", "probability": 0.90185546875 }, { "start": 129.88, "end": 130.42, "word": " multivariable", "probability": 0.914794921875 }, { "start": 130.42, "end": 130.84, "word": " calculus", "probability": 0.794921875 }, { "start": 130.84, "end": 131.02, "word": " or", "probability": 0.888671875 }, { "start": 131.02, "end": 131.26, "word": " linear", "probability": 0.84619140625 }, { "start": 131.26, "end": 131.64, "word": " algebra", "probability": 0.72412109375 }, { "start": 131.64, "end": 132.2, "word": ",", "probability": 0.92724609375 } ] }, { "id": 32, "seek": 13572, "start": 132.2, "end": 139.52, "text": " especially with some of the abstraction libraries like Scikit-learn, Keras, TensorFlow, and things like that.", "tokens": [ 51364, 2318, 365, 512, 295, 264, 37765, 15148, 411, 16942, 22681, 12, 306, 1083, 11, 591, 6985, 11, 37624, 11, 293, 721, 411, 300, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.18458945464854146, "compression_ratio": 1.5252918287937742, "no_speech_prob": 0.00023412704467773438, "words": [ { "start": 132.2, "end": 132.6, "word": " especially", "probability": 0.72216796875 }, { "start": 132.6, "end": 133.14, "word": " with", "probability": 0.8212890625 }, { "start": 133.14, "end": 133.42, "word": " some", "probability": 0.814453125 }, { "start": 133.42, "end": 133.58, "word": " of", "probability": 0.90380859375 }, { "start": 133.58, "end": 133.76, "word": " the", "probability": 0.81591796875 }, { "start": 133.76, "end": 134.2, "word": " abstraction", "probability": 0.5380859375 }, { "start": 134.2, "end": 134.74, "word": " libraries", "probability": 0.90283203125 }, { "start": 134.74, "end": 135.16, "word": " like", "probability": 0.73486328125 }, { "start": 135.16, "end": 135.54, "word": " Scikit", "probability": 0.69482421875 }, { "start": 135.54, "end": 135.96, "word": "-learn", "probability": 0.85595703125 }, { "start": 135.96, "end": 136.26, "word": ",", "probability": 0.9599609375 }, { "start": 136.26, "end": 136.62, "word": " Keras", "probability": 0.89990234375 }, { "start": 136.62, "end": 136.9, "word": ",", "probability": 0.986328125 }, { "start": 136.9, "end": 137.26, "word": " TensorFlow", "probability": 0.76806640625 }, { "start": 137.26, "end": 138.04, "word": ",", "probability": 0.81591796875 }, { "start": 138.04, "end": 138.22, "word": " and", "probability": 0.888671875 }, { "start": 138.22, "end": 138.44, "word": " things", "probability": 0.73828125 }, { "start": 138.44, "end": 138.64, "word": " like", "probability": 0.87744140625 }, { "start": 138.64, "end": 139.0, "word": " that", "probability": 0.8837890625 }, { "start": 139.0, "end": 139.52, "word": ".", "probability": 0.97314453125 } ] }, { "id": 33, "seek": 16488, "start": 139.52, "end": 144.88, "text": " And then as far as machines taking over the world, not quite.", "tokens": [ 50364, 400, 550, 382, 1400, 382, 8379, 1940, 670, 264, 1002, 11, 406, 1596, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.2345448367945526, "compression_ratio": 1.828193832599119, "no_speech_prob": 2.0802021026611328e-05, "words": [ { "start": 139.52, "end": 139.68, "word": " And", "probability": 0.404296875 }, { "start": 139.68, "end": 139.8, "word": " then", "probability": 0.6474609375 }, { "start": 139.8, "end": 139.92, "word": " as", "probability": 0.80810546875 }, { "start": 139.92, "end": 140.14, "word": " far", "probability": 0.89208984375 }, { "start": 140.14, "end": 140.5, "word": " as", "probability": 0.90185546875 }, { "start": 140.5, "end": 141.28, "word": " machines", "probability": 0.66455078125 }, { "start": 141.28, "end": 141.58, "word": " taking", "probability": 0.83154296875 }, { "start": 141.58, "end": 141.76, "word": " over", "probability": 0.8857421875 }, { "start": 141.76, "end": 141.92, "word": " the", "probability": 0.8173828125 }, { "start": 141.92, "end": 142.28, "word": " world", "probability": 0.8857421875 }, { "start": 142.28, "end": 142.66, "word": ",", "probability": 0.64697265625 }, { "start": 142.66, "end": 143.9, "word": " not", "probability": 0.6220703125 }, { "start": 143.9, "end": 144.24, "word": " quite", "probability": 0.89501953125 }, { "start": 144.24, "end": 144.88, "word": ".", "probability": 0.97265625 } ] }, { "id": 34, "seek": 16488, "start": 147.14, "end": 152.3, "text": " So machine learning and how it fits in the broader idea of artificial intelligence.", "tokens": [ 50764, 407, 3479, 2539, 293, 577, 309, 9001, 294, 264, 13227, 1558, 295, 11677, 7599, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.2345448367945526, "compression_ratio": 1.828193832599119, "no_speech_prob": 2.0802021026611328e-05, "words": [ { "start": 147.14, "end": 147.78, "word": " So", "probability": 0.7294921875 }, { "start": 147.78, "end": 148.42, "word": " machine", "probability": 0.53759765625 }, { "start": 148.42, "end": 148.74, "word": " learning", "probability": 0.849609375 }, { "start": 148.74, "end": 148.96, "word": " and", "probability": 0.849609375 }, { "start": 148.96, "end": 149.12, "word": " how", "probability": 0.90966796875 }, { "start": 149.12, "end": 149.3, "word": " it", "probability": 0.90283203125 }, { "start": 149.3, "end": 149.54, "word": " fits", "probability": 0.8896484375 }, { "start": 149.54, "end": 149.8, "word": " in", "probability": 0.88232421875 }, { "start": 149.8, "end": 150.12, "word": " the", "probability": 0.80419921875 }, { "start": 150.12, "end": 150.62, "word": " broader", "probability": 0.638671875 }, { "start": 150.62, "end": 150.96, "word": " idea", "probability": 0.7724609375 }, { "start": 150.96, "end": 151.12, "word": " of", "probability": 0.89453125 }, { "start": 151.12, "end": 151.46, "word": " artificial", "probability": 0.80615234375 }, { "start": 151.46, "end": 151.98, "word": " intelligence", "probability": 0.68798828125 }, { "start": 151.98, "end": 152.3, "word": ".", "probability": 0.94384765625 } ] }, { "id": 35, "seek": 16488, "start": 152.3, "end": 157.2, "text": " So artificial intelligence is this big umbrella term that kind of is a catch-all", "tokens": [ 50964, 407, 11677, 7599, 307, 341, 955, 21925, 1433, 300, 733, 295, 307, 257, 3745, 12, 336, 51214 ], "temperature": 0.0, "avg_logprob": -0.2345448367945526, "compression_ratio": 1.828193832599119, "no_speech_prob": 2.0802021026611328e-05, "words": [ { "start": 152.3, "end": 152.5, "word": " So", "probability": 0.7412109375 }, { "start": 152.5, "end": 152.96, "word": " artificial", "probability": 0.787109375 }, { "start": 152.96, "end": 153.46, "word": " intelligence", "probability": 0.7119140625 }, { "start": 153.46, "end": 153.72, "word": " is", "probability": 0.8994140625 }, { "start": 153.72, "end": 153.9, "word": " this", "probability": 0.85546875 }, { "start": 153.9, "end": 154.34, "word": " big", "probability": 0.89453125 }, { "start": 154.34, "end": 154.78, "word": " umbrella", "probability": 0.7724609375 }, { "start": 154.78, "end": 155.3, "word": " term", "probability": 0.8115234375 }, { "start": 155.3, "end": 155.5, "word": " that", "probability": 0.80078125 }, { "start": 155.5, "end": 155.7, "word": " kind", "probability": 0.70068359375 }, { "start": 155.7, "end": 155.86, "word": " of", "probability": 0.908203125 }, { "start": 155.86, "end": 156.4, "word": " is", "probability": 0.89599609375 }, { "start": 156.6, "end": 156.92, "word": " a catch", "probability": 0.8046875 }, { "start": 156.92, "end": 157.2, "word": "-all", "probability": 0.6883544921875 } ] }, { "id": 36, "seek": 16488, "start": 157.2, "end": 161.36, "text": " for different types of ways that machines operate.", "tokens": [ 51214, 337, 819, 3467, 295, 2098, 300, 8379, 9651, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.2345448367945526, "compression_ratio": 1.828193832599119, "no_speech_prob": 2.0802021026611328e-05, "words": [ { "start": 157.2, "end": 157.48, "word": " for", "probability": 0.9013671875 }, { "start": 157.48, "end": 157.86, "word": " different", "probability": 0.6953125 }, { "start": 157.86, "end": 158.22, "word": " types", "probability": 0.75048828125 }, { "start": 158.22, "end": 158.94, "word": " of", "probability": 0.90625 }, { "start": 158.94, "end": 159.98, "word": " ways", "probability": 0.80126953125 }, { "start": 159.98, "end": 160.16, "word": " that", "probability": 0.87548828125 }, { "start": 160.16, "end": 160.48, "word": " machines", "probability": 0.82861328125 }, { "start": 160.48, "end": 160.96, "word": " operate", "probability": 0.7685546875 }, { "start": 160.96, "end": 161.36, "word": ".", "probability": 0.96630859375 } ] }, { "id": 37, "seek": 16488, "start": 161.36, "end": 165.12, "text": " So back in the past, when they first invented digital calculators,", "tokens": [ 51414, 407, 646, 294, 264, 1791, 11, 562, 436, 700, 14479, 4562, 4322, 3391, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.2345448367945526, "compression_ratio": 1.828193832599119, "no_speech_prob": 2.0802021026611328e-05, "words": [ { "start": 161.36, "end": 161.48, "word": " So", "probability": 0.82958984375 }, { "start": 161.48, "end": 161.76, "word": " back", "probability": 0.77490234375 }, { "start": 161.76, "end": 161.86, "word": " in", "probability": 0.90673828125 }, { "start": 161.86, "end": 161.98, "word": " the", "probability": 0.8115234375 }, { "start": 161.98, "end": 162.32, "word": " past", "probability": 0.79541015625 }, { "start": 162.32, "end": 162.38, "word": ",", "probability": 0.34033203125 }, { "start": 162.38, "end": 162.48, "word": " when", "probability": 0.8720703125 }, { "start": 162.48, "end": 162.62, "word": " they", "probability": 0.72998046875 }, { "start": 162.62, "end": 162.92, "word": " first", "probability": 0.83349609375 }, { "start": 162.92, "end": 163.32, "word": " invented", "probability": 0.73681640625 }, { "start": 163.32, "end": 164.34, "word": " digital", "probability": 0.8408203125 }, { "start": 164.34, "end": 165.02, "word": " calculators", "probability": 0.93017578125 }, { "start": 165.02, "end": 165.12, "word": ",", "probability": 0.92138671875 } ] }, { "id": 38, "seek": 16488, "start": 165.12, "end": 168.68, "text": " they thought that was machine intelligence or artificial intelligence.", "tokens": [ 51614, 436, 1194, 300, 390, 3479, 7599, 420, 11677, 7599, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.2345448367945526, "compression_ratio": 1.828193832599119, "no_speech_prob": 2.0802021026611328e-05, "words": [ { "start": 165.12, "end": 165.24, "word": " they", "probability": 0.732421875 }, { "start": 165.24, "end": 165.36, "word": " thought", "probability": 0.84228515625 }, { "start": 165.36, "end": 165.56, "word": " that", "probability": 0.8798828125 }, { "start": 165.56, "end": 165.78, "word": " was", "probability": 0.89208984375 }, { "start": 165.78, "end": 166.22, "word": " machine", "probability": 0.7421875 }, { "start": 166.22, "end": 166.9, "word": " intelligence", "probability": 0.6953125 }, { "start": 166.9, "end": 167.2, "word": " or", "probability": 0.79052734375 }, { "start": 167.2, "end": 167.54, "word": " artificial", "probability": 0.81884765625 }, { "start": 167.54, "end": 168.16, "word": " intelligence", "probability": 0.71142578125 }, { "start": 168.16, "end": 168.68, "word": ".", "probability": 0.61767578125 } ] }, { "id": 39, "seek": 19132, "start": 168.68, "end": 171.4, "text": " And then it came to video game AI.", "tokens": [ 50364, 400, 550, 309, 1361, 281, 960, 1216, 7318, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.2092013869020674, "compression_ratio": 1.6544715447154472, "no_speech_prob": 6.711483001708984e-05, "words": [ { "start": 168.68, "end": 168.94, "word": " And", "probability": 0.1978759765625 }, { "start": 168.94, "end": 169.06, "word": " then", "probability": 0.69482421875 }, { "start": 169.06, "end": 169.18, "word": " it", "probability": 0.8779296875 }, { "start": 169.18, "end": 169.42, "word": " came", "probability": 0.80029296875 }, { "start": 169.42, "end": 169.74, "word": " to", "probability": 0.90283203125 }, { "start": 169.74, "end": 170.02, "word": " video", "probability": 0.7412109375 }, { "start": 170.02, "end": 170.34, "word": " game", "probability": 0.80712890625 }, { "start": 170.34, "end": 170.76, "word": " AI", "probability": 0.7890625 }, { "start": 170.76, "end": 171.4, "word": ".", "probability": 0.96044921875 } ] }, { "id": 40, "seek": 19132, "start": 172.42, "end": 176.48, "text": " Today we also see things like rules-based artificial intelligence,", "tokens": [ 50514, 2692, 321, 611, 536, 721, 411, 4474, 12, 6032, 11677, 7599, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.2092013869020674, "compression_ratio": 1.6544715447154472, "no_speech_prob": 6.711483001708984e-05, "words": [ { "start": 172.42, "end": 172.6, "word": " Today", "probability": 0.787109375 }, { "start": 172.6, "end": 172.78, "word": " we", "probability": 0.54052734375 }, { "start": 172.78, "end": 172.98, "word": " also", "probability": 0.814453125 }, { "start": 172.98, "end": 173.44, "word": " see", "probability": 0.810546875 }, { "start": 173.44, "end": 174.22, "word": " things", "probability": 0.6923828125 }, { "start": 174.22, "end": 174.62, "word": " like", "probability": 0.876953125 }, { "start": 174.62, "end": 174.98, "word": " rules", "probability": 0.6865234375 }, { "start": 174.98, "end": 175.22, "word": "-based", "probability": 0.75 }, { "start": 175.22, "end": 175.62, "word": " artificial", "probability": 0.8037109375 }, { "start": 175.62, "end": 176.16, "word": " intelligence", "probability": 0.673828125 }, { "start": 176.16, "end": 176.48, "word": ",", "probability": 0.182373046875 } ] }, { "id": 41, "seek": 19132, "start": 176.48, "end": 178.56, "text": " or classic image recognition.", "tokens": [ 50714, 420, 7230, 3256, 11150, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.2092013869020674, "compression_ratio": 1.6544715447154472, "no_speech_prob": 6.711483001708984e-05, "words": [ { "start": 176.48, "end": 176.64, "word": " or", "probability": 0.90185546875 }, { "start": 176.64, "end": 177.18, "word": " classic", "probability": 0.8095703125 }, { "start": 177.18, "end": 177.5, "word": " image", "probability": 0.83447265625 }, { "start": 177.5, "end": 177.98, "word": " recognition", "probability": 0.84228515625 }, { "start": 177.98, "end": 178.56, "word": ".", "probability": 0.96875 } ] }, { "id": 42, "seek": 19132, "start": 178.56, "end": 181.08, "text": " So there's a bunch of different artificial intelligence technologies", "tokens": [ 50814, 407, 456, 311, 257, 3840, 295, 819, 11677, 7599, 7943, 50964 ], "temperature": 0.0, "avg_logprob": -0.2092013869020674, "compression_ratio": 1.6544715447154472, "no_speech_prob": 6.711483001708984e-05, "words": [ { "start": 178.56, "end": 178.7, "word": " So", "probability": 0.79248046875 }, { "start": 178.7, "end": 178.86, "word": " there's", "probability": 0.878173828125 }, { "start": 178.96, "end": 179.1, "word": " a bunch", "probability": 0.81103515625 }, { "start": 179.1, "end": 179.22, "word": " of", "probability": 0.9033203125 }, { "start": 179.22, "end": 179.46, "word": " different", "probability": 0.63623046875 }, { "start": 179.46, "end": 179.82, "word": " artificial", "probability": 0.82568359375 }, { "start": 179.82, "end": 180.5, "word": " intelligence", "probability": 0.701171875 }, { "start": 180.5, "end": 181.08, "word": " technologies", "probability": 0.900390625 } ] }, { "id": 43, "seek": 19132, "start": 181.08, "end": 183.32, "text": " that aren't necessarily machine learning.", "tokens": [ 50964, 300, 3212, 380, 4725, 3479, 2539, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.2092013869020674, "compression_ratio": 1.6544715447154472, "no_speech_prob": 6.711483001708984e-05, "words": [ { "start": 181.08, "end": 181.32, "word": " that", "probability": 0.84423828125 }, { "start": 181.32, "end": 181.44, "word": " aren't", "probability": 0.901611328125 }, { "start": 181.44, "end": 181.94, "word": " necessarily", "probability": 0.76953125 }, { "start": 181.94, "end": 182.36, "word": " machine", "probability": 0.6875 }, { "start": 182.36, "end": 182.68, "word": " learning", "probability": 0.82763671875 }, { "start": 182.68, "end": 183.32, "word": ".", "probability": 0.994140625 } ] }, { "id": 44, "seek": 19132, "start": 183.56, "end": 187.96, "text": " Machine learning itself is more about applied statistics,", "tokens": [ 51064, 22155, 2539, 2564, 307, 544, 466, 6456, 12523, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.2092013869020674, "compression_ratio": 1.6544715447154472, "no_speech_prob": 6.711483001708984e-05, "words": [ { "start": 183.56, "end": 183.96, "word": " Machine", "probability": 0.712890625 }, { "start": 183.96, "end": 184.28, "word": " learning", "probability": 0.83056640625 }, { "start": 184.28, "end": 184.78, "word": " itself", "probability": 0.7646484375 }, { "start": 184.78, "end": 185.54, "word": " is", "probability": 0.88720703125 }, { "start": 185.54, "end": 185.9, "word": " more", "probability": 0.88330078125 }, { "start": 185.9, "end": 186.3, "word": " about", "probability": 0.83203125 }, { "start": 186.3, "end": 187.1, "word": " applied", "probability": 0.6513671875 }, { "start": 187.1, "end": 187.78, "word": " statistics", "probability": 0.875 }, { "start": 187.78, "end": 187.96, "word": ",", "probability": 0.212890625 } ] }, { "id": 45, "seek": 19132, "start": 187.96, "end": 192.14, "text": " and a merge between what used to be considered business intelligence,", "tokens": [ 51314, 293, 257, 22183, 1296, 437, 1143, 281, 312, 4888, 1606, 7599, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.2092013869020674, "compression_ratio": 1.6544715447154472, "no_speech_prob": 6.711483001708984e-05, "words": [ { "start": 187.96, "end": 188.04, "word": " and", "probability": 0.83837890625 }, { "start": 188.14, "end": 188.38, "word": " a merge", "probability": 0.87451171875 }, { "start": 188.38, "end": 188.88, "word": " between", "probability": 0.78173828125 }, { "start": 188.88, "end": 189.52, "word": " what", "probability": 0.869140625 }, { "start": 189.52, "end": 189.7, "word": " used", "probability": 0.80322265625 }, { "start": 189.7, "end": 189.78, "word": " to", "probability": 0.90673828125 }, { "start": 189.78, "end": 189.9, "word": " be", "probability": 0.904296875 }, { "start": 189.9, "end": 190.38, "word": " considered", "probability": 0.65234375 }, { "start": 190.38, "end": 191.14, "word": " business", "probability": 0.8583984375 }, { "start": 191.14, "end": 191.82, "word": " intelligence", "probability": 0.69287109375 }, { "start": 191.82, "end": 192.14, "word": ",", "probability": 0.611328125 } ] }, { "id": 46, "seek": 19132, "start": 192.14, "end": 195.12, "text": " and statisticians would do this job,", "tokens": [ 51514, 293, 29588, 2567, 576, 360, 341, 1691, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.2092013869020674, "compression_ratio": 1.6544715447154472, "no_speech_prob": 6.711483001708984e-05, "words": [ { "start": 192.14, "end": 192.52, "word": " and", "probability": 0.88818359375 }, { "start": 192.52, "end": 193.76, "word": " statisticians", "probability": 0.849853515625 }, { "start": 193.76, "end": 194.06, "word": " would", "probability": 0.80859375 }, { "start": 194.06, "end": 194.18, "word": " do", "probability": 0.90380859375 }, { "start": 194.18, "end": 194.36, "word": " this", "probability": 0.88427734375 }, { "start": 194.36, "end": 194.64, "word": " job", "probability": 0.90478515625 }, { "start": 194.64, "end": 195.12, "word": ",", "probability": 0.76123046875 } ] }, { "id": 47, "seek": 21922, "start": 195.12, "end": 197.06, "text": " and computer science.", "tokens": [ 50364, 293, 3820, 3497, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.18234536574058927, "compression_ratio": 1.763265306122449, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 195.12, "end": 195.82, "word": " and", "probability": 0.419189453125 }, { "start": 195.82, "end": 196.24, "word": " computer", "probability": 0.58740234375 }, { "start": 196.24, "end": 196.82, "word": " science", "probability": 0.87451171875 }, { "start": 196.82, "end": 197.06, "word": ".", "probability": 0.427978515625 } ] }, { "id": 48, "seek": 21922, "start": 197.06, "end": 202.16, "text": " With the improvement of computing resources such as memory and CPU,", "tokens": [ 50464, 2022, 264, 10444, 295, 15866, 3593, 1270, 382, 4675, 293, 13199, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.18234536574058927, "compression_ratio": 1.763265306122449, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 197.06, "end": 197.18, "word": " With", "probability": 0.89990234375 }, { "start": 197.18, "end": 197.58, "word": " the", "probability": 0.802734375 }, { "start": 197.58, "end": 198.22, "word": " improvement", "probability": 0.6201171875 }, { "start": 198.22, "end": 198.78, "word": " of", "probability": 0.90576171875 }, { "start": 198.78, "end": 199.48, "word": " computing", "probability": 0.77001953125 }, { "start": 199.48, "end": 200.0, "word": " resources", "probability": 0.79150390625 }, { "start": 200.0, "end": 200.34, "word": " such", "probability": 0.654296875 }, { "start": 200.34, "end": 200.48, "word": " as", "probability": 0.9052734375 }, { "start": 200.48, "end": 200.76, "word": " memory", "probability": 0.8095703125 }, { "start": 200.76, "end": 200.96, "word": " and", "probability": 0.8818359375 }, { "start": 200.96, "end": 201.34, "word": " CPU", "probability": 0.88330078125 }, { "start": 201.34, "end": 202.16, "word": ",", "probability": 0.76318359375 } ] }, { "id": 49, "seek": 21922, "start": 202.38, "end": 205.88, "text": " a lot more power can be put behind some of these algorithms.", "tokens": [ 50714, 257, 688, 544, 1347, 393, 312, 829, 2261, 512, 295, 613, 14642, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.18234536574058927, "compression_ratio": 1.763265306122449, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 202.38, "end": 202.58, "word": " a lot", "probability": 0.8935546875 }, { "start": 202.58, "end": 202.98, "word": " more", "probability": 0.8896484375 }, { "start": 202.98, "end": 203.56, "word": " power", "probability": 0.8193359375 }, { "start": 203.56, "end": 203.76, "word": " can", "probability": 0.89306640625 }, { "start": 203.76, "end": 203.92, "word": " be", "probability": 0.90576171875 }, { "start": 203.92, "end": 204.14, "word": " put", "probability": 0.88916015625 }, { "start": 204.14, "end": 204.44, "word": " behind", "probability": 0.8427734375 }, { "start": 204.44, "end": 204.64, "word": " some", "probability": 0.7939453125 }, { "start": 204.64, "end": 204.72, "word": " of", "probability": 0.9052734375 }, { "start": 204.72, "end": 204.86, "word": " these", "probability": 0.7080078125 }, { "start": 204.86, "end": 205.32, "word": " algorithms", "probability": 0.87841796875 }, { "start": 205.32, "end": 205.88, "word": ".", "probability": 0.9453125 } ] }, { "id": 50, "seek": 21922, "start": 206.64, "end": 210.26, "text": " And then deep learning is specifically talking about deep neural networks.", "tokens": [ 50914, 400, 550, 2452, 2539, 307, 4682, 1417, 466, 2452, 18161, 9590, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.18234536574058927, "compression_ratio": 1.763265306122449, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 206.64, "end": 206.72, "word": " And", "probability": 0.75927734375 }, { "start": 206.72, "end": 206.9, "word": " then", "probability": 0.74609375 }, { "start": 206.9, "end": 207.12, "word": " deep", "probability": 0.810546875 }, { "start": 207.12, "end": 207.4, "word": " learning", "probability": 0.8203125 }, { "start": 207.4, "end": 208.02, "word": " is", "probability": 0.880859375 }, { "start": 208.02, "end": 208.48, "word": " specifically", "probability": 0.740234375 }, { "start": 208.48, "end": 208.88, "word": " talking", "probability": 0.75390625 }, { "start": 208.88, "end": 209.14, "word": " about", "probability": 0.81494140625 }, { "start": 209.14, "end": 209.42, "word": " deep", "probability": 0.91455078125 }, { "start": 209.42, "end": 209.68, "word": " neural", "probability": 0.8896484375 }, { "start": 209.68, "end": 210.14, "word": " networks", "probability": 0.6435546875 }, { "start": 210.14, "end": 210.26, "word": ".", "probability": 0.96533203125 } ] }, { "id": 51, "seek": 21922, "start": 210.26, "end": 213.68, "text": " Neural networks are a type of machine learning algorithm,", "tokens": [ 51114, 1734, 1807, 9590, 366, 257, 2010, 295, 3479, 2539, 9284, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.18234536574058927, "compression_ratio": 1.763265306122449, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 210.26, "end": 210.38, "word": " Neural", "probability": 0.945068359375 }, { "start": 210.38, "end": 210.72, "word": " networks", "probability": 0.685546875 }, { "start": 210.72, "end": 210.98, "word": " are", "probability": 0.8916015625 }, { "start": 211.08, "end": 211.26, "word": " a type", "probability": 0.9306640625 }, { "start": 211.26, "end": 211.4, "word": " of", "probability": 0.90625 }, { "start": 211.4, "end": 211.7, "word": " machine", "probability": 0.712890625 }, { "start": 211.7, "end": 212.08, "word": " learning", "probability": 0.81689453125 }, { "start": 212.08, "end": 213.28, "word": " algorithm", "probability": 0.7822265625 }, { "start": 213.28, "end": 213.68, "word": ",", "probability": 0.38330078125 } ] }, { "id": 52, "seek": 21922, "start": 213.68, "end": 218.14, "text": " and then deep learning allows us to stack layers on top of these.", "tokens": [ 51264, 293, 550, 2452, 2539, 4045, 505, 281, 8630, 7914, 322, 1192, 295, 613, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.18234536574058927, "compression_ratio": 1.763265306122449, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 213.68, "end": 213.76, "word": " and", "probability": 0.8837890625 }, { "start": 213.76, "end": 213.98, "word": " then", "probability": 0.71484375 }, { "start": 213.98, "end": 214.26, "word": " deep", "probability": 0.92578125 }, { "start": 214.26, "end": 214.66, "word": " learning", "probability": 0.833984375 }, { "start": 214.66, "end": 215.74, "word": " allows", "probability": 0.80322265625 }, { "start": 215.74, "end": 215.96, "word": " us", "probability": 0.90087890625 }, { "start": 215.96, "end": 216.14, "word": " to", "probability": 0.90673828125 }, { "start": 216.14, "end": 216.42, "word": " stack", "probability": 0.9287109375 }, { "start": 216.42, "end": 216.76, "word": " layers", "probability": 0.89501953125 }, { "start": 216.76, "end": 216.96, "word": " on", "probability": 0.90380859375 }, { "start": 216.96, "end": 217.18, "word": " top", "probability": 0.8154296875 }, { "start": 217.18, "end": 217.32, "word": " of", "probability": 0.90380859375 }, { "start": 217.32, "end": 217.58, "word": " these", "probability": 0.69970703125 }, { "start": 217.58, "end": 218.14, "word": ".", "probability": 0.98974609375 } ] }, { "id": 53, "seek": 21922, "start": 218.52, "end": 223.02, "text": " So deep learning, usually these are referred to for convolutional neural networks,", "tokens": [ 51514, 407, 2452, 2539, 11, 2673, 613, 366, 10839, 281, 337, 45216, 304, 18161, 9590, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.18234536574058927, "compression_ratio": 1.763265306122449, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 218.52, "end": 218.78, "word": " So", "probability": 0.8447265625 }, { "start": 218.78, "end": 219.18, "word": " deep", "probability": 0.73583984375 }, { "start": 219.18, "end": 219.54, "word": " learning", "probability": 0.841796875 }, { "start": 219.54, "end": 219.92, "word": ",", "probability": 0.724609375 }, { "start": 219.92, "end": 220.34, "word": " usually", "probability": 0.84716796875 }, { "start": 220.34, "end": 220.58, "word": " these", "probability": 0.68115234375 }, { "start": 220.58, "end": 220.68, "word": " are", "probability": 0.89111328125 }, { "start": 220.68, "end": 220.92, "word": " referred", "probability": 0.837890625 }, { "start": 220.92, "end": 221.28, "word": " to", "probability": 0.90283203125 }, { "start": 221.28, "end": 221.7, "word": " for", "probability": 0.8740234375 }, { "start": 221.7, "end": 222.5, "word": " convolutional", "probability": 0.870849609375 }, { "start": 222.5, "end": 222.68, "word": " neural", "probability": 0.921875 }, { "start": 222.68, "end": 223.02, "word": " networks", "probability": 0.671875 }, { "start": 223.02, "end": 223.02, "word": ",", "probability": 0.71728515625 } ] }, { "id": 54, "seek": 24868, "start": 223.02, "end": 225.9, "text": " which are used for image recognition, primarily.", "tokens": [ 50364, 597, 366, 1143, 337, 3256, 11150, 11, 10029, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.19810267125389405, "compression_ratio": 1.6895306859205776, "no_speech_prob": 0.004398345947265625, "words": [ { "start": 223.02, "end": 223.24, "word": " which", "probability": 0.52099609375 }, { "start": 223.24, "end": 223.36, "word": " are", "probability": 0.876953125 }, { "start": 223.36, "end": 223.64, "word": " used", "probability": 0.833984375 }, { "start": 223.64, "end": 223.98, "word": " for", "probability": 0.88134765625 }, { "start": 223.98, "end": 224.28, "word": " image", "probability": 0.80419921875 }, { "start": 224.28, "end": 224.86, "word": " recognition", "probability": 0.87109375 }, { "start": 224.86, "end": 225.12, "word": ",", "probability": 0.22998046875 }, { "start": 225.12, "end": 225.4, "word": " primarily", "probability": 0.71337890625 }, { "start": 225.4, "end": 225.9, "word": ".", "probability": 0.236572265625 } ] }, { "id": 55, "seek": 24868, "start": 225.9, "end": 230.24, "text": " And then recurrent neural networks, which are used for cyclical pattern recognition,", "tokens": [ 50514, 400, 550, 18680, 1753, 18161, 9590, 11, 597, 366, 1143, 337, 19474, 804, 5102, 11150, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.19810267125389405, "compression_ratio": 1.6895306859205776, "no_speech_prob": 0.004398345947265625, "words": [ { "start": 225.9, "end": 225.96, "word": " And", "probability": 0.80810546875 }, { "start": 225.96, "end": 226.24, "word": " then", "probability": 0.65673828125 }, { "start": 226.24, "end": 226.88, "word": " recurrent", "probability": 0.8173828125 }, { "start": 226.88, "end": 227.06, "word": " neural", "probability": 0.9306640625 }, { "start": 227.06, "end": 227.46, "word": " networks", "probability": 0.65234375 }, { "start": 227.46, "end": 227.58, "word": ",", "probability": 0.615234375 }, { "start": 227.58, "end": 227.68, "word": " which", "probability": 0.90869140625 }, { "start": 227.68, "end": 227.78, "word": " are", "probability": 0.900390625 }, { "start": 227.78, "end": 228.04, "word": " used", "probability": 0.814453125 }, { "start": 228.04, "end": 228.46, "word": " for", "probability": 0.89599609375 }, { "start": 228.46, "end": 229.12, "word": " cyclical", "probability": 0.833984375 }, { "start": 229.12, "end": 229.44, "word": " pattern", "probability": 0.728515625 }, { "start": 229.44, "end": 229.98, "word": " recognition", "probability": 0.8037109375 }, { "start": 229.98, "end": 230.24, "word": ",", "probability": 0.7236328125 } ] }, { "id": 56, "seek": 24868, "start": 230.24, "end": 231.94, "text": " such as heartbeat monitors.", "tokens": [ 50714, 1270, 382, 34851, 26518, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.19810267125389405, "compression_ratio": 1.6895306859205776, "no_speech_prob": 0.004398345947265625, "words": [ { "start": 230.24, "end": 230.42, "word": " such", "probability": 0.8740234375 }, { "start": 230.42, "end": 230.58, "word": " as", "probability": 0.90625 }, { "start": 230.58, "end": 230.86, "word": " heartbeat", "probability": 0.890625 }, { "start": 230.86, "end": 231.38, "word": " monitors", "probability": 0.87158203125 }, { "start": 231.38, "end": 231.94, "word": ".", "probability": 0.98974609375 } ] }, { "id": 57, "seek": 24868, "start": 234.06, "end": 236.06, "text": " But if we were to find all of this,", "tokens": [ 50914, 583, 498, 321, 645, 281, 915, 439, 295, 341, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.19810267125389405, "compression_ratio": 1.6895306859205776, "no_speech_prob": 0.004398345947265625, "words": [ { "start": 234.06, "end": 234.62, "word": " But", "probability": 0.818359375 }, { "start": 234.62, "end": 234.7, "word": " if", "probability": 0.857421875 }, { "start": 234.7, "end": 234.78, "word": " we", "probability": 0.896484375 }, { "start": 234.78, "end": 234.88, "word": " were", "probability": 0.87646484375 }, { "start": 234.88, "end": 235.0, "word": " to", "probability": 0.8818359375 }, { "start": 235.0, "end": 235.18, "word": " find", "probability": 0.60498046875 }, { "start": 235.18, "end": 235.36, "word": " all", "probability": 0.89599609375 }, { "start": 235.36, "end": 235.52, "word": " of", "probability": 0.7900390625 }, { "start": 235.52, "end": 235.76, "word": " this", "probability": 0.8720703125 }, { "start": 235.76, "end": 236.06, "word": ",", "probability": 0.94384765625 } ] }, { "id": 58, "seek": 24868, "start": 236.06, "end": 239.8, "text": " I would say machine learning is a set of statistical techniques", "tokens": [ 51014, 286, 576, 584, 3479, 2539, 307, 257, 992, 295, 22820, 7512, 51214 ], "temperature": 0.0, "avg_logprob": -0.19810267125389405, "compression_ratio": 1.6895306859205776, "no_speech_prob": 0.004398345947265625, "words": [ { "start": 236.06, "end": 236.52, "word": " I", "probability": 0.9853515625 }, { "start": 236.52, "end": 236.68, "word": " would", "probability": 0.8564453125 }, { "start": 236.68, "end": 237.0, "word": " say", "probability": 0.90625 }, { "start": 237.0, "end": 237.34, "word": " machine", "probability": 0.58154296875 }, { "start": 237.34, "end": 237.58, "word": " learning", "probability": 0.84326171875 }, { "start": 237.58, "end": 237.92, "word": " is", "probability": 0.9033203125 }, { "start": 238.2, "end": 238.5, "word": " a set", "probability": 0.87744140625 }, { "start": 238.5, "end": 238.74, "word": " of", "probability": 0.90673828125 }, { "start": 238.74, "end": 239.24, "word": " statistical", "probability": 0.81591796875 }, { "start": 239.24, "end": 239.8, "word": " techniques", "probability": 0.8173828125 } ] }, { "id": 59, "seek": 24868, "start": 239.8, "end": 243.2, "text": " that enables the process of information mining,", "tokens": [ 51214, 300, 17077, 264, 1399, 295, 1589, 15512, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.19810267125389405, "compression_ratio": 1.6895306859205776, "no_speech_prob": 0.004398345947265625, "words": [ { "start": 239.8, "end": 240.38, "word": " that", "probability": 0.8623046875 }, { "start": 240.38, "end": 240.82, "word": " enables", "probability": 0.71533203125 }, { "start": 240.82, "end": 241.04, "word": " the", "probability": 0.80810546875 }, { "start": 241.04, "end": 241.5, "word": " process", "probability": 0.8642578125 }, { "start": 241.5, "end": 241.86, "word": " of", "probability": 0.90283203125 }, { "start": 241.86, "end": 242.26, "word": " information", "probability": 0.7431640625 }, { "start": 242.26, "end": 242.74, "word": " mining", "probability": 0.89111328125 }, { "start": 242.74, "end": 243.2, "word": ",", "probability": 0.982421875 } ] }, { "id": 60, "seek": 24868, "start": 243.2, "end": 245.9, "text": " pattern discovery, and drawing inferences from data.", "tokens": [ 51364, 5102, 12114, 11, 293, 6316, 13596, 2667, 490, 1412, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.19810267125389405, "compression_ratio": 1.6895306859205776, "no_speech_prob": 0.004398345947265625, "words": [ { "start": 243.2, "end": 243.42, "word": " pattern", "probability": 0.77294921875 }, { "start": 243.42, "end": 243.9, "word": " discovery", "probability": 0.79345703125 }, { "start": 243.9, "end": 244.14, "word": ",", "probability": 0.828125 }, { "start": 244.14, "end": 244.24, "word": " and", "probability": 0.88232421875 }, { "start": 244.24, "end": 244.46, "word": " drawing", "probability": 0.7109375 }, { "start": 244.46, "end": 244.84, "word": " inferences", "probability": 0.89013671875 }, { "start": 244.84, "end": 245.1, "word": " from", "probability": 0.82373046875 }, { "start": 245.1, "end": 245.4, "word": " data", "probability": 0.806640625 }, { "start": 245.4, "end": 245.9, "word": ".", "probability": 0.99560546875 } ] }, { "id": 61, "seek": 24868, "start": 245.9, "end": 248.5, "text": " The idea is that machines learn from the data,", "tokens": [ 51514, 440, 1558, 307, 300, 8379, 1466, 490, 264, 1412, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.19810267125389405, "compression_ratio": 1.6895306859205776, "no_speech_prob": 0.004398345947265625, "words": [ { "start": 245.9, "end": 246.12, "word": " The", "probability": 0.8125 }, { "start": 246.12, "end": 246.36, "word": " idea", "probability": 0.75537109375 }, { "start": 246.36, "end": 246.52, "word": " is", "probability": 0.90283203125 }, { "start": 246.52, "end": 246.66, "word": " that", "probability": 0.88330078125 }, { "start": 246.66, "end": 247.1, "word": " machines", "probability": 0.8193359375 }, { "start": 247.1, "end": 247.68, "word": " learn", "probability": 0.89892578125 }, { "start": 247.68, "end": 247.92, "word": " from", "probability": 0.8193359375 }, { "start": 247.92, "end": 248.06, "word": " the", "probability": 0.81201171875 }, { "start": 248.06, "end": 248.36, "word": " data", "probability": 0.82177734375 }, { "start": 248.36, "end": 248.5, "word": ",", "probability": 0.2529296875 } ] }, { "id": 62, "seek": 24868, "start": 248.5, "end": 252.48, "text": " instead of us having to program signatures, or heuristics,", "tokens": [ 51614, 2602, 295, 505, 1419, 281, 1461, 32322, 11, 420, 415, 374, 6006, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.19810267125389405, "compression_ratio": 1.6895306859205776, "no_speech_prob": 0.004398345947265625, "words": [ { "start": 248.5, "end": 248.8, "word": " instead", "probability": 0.8447265625 }, { "start": 248.8, "end": 248.96, "word": " of", "probability": 0.904296875 }, { "start": 248.96, "end": 249.12, "word": " us", "probability": 0.8857421875 }, { "start": 249.12, "end": 249.44, "word": " having", "probability": 0.775390625 }, { "start": 249.44, "end": 249.8, "word": " to", "probability": 0.9013671875 }, { "start": 249.8, "end": 250.38, "word": " program", "probability": 0.76171875 }, { "start": 250.38, "end": 251.4, "word": " signatures", "probability": 0.82568359375 }, { "start": 251.4, "end": 251.64, "word": ",", "probability": 0.267578125 }, { "start": 251.64, "end": 251.7, "word": " or", "probability": 0.84423828125 }, { "start": 251.7, "end": 252.2, "word": " heuristics", "probability": 0.9615885416666666 }, { "start": 252.2, "end": 252.48, "word": ",", "probability": 0.970703125 } ] }, { "id": 63, "seek": 27764, "start": 252.48, "end": 255.3, "text": " or invent new algorithms for different problems.", "tokens": [ 50364, 420, 7962, 777, 14642, 337, 819, 2740, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.19266055373970523, "compression_ratio": 1.7900763358778626, "no_speech_prob": 0.007007598876953125, "words": [ { "start": 252.48, "end": 252.6, "word": " or", "probability": 0.4970703125 }, { "start": 252.6, "end": 252.98, "word": " invent", "probability": 0.71875 }, { "start": 252.98, "end": 253.28, "word": " new", "probability": 0.7705078125 }, { "start": 253.28, "end": 253.74, "word": " algorithms", "probability": 0.8818359375 }, { "start": 253.74, "end": 254.0, "word": " for", "probability": 0.8857421875 }, { "start": 254.0, "end": 254.24, "word": " different", "probability": 0.65673828125 }, { "start": 254.24, "end": 254.74, "word": " problems", "probability": 0.7060546875 }, { "start": 254.74, "end": 255.3, "word": ".", "probability": 0.96337890625 } ] }, { "id": 64, "seek": 27764, "start": 255.86, "end": 258.86, "text": " For example, deep learning, we have convolutional neural networks", "tokens": [ 50514, 1171, 1365, 11, 2452, 2539, 11, 321, 362, 45216, 304, 18161, 9590, 50664 ], "temperature": 0.0, "avg_logprob": -0.19266055373970523, "compression_ratio": 1.7900763358778626, "no_speech_prob": 0.007007598876953125, "words": [ { "start": 255.86, "end": 255.94, "word": " For", "probability": 0.8134765625 }, { "start": 255.94, "end": 256.26, "word": " example", "probability": 0.93212890625 }, { "start": 256.26, "end": 256.5, "word": ",", "probability": 0.9111328125 }, { "start": 256.5, "end": 256.66, "word": " deep", "probability": 0.72265625 }, { "start": 256.66, "end": 256.98, "word": " learning", "probability": 0.81103515625 }, { "start": 256.98, "end": 257.54, "word": ",", "probability": 0.56494140625 }, { "start": 257.54, "end": 257.54, "word": " we", "probability": 0.8779296875 }, { "start": 257.54, "end": 257.68, "word": " have", "probability": 0.8818359375 }, { "start": 257.68, "end": 258.24, "word": " convolutional", "probability": 0.843505859375 }, { "start": 258.24, "end": 258.42, "word": " neural", "probability": 0.90185546875 }, { "start": 258.42, "end": 258.86, "word": " networks", "probability": 0.66943359375 } ] }, { "id": 65, "seek": 27764, "start": 258.86, "end": 262.14, "text": " where deciding between whether something is a bike or a bus", "tokens": [ 50664, 689, 17990, 1296, 1968, 746, 307, 257, 5656, 420, 257, 1255, 50814 ], "temperature": 0.0, "avg_logprob": -0.19266055373970523, "compression_ratio": 1.7900763358778626, "no_speech_prob": 0.007007598876953125, "words": [ { "start": 258.86, "end": 259.26, "word": " where", "probability": 0.66455078125 }, { "start": 259.26, "end": 260.02, "word": " deciding", "probability": 0.83203125 }, { "start": 260.02, "end": 260.44, "word": " between", "probability": 0.740234375 }, { "start": 260.44, "end": 260.66, "word": " whether", "probability": 0.79443359375 }, { "start": 260.66, "end": 260.94, "word": " something", "probability": 0.7373046875 }, { "start": 260.94, "end": 261.1, "word": " is", "probability": 0.90673828125 }, { "start": 261.24, "end": 261.44, "word": " a bike", "probability": 0.8095703125 }, { "start": 261.44, "end": 261.66, "word": " or", "probability": 0.8955078125 }, { "start": 261.86, "end": 262.14, "word": " a bus", "probability": 0.8896484375 } ] }, { "id": 66, "seek": 27764, "start": 262.14, "end": 264.8, "text": " is the exact same algorithm and exact same problem", "tokens": [ 50814, 307, 264, 1900, 912, 9284, 293, 1900, 912, 1154, 50964 ], "temperature": 0.0, "avg_logprob": -0.19266055373970523, "compression_ratio": 1.7900763358778626, "no_speech_prob": 0.007007598876953125, "words": [ { "start": 262.14, "end": 262.46, "word": " is", "probability": 0.82080078125 }, { "start": 262.46, "end": 262.64, "word": " the", "probability": 0.81201171875 }, { "start": 262.64, "end": 262.94, "word": " exact", "probability": 0.8193359375 }, { "start": 262.94, "end": 263.2, "word": " same", "probability": 0.83056640625 }, { "start": 263.2, "end": 263.64, "word": " algorithm", "probability": 0.80078125 }, { "start": 263.64, "end": 263.88, "word": " and", "probability": 0.607421875 }, { "start": 263.88, "end": 264.14, "word": " exact", "probability": 0.837890625 }, { "start": 264.14, "end": 264.4, "word": " same", "probability": 0.79541015625 }, { "start": 264.4, "end": 264.8, "word": " problem", "probability": 0.7646484375 } ] }, { "id": 67, "seek": 27764, "start": 264.8, "end": 269.4, "text": " as deciding whether or not something is a tiger or a cheetah.", "tokens": [ 50964, 382, 17990, 1968, 420, 406, 746, 307, 257, 21432, 420, 257, 947, 47947, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.19266055373970523, "compression_ratio": 1.7900763358778626, "no_speech_prob": 0.007007598876953125, "words": [ { "start": 264.8, "end": 265.08, "word": " as", "probability": 0.875 }, { "start": 265.08, "end": 265.58, "word": " deciding", "probability": 0.85205078125 }, { "start": 265.58, "end": 266.18, "word": " whether", "probability": 0.8544921875 }, { "start": 266.18, "end": 266.4, "word": " or", "probability": 0.8740234375 }, { "start": 266.4, "end": 266.62, "word": " not", "probability": 0.892578125 }, { "start": 266.62, "end": 266.94, "word": " something", "probability": 0.7353515625 }, { "start": 266.94, "end": 267.32, "word": " is", "probability": 0.908203125 }, { "start": 267.66, "end": 267.92, "word": " a tiger", "probability": 0.828125 }, { "start": 267.92, "end": 268.32, "word": " or", "probability": 0.900390625 }, { "start": 268.6, "end": 268.84, "word": " a cheetah", "probability": 0.95361328125 }, { "start": 268.84, "end": 269.4, "word": ".", "probability": 0.9951171875 } ] }, { "id": 68, "seek": 27764, "start": 271.3, "end": 274.22, "text": " So a couple examples, especially in the security space,", "tokens": [ 51314, 407, 257, 1916, 5110, 11, 2318, 294, 264, 3825, 1901, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.19266055373970523, "compression_ratio": 1.7900763358778626, "no_speech_prob": 0.007007598876953125, "words": [ { "start": 271.3, "end": 271.86, "word": " So", "probability": 0.66845703125 }, { "start": 272.0, "end": 272.1, "word": " a couple", "probability": 0.796875 }, { "start": 272.1, "end": 272.5, "word": " examples", "probability": 0.51611328125 }, { "start": 272.5, "end": 272.7, "word": ",", "probability": 0.81298828125 }, { "start": 272.7, "end": 272.84, "word": " especially", "probability": 0.71337890625 }, { "start": 272.84, "end": 273.02, "word": " in", "probability": 0.904296875 }, { "start": 273.02, "end": 273.12, "word": " the", "probability": 0.8125 }, { "start": 273.12, "end": 273.44, "word": " security", "probability": 0.92578125 }, { "start": 273.44, "end": 273.94, "word": " space", "probability": 0.8125 }, { "start": 273.94, "end": 274.22, "word": ",", "probability": 0.79736328125 } ] }, { "id": 69, "seek": 27764, "start": 274.22, "end": 277.92, "text": " we have the ability to classify domain generation algorithms.", "tokens": [ 51464, 321, 362, 264, 3485, 281, 33872, 9274, 5125, 14642, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.19266055373970523, "compression_ratio": 1.7900763358778626, "no_speech_prob": 0.007007598876953125, "words": [ { "start": 274.22, "end": 274.62, "word": " we", "probability": 0.89794921875 }, { "start": 274.62, "end": 274.9, "word": " have", "probability": 0.87939453125 }, { "start": 274.9, "end": 275.52, "word": " the", "probability": 0.81298828125 }, { "start": 275.52, "end": 275.72, "word": " ability", "probability": 0.8544921875 }, { "start": 275.72, "end": 275.9, "word": " to", "probability": 0.908203125 }, { "start": 275.9, "end": 276.3, "word": " classify", "probability": 0.9521484375 }, { "start": 276.3, "end": 276.72, "word": " domain", "probability": 0.87646484375 }, { "start": 276.72, "end": 277.18, "word": " generation", "probability": 0.77685546875 }, { "start": 277.18, "end": 277.64, "word": " algorithms", "probability": 0.88525390625 }, { "start": 277.64, "end": 277.92, "word": ".", "probability": 0.87841796875 } ] }, { "id": 70, "seek": 27764, "start": 277.92, "end": 281.44, "text": " These are primarily used by botnets as a way for the bot herder", "tokens": [ 51614, 1981, 366, 10029, 1143, 538, 10592, 77, 1385, 382, 257, 636, 337, 264, 10592, 720, 1068, 51814 ], "temperature": 0.0, "avg_logprob": -0.19266055373970523, "compression_ratio": 1.7900763358778626, "no_speech_prob": 0.007007598876953125, "words": [ { "start": 277.92, "end": 278.06, "word": " These", "probability": 0.9169921875 }, { "start": 278.06, "end": 278.2, "word": " are", "probability": 0.89794921875 }, { "start": 278.2, "end": 278.54, "word": " primarily", "probability": 0.81005859375 }, { "start": 278.54, "end": 278.8, "word": " used", "probability": 0.8095703125 }, { "start": 278.8, "end": 278.96, "word": " by", "probability": 0.92138671875 }, { "start": 278.96, "end": 279.44, "word": " botnets", "probability": 0.9070638020833334 }, { "start": 279.44, "end": 279.74, "word": " as", "probability": 0.876953125 }, { "start": 279.86, "end": 280.08, "word": " a way", "probability": 0.8984375 }, { "start": 280.08, "end": 280.42, "word": " for", "probability": 0.89794921875 }, { "start": 280.42, "end": 280.68, "word": " the", "probability": 0.81787109375 }, { "start": 280.68, "end": 281.0, "word": " bot", "probability": 0.8359375 }, { "start": 281.0, "end": 281.44, "word": " herder", "probability": 0.83984375 } ] }, { "id": 71, "seek": 30404, "start": 281.44, "end": 286.54, "text": " to stay in contact with their networks.", "tokens": [ 50364, 281, 1754, 294, 3385, 365, 641, 9590, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.21314102831559303, "compression_ratio": 1.6018957345971565, "no_speech_prob": 0.0078125, "words": [ { "start": 281.44, "end": 282.14, "word": " to", "probability": 0.8056640625 }, { "start": 282.14, "end": 282.78, "word": " stay", "probability": 0.92822265625 }, { "start": 282.78, "end": 283.14, "word": " in", "probability": 0.91162109375 }, { "start": 283.14, "end": 283.6, "word": " contact", "probability": 0.84912109375 }, { "start": 283.6, "end": 284.48, "word": " with", "probability": 0.82177734375 }, { "start": 284.48, "end": 284.9, "word": " their", "probability": 0.89892578125 }, { "start": 284.9, "end": 285.86, "word": " networks", "probability": 0.6533203125 }, { "start": 285.86, "end": 286.54, "word": ".", "probability": 0.96484375 } ] }, { "id": 72, "seek": 30404, "start": 287.36, "end": 290.94, "text": " Web application firewalls, these we will usually see", "tokens": [ 50664, 9573, 3861, 36109, 82, 11, 613, 321, 486, 2673, 536, 50814 ], "temperature": 0.0, "avg_logprob": -0.21314102831559303, "compression_ratio": 1.6018957345971565, "no_speech_prob": 0.0078125, "words": [ { "start": 287.36, "end": 288.04, "word": " Web", "probability": 0.81005859375 }, { "start": 288.04, "end": 288.46, "word": " application", "probability": 0.6923828125 }, { "start": 288.46, "end": 289.34, "word": " firewalls", "probability": 0.84765625 }, { "start": 289.34, "end": 289.48, "word": ",", "probability": 0.54638671875 }, { "start": 289.48, "end": 289.72, "word": " these", "probability": 0.70458984375 }, { "start": 289.72, "end": 289.9, "word": " we", "probability": 0.869140625 }, { "start": 289.9, "end": 290.06, "word": " will", "probability": 0.806640625 }, { "start": 290.06, "end": 290.38, "word": " usually", "probability": 0.81884765625 }, { "start": 290.38, "end": 290.94, "word": " see", "probability": 0.8134765625 } ] }, { "id": 73, "seek": 30404, "start": 290.94, "end": 295.18, "text": " with being able to perform some anomaly detection", "tokens": [ 50814, 365, 885, 1075, 281, 2042, 512, 42737, 17784, 51064 ], "temperature": 0.0, "avg_logprob": -0.21314102831559303, "compression_ratio": 1.6018957345971565, "no_speech_prob": 0.0078125, "words": [ { "start": 290.94, "end": 291.7, "word": " with", "probability": 0.8037109375 }, { "start": 291.7, "end": 293.64, "word": " being", "probability": 0.80517578125 }, { "start": 293.64, "end": 293.78, "word": " able", "probability": 0.89453125 }, { "start": 293.78, "end": 293.9, "word": " to", "probability": 0.90673828125 }, { "start": 293.9, "end": 294.16, "word": " perform", "probability": 0.75830078125 }, { "start": 294.16, "end": 294.38, "word": " some", "probability": 0.7958984375 }, { "start": 294.38, "end": 294.72, "word": " anomaly", "probability": 0.76123046875 }, { "start": 294.72, "end": 295.18, "word": " detection", "probability": 0.775390625 } ] }, { "id": 74, "seek": 30404, "start": 295.18, "end": 298.18, "text": " and see, okay, this is what normal user traffic looks like", "tokens": [ 51064, 293, 536, 11, 1392, 11, 341, 307, 437, 2710, 4195, 6419, 1542, 411, 51214 ], "temperature": 0.0, "avg_logprob": -0.21314102831559303, "compression_ratio": 1.6018957345971565, "no_speech_prob": 0.0078125, "words": [ { "start": 295.18, "end": 295.64, "word": " and", "probability": 0.78125 }, { "start": 295.64, "end": 295.88, "word": " see", "probability": 0.80908203125 }, { "start": 295.88, "end": 296.1, "word": ",", "probability": 0.640625 }, { "start": 296.1, "end": 296.18, "word": " okay", "probability": 0.61962890625 }, { "start": 296.18, "end": 296.26, "word": ",", "probability": 0.8330078125 }, { "start": 296.26, "end": 296.42, "word": " this", "probability": 0.8818359375 }, { "start": 296.42, "end": 296.54, "word": " is", "probability": 0.904296875 }, { "start": 296.54, "end": 296.74, "word": " what", "probability": 0.8828125 }, { "start": 296.74, "end": 297.04, "word": " normal", "probability": 0.8125 }, { "start": 297.04, "end": 297.28, "word": " user", "probability": 0.7451171875 }, { "start": 297.28, "end": 297.6, "word": " traffic", "probability": 0.787109375 }, { "start": 297.6, "end": 297.9, "word": " looks", "probability": 0.796875 }, { "start": 297.9, "end": 298.18, "word": " like", "probability": 0.8876953125 } ] }, { "id": 75, "seek": 30404, "start": 298.18, "end": 300.68, "text": " compared to abnormal user traffic.", "tokens": [ 51214, 5347, 281, 32847, 4195, 6419, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.21314102831559303, "compression_ratio": 1.6018957345971565, "no_speech_prob": 0.0078125, "words": [ { "start": 298.18, "end": 298.58, "word": " compared", "probability": 0.7802734375 }, { "start": 298.58, "end": 299.18, "word": " to", "probability": 0.90380859375 }, { "start": 299.18, "end": 299.7, "word": " abnormal", "probability": 0.7294921875 }, { "start": 299.7, "end": 300.0, "word": " user", "probability": 0.7578125 }, { "start": 300.0, "end": 300.34, "word": " traffic", "probability": 0.80126953125 }, { "start": 300.34, "end": 300.68, "word": ".", "probability": 0.9423828125 } ] }, { "id": 76, "seek": 30404, "start": 300.98, "end": 303.38, "text": " So in this case, the machine learning algorithm", "tokens": [ 51314, 407, 294, 341, 1389, 11, 264, 3479, 2539, 9284, 51464 ], "temperature": 0.0, "avg_logprob": -0.21314102831559303, "compression_ratio": 1.6018957345971565, "no_speech_prob": 0.0078125, "words": [ { "start": 300.98, "end": 301.14, "word": " So", "probability": 0.8212890625 }, { "start": 301.14, "end": 301.36, "word": " in", "probability": 0.76220703125 }, { "start": 301.36, "end": 301.58, "word": " this", "probability": 0.88134765625 }, { "start": 301.58, "end": 301.92, "word": " case", "probability": 0.81640625 }, { "start": 301.92, "end": 302.08, "word": ",", "probability": 0.8681640625 }, { "start": 302.08, "end": 302.34, "word": " the", "probability": 0.81396484375 }, { "start": 302.34, "end": 302.72, "word": " machine", "probability": 0.6845703125 }, { "start": 302.72, "end": 302.96, "word": " learning", "probability": 0.81787109375 }, { "start": 302.96, "end": 303.38, "word": " algorithm", "probability": 0.80224609375 } ] }, { "id": 77, "seek": 30404, "start": 303.38, "end": 307.84, "text": " identified a potential SQL injection in the parameter", "tokens": [ 51464, 9234, 257, 3995, 19200, 22873, 294, 264, 13075, 51664 ], "temperature": 0.0, "avg_logprob": -0.21314102831559303, "compression_ratio": 1.6018957345971565, "no_speech_prob": 0.0078125, "words": [ { "start": 303.38, "end": 303.88, "word": " identified", "probability": 0.89306640625 }, { "start": 304.54, "end": 305.04, "word": " a potential", "probability": 0.8623046875 }, { "start": 305.04, "end": 305.64, "word": " SQL", "probability": 0.89697265625 }, { "start": 305.64, "end": 306.16, "word": " injection", "probability": 0.69677734375 }, { "start": 306.16, "end": 307.32, "word": " in", "probability": 0.88623046875 }, { "start": 307.32, "end": 307.44, "word": " the", "probability": 0.81005859375 }, { "start": 307.44, "end": 307.84, "word": " parameter", "probability": 0.87353515625 } ] }, { "id": 78, "seek": 33154, "start": 307.84, "end": 311.46, "text": " because it's very abnormal from what it's used to seeing.", "tokens": [ 50364, 570, 309, 311, 588, 32847, 490, 437, 309, 311, 1143, 281, 2577, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.18628875968992248, "compression_ratio": 1.688135593220339, "no_speech_prob": 0.2939453125, "words": [ { "start": 307.84, "end": 308.34, "word": " because", "probability": 0.324462890625 }, { "start": 308.34, "end": 308.58, "word": " it's", "probability": 0.930908203125 }, { "start": 308.58, "end": 308.8, "word": " very", "probability": 0.72900390625 }, { "start": 308.8, "end": 309.42, "word": " abnormal", "probability": 0.77392578125 }, { "start": 309.42, "end": 309.88, "word": " from", "probability": 0.78271484375 }, { "start": 309.88, "end": 310.24, "word": " what", "probability": 0.8798828125 }, { "start": 310.24, "end": 310.42, "word": " it's", "probability": 0.93896484375 }, { "start": 310.42, "end": 310.6, "word": " used", "probability": 0.810546875 }, { "start": 310.6, "end": 310.78, "word": " to", "probability": 0.90380859375 }, { "start": 310.78, "end": 311.02, "word": " seeing", "probability": 0.76318359375 }, { "start": 311.02, "end": 311.46, "word": ".", "probability": 0.89013671875 } ] }, { "id": 79, "seek": 33154, "start": 312.4, "end": 314.24, "text": " And then, of course, network anomaly detection.", "tokens": [ 50514, 400, 550, 11, 295, 1164, 11, 3209, 42737, 17784, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.18628875968992248, "compression_ratio": 1.688135593220339, "no_speech_prob": 0.2939453125, "words": [ { "start": 312.4, "end": 312.46, "word": " And", "probability": 0.75634765625 }, { "start": 312.46, "end": 312.56, "word": " then", "probability": 0.7216796875 }, { "start": 312.56, "end": 312.66, "word": ",", "probability": 0.25537109375 }, { "start": 312.66, "end": 312.7, "word": " of", "probability": 0.91015625 }, { "start": 312.7, "end": 312.9, "word": " course", "probability": 0.86474609375 }, { "start": 312.9, "end": 312.98, "word": ",", "probability": 0.984375 }, { "start": 312.98, "end": 313.28, "word": " network", "probability": 0.7822265625 }, { "start": 313.28, "end": 313.56, "word": " anomaly", "probability": 0.78955078125 }, { "start": 313.56, "end": 314.04, "word": " detection", "probability": 0.751953125 }, { "start": 314.04, "end": 314.24, "word": ".", "probability": 0.8544921875 } ] }, { "id": 80, "seek": 33154, "start": 314.24, "end": 316.64, "text": " This is one of the big ones, especially in the security side,", "tokens": [ 50664, 639, 307, 472, 295, 264, 955, 2306, 11, 2318, 294, 264, 3825, 1252, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.18628875968992248, "compression_ratio": 1.688135593220339, "no_speech_prob": 0.2939453125, "words": [ { "start": 314.24, "end": 314.36, "word": " This", "probability": 0.814453125 }, { "start": 314.36, "end": 314.48, "word": " is", "probability": 0.90673828125 }, { "start": 314.48, "end": 314.6, "word": " one", "probability": 0.81884765625 }, { "start": 314.6, "end": 314.68, "word": " of", "probability": 0.900390625 }, { "start": 314.68, "end": 314.76, "word": " the", "probability": 0.8134765625 }, { "start": 314.76, "end": 314.94, "word": " big", "probability": 0.89599609375 }, { "start": 314.94, "end": 315.24, "word": " ones", "probability": 0.822265625 }, { "start": 315.24, "end": 315.34, "word": ",", "probability": 0.8603515625 }, { "start": 315.34, "end": 315.58, "word": " especially", "probability": 0.71923828125 }, { "start": 315.58, "end": 315.78, "word": " in", "probability": 0.791015625 }, { "start": 315.78, "end": 315.92, "word": " the", "probability": 0.80859375 }, { "start": 315.92, "end": 316.22, "word": " security", "probability": 0.92333984375 }, { "start": 316.22, "end": 316.54, "word": " side", "probability": 0.81640625 }, { "start": 316.54, "end": 316.64, "word": ",", "probability": 0.90771484375 } ] }, { "id": 81, "seek": 33154, "start": 316.64, "end": 319.98, "text": " the defender side of things, where we can predict", "tokens": [ 50814, 264, 26537, 1252, 295, 721, 11, 689, 321, 393, 6069, 50964 ], "temperature": 0.0, "avg_logprob": -0.18628875968992248, "compression_ratio": 1.688135593220339, "no_speech_prob": 0.2939453125, "words": [ { "start": 316.64, "end": 316.68, "word": " the", "probability": 0.81005859375 }, { "start": 316.68, "end": 316.98, "word": " defender", "probability": 0.681640625 }, { "start": 316.98, "end": 317.28, "word": " side", "probability": 0.80615234375 }, { "start": 317.28, "end": 317.42, "word": " of", "probability": 0.8896484375 }, { "start": 317.42, "end": 317.8, "word": " things", "probability": 0.73388671875 }, { "start": 317.8, "end": 318.16, "word": ",", "probability": 0.81884765625 }, { "start": 318.16, "end": 318.78, "word": " where", "probability": 0.890625 }, { "start": 318.78, "end": 318.96, "word": " we", "probability": 0.9091796875 }, { "start": 318.96, "end": 319.32, "word": " can", "probability": 0.896484375 }, { "start": 319.32, "end": 319.98, "word": " predict", "probability": 0.7998046875 } ] }, { "id": 82, "seek": 33154, "start": 319.98, "end": 323.5, "text": " what we think the network traffic will look like over a period of time", "tokens": [ 50964, 437, 321, 519, 264, 3209, 6419, 486, 574, 411, 670, 257, 2896, 295, 565, 51114 ], "temperature": 0.0, "avg_logprob": -0.18628875968992248, "compression_ratio": 1.688135593220339, "no_speech_prob": 0.2939453125, "words": [ { "start": 319.98, "end": 320.46, "word": " what", "probability": 0.88623046875 }, { "start": 320.46, "end": 320.66, "word": " we", "probability": 0.90576171875 }, { "start": 320.66, "end": 320.88, "word": " think", "probability": 0.80322265625 }, { "start": 320.88, "end": 321.02, "word": " the", "probability": 0.80322265625 }, { "start": 321.02, "end": 321.22, "word": " network", "probability": 0.853515625 }, { "start": 321.22, "end": 321.6, "word": " traffic", "probability": 0.79833984375 }, { "start": 321.6, "end": 321.82, "word": " will", "probability": 0.81005859375 }, { "start": 321.82, "end": 322.1, "word": " look", "probability": 0.91748046875 }, { "start": 322.1, "end": 322.34, "word": " like", "probability": 0.87353515625 }, { "start": 322.34, "end": 322.58, "word": " over", "probability": 0.880859375 }, { "start": 322.8, "end": 322.96, "word": " a period", "probability": 0.91357421875 }, { "start": 322.96, "end": 323.14, "word": " of", "probability": 0.9033203125 }, { "start": 323.14, "end": 323.5, "word": " time", "probability": 0.80419921875 } ] }, { "id": 83, "seek": 33154, "start": 323.5, "end": 325.86, "text": " and then compare that to what the actual is.", "tokens": [ 51114, 293, 550, 6794, 300, 281, 437, 264, 3539, 307, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.18628875968992248, "compression_ratio": 1.688135593220339, "no_speech_prob": 0.2939453125, "words": [ { "start": 323.5, "end": 323.94, "word": " and", "probability": 0.4716796875 }, { "start": 323.94, "end": 324.08, "word": " then", "probability": 0.716796875 }, { "start": 324.08, "end": 324.4, "word": " compare", "probability": 0.865234375 }, { "start": 324.4, "end": 324.62, "word": " that", "probability": 0.88671875 }, { "start": 324.62, "end": 324.78, "word": " to", "probability": 0.90234375 }, { "start": 324.78, "end": 324.9, "word": " what", "probability": 0.88916015625 }, { "start": 324.9, "end": 325.04, "word": " the", "probability": 0.81787109375 }, { "start": 325.04, "end": 325.4, "word": " actual", "probability": 0.810546875 }, { "start": 325.4, "end": 325.78, "word": " is", "probability": 0.9072265625 }, { "start": 325.78, "end": 325.86, "word": ".", "probability": 0.75048828125 } ] }, { "id": 84, "seek": 33154, "start": 325.86, "end": 329.5, "text": " Once it's beyond a certain delta, then that's something", "tokens": [ 51264, 3443, 309, 311, 4399, 257, 1629, 8289, 11, 550, 300, 311, 746, 51414 ], "temperature": 0.0, "avg_logprob": -0.18628875968992248, "compression_ratio": 1.688135593220339, "no_speech_prob": 0.2939453125, "words": [ { "start": 325.86, "end": 326.1, "word": " Once", "probability": 0.357177734375 }, { "start": 326.1, "end": 326.34, "word": " it's", "probability": 0.948486328125 }, { "start": 326.34, "end": 326.7, "word": " beyond", "probability": 0.74462890625 }, { "start": 326.94, "end": 327.18, "word": " a certain", "probability": 0.80322265625 }, { "start": 327.18, "end": 327.6, "word": " delta", "probability": 0.794921875 }, { "start": 327.6, "end": 328.2, "word": ",", "probability": 0.904296875 }, { "start": 328.2, "end": 328.44, "word": " then", "probability": 0.7197265625 }, { "start": 328.44, "end": 329.28, "word": " that's", "probability": 0.93310546875 }, { "start": 329.28, "end": 329.5, "word": " something", "probability": 0.75244140625 } ] }, { "id": 85, "seek": 33154, "start": 329.5, "end": 333.16, "text": " that we should pass off to a human to kind of dig in a little deeper", "tokens": [ 51414, 300, 321, 820, 1320, 766, 281, 257, 1952, 281, 733, 295, 2528, 294, 257, 707, 7731, 51614 ], "temperature": 0.0, "avg_logprob": -0.18628875968992248, "compression_ratio": 1.688135593220339, "no_speech_prob": 0.2939453125, "words": [ { "start": 329.5, "end": 329.66, "word": " that", "probability": 0.82958984375 }, { "start": 329.66, "end": 329.76, "word": " we", "probability": 0.900390625 }, { "start": 329.76, "end": 329.88, "word": " should", "probability": 0.93701171875 }, { "start": 329.88, "end": 330.18, "word": " pass", "probability": 0.83544921875 }, { "start": 330.18, "end": 330.44, "word": " off", "probability": 0.79443359375 }, { "start": 330.44, "end": 330.68, "word": " to", "probability": 0.90283203125 }, { "start": 331.26, "end": 331.56, "word": " a human", "probability": 0.80126953125 }, { "start": 331.56, "end": 331.86, "word": " to", "probability": 0.8896484375 }, { "start": 331.86, "end": 332.06, "word": " kind", "probability": 0.64453125 }, { "start": 332.06, "end": 332.16, "word": " of", "probability": 0.9091796875 }, { "start": 332.16, "end": 332.36, "word": " dig", "probability": 0.90966796875 }, { "start": 332.36, "end": 332.54, "word": " in", "probability": 0.90185546875 }, { "start": 332.66, "end": 332.78, "word": " a little", "probability": 0.80810546875 }, { "start": 332.78, "end": 333.16, "word": " deeper", "probability": 0.80078125 } ] }, { "id": 86, "seek": 33154, "start": 333.16, "end": 335.34, "text": " and kind of figure out what's going on.", "tokens": [ 51614, 293, 733, 295, 2573, 484, 437, 311, 516, 322, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.18628875968992248, "compression_ratio": 1.688135593220339, "no_speech_prob": 0.2939453125, "words": [ { "start": 333.16, "end": 333.72, "word": " and", "probability": 0.85791015625 }, { "start": 333.72, "end": 333.86, "word": " kind", "probability": 0.76220703125 }, { "start": 333.86, "end": 333.94, "word": " of", "probability": 0.90380859375 }, { "start": 333.94, "end": 334.1, "word": " figure", "probability": 0.921875 }, { "start": 334.1, "end": 334.26, "word": " out", "probability": 0.82275390625 }, { "start": 334.26, "end": 334.44, "word": " what's", "probability": 0.943603515625 }, { "start": 334.44, "end": 334.64, "word": " going", "probability": 0.8564453125 }, { "start": 334.64, "end": 334.9, "word": " on", "probability": 0.90625 }, { "start": 334.9, "end": 335.34, "word": ".", "probability": 0.9990234375 } ] }, { "id": 87, "seek": 35886, "start": 336.92, "end": 338.84, "text": " So why is this important?", "tokens": [ 50414, 407, 983, 307, 341, 1021, 30, 50514 ], "temperature": 0.0, "avg_logprob": -0.2081597278515498, "compression_ratio": 1.646551724137931, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 336.92, "end": 337.5, "word": " So", "probability": 0.77001953125 }, { "start": 337.5, "end": 337.68, "word": " why", "probability": 0.7041015625 }, { "start": 337.68, "end": 337.8, "word": " is", "probability": 0.908203125 }, { "start": 337.8, "end": 337.94, "word": " this", "probability": 0.87548828125 }, { "start": 337.94, "end": 338.26, "word": " important", "probability": 0.78564453125 }, { "start": 338.26, "end": 338.84, "word": "?", "probability": 0.98974609375 } ] }, { "id": 88, "seek": 35886, "start": 339.1, "end": 341.94, "text": " Well, today we have over a quarter of security products", "tokens": [ 50514, 1042, 11, 965, 321, 362, 670, 257, 6555, 295, 3825, 3383, 50664 ], "temperature": 0.0, "avg_logprob": -0.2081597278515498, "compression_ratio": 1.646551724137931, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 339.1, "end": 339.5, "word": " Well", "probability": 0.7236328125 }, { "start": 339.5, "end": 339.56, "word": ",", "probability": 0.685546875 }, { "start": 339.56, "end": 339.74, "word": " today", "probability": 0.7861328125 }, { "start": 339.74, "end": 339.92, "word": " we", "probability": 0.716796875 }, { "start": 339.92, "end": 340.1, "word": " have", "probability": 0.8740234375 }, { "start": 340.1, "end": 340.28, "word": " over", "probability": 0.86865234375 }, { "start": 340.46, "end": 340.68, "word": " a quarter", "probability": 0.81494140625 }, { "start": 340.68, "end": 341.14, "word": " of", "probability": 0.90380859375 }, { "start": 341.14, "end": 341.44, "word": " security", "probability": 0.92724609375 }, { "start": 341.44, "end": 341.94, "word": " products", "probability": 0.736328125 } ] }, { "id": 89, "seek": 35886, "start": 341.94, "end": 345.26, "text": " that are used for detection that use some form of machine learning.", "tokens": [ 50664, 300, 366, 1143, 337, 17784, 300, 764, 512, 1254, 295, 3479, 2539, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.2081597278515498, "compression_ratio": 1.646551724137931, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 341.94, "end": 342.12, "word": " that", "probability": 0.86669921875 }, { "start": 342.12, "end": 342.22, "word": " are", "probability": 0.8955078125 }, { "start": 342.22, "end": 342.38, "word": " used", "probability": 0.8115234375 }, { "start": 342.38, "end": 342.52, "word": " for", "probability": 0.90576171875 }, { "start": 342.52, "end": 342.92, "word": " detection", "probability": 0.771484375 }, { "start": 342.92, "end": 343.14, "word": " that", "probability": 0.7119140625 }, { "start": 343.14, "end": 343.3, "word": " use", "probability": 0.81689453125 }, { "start": 343.3, "end": 343.5, "word": " some", "probability": 0.82568359375 }, { "start": 343.5, "end": 343.86, "word": " form", "probability": 0.81591796875 }, { "start": 343.86, "end": 344.02, "word": " of", "probability": 0.90380859375 }, { "start": 344.02, "end": 344.36, "word": " machine", "probability": 0.697265625 }, { "start": 344.36, "end": 344.68, "word": " learning", "probability": 0.8330078125 }, { "start": 344.68, "end": 345.26, "word": ".", "probability": 0.748046875 } ] }, { "id": 90, "seek": 35886, "start": 345.4, "end": 349.12, "text": " And we see machine learning being applied to more and more things every day.", "tokens": [ 50814, 400, 321, 536, 3479, 2539, 885, 6456, 281, 544, 293, 544, 721, 633, 786, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.2081597278515498, "compression_ratio": 1.646551724137931, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 345.4, "end": 345.64, "word": " And", "probability": 0.85400390625 }, { "start": 345.64, "end": 345.84, "word": " we", "probability": 0.89453125 }, { "start": 345.84, "end": 346.04, "word": " see", "probability": 0.8271484375 }, { "start": 346.04, "end": 346.36, "word": " machine", "probability": 0.7099609375 }, { "start": 346.36, "end": 346.58, "word": " learning", "probability": 0.8466796875 }, { "start": 346.58, "end": 346.8, "word": " being", "probability": 0.88818359375 }, { "start": 346.8, "end": 347.18, "word": " applied", "probability": 0.68212890625 }, { "start": 347.18, "end": 347.64, "word": " to", "probability": 0.90380859375 }, { "start": 347.64, "end": 347.98, "word": " more", "probability": 0.8779296875 }, { "start": 347.98, "end": 348.1, "word": " and", "probability": 0.89111328125 }, { "start": 348.1, "end": 348.28, "word": " more", "probability": 0.88134765625 }, { "start": 348.28, "end": 348.58, "word": " things", "probability": 0.740234375 }, { "start": 348.58, "end": 348.8, "word": " every", "probability": 0.685546875 }, { "start": 348.8, "end": 349.0, "word": " day", "probability": 0.8955078125 }, { "start": 349.0, "end": 349.12, "word": ".", "probability": 0.86474609375 } ] }, { "id": 91, "seek": 35886, "start": 349.12, "end": 353.64, "text": " We see facial recognition, we see advanced spam filtering,", "tokens": [ 51014, 492, 536, 15642, 11150, 11, 321, 536, 7339, 24028, 30822, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.2081597278515498, "compression_ratio": 1.646551724137931, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 349.12, "end": 349.18, "word": " We", "probability": 0.89208984375 }, { "start": 349.18, "end": 349.34, "word": " see", "probability": 0.81396484375 }, { "start": 349.34, "end": 349.62, "word": " facial", "probability": 0.81103515625 }, { "start": 349.62, "end": 350.16, "word": " recognition", "probability": 0.873046875 }, { "start": 350.16, "end": 350.84, "word": ",", "probability": 0.62744140625 }, { "start": 350.84, "end": 350.92, "word": " we", "probability": 0.89306640625 }, { "start": 350.92, "end": 351.32, "word": " see", "probability": 0.8115234375 }, { "start": 351.32, "end": 352.06, "word": " advanced", "probability": 0.8037109375 }, { "start": 352.06, "end": 352.34, "word": " spam", "probability": 0.62841796875 }, { "start": 352.34, "end": 352.9, "word": " filtering", "probability": 0.7900390625 }, { "start": 352.9, "end": 353.64, "word": ",", "probability": 0.9423828125 } ] }, { "id": 92, "seek": 35886, "start": 353.64, "end": 357.36, "text": " data heuristics and persona collection.", "tokens": [ 51214, 1412, 415, 374, 6006, 293, 12184, 5765, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.2081597278515498, "compression_ratio": 1.646551724137931, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 353.64, "end": 354.14, "word": " data", "probability": 0.771484375 }, { "start": 354.14, "end": 354.68, "word": " heuristics", "probability": 0.9493815104166666 }, { "start": 354.68, "end": 355.12, "word": " and", "probability": 0.521484375 }, { "start": 355.12, "end": 356.2, "word": " persona", "probability": 0.712890625 }, { "start": 356.2, "end": 356.78, "word": " collection", "probability": 0.662109375 }, { "start": 356.78, "end": 357.36, "word": ".", "probability": 0.953125 } ] }, { "id": 93, "seek": 35886, "start": 358.1, "end": 362.66, "text": " And so in order for security analysts to properly deploy", "tokens": [ 51414, 400, 370, 294, 1668, 337, 3825, 31388, 281, 6108, 7274, 51714 ], "temperature": 0.0, "avg_logprob": -0.2081597278515498, "compression_ratio": 1.646551724137931, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 358.1, "end": 358.22, "word": " And", "probability": 0.88525390625 }, { "start": 358.22, "end": 358.5, "word": " so", "probability": 0.90380859375 }, { "start": 358.5, "end": 358.92, "word": " in", "probability": 0.6796875 }, { "start": 358.92, "end": 359.12, "word": " order", "probability": 0.82080078125 }, { "start": 359.12, "end": 359.76, "word": " for", "probability": 0.90380859375 }, { "start": 359.76, "end": 360.58, "word": " security", "probability": 0.92724609375 }, { "start": 360.58, "end": 361.06, "word": " analysts", "probability": 0.6572265625 }, { "start": 361.06, "end": 361.5, "word": " to", "probability": 0.90185546875 }, { "start": 361.5, "end": 362.06, "word": " properly", "probability": 0.83544921875 }, { "start": 362.06, "end": 362.66, "word": " deploy", "probability": 0.73486328125 } ] }, { "id": 94, "seek": 38656, "start": 362.66, "end": 365.18, "text": " and manage these machine learning products,", "tokens": [ 50364, 293, 3067, 613, 3479, 2539, 3383, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.18614130331122358, "compression_ratio": 1.8227848101265822, "no_speech_prob": 0.007694244384765625, "words": [ { "start": 362.66, "end": 362.86, "word": " and", "probability": 0.295166015625 }, { "start": 362.86, "end": 363.16, "word": " manage", "probability": 0.7861328125 }, { "start": 363.16, "end": 363.64, "word": " these", "probability": 0.59912109375 }, { "start": 363.64, "end": 364.08, "word": " machine", "probability": 0.62939453125 }, { "start": 364.08, "end": 364.4, "word": " learning", "probability": 0.80859375 }, { "start": 364.4, "end": 364.98, "word": " products", "probability": 0.7265625 }, { "start": 364.98, "end": 365.18, "word": ",", "probability": 0.63720703125 } ] }, { "id": 95, "seek": 38656, "start": 365.18, "end": 368.4, "text": " they need to have a better understanding of how they operate", "tokens": [ 50514, 436, 643, 281, 362, 257, 1101, 3701, 295, 577, 436, 9651, 50664 ], "temperature": 0.0, "avg_logprob": -0.18614130331122358, "compression_ratio": 1.8227848101265822, "no_speech_prob": 0.007694244384765625, "words": [ { "start": 365.18, "end": 365.5, "word": " they", "probability": 0.70849609375 }, { "start": 365.5, "end": 365.64, "word": " need", "probability": 0.81494140625 }, { "start": 365.64, "end": 365.7, "word": " to", "probability": 0.88623046875 }, { "start": 365.7, "end": 365.84, "word": " have", "probability": 0.87841796875 }, { "start": 365.94, "end": 366.06, "word": " a better", "probability": 0.81982421875 }, { "start": 366.06, "end": 366.72, "word": " understanding", "probability": 0.6865234375 }, { "start": 366.72, "end": 367.24, "word": " of", "probability": 0.9013671875 }, { "start": 367.24, "end": 367.76, "word": " how", "probability": 0.9033203125 }, { "start": 367.76, "end": 367.9, "word": " they", "probability": 0.7373046875 }, { "start": 367.9, "end": 368.4, "word": " operate", "probability": 0.76123046875 } ] }, { "id": 96, "seek": 38656, "start": 368.4, "end": 371.26, "text": " so that they can ensure that they work efficiently.", "tokens": [ 50664, 370, 300, 436, 393, 5586, 300, 436, 589, 19621, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.18614130331122358, "compression_ratio": 1.8227848101265822, "no_speech_prob": 0.007694244384765625, "words": [ { "start": 368.4, "end": 368.66, "word": " so", "probability": 0.7373046875 }, { "start": 368.66, "end": 368.78, "word": " that", "probability": 0.814453125 }, { "start": 368.78, "end": 368.92, "word": " they", "probability": 0.74072265625 }, { "start": 368.92, "end": 369.2, "word": " can", "probability": 0.8935546875 }, { "start": 369.2, "end": 369.64, "word": " ensure", "probability": 0.830078125 }, { "start": 369.64, "end": 369.84, "word": " that", "probability": 0.86083984375 }, { "start": 369.84, "end": 369.96, "word": " they", "probability": 0.73486328125 }, { "start": 369.96, "end": 370.22, "word": " work", "probability": 0.82763671875 }, { "start": 370.22, "end": 370.86, "word": " efficiently", "probability": 0.806640625 }, { "start": 370.86, "end": 371.26, "word": ".", "probability": 0.97509765625 } ] }, { "id": 97, "seek": 38656, "start": 375.06, "end": 378.04, "text": " So the machine learning process, it follows seven steps.", "tokens": [ 50964, 407, 264, 3479, 2539, 1399, 11, 309, 10002, 3407, 4439, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.18614130331122358, "compression_ratio": 1.8227848101265822, "no_speech_prob": 0.007694244384765625, "words": [ { "start": 375.06, "end": 375.46, "word": " So", "probability": 0.52783203125 }, { "start": 375.46, "end": 375.56, "word": " the", "probability": 0.72119140625 }, { "start": 375.56, "end": 375.76, "word": " machine", "probability": 0.67431640625 }, { "start": 375.76, "end": 375.96, "word": " learning", "probability": 0.8388671875 }, { "start": 375.96, "end": 376.4, "word": " process", "probability": 0.8818359375 }, { "start": 376.4, "end": 376.54, "word": ",", "probability": 0.59423828125 }, { "start": 376.54, "end": 376.68, "word": " it", "probability": 0.89697265625 }, { "start": 376.68, "end": 376.88, "word": " follows", "probability": 0.791015625 }, { "start": 376.88, "end": 377.2, "word": " seven", "probability": 0.740234375 }, { "start": 377.2, "end": 377.64, "word": " steps", "probability": 0.73779296875 }, { "start": 377.64, "end": 378.04, "word": ".", "probability": 0.87158203125 } ] }, { "id": 98, "seek": 38656, "start": 378.24, "end": 380.82, "text": " This is not a step one, step two, step three,", "tokens": [ 51114, 639, 307, 406, 257, 1823, 472, 11, 1823, 732, 11, 1823, 1045, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.18614130331122358, "compression_ratio": 1.8227848101265822, "no_speech_prob": 0.007694244384765625, "words": [ { "start": 378.24, "end": 378.46, "word": " This", "probability": 0.771484375 }, { "start": 378.46, "end": 378.62, "word": " is", "probability": 0.90625 }, { "start": 378.62, "end": 378.94, "word": " not", "probability": 0.88720703125 }, { "start": 379.36, "end": 379.64, "word": " a step", "probability": 0.75537109375 }, { "start": 379.64, "end": 379.84, "word": " one", "probability": 0.70068359375 }, { "start": 379.84, "end": 379.92, "word": ",", "probability": 0.947265625 }, { "start": 379.92, "end": 380.06, "word": " step", "probability": 0.806640625 }, { "start": 380.06, "end": 380.24, "word": " two", "probability": 0.81591796875 }, { "start": 380.24, "end": 380.36, "word": ",", "probability": 0.98193359375 }, { "start": 380.36, "end": 380.46, "word": " step", "probability": 0.81787109375 }, { "start": 380.46, "end": 380.74, "word": " three", "probability": 0.8369140625 }, { "start": 380.74, "end": 380.82, "word": ",", "probability": 0.81982421875 } ] }, { "id": 99, "seek": 38656, "start": 380.82, "end": 382.34, "text": " but this is really a cycle.", "tokens": [ 51264, 457, 341, 307, 534, 257, 6586, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.18614130331122358, "compression_ratio": 1.8227848101265822, "no_speech_prob": 0.007694244384765625, "words": [ { "start": 380.82, "end": 380.96, "word": " but", "probability": 0.89697265625 }, { "start": 380.96, "end": 381.12, "word": " this", "probability": 0.87744140625 }, { "start": 381.12, "end": 381.26, "word": " is", "probability": 0.90185546875 }, { "start": 381.26, "end": 381.46, "word": " really", "probability": 0.78076171875 }, { "start": 381.64, "end": 381.94, "word": " a cycle", "probability": 0.91162109375 }, { "start": 381.94, "end": 382.34, "word": ".", "probability": 0.98046875 } ] }, { "id": 100, "seek": 38656, "start": 382.46, "end": 385.48, "text": " So you start at step one, you go all the way down to step seven,", "tokens": [ 51364, 407, 291, 722, 412, 1823, 472, 11, 291, 352, 439, 264, 636, 760, 281, 1823, 3407, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.18614130331122358, "compression_ratio": 1.8227848101265822, "no_speech_prob": 0.007694244384765625, "words": [ { "start": 382.46, "end": 382.66, "word": " So", "probability": 0.8662109375 }, { "start": 382.66, "end": 382.78, "word": " you", "probability": 0.88525390625 }, { "start": 382.78, "end": 383.02, "word": " start", "probability": 0.84130859375 }, { "start": 383.02, "end": 383.14, "word": " at", "probability": 0.89794921875 }, { "start": 383.14, "end": 383.32, "word": " step", "probability": 0.80712890625 }, { "start": 383.32, "end": 383.58, "word": " one", "probability": 0.81689453125 }, { "start": 383.58, "end": 383.66, "word": ",", "probability": 0.85009765625 }, { "start": 383.66, "end": 383.74, "word": " you", "probability": 0.8740234375 }, { "start": 383.74, "end": 383.86, "word": " go", "probability": 0.491455078125 }, { "start": 383.86, "end": 384.06, "word": " all", "probability": 0.88671875 }, { "start": 384.06, "end": 384.2, "word": " the", "probability": 0.81787109375 }, { "start": 384.2, "end": 384.36, "word": " way", "probability": 0.896484375 }, { "start": 384.36, "end": 384.76, "word": " down", "probability": 0.81591796875 }, { "start": 384.76, "end": 384.9, "word": " to", "probability": 0.9033203125 }, { "start": 384.9, "end": 385.1, "word": " step", "probability": 0.80078125 }, { "start": 385.1, "end": 385.46, "word": " seven", "probability": 0.8056640625 }, { "start": 385.46, "end": 385.48, "word": ",", "probability": 0.6904296875 } ] }, { "id": 101, "seek": 38656, "start": 385.48, "end": 387.46, "text": " and then you hop back up to step one.", "tokens": [ 51514, 293, 550, 291, 3818, 646, 493, 281, 1823, 472, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.18614130331122358, "compression_ratio": 1.8227848101265822, "no_speech_prob": 0.007694244384765625, "words": [ { "start": 385.48, "end": 385.62, "word": " and", "probability": 0.89208984375 }, { "start": 385.62, "end": 385.72, "word": " then", "probability": 0.72021484375 }, { "start": 385.72, "end": 385.86, "word": " you", "probability": 0.89794921875 }, { "start": 385.86, "end": 386.06, "word": " hop", "probability": 0.90869140625 }, { "start": 386.06, "end": 386.3, "word": " back", "probability": 0.8076171875 }, { "start": 386.3, "end": 386.46, "word": " up", "probability": 0.91259765625 }, { "start": 386.46, "end": 386.58, "word": " to", "probability": 0.90673828125 }, { "start": 386.58, "end": 386.8, "word": " step", "probability": 0.82470703125 }, { "start": 386.8, "end": 387.06, "word": " one", "probability": 0.8203125 }, { "start": 387.06, "end": 387.46, "word": ".", "probability": 0.98876953125 } ] }, { "id": 102, "seek": 38656, "start": 387.52, "end": 390.36, "text": " So you start off with gathering the data.", "tokens": [ 51614, 407, 291, 722, 766, 365, 13519, 264, 1412, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.18614130331122358, "compression_ratio": 1.8227848101265822, "no_speech_prob": 0.007694244384765625, "words": [ { "start": 387.52, "end": 387.78, "word": " So", "probability": 0.85888671875 }, { "start": 387.78, "end": 388.36, "word": " you", "probability": 0.81884765625 }, { "start": 388.36, "end": 388.54, "word": " start", "probability": 0.86865234375 }, { "start": 388.54, "end": 388.68, "word": " off", "probability": 0.80517578125 }, { "start": 388.68, "end": 388.82, "word": " with", "probability": 0.82177734375 }, { "start": 388.82, "end": 389.18, "word": " gathering", "probability": 0.76220703125 }, { "start": 389.18, "end": 389.68, "word": " the", "probability": 0.798828125 }, { "start": 389.68, "end": 389.98, "word": " data", "probability": 0.8037109375 }, { "start": 389.98, "end": 390.36, "word": ".", "probability": 0.90625 } ] }, { "id": 103, "seek": 41228, "start": 390.36, "end": 392.18, "text": " So first you want to identify if I'm going to build", "tokens": [ 50364, 407, 700, 291, 528, 281, 5876, 498, 286, 478, 516, 281, 1322, 50464 ], "temperature": 0.0, "avg_logprob": -0.18538135227005362, "compression_ratio": 1.7666666666666666, "no_speech_prob": 0.0022525787353515625, "words": [ { "start": 390.36, "end": 390.62, "word": " So", "probability": 0.580078125 }, { "start": 390.62, "end": 390.96, "word": " first", "probability": 0.63525390625 }, { "start": 390.96, "end": 391.06, "word": " you", "probability": 0.7451171875 }, { "start": 391.06, "end": 391.16, "word": " want", "probability": 0.59228515625 }, { "start": 391.16, "end": 391.24, "word": " to", "probability": 0.90234375 }, { "start": 391.24, "end": 391.58, "word": " identify", "probability": 0.89794921875 }, { "start": 391.58, "end": 391.8, "word": " if", "probability": 0.83642578125 }, { "start": 391.8, "end": 391.9, "word": " I'm", "probability": 0.983642578125 }, { "start": 391.9, "end": 391.96, "word": " going", "probability": 0.6484375 }, { "start": 391.96, "end": 392.04, "word": " to", "probability": 0.9013671875 }, { "start": 392.04, "end": 392.18, "word": " build", "probability": 0.87890625 } ] }, { "id": 104, "seek": 41228, "start": 392.3, "end": 394.08, "text": " a network anomaly detection system,", "tokens": [ 50464, 257, 3209, 42737, 17784, 1185, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.18538135227005362, "compression_ratio": 1.7666666666666666, "no_speech_prob": 0.0022525787353515625, "words": [ { "start": 392.3, "end": 392.52, "word": " a network", "probability": 0.80810546875 }, { "start": 392.52, "end": 392.88, "word": " anomaly", "probability": 0.80029296875 }, { "start": 392.88, "end": 393.32, "word": " detection", "probability": 0.75390625 }, { "start": 393.32, "end": 393.92, "word": " system", "probability": 0.8720703125 }, { "start": 393.92, "end": 394.08, "word": ",", "probability": 0.73681640625 } ] }, { "id": 105, "seek": 41228, "start": 394.08, "end": 396.52, "text": " if I'm going to build some sort of hacking tool.", "tokens": [ 50564, 498, 286, 478, 516, 281, 1322, 512, 1333, 295, 31422, 2290, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.18538135227005362, "compression_ratio": 1.7666666666666666, "no_speech_prob": 0.0022525787353515625, "words": [ { "start": 394.08, "end": 394.38, "word": " if", "probability": 0.865234375 }, { "start": 394.38, "end": 394.46, "word": " I'm", "probability": 0.99609375 }, { "start": 394.46, "end": 394.54, "word": " going", "probability": 0.83642578125 }, { "start": 394.54, "end": 394.6, "word": " to", "probability": 0.90234375 }, { "start": 394.6, "end": 394.76, "word": " build", "probability": 0.86962890625 }, { "start": 394.76, "end": 395.0, "word": " some", "probability": 0.6064453125 }, { "start": 395.0, "end": 395.24, "word": " sort", "probability": 0.8310546875 }, { "start": 395.24, "end": 395.34, "word": " of", "probability": 0.90380859375 }, { "start": 395.34, "end": 395.66, "word": " hacking", "probability": 0.68701171875 }, { "start": 395.66, "end": 396.08, "word": " tool", "probability": 0.88525390625 }, { "start": 396.08, "end": 396.52, "word": ".", "probability": 0.77880859375 } ] }, { "id": 106, "seek": 41228, "start": 396.86, "end": 399.02, "text": " I need to gather data that applies to that,", "tokens": [ 50714, 286, 643, 281, 5448, 1412, 300, 13165, 281, 300, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.18538135227005362, "compression_ratio": 1.7666666666666666, "no_speech_prob": 0.0022525787353515625, "words": [ { "start": 396.86, "end": 397.06, "word": " I", "probability": 0.9921875 }, { "start": 397.06, "end": 397.18, "word": " need", "probability": 0.8193359375 }, { "start": 397.18, "end": 397.3, "word": " to", "probability": 0.90576171875 }, { "start": 397.3, "end": 397.5, "word": " gather", "probability": 0.79248046875 }, { "start": 397.5, "end": 397.82, "word": " data", "probability": 0.81396484375 }, { "start": 397.82, "end": 397.98, "word": " that", "probability": 0.88037109375 }, { "start": 397.98, "end": 398.32, "word": " applies", "probability": 0.7705078125 }, { "start": 398.32, "end": 398.5, "word": " to", "probability": 0.90087890625 }, { "start": 398.5, "end": 398.8, "word": " that", "probability": 0.8837890625 }, { "start": 398.8, "end": 399.02, "word": ",", "probability": 0.298583984375 } ] }, { "id": 107, "seek": 41228, "start": 399.02, "end": 400.8, "text": " and then I need to prepare the data.", "tokens": [ 50814, 293, 550, 286, 643, 281, 5940, 264, 1412, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.18538135227005362, "compression_ratio": 1.7666666666666666, "no_speech_prob": 0.0022525787353515625, "words": [ { "start": 399.02, "end": 399.38, "word": " and", "probability": 0.88671875 }, { "start": 399.38, "end": 399.48, "word": " then", "probability": 0.70751953125 }, { "start": 399.48, "end": 399.54, "word": " I", "probability": 0.99609375 }, { "start": 399.54, "end": 399.66, "word": " need", "probability": 0.81982421875 }, { "start": 399.66, "end": 399.76, "word": " to", "probability": 0.90380859375 }, { "start": 399.76, "end": 400.12, "word": " prepare", "probability": 0.7998046875 }, { "start": 400.12, "end": 400.32, "word": " the", "probability": 0.80908203125 }, { "start": 400.32, "end": 400.6, "word": " data", "probability": 0.814453125 }, { "start": 400.6, "end": 400.8, "word": ".", "probability": 0.59033203125 } ] }, { "id": 108, "seek": 41228, "start": 400.8, "end": 404.2, "text": " So I can't just take raw information,", "tokens": [ 50914, 407, 286, 393, 380, 445, 747, 8936, 1589, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.18538135227005362, "compression_ratio": 1.7666666666666666, "no_speech_prob": 0.0022525787353515625, "words": [ { "start": 400.8, "end": 400.92, "word": " So", "probability": 0.88037109375 }, { "start": 400.92, "end": 401.06, "word": " I", "probability": 0.97998046875 }, { "start": 401.06, "end": 401.32, "word": " can't", "probability": 0.9482421875 }, { "start": 401.32, "end": 401.54, "word": " just", "probability": 0.89111328125 }, { "start": 401.54, "end": 401.98, "word": " take", "probability": 0.81298828125 }, { "start": 401.98, "end": 403.34, "word": " raw", "probability": 0.806640625 }, { "start": 403.34, "end": 404.02, "word": " information", "probability": 0.7353515625 }, { "start": 404.02, "end": 404.2, "word": ",", "probability": 0.3232421875 } ] }, { "id": 109, "seek": 41228, "start": 404.2, "end": 407.74, "text": " I need to look at things like metadata and pre-process that.", "tokens": [ 51064, 286, 643, 281, 574, 412, 721, 411, 26603, 293, 659, 12, 41075, 300, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.18538135227005362, "compression_ratio": 1.7666666666666666, "no_speech_prob": 0.0022525787353515625, "words": [ { "start": 404.2, "end": 404.32, "word": " I", "probability": 0.998046875 }, { "start": 404.32, "end": 404.44, "word": " need", "probability": 0.81787109375 }, { "start": 404.44, "end": 404.54, "word": " to", "probability": 0.89794921875 }, { "start": 404.54, "end": 404.7, "word": " look", "probability": 0.91748046875 }, { "start": 404.7, "end": 404.8, "word": " at", "probability": 0.90625 }, { "start": 404.8, "end": 405.1, "word": " things", "probability": 0.73681640625 }, { "start": 405.1, "end": 405.3, "word": " like", "probability": 0.86083984375 }, { "start": 405.3, "end": 405.76, "word": " metadata", "probability": 0.84375 }, { "start": 405.76, "end": 406.2, "word": " and", "probability": 0.81298828125 }, { "start": 406.2, "end": 406.48, "word": " pre", "probability": 0.6494140625 }, { "start": 406.48, "end": 406.8, "word": "-process", "probability": 0.855224609375 }, { "start": 406.8, "end": 407.3, "word": " that", "probability": 0.87939453125 }, { "start": 407.3, "end": 407.74, "word": ".", "probability": 0.96875 } ] }, { "id": 110, "seek": 41228, "start": 408.22, "end": 411.22, "text": " This step is also known as pre-processing.", "tokens": [ 51264, 639, 1823, 307, 611, 2570, 382, 659, 12, 41075, 278, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.18538135227005362, "compression_ratio": 1.7666666666666666, "no_speech_prob": 0.0022525787353515625, "words": [ { "start": 408.22, "end": 408.6, "word": " This", "probability": 0.806640625 }, { "start": 408.6, "end": 408.86, "word": " step", "probability": 0.82470703125 }, { "start": 408.86, "end": 409.04, "word": " is", "probability": 0.90625 }, { "start": 409.04, "end": 409.28, "word": " also", "probability": 0.81787109375 }, { "start": 409.28, "end": 409.52, "word": " known", "probability": 0.73291015625 }, { "start": 409.52, "end": 409.98, "word": " as", "probability": 0.90576171875 }, { "start": 409.98, "end": 410.2, "word": " pre", "probability": 0.80517578125 }, { "start": 410.2, "end": 410.78, "word": "-processing", "probability": 0.8955078125 }, { "start": 410.78, "end": 411.22, "word": ".", "probability": 0.9951171875 } ] }, { "id": 111, "seek": 41228, "start": 411.84, "end": 416.08, "text": " We need to choose the model, and the model is going to depend...", "tokens": [ 51464, 492, 643, 281, 2826, 264, 2316, 11, 293, 264, 2316, 307, 516, 281, 5672, 485, 51664 ], "temperature": 0.0, "avg_logprob": -0.18538135227005362, "compression_ratio": 1.7666666666666666, "no_speech_prob": 0.0022525787353515625, "words": [ { "start": 411.84, "end": 412.28, "word": " We", "probability": 0.90869140625 }, { "start": 412.28, "end": 412.42, "word": " need", "probability": 0.80859375 }, { "start": 412.42, "end": 412.56, "word": " to", "probability": 0.90673828125 }, { "start": 412.56, "end": 412.78, "word": " choose", "probability": 0.828125 }, { "start": 412.78, "end": 412.94, "word": " the", "probability": 0.8154296875 }, { "start": 412.94, "end": 413.22, "word": " model", "probability": 0.81494140625 }, { "start": 413.22, "end": 413.46, "word": ",", "probability": 0.51318359375 }, { "start": 413.46, "end": 413.54, "word": " and", "probability": 0.89599609375 }, { "start": 413.54, "end": 413.66, "word": " the", "probability": 0.80615234375 }, { "start": 413.66, "end": 413.94, "word": " model", "probability": 0.8115234375 }, { "start": 413.94, "end": 414.12, "word": " is", "probability": 0.90380859375 }, { "start": 414.12, "end": 414.3, "word": " going", "probability": 0.85888671875 }, { "start": 414.3, "end": 414.44, "word": " to", "probability": 0.90087890625 }, { "start": 414.44, "end": 416.08, "word": " depend...", "probability": 0.513671875 } ] }, { "id": 112, "seek": 43842, "start": 416.08, "end": 417.16, "text": " There are some heuristics.", "tokens": [ 50364, 821, 366, 512, 415, 374, 6006, 13, 50414 ], "temperature": 0.0, "avg_logprob": -0.18675000667572023, "compression_ratio": 1.8122605363984674, "no_speech_prob": 0.0092620849609375, "words": [ { "start": 416.08, "end": 416.3, "word": " There", "probability": 0.55859375 }, { "start": 416.3, "end": 416.42, "word": " are", "probability": 0.88525390625 }, { "start": 416.42, "end": 416.6, "word": " some", "probability": 0.80908203125 }, { "start": 416.6, "end": 417.0, "word": " heuristics", "probability": 0.8899739583333334 }, { "start": 417.0, "end": 417.16, "word": ".", "probability": 0.57373046875 } ] }, { "id": 113, "seek": 43842, "start": 417.16, "end": 420.56, "text": " Some models work better for different problem sets,", "tokens": [ 50414, 2188, 5245, 589, 1101, 337, 819, 1154, 6352, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.18675000667572023, "compression_ratio": 1.8122605363984674, "no_speech_prob": 0.0092620849609375, "words": [ { "start": 417.16, "end": 417.26, "word": " Some", "probability": 0.81298828125 }, { "start": 417.26, "end": 417.56, "word": " models", "probability": 0.775390625 }, { "start": 417.56, "end": 417.8, "word": " work", "probability": 0.79736328125 }, { "start": 417.8, "end": 418.02, "word": " better", "probability": 0.81494140625 }, { "start": 418.02, "end": 418.34, "word": " for", "probability": 0.890625 }, { "start": 418.34, "end": 419.04, "word": " different", "probability": 0.67236328125 }, { "start": 419.04, "end": 419.6, "word": " problem", "probability": 0.74853515625 }, { "start": 419.6, "end": 419.92, "word": " sets", "probability": 0.82470703125 }, { "start": 419.92, "end": 420.56, "word": ",", "probability": 0.341552734375 } ] }, { "id": 114, "seek": 43842, "start": 420.56, "end": 423.12, "text": " but generally we're going to try a couple different models", "tokens": [ 50564, 457, 5101, 321, 434, 516, 281, 853, 257, 1916, 819, 5245, 50714 ], "temperature": 0.0, "avg_logprob": -0.18675000667572023, "compression_ratio": 1.8122605363984674, "no_speech_prob": 0.0092620849609375, "words": [ { "start": 420.56, "end": 420.96, "word": " but", "probability": 0.86962890625 }, { "start": 420.96, "end": 421.28, "word": " generally", "probability": 0.83203125 }, { "start": 421.28, "end": 421.8, "word": " we're", "probability": 0.7607421875 }, { "start": 421.8, "end": 421.88, "word": " going", "probability": 0.62060546875 }, { "start": 421.88, "end": 421.96, "word": " to", "probability": 0.9033203125 }, { "start": 421.96, "end": 422.18, "word": " try", "probability": 0.810546875 }, { "start": 422.3, "end": 422.48, "word": " a couple", "probability": 0.80224609375 }, { "start": 422.48, "end": 422.76, "word": " different", "probability": 0.55712890625 }, { "start": 422.76, "end": 423.12, "word": " models", "probability": 0.78369140625 } ] }, { "id": 115, "seek": 43842, "start": 423.12, "end": 425.18, "text": " and see what works best.", "tokens": [ 50714, 293, 536, 437, 1985, 1151, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.18675000667572023, "compression_ratio": 1.8122605363984674, "no_speech_prob": 0.0092620849609375, "words": [ { "start": 423.12, "end": 423.42, "word": " and", "probability": 0.8642578125 }, { "start": 423.42, "end": 423.66, "word": " see", "probability": 0.81298828125 }, { "start": 423.66, "end": 423.96, "word": " what", "probability": 0.88671875 }, { "start": 423.96, "end": 424.26, "word": " works", "probability": 0.73291015625 }, { "start": 424.26, "end": 424.7, "word": " best", "probability": 0.78662109375 }, { "start": 424.7, "end": 425.18, "word": ".", "probability": 0.9267578125 } ] }, { "id": 116, "seek": 43842, "start": 425.64, "end": 429.0, "text": " We're going to train the model, we're going to evaluate the model,", "tokens": [ 50864, 492, 434, 516, 281, 3847, 264, 2316, 11, 321, 434, 516, 281, 13059, 264, 2316, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.18675000667572023, "compression_ratio": 1.8122605363984674, "no_speech_prob": 0.0092620849609375, "words": [ { "start": 425.64, "end": 426.12, "word": " We're", "probability": 0.81884765625 }, { "start": 426.12, "end": 426.2, "word": " going", "probability": 0.83349609375 }, { "start": 426.2, "end": 426.3, "word": " to", "probability": 0.90234375 }, { "start": 426.3, "end": 426.52, "word": " train", "probability": 0.8017578125 }, { "start": 426.52, "end": 426.7, "word": " the", "probability": 0.8125 }, { "start": 426.7, "end": 426.98, "word": " model", "probability": 0.8193359375 }, { "start": 426.98, "end": 427.38, "word": ",", "probability": 0.50439453125 }, { "start": 427.38, "end": 427.48, "word": " we're", "probability": 0.902587890625 }, { "start": 427.48, "end": 427.54, "word": " going", "probability": 0.84521484375 }, { "start": 427.54, "end": 427.62, "word": " to", "probability": 0.90283203125 }, { "start": 427.62, "end": 427.96, "word": " evaluate", "probability": 0.7861328125 }, { "start": 427.96, "end": 428.22, "word": " the", "probability": 0.81103515625 }, { "start": 428.22, "end": 428.52, "word": " model", "probability": 0.81201171875 }, { "start": 428.52, "end": 429.0, "word": ",", "probability": 0.69140625 } ] }, { "id": 117, "seek": 43842, "start": 429.0, "end": 432.12, "text": " and then if we think that the model can perform a little bit better", "tokens": [ 51014, 293, 550, 498, 321, 519, 300, 264, 2316, 393, 2042, 257, 707, 857, 1101, 51164 ], "temperature": 0.0, "avg_logprob": -0.18675000667572023, "compression_ratio": 1.8122605363984674, "no_speech_prob": 0.0092620849609375, "words": [ { "start": 429.0, "end": 429.28, "word": " and", "probability": 0.88916015625 }, { "start": 429.28, "end": 429.54, "word": " then", "probability": 0.716796875 }, { "start": 429.54, "end": 429.8, "word": " if", "probability": 0.83349609375 }, { "start": 429.8, "end": 429.92, "word": " we", "probability": 0.9033203125 }, { "start": 429.92, "end": 430.1, "word": " think", "probability": 0.80517578125 }, { "start": 430.1, "end": 430.22, "word": " that", "probability": 0.822265625 }, { "start": 430.22, "end": 430.34, "word": " the", "probability": 0.81494140625 }, { "start": 430.34, "end": 430.66, "word": " model", "probability": 0.8212890625 }, { "start": 430.66, "end": 431.02, "word": " can", "probability": 0.89794921875 }, { "start": 431.02, "end": 431.36, "word": " perform", "probability": 0.77783203125 }, { "start": 431.5, "end": 431.58, "word": " a little", "probability": 0.802734375 }, { "start": 431.58, "end": 431.76, "word": " bit", "probability": 0.90478515625 }, { "start": 431.76, "end": 432.12, "word": " better", "probability": 0.82177734375 } ] }, { "id": 118, "seek": 43842, "start": 432.12, "end": 433.94, "text": " than it's actually performing right now,", "tokens": [ 51164, 813, 309, 311, 767, 10205, 558, 586, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.18675000667572023, "compression_ratio": 1.8122605363984674, "no_speech_prob": 0.0092620849609375, "words": [ { "start": 432.12, "end": 432.5, "word": " than", "probability": 0.791015625 }, { "start": 432.5, "end": 432.68, "word": " it's", "probability": 0.935791015625 }, { "start": 432.68, "end": 432.92, "word": " actually", "probability": 0.7861328125 }, { "start": 432.92, "end": 433.32, "word": " performing", "probability": 0.7275390625 }, { "start": 433.32, "end": 433.58, "word": " right", "probability": 0.88232421875 }, { "start": 433.58, "end": 433.86, "word": " now", "probability": 0.89404296875 }, { "start": 433.86, "end": 433.94, "word": ",", "probability": 0.87548828125 } ] }, { "id": 119, "seek": 43842, "start": 433.94, "end": 436.58, "text": " we can do what's called hyperparameter tuning.", "tokens": [ 51264, 321, 393, 360, 437, 311, 1219, 9848, 2181, 335, 2398, 15164, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.18675000667572023, "compression_ratio": 1.8122605363984674, "no_speech_prob": 0.0092620849609375, "words": [ { "start": 433.94, "end": 434.12, "word": " we", "probability": 0.89599609375 }, { "start": 434.12, "end": 434.26, "word": " can", "probability": 0.89404296875 }, { "start": 434.26, "end": 434.46, "word": " do", "probability": 0.8984375 }, { "start": 434.46, "end": 434.68, "word": " what's", "probability": 0.9384765625 }, { "start": 434.68, "end": 434.86, "word": " called", "probability": 0.8017578125 }, { "start": 434.86, "end": 435.74, "word": " hyperparameter", "probability": 0.850830078125 }, { "start": 435.74, "end": 436.1, "word": " tuning", "probability": 0.7548828125 }, { "start": 436.1, "end": 436.58, "word": ".", "probability": 0.8291015625 } ] }, { "id": 120, "seek": 43842, "start": 436.68, "end": 440.1, "text": " And so this lets us make little tweaks here and there.", "tokens": [ 51364, 400, 370, 341, 6653, 505, 652, 707, 46664, 510, 293, 456, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.18675000667572023, "compression_ratio": 1.8122605363984674, "no_speech_prob": 0.0092620849609375, "words": [ { "start": 436.68, "end": 436.76, "word": " And", "probability": 0.548828125 }, { "start": 436.76, "end": 436.88, "word": " so", "probability": 0.8984375 }, { "start": 436.88, "end": 437.06, "word": " this", "probability": 0.80322265625 }, { "start": 437.06, "end": 437.28, "word": " lets", "probability": 0.81201171875 }, { "start": 437.28, "end": 437.48, "word": " us", "probability": 0.9013671875 }, { "start": 437.48, "end": 437.66, "word": " make", "probability": 0.8720703125 }, { "start": 437.66, "end": 437.96, "word": " little", "probability": 0.2802734375 }, { "start": 437.96, "end": 438.84, "word": " tweaks", "probability": 0.91357421875 }, { "start": 438.84, "end": 439.22, "word": " here", "probability": 0.81005859375 }, { "start": 439.22, "end": 439.38, "word": " and", "probability": 0.8974609375 }, { "start": 439.38, "end": 439.62, "word": " there", "probability": 0.857421875 }, { "start": 439.62, "end": 440.1, "word": ".", "probability": 0.88720703125 } ] }, { "id": 121, "seek": 43842, "start": 440.36, "end": 442.22, "text": " And then of course we deploy it.", "tokens": [ 51564, 400, 550, 295, 1164, 321, 7274, 309, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.18675000667572023, "compression_ratio": 1.8122605363984674, "no_speech_prob": 0.0092620849609375, "words": [ { "start": 440.36, "end": 440.64, "word": " And", "probability": 0.8720703125 }, { "start": 440.64, "end": 440.74, "word": " then", "probability": 0.7119140625 }, { "start": 440.74, "end": 440.88, "word": " of", "probability": 0.6337890625 }, { "start": 440.88, "end": 441.04, "word": " course", "probability": 0.8662109375 }, { "start": 441.04, "end": 441.2, "word": " we", "probability": 0.666015625 }, { "start": 441.2, "end": 441.52, "word": " deploy", "probability": 0.7314453125 }, { "start": 441.52, "end": 441.74, "word": " it", "probability": 0.8818359375 }, { "start": 441.74, "end": 442.22, "word": ".", "probability": 0.9404296875 } ] }, { "id": 122, "seek": 46716, "start": 442.22, "end": 446.38, "text": " And as I said earlier, this is a bit of a cyclical process,", "tokens": [ 50364, 400, 382, 286, 848, 3071, 11, 341, 307, 257, 857, 295, 257, 19474, 804, 1399, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.1950120241023027, "compression_ratio": 1.6653061224489796, "no_speech_prob": 0.00555419921875, "words": [ { "start": 442.22, "end": 443.08, "word": " And", "probability": 0.178466796875 }, { "start": 443.08, "end": 443.38, "word": " as", "probability": 0.7919921875 }, { "start": 443.38, "end": 443.48, "word": " I", "probability": 0.98876953125 }, { "start": 443.48, "end": 443.66, "word": " said", "probability": 0.87158203125 }, { "start": 443.66, "end": 443.98, "word": " earlier", "probability": 0.8994140625 }, { "start": 443.98, "end": 444.28, "word": ",", "probability": 0.8896484375 }, { "start": 444.28, "end": 444.4, "word": " this", "probability": 0.869140625 }, { "start": 444.4, "end": 444.68, "word": " is", "probability": 0.90673828125 }, { "start": 445.04, "end": 445.14, "word": " a bit", "probability": 0.8369140625 }, { "start": 445.14, "end": 445.22, "word": " of", "probability": 0.900390625 }, { "start": 445.32, "end": 445.68, "word": " a cyclical", "probability": 0.828125 }, { "start": 445.68, "end": 446.14, "word": " process", "probability": 0.88818359375 }, { "start": 446.14, "end": 446.38, "word": ",", "probability": 0.25048828125 } ] }, { "id": 123, "seek": 46716, "start": 446.38, "end": 448.68, "text": " because machine learning algorithms stop learning", "tokens": [ 50564, 570, 3479, 2539, 14642, 1590, 2539, 50664 ], "temperature": 0.0, "avg_logprob": -0.1950120241023027, "compression_ratio": 1.6653061224489796, "no_speech_prob": 0.00555419921875, "words": [ { "start": 446.38, "end": 446.52, "word": " because", "probability": 0.80419921875 }, { "start": 446.52, "end": 446.88, "word": " machine", "probability": 0.69970703125 }, { "start": 446.88, "end": 447.14, "word": " learning", "probability": 0.81201171875 }, { "start": 447.14, "end": 447.7, "word": " algorithms", "probability": 0.85546875 }, { "start": 447.7, "end": 448.26, "word": " stop", "probability": 0.80419921875 }, { "start": 448.26, "end": 448.68, "word": " learning", "probability": 0.85400390625 } ] }, { "id": 124, "seek": 46716, "start": 448.68, "end": 450.82, "text": " as soon as you stop training them.", "tokens": [ 50664, 382, 2321, 382, 291, 1590, 3097, 552, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.1950120241023027, "compression_ratio": 1.6653061224489796, "no_speech_prob": 0.00555419921875, "words": [ { "start": 448.68, "end": 448.98, "word": " as", "probability": 0.87939453125 }, { "start": 448.98, "end": 449.16, "word": " soon", "probability": 0.8837890625 }, { "start": 449.16, "end": 449.28, "word": " as", "probability": 0.90576171875 }, { "start": 449.28, "end": 449.38, "word": " you", "probability": 0.90185546875 }, { "start": 449.38, "end": 449.7, "word": " stop", "probability": 0.78955078125 }, { "start": 449.7, "end": 450.0, "word": " training", "probability": 0.7998046875 }, { "start": 450.0, "end": 450.32, "word": " them", "probability": 0.732421875 }, { "start": 450.32, "end": 450.82, "word": ".", "probability": 0.86279296875 } ] }, { "id": 125, "seek": 46716, "start": 450.82, "end": 453.36, "text": " And so you want to continue to gather new data", "tokens": [ 50764, 400, 370, 291, 528, 281, 2354, 281, 5448, 777, 1412, 50914 ], "temperature": 0.0, "avg_logprob": -0.1950120241023027, "compression_ratio": 1.6653061224489796, "no_speech_prob": 0.00555419921875, "words": [ { "start": 450.82, "end": 450.92, "word": " And", "probability": 0.77197265625 }, { "start": 450.92, "end": 451.24, "word": " so", "probability": 0.9013671875 }, { "start": 451.24, "end": 451.78, "word": " you", "probability": 0.61328125 }, { "start": 451.78, "end": 451.9, "word": " want", "probability": 0.7529296875 }, { "start": 451.9, "end": 451.98, "word": " to", "probability": 0.90625 }, { "start": 451.98, "end": 452.32, "word": " continue", "probability": 0.7734375 }, { "start": 452.32, "end": 452.5, "word": " to", "probability": 0.90380859375 }, { "start": 452.5, "end": 452.7, "word": " gather", "probability": 0.78857421875 }, { "start": 452.7, "end": 452.98, "word": " new", "probability": 0.802734375 }, { "start": 452.98, "end": 453.36, "word": " data", "probability": 0.81396484375 } ] }, { "id": 126, "seek": 46716, "start": 453.36, "end": 458.96, "text": " and train new models and build them into newer and better generations.", "tokens": [ 50914, 293, 3847, 777, 5245, 293, 1322, 552, 666, 17628, 293, 1101, 10593, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.1950120241023027, "compression_ratio": 1.6653061224489796, "no_speech_prob": 0.00555419921875, "words": [ { "start": 453.36, "end": 453.68, "word": " and", "probability": 0.76318359375 }, { "start": 453.68, "end": 453.92, "word": " train", "probability": 0.80859375 }, { "start": 453.92, "end": 454.14, "word": " new", "probability": 0.8125 }, { "start": 454.14, "end": 454.54, "word": " models", "probability": 0.80419921875 }, { "start": 454.54, "end": 455.08, "word": " and", "probability": 0.779296875 }, { "start": 455.08, "end": 455.42, "word": " build", "probability": 0.876953125 }, { "start": 455.42, "end": 455.66, "word": " them", "probability": 0.74072265625 }, { "start": 455.66, "end": 455.92, "word": " into", "probability": 0.701171875 }, { "start": 455.92, "end": 456.24, "word": " newer", "probability": 0.7314453125 }, { "start": 456.24, "end": 457.46, "word": " and", "probability": 0.8251953125 }, { "start": 457.46, "end": 457.62, "word": " better", "probability": 0.76904296875 }, { "start": 457.62, "end": 458.4, "word": " generations", "probability": 0.689453125 }, { "start": 458.4, "end": 458.96, "word": ".", "probability": 0.990234375 } ] }, { "id": 127, "seek": 46716, "start": 462.02, "end": 465.8, "text": " So before we get started, what we're going to do is hop in", "tokens": [ 51364, 407, 949, 321, 483, 1409, 11, 437, 321, 434, 516, 281, 360, 307, 3818, 294, 51514 ], "temperature": 0.0, "avg_logprob": -0.1950120241023027, "compression_ratio": 1.6653061224489796, "no_speech_prob": 0.00555419921875, "words": [ { "start": 462.02, "end": 462.58, "word": " So", "probability": 0.837890625 }, { "start": 462.58, "end": 463.14, "word": " before", "probability": 0.5849609375 }, { "start": 463.14, "end": 463.32, "word": " we", "probability": 0.90234375 }, { "start": 463.32, "end": 463.44, "word": " get", "probability": 0.9052734375 }, { "start": 463.44, "end": 463.72, "word": " started", "probability": 0.80126953125 }, { "start": 463.72, "end": 463.86, "word": ",", "probability": 0.93798828125 }, { "start": 463.86, "end": 463.96, "word": " what", "probability": 0.88818359375 }, { "start": 463.96, "end": 464.1, "word": " we're", "probability": 0.92236328125 }, { "start": 464.1, "end": 464.18, "word": " going", "probability": 0.6953125 }, { "start": 464.18, "end": 464.26, "word": " to", "probability": 0.90625 }, { "start": 464.26, "end": 464.5, "word": " do", "probability": 0.91162109375 }, { "start": 464.5, "end": 465.02, "word": " is", "probability": 0.89892578125 }, { "start": 465.02, "end": 465.54, "word": " hop", "probability": 0.8623046875 }, { "start": 465.54, "end": 465.8, "word": " in", "probability": 0.90283203125 } ] }, { "id": 128, "seek": 46716, "start": 465.8, "end": 468.62, "text": " and learn how to build a basic spam filter.", "tokens": [ 51514, 293, 1466, 577, 281, 1322, 257, 3875, 24028, 6608, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.1950120241023027, "compression_ratio": 1.6653061224489796, "no_speech_prob": 0.00555419921875, "words": [ { "start": 465.8, "end": 466.36, "word": " and", "probability": 0.88623046875 }, { "start": 466.36, "end": 466.96, "word": " learn", "probability": 0.91748046875 }, { "start": 466.96, "end": 467.16, "word": " how", "probability": 0.90234375 }, { "start": 467.16, "end": 467.32, "word": " to", "probability": 0.90673828125 }, { "start": 467.32, "end": 467.48, "word": " build", "probability": 0.8623046875 }, { "start": 467.58, "end": 467.82, "word": " a basic", "probability": 0.9140625 }, { "start": 467.82, "end": 468.12, "word": " spam", "probability": 0.634765625 }, { "start": 468.12, "end": 468.44, "word": " filter", "probability": 0.86083984375 }, { "start": 468.44, "end": 468.62, "word": ".", "probability": 0.95947265625 } ] }, { "id": 129, "seek": 46716, "start": 468.62, "end": 470.96, "text": " Spam filters are fantastic first examples,", "tokens": [ 51664, 1738, 335, 15995, 366, 5456, 700, 5110, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.1950120241023027, "compression_ratio": 1.6653061224489796, "no_speech_prob": 0.00555419921875, "words": [ { "start": 468.62, "end": 468.8, "word": " Spam", "probability": 0.95849609375 }, { "start": 468.8, "end": 469.06, "word": " filters", "probability": 0.82470703125 }, { "start": 469.06, "end": 469.26, "word": " are", "probability": 0.892578125 }, { "start": 469.26, "end": 469.98, "word": " fantastic", "probability": 0.888671875 }, { "start": 469.98, "end": 470.32, "word": " first", "probability": 0.7705078125 }, { "start": 470.32, "end": 470.78, "word": " examples", "probability": 0.7783203125 }, { "start": 470.78, "end": 470.96, "word": ",", "probability": 0.94580078125 } ] }, { "id": 130, "seek": 49292, "start": 470.96, "end": 472.34, "text": " especially for a lot of the newbies,", "tokens": [ 50364, 2318, 337, 257, 688, 295, 264, 777, 23177, 11, 50464 ], "temperature": 0.0, "avg_logprob": -0.19065240966646294, "compression_ratio": 1.6857142857142857, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 470.96, "end": 471.22, "word": " especially", "probability": 0.62841796875 }, { "start": 471.22, "end": 471.5, "word": " for", "probability": 0.89306640625 }, { "start": 471.74, "end": 471.82, "word": " a lot", "probability": 0.89111328125 }, { "start": 471.82, "end": 471.92, "word": " of", "probability": 0.90087890625 }, { "start": 471.92, "end": 472.02, "word": " the", "probability": 0.81494140625 }, { "start": 472.02, "end": 472.28, "word": " newbies", "probability": 0.916259765625 }, { "start": 472.28, "end": 472.34, "word": ",", "probability": 0.5712890625 } ] }, { "id": 131, "seek": 49292, "start": 472.34, "end": 474.42, "text": " because we already know how spam filters work.", "tokens": [ 50464, 570, 321, 1217, 458, 577, 24028, 15995, 589, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.19065240966646294, "compression_ratio": 1.6857142857142857, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 472.34, "end": 472.5, "word": " because", "probability": 0.83056640625 }, { "start": 472.5, "end": 472.64, "word": " we", "probability": 0.90234375 }, { "start": 472.64, "end": 472.8, "word": " already", "probability": 0.8251953125 }, { "start": 472.8, "end": 472.96, "word": " know", "probability": 0.81982421875 }, { "start": 472.96, "end": 473.12, "word": " how", "probability": 0.908203125 }, { "start": 473.12, "end": 473.36, "word": " spam", "probability": 0.890625 }, { "start": 473.36, "end": 473.66, "word": " filters", "probability": 0.810546875 }, { "start": 473.66, "end": 473.98, "word": " work", "probability": 0.80419921875 }, { "start": 473.98, "end": 474.42, "word": ".", "probability": 0.97998046875 } ] }, { "id": 132, "seek": 49292, "start": 474.62, "end": 478.76, "text": " If it says something that looks spammy, like buy Viagra now,", "tokens": [ 50564, 759, 309, 1619, 746, 300, 1542, 24028, 2226, 11, 411, 2256, 6626, 559, 424, 586, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.19065240966646294, "compression_ratio": 1.6857142857142857, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 474.62, "end": 474.8, "word": " If", "probability": 0.9033203125 }, { "start": 474.8, "end": 474.94, "word": " it", "probability": 0.9052734375 }, { "start": 474.94, "end": 475.14, "word": " says", "probability": 0.77587890625 }, { "start": 475.14, "end": 475.54, "word": " something", "probability": 0.71826171875 }, { "start": 475.54, "end": 476.48, "word": " that", "probability": 0.865234375 }, { "start": 476.48, "end": 476.68, "word": " looks", "probability": 0.78759765625 }, { "start": 476.68, "end": 477.06, "word": " spammy", "probability": 0.90771484375 }, { "start": 477.06, "end": 477.16, "word": ",", "probability": 0.703125 }, { "start": 477.16, "end": 477.3, "word": " like", "probability": 0.87744140625 }, { "start": 477.3, "end": 477.52, "word": " buy", "probability": 0.254150390625 }, { "start": 477.52, "end": 477.96, "word": " Viagra", "probability": 0.79541015625 }, { "start": 477.96, "end": 478.32, "word": " now", "probability": 0.8828125 }, { "start": 478.32, "end": 478.76, "word": ",", "probability": 0.96728515625 } ] }, { "id": 133, "seek": 49292, "start": 478.76, "end": 482.54, "text": " then that's going to be automatically thrown away into our spam filter.", "tokens": [ 50764, 550, 300, 311, 516, 281, 312, 6772, 11732, 1314, 666, 527, 24028, 6608, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.19065240966646294, "compression_ratio": 1.6857142857142857, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 478.76, "end": 479.12, "word": " then", "probability": 0.72021484375 }, { "start": 479.12, "end": 479.46, "word": " that's", "probability": 0.935546875 }, { "start": 479.46, "end": 479.56, "word": " going", "probability": 0.220458984375 }, { "start": 479.56, "end": 479.62, "word": " to", "probability": 0.9033203125 }, { "start": 479.62, "end": 479.88, "word": " be", "probability": 0.89208984375 }, { "start": 479.88, "end": 480.5, "word": " automatically", "probability": 0.82470703125 }, { "start": 480.5, "end": 480.78, "word": " thrown", "probability": 0.86376953125 }, { "start": 480.78, "end": 481.14, "word": " away", "probability": 0.81689453125 }, { "start": 481.14, "end": 481.36, "word": " into", "probability": 0.54736328125 }, { "start": 481.36, "end": 481.5, "word": " our", "probability": 0.837890625 }, { "start": 481.5, "end": 481.74, "word": " spam", "probability": 0.89599609375 }, { "start": 481.74, "end": 482.1, "word": " filter", "probability": 0.91162109375 }, { "start": 482.1, "end": 482.54, "word": ".", "probability": 0.99462890625 } ] }, { "id": 134, "seek": 49292, "start": 482.72, "end": 485.72, "text": " If we have something that seems legitimate,", "tokens": [ 50964, 759, 321, 362, 746, 300, 2544, 17956, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.19065240966646294, "compression_ratio": 1.6857142857142857, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 482.72, "end": 483.1, "word": " If", "probability": 0.8994140625 }, { "start": 483.1, "end": 483.24, "word": " we", "probability": 0.90380859375 }, { "start": 483.24, "end": 483.46, "word": " have", "probability": 0.8857421875 }, { "start": 483.46, "end": 483.78, "word": " something", "probability": 0.73583984375 }, { "start": 483.78, "end": 484.5, "word": " that", "probability": 0.87890625 }, { "start": 484.5, "end": 485.2, "word": " seems", "probability": 0.73291015625 }, { "start": 485.2, "end": 485.58, "word": " legitimate", "probability": 0.80126953125 }, { "start": 485.58, "end": 485.72, "word": ",", "probability": 0.9111328125 } ] }, { "id": 135, "seek": 49292, "start": 485.72, "end": 487.66, "text": " then that's going to be passed on to the user.", "tokens": [ 51114, 550, 300, 311, 516, 281, 312, 4678, 322, 281, 264, 4195, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.19065240966646294, "compression_ratio": 1.6857142857142857, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 485.72, "end": 485.82, "word": " then", "probability": 0.72900390625 }, { "start": 485.82, "end": 486.02, "word": " that's", "probability": 0.939208984375 }, { "start": 486.02, "end": 486.1, "word": " going", "probability": 0.8076171875 }, { "start": 486.1, "end": 486.14, "word": " to", "probability": 0.900390625 }, { "start": 486.14, "end": 486.26, "word": " be", "probability": 0.89990234375 }, { "start": 486.26, "end": 486.52, "word": " passed", "probability": 0.73095703125 }, { "start": 486.52, "end": 486.74, "word": " on", "probability": 0.82861328125 }, { "start": 486.74, "end": 486.84, "word": " to", "probability": 0.9052734375 }, { "start": 486.84, "end": 486.98, "word": " the", "probability": 0.80712890625 }, { "start": 486.98, "end": 487.22, "word": " user", "probability": 0.810546875 }, { "start": 487.22, "end": 487.66, "word": ".", "probability": 0.9970703125 } ] }, { "id": 136, "seek": 49292, "start": 488.32, "end": 491.18, "text": " So before we get into that, are there any questions", "tokens": [ 51214, 407, 949, 321, 483, 666, 300, 11, 366, 456, 604, 1651, 51364 ], "temperature": 0.0, "avg_logprob": -0.19065240966646294, "compression_ratio": 1.6857142857142857, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 488.32, "end": 488.48, "word": " So", "probability": 0.80029296875 }, { "start": 488.48, "end": 488.78, "word": " before", "probability": 0.71044921875 }, { "start": 488.78, "end": 489.0, "word": " we", "probability": 0.9013671875 }, { "start": 489.0, "end": 489.14, "word": " get", "probability": 0.90283203125 }, { "start": 489.14, "end": 489.3, "word": " into", "probability": 0.7294921875 }, { "start": 489.3, "end": 489.68, "word": " that", "probability": 0.88232421875 }, { "start": 489.68, "end": 489.94, "word": ",", "probability": 0.98388671875 }, { "start": 489.94, "end": 490.16, "word": " are", "probability": 0.88818359375 }, { "start": 490.16, "end": 490.28, "word": " there", "probability": 0.85107421875 }, { "start": 490.28, "end": 490.64, "word": " any", "probability": 0.8212890625 }, { "start": 490.64, "end": 491.18, "word": " questions", "probability": 0.90380859375 } ] }, { "id": 137, "seek": 49292, "start": 491.18, "end": 493.74, "text": " on any of the stuff that I've gone over so far?", "tokens": [ 51364, 322, 604, 295, 264, 1507, 300, 286, 600, 2780, 670, 370, 1400, 30, 51514 ], "temperature": 0.0, "avg_logprob": -0.19065240966646294, "compression_ratio": 1.6857142857142857, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 491.18, "end": 491.64, "word": " on", "probability": 0.90087890625 }, { "start": 491.64, "end": 491.86, "word": " any", "probability": 0.8056640625 }, { "start": 491.86, "end": 491.96, "word": " of", "probability": 0.90625 }, { "start": 491.96, "end": 492.06, "word": " the", "probability": 0.35693359375 }, { "start": 492.06, "end": 492.28, "word": " stuff", "probability": 0.80126953125 }, { "start": 492.28, "end": 492.42, "word": " that", "probability": 0.86767578125 }, { "start": 492.42, "end": 492.54, "word": " I've", "probability": 0.973388671875 }, { "start": 492.54, "end": 492.7, "word": " gone", "probability": 0.8837890625 }, { "start": 492.7, "end": 492.86, "word": " over", "probability": 0.88134765625 }, { "start": 492.86, "end": 493.08, "word": " so", "probability": 0.90087890625 }, { "start": 493.08, "end": 493.3, "word": " far", "probability": 0.89990234375 }, { "start": 493.3, "end": 493.74, "word": "?", "probability": 0.990234375 } ] }, { "id": 138, "seek": 49292, "start": 502.97, "end": 503.85, "text": " Okay.", "tokens": [ 51614, 1033, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.19065240966646294, "compression_ratio": 1.6857142857142857, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 502.97, "end": 503.41, "word": " Okay", "probability": 0.74951171875 }, { "start": 503.41, "end": 503.85, "word": ".", "probability": 0.8779296875 } ] }, { "id": 139, "seek": 51856, "start": 506.81, "end": 508.03, "text": " One more thing.", "tokens": [ 50414, 1485, 544, 551, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.19752038432204205, "compression_ratio": 1.5888324873096447, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 506.81, "end": 507.25, "word": " One", "probability": 0.74267578125 }, { "start": 507.25, "end": 507.39, "word": " more", "probability": 0.88232421875 }, { "start": 507.39, "end": 507.59, "word": " thing", "probability": 0.81787109375 }, { "start": 507.59, "end": 508.03, "word": ".", "probability": 0.4453125 } ] }, { "id": 140, "seek": 51856, "start": 508.19, "end": 512.33, "text": " I totally forgot this, but this is a bit of a story that really...", "tokens": [ 50564, 286, 3879, 5298, 341, 11, 457, 341, 307, 257, 857, 295, 257, 1657, 300, 534, 485, 50764 ], "temperature": 0.0, "avg_logprob": -0.19752038432204205, "compression_ratio": 1.5888324873096447, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 508.19, "end": 508.27, "word": " I", "probability": 0.478271484375 }, { "start": 508.27, "end": 508.89, "word": " totally", "probability": 0.78125 }, { "start": 508.89, "end": 509.15, "word": " forgot", "probability": 0.7998046875 }, { "start": 509.15, "end": 509.47, "word": " this", "probability": 0.87255859375 }, { "start": 509.47, "end": 509.63, "word": ",", "probability": 0.619140625 }, { "start": 509.63, "end": 509.75, "word": " but", "probability": 0.8935546875 }, { "start": 509.75, "end": 509.97, "word": " this", "probability": 0.8720703125 }, { "start": 509.97, "end": 510.17, "word": " is", "probability": 0.8896484375 }, { "start": 510.81, "end": 510.91, "word": " a bit", "probability": 0.884765625 }, { "start": 510.91, "end": 510.99, "word": " of", "probability": 0.90576171875 }, { "start": 511.11, "end": 511.33, "word": " a story", "probability": 0.87646484375 }, { "start": 511.33, "end": 511.57, "word": " that", "probability": 0.82958984375 }, { "start": 511.57, "end": 512.33, "word": " really...", "probability": 0.4849853515625 } ] }, { "id": 141, "seek": 51856, "start": 512.33, "end": 513.31, "text": " Yes.", "tokens": [ 50764, 1079, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.19752038432204205, "compression_ratio": 1.5888324873096447, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 512.33, "end": 512.87, "word": " Yes", "probability": 0.467041015625 }, { "start": 512.87, "end": 513.31, "word": ".", "probability": 0.67431640625 } ] }, { "id": 142, "seek": 51856, "start": 516.29, "end": 517.17, "text": " Okay.", "tokens": [ 50964, 1033, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.19752038432204205, "compression_ratio": 1.5888324873096447, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 516.29, "end": 516.73, "word": " Okay", "probability": 0.70751953125 }, { "start": 516.73, "end": 517.17, "word": ".", "probability": 0.73779296875 } ] }, { "id": 143, "seek": 51856, "start": 517.25, "end": 519.87, "text": " This is a story that really made things click for me.", "tokens": [ 51014, 639, 307, 257, 1657, 300, 534, 1027, 721, 2052, 337, 385, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.19752038432204205, "compression_ratio": 1.5888324873096447, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 517.25, "end": 517.69, "word": " This", "probability": 0.80810546875 }, { "start": 517.69, "end": 517.79, "word": " is", "probability": 0.89892578125 }, { "start": 517.91, "end": 518.05, "word": " a story", "probability": 0.88818359375 }, { "start": 518.05, "end": 518.21, "word": " that", "probability": 0.88525390625 }, { "start": 518.21, "end": 518.37, "word": " really", "probability": 0.7666015625 }, { "start": 518.37, "end": 518.59, "word": " made", "probability": 0.81005859375 }, { "start": 518.59, "end": 518.81, "word": " things", "probability": 0.7138671875 }, { "start": 518.81, "end": 519.03, "word": " click", "probability": 0.77978515625 }, { "start": 519.03, "end": 519.21, "word": " for", "probability": 0.896484375 }, { "start": 519.21, "end": 519.43, "word": " me", "probability": 0.904296875 }, { "start": 519.43, "end": 519.87, "word": ".", "probability": 0.99267578125 } ] }, { "id": 144, "seek": 51856, "start": 520.49, "end": 522.93, "text": " So a friend of mine, this was a few years ago,", "tokens": [ 51164, 407, 257, 1277, 295, 3892, 11, 341, 390, 257, 1326, 924, 2057, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.19752038432204205, "compression_ratio": 1.5888324873096447, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 520.49, "end": 520.67, "word": " So", "probability": 0.7265625 }, { "start": 520.91, "end": 521.05, "word": " a friend", "probability": 0.65625 }, { "start": 521.05, "end": 521.15, "word": " of", "probability": 0.90380859375 }, { "start": 521.15, "end": 521.31, "word": " mine", "probability": 0.86669921875 }, { "start": 521.31, "end": 521.35, "word": ",", "probability": 0.8662109375 }, { "start": 521.35, "end": 521.45, "word": " this", "probability": 0.875 }, { "start": 521.45, "end": 521.57, "word": " was", "probability": 0.8916015625 }, { "start": 522.09, "end": 522.25, "word": " a few", "probability": 0.79736328125 }, { "start": 522.25, "end": 522.47, "word": " years", "probability": 0.88623046875 }, { "start": 522.47, "end": 522.75, "word": " ago", "probability": 0.8271484375 }, { "start": 522.75, "end": 522.93, "word": ",", "probability": 0.970703125 } ] }, { "id": 145, "seek": 51856, "start": 522.93, "end": 526.01, "text": " was approached by a non-profit organization.", "tokens": [ 51314, 390, 17247, 538, 257, 2107, 12, 14583, 4475, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.19752038432204205, "compression_ratio": 1.5888324873096447, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 522.93, "end": 523.25, "word": " was", "probability": 0.88818359375 }, { "start": 523.25, "end": 523.73, "word": " approached", "probability": 0.63671875 }, { "start": 523.73, "end": 524.05, "word": " by", "probability": 0.90380859375 }, { "start": 524.51, "end": 524.77, "word": " a non", "probability": 0.64794921875 }, { "start": 524.77, "end": 525.01, "word": "-profit", "probability": 0.746337890625 }, { "start": 525.01, "end": 525.57, "word": " organization", "probability": 0.84814453125 }, { "start": 525.57, "end": 526.01, "word": ".", "probability": 0.53466796875 } ] }, { "id": 146, "seek": 51856, "start": 526.01, "end": 529.49, "text": " And what this non-profit does is they have cameras set up all over Africa", "tokens": [ 51464, 400, 437, 341, 2107, 12, 14583, 775, 307, 436, 362, 8622, 992, 493, 439, 670, 7349, 51664 ], "temperature": 0.0, "avg_logprob": -0.19752038432204205, "compression_ratio": 1.5888324873096447, "no_speech_prob": 0.0018672943115234375, "words": [ { "start": 526.01, "end": 526.17, "word": " And", "probability": 0.87158203125 }, { "start": 526.17, "end": 526.31, "word": " what", "probability": 0.87744140625 }, { "start": 526.31, "end": 526.45, "word": " this", "probability": 0.88037109375 }, { "start": 526.45, "end": 526.67, "word": " non", "probability": 0.84912109375 }, { "start": 526.67, "end": 526.87, "word": "-profit", "probability": 0.89794921875 }, { "start": 526.87, "end": 527.47, "word": " does", "probability": 0.91650390625 }, { "start": 527.47, "end": 527.87, "word": " is", "probability": 0.796875 }, { "start": 527.87, "end": 528.03, "word": " they", "probability": 0.6611328125 }, { "start": 528.03, "end": 528.15, "word": " have", "probability": 0.8779296875 }, { "start": 528.15, "end": 528.51, "word": " cameras", "probability": 0.82470703125 }, { "start": 528.51, "end": 528.69, "word": " set", "probability": 0.84423828125 }, { "start": 528.69, "end": 528.79, "word": " up", "probability": 0.90576171875 }, { "start": 528.79, "end": 528.93, "word": " all", "probability": 0.90087890625 }, { "start": 528.93, "end": 529.09, "word": " over", "probability": 0.88623046875 }, { "start": 529.09, "end": 529.49, "word": " Africa", "probability": 0.744140625 } ] }, { "id": 147, "seek": 54706, "start": 529.91, "end": 533.83, "text": " and they take pictures to see if there's a cheetah.", "tokens": [ 50364, 293, 436, 747, 5242, 281, 536, 498, 456, 311, 257, 947, 47947, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.1700764371336793, "compression_ratio": 1.8164794007490637, "no_speech_prob": 0.007808685302734375, "words": [ { "start": 529.91, "end": 530.27, "word": " and", "probability": 0.46435546875 }, { "start": 530.27, "end": 530.51, "word": " they", "probability": 0.74267578125 }, { "start": 530.51, "end": 530.85, "word": " take", "probability": 0.80810546875 }, { "start": 530.85, "end": 531.27, "word": " pictures", "probability": 0.712890625 }, { "start": 531.27, "end": 531.69, "word": " to", "probability": 0.90087890625 }, { "start": 531.69, "end": 532.05, "word": " see", "probability": 0.81103515625 }, { "start": 532.05, "end": 532.39, "word": " if", "probability": 0.900390625 }, { "start": 532.39, "end": 532.91, "word": " there's", "probability": 0.906982421875 }, { "start": 533.25, "end": 533.47, "word": " a cheetah", "probability": 0.926025390625 }, { "start": 533.47, "end": 533.83, "word": ".", "probability": 0.368408203125 } ] }, { "id": 148, "seek": 54706, "start": 534.17, "end": 535.95, "text": " And they're tracking cheetah population.", "tokens": [ 50564, 400, 436, 434, 11603, 947, 47947, 4415, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.1700764371336793, "compression_ratio": 1.8164794007490637, "no_speech_prob": 0.007808685302734375, "words": [ { "start": 534.17, "end": 534.47, "word": " And", "probability": 0.6796875 }, { "start": 534.47, "end": 534.59, "word": " they're", "probability": 0.82958984375 }, { "start": 534.59, "end": 534.81, "word": " tracking", "probability": 0.7294921875 }, { "start": 534.81, "end": 535.07, "word": " cheetah", "probability": 0.916259765625 }, { "start": 535.07, "end": 535.59, "word": " population", "probability": 0.8232421875 }, { "start": 535.59, "end": 535.95, "word": ".", "probability": 0.845703125 } ] }, { "id": 149, "seek": 54706, "start": 535.99, "end": 539.31, "text": " So they'll take pictures, it'll get sent off to a human analyst,", "tokens": [ 50664, 407, 436, 603, 747, 5242, 11, 309, 603, 483, 2279, 766, 281, 257, 1952, 19085, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.1700764371336793, "compression_ratio": 1.8164794007490637, "no_speech_prob": 0.007808685302734375, "words": [ { "start": 535.99, "end": 536.19, "word": " So", "probability": 0.79736328125 }, { "start": 536.19, "end": 536.85, "word": " they'll", "probability": 0.7158203125 }, { "start": 536.85, "end": 537.11, "word": " take", "probability": 0.8125 }, { "start": 537.11, "end": 537.49, "word": " pictures", "probability": 0.701171875 }, { "start": 537.49, "end": 537.71, "word": ",", "probability": 0.70263671875 }, { "start": 537.71, "end": 537.85, "word": " it'll", "probability": 0.87646484375 }, { "start": 537.85, "end": 538.01, "word": " get", "probability": 0.89990234375 }, { "start": 538.01, "end": 538.21, "word": " sent", "probability": 0.7841796875 }, { "start": 538.21, "end": 538.35, "word": " off", "probability": 0.80810546875 }, { "start": 538.35, "end": 538.47, "word": " to", "probability": 0.90234375 }, { "start": 538.59, "end": 538.77, "word": " a human", "probability": 0.8212890625 }, { "start": 538.77, "end": 539.21, "word": " analyst", "probability": 0.5751953125 }, { "start": 539.21, "end": 539.31, "word": ",", "probability": 0.48388671875 } ] }, { "id": 150, "seek": 54706, "start": 539.31, "end": 540.53, "text": " and the human will look at it and say,", "tokens": [ 50814, 293, 264, 1952, 486, 574, 412, 309, 293, 584, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.1700764371336793, "compression_ratio": 1.8164794007490637, "no_speech_prob": 0.007808685302734375, "words": [ { "start": 539.31, "end": 539.37, "word": " and", "probability": 0.88037109375 }, { "start": 539.37, "end": 539.47, "word": " the", "probability": 0.7001953125 }, { "start": 539.47, "end": 539.65, "word": " human", "probability": 0.81884765625 }, { "start": 539.65, "end": 539.77, "word": " will", "probability": 0.75634765625 }, { "start": 539.77, "end": 539.93, "word": " look", "probability": 0.91943359375 }, { "start": 539.93, "end": 540.05, "word": " at", "probability": 0.90234375 }, { "start": 540.05, "end": 540.13, "word": " it", "probability": 0.896484375 }, { "start": 540.13, "end": 540.25, "word": " and", "probability": 0.85009765625 }, { "start": 540.25, "end": 540.39, "word": " say", "probability": 0.89111328125 }, { "start": 540.39, "end": 540.53, "word": ",", "probability": 0.7998046875 } ] }, { "id": 151, "seek": 54706, "start": 540.53, "end": 543.17, "text": " okay, is there a cheetah in the picture or not?", "tokens": [ 50914, 1392, 11, 307, 456, 257, 947, 47947, 294, 264, 3036, 420, 406, 30, 51064 ], "temperature": 0.0, "avg_logprob": -0.1700764371336793, "compression_ratio": 1.8164794007490637, "no_speech_prob": 0.007808685302734375, "words": [ { "start": 540.53, "end": 540.67, "word": " okay", "probability": 0.263427734375 }, { "start": 540.67, "end": 540.79, "word": ",", "probability": 0.876953125 }, { "start": 540.79, "end": 540.95, "word": " is", "probability": 0.89208984375 }, { "start": 540.95, "end": 541.07, "word": " there", "probability": 0.853515625 }, { "start": 541.21, "end": 541.37, "word": " a cheetah", "probability": 0.946533203125 }, { "start": 541.37, "end": 541.49, "word": " in", "probability": 0.90380859375 }, { "start": 541.49, "end": 541.59, "word": " the", "probability": 0.8134765625 }, { "start": 541.59, "end": 541.91, "word": " picture", "probability": 0.79296875 }, { "start": 541.91, "end": 542.57, "word": " or", "probability": 0.68408203125 }, { "start": 542.57, "end": 542.81, "word": " not", "probability": 0.88232421875 }, { "start": 542.81, "end": 543.17, "word": "?", "probability": 0.89453125 } ] }, { "id": 152, "seek": 54706, "start": 543.81, "end": 546.27, "text": " And so they approached my friend and they said,", "tokens": [ 51064, 400, 370, 436, 17247, 452, 1277, 293, 436, 848, 11, 51164 ], "temperature": 0.0, "avg_logprob": -0.1700764371336793, "compression_ratio": 1.8164794007490637, "no_speech_prob": 0.007808685302734375, "words": [ { "start": 543.81, "end": 544.05, "word": " And", "probability": 0.873046875 }, { "start": 544.05, "end": 544.45, "word": " so", "probability": 0.9033203125 }, { "start": 544.45, "end": 545.25, "word": " they", "probability": 0.55517578125 }, { "start": 545.25, "end": 545.47, "word": " approached", "probability": 0.62158203125 }, { "start": 545.47, "end": 545.63, "word": " my", "probability": 0.90478515625 }, { "start": 545.63, "end": 545.79, "word": " friend", "probability": 0.65283203125 }, { "start": 545.79, "end": 545.91, "word": " and", "probability": 0.74755859375 }, { "start": 545.91, "end": 546.05, "word": " they", "probability": 0.72509765625 }, { "start": 546.05, "end": 546.19, "word": " said", "probability": 0.884765625 }, { "start": 546.19, "end": 546.27, "word": ",", "probability": 0.8828125 } ] }, { "id": 153, "seek": 54706, "start": 546.27, "end": 548.17, "text": " hey, is there a way that we can improve this process?", "tokens": [ 51164, 4177, 11, 307, 456, 257, 636, 300, 321, 393, 3470, 341, 1399, 30, 51264 ], "temperature": 0.0, "avg_logprob": -0.1700764371336793, "compression_ratio": 1.8164794007490637, "no_speech_prob": 0.007808685302734375, "words": [ { "start": 546.27, "end": 546.37, "word": " hey", "probability": 0.58349609375 }, { "start": 546.37, "end": 546.47, "word": ",", "probability": 0.919921875 }, { "start": 546.47, "end": 546.57, "word": " is", "probability": 0.9033203125 }, { "start": 546.57, "end": 546.67, "word": " there", "probability": 0.85546875 }, { "start": 546.75, "end": 546.83, "word": " a way", "probability": 0.89599609375 }, { "start": 546.83, "end": 546.95, "word": " that", "probability": 0.845703125 }, { "start": 546.95, "end": 547.03, "word": " we", "probability": 0.90625 }, { "start": 547.03, "end": 547.15, "word": " can", "probability": 0.87939453125 }, { "start": 547.15, "end": 547.45, "word": " improve", "probability": 0.73193359375 }, { "start": 547.45, "end": 547.65, "word": " this", "probability": 0.8828125 }, { "start": 547.65, "end": 548.03, "word": " process", "probability": 0.87353515625 }, { "start": 548.03, "end": 548.17, "word": "?", "probability": 0.8125 } ] }, { "id": 154, "seek": 54706, "start": 548.17, "end": 549.69, "text": " What's something that we can do here?", "tokens": [ 51264, 708, 311, 746, 300, 321, 393, 360, 510, 30, 51364 ], "temperature": 0.0, "avg_logprob": -0.1700764371336793, "compression_ratio": 1.8164794007490637, "no_speech_prob": 0.007808685302734375, "words": [ { "start": 548.17, "end": 548.31, "word": " What's", "probability": 0.893310546875 }, { "start": 548.31, "end": 548.49, "word": " something", "probability": 0.7294921875 }, { "start": 548.49, "end": 548.65, "word": " that", "probability": 0.875 }, { "start": 548.65, "end": 548.73, "word": " we", "probability": 0.90380859375 }, { "start": 548.73, "end": 548.89, "word": " can", "probability": 0.89208984375 }, { "start": 548.89, "end": 549.07, "word": " do", "probability": 0.912109375 }, { "start": 549.07, "end": 549.41, "word": " here", "probability": 0.81640625 }, { "start": 549.41, "end": 549.69, "word": "?", "probability": 0.97412109375 } ] }, { "id": 155, "seek": 54706, "start": 549.69, "end": 553.63, "text": " And so he said, okay, let me try a couple things.", "tokens": [ 51364, 400, 370, 415, 848, 11, 1392, 11, 718, 385, 853, 257, 1916, 721, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.1700764371336793, "compression_ratio": 1.8164794007490637, "no_speech_prob": 0.007808685302734375, "words": [ { "start": 549.69, "end": 549.85, "word": " And", "probability": 0.87646484375 }, { "start": 549.85, "end": 549.99, "word": " so", "probability": 0.845703125 }, { "start": 549.99, "end": 550.13, "word": " he", "probability": 0.87060546875 }, { "start": 550.13, "end": 550.31, "word": " said", "probability": 0.8837890625 }, { "start": 550.31, "end": 550.37, "word": ",", "probability": 0.93701171875 }, { "start": 550.37, "end": 550.53, "word": " okay", "probability": 0.75927734375 }, { "start": 550.53, "end": 550.61, "word": ",", "probability": 0.97412109375 }, { "start": 550.61, "end": 550.73, "word": " let", "probability": 0.875 }, { "start": 550.73, "end": 551.21, "word": " me", "probability": 0.90673828125 }, { "start": 551.21, "end": 552.01, "word": " try", "probability": 0.71875 }, { "start": 552.71, "end": 552.91, "word": " a couple", "probability": 0.79345703125 }, { "start": 552.91, "end": 553.27, "word": " things", "probability": 0.6142578125 }, { "start": 553.27, "end": 553.63, "word": ".", "probability": 0.99853515625 } ] }, { "id": 156, "seek": 54706, "start": 553.91, "end": 557.99, "text": " So what he did was use a very common image library", "tokens": [ 51564, 407, 437, 415, 630, 390, 764, 257, 588, 2689, 3256, 6405, 51764 ], "temperature": 0.0, "avg_logprob": -0.1700764371336793, "compression_ratio": 1.8164794007490637, "no_speech_prob": 0.007808685302734375, "words": [ { "start": 553.91, "end": 554.27, "word": " So", "probability": 0.89453125 }, { "start": 554.27, "end": 554.53, "word": " what", "probability": 0.87939453125 }, { "start": 554.53, "end": 554.69, "word": " he", "probability": 0.90380859375 }, { "start": 554.69, "end": 554.95, "word": " did", "probability": 0.8955078125 }, { "start": 554.95, "end": 555.21, "word": " was", "probability": 0.88720703125 }, { "start": 555.21, "end": 555.49, "word": " use", "probability": 0.81201171875 }, { "start": 555.93, "end": 556.13, "word": " a very", "probability": 0.736328125 }, { "start": 556.13, "end": 556.71, "word": " common", "probability": 0.73193359375 }, { "start": 556.71, "end": 557.53, "word": " image", "probability": 0.8388671875 }, { "start": 557.53, "end": 557.99, "word": " library", "probability": 0.8466796875 } ] }, { "id": 157, "seek": 57428, "start": 557.99, "end": 562.07, "text": " and said, okay, let's train a machine learning algorithm", "tokens": [ 50364, 293, 848, 11, 1392, 11, 718, 311, 3847, 257, 3479, 2539, 9284, 50564 ], "temperature": 0.0, "avg_logprob": -0.15466102250551772, "compression_ratio": 1.7217391304347827, "no_speech_prob": 0.08270263671875, "words": [ { "start": 557.99, "end": 558.71, "word": " and", "probability": 0.403076171875 }, { "start": 558.71, "end": 559.89, "word": " said", "probability": 0.81982421875 }, { "start": 559.89, "end": 560.07, "word": ",", "probability": 0.66357421875 }, { "start": 560.07, "end": 560.29, "word": " okay", "probability": 0.304443359375 }, { "start": 560.29, "end": 560.67, "word": ",", "probability": 0.87158203125 }, { "start": 560.67, "end": 560.99, "word": " let's", "probability": 0.933837890625 }, { "start": 560.99, "end": 561.15, "word": " train", "probability": 0.88720703125 }, { "start": 561.23, "end": 561.45, "word": " a machine", "probability": 0.69580078125 }, { "start": 561.45, "end": 561.69, "word": " learning", "probability": 0.8076171875 }, { "start": 561.69, "end": 562.07, "word": " algorithm", "probability": 0.82958984375 } ] }, { "id": 158, "seek": 57428, "start": 562.07, "end": 566.05, "text": " to identify images, if there's a cheetah in the picture or not.", "tokens": [ 50564, 281, 5876, 5267, 11, 498, 456, 311, 257, 947, 47947, 294, 264, 3036, 420, 406, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.15466102250551772, "compression_ratio": 1.7217391304347827, "no_speech_prob": 0.08270263671875, "words": [ { "start": 562.07, "end": 562.47, "word": " to", "probability": 0.89697265625 }, { "start": 562.47, "end": 563.03, "word": " identify", "probability": 0.89453125 }, { "start": 563.03, "end": 563.61, "word": " images", "probability": 0.8310546875 }, { "start": 563.61, "end": 563.77, "word": ",", "probability": 0.43701171875 }, { "start": 563.77, "end": 563.99, "word": " if", "probability": 0.90283203125 }, { "start": 563.99, "end": 564.29, "word": " there's", "probability": 0.817138671875 }, { "start": 564.47, "end": 564.61, "word": " a cheetah", "probability": 0.912841796875 }, { "start": 564.61, "end": 564.73, "word": " in", "probability": 0.9013671875 }, { "start": 564.73, "end": 564.79, "word": " the", "probability": 0.7529296875 }, { "start": 564.79, "end": 565.07, "word": " picture", "probability": 0.77490234375 }, { "start": 565.07, "end": 565.31, "word": " or", "probability": 0.8740234375 }, { "start": 565.31, "end": 565.61, "word": " not", "probability": 0.89599609375 }, { "start": 565.61, "end": 566.05, "word": ".", "probability": 0.95849609375 } ] }, { "id": 159, "seek": 57428, "start": 566.45, "end": 569.01, "text": " If it reached above a 5% confidence,", "tokens": [ 50764, 759, 309, 6488, 3673, 257, 1025, 4, 6687, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.15466102250551772, "compression_ratio": 1.7217391304347827, "no_speech_prob": 0.08270263671875, "words": [ { "start": 566.45, "end": 566.75, "word": " If", "probability": 0.90185546875 }, { "start": 566.75, "end": 566.87, "word": " it", "probability": 0.90576171875 }, { "start": 566.87, "end": 567.15, "word": " reached", "probability": 0.75927734375 }, { "start": 567.15, "end": 567.51, "word": " above", "probability": 0.888671875 }, { "start": 567.69, "end": 568.03, "word": " a 5", "probability": 0.83837890625 }, { "start": 568.03, "end": 568.29, "word": "%", "probability": 0.98388671875 }, { "start": 568.29, "end": 568.89, "word": " confidence", "probability": 0.90087890625 }, { "start": 568.89, "end": 569.01, "word": ",", "probability": 0.859375 } ] }, { "id": 160, "seek": 57428, "start": 569.01, "end": 571.83, "text": " says, okay, I'm 5% confident or 6% confident", "tokens": [ 50914, 1619, 11, 1392, 11, 286, 478, 1025, 4, 6679, 420, 1386, 4, 6679, 51064 ], "temperature": 0.0, "avg_logprob": -0.15466102250551772, "compression_ratio": 1.7217391304347827, "no_speech_prob": 0.08270263671875, "words": [ { "start": 569.01, "end": 569.21, "word": " says", "probability": 0.400634765625 }, { "start": 569.21, "end": 569.33, "word": ",", "probability": 0.69580078125 }, { "start": 569.33, "end": 569.45, "word": " okay", "probability": 0.662109375 }, { "start": 569.45, "end": 569.51, "word": ",", "probability": 0.91552734375 }, { "start": 569.51, "end": 569.61, "word": " I'm", "probability": 0.991943359375 }, { "start": 569.61, "end": 569.97, "word": " 5", "probability": 0.99169921875 }, { "start": 569.97, "end": 570.21, "word": "%", "probability": 0.99462890625 }, { "start": 570.21, "end": 570.63, "word": " confident", "probability": 0.92138671875 }, { "start": 570.63, "end": 570.81, "word": " or", "probability": 0.74560546875 }, { "start": 570.81, "end": 571.07, "word": " 6", "probability": 0.99560546875 }, { "start": 571.07, "end": 571.37, "word": "%", "probability": 0.9990234375 }, { "start": 571.37, "end": 571.83, "word": " confident", "probability": 0.9228515625 } ] }, { "id": 161, "seek": 57428, "start": 571.83, "end": 575.55, "text": " that there's a cheetah in this image, it got sent over to an analyst.", "tokens": [ 51064, 300, 456, 311, 257, 947, 47947, 294, 341, 3256, 11, 309, 658, 2279, 670, 281, 364, 19085, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.15466102250551772, "compression_ratio": 1.7217391304347827, "no_speech_prob": 0.08270263671875, "words": [ { "start": 571.83, "end": 572.29, "word": " that", "probability": 0.8408203125 }, { "start": 572.29, "end": 572.49, "word": " there's", "probability": 0.917724609375 }, { "start": 572.61, "end": 572.77, "word": " a cheetah", "probability": 0.950439453125 }, { "start": 572.77, "end": 572.93, "word": " in", "probability": 0.90576171875 }, { "start": 572.93, "end": 573.09, "word": " this", "probability": 0.8828125 }, { "start": 573.09, "end": 573.39, "word": " image", "probability": 0.83447265625 }, { "start": 573.39, "end": 573.81, "word": ",", "probability": 0.87060546875 }, { "start": 573.81, "end": 573.97, "word": " it", "probability": 0.89599609375 }, { "start": 573.97, "end": 574.13, "word": " got", "probability": 0.8974609375 }, { "start": 574.13, "end": 574.33, "word": " sent", "probability": 0.80859375 }, { "start": 574.33, "end": 574.47, "word": " over", "probability": 0.8818359375 }, { "start": 574.47, "end": 574.63, "word": " to", "probability": 0.9111328125 }, { "start": 574.63, "end": 574.75, "word": " an", "probability": 0.90673828125 }, { "start": 574.75, "end": 575.11, "word": " analyst", "probability": 0.60546875 }, { "start": 575.11, "end": 575.55, "word": ".", "probability": 0.9794921875 } ] }, { "id": 162, "seek": 57428, "start": 575.81, "end": 579.65, "text": " If it was less than 5% confident, it would just throw it away.", "tokens": [ 51264, 759, 309, 390, 1570, 813, 1025, 4, 6679, 11, 309, 576, 445, 3507, 309, 1314, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.15466102250551772, "compression_ratio": 1.7217391304347827, "no_speech_prob": 0.08270263671875, "words": [ { "start": 575.81, "end": 576.05, "word": " If", "probability": 0.90185546875 }, { "start": 576.05, "end": 576.15, "word": " it", "probability": 0.90087890625 }, { "start": 576.15, "end": 576.29, "word": " was", "probability": 0.89404296875 }, { "start": 576.29, "end": 576.69, "word": " less", "probability": 0.87841796875 }, { "start": 576.69, "end": 576.89, "word": " than", "probability": 0.869140625 }, { "start": 576.89, "end": 577.17, "word": " 5", "probability": 0.998046875 }, { "start": 577.17, "end": 577.43, "word": "%", "probability": 0.99755859375 }, { "start": 577.43, "end": 577.93, "word": " confident", "probability": 0.93701171875 }, { "start": 577.93, "end": 578.37, "word": ",", "probability": 0.96728515625 }, { "start": 578.37, "end": 578.49, "word": " it", "probability": 0.8232421875 }, { "start": 578.49, "end": 578.59, "word": " would", "probability": 0.81103515625 }, { "start": 578.59, "end": 578.73, "word": " just", "probability": 0.88525390625 }, { "start": 578.73, "end": 578.91, "word": " throw", "probability": 0.8017578125 }, { "start": 578.91, "end": 579.01, "word": " it", "probability": 0.9013671875 }, { "start": 579.01, "end": 579.21, "word": " away", "probability": 0.8193359375 }, { "start": 579.21, "end": 579.65, "word": ".", "probability": 0.99560546875 } ] }, { "id": 163, "seek": 57428, "start": 580.63, "end": 585.21, "text": " Now, 5%, that doesn't really sound like a lot, and it's not.", "tokens": [ 51464, 823, 11, 1025, 8923, 300, 1177, 380, 534, 1626, 411, 257, 688, 11, 293, 309, 311, 406, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.15466102250551772, "compression_ratio": 1.7217391304347827, "no_speech_prob": 0.08270263671875, "words": [ { "start": 580.63, "end": 580.97, "word": " Now", "probability": 0.88720703125 }, { "start": 580.97, "end": 581.15, "word": ",", "probability": 0.6533203125 }, { "start": 581.15, "end": 581.67, "word": " 5%,", "probability": 0.862060546875 }, { "start": 581.67, "end": 581.87, "word": " that", "probability": 0.88623046875 }, { "start": 581.87, "end": 582.09, "word": " doesn't", "probability": 0.929443359375 }, { "start": 582.09, "end": 582.29, "word": " really", "probability": 0.7646484375 }, { "start": 582.29, "end": 582.61, "word": " sound", "probability": 0.787109375 }, { "start": 582.61, "end": 582.81, "word": " like", "probability": 0.876953125 }, { "start": 582.93, "end": 583.13, "word": " a lot", "probability": 0.88818359375 }, { "start": 583.13, "end": 583.49, "word": ",", "probability": 0.537109375 }, { "start": 583.49, "end": 583.85, "word": " and", "probability": 0.89404296875 }, { "start": 583.85, "end": 584.51, "word": " it's", "probability": 0.94970703125 }, { "start": 584.51, "end": 584.77, "word": " not", "probability": 0.896484375 }, { "start": 584.77, "end": 585.21, "word": ".", "probability": 0.466064453125 } ] }, { "id": 164, "seek": 60088, "start": 586.35, "end": 591.79, "text": " But the ROI of what this model was able to do is pretty astounding.", "tokens": [ 50414, 583, 264, 49808, 295, 437, 341, 2316, 390, 1075, 281, 360, 307, 1238, 5357, 24625, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.17142428185504216, "compression_ratio": 1.5802469135802468, "no_speech_prob": 0.0005273818969726562, "words": [ { "start": 586.35, "end": 586.83, "word": " But", "probability": 0.61083984375 }, { "start": 586.83, "end": 587.31, "word": " the", "probability": 0.61083984375 }, { "start": 587.31, "end": 587.79, "word": " ROI", "probability": 0.81640625 }, { "start": 587.79, "end": 588.13, "word": " of", "probability": 0.8837890625 }, { "start": 588.13, "end": 588.29, "word": " what", "probability": 0.8818359375 }, { "start": 588.29, "end": 588.49, "word": " this", "probability": 0.87939453125 }, { "start": 588.49, "end": 588.73, "word": " model", "probability": 0.80517578125 }, { "start": 588.73, "end": 588.89, "word": " was", "probability": 0.876953125 }, { "start": 588.89, "end": 589.05, "word": " able", "probability": 0.88427734375 }, { "start": 589.05, "end": 589.21, "word": " to", "probability": 0.90380859375 }, { "start": 589.21, "end": 589.49, "word": " do", "probability": 0.90087890625 }, { "start": 589.49, "end": 590.69, "word": " is", "probability": 0.74755859375 }, { "start": 590.69, "end": 590.89, "word": " pretty", "probability": 0.87646484375 }, { "start": 590.89, "end": 591.31, "word": " astounding", "probability": 0.9169921875 }, { "start": 591.31, "end": 591.79, "word": ".", "probability": 0.98193359375 } ] }, { "id": 165, "seek": 60088, "start": 592.09, "end": 596.13, "text": " So what normally would have taken them a year of labor to perform,", "tokens": [ 50714, 407, 437, 5646, 576, 362, 2726, 552, 257, 1064, 295, 5938, 281, 2042, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.17142428185504216, "compression_ratio": 1.5802469135802468, "no_speech_prob": 0.0005273818969726562, "words": [ { "start": 592.09, "end": 592.41, "word": " So", "probability": 0.658203125 }, { "start": 592.41, "end": 592.73, "word": " what", "probability": 0.703125 }, { "start": 592.73, "end": 593.13, "word": " normally", "probability": 0.84130859375 }, { "start": 593.13, "end": 593.31, "word": " would", "probability": 0.83935546875 }, { "start": 593.31, "end": 593.41, "word": " have", "probability": 0.76708984375 }, { "start": 593.41, "end": 593.63, "word": " taken", "probability": 0.7353515625 }, { "start": 593.63, "end": 593.85, "word": " them", "probability": 0.724609375 }, { "start": 594.05, "end": 594.43, "word": " a year", "probability": 0.87109375 }, { "start": 594.43, "end": 594.65, "word": " of", "probability": 0.8994140625 }, { "start": 594.65, "end": 594.93, "word": " labor", "probability": 0.74755859375 }, { "start": 594.93, "end": 595.33, "word": " to", "probability": 0.900390625 }, { "start": 595.33, "end": 595.79, "word": " perform", "probability": 0.77294921875 }, { "start": 595.79, "end": 596.13, "word": ",", "probability": 0.76123046875 } ] }, { "id": 166, "seek": 60088, "start": 596.13, "end": 598.27, "text": " they were able to do in one month.", "tokens": [ 50914, 436, 645, 1075, 281, 360, 294, 472, 1618, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.17142428185504216, "compression_ratio": 1.5802469135802468, "no_speech_prob": 0.0005273818969726562, "words": [ { "start": 596.13, "end": 596.57, "word": " they", "probability": 0.7265625 }, { "start": 596.57, "end": 596.67, "word": " were", "probability": 0.88427734375 }, { "start": 596.67, "end": 596.83, "word": " able", "probability": 0.89013671875 }, { "start": 596.83, "end": 596.95, "word": " to", "probability": 0.90625 }, { "start": 596.95, "end": 597.07, "word": " do", "probability": 0.9150390625 }, { "start": 597.07, "end": 597.19, "word": " in", "probability": 0.865234375 }, { "start": 597.19, "end": 597.47, "word": " one", "probability": 0.79443359375 }, { "start": 597.47, "end": 597.79, "word": " month", "probability": 0.8310546875 }, { "start": 597.79, "end": 598.27, "word": ".", "probability": 0.9736328125 } ] }, { "id": 167, "seek": 60088, "start": 598.45, "end": 601.75, "text": " That is a 1,200% increase in productivity.", "tokens": [ 51014, 663, 307, 257, 502, 11, 7629, 4, 3488, 294, 15604, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.17142428185504216, "compression_ratio": 1.5802469135802468, "no_speech_prob": 0.0005273818969726562, "words": [ { "start": 598.45, "end": 598.81, "word": " That", "probability": 0.81005859375 }, { "start": 598.81, "end": 598.89, "word": " is", "probability": 0.87890625 }, { "start": 599.07, "end": 599.63, "word": " a 1", "probability": 0.39453125 }, { "start": 599.63, "end": 599.65, "word": ",200", "probability": 0.880859375 }, { "start": 599.65, "end": 600.19, "word": "%", "probability": 0.89697265625 }, { "start": 600.19, "end": 600.71, "word": " increase", "probability": 0.7568359375 }, { "start": 600.71, "end": 600.89, "word": " in", "probability": 0.9033203125 }, { "start": 600.89, "end": 601.27, "word": " productivity", "probability": 0.9072265625 }, { "start": 601.27, "end": 601.75, "word": ".", "probability": 0.9619140625 } ] }, { "id": 168, "seek": 60088, "start": 602.75, "end": 604.19, "text": " So that's pretty powerful.", "tokens": [ 51214, 407, 300, 311, 1238, 4005, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.17142428185504216, "compression_ratio": 1.5802469135802468, "no_speech_prob": 0.0005273818969726562, "words": [ { "start": 602.75, "end": 603.23, "word": " So", "probability": 0.845703125 }, { "start": 603.23, "end": 603.43, "word": " that's", "probability": 0.92822265625 }, { "start": 603.43, "end": 603.63, "word": " pretty", "probability": 0.8642578125 }, { "start": 603.63, "end": 604.03, "word": " powerful", "probability": 0.8486328125 }, { "start": 604.03, "end": 604.19, "word": ".", "probability": 0.419677734375 } ] }, { "id": 169, "seek": 60088, "start": 604.19, "end": 605.97, "text": " And that's just a very simple model.", "tokens": [ 51314, 400, 300, 311, 445, 257, 588, 2199, 2316, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.17142428185504216, "compression_ratio": 1.5802469135802468, "no_speech_prob": 0.0005273818969726562, "words": [ { "start": 604.19, "end": 604.29, "word": " And", "probability": 0.8779296875 }, { "start": 604.29, "end": 604.49, "word": " that's", "probability": 0.9384765625 }, { "start": 604.49, "end": 604.65, "word": " just", "probability": 0.88720703125 }, { "start": 604.81, "end": 605.03, "word": " a very", "probability": 0.73193359375 }, { "start": 605.03, "end": 605.37, "word": " simple", "probability": 0.90869140625 }, { "start": 605.37, "end": 605.71, "word": " model", "probability": 0.80712890625 }, { "start": 605.71, "end": 605.97, "word": ".", "probability": 0.97900390625 } ] }, { "id": 170, "seek": 60088, "start": 605.97, "end": 609.55, "text": " So as we can develop more and more advanced things,", "tokens": [ 51414, 407, 382, 321, 393, 1499, 544, 293, 544, 7339, 721, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.17142428185504216, "compression_ratio": 1.5802469135802468, "no_speech_prob": 0.0005273818969726562, "words": [ { "start": 605.97, "end": 606.13, "word": " So", "probability": 0.81005859375 }, { "start": 606.13, "end": 606.81, "word": " as", "probability": 0.8271484375 }, { "start": 606.81, "end": 606.93, "word": " we", "probability": 0.90673828125 }, { "start": 606.93, "end": 607.11, "word": " can", "probability": 0.88671875 }, { "start": 607.11, "end": 607.51, "word": " develop", "probability": 0.69140625 }, { "start": 607.51, "end": 607.81, "word": " more", "probability": 0.8828125 }, { "start": 607.81, "end": 607.93, "word": " and", "probability": 0.89306640625 }, { "start": 607.93, "end": 608.07, "word": " more", "probability": 0.8818359375 }, { "start": 608.07, "end": 608.47, "word": " advanced", "probability": 0.83740234375 }, { "start": 608.47, "end": 608.99, "word": " things", "probability": 0.73876953125 }, { "start": 608.99, "end": 609.55, "word": ",", "probability": 0.95703125 } ] }, { "id": 171, "seek": 60088, "start": 609.55, "end": 611.81, "text": " these are ways that we can really improve our processes", "tokens": [ 51564, 613, 366, 2098, 300, 321, 393, 534, 3470, 527, 7555, 51714 ], "temperature": 0.0, "avg_logprob": -0.17142428185504216, "compression_ratio": 1.5802469135802468, "no_speech_prob": 0.0005273818969726562, "words": [ { "start": 609.55, "end": 609.97, "word": " these", "probability": 0.69970703125 }, { "start": 609.97, "end": 610.07, "word": " are", "probability": 0.89404296875 }, { "start": 610.07, "end": 610.31, "word": " ways", "probability": 0.814453125 }, { "start": 610.31, "end": 610.45, "word": " that", "probability": 0.86572265625 }, { "start": 610.45, "end": 610.55, "word": " we", "probability": 0.90380859375 }, { "start": 610.55, "end": 610.69, "word": " can", "probability": 0.89453125 }, { "start": 610.69, "end": 610.93, "word": " really", "probability": 0.787109375 }, { "start": 610.93, "end": 611.27, "word": " improve", "probability": 0.7431640625 }, { "start": 611.27, "end": 611.41, "word": " our", "probability": 0.81005859375 }, { "start": 611.41, "end": 611.81, "word": " processes", "probability": 0.81201171875 } ] }, { "id": 172, "seek": 62944, "start": 611.81, "end": 614.63, "text": " to move at machine speed and scale.", "tokens": [ 50364, 281, 1286, 412, 3479, 3073, 293, 4373, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.21585051054807053, "compression_ratio": 1.913978494623656, "no_speech_prob": 0.79296875, "words": [ { "start": 611.81, "end": 612.15, "word": " to", "probability": 0.642578125 }, { "start": 612.15, "end": 612.43, "word": " move", "probability": 0.8583984375 }, { "start": 612.43, "end": 612.57, "word": " at", "probability": 0.88330078125 }, { "start": 612.57, "end": 612.87, "word": " machine", "probability": 0.69091796875 }, { "start": 612.87, "end": 613.29, "word": " speed", "probability": 0.828125 }, { "start": 613.29, "end": 613.59, "word": " and", "probability": 0.88232421875 }, { "start": 613.59, "end": 614.03, "word": " scale", "probability": 0.80615234375 }, { "start": 614.03, "end": 614.63, "word": ".", "probability": 0.85888671875 } ] }, { "id": 173, "seek": 62944, "start": 616.73, "end": 617.67, "text": " GT?", "tokens": [ 50614, 17530, 30, 50664 ], "temperature": 0.0, "avg_logprob": -0.21585051054807053, "compression_ratio": 1.913978494623656, "no_speech_prob": 0.79296875, "words": [ { "start": 616.73, "end": 617.33, "word": " GT", "probability": 0.269287109375 }, { "start": 617.33, "end": 617.67, "word": "?", "probability": 0.5224609375 } ] }, { "id": 174, "seek": 62944, "start": 617.67, "end": 618.47, "text": " Yeah.", "tokens": [ 50664, 865, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.21585051054807053, "compression_ratio": 1.913978494623656, "no_speech_prob": 0.79296875, "words": [ { "start": 617.67, "end": 617.91, "word": " Yeah", "probability": 0.344482421875 }, { "start": 617.91, "end": 618.47, "word": ".", "probability": 0.52001953125 } ] }, { "id": 175, "seek": 62944, "start": 618.47, "end": 622.01, "text": " We have a question, and it's,", "tokens": [ 50714, 492, 362, 257, 1168, 11, 293, 309, 311, 11, 50864 ], "temperature": 0.0, "avg_logprob": -0.21585051054807053, "compression_ratio": 1.913978494623656, "no_speech_prob": 0.79296875, "words": [ { "start": 618.47, "end": 618.99, "word": " We", "probability": 0.89306640625 }, { "start": 618.99, "end": 619.41, "word": " have", "probability": 0.8828125 }, { "start": 620.01, "end": 620.71, "word": " a question", "probability": 0.79345703125 }, { "start": 620.71, "end": 621.07, "word": ",", "probability": 0.2283935546875 }, { "start": 621.07, "end": 621.17, "word": " and", "probability": 0.88720703125 }, { "start": 621.17, "end": 621.53, "word": " it's", "probability": 0.939208984375 }, { "start": 621.53, "end": 622.01, "word": ",", "probability": 0.391357421875 } ] }, { "id": 176, "seek": 62944, "start": 622.01, "end": 626.13, "text": " any links to information pertaining to creating your own models", "tokens": [ 50864, 604, 6123, 281, 1589, 49582, 281, 4084, 428, 1065, 5245, 51064 ], "temperature": 0.0, "avg_logprob": -0.21585051054807053, "compression_ratio": 1.913978494623656, "no_speech_prob": 0.79296875, "words": [ { "start": 622.01, "end": 622.19, "word": " any", "probability": 0.356201171875 }, { "start": 622.19, "end": 622.73, "word": " links", "probability": 0.78857421875 }, { "start": 622.73, "end": 622.93, "word": " to", "probability": 0.90869140625 }, { "start": 622.93, "end": 623.57, "word": " information", "probability": 0.72119140625 }, { "start": 623.57, "end": 624.15, "word": " pertaining", "probability": 0.79052734375 }, { "start": 624.15, "end": 624.45, "word": " to", "probability": 0.90087890625 }, { "start": 624.45, "end": 624.97, "word": " creating", "probability": 0.7939453125 }, { "start": 624.97, "end": 625.39, "word": " your", "probability": 0.80517578125 }, { "start": 625.39, "end": 625.69, "word": " own", "probability": 0.82373046875 }, { "start": 625.69, "end": 626.13, "word": " models", "probability": 0.8095703125 } ] }, { "id": 177, "seek": 62944, "start": 626.13, "end": 629.25, "text": " rather than training existing ones?", "tokens": [ 51064, 2831, 813, 3097, 6741, 2306, 30, 51314 ], "temperature": 0.0, "avg_logprob": -0.21585051054807053, "compression_ratio": 1.913978494623656, "no_speech_prob": 0.79296875, "words": [ { "start": 626.13, "end": 626.69, "word": " rather", "probability": 0.60009765625 }, { "start": 626.69, "end": 627.03, "word": " than", "probability": 0.8828125 }, { "start": 627.03, "end": 627.53, "word": " training", "probability": 0.75048828125 }, { "start": 627.53, "end": 628.19, "word": " existing", "probability": 0.8564453125 }, { "start": 628.19, "end": 628.65, "word": " ones", "probability": 0.83251953125 }, { "start": 628.65, "end": 629.25, "word": "?", "probability": 0.85791015625 } ] }, { "id": 178, "seek": 62944, "start": 630.67, "end": 634.59, "text": " Creating your own models rather than training existing ones?", "tokens": [ 51314, 40002, 428, 1065, 5245, 2831, 813, 3097, 6741, 2306, 30, 51514 ], "temperature": 0.0, "avg_logprob": -0.21585051054807053, "compression_ratio": 1.913978494623656, "no_speech_prob": 0.79296875, "words": [ { "start": 630.67, "end": 631.19, "word": " Creating", "probability": 0.75 }, { "start": 631.19, "end": 631.39, "word": " your", "probability": 0.78857421875 }, { "start": 631.39, "end": 631.63, "word": " own", "probability": 0.8134765625 }, { "start": 631.63, "end": 632.01, "word": " models", "probability": 0.8056640625 }, { "start": 632.01, "end": 632.33, "word": " rather", "probability": 0.76220703125 }, { "start": 632.33, "end": 632.59, "word": " than", "probability": 0.880859375 }, { "start": 632.59, "end": 632.99, "word": " training", "probability": 0.80419921875 }, { "start": 632.99, "end": 633.55, "word": " existing", "probability": 0.86083984375 }, { "start": 633.55, "end": 633.99, "word": " ones", "probability": 0.8291015625 }, { "start": 633.99, "end": 634.59, "word": "?", "probability": 0.962890625 } ] }, { "id": 179, "seek": 62944, "start": 634.89, "end": 635.31, "text": " Yeah.", "tokens": [ 51514, 865, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.21585051054807053, "compression_ratio": 1.913978494623656, "no_speech_prob": 0.79296875, "words": [ { "start": 634.89, "end": 635.17, "word": " Yeah", "probability": 0.904296875 }, { "start": 635.17, "end": 635.31, "word": ".", "probability": 0.6025390625 } ] }, { "id": 180, "seek": 62944, "start": 635.31, "end": 638.55, "text": " I think that you're going to be showing them how to create their own model.", "tokens": [ 51564, 286, 519, 300, 291, 434, 516, 281, 312, 4099, 552, 577, 281, 1884, 641, 1065, 2316, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.21585051054807053, "compression_ratio": 1.913978494623656, "no_speech_prob": 0.79296875, "words": [ { "start": 635.31, "end": 635.81, "word": " I", "probability": 0.97119140625 }, { "start": 635.81, "end": 636.25, "word": " think", "probability": 0.80908203125 }, { "start": 636.25, "end": 636.41, "word": " that", "probability": 0.859375 }, { "start": 636.41, "end": 636.59, "word": " you're", "probability": 0.918212890625 }, { "start": 636.59, "end": 636.67, "word": " going", "probability": 0.513671875 }, { "start": 636.67, "end": 636.71, "word": " to", "probability": 0.90283203125 }, { "start": 636.71, "end": 636.89, "word": " be", "probability": 0.89990234375 }, { "start": 636.89, "end": 637.17, "word": " showing", "probability": 0.7880859375 }, { "start": 637.17, "end": 637.39, "word": " them", "probability": 0.74853515625 }, { "start": 637.39, "end": 637.55, "word": " how", "probability": 0.896484375 }, { "start": 637.55, "end": 637.67, "word": " to", "probability": 0.90380859375 }, { "start": 637.67, "end": 637.93, "word": " create", "probability": 0.84716796875 }, { "start": 637.93, "end": 638.09, "word": " their", "probability": 0.9072265625 }, { "start": 638.09, "end": 638.23, "word": " own", "probability": 0.7919921875 }, { "start": 638.23, "end": 638.49, "word": " model", "probability": 0.80517578125 }, { "start": 638.49, "end": 638.55, "word": ".", "probability": 0.55859375 } ] }, { "id": 181, "seek": 62944, "start": 638.55, "end": 640.37, "text": " We are going to create our own model.", "tokens": [ 51714, 492, 366, 516, 281, 1884, 527, 1065, 2316, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.21585051054807053, "compression_ratio": 1.913978494623656, "no_speech_prob": 0.79296875, "words": [ { "start": 638.55, "end": 638.79, "word": " We", "probability": 0.8271484375 }, { "start": 638.79, "end": 638.95, "word": " are", "probability": 0.8896484375 }, { "start": 638.95, "end": 639.15, "word": " going", "probability": 0.85888671875 }, { "start": 639.15, "end": 639.33, "word": " to", "probability": 0.9013671875 }, { "start": 639.33, "end": 639.55, "word": " create", "probability": 0.83935546875 }, { "start": 639.55, "end": 639.71, "word": " our", "probability": 0.82177734375 }, { "start": 639.71, "end": 639.91, "word": " own", "probability": 0.7998046875 }, { "start": 639.91, "end": 640.27, "word": " model", "probability": 0.81396484375 }, { "start": 640.27, "end": 640.37, "word": ".", "probability": 0.83837890625 } ] }, { "id": 182, "seek": 65778, "start": 641.61, "end": 644.01, "text": " So there are existing models that you can use,", "tokens": [ 50414, 407, 456, 366, 6741, 5245, 300, 291, 393, 764, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.1600942470961147, "compression_ratio": 1.7062937062937062, "no_speech_prob": 0.029296875, "words": [ { "start": 641.61, "end": 642.01, "word": " So", "probability": 0.6416015625 }, { "start": 642.01, "end": 642.29, "word": " there", "probability": 0.658203125 }, { "start": 642.29, "end": 642.41, "word": " are", "probability": 0.86767578125 }, { "start": 642.41, "end": 642.83, "word": " existing", "probability": 0.853515625 }, { "start": 642.83, "end": 643.21, "word": " models", "probability": 0.80224609375 }, { "start": 643.21, "end": 643.41, "word": " that", "probability": 0.87109375 }, { "start": 643.41, "end": 643.53, "word": " you", "probability": 0.89501953125 }, { "start": 643.53, "end": 643.67, "word": " can", "probability": 0.88916015625 }, { "start": 643.67, "end": 643.93, "word": " use", "probability": 0.8076171875 }, { "start": 643.93, "end": 644.01, "word": ",", "probability": 0.352783203125 } ] }, { "id": 183, "seek": 65778, "start": 644.01, "end": 645.61, "text": " what's called transfer learning.", "tokens": [ 50514, 437, 311, 1219, 5003, 2539, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.1600942470961147, "compression_ratio": 1.7062937062937062, "no_speech_prob": 0.029296875, "words": [ { "start": 644.01, "end": 644.21, "word": " what's", "probability": 0.925537109375 }, { "start": 644.21, "end": 644.47, "word": " called", "probability": 0.7998046875 }, { "start": 644.47, "end": 644.93, "word": " transfer", "probability": 0.71484375 }, { "start": 644.93, "end": 645.29, "word": " learning", "probability": 0.841796875 }, { "start": 645.29, "end": 645.61, "word": ".", "probability": 0.88427734375 } ] }, { "id": 184, "seek": 65778, "start": 645.61, "end": 650.17, "text": " So you take a problem, for example, ImageNet, which is a challenge.", "tokens": [ 50614, 407, 291, 747, 257, 1154, 11, 337, 1365, 11, 29903, 31890, 11, 597, 307, 257, 3430, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.1600942470961147, "compression_ratio": 1.7062937062937062, "no_speech_prob": 0.029296875, "words": [ { "start": 645.61, "end": 645.69, "word": " So", "probability": 0.88232421875 }, { "start": 645.69, "end": 645.85, "word": " you", "probability": 0.873046875 }, { "start": 645.85, "end": 646.05, "word": " take", "probability": 0.81982421875 }, { "start": 646.17, "end": 646.53, "word": " a problem", "probability": 0.7763671875 }, { "start": 646.53, "end": 646.77, "word": ",", "probability": 0.837890625 }, { "start": 646.77, "end": 646.89, "word": " for", "probability": 0.888671875 }, { "start": 646.89, "end": 647.25, "word": " example", "probability": 0.93212890625 }, { "start": 647.25, "end": 647.61, "word": ",", "probability": 0.564453125 }, { "start": 647.61, "end": 648.45, "word": " ImageNet", "probability": 0.781494140625 }, { "start": 648.45, "end": 649.05, "word": ",", "probability": 0.82080078125 }, { "start": 649.05, "end": 649.51, "word": " which", "probability": 0.9130859375 }, { "start": 649.51, "end": 649.61, "word": " is", "probability": 0.90234375 }, { "start": 649.73, "end": 650.03, "word": " a challenge", "probability": 0.7744140625 }, { "start": 650.03, "end": 650.17, "word": ".", "probability": 0.53466796875 } ] }, { "id": 185, "seek": 65778, "start": 650.17, "end": 653.19, "text": " It can recognize hundreds of different categories of images,", "tokens": [ 50814, 467, 393, 5521, 6779, 295, 819, 10479, 295, 5267, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.1600942470961147, "compression_ratio": 1.7062937062937062, "no_speech_prob": 0.029296875, "words": [ { "start": 650.17, "end": 650.19, "word": " It", "probability": 0.8203125 }, { "start": 650.19, "end": 650.33, "word": " can", "probability": 0.90283203125 }, { "start": 650.33, "end": 651.11, "word": " recognize", "probability": 0.81396484375 }, { "start": 651.11, "end": 651.61, "word": " hundreds", "probability": 0.79150390625 }, { "start": 651.61, "end": 651.83, "word": " of", "probability": 0.9091796875 }, { "start": 651.83, "end": 652.07, "word": " different", "probability": 0.70361328125 }, { "start": 652.07, "end": 652.55, "word": " categories", "probability": 0.783203125 }, { "start": 652.55, "end": 652.73, "word": " of", "probability": 0.90966796875 }, { "start": 652.73, "end": 652.99, "word": " images", "probability": 0.85498046875 }, { "start": 652.99, "end": 653.19, "word": ",", "probability": 0.348388671875 } ] }, { "id": 186, "seek": 65778, "start": 653.19, "end": 655.65, "text": " and you can take that idea, train your own model", "tokens": [ 50964, 293, 291, 393, 747, 300, 1558, 11, 3847, 428, 1065, 2316, 51114 ], "temperature": 0.0, "avg_logprob": -0.1600942470961147, "compression_ratio": 1.7062937062937062, "no_speech_prob": 0.029296875, "words": [ { "start": 653.19, "end": 653.29, "word": " and", "probability": 0.8896484375 }, { "start": 653.29, "end": 653.41, "word": " you", "probability": 0.8935546875 }, { "start": 653.41, "end": 653.53, "word": " can", "probability": 0.88916015625 }, { "start": 653.53, "end": 653.75, "word": " take", "probability": 0.8212890625 }, { "start": 653.75, "end": 653.97, "word": " that", "probability": 0.87744140625 }, { "start": 653.97, "end": 654.35, "word": " idea", "probability": 0.78759765625 }, { "start": 654.35, "end": 654.83, "word": ",", "probability": 0.95263671875 }, { "start": 654.83, "end": 655.01, "word": " train", "probability": 0.82275390625 }, { "start": 655.01, "end": 655.17, "word": " your", "probability": 0.80810546875 }, { "start": 655.17, "end": 655.35, "word": " own", "probability": 0.8154296875 }, { "start": 655.35, "end": 655.65, "word": " model", "probability": 0.501953125 } ] }, { "id": 187, "seek": 65778, "start": 655.65, "end": 659.63, "text": " so that it can recognize whether or not there's a cheetah in an image.", "tokens": [ 51114, 370, 300, 309, 393, 5521, 1968, 420, 406, 456, 311, 257, 947, 47947, 294, 364, 3256, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.1600942470961147, "compression_ratio": 1.7062937062937062, "no_speech_prob": 0.029296875, "words": [ { "start": 655.65, "end": 655.87, "word": " so", "probability": 0.6669921875 }, { "start": 655.87, "end": 655.97, "word": " that", "probability": 0.8583984375 }, { "start": 655.97, "end": 656.03, "word": " it", "probability": 0.896484375 }, { "start": 656.03, "end": 656.17, "word": " can", "probability": 0.8984375 }, { "start": 656.17, "end": 656.91, "word": " recognize", "probability": 0.79638671875 }, { "start": 656.91, "end": 657.85, "word": " whether", "probability": 0.80419921875 }, { "start": 657.85, "end": 658.03, "word": " or", "probability": 0.9052734375 }, { "start": 658.03, "end": 658.15, "word": " not", "probability": 0.890625 }, { "start": 658.15, "end": 658.35, "word": " there's", "probability": 0.9140625 }, { "start": 658.49, "end": 658.71, "word": " a cheetah", "probability": 0.936279296875 }, { "start": 658.71, "end": 658.83, "word": " in", "probability": 0.89697265625 }, { "start": 658.83, "end": 658.95, "word": " an", "probability": 0.89990234375 }, { "start": 658.95, "end": 659.23, "word": " image", "probability": 0.83740234375 }, { "start": 659.23, "end": 659.63, "word": ".", "probability": 0.97607421875 } ] }, { "id": 188, "seek": 65778, "start": 660.27, "end": 663.03, "text": " But what we're going to do is actually build a model from scratch.", "tokens": [ 51314, 583, 437, 321, 434, 516, 281, 360, 307, 767, 1322, 257, 2316, 490, 8459, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.1600942470961147, "compression_ratio": 1.7062937062937062, "no_speech_prob": 0.029296875, "words": [ { "start": 660.27, "end": 660.67, "word": " But", "probability": 0.89111328125 }, { "start": 660.67, "end": 660.81, "word": " what", "probability": 0.8759765625 }, { "start": 660.81, "end": 660.99, "word": " we're", "probability": 0.92578125 }, { "start": 660.99, "end": 661.09, "word": " going", "probability": 0.32373046875 }, { "start": 661.09, "end": 661.15, "word": " to", "probability": 0.90625 }, { "start": 661.15, "end": 661.25, "word": " do", "probability": 0.9033203125 }, { "start": 661.25, "end": 661.37, "word": " is", "probability": 0.89794921875 }, { "start": 661.37, "end": 661.59, "word": " actually", "probability": 0.76953125 }, { "start": 661.59, "end": 661.81, "word": " build", "probability": 0.8828125 }, { "start": 661.95, "end": 662.13, "word": " a model", "probability": 0.8232421875 }, { "start": 662.13, "end": 662.41, "word": " from", "probability": 0.8212890625 }, { "start": 662.41, "end": 662.87, "word": " scratch", "probability": 0.796875 }, { "start": 662.87, "end": 663.03, "word": ".", "probability": 0.9599609375 } ] }, { "id": 189, "seek": 65778, "start": 663.03, "end": 666.87, "text": " There's no previously trained information,", "tokens": [ 51464, 821, 311, 572, 8046, 8895, 1589, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.1600942470961147, "compression_ratio": 1.7062937062937062, "no_speech_prob": 0.029296875, "words": [ { "start": 663.03, "end": 663.39, "word": " There's", "probability": 0.899169921875 }, { "start": 663.39, "end": 664.47, "word": " no", "probability": 0.90673828125 }, { "start": 664.47, "end": 665.11, "word": " previously", "probability": 0.73583984375 }, { "start": 665.11, "end": 665.51, "word": " trained", "probability": 0.7802734375 }, { "start": 665.51, "end": 666.09, "word": " information", "probability": 0.7255859375 }, { "start": 666.09, "end": 666.87, "word": ",", "probability": 0.68017578125 } ] }, { "id": 190, "seek": 65778, "start": 666.87, "end": 668.71, "text": " and I'm going to walk you through how to do that,", "tokens": [ 51664, 293, 286, 478, 516, 281, 1792, 291, 807, 577, 281, 360, 300, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.1600942470961147, "compression_ratio": 1.7062937062937062, "no_speech_prob": 0.029296875, "words": [ { "start": 666.87, "end": 667.33, "word": " and", "probability": 0.89453125 }, { "start": 667.33, "end": 667.47, "word": " I'm", "probability": 0.99853515625 }, { "start": 667.47, "end": 667.55, "word": " going", "probability": 0.82421875 }, { "start": 667.55, "end": 667.63, "word": " to", "probability": 0.90283203125 }, { "start": 667.63, "end": 667.83, "word": " walk", "probability": 0.82177734375 }, { "start": 667.83, "end": 667.97, "word": " you", "probability": 0.89501953125 }, { "start": 667.97, "end": 668.11, "word": " through", "probability": 0.78759765625 }, { "start": 668.11, "end": 668.23, "word": " how", "probability": 0.90087890625 }, { "start": 668.23, "end": 668.37, "word": " to", "probability": 0.89990234375 }, { "start": 668.37, "end": 668.49, "word": " do", "probability": 0.90625 }, { "start": 668.49, "end": 668.69, "word": " that", "probability": 0.87744140625 }, { "start": 668.69, "end": 668.71, "word": ",", "probability": 0.5986328125 } ] }, { "id": 191, "seek": 68256, "start": 668.71, "end": 670.63, "text": " and we're going to see a workbook in a little bit.", "tokens": [ 50364, 293, 321, 434, 516, 281, 536, 257, 589, 2939, 294, 257, 707, 857, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.18550531914893617, "compression_ratio": 1.506726457399103, "no_speech_prob": 0.0384521484375, "words": [ { "start": 668.71, "end": 668.79, "word": " and", "probability": 0.50830078125 }, { "start": 668.79, "end": 668.91, "word": " we're", "probability": 0.92041015625 }, { "start": 668.91, "end": 668.97, "word": " going", "probability": 0.212158203125 }, { "start": 668.97, "end": 669.03, "word": " to", "probability": 0.90576171875 }, { "start": 669.03, "end": 669.17, "word": " see", "probability": 0.802734375 }, { "start": 669.27, "end": 669.61, "word": " a workbook", "probability": 0.917236328125 }, { "start": 669.61, "end": 669.75, "word": " in", "probability": 0.900390625 }, { "start": 669.85, "end": 669.97, "word": " a little", "probability": 0.80517578125 }, { "start": 669.97, "end": 670.17, "word": " bit", "probability": 0.89892578125 }, { "start": 670.17, "end": 670.63, "word": ".", "probability": 0.98876953125 } ] }, { "id": 192, "seek": 68256, "start": 671.65, "end": 672.33, "text": " Thank you.", "tokens": [ 50514, 1044, 291, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.18550531914893617, "compression_ratio": 1.506726457399103, "no_speech_prob": 0.0384521484375, "words": [ { "start": 671.65, "end": 671.93, "word": " Thank", "probability": 0.181640625 }, { "start": 671.93, "end": 672.05, "word": " you", "probability": 0.892578125 }, { "start": 672.05, "end": 672.33, "word": ".", "probability": 0.884765625 } ] }, { "id": 193, "seek": 68256, "start": 672.33, "end": 674.05, "text": " Hopefully that helps answer the question.", "tokens": [ 50564, 10429, 300, 3665, 1867, 264, 1168, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.18550531914893617, "compression_ratio": 1.506726457399103, "no_speech_prob": 0.0384521484375, "words": [ { "start": 672.33, "end": 672.57, "word": " Hopefully", "probability": 0.74951171875 }, { "start": 672.57, "end": 672.75, "word": " that", "probability": 0.77001953125 }, { "start": 672.75, "end": 672.93, "word": " helps", "probability": 0.72216796875 }, { "start": 672.93, "end": 673.15, "word": " answer", "probability": 0.88671875 }, { "start": 673.15, "end": 673.29, "word": " the", "probability": 0.8125 }, { "start": 673.29, "end": 673.59, "word": " question", "probability": 0.7880859375 }, { "start": 673.59, "end": 674.05, "word": ".", "probability": 0.98681640625 } ] }, { "id": 194, "seek": 68256, "start": 676.75, "end": 677.67, "text": " Okay.", "tokens": [ 50764, 1033, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.18550531914893617, "compression_ratio": 1.506726457399103, "no_speech_prob": 0.0384521484375, "words": [ { "start": 676.75, "end": 677.21, "word": " Okay", "probability": 0.57373046875 }, { "start": 677.21, "end": 677.67, "word": ".", "probability": 0.67578125 } ] }, { "id": 195, "seek": 68256, "start": 678.17, "end": 681.91, "text": " So before we get started, machine learning, it uses statistics,", "tokens": [ 50814, 407, 949, 321, 483, 1409, 11, 3479, 2539, 11, 309, 4960, 12523, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.18550531914893617, "compression_ratio": 1.506726457399103, "no_speech_prob": 0.0384521484375, "words": [ { "start": 678.17, "end": 678.63, "word": " So", "probability": 0.88037109375 }, { "start": 678.63, "end": 678.81, "word": " before", "probability": 0.7412109375 }, { "start": 678.81, "end": 678.93, "word": " we", "probability": 0.8984375 }, { "start": 678.93, "end": 679.05, "word": " get", "probability": 0.90478515625 }, { "start": 679.05, "end": 679.37, "word": " started", "probability": 0.7958984375 }, { "start": 679.37, "end": 679.67, "word": ",", "probability": 0.76611328125 }, { "start": 679.67, "end": 680.29, "word": " machine", "probability": 0.541015625 }, { "start": 680.29, "end": 680.61, "word": " learning", "probability": 0.8505859375 }, { "start": 680.61, "end": 680.63, "word": ",", "probability": 0.7802734375 }, { "start": 680.63, "end": 680.81, "word": " it", "probability": 0.89306640625 }, { "start": 680.81, "end": 681.03, "word": " uses", "probability": 0.81787109375 }, { "start": 681.03, "end": 681.63, "word": " statistics", "probability": 0.87646484375 }, { "start": 681.63, "end": 681.91, "word": ",", "probability": 0.1357421875 } ] }, { "id": 196, "seek": 68256, "start": 681.91, "end": 686.79, "text": " and so what we need to do is grab information and turn them into numbers.", "tokens": [ 51014, 293, 370, 437, 321, 643, 281, 360, 307, 4444, 1589, 293, 1261, 552, 666, 3547, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.18550531914893617, "compression_ratio": 1.506726457399103, "no_speech_prob": 0.0384521484375, "words": [ { "start": 681.91, "end": 682.03, "word": " and", "probability": 0.88232421875 }, { "start": 682.03, "end": 682.27, "word": " so", "probability": 0.89599609375 }, { "start": 682.27, "end": 682.49, "word": " what", "probability": 0.85205078125 }, { "start": 682.49, "end": 682.61, "word": " we", "probability": 0.904296875 }, { "start": 682.61, "end": 682.75, "word": " need", "probability": 0.81103515625 }, { "start": 682.75, "end": 682.85, "word": " to", "probability": 0.90673828125 }, { "start": 682.85, "end": 683.07, "word": " do", "probability": 0.90673828125 }, { "start": 683.07, "end": 683.49, "word": " is", "probability": 0.89990234375 }, { "start": 683.49, "end": 683.79, "word": " grab", "probability": 0.78564453125 }, { "start": 683.79, "end": 684.25, "word": " information", "probability": 0.74072265625 }, { "start": 684.25, "end": 684.95, "word": " and", "probability": 0.86669921875 }, { "start": 684.95, "end": 685.31, "word": " turn", "probability": 0.826171875 }, { "start": 685.31, "end": 685.51, "word": " them", "probability": 0.73583984375 }, { "start": 685.51, "end": 685.81, "word": " into", "probability": 0.7294921875 }, { "start": 685.81, "end": 686.33, "word": " numbers", "probability": 0.86572265625 }, { "start": 686.33, "end": 686.79, "word": ".", "probability": 0.8984375 } ] }, { "id": 197, "seek": 68256, "start": 687.09, "end": 690.35, "text": " But if we wanted to have the idea of a spam email", "tokens": [ 51264, 583, 498, 321, 1415, 281, 362, 264, 1558, 295, 257, 24028, 3796, 51414 ], "temperature": 0.0, "avg_logprob": -0.18550531914893617, "compression_ratio": 1.506726457399103, "no_speech_prob": 0.0384521484375, "words": [ { "start": 687.09, "end": 687.55, "word": " But", "probability": 0.892578125 }, { "start": 687.55, "end": 687.89, "word": " if", "probability": 0.88232421875 }, { "start": 687.89, "end": 688.07, "word": " we", "probability": 0.9013671875 }, { "start": 688.07, "end": 688.23, "word": " wanted", "probability": 0.76611328125 }, { "start": 688.23, "end": 688.37, "word": " to", "probability": 0.9013671875 }, { "start": 688.37, "end": 688.53, "word": " have", "probability": 0.88623046875 }, { "start": 688.53, "end": 688.65, "word": " the", "probability": 0.81396484375 }, { "start": 688.65, "end": 689.01, "word": " idea", "probability": 0.771484375 }, { "start": 689.01, "end": 689.57, "word": " of", "probability": 0.89990234375 }, { "start": 689.79, "end": 690.01, "word": " a spam", "probability": 0.935546875 }, { "start": 690.01, "end": 690.35, "word": " email", "probability": 0.89453125 } ] }, { "id": 198, "seek": 68256, "start": 690.35, "end": 693.49, "text": " versus a regular email or a ham email,", "tokens": [ 51414, 5717, 257, 3890, 3796, 420, 257, 7852, 3796, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.18550531914893617, "compression_ratio": 1.506726457399103, "no_speech_prob": 0.0384521484375, "words": [ { "start": 690.35, "end": 690.69, "word": " versus", "probability": 0.73828125 }, { "start": 691.13, "end": 691.37, "word": " a regular", "probability": 0.88916015625 }, { "start": 691.37, "end": 691.69, "word": " email", "probability": 0.916015625 }, { "start": 691.69, "end": 691.87, "word": " or", "probability": 0.8291015625 }, { "start": 692.03, "end": 692.33, "word": " a ham", "probability": 0.76806640625 }, { "start": 692.33, "end": 692.89, "word": " email", "probability": 0.8994140625 }, { "start": 692.89, "end": 693.49, "word": ",", "probability": 0.9453125 } ] }, { "id": 199, "seek": 71020, "start": 694.11, "end": 698.41, "text": " we need to kind of understand how we're going to interpret words into numbers.", "tokens": [ 50414, 321, 643, 281, 733, 295, 1223, 577, 321, 434, 516, 281, 7302, 2283, 666, 3547, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.18590856812618398, "compression_ratio": 1.7740585774058577, "no_speech_prob": 0.0078125, "words": [ { "start": 694.11, "end": 694.55, "word": " we", "probability": 0.29443359375 }, { "start": 694.55, "end": 694.69, "word": " need", "probability": 0.81982421875 }, { "start": 694.69, "end": 694.79, "word": " to", "probability": 0.90380859375 }, { "start": 694.79, "end": 694.89, "word": " kind", "probability": 0.50244140625 }, { "start": 694.89, "end": 694.97, "word": " of", "probability": 0.90625 }, { "start": 694.97, "end": 695.39, "word": " understand", "probability": 0.7490234375 }, { "start": 695.39, "end": 695.63, "word": " how", "probability": 0.884765625 }, { "start": 695.63, "end": 695.79, "word": " we're", "probability": 0.91015625 }, { "start": 695.79, "end": 695.95, "word": " going", "probability": 0.84765625 }, { "start": 695.95, "end": 696.11, "word": " to", "probability": 0.90283203125 }, { "start": 696.11, "end": 696.41, "word": " interpret", "probability": 0.7607421875 }, { "start": 696.41, "end": 697.05, "word": " words", "probability": 0.7255859375 }, { "start": 697.05, "end": 697.57, "word": " into", "probability": 0.71875 }, { "start": 697.57, "end": 697.97, "word": " numbers", "probability": 0.86767578125 }, { "start": 697.97, "end": 698.41, "word": ".", "probability": 0.93115234375 } ] }, { "id": 200, "seek": 71020, "start": 699.27, "end": 704.47, "text": " So here's a couple sentences that refer to sports and not sports,", "tokens": [ 50664, 407, 510, 311, 257, 1916, 16579, 300, 2864, 281, 6573, 293, 406, 6573, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.18590856812618398, "compression_ratio": 1.7740585774058577, "no_speech_prob": 0.0078125, "words": [ { "start": 699.27, "end": 699.67, "word": " So", "probability": 0.76611328125 }, { "start": 699.67, "end": 700.11, "word": " here's", "probability": 0.806396484375 }, { "start": 700.19, "end": 700.33, "word": " a couple", "probability": 0.7890625 }, { "start": 700.33, "end": 700.73, "word": " sentences", "probability": 0.720703125 }, { "start": 700.73, "end": 701.81, "word": " that", "probability": 0.8232421875 }, { "start": 701.81, "end": 702.11, "word": " refer", "probability": 0.7998046875 }, { "start": 702.11, "end": 702.45, "word": " to", "probability": 0.90869140625 }, { "start": 702.45, "end": 703.05, "word": " sports", "probability": 0.76025390625 }, { "start": 703.05, "end": 703.59, "word": " and", "probability": 0.8720703125 }, { "start": 703.59, "end": 703.97, "word": " not", "probability": 0.8603515625 }, { "start": 703.97, "end": 704.29, "word": " sports", "probability": 0.763671875 }, { "start": 704.29, "end": 704.47, "word": ",", "probability": 0.375732421875 } ] }, { "id": 201, "seek": 71020, "start": 704.47, "end": 706.69, "text": " or realistically, elections.", "tokens": [ 50914, 420, 40734, 11, 12870, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.18590856812618398, "compression_ratio": 1.7740585774058577, "no_speech_prob": 0.0078125, "words": [ { "start": 704.47, "end": 704.75, "word": " or", "probability": 0.90283203125 }, { "start": 704.75, "end": 705.57, "word": " realistically", "probability": 0.7724609375 }, { "start": 705.57, "end": 705.83, "word": ",", "probability": 0.495849609375 }, { "start": 705.83, "end": 706.31, "word": " elections", "probability": 0.76953125 }, { "start": 706.31, "end": 706.69, "word": ".", "probability": 0.978515625 } ] }, { "id": 202, "seek": 71020, "start": 706.69, "end": 711.69, "text": " So we see a great game, and that talks about sports.", "tokens": [ 51014, 407, 321, 536, 257, 869, 1216, 11, 293, 300, 6686, 466, 6573, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.18590856812618398, "compression_ratio": 1.7740585774058577, "no_speech_prob": 0.0078125, "words": [ { "start": 706.69, "end": 706.95, "word": " So", "probability": 0.85302734375 }, { "start": 706.95, "end": 707.09, "word": " we", "probability": 0.888671875 }, { "start": 707.09, "end": 707.35, "word": " see", "probability": 0.81787109375 }, { "start": 707.59, "end": 707.91, "word": " a great", "probability": 0.8271484375 }, { "start": 707.91, "end": 709.59, "word": " game", "probability": 0.420654296875 }, { "start": 709.59, "end": 710.03, "word": ",", "probability": 0.56005859375 }, { "start": 710.03, "end": 710.25, "word": " and", "probability": 0.69970703125 }, { "start": 710.25, "end": 710.35, "word": " that", "probability": 0.8671875 }, { "start": 710.35, "end": 710.55, "word": " talks", "probability": 0.73876953125 }, { "start": 710.55, "end": 710.73, "word": " about", "probability": 0.818359375 }, { "start": 710.73, "end": 711.25, "word": " sports", "probability": 0.77783203125 }, { "start": 711.25, "end": 711.69, "word": ".", "probability": 0.7412109375 } ] }, { "id": 203, "seek": 71020, "start": 711.95, "end": 715.15, "text": " And then we see the election was over, and that talks about not sports.", "tokens": [ 51264, 400, 550, 321, 536, 264, 6618, 390, 670, 11, 293, 300, 6686, 466, 406, 6573, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.18590856812618398, "compression_ratio": 1.7740585774058577, "no_speech_prob": 0.0078125, "words": [ { "start": 711.95, "end": 712.07, "word": " And", "probability": 0.765625 }, { "start": 712.07, "end": 712.15, "word": " then", "probability": 0.7177734375 }, { "start": 712.15, "end": 712.25, "word": " we", "probability": 0.90087890625 }, { "start": 712.25, "end": 712.51, "word": " see", "probability": 0.81103515625 }, { "start": 712.51, "end": 712.73, "word": " the", "probability": 0.76416015625 }, { "start": 712.73, "end": 712.97, "word": " election", "probability": 0.8818359375 }, { "start": 712.97, "end": 713.19, "word": " was", "probability": 0.88916015625 }, { "start": 713.19, "end": 713.47, "word": " over", "probability": 0.88037109375 }, { "start": 713.47, "end": 713.55, "word": ",", "probability": 0.67724609375 }, { "start": 713.55, "end": 713.65, "word": " and", "probability": 0.892578125 }, { "start": 713.65, "end": 713.77, "word": " that", "probability": 0.8779296875 }, { "start": 713.77, "end": 713.97, "word": " talks", "probability": 0.75244140625 }, { "start": 713.97, "end": 714.15, "word": " about", "probability": 0.833984375 }, { "start": 714.15, "end": 714.37, "word": " not", "probability": 0.8720703125 }, { "start": 714.37, "end": 714.71, "word": " sports", "probability": 0.77197265625 }, { "start": 714.71, "end": 715.15, "word": ".", "probability": 0.99755859375 } ] }, { "id": 204, "seek": 71020, "start": 715.79, "end": 719.47, "text": " So the idea is how do we take a sentence that we haven't seen before,", "tokens": [ 51464, 407, 264, 1558, 307, 577, 360, 321, 747, 257, 8174, 300, 321, 2378, 380, 1612, 949, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.18590856812618398, "compression_ratio": 1.7740585774058577, "no_speech_prob": 0.0078125, "words": [ { "start": 715.79, "end": 716.13, "word": " So", "probability": 0.87744140625 }, { "start": 716.13, "end": 716.29, "word": " the", "probability": 0.8115234375 }, { "start": 716.29, "end": 716.51, "word": " idea", "probability": 0.7822265625 }, { "start": 716.51, "end": 716.73, "word": " is", "probability": 0.90673828125 }, { "start": 716.73, "end": 716.95, "word": " how", "probability": 0.401123046875 }, { "start": 716.95, "end": 717.07, "word": " do", "probability": 0.9072265625 }, { "start": 717.07, "end": 717.27, "word": " we", "probability": 0.9013671875 }, { "start": 717.27, "end": 717.67, "word": " take", "probability": 0.8115234375 }, { "start": 717.87, "end": 718.09, "word": " a sentence", "probability": 0.84228515625 }, { "start": 718.09, "end": 718.27, "word": " that", "probability": 0.8837890625 }, { "start": 718.27, "end": 718.41, "word": " we", "probability": 0.9072265625 }, { "start": 718.41, "end": 718.79, "word": " haven't", "probability": 0.940673828125 }, { "start": 718.79, "end": 719.01, "word": " seen", "probability": 0.88720703125 }, { "start": 719.01, "end": 719.37, "word": " before", "probability": 0.79296875 }, { "start": 719.37, "end": 719.47, "word": ",", "probability": 0.65869140625 } ] }, { "id": 205, "seek": 71020, "start": 719.47, "end": 721.13, "text": " because that's what machine learning is supposed to do.", "tokens": [ 51664, 570, 300, 311, 437, 3479, 2539, 307, 3442, 281, 360, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.18590856812618398, "compression_ratio": 1.7740585774058577, "no_speech_prob": 0.0078125, "words": [ { "start": 719.47, "end": 719.67, "word": " because", "probability": 0.8369140625 }, { "start": 719.67, "end": 719.89, "word": " that's", "probability": 0.939697265625 }, { "start": 719.89, "end": 719.99, "word": " what", "probability": 0.87939453125 }, { "start": 719.99, "end": 720.23, "word": " machine", "probability": 0.70068359375 }, { "start": 720.23, "end": 720.45, "word": " learning", "probability": 0.84814453125 }, { "start": 720.45, "end": 720.59, "word": " is", "probability": 0.900390625 }, { "start": 720.59, "end": 720.71, "word": " supposed", "probability": 0.91845703125 }, { "start": 720.71, "end": 720.85, "word": " to", "probability": 0.90673828125 }, { "start": 720.85, "end": 721.03, "word": " do", "probability": 0.90673828125 }, { "start": 721.03, "end": 721.13, "word": ".", "probability": 0.7587890625 } ] }, { "id": 206, "seek": 73730, "start": 721.13, "end": 723.47, "text": " We were trained on certain information,", "tokens": [ 50364, 492, 645, 8895, 322, 1629, 1589, 11, 50464 ], "temperature": 0.0, "avg_logprob": -0.16073495660115172, "compression_ratio": 1.6938775510204083, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 721.13, "end": 721.25, "word": " We", "probability": 0.55615234375 }, { "start": 721.25, "end": 721.67, "word": " were", "probability": 0.65966796875 }, { "start": 721.67, "end": 722.07, "word": " trained", "probability": 0.8115234375 }, { "start": 722.07, "end": 722.27, "word": " on", "probability": 0.91162109375 }, { "start": 722.27, "end": 722.51, "word": " certain", "probability": 0.79931640625 }, { "start": 722.51, "end": 723.07, "word": " information", "probability": 0.73291015625 }, { "start": 723.07, "end": 723.47, "word": ",", "probability": 0.73095703125 } ] }, { "id": 207, "seek": 73730, "start": 723.47, "end": 726.69, "text": " but we want to predict on information that we haven't seen before.", "tokens": [ 50464, 457, 321, 528, 281, 6069, 322, 1589, 300, 321, 2378, 380, 1612, 949, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.16073495660115172, "compression_ratio": 1.6938775510204083, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 723.47, "end": 723.83, "word": " but", "probability": 0.8984375 }, { "start": 723.83, "end": 723.95, "word": " we", "probability": 0.9091796875 }, { "start": 723.95, "end": 724.09, "word": " want", "probability": 0.47021484375 }, { "start": 724.09, "end": 724.19, "word": " to", "probability": 0.90673828125 }, { "start": 724.19, "end": 724.53, "word": " predict", "probability": 0.80517578125 }, { "start": 724.53, "end": 724.71, "word": " on", "probability": 0.8876953125 }, { "start": 724.71, "end": 725.09, "word": " information", "probability": 0.7373046875 }, { "start": 725.09, "end": 725.27, "word": " that", "probability": 0.86474609375 }, { "start": 725.27, "end": 725.37, "word": " we", "probability": 0.9091796875 }, { "start": 725.37, "end": 725.61, "word": " haven't", "probability": 0.93994140625 }, { "start": 725.61, "end": 725.81, "word": " seen", "probability": 0.8896484375 }, { "start": 725.81, "end": 726.17, "word": " before", "probability": 0.79345703125 }, { "start": 726.17, "end": 726.69, "word": ".", "probability": 0.95654296875 } ] }, { "id": 208, "seek": 73730, "start": 727.01, "end": 730.17, "text": " How do we take a new sentence and then try and make a decision", "tokens": [ 50664, 1012, 360, 321, 747, 257, 777, 8174, 293, 550, 853, 293, 652, 257, 3537, 50814 ], "temperature": 0.0, "avg_logprob": -0.16073495660115172, "compression_ratio": 1.6938775510204083, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 727.01, "end": 727.53, "word": " How", "probability": 0.8798828125 }, { "start": 727.53, "end": 727.61, "word": " do", "probability": 0.91259765625 }, { "start": 727.61, "end": 727.69, "word": " we", "probability": 0.900390625 }, { "start": 727.69, "end": 727.87, "word": " take", "probability": 0.8125 }, { "start": 728.03, "end": 728.27, "word": " a new", "probability": 0.81689453125 }, { "start": 728.27, "end": 728.71, "word": " sentence", "probability": 0.826171875 }, { "start": 728.71, "end": 728.97, "word": " and", "probability": 0.73828125 }, { "start": 728.97, "end": 729.13, "word": " then", "probability": 0.6953125 }, { "start": 729.13, "end": 729.35, "word": " try", "probability": 0.8173828125 }, { "start": 729.35, "end": 729.55, "word": " and", "probability": 0.880859375 }, { "start": 729.55, "end": 729.79, "word": " make", "probability": 0.88037109375 }, { "start": 729.91, "end": 730.17, "word": " a decision", "probability": 0.8466796875 } ] }, { "id": 209, "seek": 73730, "start": 730.17, "end": 733.23, "text": " whether or not it's talking about sports or not sports?", "tokens": [ 50814, 1968, 420, 406, 309, 311, 1417, 466, 6573, 420, 406, 6573, 30, 51064 ], "temperature": 0.0, "avg_logprob": -0.16073495660115172, "compression_ratio": 1.6938775510204083, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 730.17, "end": 730.43, "word": " whether", "probability": 0.80908203125 }, { "start": 730.43, "end": 730.57, "word": " or", "probability": 0.89501953125 }, { "start": 730.57, "end": 730.65, "word": " not", "probability": 0.89794921875 }, { "start": 730.65, "end": 730.81, "word": " it's", "probability": 0.948974609375 }, { "start": 730.81, "end": 730.99, "word": " talking", "probability": 0.765625 }, { "start": 730.99, "end": 731.19, "word": " about", "probability": 0.8095703125 }, { "start": 731.19, "end": 731.65, "word": " sports", "probability": 0.78369140625 }, { "start": 731.65, "end": 732.13, "word": " or", "probability": 0.82470703125 }, { "start": 732.13, "end": 732.33, "word": " not", "probability": 0.8876953125 }, { "start": 732.33, "end": 732.71, "word": " sports", "probability": 0.78466796875 }, { "start": 732.71, "end": 733.23, "word": "?", "probability": 0.80517578125 } ] }, { "id": 210, "seek": 73730, "start": 734.95, "end": 738.35, "text": " So to do that, we're going to use what's called Bayes' theorem.", "tokens": [ 51064, 407, 281, 360, 300, 11, 321, 434, 516, 281, 764, 437, 311, 1219, 7840, 279, 6, 20904, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.16073495660115172, "compression_ratio": 1.6938775510204083, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 734.95, "end": 735.47, "word": " So", "probability": 0.759765625 }, { "start": 735.47, "end": 735.59, "word": " to", "probability": 0.82373046875 }, { "start": 735.59, "end": 735.71, "word": " do", "probability": 0.90625 }, { "start": 735.71, "end": 735.95, "word": " that", "probability": 0.8857421875 }, { "start": 735.95, "end": 735.99, "word": ",", "probability": 0.8818359375 }, { "start": 735.99, "end": 736.15, "word": " we're", "probability": 0.92626953125 }, { "start": 736.15, "end": 736.23, "word": " going", "probability": 0.4873046875 }, { "start": 736.23, "end": 736.33, "word": " to", "probability": 0.90380859375 }, { "start": 736.33, "end": 736.69, "word": " use", "probability": 0.8173828125 }, { "start": 736.69, "end": 737.01, "word": " what's", "probability": 0.939453125 }, { "start": 737.01, "end": 737.21, "word": " called", "probability": 0.81103515625 }, { "start": 737.21, "end": 737.55, "word": " Bayes", "probability": 0.89599609375 }, { "start": 737.55, "end": 737.61, "word": "'", "probability": 0.58056640625 }, { "start": 737.61, "end": 737.83, "word": " theorem", "probability": 0.465576171875 }, { "start": 737.83, "end": 738.35, "word": ".", "probability": 0.97412109375 } ] }, { "id": 211, "seek": 73730, "start": 738.39, "end": 743.25, "text": " Bayes' theorem is a very common probability theorem that basically says,", "tokens": [ 51214, 7840, 279, 6, 20904, 307, 257, 588, 2689, 8482, 20904, 300, 1936, 1619, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.16073495660115172, "compression_ratio": 1.6938775510204083, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 738.39, "end": 738.89, "word": " Bayes", "probability": 0.894287109375 }, { "start": 738.89, "end": 738.99, "word": "'", "probability": 0.95166015625 }, { "start": 738.99, "end": 739.15, "word": " theorem", "probability": 0.74755859375 }, { "start": 739.15, "end": 739.67, "word": " is", "probability": 0.89990234375 }, { "start": 740.11, "end": 740.45, "word": " a very", "probability": 0.74853515625 }, { "start": 740.45, "end": 740.89, "word": " common", "probability": 0.74658203125 }, { "start": 740.89, "end": 741.37, "word": " probability", "probability": 0.89892578125 }, { "start": 741.37, "end": 741.87, "word": " theorem", "probability": 0.72998046875 }, { "start": 741.87, "end": 742.31, "word": " that", "probability": 0.83203125 }, { "start": 742.31, "end": 742.61, "word": " basically", "probability": 0.90380859375 }, { "start": 742.61, "end": 743.09, "word": " says", "probability": 0.8154296875 }, { "start": 743.09, "end": 743.25, "word": ",", "probability": 0.890625 } ] }, { "id": 212, "seek": 73730, "start": 743.25, "end": 748.23, "text": " okay, so if we have a sentence that we already know,", "tokens": [ 51464, 1392, 11, 370, 498, 321, 362, 257, 8174, 300, 321, 1217, 458, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.16073495660115172, "compression_ratio": 1.6938775510204083, "no_speech_prob": 0.00021648406982421875, "words": [ { "start": 743.25, "end": 743.51, "word": " okay", "probability": 0.37744140625 }, { "start": 743.51, "end": 744.01, "word": ",", "probability": 0.9248046875 }, { "start": 744.01, "end": 744.35, "word": " so", "probability": 0.87353515625 }, { "start": 744.35, "end": 744.71, "word": " if", "probability": 0.88427734375 }, { "start": 744.71, "end": 744.97, "word": " we", "probability": 0.90673828125 }, { "start": 744.97, "end": 745.55, "word": " have", "probability": 0.884765625 }, { "start": 746.35, "end": 746.57, "word": " a sentence", "probability": 0.8447265625 }, { "start": 746.57, "end": 746.89, "word": " that", "probability": 0.8818359375 }, { "start": 746.89, "end": 746.99, "word": " we", "probability": 0.9013671875 }, { "start": 746.99, "end": 747.31, "word": " already", "probability": 0.83349609375 }, { "start": 747.31, "end": 747.65, "word": " know", "probability": 0.81787109375 }, { "start": 747.65, "end": 748.23, "word": ",", "probability": 0.57177734375 } ] }, { "id": 213, "seek": 76332, "start": 748.23, "end": 754.89, "text": " and given the probability that this sentence is talking about sports,", "tokens": [ 50364, 293, 2212, 264, 8482, 300, 341, 8174, 307, 1417, 466, 6573, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.19106657851649367, "compression_ratio": 1.9076923076923078, "no_speech_prob": 0.0016489028930664062, "words": [ { "start": 748.23, "end": 748.45, "word": " and", "probability": 0.360107421875 }, { "start": 748.45, "end": 749.77, "word": " given", "probability": 0.6826171875 }, { "start": 749.77, "end": 750.35, "word": " the", "probability": 0.2958984375 }, { "start": 750.35, "end": 751.75, "word": " probability", "probability": 0.9130859375 }, { "start": 751.75, "end": 752.01, "word": " that", "probability": 0.86083984375 }, { "start": 752.01, "end": 752.19, "word": " this", "probability": 0.853515625 }, { "start": 752.19, "end": 752.43, "word": " sentence", "probability": 0.84423828125 }, { "start": 752.43, "end": 752.57, "word": " is", "probability": 0.896484375 }, { "start": 752.57, "end": 752.79, "word": " talking", "probability": 0.7705078125 }, { "start": 752.79, "end": 753.05, "word": " about", "probability": 0.80712890625 }, { "start": 753.05, "end": 753.55, "word": " sports", "probability": 0.7763671875 }, { "start": 753.55, "end": 754.89, "word": ",", "probability": 0.386962890625 } ] }, { "id": 214, "seek": 76332, "start": 754.89, "end": 758.39, "text": " versus here's a new sentence,", "tokens": [ 50714, 5717, 510, 311, 257, 777, 8174, 11, 50864 ], "temperature": 0.0, "avg_logprob": -0.19106657851649367, "compression_ratio": 1.9076923076923078, "no_speech_prob": 0.0016489028930664062, "words": [ { "start": 754.89, "end": 755.77, "word": " versus", "probability": 0.7119140625 }, { "start": 755.77, "end": 757.11, "word": " here's", "probability": 0.741943359375 }, { "start": 757.21, "end": 757.37, "word": " a new", "probability": 0.8095703125 }, { "start": 757.37, "end": 757.77, "word": " sentence", "probability": 0.83544921875 }, { "start": 757.77, "end": 758.39, "word": ",", "probability": 0.6591796875 } ] }, { "id": 215, "seek": 76332, "start": 758.39, "end": 762.13, "text": " what is the probability that it's talking about sports given that new sentence?", "tokens": [ 50864, 437, 307, 264, 8482, 300, 309, 311, 1417, 466, 6573, 2212, 300, 777, 8174, 30, 51064 ], "temperature": 0.0, "avg_logprob": -0.19106657851649367, "compression_ratio": 1.9076923076923078, "no_speech_prob": 0.0016489028930664062, "words": [ { "start": 758.39, "end": 758.59, "word": " what", "probability": 0.861328125 }, { "start": 758.59, "end": 758.73, "word": " is", "probability": 0.89013671875 }, { "start": 758.73, "end": 758.87, "word": " the", "probability": 0.814453125 }, { "start": 758.87, "end": 759.27, "word": " probability", "probability": 0.8876953125 }, { "start": 759.27, "end": 759.51, "word": " that", "probability": 0.87548828125 }, { "start": 759.51, "end": 759.63, "word": " it's", "probability": 0.93603515625 }, { "start": 759.63, "end": 759.85, "word": " talking", "probability": 0.76171875 }, { "start": 759.85, "end": 760.05, "word": " about", "probability": 0.806640625 }, { "start": 760.05, "end": 760.43, "word": " sports", "probability": 0.78271484375 }, { "start": 760.43, "end": 760.81, "word": " given", "probability": 0.5224609375 }, { "start": 760.81, "end": 761.03, "word": " that", "probability": 0.8779296875 }, { "start": 761.03, "end": 761.27, "word": " new", "probability": 0.78271484375 }, { "start": 761.27, "end": 761.63, "word": " sentence", "probability": 0.865234375 }, { "start": 761.63, "end": 762.13, "word": "?", "probability": 0.80859375 } ] }, { "id": 216, "seek": 76332, "start": 762.59, "end": 767.99, "text": " So the probability of A given B equals probability of B given A, blah, blah, blah.", "tokens": [ 51064, 407, 264, 8482, 295, 316, 2212, 363, 6915, 8482, 295, 363, 2212, 316, 11, 12288, 11, 12288, 11, 12288, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.19106657851649367, "compression_ratio": 1.9076923076923078, "no_speech_prob": 0.0016489028930664062, "words": [ { "start": 762.59, "end": 762.81, "word": " So", "probability": 0.7568359375 }, { "start": 762.81, "end": 762.97, "word": " the", "probability": 0.71630859375 }, { "start": 762.97, "end": 763.29, "word": " probability", "probability": 0.87451171875 }, { "start": 763.29, "end": 763.53, "word": " of", "probability": 0.8994140625 }, { "start": 763.53, "end": 763.89, "word": " A", "probability": 0.927734375 }, { "start": 763.89, "end": 764.43, "word": " given", "probability": 0.6953125 }, { "start": 764.43, "end": 764.83, "word": " B", "probability": 0.99609375 }, { "start": 764.83, "end": 765.29, "word": " equals", "probability": 0.75390625 }, { "start": 765.29, "end": 765.65, "word": " probability", "probability": 0.60205078125 }, { "start": 765.65, "end": 765.87, "word": " of", "probability": 0.88916015625 }, { "start": 765.87, "end": 766.05, "word": " B", "probability": 0.99560546875 }, { "start": 766.05, "end": 766.31, "word": " given", "probability": 0.8095703125 }, { "start": 766.31, "end": 766.73, "word": " A", "probability": 0.9912109375 }, { "start": 766.73, "end": 767.15, "word": ",", "probability": 0.6123046875 }, { "start": 767.15, "end": 767.29, "word": " blah", "probability": 0.8798828125 }, { "start": 767.29, "end": 767.35, "word": ",", "probability": 0.55859375 }, { "start": 767.35, "end": 767.41, "word": " blah", "probability": 0.80029296875 }, { "start": 767.41, "end": 767.49, "word": ",", "probability": 0.9765625 }, { "start": 767.49, "end": 767.57, "word": " blah", "probability": 0.81787109375 }, { "start": 767.57, "end": 767.99, "word": ".", "probability": 0.9501953125 } ] }, { "id": 217, "seek": 76332, "start": 767.99, "end": 770.65, "text": " We don't need to know too much about this,", "tokens": [ 51364, 492, 500, 380, 643, 281, 458, 886, 709, 466, 341, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.19106657851649367, "compression_ratio": 1.9076923076923078, "no_speech_prob": 0.0016489028930664062, "words": [ { "start": 767.99, "end": 768.21, "word": " We", "probability": 0.8984375 }, { "start": 768.21, "end": 768.33, "word": " don't", "probability": 0.94677734375 }, { "start": 768.33, "end": 768.49, "word": " need", "probability": 0.80322265625 }, { "start": 768.49, "end": 768.59, "word": " to", "probability": 0.90771484375 }, { "start": 768.59, "end": 768.85, "word": " know", "probability": 0.79541015625 }, { "start": 768.85, "end": 769.53, "word": " too", "probability": 0.80224609375 }, { "start": 769.53, "end": 769.73, "word": " much", "probability": 0.81689453125 }, { "start": 769.73, "end": 769.95, "word": " about", "probability": 0.8271484375 }, { "start": 769.95, "end": 770.37, "word": " this", "probability": 0.87890625 }, { "start": 770.37, "end": 770.65, "word": ",", "probability": 0.8203125 } ] }, { "id": 218, "seek": 76332, "start": 770.65, "end": 774.25, "text": " but it's important to get a good foundation of this understanding.", "tokens": [ 51464, 457, 309, 311, 1021, 281, 483, 257, 665, 7030, 295, 341, 3701, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.19106657851649367, "compression_ratio": 1.9076923076923078, "no_speech_prob": 0.0016489028930664062, "words": [ { "start": 770.65, "end": 770.93, "word": " but", "probability": 0.90283203125 }, { "start": 770.93, "end": 771.17, "word": " it's", "probability": 0.95068359375 }, { "start": 771.17, "end": 771.49, "word": " important", "probability": 0.7783203125 }, { "start": 771.49, "end": 771.63, "word": " to", "probability": 0.9091796875 }, { "start": 771.63, "end": 771.79, "word": " get", "probability": 0.89697265625 }, { "start": 772.11, "end": 772.31, "word": " a good", "probability": 0.892578125 }, { "start": 772.31, "end": 772.79, "word": " foundation", "probability": 0.8701171875 }, { "start": 772.79, "end": 773.05, "word": " of", "probability": 0.8955078125 }, { "start": 773.05, "end": 773.25, "word": " this", "probability": 0.88037109375 }, { "start": 773.25, "end": 773.75, "word": " understanding", "probability": 0.69384765625 }, { "start": 773.75, "end": 774.25, "word": ".", "probability": 0.9892578125 } ] }, { "id": 219, "seek": 79058, "start": 774.25, "end": 777.07, "text": " So the idea is, what is the probability that the sentence,", "tokens": [ 50364, 407, 264, 1558, 307, 11, 437, 307, 264, 8482, 300, 264, 8174, 11, 50464 ], "temperature": 0.0, "avg_logprob": -0.2096238916954108, "compression_ratio": 1.7584745762711864, "no_speech_prob": 0.0233306884765625, "words": [ { "start": 774.25, "end": 774.61, "word": " So", "probability": 0.60107421875 }, { "start": 774.61, "end": 774.75, "word": " the", "probability": 0.7138671875 }, { "start": 774.75, "end": 775.01, "word": " idea", "probability": 0.771484375 }, { "start": 775.01, "end": 775.33, "word": " is", "probability": 0.904296875 }, { "start": 775.33, "end": 775.41, "word": ",", "probability": 0.46630859375 }, { "start": 775.41, "end": 775.47, "word": " what", "probability": 0.837890625 }, { "start": 775.47, "end": 775.55, "word": " is", "probability": 0.890625 }, { "start": 775.55, "end": 775.65, "word": " the", "probability": 0.771484375 }, { "start": 775.65, "end": 775.95, "word": " probability", "probability": 0.8798828125 }, { "start": 775.95, "end": 776.39, "word": " that", "probability": 0.86328125 }, { "start": 776.39, "end": 776.53, "word": " the", "probability": 0.77685546875 }, { "start": 776.53, "end": 776.91, "word": " sentence", "probability": 0.84814453125 }, { "start": 776.91, "end": 777.07, "word": ",", "probability": 0.32470703125 } ] }, { "id": 220, "seek": 79058, "start": 777.13, "end": 780.23, "text": " a very close game, is talking about sports?", "tokens": [ 50464, 257, 588, 1998, 1216, 11, 307, 1417, 466, 6573, 30, 50664 ], "temperature": 0.0, "avg_logprob": -0.2096238916954108, "compression_ratio": 1.7584745762711864, "no_speech_prob": 0.0233306884765625, "words": [ { "start": 777.13, "end": 777.35, "word": " a very", "probability": 0.71044921875 }, { "start": 777.35, "end": 777.67, "word": " close", "probability": 0.84326171875 }, { "start": 777.67, "end": 778.05, "word": " game", "probability": 0.81298828125 }, { "start": 778.05, "end": 778.29, "word": ",", "probability": 0.748046875 }, { "start": 778.29, "end": 778.53, "word": " is", "probability": 0.8916015625 }, { "start": 778.53, "end": 778.77, "word": " talking", "probability": 0.7744140625 }, { "start": 778.77, "end": 779.11, "word": " about", "probability": 0.8125 }, { "start": 779.11, "end": 779.75, "word": " sports", "probability": 0.78369140625 }, { "start": 779.75, "end": 780.23, "word": "?", "probability": 0.828125 } ] }, { "id": 221, "seek": 79058, "start": 781.05, "end": 782.43, "text": " We don't know the answer to that.", "tokens": [ 50664, 492, 500, 380, 458, 264, 1867, 281, 300, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.2096238916954108, "compression_ratio": 1.7584745762711864, "no_speech_prob": 0.0233306884765625, "words": [ { "start": 781.05, "end": 781.53, "word": " We", "probability": 0.88330078125 }, { "start": 781.53, "end": 781.65, "word": " don't", "probability": 0.940673828125 }, { "start": 781.65, "end": 781.77, "word": " know", "probability": 0.82421875 }, { "start": 781.77, "end": 781.89, "word": " the", "probability": 0.814453125 }, { "start": 781.89, "end": 782.09, "word": " answer", "probability": 0.888671875 }, { "start": 782.09, "end": 782.19, "word": " to", "probability": 0.88232421875 }, { "start": 782.19, "end": 782.31, "word": " that", "probability": 0.8837890625 }, { "start": 782.31, "end": 782.43, "word": ".", "probability": 0.77490234375 } ] }, { "id": 222, "seek": 79058, "start": 782.43, "end": 785.85, "text": " We've never come across the sentence of a very close game,", "tokens": [ 50764, 492, 600, 1128, 808, 2108, 264, 8174, 295, 257, 588, 1998, 1216, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.2096238916954108, "compression_ratio": 1.7584745762711864, "no_speech_prob": 0.0233306884765625, "words": [ { "start": 782.43, "end": 782.81, "word": " We've", "probability": 0.785888671875 }, { "start": 782.81, "end": 782.97, "word": " never", "probability": 0.8642578125 }, { "start": 782.97, "end": 783.21, "word": " come", "probability": 0.77734375 }, { "start": 783.21, "end": 783.59, "word": " across", "probability": 0.71240234375 }, { "start": 783.59, "end": 783.95, "word": " the", "probability": 0.78759765625 }, { "start": 783.95, "end": 784.25, "word": " sentence", "probability": 0.81884765625 }, { "start": 784.25, "end": 784.45, "word": " of", "probability": 0.8876953125 }, { "start": 784.61, "end": 784.81, "word": " a very", "probability": 0.71875 }, { "start": 784.81, "end": 785.09, "word": " close", "probability": 0.853515625 }, { "start": 785.09, "end": 785.41, "word": " game", "probability": 0.80078125 }, { "start": 785.41, "end": 785.85, "word": ",", "probability": 0.44384765625 } ] }, { "id": 223, "seek": 79058, "start": 785.85, "end": 790.09, "text": " but we would need to fill it into this algorithm here.", "tokens": [ 50914, 457, 321, 576, 643, 281, 2836, 309, 666, 341, 9284, 510, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.2096238916954108, "compression_ratio": 1.7584745762711864, "no_speech_prob": 0.0233306884765625, "words": [ { "start": 785.85, "end": 786.71, "word": " but", "probability": 0.8896484375 }, { "start": 786.71, "end": 786.83, "word": " we", "probability": 0.9052734375 }, { "start": 786.83, "end": 786.93, "word": " would", "probability": 0.83251953125 }, { "start": 786.93, "end": 787.07, "word": " need", "probability": 0.81689453125 }, { "start": 787.07, "end": 787.19, "word": " to", "probability": 0.90283203125 }, { "start": 787.19, "end": 787.33, "word": " fill", "probability": 0.80126953125 }, { "start": 787.33, "end": 787.45, "word": " it", "probability": 0.908203125 }, { "start": 787.45, "end": 787.71, "word": " into", "probability": 0.60400390625 }, { "start": 787.71, "end": 788.29, "word": " this", "probability": 0.88134765625 }, { "start": 788.29, "end": 789.19, "word": " algorithm", "probability": 0.73193359375 }, { "start": 789.19, "end": 789.61, "word": " here", "probability": 0.76123046875 }, { "start": 789.61, "end": 790.09, "word": ".", "probability": 0.99267578125 } ] }, { "id": 224, "seek": 79058, "start": 790.93, "end": 794.57, "text": " So instead, what we can do is actually break up a very close game", "tokens": [ 51164, 407, 2602, 11, 437, 321, 393, 360, 307, 767, 1821, 493, 257, 588, 1998, 1216, 51364 ], "temperature": 0.0, "avg_logprob": -0.2096238916954108, "compression_ratio": 1.7584745762711864, "no_speech_prob": 0.0233306884765625, "words": [ { "start": 790.93, "end": 791.15, "word": " So", "probability": 0.83203125 }, { "start": 791.15, "end": 791.51, "word": " instead", "probability": 0.806640625 }, { "start": 791.51, "end": 791.87, "word": ",", "probability": 0.822265625 }, { "start": 791.87, "end": 792.05, "word": " what", "probability": 0.88037109375 }, { "start": 792.05, "end": 792.15, "word": " we", "probability": 0.90380859375 }, { "start": 792.15, "end": 792.27, "word": " can", "probability": 0.8857421875 }, { "start": 792.27, "end": 792.39, "word": " do", "probability": 0.89990234375 }, { "start": 792.39, "end": 792.51, "word": " is", "probability": 0.88134765625 }, { "start": 792.51, "end": 792.79, "word": " actually", "probability": 0.78564453125 }, { "start": 792.79, "end": 793.23, "word": " break", "probability": 0.9072265625 }, { "start": 793.23, "end": 793.51, "word": " up", "probability": 0.9150390625 }, { "start": 793.73, "end": 793.93, "word": " a very", "probability": 0.720703125 }, { "start": 793.93, "end": 794.23, "word": " close", "probability": 0.85302734375 }, { "start": 794.23, "end": 794.57, "word": " game", "probability": 0.8046875 } ] }, { "id": 225, "seek": 79058, "start": 794.57, "end": 799.05, "text": " into their individual words, a, very, close, and game.", "tokens": [ 51364, 666, 641, 2609, 2283, 11, 257, 11, 588, 11, 1998, 11, 293, 1216, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.2096238916954108, "compression_ratio": 1.7584745762711864, "no_speech_prob": 0.0233306884765625, "words": [ { "start": 794.57, "end": 794.83, "word": " into", "probability": 0.732421875 }, { "start": 794.83, "end": 795.01, "word": " their", "probability": 0.9013671875 }, { "start": 795.01, "end": 795.51, "word": " individual", "probability": 0.74267578125 }, { "start": 795.51, "end": 796.19, "word": " words", "probability": 0.728515625 }, { "start": 796.19, "end": 796.45, "word": ",", "probability": 0.57373046875 }, { "start": 796.71, "end": 796.93, "word": " a,", "probability": 0.47119140625 }, { "start": 796.93, "end": 797.19, "word": " very", "probability": 0.7197265625 }, { "start": 797.19, "end": 797.57, "word": ",", "probability": 0.95751953125 }, { "start": 797.57, "end": 797.85, "word": " close", "probability": 0.80712890625 }, { "start": 797.85, "end": 798.17, "word": ",", "probability": 0.84912109375 }, { "start": 798.17, "end": 798.23, "word": " and", "probability": 0.84130859375 }, { "start": 798.23, "end": 798.57, "word": " game", "probability": 0.79052734375 }, { "start": 798.57, "end": 799.05, "word": ".", "probability": 0.79541015625 } ] }, { "id": 226, "seek": 79058, "start": 799.11, "end": 801.51, "text": " And then we can turn that probability into,", "tokens": [ 51564, 400, 550, 321, 393, 1261, 300, 8482, 666, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.2096238916954108, "compression_ratio": 1.7584745762711864, "no_speech_prob": 0.0233306884765625, "words": [ { "start": 799.11, "end": 799.31, "word": " And", "probability": 0.85205078125 }, { "start": 799.31, "end": 799.41, "word": " then", "probability": 0.7138671875 }, { "start": 799.41, "end": 799.53, "word": " we", "probability": 0.89453125 }, { "start": 799.53, "end": 799.69, "word": " can", "probability": 0.89013671875 }, { "start": 799.69, "end": 800.13, "word": " turn", "probability": 0.81787109375 }, { "start": 800.13, "end": 800.31, "word": " that", "probability": 0.8818359375 }, { "start": 800.31, "end": 800.73, "word": " probability", "probability": 0.88525390625 }, { "start": 800.73, "end": 801.29, "word": " into", "probability": 0.72802734375 }, { "start": 801.29, "end": 801.51, "word": ",", "probability": 0.41796875 } ] }, { "id": 227, "seek": 82004, "start": 801.51, "end": 806.51, "text": " what's the probability that A is talking about sports?", "tokens": [ 50364, 437, 311, 264, 8482, 300, 316, 307, 1417, 466, 6573, 30, 50614 ], "temperature": 0.0, "avg_logprob": -0.20416666927436988, "compression_ratio": 2.2758620689655173, "no_speech_prob": 0.037322998046875, "words": [ { "start": 801.51, "end": 801.65, "word": " what's", "probability": 0.58001708984375 }, { "start": 801.65, "end": 801.77, "word": " the", "probability": 0.8154296875 }, { "start": 801.77, "end": 802.11, "word": " probability", "probability": 0.8671875 }, { "start": 802.11, "end": 802.87, "word": " that", "probability": 0.8525390625 }, { "start": 802.87, "end": 805.07, "word": " A", "probability": 0.405029296875 }, { "start": 805.07, "end": 805.53, "word": " is", "probability": 0.87158203125 }, { "start": 805.53, "end": 805.83, "word": " talking", "probability": 0.77685546875 }, { "start": 805.83, "end": 806.09, "word": " about", "probability": 0.81689453125 }, { "start": 806.09, "end": 806.41, "word": " sports", "probability": 0.7314453125 }, { "start": 806.41, "end": 806.51, "word": "?", "probability": 0.46435546875 } ] }, { "id": 228, "seek": 82004, "start": 806.51, "end": 808.99, "text": " What's the probability that very is talking about sports?", "tokens": [ 50614, 708, 311, 264, 8482, 300, 588, 307, 1417, 466, 6573, 30, 50714 ], "temperature": 0.0, "avg_logprob": -0.20416666927436988, "compression_ratio": 2.2758620689655173, "no_speech_prob": 0.037322998046875, "words": [ { "start": 806.51, "end": 806.65, "word": " What's", "probability": 0.801513671875 }, { "start": 806.65, "end": 806.75, "word": " the", "probability": 0.8046875 }, { "start": 806.75, "end": 807.01, "word": " probability", "probability": 0.86328125 }, { "start": 807.01, "end": 807.35, "word": " that", "probability": 0.87158203125 }, { "start": 807.35, "end": 807.73, "word": " very", "probability": 0.282958984375 }, { "start": 807.73, "end": 808.05, "word": " is", "probability": 0.8779296875 }, { "start": 808.05, "end": 808.31, "word": " talking", "probability": 0.775390625 }, { "start": 808.31, "end": 808.55, "word": " about", "probability": 0.81396484375 }, { "start": 808.55, "end": 808.89, "word": " sports", "probability": 0.7841796875 }, { "start": 808.89, "end": 808.99, "word": "?", "probability": 0.9208984375 } ] }, { "id": 229, "seek": 82004, "start": 808.99, "end": 811.31, "text": " What's the probability of close talking about sports,", "tokens": [ 50714, 708, 311, 264, 8482, 295, 1998, 1417, 466, 6573, 11, 50864 ], "temperature": 0.0, "avg_logprob": -0.20416666927436988, "compression_ratio": 2.2758620689655173, "no_speech_prob": 0.037322998046875, "words": [ { "start": 808.99, "end": 809.11, "word": " What's", "probability": 0.875732421875 }, { "start": 809.11, "end": 809.19, "word": " the", "probability": 0.796875 }, { "start": 809.19, "end": 809.51, "word": " probability", "probability": 0.86669921875 }, { "start": 809.51, "end": 809.73, "word": " of", "probability": 0.77587890625 }, { "start": 809.73, "end": 810.09, "word": " close", "probability": 0.74609375 }, { "start": 810.09, "end": 810.45, "word": " talking", "probability": 0.68798828125 }, { "start": 810.45, "end": 810.71, "word": " about", "probability": 0.81298828125 }, { "start": 810.71, "end": 811.15, "word": " sports", "probability": 0.79150390625 }, { "start": 811.15, "end": 811.31, "word": ",", "probability": 0.1807861328125 } ] }, { "id": 230, "seek": 82004, "start": 811.31, "end": 813.81, "text": " and game talking about sports?", "tokens": [ 50864, 293, 1216, 1417, 466, 6573, 30, 51064 ], "temperature": 0.0, "avg_logprob": -0.20416666927436988, "compression_ratio": 2.2758620689655173, "no_speech_prob": 0.037322998046875, "words": [ { "start": 811.31, "end": 811.75, "word": " and", "probability": 0.89404296875 }, { "start": 811.75, "end": 812.11, "word": " game", "probability": 0.82421875 }, { "start": 812.11, "end": 812.73, "word": " talking", "probability": 0.728515625 }, { "start": 812.73, "end": 812.95, "word": " about", "probability": 0.8173828125 }, { "start": 812.95, "end": 813.33, "word": " sports", "probability": 0.79150390625 }, { "start": 813.33, "end": 813.81, "word": "?", "probability": 0.9365234375 } ] }, { "id": 231, "seek": 82004, "start": 815.97, "end": 819.03, "text": " So this winds up becoming a bit of a counting game.", "tokens": [ 51064, 407, 341, 17765, 493, 5617, 257, 857, 295, 257, 13251, 1216, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.20416666927436988, "compression_ratio": 2.2758620689655173, "no_speech_prob": 0.037322998046875, "words": [ { "start": 815.97, "end": 816.45, "word": " So", "probability": 0.521484375 }, { "start": 816.45, "end": 816.93, "word": " this", "probability": 0.56982421875 }, { "start": 816.93, "end": 817.13, "word": " winds", "probability": 0.84228515625 }, { "start": 817.13, "end": 817.27, "word": " up", "probability": 0.91455078125 }, { "start": 817.27, "end": 817.59, "word": " becoming", "probability": 0.79296875 }, { "start": 817.83, "end": 817.91, "word": " a bit", "probability": 0.89404296875 }, { "start": 817.91, "end": 817.99, "word": " of", "probability": 0.90576171875 }, { "start": 818.09, "end": 818.27, "word": " a counting", "probability": 0.78125 }, { "start": 818.27, "end": 818.55, "word": " game", "probability": 0.8115234375 }, { "start": 818.55, "end": 819.03, "word": ".", "probability": 0.92138671875 } ] }, { "id": 232, "seek": 82004, "start": 819.23, "end": 822.63, "text": " How many times do we see A, and it's talking about sports?", "tokens": [ 51264, 1012, 867, 1413, 360, 321, 536, 316, 11, 293, 309, 311, 1417, 466, 6573, 30, 51414 ], "temperature": 0.0, "avg_logprob": -0.20416666927436988, "compression_ratio": 2.2758620689655173, "no_speech_prob": 0.037322998046875, "words": [ { "start": 819.23, "end": 819.71, "word": " How", "probability": 0.892578125 }, { "start": 819.71, "end": 819.85, "word": " many", "probability": 0.81591796875 }, { "start": 819.85, "end": 820.09, "word": " times", "probability": 0.8154296875 }, { "start": 820.09, "end": 820.19, "word": " do", "probability": 0.8662109375 }, { "start": 820.19, "end": 820.29, "word": " we", "probability": 0.90234375 }, { "start": 820.29, "end": 820.49, "word": " see", "probability": 0.81787109375 }, { "start": 820.49, "end": 820.93, "word": " A", "probability": 0.95556640625 }, { "start": 820.93, "end": 821.03, "word": ",", "probability": 0.30712890625 }, { "start": 821.03, "end": 821.21, "word": " and", "probability": 0.8818359375 }, { "start": 821.21, "end": 821.35, "word": " it's", "probability": 0.939208984375 }, { "start": 821.35, "end": 821.55, "word": " talking", "probability": 0.77490234375 }, { "start": 821.55, "end": 821.75, "word": " about", "probability": 0.814453125 }, { "start": 821.75, "end": 822.19, "word": " sports", "probability": 0.78564453125 }, { "start": 822.19, "end": 822.63, "word": "?", "probability": 0.888671875 } ] }, { "id": 233, "seek": 82004, "start": 822.63, "end": 823.55, "text": " Twice.", "tokens": [ 51414, 46964, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.20416666927436988, "compression_ratio": 2.2758620689655173, "no_speech_prob": 0.037322998046875, "words": [ { "start": 822.63, "end": 823.07, "word": " Twice", "probability": 0.89404296875 }, { "start": 823.07, "end": 823.55, "word": ".", "probability": 0.87255859375 } ] }, { "id": 234, "seek": 82004, "start": 823.91, "end": 826.25, "text": " And of course we need to do the same thing for not sports,", "tokens": [ 51464, 400, 295, 1164, 321, 643, 281, 360, 264, 912, 551, 337, 406, 6573, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.20416666927436988, "compression_ratio": 2.2758620689655173, "no_speech_prob": 0.037322998046875, "words": [ { "start": 823.91, "end": 824.07, "word": " And", "probability": 0.7841796875 }, { "start": 824.07, "end": 824.21, "word": " of", "probability": 0.83349609375 }, { "start": 824.21, "end": 824.33, "word": " course", "probability": 0.87158203125 }, { "start": 824.33, "end": 824.47, "word": " we", "probability": 0.625 }, { "start": 824.47, "end": 824.59, "word": " need", "probability": 0.796875 }, { "start": 824.59, "end": 824.67, "word": " to", "probability": 0.904296875 }, { "start": 824.67, "end": 824.77, "word": " do", "probability": 0.8994140625 }, { "start": 824.77, "end": 824.91, "word": " the", "probability": 0.8095703125 }, { "start": 824.91, "end": 825.05, "word": " same", "probability": 0.828125 }, { "start": 825.05, "end": 825.23, "word": " thing", "probability": 0.78515625 }, { "start": 825.23, "end": 825.39, "word": " for", "probability": 0.89697265625 }, { "start": 825.39, "end": 825.63, "word": " not", "probability": 0.802734375 }, { "start": 825.63, "end": 826.09, "word": " sports", "probability": 0.6513671875 }, { "start": 826.09, "end": 826.25, "word": ",", "probability": 0.6142578125 } ] }, { "id": 235, "seek": 82004, "start": 826.25, "end": 829.13, "text": " because we need to find the probability of A happening,", "tokens": [ 51614, 570, 321, 643, 281, 915, 264, 8482, 295, 316, 2737, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.20416666927436988, "compression_ratio": 2.2758620689655173, "no_speech_prob": 0.037322998046875, "words": [ { "start": 826.25, "end": 826.51, "word": " because", "probability": 0.83740234375 }, { "start": 826.51, "end": 826.65, "word": " we", "probability": 0.90234375 }, { "start": 826.65, "end": 826.75, "word": " need", "probability": 0.80859375 }, { "start": 826.75, "end": 826.87, "word": " to", "probability": 0.90673828125 }, { "start": 826.87, "end": 827.05, "word": " find", "probability": 0.79736328125 }, { "start": 827.05, "end": 827.21, "word": " the", "probability": 0.80126953125 }, { "start": 827.21, "end": 827.47, "word": " probability", "probability": 0.869140625 }, { "start": 827.47, "end": 827.89, "word": " of", "probability": 0.896484375 }, { "start": 827.89, "end": 828.47, "word": " A", "probability": 0.98583984375 }, { "start": 828.47, "end": 828.85, "word": " happening", "probability": 0.76220703125 }, { "start": 828.85, "end": 829.13, "word": ",", "probability": 0.90576171875 } ] }, { "id": 236, "seek": 82004, "start": 829.13, "end": 830.97, "text": " the probability of B happening,", "tokens": [ 51714, 264, 8482, 295, 363, 2737, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.20416666927436988, "compression_ratio": 2.2758620689655173, "no_speech_prob": 0.037322998046875, "words": [ { "start": 829.13, "end": 829.25, "word": " the", "probability": 0.5 }, { "start": 829.25, "end": 829.45, "word": " probability", "probability": 0.86328125 }, { "start": 829.45, "end": 829.71, "word": " of", "probability": 0.90576171875 }, { "start": 829.71, "end": 829.89, "word": " B", "probability": 0.9970703125 }, { "start": 829.89, "end": 830.29, "word": " happening", "probability": 0.7607421875 }, { "start": 830.29, "end": 830.97, "word": ",", "probability": 0.494140625 } ] }, { "id": 237, "seek": 84422, "start": 830.97, "end": 832.79, "text": " and we take whichever is higher.", "tokens": [ 50364, 293, 321, 747, 24123, 307, 2946, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.1726562525331974, "compression_ratio": 1.778894472361809, "no_speech_prob": 0.005138397216796875, "words": [ { "start": 830.97, "end": 831.37, "word": " and", "probability": 0.30322265625 }, { "start": 831.37, "end": 831.47, "word": " we", "probability": 0.8837890625 }, { "start": 831.47, "end": 831.69, "word": " take", "probability": 0.81201171875 }, { "start": 831.69, "end": 831.95, "word": " whichever", "probability": 0.8173828125 }, { "start": 831.95, "end": 832.11, "word": " is", "probability": 0.45947265625 }, { "start": 832.11, "end": 832.35, "word": " higher", "probability": 0.8408203125 }, { "start": 832.35, "end": 832.79, "word": ".", "probability": 0.8515625 } ] }, { "id": 238, "seek": 84422, "start": 832.91, "end": 835.31, "text": " So the probability that A is talking about sports,", "tokens": [ 50464, 407, 264, 8482, 300, 316, 307, 1417, 466, 6573, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.1726562525331974, "compression_ratio": 1.778894472361809, "no_speech_prob": 0.005138397216796875, "words": [ { "start": 832.91, "end": 832.99, "word": " So", "probability": 0.73095703125 }, { "start": 832.99, "end": 833.13, "word": " the", "probability": 0.7626953125 }, { "start": 833.13, "end": 833.49, "word": " probability", "probability": 0.88671875 }, { "start": 833.49, "end": 833.71, "word": " that", "probability": 0.8720703125 }, { "start": 833.71, "end": 834.29, "word": " A", "probability": 0.525390625 }, { "start": 834.29, "end": 834.45, "word": " is", "probability": 0.8896484375 }, { "start": 834.45, "end": 834.65, "word": " talking", "probability": 0.7626953125 }, { "start": 834.65, "end": 834.87, "word": " about", "probability": 0.79931640625 }, { "start": 834.87, "end": 835.21, "word": " sports", "probability": 0.7451171875 }, { "start": 835.21, "end": 835.31, "word": ",", "probability": 0.7451171875 } ] }, { "id": 239, "seek": 84422, "start": 835.31, "end": 839.05, "text": " we see it twice in two of our sentences,", "tokens": [ 50564, 321, 536, 309, 6091, 294, 732, 295, 527, 16579, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.1726562525331974, "compression_ratio": 1.778894472361809, "no_speech_prob": 0.005138397216796875, "words": [ { "start": 835.31, "end": 835.41, "word": " we", "probability": 0.88623046875 }, { "start": 835.41, "end": 835.57, "word": " see", "probability": 0.81201171875 }, { "start": 835.57, "end": 835.77, "word": " it", "probability": 0.8720703125 }, { "start": 835.77, "end": 836.33, "word": " twice", "probability": 0.88330078125 }, { "start": 836.33, "end": 837.43, "word": " in", "probability": 0.740234375 }, { "start": 837.43, "end": 837.57, "word": " two", "probability": 0.80419921875 }, { "start": 837.57, "end": 837.69, "word": " of", "probability": 0.90576171875 }, { "start": 837.69, "end": 837.81, "word": " our", "probability": 0.83349609375 }, { "start": 837.81, "end": 838.13, "word": " sentences", "probability": 0.87841796875 }, { "start": 838.13, "end": 839.05, "word": ",", "probability": 0.52880859375 } ] }, { "id": 240, "seek": 84422, "start": 839.05, "end": 842.25, "text": " or twice across all of our sports sentences.", "tokens": [ 50764, 420, 6091, 2108, 439, 295, 527, 6573, 16579, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.1726562525331974, "compression_ratio": 1.778894472361809, "no_speech_prob": 0.005138397216796875, "words": [ { "start": 839.05, "end": 839.27, "word": " or", "probability": 0.892578125 }, { "start": 839.27, "end": 839.87, "word": " twice", "probability": 0.85302734375 }, { "start": 839.87, "end": 840.51, "word": " across", "probability": 0.72998046875 }, { "start": 840.51, "end": 840.89, "word": " all", "probability": 0.904296875 }, { "start": 840.89, "end": 840.99, "word": " of", "probability": 0.900390625 }, { "start": 840.99, "end": 841.13, "word": " our", "probability": 0.82666015625 }, { "start": 841.13, "end": 841.39, "word": " sports", "probability": 0.708984375 }, { "start": 841.39, "end": 841.87, "word": " sentences", "probability": 0.84033203125 }, { "start": 841.87, "end": 842.25, "word": ".", "probability": 0.47119140625 } ] }, { "id": 241, "seek": 84422, "start": 842.25, "end": 843.47, "text": " Got to be precise.", "tokens": [ 50914, 5803, 281, 312, 13600, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.1726562525331974, "compression_ratio": 1.778894472361809, "no_speech_prob": 0.005138397216796875, "words": [ { "start": 842.25, "end": 842.45, "word": " Got", "probability": 0.2783203125 }, { "start": 842.45, "end": 842.51, "word": " to", "probability": 0.8916015625 }, { "start": 842.51, "end": 842.61, "word": " be", "probability": 0.91162109375 }, { "start": 842.61, "end": 843.03, "word": " precise", "probability": 0.876953125 }, { "start": 843.03, "end": 843.47, "word": ".", "probability": 0.97900390625 } ] }, { "id": 242, "seek": 84422, "start": 843.77, "end": 846.87, "text": " We don't see A in not sports at all,", "tokens": [ 51014, 492, 500, 380, 536, 316, 294, 406, 6573, 412, 439, 11, 51164 ], "temperature": 0.0, "avg_logprob": -0.1726562525331974, "compression_ratio": 1.778894472361809, "no_speech_prob": 0.005138397216796875, "words": [ { "start": 843.77, "end": 844.21, "word": " We", "probability": 0.89697265625 }, { "start": 844.21, "end": 844.37, "word": " don't", "probability": 0.943603515625 }, { "start": 844.37, "end": 844.65, "word": " see", "probability": 0.82177734375 }, { "start": 844.65, "end": 845.13, "word": " A", "probability": 0.9775390625 }, { "start": 845.13, "end": 845.73, "word": " in", "probability": 0.87158203125 }, { "start": 845.73, "end": 845.95, "word": " not", "probability": 0.62451171875 }, { "start": 845.95, "end": 846.33, "word": " sports", "probability": 0.7353515625 }, { "start": 846.33, "end": 846.57, "word": " at", "probability": 0.87451171875 }, { "start": 846.57, "end": 846.77, "word": " all", "probability": 0.8984375 }, { "start": 846.77, "end": 846.87, "word": ",", "probability": 0.51953125 } ] }, { "id": 243, "seek": 84422, "start": 846.87, "end": 850.11, "text": " so that's going to be zero across all of our not sports sentences.", "tokens": [ 51164, 370, 300, 311, 516, 281, 312, 4018, 2108, 439, 295, 527, 406, 6573, 16579, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.1726562525331974, "compression_ratio": 1.778894472361809, "no_speech_prob": 0.005138397216796875, "words": [ { "start": 846.87, "end": 846.97, "word": " so", "probability": 0.88525390625 }, { "start": 846.97, "end": 847.13, "word": " that's", "probability": 0.937744140625 }, { "start": 847.13, "end": 847.21, "word": " going", "probability": 0.5546875 }, { "start": 847.21, "end": 847.27, "word": " to", "probability": 0.90625 }, { "start": 847.27, "end": 847.39, "word": " be", "probability": 0.90234375 }, { "start": 847.39, "end": 847.69, "word": " zero", "probability": 0.791015625 }, { "start": 847.69, "end": 848.07, "word": " across", "probability": 0.69970703125 }, { "start": 848.07, "end": 848.29, "word": " all", "probability": 0.9013671875 }, { "start": 848.29, "end": 848.41, "word": " of", "probability": 0.90380859375 }, { "start": 848.41, "end": 848.57, "word": " our", "probability": 0.8203125 }, { "start": 848.57, "end": 848.91, "word": " not", "probability": 0.87353515625 }, { "start": 848.91, "end": 849.17, "word": " sports", "probability": 0.740234375 }, { "start": 849.17, "end": 849.67, "word": " sentences", "probability": 0.8603515625 }, { "start": 849.67, "end": 850.11, "word": ".", "probability": 0.994140625 } ] }, { "id": 244, "seek": 84422, "start": 850.87, "end": 855.15, "text": " Very shows up in sports once, does not show up in not sports.", "tokens": [ 51364, 4372, 3110, 493, 294, 6573, 1564, 11, 775, 406, 855, 493, 294, 406, 6573, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.1726562525331974, "compression_ratio": 1.778894472361809, "no_speech_prob": 0.005138397216796875, "words": [ { "start": 850.87, "end": 851.09, "word": " Very", "probability": 0.71826171875 }, { "start": 851.09, "end": 851.57, "word": " shows", "probability": 0.7880859375 }, { "start": 851.57, "end": 851.69, "word": " up", "probability": 0.90380859375 }, { "start": 851.69, "end": 851.83, "word": " in", "probability": 0.9130859375 }, { "start": 851.83, "end": 852.15, "word": " sports", "probability": 0.80419921875 }, { "start": 852.15, "end": 852.65, "word": " once", "probability": 0.82275390625 }, { "start": 852.65, "end": 853.13, "word": ",", "probability": 0.828125 }, { "start": 853.13, "end": 853.55, "word": " does", "probability": 0.9091796875 }, { "start": 853.55, "end": 853.79, "word": " not", "probability": 0.9013671875 }, { "start": 853.79, "end": 853.97, "word": " show", "probability": 0.8828125 }, { "start": 853.97, "end": 854.11, "word": " up", "probability": 0.9033203125 }, { "start": 854.11, "end": 854.23, "word": " in", "probability": 0.8994140625 }, { "start": 854.23, "end": 854.43, "word": " not", "probability": 0.89013671875 }, { "start": 854.43, "end": 854.71, "word": " sports", "probability": 0.7958984375 }, { "start": 854.71, "end": 855.15, "word": ".", "probability": 0.8896484375 } ] }, { "id": 245, "seek": 87322, "start": 855.15, "end": 859.55, "text": " Close shows up in not sports once,", "tokens": [ 50364, 16346, 3110, 493, 294, 406, 6573, 1564, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.1859262553479174, "compression_ratio": 1.8693877551020408, "no_speech_prob": 0.055816650390625, "words": [ { "start": 855.15, "end": 855.93, "word": " Close", "probability": 0.478759765625 }, { "start": 855.93, "end": 856.49, "word": " shows", "probability": 0.697265625 }, { "start": 856.49, "end": 856.65, "word": " up", "probability": 0.9052734375 }, { "start": 856.65, "end": 856.77, "word": " in", "probability": 0.8037109375 }, { "start": 856.77, "end": 857.13, "word": " not", "probability": 0.453857421875 }, { "start": 857.13, "end": 857.63, "word": " sports", "probability": 0.63330078125 }, { "start": 857.63, "end": 858.47, "word": " once", "probability": 0.7216796875 }, { "start": 858.47, "end": 859.55, "word": ",", "probability": 0.346923828125 } ] }, { "id": 246, "seek": 87322, "start": 859.55, "end": 861.35, "text": " does not show up in sports,", "tokens": [ 50564, 775, 406, 855, 493, 294, 6573, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.1859262553479174, "compression_ratio": 1.8693877551020408, "no_speech_prob": 0.055816650390625, "words": [ { "start": 859.55, "end": 860.23, "word": " does", "probability": 0.5546875 }, { "start": 860.23, "end": 860.43, "word": " not", "probability": 0.9033203125 }, { "start": 860.43, "end": 860.57, "word": " show", "probability": 0.87841796875 }, { "start": 860.57, "end": 860.67, "word": " up", "probability": 0.91552734375 }, { "start": 860.67, "end": 860.81, "word": " in", "probability": 0.91064453125 }, { "start": 860.81, "end": 861.15, "word": " sports", "probability": 0.7880859375 }, { "start": 861.15, "end": 861.35, "word": ",", "probability": 0.62841796875 } ] }, { "id": 247, "seek": 87322, "start": 861.35, "end": 863.83, "text": " and then game shows up in sports twice,", "tokens": [ 50664, 293, 550, 1216, 3110, 493, 294, 6573, 6091, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.1859262553479174, "compression_ratio": 1.8693877551020408, "no_speech_prob": 0.055816650390625, "words": [ { "start": 861.35, "end": 861.39, "word": " and", "probability": 0.857421875 }, { "start": 861.39, "end": 861.55, "word": " then", "probability": 0.697265625 }, { "start": 861.55, "end": 861.89, "word": " game", "probability": 0.428466796875 }, { "start": 861.89, "end": 862.33, "word": " shows", "probability": 0.81103515625 }, { "start": 862.33, "end": 862.47, "word": " up", "probability": 0.91357421875 }, { "start": 862.47, "end": 862.59, "word": " in", "probability": 0.90380859375 }, { "start": 862.59, "end": 862.89, "word": " sports", "probability": 0.791015625 }, { "start": 862.89, "end": 863.51, "word": " twice", "probability": 0.85986328125 }, { "start": 863.51, "end": 863.83, "word": ",", "probability": 0.583984375 } ] }, { "id": 248, "seek": 87322, "start": 863.83, "end": 865.81, "text": " and it doesn't show up in not sports.", "tokens": [ 50764, 293, 309, 1177, 380, 855, 493, 294, 406, 6573, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.1859262553479174, "compression_ratio": 1.8693877551020408, "no_speech_prob": 0.055816650390625, "words": [ { "start": 863.83, "end": 863.87, "word": " and", "probability": 0.578125 }, { "start": 863.87, "end": 863.95, "word": " it", "probability": 0.73486328125 }, { "start": 863.95, "end": 864.17, "word": " doesn't", "probability": 0.9287109375 }, { "start": 864.17, "end": 864.37, "word": " show", "probability": 0.88623046875 }, { "start": 864.37, "end": 864.55, "word": " up", "probability": 0.9140625 }, { "start": 864.55, "end": 864.83, "word": " in", "probability": 0.8466796875 }, { "start": 864.83, "end": 865.07, "word": " not", "probability": 0.88525390625 }, { "start": 865.07, "end": 865.41, "word": " sports", "probability": 0.77685546875 }, { "start": 865.41, "end": 865.81, "word": ".", "probability": 0.97900390625 } ] }, { "id": 249, "seek": 87322, "start": 867.11, "end": 869.17, "text": " So we take those numbers and we plug them in.", "tokens": [ 50964, 407, 321, 747, 729, 3547, 293, 321, 5452, 552, 294, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.1859262553479174, "compression_ratio": 1.8693877551020408, "no_speech_prob": 0.055816650390625, "words": [ { "start": 867.11, "end": 867.51, "word": " So", "probability": 0.7451171875 }, { "start": 867.51, "end": 867.61, "word": " we", "probability": 0.8310546875 }, { "start": 867.61, "end": 867.77, "word": " take", "probability": 0.80908203125 }, { "start": 867.77, "end": 867.93, "word": " those", "probability": 0.85302734375 }, { "start": 867.93, "end": 868.25, "word": " numbers", "probability": 0.857421875 }, { "start": 868.25, "end": 868.39, "word": " and", "probability": 0.6669921875 }, { "start": 868.39, "end": 868.47, "word": " we", "probability": 0.8759765625 }, { "start": 868.47, "end": 868.63, "word": " plug", "probability": 0.78662109375 }, { "start": 868.63, "end": 868.79, "word": " them", "probability": 0.73193359375 }, { "start": 868.79, "end": 869.01, "word": " in", "probability": 0.90625 }, { "start": 869.01, "end": 869.17, "word": ".", "probability": 0.77294921875 } ] }, { "id": 250, "seek": 87322, "start": 869.17, "end": 871.67, "text": " We saw for sports, A showed up twice,", "tokens": [ 51064, 492, 1866, 337, 6573, 11, 316, 4712, 493, 6091, 11, 51164 ], "temperature": 0.0, "avg_logprob": -0.1859262553479174, "compression_ratio": 1.8693877551020408, "no_speech_prob": 0.055816650390625, "words": [ { "start": 869.17, "end": 869.27, "word": " We", "probability": 0.8935546875 }, { "start": 869.27, "end": 869.55, "word": " saw", "probability": 0.82861328125 }, { "start": 869.55, "end": 869.87, "word": " for", "probability": 0.849609375 }, { "start": 869.87, "end": 870.37, "word": " sports", "probability": 0.77685546875 }, { "start": 870.37, "end": 870.53, "word": ",", "probability": 0.77294921875 }, { "start": 870.53, "end": 870.63, "word": " A", "probability": 0.62548828125 }, { "start": 870.63, "end": 870.89, "word": " showed", "probability": 0.802734375 }, { "start": 870.89, "end": 871.03, "word": " up", "probability": 0.9140625 }, { "start": 871.03, "end": 871.45, "word": " twice", "probability": 0.84814453125 }, { "start": 871.45, "end": 871.67, "word": ",", "probability": 0.91162109375 } ] }, { "id": 251, "seek": 87322, "start": 871.67, "end": 872.79, "text": " Very showed up once,", "tokens": [ 51164, 4372, 4712, 493, 1564, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.1859262553479174, "compression_ratio": 1.8693877551020408, "no_speech_prob": 0.055816650390625, "words": [ { "start": 871.67, "end": 871.77, "word": " Very", "probability": 0.30224609375 }, { "start": 871.77, "end": 871.99, "word": " showed", "probability": 0.783203125 }, { "start": 871.99, "end": 872.15, "word": " up", "probability": 0.9150390625 }, { "start": 872.15, "end": 872.57, "word": " once", "probability": 0.81591796875 }, { "start": 872.57, "end": 872.79, "word": ",", "probability": 0.82080078125 } ] }, { "id": 252, "seek": 87322, "start": 872.79, "end": 874.83, "text": " Close didn't show up at all,", "tokens": [ 51214, 16346, 994, 380, 855, 493, 412, 439, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.1859262553479174, "compression_ratio": 1.8693877551020408, "no_speech_prob": 0.055816650390625, "words": [ { "start": 872.79, "end": 873.09, "word": " Close", "probability": 0.83544921875 }, { "start": 873.09, "end": 873.67, "word": " didn't", "probability": 0.923828125 }, { "start": 873.67, "end": 873.85, "word": " show", "probability": 0.8759765625 }, { "start": 873.85, "end": 874.01, "word": " up", "probability": 0.904296875 }, { "start": 874.01, "end": 874.11, "word": " at", "probability": 0.9072265625 }, { "start": 874.11, "end": 874.37, "word": " all", "probability": 0.89892578125 }, { "start": 874.37, "end": 874.83, "word": ",", "probability": 0.89599609375 } ] }, { "id": 253, "seek": 87322, "start": 874.83, "end": 876.35, "text": " and Game showed up twice.", "tokens": [ 51314, 293, 7522, 4712, 493, 6091, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.1859262553479174, "compression_ratio": 1.8693877551020408, "no_speech_prob": 0.055816650390625, "words": [ { "start": 874.83, "end": 875.01, "word": " and", "probability": 0.8955078125 }, { "start": 875.01, "end": 875.19, "word": " Game", "probability": 0.61181640625 }, { "start": 875.19, "end": 875.41, "word": " showed", "probability": 0.810546875 }, { "start": 875.41, "end": 875.55, "word": " up", "probability": 0.91455078125 }, { "start": 875.55, "end": 875.95, "word": " twice", "probability": 0.8564453125 }, { "start": 875.95, "end": 876.35, "word": ".", "probability": 0.923828125 } ] }, { "id": 254, "seek": 87322, "start": 876.45, "end": 878.65, "text": " And then if we count the number of words that we have", "tokens": [ 51414, 400, 550, 498, 321, 1207, 264, 1230, 295, 2283, 300, 321, 362, 51514 ], "temperature": 0.0, "avg_logprob": -0.1859262553479174, "compression_ratio": 1.8693877551020408, "no_speech_prob": 0.055816650390625, "words": [ { "start": 876.45, "end": 876.59, "word": " And", "probability": 0.81591796875 }, { "start": 876.59, "end": 876.69, "word": " then", "probability": 0.70849609375 }, { "start": 876.69, "end": 876.77, "word": " if", "probability": 0.87451171875 }, { "start": 876.77, "end": 876.87, "word": " we", "probability": 0.89794921875 }, { "start": 876.87, "end": 877.05, "word": " count", "probability": 0.8056640625 }, { "start": 877.05, "end": 877.19, "word": " the", "probability": 0.81787109375 }, { "start": 877.19, "end": 877.39, "word": " number", "probability": 0.8837890625 }, { "start": 877.39, "end": 877.59, "word": " of", "probability": 0.90380859375 }, { "start": 877.59, "end": 877.89, "word": " words", "probability": 0.7177734375 }, { "start": 877.89, "end": 878.09, "word": " that", "probability": 0.87060546875 }, { "start": 878.09, "end": 878.21, "word": " we", "probability": 0.90087890625 }, { "start": 878.21, "end": 878.65, "word": " have", "probability": 0.87939453125 } ] }, { "id": 255, "seek": 87322, "start": 878.65, "end": 880.57, "text": " across all of the sports sentences,", "tokens": [ 51514, 2108, 439, 295, 264, 6573, 16579, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.1859262553479174, "compression_ratio": 1.8693877551020408, "no_speech_prob": 0.055816650390625, "words": [ { "start": 878.65, "end": 879.11, "word": " across", "probability": 0.68017578125 }, { "start": 879.11, "end": 879.47, "word": " all", "probability": 0.9033203125 }, { "start": 879.47, "end": 879.61, "word": " of", "probability": 0.8935546875 }, { "start": 879.61, "end": 879.73, "word": " the", "probability": 0.80810546875 }, { "start": 879.73, "end": 879.99, "word": " sports", "probability": 0.62353515625 }, { "start": 879.99, "end": 880.41, "word": " sentences", "probability": 0.8251953125 }, { "start": 880.41, "end": 880.57, "word": ",", "probability": 0.92236328125 } ] }, { "id": 256, "seek": 87322, "start": 880.57, "end": 881.89, "text": " we have a total of 11.", "tokens": [ 51614, 321, 362, 257, 3217, 295, 2975, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.1859262553479174, "compression_ratio": 1.8693877551020408, "no_speech_prob": 0.055816650390625, "words": [ { "start": 880.57, "end": 880.73, "word": " we", "probability": 0.89990234375 }, { "start": 880.73, "end": 880.85, "word": " have", "probability": 0.8759765625 }, { "start": 880.95, "end": 881.09, "word": " a total", "probability": 0.80859375 }, { "start": 881.09, "end": 881.27, "word": " of", "probability": 0.89794921875 }, { "start": 881.27, "end": 881.55, "word": " 11", "probability": 0.79541015625 }, { "start": 881.55, "end": 881.89, "word": ".", "probability": 0.93115234375 } ] }, { "id": 257, "seek": 87322, "start": 881.89, "end": 884.15, "text": " So it just becomes a simple 2 divided by 11,", "tokens": [ 51714, 407, 309, 445, 3643, 257, 2199, 568, 6666, 538, 2975, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.1859262553479174, "compression_ratio": 1.8693877551020408, "no_speech_prob": 0.055816650390625, "words": [ { "start": 881.89, "end": 882.05, "word": " So", "probability": 0.8828125 }, { "start": 882.05, "end": 882.17, "word": " it", "probability": 0.88916015625 }, { "start": 882.17, "end": 882.29, "word": " just", "probability": 0.8828125 }, { "start": 882.29, "end": 882.57, "word": " becomes", "probability": 0.77978515625 }, { "start": 882.71, "end": 882.95, "word": " a simple", "probability": 0.904296875 }, { "start": 882.95, "end": 883.27, "word": " 2", "probability": 0.6142578125 }, { "start": 883.27, "end": 883.51, "word": " divided", "probability": 0.509765625 }, { "start": 883.51, "end": 883.67, "word": " by", "probability": 0.89892578125 }, { "start": 883.67, "end": 884.01, "word": " 11", "probability": 0.89697265625 }, { "start": 884.01, "end": 884.15, "word": ",", "probability": 0.9541015625 } ] }, { "id": 258, "seek": 90202, "start": 884.15, "end": 886.87, "text": " 1 divided by 11, and so on.", "tokens": [ 50364, 502, 6666, 538, 2975, 11, 293, 370, 322, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.2183493599932418, "compression_ratio": 1.7155172413793103, "no_speech_prob": 0.009857177734375, "words": [ { "start": 884.15, "end": 884.27, "word": " 1", "probability": 0.1961669921875 }, { "start": 884.27, "end": 884.53, "word": " divided", "probability": 0.3203125 }, { "start": 884.53, "end": 884.73, "word": " by", "probability": 0.90576171875 }, { "start": 884.73, "end": 885.15, "word": " 11", "probability": 0.87109375 }, { "start": 885.15, "end": 885.63, "word": ",", "probability": 0.5078125 }, { "start": 885.63, "end": 885.93, "word": " and", "probability": 0.8583984375 }, { "start": 885.93, "end": 886.11, "word": " so", "probability": 0.8974609375 }, { "start": 886.11, "end": 886.31, "word": " on", "probability": 0.9052734375 }, { "start": 886.31, "end": 886.87, "word": ".", "probability": 0.8701171875 } ] }, { "id": 259, "seek": 90202, "start": 887.55, "end": 890.37, "text": " But we can't use straight, naive Bayesian.", "tokens": [ 50514, 583, 321, 393, 380, 764, 2997, 11, 29052, 7840, 42434, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.2183493599932418, "compression_ratio": 1.7155172413793103, "no_speech_prob": 0.009857177734375, "words": [ { "start": 887.55, "end": 888.11, "word": " But", "probability": 0.77001953125 }, { "start": 888.11, "end": 888.23, "word": " we", "probability": 0.86572265625 }, { "start": 888.23, "end": 888.55, "word": " can't", "probability": 0.94482421875 }, { "start": 888.55, "end": 888.83, "word": " use", "probability": 0.8037109375 }, { "start": 888.83, "end": 889.11, "word": " straight", "probability": 0.70654296875 }, { "start": 889.11, "end": 889.19, "word": ",", "probability": 0.2437744140625 }, { "start": 889.19, "end": 889.49, "word": " naive", "probability": 0.55810546875 }, { "start": 889.49, "end": 889.81, "word": " Bayesian", "probability": 0.943359375 }, { "start": 889.81, "end": 890.37, "word": ".", "probability": 0.68212890625 } ] }, { "id": 260, "seek": 90202, "start": 890.43, "end": 893.53, "text": " And the reason why is because we have these zeros.", "tokens": [ 50664, 400, 264, 1778, 983, 307, 570, 321, 362, 613, 35193, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.2183493599932418, "compression_ratio": 1.7155172413793103, "no_speech_prob": 0.009857177734375, "words": [ { "start": 890.43, "end": 890.51, "word": " And", "probability": 0.54833984375 }, { "start": 890.51, "end": 890.65, "word": " the", "probability": 0.81201171875 }, { "start": 890.65, "end": 890.93, "word": " reason", "probability": 0.90576171875 }, { "start": 890.93, "end": 891.39, "word": " why", "probability": 0.79833984375 }, { "start": 891.39, "end": 891.71, "word": " is", "probability": 0.771484375 }, { "start": 891.71, "end": 892.05, "word": " because", "probability": 0.81005859375 }, { "start": 892.05, "end": 892.25, "word": " we", "probability": 0.888671875 }, { "start": 892.25, "end": 892.45, "word": " have", "probability": 0.87890625 }, { "start": 892.45, "end": 892.67, "word": " these", "probability": 0.6884765625 }, { "start": 892.67, "end": 892.97, "word": " zeros", "probability": 0.52099609375 }, { "start": 892.97, "end": 893.53, "word": ".", "probability": 0.96728515625 } ] }, { "id": 261, "seek": 90202, "start": 893.91, "end": 897.25, "text": " Now, close is a word that we've never seen in sports,", "tokens": [ 50814, 823, 11, 1998, 307, 257, 1349, 300, 321, 600, 1128, 1612, 294, 6573, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.2183493599932418, "compression_ratio": 1.7155172413793103, "no_speech_prob": 0.009857177734375, "words": [ { "start": 893.91, "end": 894.23, "word": " Now", "probability": 0.71923828125 }, { "start": 894.23, "end": 894.51, "word": ",", "probability": 0.62939453125 }, { "start": 894.51, "end": 894.93, "word": " close", "probability": 0.34326171875 }, { "start": 894.93, "end": 895.11, "word": " is", "probability": 0.89208984375 }, { "start": 895.25, "end": 895.39, "word": " a word", "probability": 0.80419921875 }, { "start": 895.39, "end": 895.53, "word": " that", "probability": 0.76806640625 }, { "start": 895.53, "end": 895.69, "word": " we've", "probability": 0.912109375 }, { "start": 895.69, "end": 895.85, "word": " never", "probability": 0.869140625 }, { "start": 895.85, "end": 896.15, "word": " seen", "probability": 0.8701171875 }, { "start": 896.15, "end": 896.35, "word": " in", "probability": 0.90576171875 }, { "start": 896.35, "end": 896.83, "word": " sports", "probability": 0.79833984375 }, { "start": 896.83, "end": 897.25, "word": ",", "probability": 0.484619140625 } ] }, { "id": 262, "seek": 90202, "start": 897.25, "end": 899.63, "text": " so we get zero, and that winds up being", "tokens": [ 51014, 370, 321, 483, 4018, 11, 293, 300, 17765, 493, 885, 51114 ], "temperature": 0.0, "avg_logprob": -0.2183493599932418, "compression_ratio": 1.7155172413793103, "no_speech_prob": 0.009857177734375, "words": [ { "start": 897.25, "end": 897.69, "word": " so", "probability": 0.8896484375 }, { "start": 897.69, "end": 897.81, "word": " we", "probability": 0.892578125 }, { "start": 897.81, "end": 897.93, "word": " get", "probability": 0.90869140625 }, { "start": 897.93, "end": 898.29, "word": " zero", "probability": 0.65771484375 }, { "start": 898.29, "end": 898.53, "word": ",", "probability": 0.472900390625 }, { "start": 898.53, "end": 898.59, "word": " and", "probability": 0.8779296875 }, { "start": 898.59, "end": 898.85, "word": " that", "probability": 0.880859375 }, { "start": 898.85, "end": 899.25, "word": " winds", "probability": 0.8046875 }, { "start": 899.25, "end": 899.41, "word": " up", "probability": 0.91357421875 }, { "start": 899.41, "end": 899.63, "word": " being", "probability": 0.8720703125 } ] }, { "id": 263, "seek": 90202, "start": 899.63, "end": 901.35, "text": " zero divided by 11, which is zero.", "tokens": [ 51114, 4018, 6666, 538, 2975, 11, 597, 307, 4018, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.2183493599932418, "compression_ratio": 1.7155172413793103, "no_speech_prob": 0.009857177734375, "words": [ { "start": 899.63, "end": 899.87, "word": " zero", "probability": 0.61083984375 }, { "start": 899.87, "end": 900.09, "word": " divided", "probability": 0.75 }, { "start": 900.09, "end": 900.29, "word": " by", "probability": 0.90771484375 }, { "start": 900.29, "end": 900.59, "word": " 11", "probability": 0.84033203125 }, { "start": 900.59, "end": 900.71, "word": ",", "probability": 0.888671875 }, { "start": 900.71, "end": 900.83, "word": " which", "probability": 0.91796875 }, { "start": 900.83, "end": 900.97, "word": " is", "probability": 0.90087890625 }, { "start": 900.97, "end": 901.25, "word": " zero", "probability": 0.80908203125 }, { "start": 901.25, "end": 901.35, "word": ".", "probability": 0.53662109375 } ] }, { "id": 264, "seek": 90202, "start": 901.35, "end": 903.31, "text": " Zero times everything is zero,", "tokens": [ 51214, 17182, 1413, 1203, 307, 4018, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.2183493599932418, "compression_ratio": 1.7155172413793103, "no_speech_prob": 0.009857177734375, "words": [ { "start": 901.35, "end": 901.53, "word": " Zero", "probability": 0.859375 }, { "start": 901.53, "end": 901.85, "word": " times", "probability": 0.7744140625 }, { "start": 901.85, "end": 902.35, "word": " everything", "probability": 0.87890625 }, { "start": 902.35, "end": 902.75, "word": " is", "probability": 0.88330078125 }, { "start": 902.75, "end": 903.07, "word": " zero", "probability": 0.83447265625 }, { "start": 903.07, "end": 903.31, "word": ",", "probability": 0.50732421875 } ] }, { "id": 265, "seek": 90202, "start": 903.31, "end": 905.65, "text": " and so unfortunately the probability of", "tokens": [ 51314, 293, 370, 7015, 264, 8482, 295, 51464 ], "temperature": 0.0, "avg_logprob": -0.2183493599932418, "compression_ratio": 1.7155172413793103, "no_speech_prob": 0.009857177734375, "words": [ { "start": 903.31, "end": 903.37, "word": " and", "probability": 0.8291015625 }, { "start": 903.37, "end": 903.55, "word": " so", "probability": 0.90087890625 }, { "start": 903.55, "end": 904.09, "word": " unfortunately", "probability": 0.666015625 }, { "start": 904.09, "end": 904.37, "word": " the", "probability": 0.4482421875 }, { "start": 904.37, "end": 904.87, "word": " probability", "probability": 0.8974609375 }, { "start": 904.87, "end": 905.65, "word": " of", "probability": 0.9013671875 } ] }, { "id": 266, "seek": 90202, "start": 905.65, "end": 908.89, "text": " this sentence being about sports,", "tokens": [ 51464, 341, 8174, 885, 466, 6573, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.2183493599932418, "compression_ratio": 1.7155172413793103, "no_speech_prob": 0.009857177734375, "words": [ { "start": 905.65, "end": 906.45, "word": " this", "probability": 0.875 }, { "start": 906.45, "end": 907.09, "word": " sentence", "probability": 0.8408203125 }, { "start": 907.09, "end": 907.41, "word": " being", "probability": 0.8818359375 }, { "start": 907.41, "end": 908.23, "word": " about", "probability": 0.80224609375 }, { "start": 908.23, "end": 908.79, "word": " sports", "probability": 0.783203125 }, { "start": 908.79, "end": 908.89, "word": ",", "probability": 0.7841796875 } ] }, { "id": 267, "seek": 90202, "start": 908.89, "end": 911.19, "text": " if we just use straight Bayesian,", "tokens": [ 51564, 498, 321, 445, 764, 2997, 7840, 42434, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.2183493599932418, "compression_ratio": 1.7155172413793103, "no_speech_prob": 0.009857177734375, "words": [ { "start": 908.89, "end": 909.09, "word": " if", "probability": 0.90234375 }, { "start": 909.09, "end": 909.19, "word": " we", "probability": 0.900390625 }, { "start": 909.19, "end": 909.35, "word": " just", "probability": 0.8779296875 }, { "start": 909.35, "end": 909.53, "word": " use", "probability": 0.76318359375 }, { "start": 909.53, "end": 909.97, "word": " straight", "probability": 0.8271484375 }, { "start": 909.97, "end": 910.91, "word": " Bayesian", "probability": 0.948974609375 }, { "start": 910.91, "end": 911.19, "word": ",", "probability": 0.892578125 } ] }, { "id": 268, "seek": 90202, "start": 911.77, "end": 912.95, "text": " is zero.", "tokens": [ 51714, 307, 4018, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.2183493599932418, "compression_ratio": 1.7155172413793103, "no_speech_prob": 0.009857177734375, "words": [ { "start": 911.77, "end": 912.15, "word": " is", "probability": 0.90478515625 }, { "start": 912.15, "end": 912.39, "word": " zero", "probability": 0.82373046875 }, { "start": 912.39, "end": 912.95, "word": ".", "probability": 0.9921875 } ] }, { "id": 269, "seek": 93132, "start": 913.53, "end": 915.55, "text": " So that doesn't really work for us.", "tokens": [ 50364, 407, 300, 1177, 380, 534, 589, 337, 505, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.17121010426933883, "compression_ratio": 1.699248120300752, "no_speech_prob": 0.0035381317138671875, "words": [ { "start": 913.53, "end": 913.97, "word": " So", "probability": 0.30419921875 }, { "start": 913.97, "end": 914.11, "word": " that", "probability": 0.5849609375 }, { "start": 914.11, "end": 914.33, "word": " doesn't", "probability": 0.924072265625 }, { "start": 914.33, "end": 914.49, "word": " really", "probability": 0.68310546875 }, { "start": 914.49, "end": 914.69, "word": " work", "probability": 0.8203125 }, { "start": 914.69, "end": 914.85, "word": " for", "probability": 0.88818359375 }, { "start": 914.85, "end": 915.11, "word": " us", "probability": 0.8994140625 }, { "start": 915.11, "end": 915.55, "word": ".", "probability": 0.8818359375 } ] }, { "id": 270, "seek": 93132, "start": 916.59, "end": 918.33, "text": " So instead, what we're going to use is called", "tokens": [ 50514, 407, 2602, 11, 437, 321, 434, 516, 281, 764, 307, 1219, 50614 ], "temperature": 0.0, "avg_logprob": -0.17121010426933883, "compression_ratio": 1.699248120300752, "no_speech_prob": 0.0035381317138671875, "words": [ { "start": 916.59, "end": 916.69, "word": " So", "probability": 0.6728515625 }, { "start": 916.69, "end": 916.99, "word": " instead", "probability": 0.7978515625 }, { "start": 916.99, "end": 917.17, "word": ",", "probability": 0.455322265625 }, { "start": 917.17, "end": 917.25, "word": " what", "probability": 0.80908203125 }, { "start": 917.25, "end": 917.39, "word": " we're", "probability": 0.91259765625 }, { "start": 917.39, "end": 917.49, "word": " going", "probability": 0.6484375 }, { "start": 917.49, "end": 917.55, "word": " to", "probability": 0.90478515625 }, { "start": 917.55, "end": 917.83, "word": " use", "probability": 0.82421875 }, { "start": 917.83, "end": 918.05, "word": " is", "probability": 0.89013671875 }, { "start": 918.05, "end": 918.33, "word": " called", "probability": 0.7060546875 } ] }, { "id": 271, "seek": 93132, "start": 918.33, "end": 920.23, "text": " multinomial naive Bayesian.", "tokens": [ 50614, 45872, 47429, 29052, 7840, 42434, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.17121010426933883, "compression_ratio": 1.699248120300752, "no_speech_prob": 0.0035381317138671875, "words": [ { "start": 918.33, "end": 919.11, "word": " multinomial", "probability": 0.818359375 }, { "start": 919.11, "end": 919.45, "word": " naive", "probability": 0.022125244140625 }, { "start": 919.45, "end": 919.83, "word": " Bayesian", "probability": 0.72216796875 }, { "start": 919.83, "end": 920.23, "word": ".", "probability": 0.94287109375 } ] }, { "id": 272, "seek": 93132, "start": 920.23, "end": 922.13, "text": " It's a very similar formula, but we have", "tokens": [ 50714, 467, 311, 257, 588, 2531, 8513, 11, 457, 321, 362, 50814 ], "temperature": 0.0, "avg_logprob": -0.17121010426933883, "compression_ratio": 1.699248120300752, "no_speech_prob": 0.0035381317138671875, "words": [ { "start": 920.23, "end": 920.43, "word": " It's", "probability": 0.931640625 }, { "start": 920.49, "end": 920.63, "word": " a very", "probability": 0.7294921875 }, { "start": 920.63, "end": 920.97, "word": " similar", "probability": 0.92578125 }, { "start": 920.97, "end": 921.33, "word": " formula", "probability": 0.8115234375 }, { "start": 921.33, "end": 921.59, "word": ",", "probability": 0.7734375 }, { "start": 921.59, "end": 921.67, "word": " but", "probability": 0.9013671875 }, { "start": 921.67, "end": 921.81, "word": " we", "probability": 0.8984375 }, { "start": 921.81, "end": 922.13, "word": " have", "probability": 0.87939453125 } ] }, { "id": 273, "seek": 93132, "start": 922.13, "end": 923.71, "text": " what's called a smoothing filter,", "tokens": [ 50814, 437, 311, 1219, 257, 899, 6259, 571, 6608, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.17121010426933883, "compression_ratio": 1.699248120300752, "no_speech_prob": 0.0035381317138671875, "words": [ { "start": 922.13, "end": 922.41, "word": " what's", "probability": 0.920166015625 }, { "start": 922.41, "end": 922.55, "word": " called", "probability": 0.8076171875 }, { "start": 922.77, "end": 923.15, "word": " a smoothing", "probability": 0.8922526041666666 }, { "start": 923.15, "end": 923.49, "word": " filter", "probability": 0.90087890625 }, { "start": 923.49, "end": 923.71, "word": ",", "probability": 0.480712890625 } ] }, { "id": 274, "seek": 93132, "start": 923.71, "end": 925.05, "text": " and that's this alpha.", "tokens": [ 50914, 293, 300, 311, 341, 8961, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.17121010426933883, "compression_ratio": 1.699248120300752, "no_speech_prob": 0.0035381317138671875, "words": [ { "start": 923.71, "end": 923.75, "word": " and", "probability": 0.8837890625 }, { "start": 923.75, "end": 923.99, "word": " that's", "probability": 0.93505859375 }, { "start": 923.99, "end": 924.23, "word": " this", "probability": 0.86474609375 }, { "start": 924.23, "end": 924.61, "word": " alpha", "probability": 0.7421875 }, { "start": 924.61, "end": 925.05, "word": ".", "probability": 0.96337890625 } ] }, { "id": 275, "seek": 93132, "start": 925.05, "end": 927.07, "text": " We can set this alpha to whatever we want.", "tokens": [ 50964, 492, 393, 992, 341, 8961, 281, 2035, 321, 528, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.17121010426933883, "compression_ratio": 1.699248120300752, "no_speech_prob": 0.0035381317138671875, "words": [ { "start": 925.05, "end": 925.33, "word": " We", "probability": 0.900390625 }, { "start": 925.33, "end": 925.45, "word": " can", "probability": 0.8994140625 }, { "start": 925.45, "end": 925.65, "word": " set", "probability": 0.88671875 }, { "start": 925.65, "end": 925.83, "word": " this", "probability": 0.87109375 }, { "start": 925.83, "end": 926.09, "word": " alpha", "probability": 0.779296875 }, { "start": 926.09, "end": 926.31, "word": " to", "probability": 0.90234375 }, { "start": 926.31, "end": 926.51, "word": " whatever", "probability": 0.80712890625 }, { "start": 926.51, "end": 926.73, "word": " we", "probability": 0.8896484375 }, { "start": 926.73, "end": 926.97, "word": " want", "probability": 0.81982421875 }, { "start": 926.97, "end": 927.07, "word": ".", "probability": 0.7373046875 } ] }, { "id": 276, "seek": 93132, "start": 927.07, "end": 928.65, "text": " Usually we just set it to 1.", "tokens": [ 51064, 11419, 321, 445, 992, 309, 281, 502, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.17121010426933883, "compression_ratio": 1.699248120300752, "no_speech_prob": 0.0035381317138671875, "words": [ { "start": 927.07, "end": 927.25, "word": " Usually", "probability": 0.75537109375 }, { "start": 927.25, "end": 927.39, "word": " we", "probability": 0.67919921875 }, { "start": 927.39, "end": 927.55, "word": " just", "probability": 0.873046875 }, { "start": 927.55, "end": 927.73, "word": " set", "probability": 0.88818359375 }, { "start": 927.73, "end": 927.83, "word": " it", "probability": 0.8994140625 }, { "start": 927.83, "end": 927.97, "word": " to", "probability": 0.900390625 }, { "start": 927.97, "end": 928.21, "word": " 1", "probability": 0.40283203125 }, { "start": 928.21, "end": 928.65, "word": ".", "probability": 0.6494140625 } ] }, { "id": 277, "seek": 93132, "start": 929.83, "end": 932.07, "text": " But we can modify that, and this will be", "tokens": [ 51164, 583, 321, 393, 16927, 300, 11, 293, 341, 486, 312, 51314 ], "temperature": 0.0, "avg_logprob": -0.17121010426933883, "compression_ratio": 1.699248120300752, "no_speech_prob": 0.0035381317138671875, "words": [ { "start": 929.83, "end": 930.27, "word": " But", "probability": 0.7724609375 }, { "start": 930.27, "end": 930.45, "word": " we", "probability": 0.8837890625 }, { "start": 930.45, "end": 930.61, "word": " can", "probability": 0.8984375 }, { "start": 930.61, "end": 930.97, "word": " modify", "probability": 0.87158203125 }, { "start": 930.97, "end": 931.33, "word": " that", "probability": 0.8828125 }, { "start": 931.33, "end": 931.47, "word": ",", "probability": 0.5634765625 }, { "start": 931.47, "end": 931.51, "word": " and", "probability": 0.89453125 }, { "start": 931.51, "end": 931.67, "word": " this", "probability": 0.8720703125 }, { "start": 931.67, "end": 931.77, "word": " will", "probability": 0.701171875 }, { "start": 931.77, "end": 932.07, "word": " be", "probability": 0.8974609375 } ] }, { "id": 278, "seek": 93132, "start": 933.13, "end": 934.83, "text": " a hyperparameter that we'll take a look at", "tokens": [ 51314, 257, 9848, 2181, 335, 2398, 300, 321, 603, 747, 257, 574, 412, 51464 ], "temperature": 0.0, "avg_logprob": -0.17121010426933883, "compression_ratio": 1.699248120300752, "no_speech_prob": 0.0035381317138671875, "words": [ { "start": 933.13, "end": 933.57, "word": " a hyperparameter", "probability": 0.8984375 }, { "start": 933.57, "end": 934.01, "word": " that", "probability": 0.83935546875 }, { "start": 934.01, "end": 934.11, "word": " we'll", "probability": 0.916015625 }, { "start": 934.11, "end": 934.31, "word": " take", "probability": 0.806640625 }, { "start": 934.43, "end": 934.57, "word": " a look", "probability": 0.9169921875 }, { "start": 934.57, "end": 934.83, "word": " at", "probability": 0.90966796875 } ] }, { "id": 279, "seek": 93132, "start": 934.83, "end": 936.43, "text": " later in our workbook.", "tokens": [ 51464, 1780, 294, 527, 589, 2939, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.17121010426933883, "compression_ratio": 1.699248120300752, "no_speech_prob": 0.0035381317138671875, "words": [ { "start": 934.83, "end": 935.33, "word": " later", "probability": 0.88037109375 }, { "start": 935.33, "end": 935.49, "word": " in", "probability": 0.9013671875 }, { "start": 935.49, "end": 935.61, "word": " our", "probability": 0.80126953125 }, { "start": 935.61, "end": 935.99, "word": " workbook", "probability": 0.89404296875 }, { "start": 935.99, "end": 936.43, "word": ".", "probability": 0.99267578125 } ] }, { "id": 280, "seek": 93132, "start": 938.59, "end": 940.55, "text": " So with the smoothing filter,", "tokens": [ 51614, 407, 365, 264, 899, 6259, 571, 6608, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.17121010426933883, "compression_ratio": 1.699248120300752, "no_speech_prob": 0.0035381317138671875, "words": [ { "start": 938.59, "end": 939.03, "word": " So", "probability": 0.8203125 }, { "start": 939.03, "end": 939.37, "word": " with", "probability": 0.66650390625 }, { "start": 939.37, "end": 939.51, "word": " the", "probability": 0.7548828125 }, { "start": 939.51, "end": 939.83, "word": " smoothing", "probability": 0.9098307291666666 }, { "start": 939.83, "end": 940.19, "word": " filter", "probability": 0.90771484375 }, { "start": 940.19, "end": 940.55, "word": ",", "probability": 0.9013671875 } ] }, { "id": 281, "seek": 93132, "start": 940.55, "end": 942.25, "text": " we do the exact same word counting.", "tokens": [ 51714, 321, 360, 264, 1900, 912, 1349, 13251, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.17121010426933883, "compression_ratio": 1.699248120300752, "no_speech_prob": 0.0035381317138671875, "words": [ { "start": 940.55, "end": 940.93, "word": " we", "probability": 0.89501953125 }, { "start": 940.93, "end": 941.05, "word": " do", "probability": 0.853515625 }, { "start": 941.05, "end": 941.17, "word": " the", "probability": 0.81005859375 }, { "start": 941.17, "end": 941.43, "word": " exact", "probability": 0.859375 }, { "start": 941.43, "end": 941.67, "word": " same", "probability": 0.82275390625 }, { "start": 941.67, "end": 941.87, "word": " word", "probability": 0.8271484375 }, { "start": 941.87, "end": 942.13, "word": " counting", "probability": 0.66357421875 }, { "start": 942.13, "end": 942.25, "word": ".", "probability": 0.73876953125 } ] }, { "id": 282, "seek": 96010, "start": 942.25, "end": 943.75, "text": " We see A showed up twice in sports.", "tokens": [ 50364, 492, 536, 316, 4712, 493, 6091, 294, 6573, 13, 50414 ], "temperature": 0.0, "avg_logprob": -0.19312959547866793, "compression_ratio": 1.7870722433460076, "no_speech_prob": 0.0027141571044921875, "words": [ { "start": 942.25, "end": 942.31, "word": " We", "probability": 0.444091796875 }, { "start": 942.31, "end": 942.47, "word": " see", "probability": 0.7900390625 }, { "start": 942.47, "end": 942.65, "word": " A", "probability": 0.464111328125 }, { "start": 942.65, "end": 942.83, "word": " showed", "probability": 0.8046875 }, { "start": 942.83, "end": 942.95, "word": " up", "probability": 0.91455078125 }, { "start": 942.95, "end": 943.19, "word": " twice", "probability": 0.82666015625 }, { "start": 943.19, "end": 943.37, "word": " in", "probability": 0.8974609375 }, { "start": 943.37, "end": 943.61, "word": " sports", "probability": 0.63671875 }, { "start": 943.61, "end": 943.75, "word": ".", "probability": 0.30419921875 } ] }, { "id": 283, "seek": 96010, "start": 943.75, "end": 945.07, "text": " Very showed up once in sports.", "tokens": [ 50414, 4372, 4712, 493, 1564, 294, 6573, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.19312959547866793, "compression_ratio": 1.7870722433460076, "no_speech_prob": 0.0027141571044921875, "words": [ { "start": 943.75, "end": 943.87, "word": " Very", "probability": 0.48486328125 }, { "start": 943.87, "end": 944.07, "word": " showed", "probability": 0.6982421875 }, { "start": 944.07, "end": 944.21, "word": " up", "probability": 0.9208984375 }, { "start": 944.21, "end": 944.41, "word": " once", "probability": 0.806640625 }, { "start": 944.41, "end": 944.59, "word": " in", "probability": 0.900390625 }, { "start": 944.59, "end": 944.91, "word": " sports", "probability": 0.76416015625 }, { "start": 944.91, "end": 945.07, "word": ".", "probability": 0.85009765625 } ] }, { "id": 284, "seek": 96010, "start": 945.07, "end": 946.21, "text": " Close, zero.", "tokens": [ 50514, 16346, 11, 4018, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.19312959547866793, "compression_ratio": 1.7870722433460076, "no_speech_prob": 0.0027141571044921875, "words": [ { "start": 945.07, "end": 945.33, "word": " Close", "probability": 0.91015625 }, { "start": 945.33, "end": 945.45, "word": ",", "probability": 0.60595703125 }, { "start": 945.45, "end": 945.81, "word": " zero", "probability": 0.71826171875 }, { "start": 945.81, "end": 946.21, "word": ".", "probability": 0.9423828125 } ] }, { "id": 285, "seek": 96010, "start": 946.65, "end": 948.61, "text": " Game showed up twice in sports.", "tokens": [ 50564, 7522, 4712, 493, 6091, 294, 6573, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.19312959547866793, "compression_ratio": 1.7870722433460076, "no_speech_prob": 0.0027141571044921875, "words": [ { "start": 946.65, "end": 947.05, "word": " Game", "probability": 0.7744140625 }, { "start": 947.05, "end": 947.27, "word": " showed", "probability": 0.79736328125 }, { "start": 947.27, "end": 947.39, "word": " up", "probability": 0.9150390625 }, { "start": 947.39, "end": 947.63, "word": " twice", "probability": 0.85986328125 }, { "start": 947.63, "end": 947.81, "word": " in", "probability": 0.90576171875 }, { "start": 947.81, "end": 948.21, "word": " sports", "probability": 0.78271484375 }, { "start": 948.21, "end": 948.61, "word": ".", "probability": 0.8876953125 } ] }, { "id": 286, "seek": 96010, "start": 948.65, "end": 950.59, "text": " And then we do the same thing for not sports.", "tokens": [ 50664, 400, 550, 321, 360, 264, 912, 551, 337, 406, 6573, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.19312959547866793, "compression_ratio": 1.7870722433460076, "no_speech_prob": 0.0027141571044921875, "words": [ { "start": 948.65, "end": 948.73, "word": " And", "probability": 0.7177734375 }, { "start": 948.73, "end": 948.81, "word": " then", "probability": 0.70068359375 }, { "start": 948.81, "end": 948.87, "word": " we", "probability": 0.88671875 }, { "start": 948.87, "end": 948.97, "word": " do", "probability": 0.88330078125 }, { "start": 948.97, "end": 949.11, "word": " the", "probability": 0.81201171875 }, { "start": 949.11, "end": 949.27, "word": " same", "probability": 0.814453125 }, { "start": 949.27, "end": 949.45, "word": " thing", "probability": 0.8037109375 }, { "start": 949.45, "end": 949.61, "word": " for", "probability": 0.8994140625 }, { "start": 949.61, "end": 949.83, "word": " not", "probability": 0.72314453125 }, { "start": 949.83, "end": 950.19, "word": " sports", "probability": 0.72021484375 }, { "start": 950.19, "end": 950.59, "word": ".", "probability": 0.7509765625 } ] }, { "id": 287, "seek": 96010, "start": 950.81, "end": 953.53, "text": " But you see here where it says close for sports?", "tokens": [ 50764, 583, 291, 536, 510, 689, 309, 1619, 1998, 337, 6573, 30, 50914 ], "temperature": 0.0, "avg_logprob": -0.19312959547866793, "compression_ratio": 1.7870722433460076, "no_speech_prob": 0.0027141571044921875, "words": [ { "start": 950.81, "end": 951.03, "word": " But", "probability": 0.85986328125 }, { "start": 951.03, "end": 951.15, "word": " you", "probability": 0.888671875 }, { "start": 951.15, "end": 951.29, "word": " see", "probability": 0.814453125 }, { "start": 951.29, "end": 951.45, "word": " here", "probability": 0.80615234375 }, { "start": 951.45, "end": 951.57, "word": " where", "probability": 0.8662109375 }, { "start": 951.57, "end": 951.69, "word": " it", "probability": 0.9052734375 }, { "start": 951.69, "end": 951.85, "word": " says", "probability": 0.77392578125 }, { "start": 951.85, "end": 952.27, "word": " close", "probability": 0.6826171875 }, { "start": 952.27, "end": 952.63, "word": " for", "probability": 0.87255859375 }, { "start": 952.63, "end": 953.13, "word": " sports", "probability": 0.78369140625 }, { "start": 953.13, "end": 953.53, "word": "?", "probability": 0.384521484375 } ] }, { "id": 288, "seek": 96010, "start": 953.83, "end": 955.59, "text": " That smoothing filter makes it so that", "tokens": [ 50914, 663, 899, 6259, 571, 6608, 1669, 309, 370, 300, 51014 ], "temperature": 0.0, "avg_logprob": -0.19312959547866793, "compression_ratio": 1.7870722433460076, "no_speech_prob": 0.0027141571044921875, "words": [ { "start": 953.83, "end": 954.23, "word": " That", "probability": 0.802734375 }, { "start": 954.23, "end": 954.59, "word": " smoothing", "probability": 0.9051106770833334 }, { "start": 954.59, "end": 954.91, "word": " filter", "probability": 0.908203125 }, { "start": 954.91, "end": 955.13, "word": " makes", "probability": 0.73095703125 }, { "start": 955.13, "end": 955.25, "word": " it", "probability": 0.89794921875 }, { "start": 955.25, "end": 955.39, "word": " so", "probability": 0.8828125 }, { "start": 955.39, "end": 955.59, "word": " that", "probability": 0.87353515625 } ] }, { "id": 289, "seek": 96010, "start": 955.59, "end": 958.71, "text": " that number never becomes zero.", "tokens": [ 51014, 300, 1230, 1128, 3643, 4018, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.19312959547866793, "compression_ratio": 1.7870722433460076, "no_speech_prob": 0.0027141571044921875, "words": [ { "start": 955.59, "end": 955.75, "word": " that", "probability": 0.498291015625 }, { "start": 955.75, "end": 956.45, "word": " number", "probability": 0.7705078125 }, { "start": 956.45, "end": 956.89, "word": " never", "probability": 0.86376953125 }, { "start": 956.89, "end": 957.63, "word": " becomes", "probability": 0.77783203125 }, { "start": 957.63, "end": 958.31, "word": " zero", "probability": 0.81787109375 }, { "start": 958.31, "end": 958.71, "word": ".", "probability": 0.92431640625 } ] }, { "id": 290, "seek": 96010, "start": 958.81, "end": 960.81, "text": " It's always greater than zero.", "tokens": [ 51164, 467, 311, 1009, 5044, 813, 4018, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.19312959547866793, "compression_ratio": 1.7870722433460076, "no_speech_prob": 0.0027141571044921875, "words": [ { "start": 958.81, "end": 959.09, "word": " It's", "probability": 0.9501953125 }, { "start": 959.09, "end": 959.39, "word": " always", "probability": 0.77880859375 }, { "start": 959.39, "end": 959.85, "word": " greater", "probability": 0.84716796875 }, { "start": 959.85, "end": 960.09, "word": " than", "probability": 0.875 }, { "start": 960.09, "end": 960.45, "word": " zero", "probability": 0.8232421875 }, { "start": 960.45, "end": 960.81, "word": ".", "probability": 0.82275390625 } ] }, { "id": 291, "seek": 96010, "start": 960.81, "end": 963.09, "text": " So our probabilities will always fit.", "tokens": [ 51264, 407, 527, 33783, 486, 1009, 3318, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.19312959547866793, "compression_ratio": 1.7870722433460076, "no_speech_prob": 0.0027141571044921875, "words": [ { "start": 960.81, "end": 960.91, "word": " So", "probability": 0.8427734375 }, { "start": 960.91, "end": 961.07, "word": " our", "probability": 0.771484375 }, { "start": 961.07, "end": 961.61, "word": " probabilities", "probability": 0.81689453125 }, { "start": 961.61, "end": 962.19, "word": " will", "probability": 0.8203125 }, { "start": 962.19, "end": 962.47, "word": " always", "probability": 0.7802734375 }, { "start": 962.47, "end": 962.69, "word": " fit", "probability": 0.87890625 }, { "start": 962.69, "end": 963.09, "word": ".", "probability": 0.98388671875 } ] }, { "id": 292, "seek": 96010, "start": 963.53, "end": 965.09, "text": " And then this is just simple addition", "tokens": [ 51414, 400, 550, 341, 307, 445, 2199, 4500, 51514 ], "temperature": 0.0, "avg_logprob": -0.19312959547866793, "compression_ratio": 1.7870722433460076, "no_speech_prob": 0.0027141571044921875, "words": [ { "start": 963.53, "end": 963.71, "word": " And", "probability": 0.875 }, { "start": 963.71, "end": 963.81, "word": " then", "probability": 0.71923828125 }, { "start": 963.81, "end": 963.97, "word": " this", "probability": 0.87646484375 }, { "start": 963.97, "end": 964.07, "word": " is", "probability": 0.908203125 }, { "start": 964.07, "end": 964.21, "word": " just", "probability": 0.896484375 }, { "start": 964.21, "end": 964.59, "word": " simple", "probability": 0.884765625 }, { "start": 964.59, "end": 965.09, "word": " addition", "probability": 0.87548828125 } ] }, { "id": 293, "seek": 96010, "start": 965.09, "end": 966.45, "text": " and then division.", "tokens": [ 51514, 293, 550, 10044, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.19312959547866793, "compression_ratio": 1.7870722433460076, "no_speech_prob": 0.0027141571044921875, "words": [ { "start": 965.09, "end": 965.43, "word": " and", "probability": 0.74267578125 }, { "start": 965.43, "end": 965.63, "word": " then", "probability": 0.70068359375 }, { "start": 965.63, "end": 966.05, "word": " division", "probability": 0.85888671875 }, { "start": 966.05, "end": 966.45, "word": ".", "probability": 0.95361328125 } ] }, { "id": 294, "seek": 96010, "start": 967.45, "end": 969.49, "text": " And if we took out a calculator,", "tokens": [ 51614, 400, 498, 321, 1890, 484, 257, 24993, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.19312959547866793, "compression_ratio": 1.7870722433460076, "no_speech_prob": 0.0027141571044921875, "words": [ { "start": 967.45, "end": 967.81, "word": " And", "probability": 0.8740234375 }, { "start": 967.81, "end": 967.99, "word": " if", "probability": 0.89892578125 }, { "start": 967.99, "end": 968.27, "word": " we", "probability": 0.90087890625 }, { "start": 968.27, "end": 968.73, "word": " took", "probability": 0.85546875 }, { "start": 968.73, "end": 968.85, "word": " out", "probability": 0.81787109375 }, { "start": 968.95, "end": 969.29, "word": " a calculator", "probability": 0.8662109375 }, { "start": 969.29, "end": 969.49, "word": ",", "probability": 0.884765625 } ] }, { "id": 295, "seek": 96010, "start": 969.49, "end": 971.03, "text": " did all our math, we can see that", "tokens": [ 51714, 630, 439, 527, 5221, 11, 321, 393, 536, 300, 51814 ], "temperature": 0.0, "avg_logprob": -0.19312959547866793, "compression_ratio": 1.7870722433460076, "no_speech_prob": 0.0027141571044921875, "words": [ { "start": 969.49, "end": 969.61, "word": " did", "probability": 0.8955078125 }, { "start": 969.61, "end": 969.73, "word": " all", "probability": 0.8955078125 }, { "start": 969.73, "end": 969.83, "word": " our", "probability": 0.2529296875 }, { "start": 969.83, "end": 970.11, "word": " math", "probability": 0.8876953125 }, { "start": 970.11, "end": 970.19, "word": ",", "probability": 0.89404296875 }, { "start": 970.19, "end": 970.29, "word": " we", "probability": 0.89892578125 }, { "start": 970.29, "end": 970.45, "word": " can", "probability": 0.8916015625 }, { "start": 970.45, "end": 970.71, "word": " see", "probability": 0.82470703125 }, { "start": 970.71, "end": 971.03, "word": " that", "probability": 0.880859375 } ] }, { "id": 296, "seek": 98504, "start": 971.65, "end": 976.41, "text": " AVeryCloseGame has a probability of .0000461", "tokens": [ 50364, 316, 31733, 9966, 541, 32700, 575, 257, 8482, 295, 2411, 33202, 16169, 16, 50614 ], "temperature": 0.0, "avg_logprob": -0.21857829703079476, "compression_ratio": 1.8, "no_speech_prob": 0.035675048828125, "words": [ { "start": 971.65, "end": 972.21, "word": " AVeryCloseGame", "probability": 0.588519287109375 }, { "start": 972.21, "end": 972.63, "word": " has", "probability": 0.6689453125 }, { "start": 972.75, "end": 973.19, "word": " a probability", "probability": 0.88525390625 }, { "start": 973.19, "end": 973.65, "word": " of", "probability": 0.8310546875 }, { "start": 973.65, "end": 976.41, "word": " .0000461", "probability": 0.8359375 } ] }, { "id": 297, "seek": 98504, "start": 976.41, "end": 978.81, "text": " that it's talking about sports.", "tokens": [ 50614, 300, 309, 311, 1417, 466, 6573, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.21857829703079476, "compression_ratio": 1.8, "no_speech_prob": 0.035675048828125, "words": [ { "start": 976.41, "end": 977.09, "word": " that", "probability": 0.62646484375 }, { "start": 977.09, "end": 977.23, "word": " it's", "probability": 0.895751953125 }, { "start": 977.23, "end": 977.47, "word": " talking", "probability": 0.77734375 }, { "start": 977.47, "end": 977.71, "word": " about", "probability": 0.80859375 }, { "start": 977.71, "end": 978.25, "word": " sports", "probability": 0.6357421875 }, { "start": 978.25, "end": 978.81, "word": ".", "probability": 0.407958984375 } ] }, { "id": 298, "seek": 98504, "start": 978.81, "end": 980.77, "text": " And then AVeryCloseGame has a probability of", "tokens": [ 50714, 400, 550, 316, 31733, 9966, 541, 32700, 575, 257, 8482, 295, 50814 ], "temperature": 0.0, "avg_logprob": -0.21857829703079476, "compression_ratio": 1.8, "no_speech_prob": 0.035675048828125, "words": [ { "start": 978.81, "end": 978.83, "word": " And", "probability": 0.371826171875 }, { "start": 978.83, "end": 979.05, "word": " then", "probability": 0.489990234375 }, { "start": 979.05, "end": 979.87, "word": " AVeryCloseGame", "probability": 0.89677734375 }, { "start": 979.87, "end": 980.09, "word": " has", "probability": 0.90380859375 }, { "start": 980.23, "end": 980.53, "word": " a probability", "probability": 0.8916015625 }, { "start": 980.53, "end": 980.77, "word": " of", "probability": 0.8935546875 } ] }, { "id": 299, "seek": 98504, "start": 982.53, "end": 985.79, "text": " 0000143 that it's talking about not sports.", "tokens": [ 50814, 7143, 628, 7271, 18, 300, 309, 311, 1417, 466, 406, 6573, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.21857829703079476, "compression_ratio": 1.8, "no_speech_prob": 0.035675048828125, "words": [ { "start": 982.53, "end": 983.09, "word": " 0000143", "probability": 0.784423828125 }, { "start": 983.09, "end": 983.61, "word": " that", "probability": 0.80859375 }, { "start": 983.61, "end": 983.75, "word": " it's", "probability": 0.942138671875 }, { "start": 983.75, "end": 983.99, "word": " talking", "probability": 0.76708984375 }, { "start": 983.99, "end": 984.31, "word": " about", "probability": 0.8310546875 }, { "start": 984.31, "end": 984.81, "word": " not", "probability": 0.77001953125 }, { "start": 984.81, "end": 985.23, "word": " sports", "probability": 0.71826171875 }, { "start": 985.23, "end": 985.79, "word": ".", "probability": 0.98046875 } ] }, { "id": 300, "seek": 98504, "start": 985.97, "end": 987.25, "text": " So we take whichever is higher,", "tokens": [ 51064, 407, 321, 747, 24123, 307, 2946, 11, 51164 ], "temperature": 0.0, "avg_logprob": -0.21857829703079476, "compression_ratio": 1.8, "no_speech_prob": 0.035675048828125, "words": [ { "start": 985.97, "end": 986.15, "word": " So", "probability": 0.7607421875 }, { "start": 986.15, "end": 986.23, "word": " we", "probability": 0.85888671875 }, { "start": 986.23, "end": 986.41, "word": " take", "probability": 0.8046875 }, { "start": 986.41, "end": 986.61, "word": " whichever", "probability": 0.84912109375 }, { "start": 986.61, "end": 986.81, "word": " is", "probability": 0.60107421875 }, { "start": 986.81, "end": 987.07, "word": " higher", "probability": 0.84326171875 }, { "start": 987.07, "end": 987.25, "word": ",", "probability": 0.76025390625 } ] }, { "id": 301, "seek": 98504, "start": 987.25, "end": 989.27, "text": " in this case sports, and so our classifier", "tokens": [ 51164, 294, 341, 1389, 6573, 11, 293, 370, 527, 1508, 9902, 51264 ], "temperature": 0.0, "avg_logprob": -0.21857829703079476, "compression_ratio": 1.8, "no_speech_prob": 0.035675048828125, "words": [ { "start": 987.25, "end": 987.33, "word": " in", "probability": 0.89697265625 }, { "start": 987.33, "end": 987.49, "word": " this", "probability": 0.88134765625 }, { "start": 987.49, "end": 987.71, "word": " case", "probability": 0.8046875 }, { "start": 987.71, "end": 988.15, "word": " sports", "probability": 0.5546875 }, { "start": 988.15, "end": 988.41, "word": ",", "probability": 0.55859375 }, { "start": 988.41, "end": 988.49, "word": " and", "probability": 0.8466796875 }, { "start": 988.49, "end": 988.75, "word": " so", "probability": 0.85791015625 }, { "start": 988.75, "end": 988.99, "word": " our", "probability": 0.82470703125 }, { "start": 988.99, "end": 989.27, "word": " classifier", "probability": 0.9599609375 } ] }, { "id": 302, "seek": 98504, "start": 990.79, "end": 993.51, "text": " has decided that AVeryCloseGame", "tokens": [ 51264, 575, 3047, 300, 316, 31733, 9966, 541, 32700, 51464 ], "temperature": 0.0, "avg_logprob": -0.21857829703079476, "compression_ratio": 1.8, "no_speech_prob": 0.035675048828125, "words": [ { "start": 990.79, "end": 991.35, "word": " has", "probability": 0.892578125 }, { "start": 991.35, "end": 991.91, "word": " decided", "probability": 0.880859375 }, { "start": 991.91, "end": 992.47, "word": " that", "probability": 0.87841796875 }, { "start": 992.47, "end": 993.51, "word": " AVeryCloseGame", "probability": 0.92060546875 } ] }, { "id": 303, "seek": 98504, "start": 993.51, "end": 995.97, "text": " is talking about sports.", "tokens": [ 51464, 307, 1417, 466, 6573, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.21857829703079476, "compression_ratio": 1.8, "no_speech_prob": 0.035675048828125, "words": [ { "start": 993.51, "end": 994.09, "word": " is", "probability": 0.8662109375 }, { "start": 994.09, "end": 994.33, "word": " talking", "probability": 0.76953125 }, { "start": 994.33, "end": 994.63, "word": " about", "probability": 0.822265625 }, { "start": 994.63, "end": 995.41, "word": " sports", "probability": 0.75732421875 }, { "start": 995.41, "end": 995.97, "word": ".", "probability": 0.98388671875 } ] }, { "id": 304, "seek": 101250, "start": 999.43, "end": 1001.67, "text": " So I know that was a lot of information.", "tokens": [ 50414, 407, 286, 458, 300, 390, 257, 688, 295, 1589, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.18898167807994218, "compression_ratio": 1.724890829694323, "no_speech_prob": 0.020965576171875, "words": [ { "start": 999.43, "end": 999.83, "word": " So", "probability": 0.4609375 }, { "start": 999.83, "end": 1000.23, "word": " I", "probability": 0.6181640625 }, { "start": 1000.23, "end": 1000.33, "word": " know", "probability": 0.826171875 }, { "start": 1000.33, "end": 1000.41, "word": " that", "probability": 0.63330078125 }, { "start": 1000.41, "end": 1000.53, "word": " was", "probability": 0.8603515625 }, { "start": 1000.63, "end": 1000.73, "word": " a lot", "probability": 0.9013671875 }, { "start": 1000.73, "end": 1000.83, "word": " of", "probability": 0.89990234375 }, { "start": 1000.83, "end": 1001.27, "word": " information", "probability": 0.74755859375 }, { "start": 1001.27, "end": 1001.67, "word": ".", "probability": 0.744140625 } ] }, { "id": 305, "seek": 101250, "start": 1001.93, "end": 1003.69, "text": " Let me know if there's any questions.", "tokens": [ 50614, 961, 385, 458, 498, 456, 311, 604, 1651, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.18898167807994218, "compression_ratio": 1.724890829694323, "no_speech_prob": 0.020965576171875, "words": [ { "start": 1001.93, "end": 1002.33, "word": " Let", "probability": 0.87158203125 }, { "start": 1002.33, "end": 1002.41, "word": " me", "probability": 0.9013671875 }, { "start": 1002.41, "end": 1002.51, "word": " know", "probability": 0.81591796875 }, { "start": 1002.51, "end": 1002.61, "word": " if", "probability": 0.90478515625 }, { "start": 1002.61, "end": 1002.75, "word": " there's", "probability": 0.898681640625 }, { "start": 1002.75, "end": 1002.89, "word": " any", "probability": 0.81298828125 }, { "start": 1002.89, "end": 1003.29, "word": " questions", "probability": 0.90576171875 }, { "start": 1003.29, "end": 1003.69, "word": ".", "probability": 0.93701171875 } ] }, { "id": 306, "seek": 101250, "start": 1004.09, "end": 1007.29, "text": " I'm going to kind of hop forward a little bit,", "tokens": [ 50714, 286, 478, 516, 281, 733, 295, 3818, 2128, 257, 707, 857, 11, 50864 ], "temperature": 0.0, "avg_logprob": -0.18898167807994218, "compression_ratio": 1.724890829694323, "no_speech_prob": 0.020965576171875, "words": [ { "start": 1004.09, "end": 1004.23, "word": " I'm", "probability": 0.99462890625 }, { "start": 1004.23, "end": 1004.35, "word": " going", "probability": 0.324951171875 }, { "start": 1004.35, "end": 1004.85, "word": " to", "probability": 0.90087890625 }, { "start": 1004.85, "end": 1005.11, "word": " kind", "probability": 0.6611328125 }, { "start": 1005.11, "end": 1005.29, "word": " of", "probability": 0.90625 }, { "start": 1005.29, "end": 1005.97, "word": " hop", "probability": 0.9169921875 }, { "start": 1005.97, "end": 1006.27, "word": " forward", "probability": 0.8330078125 }, { "start": 1006.39, "end": 1006.53, "word": " a little", "probability": 0.8046875 }, { "start": 1006.53, "end": 1006.81, "word": " bit", "probability": 0.90576171875 }, { "start": 1006.81, "end": 1007.29, "word": ",", "probability": 0.58154296875 } ] }, { "id": 307, "seek": 101250, "start": 1007.29, "end": 1009.45, "text": " but TAs, feel free to chime in", "tokens": [ 50864, 457, 314, 10884, 11, 841, 1737, 281, 40921, 294, 51014 ], "temperature": 0.0, "avg_logprob": -0.18898167807994218, "compression_ratio": 1.724890829694323, "no_speech_prob": 0.020965576171875, "words": [ { "start": 1007.29, "end": 1007.49, "word": " but", "probability": 0.888671875 }, { "start": 1007.49, "end": 1008.15, "word": " TAs", "probability": 0.865478515625 }, { "start": 1008.15, "end": 1008.25, "word": ",", "probability": 0.53857421875 }, { "start": 1008.25, "end": 1008.35, "word": " feel", "probability": 0.912109375 }, { "start": 1008.35, "end": 1008.55, "word": " free", "probability": 0.85693359375 }, { "start": 1008.55, "end": 1008.83, "word": " to", "probability": 0.90869140625 }, { "start": 1008.83, "end": 1009.31, "word": " chime", "probability": 0.87451171875 }, { "start": 1009.31, "end": 1009.45, "word": " in", "probability": 0.90673828125 } ] }, { "id": 308, "seek": 101250, "start": 1009.45, "end": 1011.13, "text": " if there's any questions on this.", "tokens": [ 51014, 498, 456, 311, 604, 1651, 322, 341, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.18898167807994218, "compression_ratio": 1.724890829694323, "no_speech_prob": 0.020965576171875, "words": [ { "start": 1009.45, "end": 1009.57, "word": " if", "probability": 0.87890625 }, { "start": 1009.57, "end": 1009.73, "word": " there's", "probability": 0.9169921875 }, { "start": 1009.73, "end": 1009.87, "word": " any", "probability": 0.81396484375 }, { "start": 1009.87, "end": 1010.23, "word": " questions", "probability": 0.900390625 }, { "start": 1010.23, "end": 1010.47, "word": " on", "probability": 0.9052734375 }, { "start": 1010.47, "end": 1010.73, "word": " this", "probability": 0.880859375 }, { "start": 1010.73, "end": 1011.13, "word": ".", "probability": 0.99462890625 } ] }, { "id": 309, "seek": 101250, "start": 1011.17, "end": 1013.99, "text": " I know this bit's a little confusing sometimes,", "tokens": [ 51114, 286, 458, 341, 857, 311, 257, 707, 13181, 2171, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.18898167807994218, "compression_ratio": 1.724890829694323, "no_speech_prob": 0.020965576171875, "words": [ { "start": 1011.17, "end": 1011.25, "word": " I", "probability": 0.99072265625 }, { "start": 1011.25, "end": 1011.35, "word": " know", "probability": 0.82470703125 }, { "start": 1011.35, "end": 1011.61, "word": " this", "probability": 0.83544921875 }, { "start": 1011.61, "end": 1011.87, "word": " bit's", "probability": 0.820068359375 }, { "start": 1011.99, "end": 1012.19, "word": " a little", "probability": 0.8037109375 }, { "start": 1012.19, "end": 1012.91, "word": " confusing", "probability": 0.92919921875 }, { "start": 1012.91, "end": 1013.49, "word": " sometimes", "probability": 0.8984375 }, { "start": 1013.49, "end": 1013.99, "word": ",", "probability": 0.89794921875 } ] }, { "id": 310, "seek": 101250, "start": 1013.99, "end": 1016.11, "text": " but it's not something we need to harp on too much.", "tokens": [ 51214, 457, 309, 311, 406, 746, 321, 643, 281, 50093, 322, 886, 709, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.18898167807994218, "compression_ratio": 1.724890829694323, "no_speech_prob": 0.020965576171875, "words": [ { "start": 1013.99, "end": 1014.23, "word": " but", "probability": 0.90185546875 }, { "start": 1014.23, "end": 1014.45, "word": " it's", "probability": 0.953125 }, { "start": 1014.45, "end": 1014.61, "word": " not", "probability": 0.89599609375 }, { "start": 1014.61, "end": 1014.83, "word": " something", "probability": 0.72998046875 }, { "start": 1014.83, "end": 1014.97, "word": " we", "probability": 0.89990234375 }, { "start": 1014.97, "end": 1015.09, "word": " need", "probability": 0.7978515625 }, { "start": 1015.09, "end": 1015.21, "word": " to", "probability": 0.888671875 }, { "start": 1015.21, "end": 1015.41, "word": " harp", "probability": 0.80078125 }, { "start": 1015.41, "end": 1015.59, "word": " on", "probability": 0.89697265625 }, { "start": 1015.59, "end": 1015.79, "word": " too", "probability": 0.80615234375 }, { "start": 1015.79, "end": 1016.05, "word": " much", "probability": 0.80712890625 }, { "start": 1016.05, "end": 1016.11, "word": ".", "probability": 0.88232421875 } ] }, { "id": 311, "seek": 101250, "start": 1016.11, "end": 1017.75, "text": " It's just an underlying foundation", "tokens": [ 51314, 467, 311, 445, 364, 14217, 7030, 51414 ], "temperature": 0.0, "avg_logprob": -0.18898167807994218, "compression_ratio": 1.724890829694323, "no_speech_prob": 0.020965576171875, "words": [ { "start": 1016.11, "end": 1016.29, "word": " It's", "probability": 0.95068359375 }, { "start": 1016.29, "end": 1016.51, "word": " just", "probability": 0.8876953125 }, { "start": 1016.51, "end": 1016.79, "word": " an", "probability": 0.703125 }, { "start": 1016.79, "end": 1017.13, "word": " underlying", "probability": 0.91748046875 }, { "start": 1017.13, "end": 1017.75, "word": " foundation", "probability": 0.86865234375 } ] }, { "id": 312, "seek": 101250, "start": 1017.75, "end": 1018.93, "text": " that's good to know.", "tokens": [ 51414, 300, 311, 665, 281, 458, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.18898167807994218, "compression_ratio": 1.724890829694323, "no_speech_prob": 0.020965576171875, "words": [ { "start": 1017.75, "end": 1018.03, "word": " that's", "probability": 0.918701171875 }, { "start": 1018.03, "end": 1018.17, "word": " good", "probability": 0.8740234375 }, { "start": 1018.17, "end": 1018.31, "word": " to", "probability": 0.89599609375 }, { "start": 1018.31, "end": 1018.53, "word": " know", "probability": 0.81005859375 }, { "start": 1018.53, "end": 1018.93, "word": ".", "probability": 0.99755859375 } ] }, { "id": 313, "seek": 101250, "start": 1021.45, "end": 1023.43, "text": " So the five things that we need to keep track of", "tokens": [ 51564, 407, 264, 1732, 721, 300, 321, 643, 281, 1066, 2837, 295, 51714 ], "temperature": 0.0, "avg_logprob": -0.18898167807994218, "compression_ratio": 1.724890829694323, "no_speech_prob": 0.020965576171875, "words": [ { "start": 1021.45, "end": 1021.85, "word": " So", "probability": 0.794921875 }, { "start": 1021.85, "end": 1021.95, "word": " the", "probability": 0.80029296875 }, { "start": 1021.95, "end": 1022.13, "word": " five", "probability": 0.7744140625 }, { "start": 1022.13, "end": 1022.33, "word": " things", "probability": 0.73388671875 }, { "start": 1022.33, "end": 1022.45, "word": " that", "probability": 0.8720703125 }, { "start": 1022.45, "end": 1022.53, "word": " we", "probability": 0.904296875 }, { "start": 1022.53, "end": 1022.65, "word": " need", "probability": 0.80322265625 }, { "start": 1022.65, "end": 1022.75, "word": " to", "probability": 0.90966796875 }, { "start": 1022.75, "end": 1022.87, "word": " keep", "probability": 0.8134765625 }, { "start": 1022.87, "end": 1023.15, "word": " track", "probability": 0.8349609375 }, { "start": 1023.15, "end": 1023.43, "word": " of", "probability": 0.89599609375 } ] }, { "id": 314, "seek": 103938, "start": 1023.43, "end": 1026.45, "text": " in order to do our pen and pencil math", "tokens": [ 50364, 294, 1668, 281, 360, 527, 3435, 293, 10985, 5221, 50514 ], "temperature": 0.0, "avg_logprob": -0.19738248525521693, "compression_ratio": 1.9753694581280787, "no_speech_prob": 0.005641937255859375, "words": [ { "start": 1023.43, "end": 1023.69, "word": " in", "probability": 0.5302734375 }, { "start": 1023.69, "end": 1023.83, "word": " order", "probability": 0.783203125 }, { "start": 1023.83, "end": 1023.99, "word": " to", "probability": 0.8984375 }, { "start": 1023.99, "end": 1024.21, "word": " do", "probability": 0.896484375 }, { "start": 1024.21, "end": 1024.37, "word": " our", "probability": 0.77734375 }, { "start": 1024.37, "end": 1025.59, "word": " pen", "probability": 0.90625 }, { "start": 1025.59, "end": 1025.69, "word": " and", "probability": 0.83447265625 }, { "start": 1025.69, "end": 1025.91, "word": " pencil", "probability": 0.5439453125 }, { "start": 1025.91, "end": 1026.45, "word": " math", "probability": 0.837890625 } ] }, { "id": 315, "seek": 103938, "start": 1026.45, "end": 1028.33, "text": " that we did earlier, is we need to keep track", "tokens": [ 50514, 300, 321, 630, 3071, 11, 307, 321, 643, 281, 1066, 2837, 50614 ], "temperature": 0.0, "avg_logprob": -0.19738248525521693, "compression_ratio": 1.9753694581280787, "no_speech_prob": 0.005641937255859375, "words": [ { "start": 1026.45, "end": 1026.61, "word": " that", "probability": 0.81640625 }, { "start": 1026.61, "end": 1026.69, "word": " we", "probability": 0.904296875 }, { "start": 1026.69, "end": 1026.83, "word": " did", "probability": 0.892578125 }, { "start": 1026.83, "end": 1027.17, "word": " earlier", "probability": 0.89892578125 }, { "start": 1027.17, "end": 1027.45, "word": ",", "probability": 0.3984375 }, { "start": 1027.45, "end": 1027.67, "word": " is", "probability": 0.783203125 }, { "start": 1027.67, "end": 1027.77, "word": " we", "probability": 0.87548828125 }, { "start": 1027.77, "end": 1027.89, "word": " need", "probability": 0.7900390625 }, { "start": 1027.89, "end": 1027.99, "word": " to", "probability": 0.91162109375 }, { "start": 1027.99, "end": 1028.11, "word": " keep", "probability": 0.80615234375 }, { "start": 1028.11, "end": 1028.33, "word": " track", "probability": 0.833984375 } ] }, { "id": 316, "seek": 103938, "start": 1028.33, "end": 1030.59, "text": " of the total number of unique words,", "tokens": [ 50614, 295, 264, 3217, 1230, 295, 3845, 2283, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.19738248525521693, "compression_ratio": 1.9753694581280787, "no_speech_prob": 0.005641937255859375, "words": [ { "start": 1028.33, "end": 1028.47, "word": " of", "probability": 0.90576171875 }, { "start": 1028.47, "end": 1028.59, "word": " the", "probability": 0.81689453125 }, { "start": 1028.59, "end": 1028.85, "word": " total", "probability": 0.8095703125 }, { "start": 1028.85, "end": 1029.11, "word": " number", "probability": 0.88916015625 }, { "start": 1029.11, "end": 1029.31, "word": " of", "probability": 0.90869140625 }, { "start": 1029.31, "end": 1029.69, "word": " unique", "probability": 0.78173828125 }, { "start": 1029.69, "end": 1030.15, "word": " words", "probability": 0.73095703125 }, { "start": 1030.15, "end": 1030.59, "word": ",", "probability": 0.84619140625 } ] }, { "id": 317, "seek": 103938, "start": 1030.59, "end": 1032.91, "text": " the total number of words in spam,", "tokens": [ 50714, 264, 3217, 1230, 295, 2283, 294, 24028, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.19738248525521693, "compression_ratio": 1.9753694581280787, "no_speech_prob": 0.005641937255859375, "words": [ { "start": 1030.59, "end": 1030.95, "word": " the", "probability": 0.81005859375 }, { "start": 1030.95, "end": 1031.23, "word": " total", "probability": 0.80859375 }, { "start": 1031.23, "end": 1031.49, "word": " number", "probability": 0.88525390625 }, { "start": 1031.49, "end": 1031.71, "word": " of", "probability": 0.9033203125 }, { "start": 1031.71, "end": 1031.97, "word": " words", "probability": 0.736328125 }, { "start": 1031.97, "end": 1032.15, "word": " in", "probability": 0.88623046875 }, { "start": 1032.15, "end": 1032.45, "word": " spam", "probability": 0.6005859375 }, { "start": 1032.45, "end": 1032.91, "word": ",", "probability": 0.98193359375 } ] }, { "id": 318, "seek": 103938, "start": 1032.91, "end": 1035.41, "text": " the total number of words in ham,", "tokens": [ 50814, 264, 3217, 1230, 295, 2283, 294, 7852, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.19738248525521693, "compression_ratio": 1.9753694581280787, "no_speech_prob": 0.005641937255859375, "words": [ { "start": 1032.91, "end": 1033.21, "word": " the", "probability": 0.7998046875 }, { "start": 1033.21, "end": 1033.41, "word": " total", "probability": 0.8056640625 }, { "start": 1033.41, "end": 1033.67, "word": " number", "probability": 0.880859375 }, { "start": 1033.67, "end": 1033.85, "word": " of", "probability": 0.90625 }, { "start": 1033.85, "end": 1034.05, "word": " words", "probability": 0.74072265625 }, { "start": 1034.05, "end": 1034.25, "word": " in", "probability": 0.88623046875 }, { "start": 1034.25, "end": 1034.57, "word": " ham", "probability": 0.82275390625 }, { "start": 1034.57, "end": 1035.41, "word": ",", "probability": 0.619140625 } ] }, { "id": 319, "seek": 103938, "start": 1035.41, "end": 1039.87, "text": " and these two were what we've put in the denominator.", "tokens": [ 50964, 293, 613, 732, 645, 437, 321, 600, 829, 294, 264, 20687, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.19738248525521693, "compression_ratio": 1.9753694581280787, "no_speech_prob": 0.005641937255859375, "words": [ { "start": 1035.41, "end": 1035.71, "word": " and", "probability": 0.841796875 }, { "start": 1035.71, "end": 1036.07, "word": " these", "probability": 0.66552734375 }, { "start": 1036.07, "end": 1036.39, "word": " two", "probability": 0.81591796875 }, { "start": 1036.39, "end": 1036.87, "word": " were", "probability": 0.8095703125 }, { "start": 1036.87, "end": 1037.43, "word": " what", "probability": 0.87255859375 }, { "start": 1037.43, "end": 1037.65, "word": " we've", "probability": 0.824951171875 }, { "start": 1037.65, "end": 1037.97, "word": " put", "probability": 0.8994140625 }, { "start": 1037.97, "end": 1038.09, "word": " in", "probability": 0.89013671875 }, { "start": 1038.09, "end": 1038.19, "word": " the", "probability": 0.81396484375 }, { "start": 1038.19, "end": 1039.39, "word": " denominator", "probability": 0.8251953125 }, { "start": 1039.39, "end": 1039.87, "word": ".", "probability": 0.50634765625 } ] }, { "id": 320, "seek": 103938, "start": 1040.45, "end": 1042.53, "text": " The count of each word in spam", "tokens": [ 51214, 440, 1207, 295, 1184, 1349, 294, 24028, 51314 ], "temperature": 0.0, "avg_logprob": -0.19738248525521693, "compression_ratio": 1.9753694581280787, "no_speech_prob": 0.005641937255859375, "words": [ { "start": 1040.45, "end": 1040.93, "word": " The", "probability": 0.79150390625 }, { "start": 1040.93, "end": 1041.33, "word": " count", "probability": 0.80126953125 }, { "start": 1041.33, "end": 1041.57, "word": " of", "probability": 0.90625 }, { "start": 1041.57, "end": 1041.81, "word": " each", "probability": 0.8720703125 }, { "start": 1041.81, "end": 1042.05, "word": " word", "probability": 0.8115234375 }, { "start": 1042.05, "end": 1042.21, "word": " in", "probability": 0.884765625 }, { "start": 1042.21, "end": 1042.53, "word": " spam", "probability": 0.912109375 } ] }, { "id": 321, "seek": 103938, "start": 1042.53, "end": 1044.49, "text": " and the count of each word in ham.", "tokens": [ 51314, 293, 264, 1207, 295, 1184, 1349, 294, 7852, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.19738248525521693, "compression_ratio": 1.9753694581280787, "no_speech_prob": 0.005641937255859375, "words": [ { "start": 1042.53, "end": 1043.11, "word": " and", "probability": 0.6279296875 }, { "start": 1043.11, "end": 1043.23, "word": " the", "probability": 0.8173828125 }, { "start": 1043.23, "end": 1043.51, "word": " count", "probability": 0.78662109375 }, { "start": 1043.51, "end": 1043.65, "word": " of", "probability": 0.9033203125 }, { "start": 1043.65, "end": 1043.81, "word": " each", "probability": 0.8740234375 }, { "start": 1043.81, "end": 1044.03, "word": " word", "probability": 0.81103515625 }, { "start": 1044.03, "end": 1044.17, "word": " in", "probability": 0.8798828125 }, { "start": 1044.17, "end": 1044.37, "word": " ham", "probability": 0.8134765625 }, { "start": 1044.37, "end": 1044.49, "word": ".", "probability": 0.7607421875 } ] }, { "id": 322, "seek": 103938, "start": 1044.49, "end": 1047.23, "text": " So this is where we had to count the word A,", "tokens": [ 51414, 407, 341, 307, 689, 321, 632, 281, 1207, 264, 1349, 316, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.19738248525521693, "compression_ratio": 1.9753694581280787, "no_speech_prob": 0.005641937255859375, "words": [ { "start": 1044.49, "end": 1044.57, "word": " So", "probability": 0.7294921875 }, { "start": 1044.57, "end": 1044.71, "word": " this", "probability": 0.79931640625 }, { "start": 1044.71, "end": 1044.81, "word": " is", "probability": 0.90283203125 }, { "start": 1044.81, "end": 1044.93, "word": " where", "probability": 0.908203125 }, { "start": 1044.93, "end": 1045.03, "word": " we", "probability": 0.904296875 }, { "start": 1045.03, "end": 1045.17, "word": " had", "probability": 0.80908203125 }, { "start": 1045.17, "end": 1045.33, "word": " to", "probability": 0.9033203125 }, { "start": 1045.33, "end": 1045.71, "word": " count", "probability": 0.7841796875 }, { "start": 1045.71, "end": 1046.33, "word": " the", "probability": 0.80029296875 }, { "start": 1046.33, "end": 1046.67, "word": " word", "probability": 0.8095703125 }, { "start": 1046.67, "end": 1047.01, "word": " A", "probability": 0.2392578125 }, { "start": 1047.01, "end": 1047.23, "word": ",", "probability": 0.9326171875 } ] }, { "id": 323, "seek": 103938, "start": 1047.23, "end": 1050.31, "text": " count the word very, count close, count game.", "tokens": [ 51564, 1207, 264, 1349, 588, 11, 1207, 1998, 11, 1207, 1216, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.19738248525521693, "compression_ratio": 1.9753694581280787, "no_speech_prob": 0.005641937255859375, "words": [ { "start": 1047.23, "end": 1047.47, "word": " count", "probability": 0.80029296875 }, { "start": 1047.47, "end": 1047.63, "word": " the", "probability": 0.80810546875 }, { "start": 1047.63, "end": 1047.85, "word": " word", "probability": 0.81591796875 }, { "start": 1047.85, "end": 1048.15, "word": " very", "probability": 0.6337890625 }, { "start": 1048.15, "end": 1048.39, "word": ",", "probability": 0.97314453125 }, { "start": 1048.39, "end": 1048.63, "word": " count", "probability": 0.83056640625 }, { "start": 1048.63, "end": 1049.09, "word": " close", "probability": 0.81787109375 }, { "start": 1049.09, "end": 1049.21, "word": ",", "probability": 0.97412109375 }, { "start": 1049.21, "end": 1049.47, "word": " count", "probability": 0.833984375 }, { "start": 1049.47, "end": 1049.83, "word": " game", "probability": 0.7919921875 }, { "start": 1049.83, "end": 1050.31, "word": ".", "probability": 0.81884765625 } ] }, { "id": 324, "seek": 106762, "start": 1051.29, "end": 1052.55, "text": " And so these are the five things", "tokens": [ 50414, 400, 370, 613, 366, 264, 1732, 721, 50464 ], "temperature": 0.0, "avg_logprob": -0.1788194513682163, "compression_ratio": 1.5656565656565657, "no_speech_prob": 0.025177001953125, "words": [ { "start": 1051.29, "end": 1051.73, "word": " And", "probability": 0.260986328125 }, { "start": 1051.73, "end": 1051.83, "word": " so", "probability": 0.86474609375 }, { "start": 1051.83, "end": 1052.01, "word": " these", "probability": 0.607421875 }, { "start": 1052.01, "end": 1052.09, "word": " are", "probability": 0.90087890625 }, { "start": 1052.09, "end": 1052.17, "word": " the", "probability": 0.8154296875 }, { "start": 1052.17, "end": 1052.35, "word": " five", "probability": 0.74267578125 }, { "start": 1052.35, "end": 1052.55, "word": " things", "probability": 0.71875 } ] }, { "id": 325, "seek": 106762, "start": 1052.55, "end": 1054.09, "text": " that we need to pay attention to.", "tokens": [ 50464, 300, 321, 643, 281, 1689, 3202, 281, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.1788194513682163, "compression_ratio": 1.5656565656565657, "no_speech_prob": 0.025177001953125, "words": [ { "start": 1052.55, "end": 1052.67, "word": " that", "probability": 0.7783203125 }, { "start": 1052.67, "end": 1052.73, "word": " we", "probability": 0.904296875 }, { "start": 1052.73, "end": 1052.85, "word": " need", "probability": 0.814453125 }, { "start": 1052.85, "end": 1052.95, "word": " to", "probability": 0.908203125 }, { "start": 1052.95, "end": 1053.05, "word": " pay", "probability": 0.89892578125 }, { "start": 1053.05, "end": 1053.33, "word": " attention", "probability": 0.85693359375 }, { "start": 1053.33, "end": 1053.65, "word": " to", "probability": 0.89208984375 }, { "start": 1053.65, "end": 1054.09, "word": ".", "probability": 0.9130859375 } ] }, { "id": 326, "seek": 106762, "start": 1055.29, "end": 1057.61, "text": " Are there any questions so far?", "tokens": [ 50614, 2014, 456, 604, 1651, 370, 1400, 30, 50764 ], "temperature": 0.0, "avg_logprob": -0.1788194513682163, "compression_ratio": 1.5656565656565657, "no_speech_prob": 0.025177001953125, "words": [ { "start": 1055.29, "end": 1055.73, "word": " Are", "probability": 0.87841796875 }, { "start": 1055.73, "end": 1055.95, "word": " there", "probability": 0.85498046875 }, { "start": 1055.95, "end": 1056.27, "word": " any", "probability": 0.82861328125 }, { "start": 1056.27, "end": 1056.73, "word": " questions", "probability": 0.9130859375 }, { "start": 1056.73, "end": 1056.99, "word": " so", "probability": 0.8974609375 }, { "start": 1056.99, "end": 1057.17, "word": " far", "probability": 0.8994140625 }, { "start": 1057.17, "end": 1057.61, "word": "?", "probability": 0.98779296875 } ] }, { "id": 327, "seek": 106762, "start": 1061.05, "end": 1063.73, "text": " It looks like we're clear on questions right now.", "tokens": [ 50864, 467, 1542, 411, 321, 434, 1850, 322, 1651, 558, 586, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.1788194513682163, "compression_ratio": 1.5656565656565657, "no_speech_prob": 0.025177001953125, "words": [ { "start": 1061.05, "end": 1061.49, "word": " It", "probability": 0.321533203125 }, { "start": 1061.49, "end": 1061.93, "word": " looks", "probability": 0.79931640625 }, { "start": 1061.93, "end": 1062.17, "word": " like", "probability": 0.88037109375 }, { "start": 1062.17, "end": 1062.35, "word": " we're", "probability": 0.912841796875 }, { "start": 1062.35, "end": 1062.63, "word": " clear", "probability": 0.7080078125 }, { "start": 1062.63, "end": 1062.77, "word": " on", "probability": 0.87744140625 }, { "start": 1062.77, "end": 1063.13, "word": " questions", "probability": 0.9033203125 }, { "start": 1063.13, "end": 1063.37, "word": " right", "probability": 0.8681640625 }, { "start": 1063.37, "end": 1063.61, "word": " now", "probability": 0.8984375 }, { "start": 1063.61, "end": 1063.73, "word": ".", "probability": 0.96337890625 } ] }, { "id": 328, "seek": 106762, "start": 1063.77, "end": 1064.65, "text": " Awesome.", "tokens": [ 51014, 10391, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.1788194513682163, "compression_ratio": 1.5656565656565657, "no_speech_prob": 0.025177001953125, "words": [ { "start": 1063.77, "end": 1064.21, "word": " Awesome", "probability": 0.87646484375 }, { "start": 1064.21, "end": 1064.65, "word": ".", "probability": 0.88623046875 } ] }, { "id": 329, "seek": 106762, "start": 1065.77, "end": 1067.97, "text": " Okay, so how do we take this idea", "tokens": [ 51114, 1033, 11, 370, 577, 360, 321, 747, 341, 1558, 51264 ], "temperature": 0.0, "avg_logprob": -0.1788194513682163, "compression_ratio": 1.5656565656565657, "no_speech_prob": 0.025177001953125, "words": [ { "start": 1065.77, "end": 1066.21, "word": " Okay", "probability": 0.63525390625 }, { "start": 1066.21, "end": 1066.39, "word": ",", "probability": 0.54296875 }, { "start": 1066.39, "end": 1066.77, "word": " so", "probability": 0.89453125 }, { "start": 1066.77, "end": 1067.07, "word": " how", "probability": 0.85791015625 }, { "start": 1067.07, "end": 1067.15, "word": " do", "probability": 0.90771484375 }, { "start": 1067.15, "end": 1067.23, "word": " we", "probability": 0.90087890625 }, { "start": 1067.23, "end": 1067.43, "word": " take", "probability": 0.81494140625 }, { "start": 1067.43, "end": 1067.61, "word": " this", "probability": 0.88232421875 }, { "start": 1067.61, "end": 1067.97, "word": " idea", "probability": 0.77880859375 } ] }, { "id": 330, "seek": 106762, "start": 1067.97, "end": 1070.49, "text": " and expand it to a full email?", "tokens": [ 51264, 293, 5268, 309, 281, 257, 1577, 3796, 30, 51414 ], "temperature": 0.0, "avg_logprob": -0.1788194513682163, "compression_ratio": 1.5656565656565657, "no_speech_prob": 0.025177001953125, "words": [ { "start": 1067.97, "end": 1068.51, "word": " and", "probability": 0.87646484375 }, { "start": 1068.51, "end": 1068.97, "word": " expand", "probability": 0.8251953125 }, { "start": 1068.97, "end": 1069.19, "word": " it", "probability": 0.9052734375 }, { "start": 1069.19, "end": 1069.35, "word": " to", "probability": 0.89892578125 }, { "start": 1069.49, "end": 1069.75, "word": " a full", "probability": 0.79833984375 }, { "start": 1069.75, "end": 1070.05, "word": " email", "probability": 0.884765625 }, { "start": 1070.05, "end": 1070.49, "word": "?", "probability": 0.93212890625 } ] }, { "id": 331, "seek": 106762, "start": 1071.81, "end": 1074.21, "text": " Well, here's a spam email.", "tokens": [ 51414, 1042, 11, 510, 311, 257, 24028, 3796, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.1788194513682163, "compression_ratio": 1.5656565656565657, "no_speech_prob": 0.025177001953125, "words": [ { "start": 1071.81, "end": 1072.25, "word": " Well", "probability": 0.71484375 }, { "start": 1072.25, "end": 1072.37, "word": ",", "probability": 0.79833984375 }, { "start": 1072.37, "end": 1072.59, "word": " here's", "probability": 0.906005859375 }, { "start": 1073.05, "end": 1073.39, "word": " a spam", "probability": 0.89599609375 }, { "start": 1073.39, "end": 1073.77, "word": " email", "probability": 0.91259765625 }, { "start": 1073.77, "end": 1074.21, "word": ".", "probability": 0.3369140625 } ] }, { "id": 332, "seek": 106762, "start": 1075.11, "end": 1076.91, "text": " Yeah, no, this is not a spam email.", "tokens": [ 51564, 865, 11, 572, 11, 341, 307, 406, 257, 24028, 3796, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.1788194513682163, "compression_ratio": 1.5656565656565657, "no_speech_prob": 0.025177001953125, "words": [ { "start": 1075.11, "end": 1075.55, "word": " Yeah", "probability": 0.36767578125 }, { "start": 1075.55, "end": 1075.75, "word": ",", "probability": 0.90576171875 }, { "start": 1075.75, "end": 1075.89, "word": " no", "probability": 0.83740234375 }, { "start": 1075.89, "end": 1075.97, "word": ",", "probability": 0.84033203125 }, { "start": 1075.97, "end": 1076.11, "word": " this", "probability": 0.88232421875 }, { "start": 1076.11, "end": 1076.23, "word": " is", "probability": 0.90380859375 }, { "start": 1076.23, "end": 1076.37, "word": " not", "probability": 0.8955078125 }, { "start": 1076.47, "end": 1076.63, "word": " a spam", "probability": 0.9130859375 }, { "start": 1076.63, "end": 1076.81, "word": " email", "probability": 0.89306640625 }, { "start": 1076.81, "end": 1076.91, "word": ".", "probability": 0.63818359375 } ] }, { "id": 333, "seek": 106762, "start": 1076.91, "end": 1078.55, "text": " This is a regular email.", "tokens": [ 51664, 639, 307, 257, 3890, 3796, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.1788194513682163, "compression_ratio": 1.5656565656565657, "no_speech_prob": 0.025177001953125, "words": [ { "start": 1076.91, "end": 1077.03, "word": " This", "probability": 0.802734375 }, { "start": 1077.03, "end": 1077.17, "word": " is", "probability": 0.90234375 }, { "start": 1077.43, "end": 1077.69, "word": " a regular", "probability": 0.88720703125 }, { "start": 1077.69, "end": 1078.11, "word": " email", "probability": 0.92041015625 }, { "start": 1078.11, "end": 1078.55, "word": ".", "probability": 0.65771484375 } ] }, { "id": 334, "seek": 109602, "start": 1078.55, "end": 1080.55, "text": " And we're going to use this as a common example", "tokens": [ 50364, 400, 321, 434, 516, 281, 764, 341, 382, 257, 2689, 1365, 50464 ], "temperature": 0.0, "avg_logprob": -0.19468522158852458, "compression_ratio": 1.6981818181818182, "no_speech_prob": 0.0004239082336425781, "words": [ { "start": 1078.55, "end": 1079.01, "word": " And", "probability": 0.30908203125 }, { "start": 1079.01, "end": 1079.21, "word": " we're", "probability": 0.828857421875 }, { "start": 1079.21, "end": 1079.21, "word": " going", "probability": 0.4384765625 }, { "start": 1079.21, "end": 1079.21, "word": " to", "probability": 0.90673828125 }, { "start": 1079.21, "end": 1079.39, "word": " use", "probability": 0.8193359375 }, { "start": 1079.39, "end": 1079.53, "word": " this", "probability": 0.8701171875 }, { "start": 1079.53, "end": 1079.69, "word": " as", "probability": 0.89013671875 }, { "start": 1079.91, "end": 1080.15, "word": " a common", "probability": 0.73046875 }, { "start": 1080.15, "end": 1080.55, "word": " example", "probability": 0.927734375 } ] }, { "id": 335, "seek": 109602, "start": 1080.55, "end": 1082.31, "text": " throughout the rest of our workbook.", "tokens": [ 50464, 3710, 264, 1472, 295, 527, 589, 2939, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.19468522158852458, "compression_ratio": 1.6981818181818182, "no_speech_prob": 0.0004239082336425781, "words": [ { "start": 1080.55, "end": 1080.81, "word": " throughout", "probability": 0.72412109375 }, { "start": 1080.81, "end": 1080.99, "word": " the", "probability": 0.81396484375 }, { "start": 1080.99, "end": 1081.17, "word": " rest", "probability": 0.8046875 }, { "start": 1081.17, "end": 1081.29, "word": " of", "probability": 0.9033203125 }, { "start": 1081.29, "end": 1081.41, "word": " our", "probability": 0.79443359375 }, { "start": 1081.41, "end": 1081.85, "word": " workbook", "probability": 0.894775390625 }, { "start": 1081.85, "end": 1082.31, "word": ".", "probability": 0.953125 } ] }, { "id": 336, "seek": 109602, "start": 1082.65, "end": 1084.33, "text": " So in this example email,", "tokens": [ 50564, 407, 294, 341, 1365, 3796, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.19468522158852458, "compression_ratio": 1.6981818181818182, "no_speech_prob": 0.0004239082336425781, "words": [ { "start": 1082.65, "end": 1082.77, "word": " So", "probability": 0.75341796875 }, { "start": 1082.77, "end": 1083.05, "word": " in", "probability": 0.67822265625 }, { "start": 1083.05, "end": 1083.21, "word": " this", "probability": 0.87548828125 }, { "start": 1083.21, "end": 1083.53, "word": " example", "probability": 0.91943359375 }, { "start": 1083.53, "end": 1083.83, "word": " email", "probability": 0.87451171875 }, { "start": 1083.83, "end": 1084.33, "word": ",", "probability": 0.7060546875 } ] }, { "id": 337, "seek": 109602, "start": 1084.33, "end": 1087.39, "text": " we have re, re, East Asian fonts in Lenny.", "tokens": [ 50664, 321, 362, 319, 11, 319, 11, 6747, 10645, 35316, 294, 23009, 1634, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.19468522158852458, "compression_ratio": 1.6981818181818182, "no_speech_prob": 0.0004239082336425781, "words": [ { "start": 1084.33, "end": 1084.71, "word": " we", "probability": 0.888671875 }, { "start": 1084.71, "end": 1085.09, "word": " have", "probability": 0.8681640625 }, { "start": 1085.09, "end": 1085.35, "word": " re", "probability": 0.04278564453125 }, { "start": 1085.35, "end": 1085.47, "word": ",", "probability": 0.279541015625 }, { "start": 1085.47, "end": 1085.77, "word": " re", "probability": 0.74267578125 }, { "start": 1085.77, "end": 1085.93, "word": ",", "probability": 0.86669921875 }, { "start": 1085.93, "end": 1086.17, "word": " East", "probability": 0.53125 }, { "start": 1086.17, "end": 1086.39, "word": " Asian", "probability": 0.763671875 }, { "start": 1086.39, "end": 1086.79, "word": " fonts", "probability": 0.73095703125 }, { "start": 1086.79, "end": 1086.99, "word": " in", "probability": 0.440185546875 }, { "start": 1086.99, "end": 1087.25, "word": " Lenny", "probability": 0.791259765625 }, { "start": 1087.25, "end": 1087.39, "word": ".", "probability": 0.57763671875 } ] }, { "id": 338, "seek": 109602, "start": 1087.39, "end": 1088.41, "text": " Thanks for your support.", "tokens": [ 50814, 2561, 337, 428, 1406, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.19468522158852458, "compression_ratio": 1.6981818181818182, "no_speech_prob": 0.0004239082336425781, "words": [ { "start": 1087.39, "end": 1087.55, "word": " Thanks", "probability": 0.75341796875 }, { "start": 1087.55, "end": 1087.67, "word": " for", "probability": 0.89794921875 }, { "start": 1087.67, "end": 1087.79, "word": " your", "probability": 0.80419921875 }, { "start": 1087.79, "end": 1088.15, "word": " support", "probability": 0.935546875 }, { "start": 1088.15, "end": 1088.41, "word": ".", "probability": 0.80029296875 } ] }, { "id": 339, "seek": 109602, "start": 1088.41, "end": 1090.35, "text": " Installing Unifonts did it well for me.", "tokens": [ 50864, 2730, 24021, 1156, 351, 896, 82, 630, 309, 731, 337, 385, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.19468522158852458, "compression_ratio": 1.6981818181818182, "no_speech_prob": 0.0004239082336425781, "words": [ { "start": 1088.41, "end": 1088.73, "word": " Installing", "probability": 0.949462890625 }, { "start": 1088.73, "end": 1089.21, "word": " Unifonts", "probability": 0.7955322265625 }, { "start": 1089.21, "end": 1089.35, "word": " did", "probability": 0.84521484375 }, { "start": 1089.35, "end": 1089.45, "word": " it", "probability": 0.90087890625 }, { "start": 1089.45, "end": 1089.57, "word": " well", "probability": 0.8798828125 }, { "start": 1089.57, "end": 1089.73, "word": " for", "probability": 0.89404296875 }, { "start": 1089.73, "end": 1089.89, "word": " me", "probability": 0.904296875 }, { "start": 1089.89, "end": 1090.35, "word": ".", "probability": 0.982421875 } ] }, { "id": 340, "seek": 109602, "start": 1091.87, "end": 1094.53, "text": " Now, we could take this entire email", "tokens": [ 51014, 823, 11, 321, 727, 747, 341, 2302, 3796, 51164 ], "temperature": 0.0, "avg_logprob": -0.19468522158852458, "compression_ratio": 1.6981818181818182, "no_speech_prob": 0.0004239082336425781, "words": [ { "start": 1091.87, "end": 1092.33, "word": " Now", "probability": 0.8798828125 }, { "start": 1092.33, "end": 1092.65, "word": ",", "probability": 0.658203125 }, { "start": 1092.65, "end": 1093.35, "word": " we", "probability": 0.89990234375 }, { "start": 1093.35, "end": 1093.47, "word": " could", "probability": 0.75830078125 }, { "start": 1093.47, "end": 1093.65, "word": " take", "probability": 0.81689453125 }, { "start": 1093.65, "end": 1093.83, "word": " this", "probability": 0.875 }, { "start": 1093.83, "end": 1094.21, "word": " entire", "probability": 0.76123046875 }, { "start": 1094.21, "end": 1094.53, "word": " email", "probability": 0.9111328125 } ] }, { "id": 341, "seek": 109602, "start": 1094.53, "end": 1096.53, "text": " and look at it,", "tokens": [ 51164, 293, 574, 412, 309, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.19468522158852458, "compression_ratio": 1.6981818181818182, "no_speech_prob": 0.0004239082336425781, "words": [ { "start": 1094.53, "end": 1095.37, "word": " and", "probability": 0.87548828125 }, { "start": 1095.37, "end": 1095.69, "word": " look", "probability": 0.91455078125 }, { "start": 1095.69, "end": 1095.89, "word": " at", "probability": 0.9091796875 }, { "start": 1095.89, "end": 1096.07, "word": " it", "probability": 0.90283203125 }, { "start": 1096.07, "end": 1096.53, "word": ",", "probability": 0.509765625 } ] }, { "id": 342, "seek": 109602, "start": 1096.53, "end": 1099.03, "text": " but there are some things that we want to", "tokens": [ 51264, 457, 456, 366, 512, 721, 300, 321, 528, 281, 51414 ], "temperature": 0.0, "avg_logprob": -0.19468522158852458, "compression_ratio": 1.6981818181818182, "no_speech_prob": 0.0004239082336425781, "words": [ { "start": 1096.53, "end": 1096.83, "word": " but", "probability": 0.89453125 }, { "start": 1096.83, "end": 1097.61, "word": " there", "probability": 0.83837890625 }, { "start": 1097.61, "end": 1097.67, "word": " are", "probability": 0.6201171875 }, { "start": 1097.67, "end": 1097.81, "word": " some", "probability": 0.8271484375 }, { "start": 1097.81, "end": 1098.05, "word": " things", "probability": 0.73388671875 }, { "start": 1098.05, "end": 1098.19, "word": " that", "probability": 0.869140625 }, { "start": 1098.19, "end": 1098.35, "word": " we", "probability": 0.90380859375 }, { "start": 1098.35, "end": 1098.63, "word": " want", "probability": 0.79345703125 }, { "start": 1098.63, "end": 1099.03, "word": " to", "probability": 0.90380859375 } ] }, { "id": 343, "seek": 109602, "start": 1099.65, "end": 1100.79, "text": " probably remove,", "tokens": [ 51414, 1391, 4159, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.19468522158852458, "compression_ratio": 1.6981818181818182, "no_speech_prob": 0.0004239082336425781, "words": [ { "start": 1099.65, "end": 1100.11, "word": " probably", "probability": 0.84228515625 }, { "start": 1100.11, "end": 1100.57, "word": " remove", "probability": 0.87158203125 }, { "start": 1100.57, "end": 1100.79, "word": ",", "probability": 0.57421875 } ] }, { "id": 344, "seek": 109602, "start": 1100.79, "end": 1102.43, "text": " things that don't really make a lot of sense,", "tokens": [ 51464, 721, 300, 500, 380, 534, 652, 257, 688, 295, 2020, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.19468522158852458, "compression_ratio": 1.6981818181818182, "no_speech_prob": 0.0004239082336425781, "words": [ { "start": 1100.79, "end": 1101.01, "word": " things", "probability": 0.73828125 }, { "start": 1101.01, "end": 1101.15, "word": " that", "probability": 0.8837890625 }, { "start": 1101.15, "end": 1101.31, "word": " don't", "probability": 0.94287109375 }, { "start": 1101.31, "end": 1101.53, "word": " really", "probability": 0.7412109375 }, { "start": 1101.53, "end": 1101.73, "word": " make", "probability": 0.87744140625 }, { "start": 1101.85, "end": 1101.97, "word": " a lot", "probability": 0.89208984375 }, { "start": 1101.97, "end": 1102.11, "word": " of", "probability": 0.9072265625 }, { "start": 1102.11, "end": 1102.35, "word": " sense", "probability": 0.74462890625 }, { "start": 1102.35, "end": 1102.43, "word": ",", "probability": 0.92724609375 } ] }, { "id": 345, "seek": 109602, "start": 1102.43, "end": 1104.21, "text": " especially in the English language.", "tokens": [ 51564, 2318, 294, 264, 3669, 2856, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.19468522158852458, "compression_ratio": 1.6981818181818182, "no_speech_prob": 0.0004239082336425781, "words": [ { "start": 1102.43, "end": 1102.71, "word": " especially", "probability": 0.716796875 }, { "start": 1102.71, "end": 1102.89, "word": " in", "probability": 0.89990234375 }, { "start": 1102.89, "end": 1103.01, "word": " the", "probability": 0.818359375 }, { "start": 1103.01, "end": 1103.25, "word": " English", "probability": 0.90771484375 }, { "start": 1103.25, "end": 1103.75, "word": " language", "probability": 0.6728515625 }, { "start": 1103.75, "end": 1104.21, "word": ".", "probability": 0.86767578125 } ] }, { "id": 346, "seek": 109602, "start": 1104.35, "end": 1106.95, "text": " So punctuation, punctuation doesn't really make sense.", "tokens": [ 51664, 407, 27006, 16073, 11, 27006, 16073, 1177, 380, 534, 652, 2020, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.19468522158852458, "compression_ratio": 1.6981818181818182, "no_speech_prob": 0.0004239082336425781, "words": [ { "start": 1104.35, "end": 1104.71, "word": " So", "probability": 0.87890625 }, { "start": 1104.71, "end": 1105.35, "word": " punctuation", "probability": 0.876708984375 }, { "start": 1105.35, "end": 1105.45, "word": ",", "probability": 0.58544921875 }, { "start": 1105.45, "end": 1105.95, "word": " punctuation", "probability": 0.9267578125 }, { "start": 1105.95, "end": 1106.25, "word": " doesn't", "probability": 0.9228515625 }, { "start": 1106.25, "end": 1106.39, "word": " really", "probability": 0.7607421875 }, { "start": 1106.39, "end": 1106.63, "word": " make", "probability": 0.873046875 }, { "start": 1106.63, "end": 1106.87, "word": " sense", "probability": 0.7548828125 }, { "start": 1106.87, "end": 1106.95, "word": ".", "probability": 0.78564453125 } ] }, { "id": 347, "seek": 112406, "start": 1106.95, "end": 1109.61, "text": " It doesn't add any context to a sentence.", "tokens": [ 50364, 467, 1177, 380, 909, 604, 4319, 281, 257, 8174, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.1950334877307926, "compression_ratio": 1.68348623853211, "no_speech_prob": 0.011871337890625, "words": [ { "start": 1106.95, "end": 1106.99, "word": " It", "probability": 0.239990234375 }, { "start": 1106.99, "end": 1107.19, "word": " doesn't", "probability": 0.938720703125 }, { "start": 1107.19, "end": 1107.51, "word": " add", "probability": 0.8251953125 }, { "start": 1107.51, "end": 1107.71, "word": " any", "probability": 0.8232421875 }, { "start": 1107.71, "end": 1108.27, "word": " context", "probability": 0.77197265625 }, { "start": 1108.27, "end": 1108.47, "word": " to", "probability": 0.90869140625 }, { "start": 1108.63, "end": 1109.13, "word": " a sentence", "probability": 0.8427734375 }, { "start": 1109.13, "end": 1109.61, "word": ".", "probability": 0.96044921875 } ] }, { "id": 348, "seek": 112406, "start": 1110.95, "end": 1114.11, "text": " Small words, which are called stop words,", "tokens": [ 50564, 15287, 2283, 11, 597, 366, 1219, 1590, 2283, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.1950334877307926, "compression_ratio": 1.68348623853211, "no_speech_prob": 0.011871337890625, "words": [ { "start": 1110.95, "end": 1111.43, "word": " Small", "probability": 0.765625 }, { "start": 1111.43, "end": 1111.91, "word": " words", "probability": 0.7421875 }, { "start": 1111.91, "end": 1111.99, "word": ",", "probability": 0.505859375 }, { "start": 1111.99, "end": 1112.07, "word": " which", "probability": 0.90625 }, { "start": 1112.07, "end": 1112.19, "word": " are", "probability": 0.90576171875 }, { "start": 1112.19, "end": 1112.49, "word": " called", "probability": 0.80078125 }, { "start": 1112.49, "end": 1113.29, "word": " stop", "probability": 0.857421875 }, { "start": 1113.29, "end": 1113.69, "word": " words", "probability": 0.66357421875 }, { "start": 1113.69, "end": 1114.11, "word": ",", "probability": 0.76708984375 } ] }, { "id": 349, "seek": 112406, "start": 1114.11, "end": 1117.51, "text": " such as in, of, on, for, the,", "tokens": [ 50714, 1270, 382, 294, 11, 295, 11, 322, 11, 337, 11, 264, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.1950334877307926, "compression_ratio": 1.68348623853211, "no_speech_prob": 0.011871337890625, "words": [ { "start": 1114.11, "end": 1114.35, "word": " such", "probability": 0.8642578125 }, { "start": 1114.35, "end": 1114.59, "word": " as", "probability": 0.90576171875 }, { "start": 1114.59, "end": 1114.97, "word": " in", "probability": 0.72802734375 }, { "start": 1114.97, "end": 1115.07, "word": ",", "probability": 0.955078125 }, { "start": 1115.07, "end": 1115.51, "word": " of", "probability": 0.8974609375 }, { "start": 1115.51, "end": 1115.67, "word": ",", "probability": 0.994140625 }, { "start": 1115.67, "end": 1116.01, "word": " on", "probability": 0.912109375 }, { "start": 1116.01, "end": 1116.21, "word": ",", "probability": 0.91162109375 }, { "start": 1116.21, "end": 1116.49, "word": " for", "probability": 0.8896484375 }, { "start": 1116.49, "end": 1116.73, "word": ",", "probability": 0.87109375 }, { "start": 1116.73, "end": 1116.91, "word": " the", "probability": 0.492431640625 }, { "start": 1116.91, "end": 1117.51, "word": ",", "probability": 0.6943359375 } ] }, { "id": 350, "seek": 112406, "start": 1117.51, "end": 1119.87, "text": " they also don't add any context.", "tokens": [ 50914, 436, 611, 500, 380, 909, 604, 4319, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.1950334877307926, "compression_ratio": 1.68348623853211, "no_speech_prob": 0.011871337890625, "words": [ { "start": 1117.51, "end": 1118.03, "word": " they", "probability": 0.72998046875 }, { "start": 1118.03, "end": 1118.27, "word": " also", "probability": 0.8193359375 }, { "start": 1118.27, "end": 1118.51, "word": " don't", "probability": 0.94384765625 }, { "start": 1118.51, "end": 1118.69, "word": " add", "probability": 0.8017578125 }, { "start": 1118.69, "end": 1119.01, "word": " any", "probability": 0.78173828125 }, { "start": 1119.01, "end": 1119.59, "word": " context", "probability": 0.7626953125 }, { "start": 1119.59, "end": 1119.87, "word": ".", "probability": 0.6884765625 } ] }, { "id": 351, "seek": 112406, "start": 1119.87, "end": 1121.61, "text": " So we can just go ahead and remove that,", "tokens": [ 51014, 407, 321, 393, 445, 352, 2286, 293, 4159, 300, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.1950334877307926, "compression_ratio": 1.68348623853211, "no_speech_prob": 0.011871337890625, "words": [ { "start": 1119.87, "end": 1119.97, "word": " So", "probability": 0.88525390625 }, { "start": 1119.97, "end": 1120.09, "word": " we", "probability": 0.79541015625 }, { "start": 1120.09, "end": 1120.17, "word": " can", "probability": 0.892578125 }, { "start": 1120.17, "end": 1120.33, "word": " just", "probability": 0.8779296875 }, { "start": 1120.33, "end": 1120.47, "word": " go", "probability": 0.8994140625 }, { "start": 1120.47, "end": 1120.67, "word": " ahead", "probability": 0.85009765625 }, { "start": 1120.67, "end": 1120.79, "word": " and", "probability": 0.888671875 }, { "start": 1120.79, "end": 1121.03, "word": " remove", "probability": 0.859375 }, { "start": 1121.03, "end": 1121.33, "word": " that", "probability": 0.88330078125 }, { "start": 1121.33, "end": 1121.61, "word": ",", "probability": 0.47216796875 } ] }, { "id": 352, "seek": 112406, "start": 1121.61, "end": 1123.85, "text": " and that'll reduce the amount of words", "tokens": [ 51114, 293, 300, 603, 5407, 264, 2372, 295, 2283, 51214 ], "temperature": 0.0, "avg_logprob": -0.1950334877307926, "compression_ratio": 1.68348623853211, "no_speech_prob": 0.011871337890625, "words": [ { "start": 1121.61, "end": 1121.77, "word": " and", "probability": 0.8974609375 }, { "start": 1121.77, "end": 1122.01, "word": " that'll", "probability": 0.85546875 }, { "start": 1122.01, "end": 1122.67, "word": " reduce", "probability": 0.76416015625 }, { "start": 1122.67, "end": 1123.13, "word": " the", "probability": 0.806640625 }, { "start": 1123.13, "end": 1123.37, "word": " amount", "probability": 0.85009765625 }, { "start": 1123.37, "end": 1123.53, "word": " of", "probability": 0.90380859375 }, { "start": 1123.53, "end": 1123.85, "word": " words", "probability": 0.734375 } ] }, { "id": 353, "seek": 112406, "start": 1123.85, "end": 1125.33, "text": " that we're looking at in this email,", "tokens": [ 51214, 300, 321, 434, 1237, 412, 294, 341, 3796, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.1950334877307926, "compression_ratio": 1.68348623853211, "no_speech_prob": 0.011871337890625, "words": [ { "start": 1123.85, "end": 1124.05, "word": " that", "probability": 0.875 }, { "start": 1124.05, "end": 1124.17, "word": " we're", "probability": 0.929443359375 }, { "start": 1124.17, "end": 1124.43, "word": " looking", "probability": 0.7978515625 }, { "start": 1124.43, "end": 1124.63, "word": " at", "probability": 0.904296875 }, { "start": 1124.63, "end": 1124.71, "word": " in", "probability": 0.89453125 }, { "start": 1124.71, "end": 1124.89, "word": " this", "probability": 0.876953125 }, { "start": 1124.89, "end": 1125.17, "word": " email", "probability": 0.8720703125 }, { "start": 1125.17, "end": 1125.33, "word": ",", "probability": 0.5869140625 } ] }, { "id": 354, "seek": 112406, "start": 1125.33, "end": 1126.97, "text": " because we want to look at keywords.", "tokens": [ 51264, 570, 321, 528, 281, 574, 412, 21009, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.1950334877307926, "compression_ratio": 1.68348623853211, "no_speech_prob": 0.011871337890625, "words": [ { "start": 1125.33, "end": 1125.47, "word": " because", "probability": 0.26220703125 }, { "start": 1125.47, "end": 1125.57, "word": " we", "probability": 0.90283203125 }, { "start": 1125.57, "end": 1125.67, "word": " want", "probability": 0.47216796875 }, { "start": 1125.67, "end": 1125.75, "word": " to", "probability": 0.90380859375 }, { "start": 1125.75, "end": 1125.87, "word": " look", "probability": 0.91845703125 }, { "start": 1125.87, "end": 1125.99, "word": " at", "probability": 0.89892578125 }, { "start": 1125.99, "end": 1126.49, "word": " keywords", "probability": 0.34912109375 }, { "start": 1126.49, "end": 1126.97, "word": ".", "probability": 0.984375 } ] }, { "id": 355, "seek": 112406, "start": 1128.81, "end": 1131.99, "text": " Things like unsubscribe and unsubscribed,", "tokens": [ 51464, 9514, 411, 2693, 9493, 293, 2693, 5432, 18732, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.1950334877307926, "compression_ratio": 1.68348623853211, "no_speech_prob": 0.011871337890625, "words": [ { "start": 1128.81, "end": 1129.29, "word": " Things", "probability": 0.73828125 }, { "start": 1129.29, "end": 1129.57, "word": " like", "probability": 0.87109375 }, { "start": 1129.57, "end": 1130.17, "word": " unsubscribe", "probability": 0.8408203125 }, { "start": 1130.17, "end": 1130.65, "word": " and", "probability": 0.8310546875 }, { "start": 1130.65, "end": 1131.55, "word": " unsubscribed", "probability": 0.85791015625 }, { "start": 1131.55, "end": 1131.99, "word": ",", "probability": 0.73974609375 } ] }, { "id": 356, "seek": 112406, "start": 1131.99, "end": 1134.99, "text": " or thanks, or thank you.", "tokens": [ 51614, 420, 3231, 11, 420, 1309, 291, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.1950334877307926, "compression_ratio": 1.68348623853211, "no_speech_prob": 0.011871337890625, "words": [ { "start": 1131.99, "end": 1132.35, "word": " or", "probability": 0.908203125 }, { "start": 1132.35, "end": 1133.27, "word": " thanks", "probability": 0.755859375 }, { "start": 1133.27, "end": 1133.57, "word": ",", "probability": 0.482421875 }, { "start": 1133.57, "end": 1133.73, "word": " or", "probability": 0.9033203125 }, { "start": 1133.73, "end": 1134.15, "word": " thank", "probability": 0.80322265625 }, { "start": 1134.15, "end": 1134.51, "word": " you", "probability": 0.888671875 }, { "start": 1134.51, "end": 1134.99, "word": ".", "probability": 0.28564453125 } ] }, { "id": 357, "seek": 115236, "start": 1134.99, "end": 1137.31, "text": " They mean the same thing.", "tokens": [ 50364, 814, 914, 264, 912, 551, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.17494876890397462, "compression_ratio": 1.729957805907173, "no_speech_prob": 0.0758056640625, "words": [ { "start": 1134.99, "end": 1135.75, "word": " They", "probability": 0.486328125 }, { "start": 1135.75, "end": 1136.03, "word": " mean", "probability": 0.92529296875 }, { "start": 1136.03, "end": 1136.23, "word": " the", "probability": 0.8154296875 }, { "start": 1136.23, "end": 1136.45, "word": " same", "probability": 0.81201171875 }, { "start": 1136.45, "end": 1136.87, "word": " thing", "probability": 0.80712890625 }, { "start": 1136.87, "end": 1137.31, "word": ".", "probability": 0.463134765625 } ] }, { "id": 358, "seek": 115236, "start": 1137.39, "end": 1139.59, "text": " A really good example, especially in English,", "tokens": [ 50464, 316, 534, 665, 1365, 11, 2318, 294, 3669, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.17494876890397462, "compression_ratio": 1.729957805907173, "no_speech_prob": 0.0758056640625, "words": [ { "start": 1137.39, "end": 1137.83, "word": " A", "probability": 0.9697265625 }, { "start": 1137.83, "end": 1137.99, "word": " really", "probability": 0.76416015625 }, { "start": 1137.99, "end": 1138.15, "word": " good", "probability": 0.8662109375 }, { "start": 1138.15, "end": 1138.47, "word": " example", "probability": 0.92236328125 }, { "start": 1138.47, "end": 1138.69, "word": ",", "probability": 0.7841796875 }, { "start": 1138.69, "end": 1138.81, "word": " especially", "probability": 0.7197265625 }, { "start": 1138.81, "end": 1138.99, "word": " in", "probability": 0.89892578125 }, { "start": 1138.99, "end": 1139.37, "word": " English", "probability": 0.8984375 }, { "start": 1139.37, "end": 1139.59, "word": ",", "probability": 0.421142578125 } ] }, { "id": 359, "seek": 115236, "start": 1139.59, "end": 1142.09, "text": " is congrats and congratulations.", "tokens": [ 50564, 307, 8882, 1720, 293, 13568, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.17494876890397462, "compression_ratio": 1.729957805907173, "no_speech_prob": 0.0758056640625, "words": [ { "start": 1139.59, "end": 1139.69, "word": " is", "probability": 0.90380859375 }, { "start": 1139.69, "end": 1140.51, "word": " congrats", "probability": 0.6463623046875 }, { "start": 1140.51, "end": 1140.85, "word": " and", "probability": 0.8583984375 }, { "start": 1140.85, "end": 1141.65, "word": " congratulations", "probability": 0.72509765625 }, { "start": 1141.65, "end": 1142.09, "word": ".", "probability": 0.76220703125 } ] }, { "id": 360, "seek": 115236, "start": 1142.47, "end": 1144.05, "text": " They mean the same thing.", "tokens": [ 50714, 814, 914, 264, 912, 551, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.17494876890397462, "compression_ratio": 1.729957805907173, "no_speech_prob": 0.0758056640625, "words": [ { "start": 1142.47, "end": 1142.83, "word": " They", "probability": 0.7294921875 }, { "start": 1142.83, "end": 1143.11, "word": " mean", "probability": 0.93212890625 }, { "start": 1143.11, "end": 1143.31, "word": " the", "probability": 0.81640625 }, { "start": 1143.31, "end": 1143.53, "word": " same", "probability": 0.81298828125 }, { "start": 1143.53, "end": 1143.93, "word": " thing", "probability": 0.8046875 }, { "start": 1143.93, "end": 1144.05, "word": ".", "probability": 0.55517578125 } ] }, { "id": 361, "seek": 115236, "start": 1144.05, "end": 1146.37, "text": " And if we want to narrow this down to keywords,", "tokens": [ 50814, 400, 498, 321, 528, 281, 9432, 341, 760, 281, 21009, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.17494876890397462, "compression_ratio": 1.729957805907173, "no_speech_prob": 0.0758056640625, "words": [ { "start": 1144.05, "end": 1144.11, "word": " And", "probability": 0.79736328125 }, { "start": 1144.11, "end": 1144.21, "word": " if", "probability": 0.8935546875 }, { "start": 1144.21, "end": 1144.31, "word": " we", "probability": 0.90283203125 }, { "start": 1144.31, "end": 1144.47, "word": " want", "probability": 0.7958984375 }, { "start": 1144.47, "end": 1144.57, "word": " to", "probability": 0.9013671875 }, { "start": 1144.57, "end": 1144.73, "word": " narrow", "probability": 0.7705078125 }, { "start": 1144.73, "end": 1144.95, "word": " this", "probability": 0.8896484375 }, { "start": 1144.95, "end": 1145.11, "word": " down", "probability": 0.8173828125 }, { "start": 1145.11, "end": 1145.25, "word": " to", "probability": 0.89453125 }, { "start": 1145.25, "end": 1145.61, "word": " keywords", "probability": 0.34033203125 }, { "start": 1145.61, "end": 1146.37, "word": ",", "probability": 0.83203125 } ] }, { "id": 362, "seek": 115236, "start": 1146.37, "end": 1148.35, "text": " we should do what's called stemming.", "tokens": [ 50914, 321, 820, 360, 437, 311, 1219, 12312, 2810, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.17494876890397462, "compression_ratio": 1.729957805907173, "no_speech_prob": 0.0758056640625, "words": [ { "start": 1146.37, "end": 1146.59, "word": " we", "probability": 0.87744140625 }, { "start": 1146.59, "end": 1146.79, "word": " should", "probability": 0.92529296875 }, { "start": 1146.79, "end": 1147.03, "word": " do", "probability": 0.89453125 }, { "start": 1147.03, "end": 1147.27, "word": " what's", "probability": 0.94091796875 }, { "start": 1147.27, "end": 1147.51, "word": " called", "probability": 0.80126953125 }, { "start": 1147.51, "end": 1148.05, "word": " stemming", "probability": 0.88623046875 }, { "start": 1148.05, "end": 1148.35, "word": ".", "probability": 0.923828125 } ] }, { "id": 363, "seek": 115236, "start": 1148.35, "end": 1149.53, "text": " And so what stemming does", "tokens": [ 51014, 400, 370, 437, 12312, 2810, 775, 51064 ], "temperature": 0.0, "avg_logprob": -0.17494876890397462, "compression_ratio": 1.729957805907173, "no_speech_prob": 0.0758056640625, "words": [ { "start": 1148.35, "end": 1148.41, "word": " And", "probability": 0.7958984375 }, { "start": 1148.41, "end": 1148.55, "word": " so", "probability": 0.8876953125 }, { "start": 1148.55, "end": 1148.73, "word": " what", "probability": 0.83837890625 }, { "start": 1148.73, "end": 1149.15, "word": " stemming", "probability": 0.92529296875 }, { "start": 1149.15, "end": 1149.53, "word": " does", "probability": 0.91943359375 } ] }, { "id": 364, "seek": 115236, "start": 1149.53, "end": 1151.35, "text": " is it shortens the word down", "tokens": [ 51064, 307, 309, 2099, 694, 264, 1349, 760, 51164 ], "temperature": 0.0, "avg_logprob": -0.17494876890397462, "compression_ratio": 1.729957805907173, "no_speech_prob": 0.0758056640625, "words": [ { "start": 1149.53, "end": 1149.73, "word": " is", "probability": 0.78466796875 }, { "start": 1149.73, "end": 1149.93, "word": " it", "probability": 0.87353515625 }, { "start": 1149.93, "end": 1150.39, "word": " shortens", "probability": 0.930419921875 }, { "start": 1150.39, "end": 1150.59, "word": " the", "probability": 0.8056640625 }, { "start": 1150.59, "end": 1150.81, "word": " word", "probability": 0.8134765625 }, { "start": 1150.81, "end": 1151.35, "word": " down", "probability": 0.80615234375 } ] }, { "id": 365, "seek": 115236, "start": 1151.35, "end": 1154.27, "text": " so that you have I thanked somebody today,", "tokens": [ 51164, 370, 300, 291, 362, 286, 48137, 2618, 965, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.17494876890397462, "compression_ratio": 1.729957805907173, "no_speech_prob": 0.0758056640625, "words": [ { "start": 1151.35, "end": 1151.85, "word": " so", "probability": 0.763671875 }, { "start": 1151.85, "end": 1151.99, "word": " that", "probability": 0.8779296875 }, { "start": 1151.99, "end": 1152.13, "word": " you", "probability": 0.8984375 }, { "start": 1152.13, "end": 1152.41, "word": " have", "probability": 0.87890625 }, { "start": 1152.41, "end": 1152.63, "word": " I", "probability": 0.3056640625 }, { "start": 1152.63, "end": 1153.03, "word": " thanked", "probability": 0.75634765625 }, { "start": 1153.03, "end": 1153.79, "word": " somebody", "probability": 0.80078125 }, { "start": 1153.79, "end": 1154.17, "word": " today", "probability": 0.77099609375 }, { "start": 1154.17, "end": 1154.27, "word": ",", "probability": 0.3740234375 } ] }, { "id": 366, "seek": 115236, "start": 1154.27, "end": 1156.41, "text": " as in past tense, thank-ed,", "tokens": [ 51314, 382, 294, 1791, 18760, 11, 1309, 12, 292, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.17494876890397462, "compression_ratio": 1.729957805907173, "no_speech_prob": 0.0758056640625, "words": [ { "start": 1154.27, "end": 1154.35, "word": " as", "probability": 0.8720703125 }, { "start": 1154.35, "end": 1154.47, "word": " in", "probability": 0.876953125 }, { "start": 1154.47, "end": 1154.75, "word": " past", "probability": 0.7451171875 }, { "start": 1154.75, "end": 1154.99, "word": " tense", "probability": 0.71826171875 }, { "start": 1154.99, "end": 1155.13, "word": ",", "probability": 0.583984375 }, { "start": 1155.13, "end": 1155.33, "word": " thank", "probability": 0.5107421875 }, { "start": 1155.33, "end": 1155.63, "word": "-ed", "probability": 0.51055908203125 }, { "start": 1155.63, "end": 1156.41, "word": ",", "probability": 0.521484375 } ] }, { "id": 367, "seek": 115236, "start": 1157.49, "end": 1160.83, "text": " thanks, thank with an S,", "tokens": [ 51414, 3231, 11, 1309, 365, 364, 318, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.17494876890397462, "compression_ratio": 1.729957805907173, "no_speech_prob": 0.0758056640625, "words": [ { "start": 1157.49, "end": 1157.93, "word": " thanks", "probability": 0.68310546875 }, { "start": 1157.93, "end": 1158.37, "word": ",", "probability": 0.84814453125 }, { "start": 1158.37, "end": 1158.57, "word": " thank", "probability": 0.68212890625 }, { "start": 1158.57, "end": 1159.77, "word": " with", "probability": 0.53857421875 }, { "start": 1159.77, "end": 1159.93, "word": " an", "probability": 0.89794921875 }, { "start": 1159.93, "end": 1160.25, "word": " S", "probability": 0.4462890625 }, { "start": 1160.25, "end": 1160.83, "word": ",", "probability": 0.82470703125 } ] }, { "id": 368, "seek": 115236, "start": 1160.83, "end": 1163.29, "text": " and thank you, where it's just plain thank.", "tokens": [ 51614, 293, 1309, 291, 11, 689, 309, 311, 445, 11121, 1309, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.17494876890397462, "compression_ratio": 1.729957805907173, "no_speech_prob": 0.0758056640625, "words": [ { "start": 1160.83, "end": 1161.05, "word": " and", "probability": 0.89013671875 }, { "start": 1161.05, "end": 1161.53, "word": " thank", "probability": 0.794921875 }, { "start": 1161.53, "end": 1161.81, "word": " you", "probability": 0.826171875 }, { "start": 1161.81, "end": 1162.01, "word": ",", "probability": 0.62841796875 }, { "start": 1162.01, "end": 1162.11, "word": " where", "probability": 0.79736328125 }, { "start": 1162.11, "end": 1162.27, "word": " it's", "probability": 0.949951171875 }, { "start": 1162.27, "end": 1162.45, "word": " just", "probability": 0.88916015625 }, { "start": 1162.45, "end": 1162.69, "word": " plain", "probability": 0.8681640625 }, { "start": 1162.69, "end": 1163.03, "word": " thank", "probability": 0.6318359375 }, { "start": 1163.03, "end": 1163.29, "word": ".", "probability": 0.96728515625 } ] }, { "id": 369, "seek": 118164, "start": 1163.29, "end": 1165.71, "text": " We want to count those all as the same word.", "tokens": [ 50364, 492, 528, 281, 1207, 729, 439, 382, 264, 912, 1349, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.20324706949759275, "compression_ratio": 1.7629310344827587, "no_speech_prob": 0.0164031982421875, "words": [ { "start": 1163.29, "end": 1163.43, "word": " We", "probability": 0.4462890625 }, { "start": 1163.43, "end": 1163.57, "word": " want", "probability": 0.7041015625 }, { "start": 1163.57, "end": 1163.67, "word": " to", "probability": 0.9033203125 }, { "start": 1163.67, "end": 1163.89, "word": " count", "probability": 0.75439453125 }, { "start": 1163.89, "end": 1164.09, "word": " those", "probability": 0.689453125 }, { "start": 1164.09, "end": 1164.37, "word": " all", "probability": 0.84033203125 }, { "start": 1164.37, "end": 1164.53, "word": " as", "probability": 0.88037109375 }, { "start": 1164.53, "end": 1164.69, "word": " the", "probability": 0.80322265625 }, { "start": 1164.69, "end": 1164.95, "word": " same", "probability": 0.79248046875 }, { "start": 1164.95, "end": 1165.31, "word": " word", "probability": 0.78466796875 }, { "start": 1165.31, "end": 1165.71, "word": ".", "probability": 0.90966796875 } ] }, { "id": 370, "seek": 118164, "start": 1167.63, "end": 1168.45, "text": " And then, of course,", "tokens": [ 50564, 400, 550, 11, 295, 1164, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.20324706949759275, "compression_ratio": 1.7629310344827587, "no_speech_prob": 0.0164031982421875, "words": [ { "start": 1167.63, "end": 1168.03, "word": " And", "probability": 0.56201171875 }, { "start": 1168.03, "end": 1168.13, "word": " then", "probability": 0.67919921875 }, { "start": 1168.13, "end": 1168.23, "word": ",", "probability": 0.2034912109375 }, { "start": 1168.23, "end": 1168.27, "word": " of", "probability": 0.896484375 }, { "start": 1168.27, "end": 1168.39, "word": " course", "probability": 0.86767578125 }, { "start": 1168.39, "end": 1168.45, "word": ",", "probability": 0.94775390625 } ] }, { "id": 371, "seek": 118164, "start": 1168.45, "end": 1170.61, "text": " we want to set everything to lowercase,", "tokens": [ 50614, 321, 528, 281, 992, 1203, 281, 3126, 9765, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.20324706949759275, "compression_ratio": 1.7629310344827587, "no_speech_prob": 0.0164031982421875, "words": [ { "start": 1168.45, "end": 1168.51, "word": " we", "probability": 0.90283203125 }, { "start": 1168.51, "end": 1168.65, "word": " want", "probability": 0.794921875 }, { "start": 1168.65, "end": 1168.73, "word": " to", "probability": 0.89990234375 }, { "start": 1168.73, "end": 1168.89, "word": " set", "probability": 0.90869140625 }, { "start": 1168.89, "end": 1169.17, "word": " everything", "probability": 0.89013671875 }, { "start": 1169.17, "end": 1169.37, "word": " to", "probability": 0.88818359375 }, { "start": 1169.37, "end": 1169.99, "word": " lowercase", "probability": 0.7578125 }, { "start": 1169.99, "end": 1170.61, "word": ",", "probability": 0.2734375 } ] }, { "id": 372, "seek": 118164, "start": 1170.61, "end": 1174.51, "text": " because capital words such as unsubscribe,", "tokens": [ 50714, 570, 4238, 2283, 1270, 382, 2693, 9493, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.20324706949759275, "compression_ratio": 1.7629310344827587, "no_speech_prob": 0.0164031982421875, "words": [ { "start": 1170.61, "end": 1170.97, "word": " because", "probability": 0.79248046875 }, { "start": 1170.97, "end": 1171.57, "word": " capital", "probability": 0.82177734375 }, { "start": 1171.57, "end": 1173.13, "word": " words", "probability": 0.7060546875 }, { "start": 1173.13, "end": 1173.61, "word": " such", "probability": 0.5146484375 }, { "start": 1173.61, "end": 1173.89, "word": " as", "probability": 0.9033203125 }, { "start": 1173.89, "end": 1174.35, "word": " unsubscribe", "probability": 0.423583984375 }, { "start": 1174.35, "end": 1174.51, "word": ",", "probability": 0.460693359375 } ] }, { "id": 373, "seek": 118164, "start": 1174.51, "end": 1178.45, "text": " all caps, is the exact same as unsubscribe, lowercase.", "tokens": [ 50914, 439, 13855, 11, 307, 264, 1900, 912, 382, 2693, 9493, 11, 3126, 9765, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.20324706949759275, "compression_ratio": 1.7629310344827587, "no_speech_prob": 0.0164031982421875, "words": [ { "start": 1174.51, "end": 1174.67, "word": " all", "probability": 0.87109375 }, { "start": 1174.67, "end": 1174.99, "word": " caps", "probability": 0.654296875 }, { "start": 1174.99, "end": 1175.05, "word": ",", "probability": 0.51025390625 }, { "start": 1175.05, "end": 1175.15, "word": " is", "probability": 0.83349609375 }, { "start": 1175.15, "end": 1175.27, "word": " the", "probability": 0.80078125 }, { "start": 1175.27, "end": 1175.53, "word": " exact", "probability": 0.83837890625 }, { "start": 1175.53, "end": 1175.91, "word": " same", "probability": 0.82958984375 }, { "start": 1175.91, "end": 1176.71, "word": " as", "probability": 0.87060546875 }, { "start": 1176.71, "end": 1177.37, "word": " unsubscribe", "probability": 0.8017578125 }, { "start": 1177.37, "end": 1177.53, "word": ",", "probability": 0.57470703125 }, { "start": 1177.53, "end": 1178.05, "word": " lowercase", "probability": 0.8408203125 }, { "start": 1178.05, "end": 1178.45, "word": ".", "probability": 0.9833984375 } ] }, { "id": 374, "seek": 118164, "start": 1178.71, "end": 1181.37, "text": " So this is our preprocessing step.", "tokens": [ 51114, 407, 341, 307, 527, 2666, 340, 780, 278, 1823, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.20324706949759275, "compression_ratio": 1.7629310344827587, "no_speech_prob": 0.0164031982421875, "words": [ { "start": 1178.71, "end": 1178.91, "word": " So", "probability": 0.634765625 }, { "start": 1178.91, "end": 1179.81, "word": " this", "probability": 0.64697265625 }, { "start": 1179.81, "end": 1179.93, "word": " is", "probability": 0.90185546875 }, { "start": 1179.93, "end": 1180.07, "word": " our", "probability": 0.8193359375 }, { "start": 1180.07, "end": 1180.79, "word": " preprocessing", "probability": 0.85052490234375 }, { "start": 1180.79, "end": 1181.13, "word": " step", "probability": 0.8232421875 }, { "start": 1181.13, "end": 1181.37, "word": ".", "probability": 0.5244140625 } ] }, { "id": 375, "seek": 118164, "start": 1181.37, "end": 1183.37, "text": " And what we did was we removed all the stop words.", "tokens": [ 51264, 400, 437, 321, 630, 390, 321, 7261, 439, 264, 1590, 2283, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.20324706949759275, "compression_ratio": 1.7629310344827587, "no_speech_prob": 0.0164031982421875, "words": [ { "start": 1181.37, "end": 1181.49, "word": " And", "probability": 0.74365234375 }, { "start": 1181.49, "end": 1181.67, "word": " what", "probability": 0.87744140625 }, { "start": 1181.67, "end": 1181.81, "word": " we", "probability": 0.90673828125 }, { "start": 1181.81, "end": 1181.97, "word": " did", "probability": 0.900390625 }, { "start": 1181.97, "end": 1182.13, "word": " was", "probability": 0.8642578125 }, { "start": 1182.13, "end": 1182.25, "word": " we", "probability": 0.79638671875 }, { "start": 1182.25, "end": 1182.45, "word": " removed", "probability": 0.69140625 }, { "start": 1182.45, "end": 1182.63, "word": " all", "probability": 0.88232421875 }, { "start": 1182.63, "end": 1182.79, "word": " the", "probability": 0.63916015625 }, { "start": 1182.79, "end": 1183.05, "word": " stop", "probability": 0.8505859375 }, { "start": 1183.05, "end": 1183.25, "word": " words", "probability": 0.65185546875 }, { "start": 1183.25, "end": 1183.37, "word": ".", "probability": 0.6455078125 } ] }, { "id": 376, "seek": 118164, "start": 1183.37, "end": 1187.07, "text": " We removed re, in, for, your, did, it, for.", "tokens": [ 51364, 492, 7261, 319, 11, 294, 11, 337, 11, 428, 11, 630, 11, 309, 11, 337, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.20324706949759275, "compression_ratio": 1.7629310344827587, "no_speech_prob": 0.0164031982421875, "words": [ { "start": 1183.37, "end": 1183.41, "word": " We", "probability": 0.8984375 }, { "start": 1183.41, "end": 1183.67, "word": " removed", "probability": 0.7216796875 }, { "start": 1183.67, "end": 1184.03, "word": " re", "probability": 0.2357177734375 }, { "start": 1184.03, "end": 1184.31, "word": ",", "probability": 0.88916015625 }, { "start": 1184.31, "end": 1184.77, "word": " in", "probability": 0.80419921875 }, { "start": 1184.77, "end": 1184.93, "word": ",", "probability": 0.85888671875 }, { "start": 1184.93, "end": 1185.21, "word": " for", "probability": 0.896484375 }, { "start": 1185.21, "end": 1185.41, "word": ",", "probability": 0.99267578125 }, { "start": 1185.41, "end": 1185.61, "word": " your", "probability": 0.77392578125 }, { "start": 1185.61, "end": 1185.77, "word": ",", "probability": 0.9921875 }, { "start": 1185.77, "end": 1185.99, "word": " did", "probability": 0.8984375 }, { "start": 1185.99, "end": 1186.13, "word": ",", "probability": 0.91357421875 }, { "start": 1186.13, "end": 1186.33, "word": " it", "probability": 0.888671875 }, { "start": 1186.33, "end": 1186.41, "word": ",", "probability": 0.98779296875 }, { "start": 1186.41, "end": 1186.67, "word": " for", "probability": 0.89990234375 }, { "start": 1186.67, "end": 1187.07, "word": ".", "probability": 0.66455078125 } ] }, { "id": 377, "seek": 118164, "start": 1188.13, "end": 1190.35, "text": " And then we're going to stem the words.", "tokens": [ 51614, 400, 550, 321, 434, 516, 281, 12312, 264, 2283, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.20324706949759275, "compression_ratio": 1.7629310344827587, "no_speech_prob": 0.0164031982421875, "words": [ { "start": 1188.13, "end": 1188.53, "word": " And", "probability": 0.884765625 }, { "start": 1188.53, "end": 1188.67, "word": " then", "probability": 0.7265625 }, { "start": 1188.67, "end": 1188.85, "word": " we're", "probability": 0.908203125 }, { "start": 1188.85, "end": 1189.09, "word": " going", "probability": 0.8564453125 }, { "start": 1189.09, "end": 1189.49, "word": " to", "probability": 0.90625 }, { "start": 1189.49, "end": 1189.89, "word": " stem", "probability": 0.8349609375 }, { "start": 1189.89, "end": 1190.05, "word": " the", "probability": 0.80615234375 }, { "start": 1190.05, "end": 1190.27, "word": " words", "probability": 0.67919921875 }, { "start": 1190.27, "end": 1190.35, "word": ".", "probability": 0.98828125 } ] }, { "id": 378, "seek": 118164, "start": 1190.35, "end": 1192.57, "text": " I didn't show the stemming in here,", "tokens": [ 51714, 286, 994, 380, 855, 264, 12312, 2810, 294, 510, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.20324706949759275, "compression_ratio": 1.7629310344827587, "no_speech_prob": 0.0164031982421875, "words": [ { "start": 1190.35, "end": 1190.43, "word": " I", "probability": 0.99755859375 }, { "start": 1190.43, "end": 1190.65, "word": " didn't", "probability": 0.923583984375 }, { "start": 1190.65, "end": 1190.97, "word": " show", "probability": 0.86767578125 }, { "start": 1190.97, "end": 1191.29, "word": " the", "probability": 0.7861328125 }, { "start": 1191.29, "end": 1191.73, "word": " stemming", "probability": 0.91748046875 }, { "start": 1191.73, "end": 1191.91, "word": " in", "probability": 0.8974609375 }, { "start": 1191.91, "end": 1192.19, "word": " here", "probability": 0.8125 }, { "start": 1192.19, "end": 1192.57, "word": ",", "probability": 0.397216796875 } ] }, { "id": 379, "seek": 120994, "start": 1192.57, "end": 1194.59, "text": " and we'll see in the workbook as we go along", "tokens": [ 50364, 293, 321, 603, 536, 294, 264, 589, 2939, 382, 321, 352, 2051, 50464 ], "temperature": 0.0, "avg_logprob": -0.16006679821560402, "compression_ratio": 1.8619246861924685, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1192.57, "end": 1192.83, "word": " and", "probability": 0.281005859375 }, { "start": 1192.83, "end": 1193.05, "word": " we'll", "probability": 0.904541015625 }, { "start": 1193.05, "end": 1193.23, "word": " see", "probability": 0.8154296875 }, { "start": 1193.23, "end": 1193.31, "word": " in", "probability": 0.90087890625 }, { "start": 1193.31, "end": 1193.43, "word": " the", "probability": 0.8154296875 }, { "start": 1193.43, "end": 1193.85, "word": " workbook", "probability": 0.88037109375 }, { "start": 1193.85, "end": 1194.05, "word": " as", "probability": 0.8115234375 }, { "start": 1194.05, "end": 1194.17, "word": " we", "probability": 0.90576171875 }, { "start": 1194.17, "end": 1194.29, "word": " go", "probability": 0.89404296875 }, { "start": 1194.29, "end": 1194.59, "word": " along", "probability": 0.88671875 } ] }, { "id": 380, "seek": 120994, "start": 1194.59, "end": 1196.49, "text": " what the stemming actually looks like.", "tokens": [ 50464, 437, 264, 12312, 2810, 767, 1542, 411, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.16006679821560402, "compression_ratio": 1.8619246861924685, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1194.59, "end": 1194.79, "word": " what", "probability": 0.77685546875 }, { "start": 1194.79, "end": 1194.95, "word": " the", "probability": 0.79638671875 }, { "start": 1194.95, "end": 1195.19, "word": " stemming", "probability": 0.92041015625 }, { "start": 1195.19, "end": 1195.49, "word": " actually", "probability": 0.7802734375 }, { "start": 1195.49, "end": 1195.75, "word": " looks", "probability": 0.8046875 }, { "start": 1195.75, "end": 1196.01, "word": " like", "probability": 0.87939453125 }, { "start": 1196.01, "end": 1196.49, "word": ".", "probability": 0.591796875 } ] }, { "id": 381, "seek": 120994, "start": 1196.77, "end": 1200.13, "text": " But we can see that we kind of shrunk the email a little bit,", "tokens": [ 50564, 583, 321, 393, 536, 300, 321, 733, 295, 9884, 3197, 264, 3796, 257, 707, 857, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.16006679821560402, "compression_ratio": 1.8619246861924685, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1196.77, "end": 1197.01, "word": " But", "probability": 0.7333984375 }, { "start": 1197.01, "end": 1197.13, "word": " we", "probability": 0.8818359375 }, { "start": 1197.13, "end": 1197.27, "word": " can", "probability": 0.89501953125 }, { "start": 1197.27, "end": 1197.51, "word": " see", "probability": 0.8173828125 }, { "start": 1197.51, "end": 1197.81, "word": " that", "probability": 0.8740234375 }, { "start": 1197.81, "end": 1198.13, "word": " we", "probability": 0.8984375 }, { "start": 1198.13, "end": 1198.43, "word": " kind", "probability": 0.71826171875 }, { "start": 1198.43, "end": 1198.53, "word": " of", "probability": 0.8974609375 }, { "start": 1198.53, "end": 1198.87, "word": " shrunk", "probability": 0.906005859375 }, { "start": 1198.87, "end": 1199.07, "word": " the", "probability": 0.8095703125 }, { "start": 1199.07, "end": 1199.31, "word": " email", "probability": 0.87646484375 }, { "start": 1199.55, "end": 1199.67, "word": " a little", "probability": 0.806640625 }, { "start": 1199.67, "end": 1199.93, "word": " bit", "probability": 0.89599609375 }, { "start": 1199.93, "end": 1200.13, "word": ",", "probability": 0.367919921875 } ] }, { "id": 382, "seek": 120994, "start": 1200.13, "end": 1201.91, "text": " and this is going to be a little easier", "tokens": [ 50714, 293, 341, 307, 516, 281, 312, 257, 707, 3571, 50814 ], "temperature": 0.0, "avg_logprob": -0.16006679821560402, "compression_ratio": 1.8619246861924685, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1200.13, "end": 1200.73, "word": " and", "probability": 0.89404296875 }, { "start": 1200.73, "end": 1200.91, "word": " this", "probability": 0.884765625 }, { "start": 1200.91, "end": 1201.03, "word": " is", "probability": 0.90625 }, { "start": 1201.03, "end": 1201.11, "word": " going", "probability": 0.662109375 }, { "start": 1201.11, "end": 1201.15, "word": " to", "probability": 0.90625 }, { "start": 1201.15, "end": 1201.27, "word": " be", "probability": 0.904296875 }, { "start": 1201.41, "end": 1201.53, "word": " a little", "probability": 0.8056640625 }, { "start": 1201.53, "end": 1201.91, "word": " easier", "probability": 0.90869140625 } ] }, { "id": 383, "seek": 120994, "start": 1201.91, "end": 1205.27, "text": " for us to compare emails to each other.", "tokens": [ 50814, 337, 505, 281, 6794, 12524, 281, 1184, 661, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.16006679821560402, "compression_ratio": 1.8619246861924685, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1201.91, "end": 1202.13, "word": " for", "probability": 0.89208984375 }, { "start": 1202.13, "end": 1202.31, "word": " us", "probability": 0.9013671875 }, { "start": 1202.31, "end": 1202.43, "word": " to", "probability": 0.90576171875 }, { "start": 1202.43, "end": 1202.79, "word": " compare", "probability": 0.86865234375 }, { "start": 1202.79, "end": 1203.37, "word": " emails", "probability": 0.80517578125 }, { "start": 1203.37, "end": 1204.13, "word": " to", "probability": 0.89697265625 }, { "start": 1204.13, "end": 1204.49, "word": " each", "probability": 0.861328125 }, { "start": 1204.49, "end": 1204.79, "word": " other", "probability": 0.7841796875 }, { "start": 1204.79, "end": 1205.27, "word": ".", "probability": 0.98046875 } ] }, { "id": 384, "seek": 120994, "start": 1206.43, "end": 1209.85, "text": " So I think this is the point", "tokens": [ 51064, 407, 286, 519, 341, 307, 264, 935, 51214 ], "temperature": 0.0, "avg_logprob": -0.16006679821560402, "compression_ratio": 1.8619246861924685, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1206.43, "end": 1206.91, "word": " So", "probability": 0.84375 }, { "start": 1206.91, "end": 1207.17, "word": " I", "probability": 0.7958984375 }, { "start": 1207.17, "end": 1207.47, "word": " think", "probability": 0.810546875 }, { "start": 1207.47, "end": 1208.05, "word": " this", "probability": 0.87353515625 }, { "start": 1208.05, "end": 1208.67, "word": " is", "probability": 0.90380859375 }, { "start": 1208.67, "end": 1209.51, "word": " the", "probability": 0.81298828125 }, { "start": 1209.51, "end": 1209.85, "word": " point", "probability": 0.8642578125 } ] }, { "id": 385, "seek": 120994, "start": 1209.85, "end": 1212.73, "text": " where we can go ahead and open up our workbook.", "tokens": [ 51214, 689, 321, 393, 352, 2286, 293, 1269, 493, 527, 589, 2939, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.16006679821560402, "compression_ratio": 1.8619246861924685, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1209.85, "end": 1210.01, "word": " where", "probability": 0.90087890625 }, { "start": 1210.01, "end": 1210.13, "word": " we", "probability": 0.90380859375 }, { "start": 1210.13, "end": 1210.27, "word": " can", "probability": 0.8974609375 }, { "start": 1210.27, "end": 1210.43, "word": " go", "probability": 0.8955078125 }, { "start": 1210.43, "end": 1210.77, "word": " ahead", "probability": 0.85791015625 }, { "start": 1210.77, "end": 1211.05, "word": " and", "probability": 0.88916015625 }, { "start": 1211.05, "end": 1211.29, "word": " open", "probability": 0.82763671875 }, { "start": 1211.29, "end": 1211.47, "word": " up", "probability": 0.90771484375 }, { "start": 1211.47, "end": 1211.69, "word": " our", "probability": 0.80712890625 }, { "start": 1211.69, "end": 1212.25, "word": " workbook", "probability": 0.88330078125 }, { "start": 1212.25, "end": 1212.73, "word": ".", "probability": 0.884765625 } ] }, { "id": 386, "seek": 120994, "start": 1213.43, "end": 1217.11, "text": " So I'm going to escape out of there, open this up.", "tokens": [ 51414, 407, 286, 478, 516, 281, 7615, 484, 295, 456, 11, 1269, 341, 493, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.16006679821560402, "compression_ratio": 1.8619246861924685, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1213.43, "end": 1213.77, "word": " So", "probability": 0.84423828125 }, { "start": 1213.77, "end": 1214.01, "word": " I'm", "probability": 0.959716796875 }, { "start": 1214.01, "end": 1214.17, "word": " going", "probability": 0.8515625 }, { "start": 1214.17, "end": 1214.45, "word": " to", "probability": 0.904296875 }, { "start": 1214.45, "end": 1214.89, "word": " escape", "probability": 0.7900390625 }, { "start": 1214.89, "end": 1215.11, "word": " out", "probability": 0.8173828125 }, { "start": 1215.11, "end": 1215.23, "word": " of", "probability": 0.9052734375 }, { "start": 1215.23, "end": 1215.49, "word": " there", "probability": 0.861328125 }, { "start": 1215.49, "end": 1215.91, "word": ",", "probability": 0.62841796875 }, { "start": 1215.91, "end": 1216.19, "word": " open", "probability": 0.8203125 }, { "start": 1216.19, "end": 1216.41, "word": " this", "probability": 0.8798828125 }, { "start": 1216.41, "end": 1216.63, "word": " up", "probability": 0.90673828125 }, { "start": 1216.63, "end": 1217.11, "word": ".", "probability": 0.919921875 } ] }, { "id": 387, "seek": 120994, "start": 1217.41, "end": 1218.67, "text": " So for our workshops,", "tokens": [ 51614, 407, 337, 527, 19162, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.16006679821560402, "compression_ratio": 1.8619246861924685, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1217.41, "end": 1217.89, "word": " So", "probability": 0.84716796875 }, { "start": 1217.89, "end": 1218.09, "word": " for", "probability": 0.875 }, { "start": 1218.09, "end": 1218.23, "word": " our", "probability": 0.80419921875 }, { "start": 1218.23, "end": 1218.59, "word": " workshops", "probability": 0.6181640625 }, { "start": 1218.59, "end": 1218.67, "word": ",", "probability": 0.62646484375 } ] }, { "id": 388, "seek": 120994, "start": 1218.67, "end": 1219.79, "text": " we're going to do this for this workshop", "tokens": [ 51664, 321, 434, 516, 281, 360, 341, 337, 341, 13541, 51714 ], "temperature": 0.0, "avg_logprob": -0.16006679821560402, "compression_ratio": 1.8619246861924685, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1218.67, "end": 1218.79, "word": " we're", "probability": 0.924560546875 }, { "start": 1218.79, "end": 1218.85, "word": " going", "probability": 0.7783203125 }, { "start": 1218.85, "end": 1218.91, "word": " to", "probability": 0.90576171875 }, { "start": 1218.91, "end": 1218.99, "word": " do", "probability": 0.90673828125 }, { "start": 1218.99, "end": 1219.15, "word": " this", "probability": 0.87548828125 }, { "start": 1219.15, "end": 1219.25, "word": " for", "probability": 0.81201171875 }, { "start": 1219.25, "end": 1219.45, "word": " this", "probability": 0.8828125 }, { "start": 1219.45, "end": 1219.79, "word": " workshop", "probability": 0.6982421875 } ] }, { "id": 389, "seek": 120994, "start": 1219.79, "end": 1220.87, "text": " and for the other workshops.", "tokens": [ 51714, 293, 337, 264, 661, 19162, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.16006679821560402, "compression_ratio": 1.8619246861924685, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1219.79, "end": 1220.09, "word": " and", "probability": 0.41650390625 }, { "start": 1220.09, "end": 1220.21, "word": " for", "probability": 0.892578125 }, { "start": 1220.21, "end": 1220.33, "word": " the", "probability": 0.81591796875 }, { "start": 1220.33, "end": 1220.47, "word": " other", "probability": 0.794921875 }, { "start": 1220.47, "end": 1220.87, "word": " workshops", "probability": 0.59521484375 }, { "start": 1220.87, "end": 1220.87, "word": ".", "probability": 0.400634765625 } ] }, { "id": 390, "seek": 123394, "start": 1220.87, "end": 1222.49, "text": " We're going to use a system called MyBender.", "tokens": [ 50364, 492, 434, 516, 281, 764, 257, 1185, 1219, 1222, 33, 3216, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.17676957903138127, "compression_ratio": 1.4728260869565217, "no_speech_prob": 0.268798828125, "words": [ { "start": 1220.87, "end": 1221.11, "word": " We're", "probability": 0.6790771484375 }, { "start": 1221.11, "end": 1221.17, "word": " going", "probability": 0.56689453125 }, { "start": 1221.17, "end": 1221.19, "word": " to", "probability": 0.90673828125 }, { "start": 1221.19, "end": 1221.35, "word": " use", "probability": 0.83251953125 }, { "start": 1221.45, "end": 1221.65, "word": " a system", "probability": 0.85546875 }, { "start": 1221.65, "end": 1221.89, "word": " called", "probability": 0.80029296875 }, { "start": 1221.89, "end": 1222.37, "word": " MyBender", "probability": 0.5257161458333334 }, { "start": 1222.37, "end": 1222.49, "word": ".", "probability": 0.83984375 } ] }, { "id": 391, "seek": 123394, "start": 1222.49, "end": 1224.31, "text": " MyBender is fantastic.", "tokens": [ 50464, 1222, 33, 3216, 307, 5456, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.17676957903138127, "compression_ratio": 1.4728260869565217, "no_speech_prob": 0.268798828125, "words": [ { "start": 1222.49, "end": 1222.87, "word": " MyBender", "probability": 0.8274739583333334 }, { "start": 1222.87, "end": 1223.25, "word": " is", "probability": 0.88134765625 }, { "start": 1223.25, "end": 1224.09, "word": " fantastic", "probability": 0.91748046875 }, { "start": 1224.09, "end": 1224.31, "word": ".", "probability": 0.87939453125 } ] }, { "id": 392, "seek": 123394, "start": 1224.31, "end": 1227.87, "text": " It uses Jupyter notebooks in a Docker container.", "tokens": [ 50514, 467, 4960, 22125, 88, 391, 43782, 294, 257, 33772, 10129, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.17676957903138127, "compression_ratio": 1.4728260869565217, "no_speech_prob": 0.268798828125, "words": [ { "start": 1224.31, "end": 1224.31, "word": " It", "probability": 0.88427734375 }, { "start": 1224.31, "end": 1224.49, "word": " uses", "probability": 0.8447265625 }, { "start": 1224.49, "end": 1224.87, "word": " Jupyter", "probability": 0.9093424479166666 }, { "start": 1224.87, "end": 1225.31, "word": " notebooks", "probability": 0.505859375 }, { "start": 1225.31, "end": 1226.71, "word": " in", "probability": 0.8369140625 }, { "start": 1227.05, "end": 1227.29, "word": " a Docker", "probability": 0.419189453125 }, { "start": 1227.29, "end": 1227.71, "word": " container", "probability": 0.81005859375 }, { "start": 1227.71, "end": 1227.87, "word": ".", "probability": 0.84228515625 } ] }, { "id": 393, "seek": 123394, "start": 1227.87, "end": 1231.57, "text": " So I'm going to go ahead and copy this", "tokens": [ 50714, 407, 286, 478, 516, 281, 352, 2286, 293, 5055, 341, 50914 ], "temperature": 0.0, "avg_logprob": -0.17676957903138127, "compression_ratio": 1.4728260869565217, "no_speech_prob": 0.268798828125, "words": [ { "start": 1227.87, "end": 1227.93, "word": " So", "probability": 0.64013671875 }, { "start": 1227.93, "end": 1228.01, "word": " I'm", "probability": 0.693603515625 }, { "start": 1228.01, "end": 1228.07, "word": " going", "probability": 0.7919921875 }, { "start": 1228.07, "end": 1228.09, "word": " to", "probability": 0.8994140625 }, { "start": 1228.09, "end": 1228.19, "word": " go", "probability": 0.85888671875 }, { "start": 1228.19, "end": 1228.63, "word": " ahead", "probability": 0.83203125 }, { "start": 1228.63, "end": 1229.29, "word": " and", "probability": 0.884765625 }, { "start": 1229.29, "end": 1230.91, "word": " copy", "probability": 0.818359375 }, { "start": 1230.91, "end": 1231.57, "word": " this", "probability": 0.8837890625 } ] }, { "id": 394, "seek": 123394, "start": 1231.57, "end": 1236.59, "text": " and send it off into Discord somehow.", "tokens": [ 50914, 293, 2845, 309, 766, 666, 32623, 6063, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.17676957903138127, "compression_ratio": 1.4728260869565217, "no_speech_prob": 0.268798828125, "words": [ { "start": 1231.57, "end": 1232.57, "word": " and", "probability": 0.736328125 }, { "start": 1232.57, "end": 1233.01, "word": " send", "probability": 0.7919921875 }, { "start": 1233.01, "end": 1233.19, "word": " it", "probability": 0.90185546875 }, { "start": 1233.19, "end": 1233.53, "word": " off", "probability": 0.8056640625 }, { "start": 1233.53, "end": 1234.07, "word": " into", "probability": 0.74951171875 }, { "start": 1234.07, "end": 1234.91, "word": " Discord", "probability": 0.6904296875 }, { "start": 1234.91, "end": 1236.05, "word": " somehow", "probability": 0.7783203125 }, { "start": 1236.05, "end": 1236.59, "word": ".", "probability": 0.9736328125 } ] }, { "id": 395, "seek": 123394, "start": 1237.81, "end": 1241.79, "text": " Actually, is there a way...", "tokens": [ 51214, 5135, 11, 307, 456, 257, 636, 485, 51414 ], "temperature": 0.0, "avg_logprob": -0.17676957903138127, "compression_ratio": 1.4728260869565217, "no_speech_prob": 0.268798828125, "words": [ { "start": 1237.81, "end": 1238.35, "word": " Actually", "probability": 0.83447265625 }, { "start": 1238.35, "end": 1238.89, "word": ",", "probability": 0.67041015625 }, { "start": 1238.89, "end": 1240.91, "word": " is", "probability": 0.87890625 }, { "start": 1240.91, "end": 1241.13, "word": " there", "probability": 0.857421875 }, { "start": 1241.31, "end": 1241.79, "word": " a way...", "probability": 0.51239013671875 } ] }, { "id": 396, "seek": 123394, "start": 1241.79, "end": 1244.87, "text": " I'm going to kind of hide my screen for a second.", "tokens": [ 51414, 286, 478, 516, 281, 733, 295, 6479, 452, 2568, 337, 257, 1150, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.17676957903138127, "compression_ratio": 1.4728260869565217, "no_speech_prob": 0.268798828125, "words": [ { "start": 1241.79, "end": 1241.99, "word": " I'm", "probability": 0.982177734375 }, { "start": 1241.99, "end": 1242.15, "word": " going", "probability": 0.85498046875 }, { "start": 1242.15, "end": 1242.51, "word": " to", "probability": 0.90673828125 }, { "start": 1242.51, "end": 1242.73, "word": " kind", "probability": 0.732421875 }, { "start": 1242.73, "end": 1242.85, "word": " of", "probability": 0.90673828125 }, { "start": 1242.85, "end": 1243.15, "word": " hide", "probability": 0.8076171875 }, { "start": 1243.15, "end": 1243.37, "word": " my", "probability": 0.8984375 }, { "start": 1243.37, "end": 1243.73, "word": " screen", "probability": 0.85009765625 }, { "start": 1243.73, "end": 1243.95, "word": " for", "probability": 0.89111328125 }, { "start": 1244.11, "end": 1244.33, "word": " a second", "probability": 0.79248046875 }, { "start": 1244.33, "end": 1244.87, "word": ".", "probability": 0.9453125 } ] }, { "id": 397, "seek": 126334, "start": 1245.73, "end": 1247.21, "text": " Yeah, just post it to me,", "tokens": [ 50414, 865, 11, 445, 2183, 309, 281, 385, 11, 50464 ], "temperature": 0.0, "avg_logprob": -0.15932158425322965, "compression_ratio": 1.4914529914529915, "no_speech_prob": 0.0926513671875, "words": [ { "start": 1245.73, "end": 1246.17, "word": " Yeah", "probability": 0.1982421875 }, { "start": 1246.17, "end": 1246.27, "word": ",", "probability": 0.8232421875 }, { "start": 1246.27, "end": 1246.43, "word": " just", "probability": 0.82373046875 }, { "start": 1246.43, "end": 1246.77, "word": " post", "probability": 0.7998046875 }, { "start": 1246.77, "end": 1246.89, "word": " it", "probability": 0.90625 }, { "start": 1246.89, "end": 1246.99, "word": " to", "probability": 0.900390625 }, { "start": 1246.99, "end": 1247.15, "word": " me", "probability": 0.900390625 }, { "start": 1247.15, "end": 1247.21, "word": ",", "probability": 0.19580078125 } ] }, { "id": 398, "seek": 126334, "start": 1247.21, "end": 1250.53, "text": " and I'll put it in all the places for you.", "tokens": [ 50464, 293, 286, 603, 829, 309, 294, 439, 264, 3190, 337, 291, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.15932158425322965, "compression_ratio": 1.4914529914529915, "no_speech_prob": 0.0926513671875, "words": [ { "start": 1247.21, "end": 1247.27, "word": " and", "probability": 0.87841796875 }, { "start": 1247.27, "end": 1247.97, "word": " I'll", "probability": 0.9697265625 }, { "start": 1247.97, "end": 1248.79, "word": " put", "probability": 0.82080078125 }, { "start": 1248.79, "end": 1248.91, "word": " it", "probability": 0.89111328125 }, { "start": 1248.91, "end": 1249.01, "word": " in", "probability": 0.86279296875 }, { "start": 1249.01, "end": 1249.17, "word": " all", "probability": 0.8818359375 }, { "start": 1249.17, "end": 1249.29, "word": " the", "probability": 0.71044921875 }, { "start": 1249.29, "end": 1249.61, "word": " places", "probability": 0.87744140625 }, { "start": 1249.61, "end": 1249.87, "word": " for", "probability": 0.89404296875 }, { "start": 1249.87, "end": 1250.09, "word": " you", "probability": 0.77294921875 }, { "start": 1250.09, "end": 1250.53, "word": ".", "probability": 0.93017578125 } ] }, { "id": 399, "seek": 126334, "start": 1251.95, "end": 1253.59, "text": " Yeah, absolutely.", "tokens": [ 50714, 865, 11, 3122, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.15932158425322965, "compression_ratio": 1.4914529914529915, "no_speech_prob": 0.0926513671875, "words": [ { "start": 1251.95, "end": 1252.39, "word": " Yeah", "probability": 0.76904296875 }, { "start": 1252.39, "end": 1252.65, "word": ",", "probability": 0.85986328125 }, { "start": 1252.65, "end": 1253.15, "word": " absolutely", "probability": 0.705078125 }, { "start": 1253.15, "end": 1253.59, "word": ".", "probability": 0.97119140625 } ] }, { "id": 400, "seek": 126334, "start": 1255.69, "end": 1256.57, "text": " Okay.", "tokens": [ 50914, 1033, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.15932158425322965, "compression_ratio": 1.4914529914529915, "no_speech_prob": 0.0926513671875, "words": [ { "start": 1255.69, "end": 1256.13, "word": " Okay", "probability": 0.61083984375 }, { "start": 1256.13, "end": 1256.57, "word": ".", "probability": 0.88818359375 } ] }, { "id": 401, "seek": 126334, "start": 1256.83, "end": 1258.29, "text": " All right, perfect.", "tokens": [ 50964, 1057, 558, 11, 2176, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.15932158425322965, "compression_ratio": 1.4914529914529915, "no_speech_prob": 0.0926513671875, "words": [ { "start": 1256.83, "end": 1257.23, "word": " All", "probability": 0.38671875 }, { "start": 1257.23, "end": 1257.35, "word": " right", "probability": 0.87744140625 }, { "start": 1257.35, "end": 1257.53, "word": ",", "probability": 0.529296875 }, { "start": 1257.53, "end": 1257.91, "word": " perfect", "probability": 0.8525390625 }, { "start": 1257.91, "end": 1258.29, "word": ".", "probability": 0.98193359375 } ] }, { "id": 402, "seek": 126334, "start": 1258.29, "end": 1259.41, "text": " Got it.", "tokens": [ 51014, 5803, 309, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.15932158425322965, "compression_ratio": 1.4914529914529915, "no_speech_prob": 0.0926513671875, "words": [ { "start": 1258.29, "end": 1258.69, "word": " Got", "probability": 0.88037109375 }, { "start": 1258.69, "end": 1258.97, "word": " it", "probability": 0.9033203125 }, { "start": 1258.97, "end": 1259.41, "word": ".", "probability": 0.98828125 } ] }, { "id": 403, "seek": 126334, "start": 1260.15, "end": 1261.45, "text": " Display capture.", "tokens": [ 51114, 32229, 7983, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.15932158425322965, "compression_ratio": 1.4914529914529915, "no_speech_prob": 0.0926513671875, "words": [ { "start": 1260.15, "end": 1260.59, "word": " Display", "probability": 0.70458984375 }, { "start": 1260.59, "end": 1261.01, "word": " capture", "probability": 0.48828125 }, { "start": 1261.01, "end": 1261.45, "word": ".", "probability": 0.7490234375 } ] }, { "id": 404, "seek": 126334, "start": 1261.49, "end": 1263.87, "text": " I'm still getting used to OBS and Twitch streaming.", "tokens": [ 51164, 286, 478, 920, 1242, 1143, 281, 422, 8176, 293, 22222, 11791, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.15932158425322965, "compression_ratio": 1.4914529914529915, "no_speech_prob": 0.0926513671875, "words": [ { "start": 1261.49, "end": 1261.75, "word": " I'm", "probability": 0.993408203125 }, { "start": 1261.75, "end": 1261.89, "word": " still", "probability": 0.9072265625 }, { "start": 1261.89, "end": 1262.11, "word": " getting", "probability": 0.88671875 }, { "start": 1262.11, "end": 1262.33, "word": " used", "probability": 0.8203125 }, { "start": 1262.33, "end": 1262.61, "word": " to", "probability": 0.9150390625 }, { "start": 1262.61, "end": 1263.03, "word": " OBS", "probability": 0.958251953125 }, { "start": 1263.03, "end": 1263.23, "word": " and", "probability": 0.8505859375 }, { "start": 1263.23, "end": 1263.41, "word": " Twitch", "probability": 0.91064453125 }, { "start": 1263.41, "end": 1263.73, "word": " streaming", "probability": 0.6923828125 }, { "start": 1263.73, "end": 1263.87, "word": ".", "probability": 0.857421875 } ] }, { "id": 405, "seek": 126334, "start": 1263.87, "end": 1266.59, "text": " I haven't done this before, but I'm really excited.", "tokens": [ 51314, 286, 2378, 380, 1096, 341, 949, 11, 457, 286, 478, 534, 2919, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.15932158425322965, "compression_ratio": 1.4914529914529915, "no_speech_prob": 0.0926513671875, "words": [ { "start": 1263.87, "end": 1263.91, "word": " I", "probability": 0.99853515625 }, { "start": 1263.91, "end": 1264.13, "word": " haven't", "probability": 0.94189453125 }, { "start": 1264.13, "end": 1264.29, "word": " done", "probability": 0.80224609375 }, { "start": 1264.29, "end": 1264.47, "word": " this", "probability": 0.87939453125 }, { "start": 1264.47, "end": 1264.79, "word": " before", "probability": 0.80126953125 }, { "start": 1264.79, "end": 1264.93, "word": ",", "probability": 0.89453125 }, { "start": 1264.93, "end": 1265.13, "word": " but", "probability": 0.90625 }, { "start": 1265.13, "end": 1265.41, "word": " I'm", "probability": 0.9970703125 }, { "start": 1265.41, "end": 1265.79, "word": " really", "probability": 0.78271484375 }, { "start": 1265.79, "end": 1266.15, "word": " excited", "probability": 0.89501953125 }, { "start": 1266.15, "end": 1266.59, "word": ".", "probability": 0.99365234375 } ] }, { "id": 406, "seek": 126334, "start": 1267.99, "end": 1269.61, "text": " So MyBender, once you get the link,", "tokens": [ 51514, 407, 1222, 33, 3216, 11, 1564, 291, 483, 264, 2113, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.15932158425322965, "compression_ratio": 1.4914529914529915, "no_speech_prob": 0.0926513671875, "words": [ { "start": 1267.99, "end": 1268.43, "word": " So", "probability": 0.85302734375 }, { "start": 1268.43, "end": 1268.81, "word": " MyBender", "probability": 0.5723470052083334 }, { "start": 1268.81, "end": 1268.89, "word": ",", "probability": 0.92822265625 }, { "start": 1268.89, "end": 1269.01, "word": " once", "probability": 0.84228515625 }, { "start": 1269.01, "end": 1269.09, "word": " you", "probability": 0.89599609375 }, { "start": 1269.09, "end": 1269.19, "word": " get", "probability": 0.89990234375 }, { "start": 1269.19, "end": 1269.33, "word": " the", "probability": 0.8134765625 }, { "start": 1269.33, "end": 1269.53, "word": " link", "probability": 0.892578125 }, { "start": 1269.53, "end": 1269.61, "word": ",", "probability": 0.951171875 } ] }, { "id": 407, "seek": 126334, "start": 1269.61, "end": 1272.43, "text": " you can just grab that link, paste it in here,", "tokens": [ 51564, 291, 393, 445, 4444, 300, 2113, 11, 9163, 309, 294, 510, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.15932158425322965, "compression_ratio": 1.4914529914529915, "no_speech_prob": 0.0926513671875, "words": [ { "start": 1269.61, "end": 1269.71, "word": " you", "probability": 0.8955078125 }, { "start": 1269.71, "end": 1269.85, "word": " can", "probability": 0.89892578125 }, { "start": 1269.85, "end": 1270.09, "word": " just", "probability": 0.88525390625 }, { "start": 1270.09, "end": 1270.35, "word": " grab", "probability": 0.8134765625 }, { "start": 1270.35, "end": 1270.55, "word": " that", "probability": 0.880859375 }, { "start": 1270.55, "end": 1270.85, "word": " link", "probability": 0.89111328125 }, { "start": 1270.85, "end": 1271.21, "word": ",", "probability": 0.9248046875 }, { "start": 1271.21, "end": 1271.83, "word": " paste", "probability": 0.6689453125 }, { "start": 1271.83, "end": 1272.01, "word": " it", "probability": 0.90087890625 }, { "start": 1272.01, "end": 1272.17, "word": " in", "probability": 0.9052734375 }, { "start": 1272.17, "end": 1272.41, "word": " here", "probability": 0.81201171875 }, { "start": 1272.41, "end": 1272.43, "word": ",", "probability": 0.7802734375 } ] }, { "id": 408, "seek": 126334, "start": 1272.43, "end": 1274.27, "text": " or you can click launch,", "tokens": [ 51714, 420, 291, 393, 2052, 4025, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.15932158425322965, "compression_ratio": 1.4914529914529915, "no_speech_prob": 0.0926513671875, "words": [ { "start": 1272.43, "end": 1272.63, "word": " or", "probability": 0.900390625 }, { "start": 1272.63, "end": 1272.73, "word": " you", "probability": 0.89306640625 }, { "start": 1272.73, "end": 1272.85, "word": " can", "probability": 0.89501953125 }, { "start": 1272.85, "end": 1273.17, "word": " click", "probability": 0.79931640625 }, { "start": 1273.17, "end": 1274.15, "word": " launch", "probability": 0.51513671875 }, { "start": 1274.15, "end": 1274.27, "word": ",", "probability": 0.62548828125 } ] }, { "id": 409, "seek": 129164, "start": 1274.27, "end": 1276.81, "text": " and you can do this with any GitHub repository.", "tokens": [ 50364, 293, 291, 393, 360, 341, 365, 604, 23331, 25841, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.15301723739710346, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.01971435546875, "words": [ { "start": 1274.27, "end": 1274.37, "word": " and", "probability": 0.306396484375 }, { "start": 1274.37, "end": 1274.43, "word": " you", "probability": 0.89501953125 }, { "start": 1274.43, "end": 1274.53, "word": " can", "probability": 0.89453125 }, { "start": 1274.53, "end": 1274.65, "word": " do", "probability": 0.90869140625 }, { "start": 1274.65, "end": 1274.77, "word": " this", "probability": 0.87451171875 }, { "start": 1274.77, "end": 1274.93, "word": " with", "probability": 0.8046875 }, { "start": 1274.93, "end": 1275.23, "word": " any", "probability": 0.794921875 }, { "start": 1275.23, "end": 1275.73, "word": " GitHub", "probability": 0.6982421875 }, { "start": 1275.73, "end": 1276.37, "word": " repository", "probability": 0.865234375 }, { "start": 1276.37, "end": 1276.81, "word": ".", "probability": 0.89404296875 } ] }, { "id": 410, "seek": 129164, "start": 1277.21, "end": 1280.85, "text": " So this is going to launch some Jupyter notebooks.", "tokens": [ 50464, 407, 341, 307, 516, 281, 4025, 512, 22125, 88, 391, 43782, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.15301723739710346, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.01971435546875, "words": [ { "start": 1277.21, "end": 1277.27, "word": " So", "probability": 0.662109375 }, { "start": 1277.27, "end": 1277.47, "word": " this", "probability": 0.736328125 }, { "start": 1277.47, "end": 1277.59, "word": " is", "probability": 0.900390625 }, { "start": 1277.59, "end": 1277.73, "word": " going", "probability": 0.859375 }, { "start": 1277.73, "end": 1277.95, "word": " to", "probability": 0.90576171875 }, { "start": 1277.95, "end": 1278.39, "word": " launch", "probability": 0.93310546875 }, { "start": 1278.39, "end": 1279.05, "word": " some", "probability": 0.84814453125 }, { "start": 1279.05, "end": 1280.11, "word": " Jupyter", "probability": 0.9000651041666666 }, { "start": 1280.11, "end": 1280.55, "word": " notebooks", "probability": 0.47900390625 }, { "start": 1280.55, "end": 1280.85, "word": ".", "probability": 0.8251953125 } ] }, { "id": 411, "seek": 129164, "start": 1280.85, "end": 1285.15, "text": " It takes about a minute or two to spin up.", "tokens": [ 50664, 467, 2516, 466, 257, 3456, 420, 732, 281, 6060, 493, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.15301723739710346, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.01971435546875, "words": [ { "start": 1280.85, "end": 1281.05, "word": " It", "probability": 0.5390625 }, { "start": 1281.05, "end": 1281.33, "word": " takes", "probability": 0.7294921875 }, { "start": 1281.33, "end": 1282.47, "word": " about", "probability": 0.7958984375 }, { "start": 1282.71, "end": 1282.87, "word": " a minute", "probability": 0.87939453125 }, { "start": 1282.87, "end": 1283.09, "word": " or", "probability": 0.90185546875 }, { "start": 1283.09, "end": 1283.39, "word": " two", "probability": 0.8115234375 }, { "start": 1283.39, "end": 1283.87, "word": " to", "probability": 0.90478515625 }, { "start": 1283.87, "end": 1284.45, "word": " spin", "probability": 0.787109375 }, { "start": 1284.45, "end": 1284.71, "word": " up", "probability": 0.8984375 }, { "start": 1284.71, "end": 1285.15, "word": ".", "probability": 0.62451171875 } ] }, { "id": 412, "seek": 129164, "start": 1285.43, "end": 1288.87, "text": " So I'm going to let you guys get that link from the TA,", "tokens": [ 50914, 407, 286, 478, 516, 281, 718, 291, 1074, 483, 300, 2113, 490, 264, 20094, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.15301723739710346, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.01971435546875, "words": [ { "start": 1285.43, "end": 1285.63, "word": " So", "probability": 0.81591796875 }, { "start": 1285.63, "end": 1285.89, "word": " I'm", "probability": 0.937255859375 }, { "start": 1285.89, "end": 1285.95, "word": " going", "probability": 0.50439453125 }, { "start": 1285.95, "end": 1285.95, "word": " to", "probability": 0.90087890625 }, { "start": 1285.95, "end": 1286.11, "word": " let", "probability": 0.9052734375 }, { "start": 1286.11, "end": 1286.21, "word": " you", "probability": 0.89892578125 }, { "start": 1286.21, "end": 1286.65, "word": " guys", "probability": 0.90234375 }, { "start": 1286.65, "end": 1287.11, "word": " get", "probability": 0.896484375 }, { "start": 1287.11, "end": 1287.31, "word": " that", "probability": 0.876953125 }, { "start": 1287.31, "end": 1287.61, "word": " link", "probability": 0.89794921875 }, { "start": 1287.61, "end": 1288.13, "word": " from", "probability": 0.81298828125 }, { "start": 1288.13, "end": 1288.37, "word": " the", "probability": 0.8154296875 }, { "start": 1288.37, "end": 1288.65, "word": " TA", "probability": 0.91845703125 }, { "start": 1288.65, "end": 1288.87, "word": ",", "probability": 0.60498046875 } ] }, { "id": 413, "seek": 129164, "start": 1288.87, "end": 1290.45, "text": " from the workshops channel,", "tokens": [ 51064, 490, 264, 19162, 2269, 11, 51164 ], "temperature": 0.0, "avg_logprob": -0.15301723739710346, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.01971435546875, "words": [ { "start": 1288.87, "end": 1288.99, "word": " from", "probability": 0.794921875 }, { "start": 1288.99, "end": 1289.11, "word": " the", "probability": 0.80224609375 }, { "start": 1289.11, "end": 1289.47, "word": " workshops", "probability": 0.412109375 }, { "start": 1289.47, "end": 1289.87, "word": " channel", "probability": 0.7626953125 }, { "start": 1289.87, "end": 1290.45, "word": ",", "probability": 0.4384765625 } ] }, { "id": 414, "seek": 129164, "start": 1290.45, "end": 1294.03, "text": " and then I'll let this spin up for me.", "tokens": [ 51164, 293, 550, 286, 603, 718, 341, 6060, 493, 337, 385, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.15301723739710346, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.01971435546875, "words": [ { "start": 1290.45, "end": 1290.63, "word": " and", "probability": 0.88623046875 }, { "start": 1290.63, "end": 1291.01, "word": " then", "probability": 0.72705078125 }, { "start": 1291.01, "end": 1292.59, "word": " I'll", "probability": 0.956787109375 }, { "start": 1292.59, "end": 1292.73, "word": " let", "probability": 0.89501953125 }, { "start": 1292.73, "end": 1292.97, "word": " this", "probability": 0.880859375 }, { "start": 1292.97, "end": 1293.43, "word": " spin", "probability": 0.80322265625 }, { "start": 1293.43, "end": 1293.57, "word": " up", "probability": 0.90234375 }, { "start": 1293.57, "end": 1293.71, "word": " for", "probability": 0.89501953125 }, { "start": 1293.71, "end": 1293.91, "word": " me", "probability": 0.9013671875 }, { "start": 1293.91, "end": 1294.03, "word": ".", "probability": 0.673828125 } ] }, { "id": 415, "seek": 129164, "start": 1294.03, "end": 1296.37, "text": " I'll wait a little bit longer so that it spins up for you,", "tokens": [ 51314, 286, 603, 1699, 257, 707, 857, 2854, 370, 300, 309, 31587, 493, 337, 291, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.15301723739710346, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.01971435546875, "words": [ { "start": 1294.03, "end": 1294.19, "word": " I'll", "probability": 0.9765625 }, { "start": 1294.19, "end": 1294.33, "word": " wait", "probability": 0.82421875 }, { "start": 1294.43, "end": 1294.53, "word": " a little", "probability": 0.7978515625 }, { "start": 1294.53, "end": 1294.73, "word": " bit", "probability": 0.88427734375 }, { "start": 1294.73, "end": 1294.99, "word": " longer", "probability": 0.8349609375 }, { "start": 1294.99, "end": 1295.21, "word": " so", "probability": 0.83349609375 }, { "start": 1295.21, "end": 1295.33, "word": " that", "probability": 0.82177734375 }, { "start": 1295.33, "end": 1295.43, "word": " it", "probability": 0.90234375 }, { "start": 1295.43, "end": 1295.63, "word": " spins", "probability": 0.90234375 }, { "start": 1295.63, "end": 1295.79, "word": " up", "probability": 0.908203125 }, { "start": 1295.79, "end": 1295.93, "word": " for", "probability": 0.8994140625 }, { "start": 1295.93, "end": 1296.23, "word": " you", "probability": 0.89111328125 }, { "start": 1296.23, "end": 1296.37, "word": ",", "probability": 0.4912109375 } ] }, { "id": 416, "seek": 129164, "start": 1296.37, "end": 1298.71, "text": " and then we can get moving.", "tokens": [ 51464, 293, 550, 321, 393, 483, 2684, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.15301723739710346, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.01971435546875, "words": [ { "start": 1296.37, "end": 1296.79, "word": " and", "probability": 0.8935546875 }, { "start": 1296.79, "end": 1296.97, "word": " then", "probability": 0.7275390625 }, { "start": 1296.97, "end": 1297.21, "word": " we", "probability": 0.90234375 }, { "start": 1297.21, "end": 1297.39, "word": " can", "probability": 0.89697265625 }, { "start": 1297.39, "end": 1297.85, "word": " get", "probability": 0.90625 }, { "start": 1297.85, "end": 1298.27, "word": " moving", "probability": 0.86865234375 }, { "start": 1298.27, "end": 1298.71, "word": ".", "probability": 0.9912109375 } ] }, { "id": 417, "seek": 129164, "start": 1300.13, "end": 1302.57, "text": " While this is happening, are there any questions?", "tokens": [ 51664, 3987, 341, 307, 2737, 11, 366, 456, 604, 1651, 30, 51764 ], "temperature": 0.0, "avg_logprob": -0.15301723739710346, "compression_ratio": 1.636734693877551, "no_speech_prob": 0.01971435546875, "words": [ { "start": 1300.13, "end": 1300.57, "word": " While", "probability": 0.8955078125 }, { "start": 1300.57, "end": 1300.71, "word": " this", "probability": 0.8779296875 }, { "start": 1300.71, "end": 1300.81, "word": " is", "probability": 0.90087890625 }, { "start": 1300.81, "end": 1301.15, "word": " happening", "probability": 0.73779296875 }, { "start": 1301.15, "end": 1301.31, "word": ",", "probability": 0.87890625 }, { "start": 1301.31, "end": 1301.47, "word": " are", "probability": 0.88671875 }, { "start": 1301.47, "end": 1301.73, "word": " there", "probability": 0.8525390625 }, { "start": 1301.73, "end": 1302.05, "word": " any", "probability": 0.81787109375 }, { "start": 1302.05, "end": 1302.57, "word": " questions", "probability": 0.90478515625 }, { "start": 1302.57, "end": 1302.57, "word": "?", "probability": 0.56103515625 } ] }, { "id": 418, "seek": 131812, "start": 1302.57, "end": 1304.31, "text": " Feel free to just write them in the channel,", "tokens": [ 50364, 14113, 1737, 281, 445, 2464, 552, 294, 264, 2269, 11, 50414 ], "temperature": 0.0, "avg_logprob": -0.18458945464854146, "compression_ratio": 1.6339285714285714, "no_speech_prob": 0.103759765625, "words": [ { "start": 1302.57, "end": 1302.87, "word": " Feel", "probability": 0.2420654296875 }, { "start": 1302.87, "end": 1303.03, "word": " free", "probability": 0.8642578125 }, { "start": 1303.03, "end": 1303.17, "word": " to", "probability": 0.9013671875 }, { "start": 1303.17, "end": 1303.33, "word": " just", "probability": 0.82568359375 }, { "start": 1303.33, "end": 1303.49, "word": " write", "probability": 0.8193359375 }, { "start": 1303.49, "end": 1303.59, "word": " them", "probability": 0.716796875 }, { "start": 1303.59, "end": 1303.67, "word": " in", "probability": 0.8984375 }, { "start": 1303.67, "end": 1303.77, "word": " the", "probability": 0.81396484375 }, { "start": 1303.77, "end": 1304.03, "word": " channel", "probability": 0.80078125 }, { "start": 1304.03, "end": 1304.31, "word": ",", "probability": 0.1868896484375 } ] }, { "id": 419, "seek": 131812, "start": 1304.31, "end": 1306.27, "text": " and the TAs will relay them.", "tokens": [ 50414, 293, 264, 314, 10884, 486, 24214, 552, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.18458945464854146, "compression_ratio": 1.6339285714285714, "no_speech_prob": 0.103759765625, "words": [ { "start": 1304.31, "end": 1304.39, "word": " and", "probability": 0.88671875 }, { "start": 1304.39, "end": 1304.67, "word": " the", "probability": 0.8154296875 }, { "start": 1304.67, "end": 1305.01, "word": " TAs", "probability": 0.850341796875 }, { "start": 1305.01, "end": 1305.19, "word": " will", "probability": 0.79931640625 }, { "start": 1305.19, "end": 1305.47, "word": " relay", "probability": 0.76953125 }, { "start": 1305.47, "end": 1305.75, "word": " them", "probability": 0.72900390625 }, { "start": 1305.75, "end": 1306.27, "word": ".", "probability": 0.96875 } ] }, { "id": 420, "seek": 131812, "start": 1322.57, "end": 1325.91, "text": " And once yours spins up the way that I have this laid out,", "tokens": [ 50614, 400, 1564, 6342, 31587, 493, 264, 636, 300, 286, 362, 341, 9897, 484, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.18458945464854146, "compression_ratio": 1.6339285714285714, "no_speech_prob": 0.103759765625, "words": [ { "start": 1322.57, "end": 1323.09, "word": " And", "probability": 0.7578125 }, { "start": 1323.09, "end": 1323.33, "word": " once", "probability": 0.80322265625 }, { "start": 1323.33, "end": 1323.51, "word": " yours", "probability": 0.505859375 }, { "start": 1323.51, "end": 1323.79, "word": " spins", "probability": 0.8837890625 }, { "start": 1323.79, "end": 1324.05, "word": " up", "probability": 0.90673828125 }, { "start": 1324.05, "end": 1324.21, "word": " the", "probability": 0.6337890625 }, { "start": 1324.21, "end": 1324.33, "word": " way", "probability": 0.89697265625 }, { "start": 1324.33, "end": 1324.45, "word": " that", "probability": 0.85546875 }, { "start": 1324.45, "end": 1324.51, "word": " I", "probability": 0.9912109375 }, { "start": 1324.51, "end": 1324.65, "word": " have", "probability": 0.873046875 }, { "start": 1324.65, "end": 1324.85, "word": " this", "probability": 0.87158203125 }, { "start": 1324.85, "end": 1325.01, "word": " laid", "probability": 0.86669921875 }, { "start": 1325.01, "end": 1325.27, "word": " out", "probability": 0.82470703125 }, { "start": 1325.27, "end": 1325.91, "word": ",", "probability": 0.87646484375 } ] }, { "id": 421, "seek": 131812, "start": 1325.91, "end": 1328.81, "text": " go into the workbooks directory.", "tokens": [ 50814, 352, 666, 264, 589, 15170, 21120, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.18458945464854146, "compression_ratio": 1.6339285714285714, "no_speech_prob": 0.103759765625, "words": [ { "start": 1325.91, "end": 1326.93, "word": " go", "probability": 0.814453125 }, { "start": 1326.93, "end": 1327.13, "word": " into", "probability": 0.755859375 }, { "start": 1327.13, "end": 1327.37, "word": " the", "probability": 0.80810546875 }, { "start": 1327.37, "end": 1327.83, "word": " workbooks", "probability": 0.720947265625 }, { "start": 1327.83, "end": 1328.29, "word": " directory", "probability": 0.82666015625 }, { "start": 1328.29, "end": 1328.81, "word": ".", "probability": 0.95166015625 } ] }, { "id": 422, "seek": 131812, "start": 1329.07, "end": 1332.93, "text": " If you would like to follow along in the live coding session,", "tokens": [ 50964, 759, 291, 576, 411, 281, 1524, 2051, 294, 264, 1621, 17720, 5481, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.18458945464854146, "compression_ratio": 1.6339285714285714, "no_speech_prob": 0.103759765625, "words": [ { "start": 1329.07, "end": 1329.59, "word": " If", "probability": 0.896484375 }, { "start": 1329.59, "end": 1329.79, "word": " you", "probability": 0.89404296875 }, { "start": 1329.79, "end": 1330.03, "word": " would", "probability": 0.84521484375 }, { "start": 1330.03, "end": 1330.23, "word": " like", "probability": 0.8779296875 }, { "start": 1330.23, "end": 1330.43, "word": " to", "probability": 0.904296875 }, { "start": 1330.43, "end": 1330.63, "word": " follow", "probability": 0.8720703125 }, { "start": 1330.63, "end": 1331.09, "word": " along", "probability": 0.8935546875 }, { "start": 1331.09, "end": 1331.29, "word": " in", "probability": 0.8994140625 }, { "start": 1331.29, "end": 1331.41, "word": " the", "probability": 0.79541015625 }, { "start": 1331.41, "end": 1331.71, "word": " live", "probability": 0.876953125 }, { "start": 1331.71, "end": 1332.03, "word": " coding", "probability": 0.84619140625 }, { "start": 1332.03, "end": 1332.49, "word": " session", "probability": 0.82861328125 }, { "start": 1332.49, "end": 1332.93, "word": ",", "probability": 0.919921875 } ] }, { "id": 423, "seek": 131812, "start": 1332.93, "end": 1338.55, "text": " we're going to use the workbook spam filter sklearn document.", "tokens": [ 51114, 321, 434, 516, 281, 764, 264, 589, 2939, 24028, 6608, 1110, 306, 1083, 4166, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.18458945464854146, "compression_ratio": 1.6339285714285714, "no_speech_prob": 0.103759765625, "words": [ { "start": 1332.93, "end": 1333.27, "word": " we're", "probability": 0.91748046875 }, { "start": 1333.27, "end": 1333.47, "word": " going", "probability": 0.857421875 }, { "start": 1333.47, "end": 1333.67, "word": " to", "probability": 0.90673828125 }, { "start": 1333.67, "end": 1334.01, "word": " use", "probability": 0.826171875 }, { "start": 1334.01, "end": 1334.45, "word": " the", "probability": 0.8134765625 }, { "start": 1334.45, "end": 1334.99, "word": " workbook", "probability": 0.75537109375 }, { "start": 1334.99, "end": 1335.27, "word": " spam", "probability": 0.4736328125 }, { "start": 1335.27, "end": 1335.67, "word": " filter", "probability": 0.7578125 }, { "start": 1335.67, "end": 1336.63, "word": " sklearn", "probability": 0.7759602864583334 }, { "start": 1336.63, "end": 1338.07, "word": " document", "probability": 0.80078125 }, { "start": 1338.07, "end": 1338.55, "word": ".", "probability": 0.97802734375 } ] }, { "id": 424, "seek": 131812, "start": 1338.55, "end": 1341.63, "text": " If you are not that familiar with Python,", "tokens": [ 51414, 759, 291, 366, 406, 300, 4963, 365, 15329, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.18458945464854146, "compression_ratio": 1.6339285714285714, "no_speech_prob": 0.103759765625, "words": [ { "start": 1338.55, "end": 1339.07, "word": " If", "probability": 0.89697265625 }, { "start": 1339.07, "end": 1339.33, "word": " you", "probability": 0.8935546875 }, { "start": 1339.33, "end": 1339.73, "word": " are", "probability": 0.8935546875 }, { "start": 1339.73, "end": 1340.13, "word": " not", "probability": 0.89794921875 }, { "start": 1340.13, "end": 1340.33, "word": " that", "probability": 0.87646484375 }, { "start": 1340.33, "end": 1340.57, "word": " familiar", "probability": 0.767578125 }, { "start": 1340.57, "end": 1340.81, "word": " with", "probability": 0.81298828125 }, { "start": 1340.81, "end": 1341.17, "word": " Python", "probability": 0.87109375 }, { "start": 1341.17, "end": 1341.63, "word": ",", "probability": 0.41455078125 } ] }, { "id": 425, "seek": 131812, "start": 1341.63, "end": 1343.57, "text": " and you just want to follow along,", "tokens": [ 51564, 293, 291, 445, 528, 281, 1524, 2051, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.18458945464854146, "compression_ratio": 1.6339285714285714, "no_speech_prob": 0.103759765625, "words": [ { "start": 1341.63, "end": 1341.91, "word": " and", "probability": 0.673828125 }, { "start": 1341.91, "end": 1342.05, "word": " you", "probability": 0.8916015625 }, { "start": 1342.05, "end": 1342.25, "word": " just", "probability": 0.88916015625 }, { "start": 1342.25, "end": 1342.41, "word": " want", "probability": 0.7265625 }, { "start": 1342.41, "end": 1342.53, "word": " to", "probability": 0.90673828125 }, { "start": 1342.53, "end": 1342.75, "word": " follow", "probability": 0.8701171875 }, { "start": 1342.75, "end": 1343.19, "word": " along", "probability": 0.8896484375 }, { "start": 1343.19, "end": 1343.57, "word": ",", "probability": 0.9697265625 } ] }, { "id": 426, "seek": 134692, "start": 1343.57, "end": 1346.31, "text": " you can go ahead and use the completed workbook.", "tokens": [ 50364, 291, 393, 352, 2286, 293, 764, 264, 7365, 589, 2939, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.22400700461084597, "compression_ratio": 1.6835443037974684, "no_speech_prob": 0.25390625, "words": [ { "start": 1343.57, "end": 1343.69, "word": " you", "probability": 0.2548828125 }, { "start": 1343.69, "end": 1343.83, "word": " can", "probability": 0.8603515625 }, { "start": 1343.83, "end": 1343.97, "word": " go", "probability": 0.837890625 }, { "start": 1343.97, "end": 1344.25, "word": " ahead", "probability": 0.841796875 }, { "start": 1344.25, "end": 1344.45, "word": " and", "probability": 0.88720703125 }, { "start": 1344.45, "end": 1344.65, "word": " use", "probability": 0.8212890625 }, { "start": 1344.65, "end": 1344.83, "word": " the", "probability": 0.8076171875 }, { "start": 1344.83, "end": 1345.31, "word": " completed", "probability": 0.6435546875 }, { "start": 1345.31, "end": 1345.87, "word": " workbook", "probability": 0.87841796875 }, { "start": 1345.87, "end": 1346.31, "word": ".", "probability": 0.900390625 } ] }, { "id": 427, "seek": 134692, "start": 1347.87, "end": 1352.83, "text": " I would give it just another couple of minutes to make sure theirs are spun up.", "tokens": [ 50564, 286, 576, 976, 309, 445, 1071, 1916, 295, 2077, 281, 652, 988, 22760, 366, 37038, 493, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.22400700461084597, "compression_ratio": 1.6835443037974684, "no_speech_prob": 0.25390625, "words": [ { "start": 1347.87, "end": 1348.31, "word": " I", "probability": 0.576171875 }, { "start": 1348.31, "end": 1348.49, "word": " would", "probability": 0.8486328125 }, { "start": 1348.49, "end": 1348.67, "word": " give", "probability": 0.8330078125 }, { "start": 1348.67, "end": 1348.81, "word": " it", "probability": 0.89599609375 }, { "start": 1348.81, "end": 1349.29, "word": " just", "probability": 0.87109375 }, { "start": 1349.29, "end": 1349.57, "word": " another", "probability": 0.6708984375 }, { "start": 1349.57, "end": 1349.81, "word": " couple", "probability": 0.8125 }, { "start": 1349.81, "end": 1349.97, "word": " of", "probability": 0.79345703125 }, { "start": 1349.97, "end": 1350.19, "word": " minutes", "probability": 0.88525390625 }, { "start": 1350.19, "end": 1350.47, "word": " to", "probability": 0.7666015625 }, { "start": 1350.47, "end": 1351.13, "word": " make", "probability": 0.607421875 }, { "start": 1351.13, "end": 1351.35, "word": " sure", "probability": 0.8330078125 }, { "start": 1351.35, "end": 1351.73, "word": " theirs", "probability": 0.6904296875 }, { "start": 1351.73, "end": 1351.89, "word": " are", "probability": 0.77001953125 }, { "start": 1351.89, "end": 1352.19, "word": " spun", "probability": 0.84033203125 }, { "start": 1352.19, "end": 1352.39, "word": " up", "probability": 0.80517578125 }, { "start": 1352.39, "end": 1352.83, "word": ".", "probability": 0.94287109375 } ] }, { "id": 428, "seek": 134692, "start": 1352.83, "end": 1354.69, "text": " Yes, absolutely. Absolutely.", "tokens": [ 50814, 1079, 11, 3122, 13, 7021, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.22400700461084597, "compression_ratio": 1.6835443037974684, "no_speech_prob": 0.25390625, "words": [ { "start": 1352.83, "end": 1353.03, "word": " Yes", "probability": 0.8671875 }, { "start": 1353.03, "end": 1353.19, "word": ",", "probability": 0.818359375 }, { "start": 1353.19, "end": 1353.65, "word": " absolutely", "probability": 0.69482421875 }, { "start": 1353.65, "end": 1353.95, "word": ".", "probability": 0.68896484375 }, { "start": 1353.95, "end": 1354.25, "word": " Absolutely", "probability": 0.537109375 }, { "start": 1354.25, "end": 1354.69, "word": ".", "probability": 0.98779296875 } ] }, { "id": 429, "seek": 134692, "start": 1356.05, "end": 1359.17, "text": " So I just want to check something real quick on my other screen.", "tokens": [ 50964, 407, 286, 445, 528, 281, 1520, 746, 957, 1702, 322, 452, 661, 2568, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.22400700461084597, "compression_ratio": 1.6835443037974684, "no_speech_prob": 0.25390625, "words": [ { "start": 1356.05, "end": 1356.49, "word": " So", "probability": 0.6171875 }, { "start": 1356.49, "end": 1356.69, "word": " I", "probability": 0.7197265625 }, { "start": 1356.69, "end": 1356.83, "word": " just", "probability": 0.8857421875 }, { "start": 1356.83, "end": 1356.97, "word": " want", "probability": 0.72412109375 }, { "start": 1356.97, "end": 1357.09, "word": " to", "probability": 0.90869140625 }, { "start": 1357.09, "end": 1357.37, "word": " check", "probability": 0.8505859375 }, { "start": 1357.37, "end": 1357.65, "word": " something", "probability": 0.75048828125 }, { "start": 1357.65, "end": 1357.87, "word": " real", "probability": 0.85693359375 }, { "start": 1357.87, "end": 1358.07, "word": " quick", "probability": 0.9228515625 }, { "start": 1358.07, "end": 1358.19, "word": " on", "probability": 0.8544921875 }, { "start": 1358.19, "end": 1358.29, "word": " my", "probability": 0.83154296875 }, { "start": 1358.29, "end": 1358.45, "word": " other", "probability": 0.7978515625 }, { "start": 1358.45, "end": 1358.73, "word": " screen", "probability": 0.8486328125 }, { "start": 1358.73, "end": 1359.17, "word": ".", "probability": 0.88720703125 } ] }, { "id": 430, "seek": 134692, "start": 1386.8, "end": 1389.14, "text": " And these workbooks outside of this workshop,", "tokens": [ 51214, 400, 613, 589, 15170, 2380, 295, 341, 13541, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.22400700461084597, "compression_ratio": 1.6835443037974684, "no_speech_prob": 0.25390625, "words": [ { "start": 1386.8, "end": 1386.92, "word": " And", "probability": 0.7275390625 }, { "start": 1386.92, "end": 1387.04, "word": " these", "probability": 0.59716796875 }, { "start": 1387.04, "end": 1387.44, "word": " workbooks", "probability": 0.8779296875 }, { "start": 1387.44, "end": 1387.76, "word": " outside", "probability": 0.611328125 }, { "start": 1387.76, "end": 1387.94, "word": " of", "probability": 0.9052734375 }, { "start": 1387.94, "end": 1388.2, "word": " this", "probability": 0.88232421875 }, { "start": 1388.2, "end": 1388.86, "word": " workshop", "probability": 0.5595703125 }, { "start": 1388.86, "end": 1389.14, "word": ",", "probability": 0.77001953125 } ] }, { "id": 431, "seek": 134692, "start": 1389.14, "end": 1391.48, "text": " you can play with them on your own.", "tokens": [ 51314, 291, 393, 862, 365, 552, 322, 428, 1065, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.22400700461084597, "compression_ratio": 1.6835443037974684, "no_speech_prob": 0.25390625, "words": [ { "start": 1389.14, "end": 1389.22, "word": " you", "probability": 0.892578125 }, { "start": 1389.22, "end": 1389.52, "word": " can", "probability": 0.8984375 }, { "start": 1389.52, "end": 1390.24, "word": " play", "probability": 0.85546875 }, { "start": 1390.24, "end": 1390.38, "word": " with", "probability": 0.8212890625 }, { "start": 1390.38, "end": 1390.46, "word": " them", "probability": 0.7431640625 }, { "start": 1390.46, "end": 1390.58, "word": " on", "probability": 0.90673828125 }, { "start": 1390.58, "end": 1390.72, "word": " your", "probability": 0.810546875 }, { "start": 1390.72, "end": 1391.04, "word": " own", "probability": 0.818359375 }, { "start": 1391.04, "end": 1391.48, "word": ".", "probability": 0.96044921875 } ] }, { "id": 432, "seek": 134692, "start": 1391.68, "end": 1395.3, "text": " I have a couple others if you want to take a look.", "tokens": [ 51464, 286, 362, 257, 1916, 2357, 498, 291, 528, 281, 747, 257, 574, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.22400700461084597, "compression_ratio": 1.6835443037974684, "no_speech_prob": 0.25390625, "words": [ { "start": 1391.68, "end": 1392.06, "word": " I", "probability": 0.99365234375 }, { "start": 1392.06, "end": 1392.2, "word": " have", "probability": 0.87646484375 }, { "start": 1392.3, "end": 1392.44, "word": " a couple", "probability": 0.7900390625 }, { "start": 1392.44, "end": 1392.8, "word": " others", "probability": 0.68603515625 }, { "start": 1392.8, "end": 1392.98, "word": " if", "probability": 0.79296875 }, { "start": 1392.98, "end": 1393.12, "word": " you", "probability": 0.8935546875 }, { "start": 1393.12, "end": 1393.38, "word": " want", "probability": 0.8193359375 }, { "start": 1393.38, "end": 1393.7, "word": " to", "probability": 0.9013671875 }, { "start": 1393.7, "end": 1394.6, "word": " take", "probability": 0.78857421875 }, { "start": 1394.7, "end": 1394.86, "word": " a look", "probability": 0.90869140625 }, { "start": 1394.86, "end": 1395.3, "word": ".", "probability": 0.90771484375 } ] }, { "id": 433, "seek": 134692, "start": 1396.16, "end": 1398.12, "text": " But yeah, for the purpose of this workshop,", "tokens": [ 51664, 583, 1338, 11, 337, 264, 4334, 295, 341, 13541, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.22400700461084597, "compression_ratio": 1.6835443037974684, "no_speech_prob": 0.25390625, "words": [ { "start": 1396.16, "end": 1396.6, "word": " But", "probability": 0.8203125 }, { "start": 1396.6, "end": 1397.04, "word": " yeah", "probability": 0.509765625 }, { "start": 1397.04, "end": 1397.04, "word": ",", "probability": 0.939453125 }, { "start": 1397.04, "end": 1397.2, "word": " for", "probability": 0.89892578125 }, { "start": 1397.2, "end": 1397.32, "word": " the", "probability": 0.8115234375 }, { "start": 1397.32, "end": 1397.5, "word": " purpose", "probability": 0.70947265625 }, { "start": 1397.5, "end": 1397.66, "word": " of", "probability": 0.904296875 }, { "start": 1397.66, "end": 1397.82, "word": " this", "probability": 0.88330078125 }, { "start": 1397.82, "end": 1398.12, "word": " workshop", "probability": 0.68798828125 }, { "start": 1398.12, "end": 1398.12, "word": ",", "probability": 0.91357421875 } ] }, { "id": 434, "seek": 137656, "start": 1398.12, "end": 1400.66, "text": " we're going to be using the spam filter sklearn,", "tokens": [ 50364, 321, 434, 516, 281, 312, 1228, 264, 24028, 6608, 1110, 306, 1083, 11, 50464 ], "temperature": 0.0, "avg_logprob": -0.1623114243406674, "compression_ratio": 1.8056872037914693, "no_speech_prob": 0.042724609375, "words": [ { "start": 1398.12, "end": 1398.34, "word": " we're", "probability": 0.542236328125 }, { "start": 1398.34, "end": 1398.46, "word": " going", "probability": 0.60205078125 }, { "start": 1398.46, "end": 1398.46, "word": " to", "probability": 0.90771484375 }, { "start": 1398.46, "end": 1398.58, "word": " be", "probability": 0.8486328125 }, { "start": 1398.58, "end": 1398.8, "word": " using", "probability": 0.84228515625 }, { "start": 1398.8, "end": 1398.98, "word": " the", "probability": 0.79150390625 }, { "start": 1398.98, "end": 1399.18, "word": " spam", "probability": 0.03326416015625 }, { "start": 1399.18, "end": 1399.54, "word": " filter", "probability": 0.833984375 }, { "start": 1399.54, "end": 1400.38, "word": " sklearn", "probability": 0.7898763020833334 }, { "start": 1400.38, "end": 1400.66, "word": ",", "probability": 0.1597900390625 } ] }, { "id": 435, "seek": 137656, "start": 1400.66, "end": 1403.6, "text": " or the completed spam filter sklearn.", "tokens": [ 50464, 420, 264, 7365, 24028, 6608, 1110, 306, 1083, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.1623114243406674, "compression_ratio": 1.8056872037914693, "no_speech_prob": 0.042724609375, "words": [ { "start": 1400.66, "end": 1400.86, "word": " or", "probability": 0.86669921875 }, { "start": 1400.86, "end": 1401.1, "word": " the", "probability": 0.80712890625 }, { "start": 1401.1, "end": 1401.64, "word": " completed", "probability": 0.64990234375 }, { "start": 1401.64, "end": 1402.14, "word": " spam", "probability": 0.7880859375 }, { "start": 1402.14, "end": 1402.44, "word": " filter", "probability": 0.91162109375 }, { "start": 1402.44, "end": 1403.14, "word": " sklearn", "probability": 0.9620768229166666 }, { "start": 1403.14, "end": 1403.6, "word": ".", "probability": 0.93408203125 } ] }, { "id": 436, "seek": 137656, "start": 1412.7, "end": 1413.62, "text": " Okay.", "tokens": [ 50764, 1033, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.1623114243406674, "compression_ratio": 1.8056872037914693, "no_speech_prob": 0.042724609375, "words": [ { "start": 1412.7, "end": 1413.16, "word": " Okay", "probability": 0.43994140625 }, { "start": 1413.16, "end": 1413.62, "word": ".", "probability": 0.40234375 } ] }, { "id": 437, "seek": 137656, "start": 1415.28, "end": 1418.12, "text": " So I'm going to go ahead and start.", "tokens": [ 50864, 407, 286, 478, 516, 281, 352, 2286, 293, 722, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.1623114243406674, "compression_ratio": 1.8056872037914693, "no_speech_prob": 0.042724609375, "words": [ { "start": 1415.28, "end": 1415.74, "word": " So", "probability": 0.83447265625 }, { "start": 1415.74, "end": 1416.2, "word": " I'm", "probability": 0.831787109375 }, { "start": 1416.2, "end": 1416.28, "word": " going", "probability": 0.68798828125 }, { "start": 1416.28, "end": 1416.36, "word": " to", "probability": 0.90576171875 }, { "start": 1416.36, "end": 1416.5, "word": " go", "probability": 0.89404296875 }, { "start": 1416.5, "end": 1416.8, "word": " ahead", "probability": 0.8466796875 }, { "start": 1416.8, "end": 1417.1, "word": " and", "probability": 0.896484375 }, { "start": 1417.1, "end": 1417.66, "word": " start", "probability": 0.861328125 }, { "start": 1417.66, "end": 1418.12, "word": ".", "probability": 0.70849609375 } ] }, { "id": 438, "seek": 137656, "start": 1419.02, "end": 1423.66, "text": " The first couple things that I'm going to go over are just next, next, next run.", "tokens": [ 51064, 440, 700, 1916, 721, 300, 286, 478, 516, 281, 352, 670, 366, 445, 958, 11, 958, 11, 958, 1190, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.1623114243406674, "compression_ratio": 1.8056872037914693, "no_speech_prob": 0.042724609375, "words": [ { "start": 1419.02, "end": 1419.48, "word": " The", "probability": 0.783203125 }, { "start": 1419.48, "end": 1419.9, "word": " first", "probability": 0.81640625 }, { "start": 1419.9, "end": 1420.2, "word": " couple", "probability": 0.7880859375 }, { "start": 1420.2, "end": 1420.5, "word": " things", "probability": 0.6728515625 }, { "start": 1420.5, "end": 1420.62, "word": " that", "probability": 0.77490234375 }, { "start": 1420.62, "end": 1420.72, "word": " I'm", "probability": 0.9892578125 }, { "start": 1420.72, "end": 1420.78, "word": " going", "probability": 0.841796875 }, { "start": 1420.78, "end": 1420.82, "word": " to", "probability": 0.90771484375 }, { "start": 1420.82, "end": 1420.98, "word": " go", "probability": 0.89697265625 }, { "start": 1420.98, "end": 1421.36, "word": " over", "probability": 0.8876953125 }, { "start": 1421.36, "end": 1421.66, "word": " are", "probability": 0.86474609375 }, { "start": 1421.66, "end": 1421.96, "word": " just", "probability": 0.859375 }, { "start": 1421.96, "end": 1422.42, "word": " next", "probability": 0.77294921875 }, { "start": 1422.42, "end": 1422.46, "word": ",", "probability": 0.59033203125 }, { "start": 1422.46, "end": 1422.64, "word": " next", "probability": 0.85498046875 }, { "start": 1422.64, "end": 1422.66, "word": ",", "probability": 0.96142578125 }, { "start": 1422.66, "end": 1422.86, "word": " next", "probability": 0.84912109375 }, { "start": 1422.86, "end": 1423.2, "word": " run", "probability": 0.79541015625 }, { "start": 1423.2, "end": 1423.66, "word": ".", "probability": 0.89501953125 } ] }, { "id": 439, "seek": 137656, "start": 1423.88, "end": 1427.56, "text": " If you're still waiting for your instance to spin up, don't feel bad.", "tokens": [ 51314, 759, 291, 434, 920, 3806, 337, 428, 5197, 281, 6060, 493, 11, 500, 380, 841, 1578, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.1623114243406674, "compression_ratio": 1.8056872037914693, "no_speech_prob": 0.042724609375, "words": [ { "start": 1423.88, "end": 1424.18, "word": " If", "probability": 0.853515625 }, { "start": 1424.18, "end": 1424.3, "word": " you're", "probability": 0.927001953125 }, { "start": 1424.3, "end": 1424.46, "word": " still", "probability": 0.908203125 }, { "start": 1424.46, "end": 1424.64, "word": " waiting", "probability": 0.8369140625 }, { "start": 1424.64, "end": 1424.78, "word": " for", "probability": 0.9013671875 }, { "start": 1424.78, "end": 1424.9, "word": " your", "probability": 0.8076171875 }, { "start": 1424.9, "end": 1425.18, "word": " instance", "probability": 0.923828125 }, { "start": 1425.18, "end": 1425.44, "word": " to", "probability": 0.9091796875 }, { "start": 1425.44, "end": 1425.66, "word": " spin", "probability": 0.84765625 }, { "start": 1425.66, "end": 1425.98, "word": " up", "probability": 0.8974609375 }, { "start": 1425.98, "end": 1426.22, "word": ",", "probability": 0.9169921875 }, { "start": 1426.22, "end": 1426.8, "word": " don't", "probability": 0.94677734375 }, { "start": 1426.8, "end": 1426.94, "word": " feel", "probability": 0.92041015625 }, { "start": 1426.94, "end": 1427.36, "word": " bad", "probability": 0.88720703125 }, { "start": 1427.36, "end": 1427.56, "word": ".", "probability": 0.55810546875 } ] }, { "id": 440, "seek": 137656, "start": 1427.56, "end": 1429.4, "text": " You'll be able to catch up very quickly.", "tokens": [ 51464, 509, 603, 312, 1075, 281, 3745, 493, 588, 2661, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.1623114243406674, "compression_ratio": 1.8056872037914693, "no_speech_prob": 0.042724609375, "words": [ { "start": 1427.56, "end": 1427.84, "word": " You'll", "probability": 0.911376953125 }, { "start": 1427.84, "end": 1427.94, "word": " be", "probability": 0.9091796875 }, { "start": 1427.94, "end": 1428.06, "word": " able", "probability": 0.8740234375 }, { "start": 1428.06, "end": 1428.18, "word": " to", "probability": 0.904296875 }, { "start": 1428.18, "end": 1428.36, "word": " catch", "probability": 0.83740234375 }, { "start": 1428.36, "end": 1428.5, "word": " up", "probability": 0.90283203125 }, { "start": 1428.5, "end": 1428.66, "word": " very", "probability": 0.73486328125 }, { "start": 1428.66, "end": 1428.94, "word": " quickly", "probability": 0.87109375 }, { "start": 1428.94, "end": 1429.4, "word": ".", "probability": 0.990234375 } ] }, { "id": 441, "seek": 137656, "start": 1431.08, "end": 1434.6, "text": " So I'm going to go ahead and open up my spam filter sklearn.", "tokens": [ 51664, 407, 286, 478, 516, 281, 352, 2286, 293, 1269, 493, 452, 24028, 6608, 1110, 306, 1083, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.1623114243406674, "compression_ratio": 1.8056872037914693, "no_speech_prob": 0.042724609375, "words": [ { "start": 1431.08, "end": 1431.54, "word": " So", "probability": 0.8642578125 }, { "start": 1431.54, "end": 1431.66, "word": " I'm", "probability": 0.98779296875 }, { "start": 1431.66, "end": 1431.7, "word": " going", "probability": 0.81689453125 }, { "start": 1431.7, "end": 1431.72, "word": " to", "probability": 0.9033203125 }, { "start": 1431.72, "end": 1431.84, "word": " go", "probability": 0.89453125 }, { "start": 1431.84, "end": 1431.98, "word": " ahead", "probability": 0.85498046875 }, { "start": 1431.98, "end": 1432.06, "word": " and", "probability": 0.89501953125 }, { "start": 1432.06, "end": 1432.26, "word": " open", "probability": 0.822265625 }, { "start": 1432.26, "end": 1432.4, "word": " up", "probability": 0.9013671875 }, { "start": 1432.4, "end": 1432.68, "word": " my", "probability": 0.9052734375 }, { "start": 1432.68, "end": 1433.38, "word": " spam", "probability": 0.87255859375 }, { "start": 1433.38, "end": 1433.7, "word": " filter", "probability": 0.90576171875 }, { "start": 1433.7, "end": 1434.38, "word": " sklearn", "probability": 0.95654296875 }, { "start": 1434.38, "end": 1434.6, "word": ".", "probability": 0.525390625 } ] }, { "id": 442, "seek": 140404, "start": 1434.6, "end": 1437.5, "text": " And in this one, we are going to use scikit-learn,", "tokens": [ 50364, 400, 294, 341, 472, 11, 321, 366, 516, 281, 764, 2180, 22681, 12, 306, 1083, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.19280134620411055, "compression_ratio": 1.6359832635983265, "no_speech_prob": 0.04022216796875, "words": [ { "start": 1434.6, "end": 1434.68, "word": " And", "probability": 0.130859375 }, { "start": 1434.68, "end": 1434.8, "word": " in", "probability": 0.83544921875 }, { "start": 1434.8, "end": 1434.98, "word": " this", "probability": 0.884765625 }, { "start": 1434.98, "end": 1435.18, "word": " one", "probability": 0.8134765625 }, { "start": 1435.18, "end": 1435.32, "word": ",", "probability": 0.58935546875 }, { "start": 1435.32, "end": 1435.38, "word": " we", "probability": 0.89990234375 }, { "start": 1435.38, "end": 1435.5, "word": " are", "probability": 0.67431640625 }, { "start": 1435.5, "end": 1435.72, "word": " going", "probability": 0.86279296875 }, { "start": 1435.72, "end": 1435.9, "word": " to", "probability": 0.904296875 }, { "start": 1435.9, "end": 1436.24, "word": " use", "probability": 0.8056640625 }, { "start": 1436.24, "end": 1436.6, "word": " scikit", "probability": 0.6497802734375 }, { "start": 1436.6, "end": 1436.88, "word": "-learn", "probability": 0.9381510416666666 }, { "start": 1436.88, "end": 1437.5, "word": ",", "probability": 0.75634765625 } ] }, { "id": 443, "seek": 140404, "start": 1437.5, "end": 1440.1, "text": " which is a wonderful abstraction library.", "tokens": [ 50514, 597, 307, 257, 3715, 37765, 6405, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.19280134620411055, "compression_ratio": 1.6359832635983265, "no_speech_prob": 0.04022216796875, "words": [ { "start": 1437.5, "end": 1438.0, "word": " which", "probability": 0.90966796875 }, { "start": 1438.0, "end": 1438.14, "word": " is", "probability": 0.90283203125 }, { "start": 1438.34, "end": 1438.62, "word": " a wonderful", "probability": 0.77587890625 }, { "start": 1438.62, "end": 1439.1, "word": " abstraction", "probability": 0.5791015625 }, { "start": 1439.1, "end": 1439.64, "word": " library", "probability": 0.83740234375 }, { "start": 1439.64, "end": 1440.1, "word": ".", "probability": 0.2313232421875 } ] }, { "id": 444, "seek": 140404, "start": 1440.24, "end": 1441.66, "text": " Great for beginners.", "tokens": [ 50664, 3769, 337, 26992, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.19280134620411055, "compression_ratio": 1.6359832635983265, "no_speech_prob": 0.04022216796875, "words": [ { "start": 1440.24, "end": 1440.7, "word": " Great", "probability": 0.82666015625 }, { "start": 1440.7, "end": 1440.86, "word": " for", "probability": 0.89892578125 }, { "start": 1440.86, "end": 1441.2, "word": " beginners", "probability": 0.72802734375 }, { "start": 1441.2, "end": 1441.66, "word": ".", "probability": 0.98681640625 } ] }, { "id": 445, "seek": 140404, "start": 1443.5, "end": 1447.74, "text": " So we're going to go ahead and install a couple tools.", "tokens": [ 50814, 407, 321, 434, 516, 281, 352, 2286, 293, 3625, 257, 1916, 3873, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.19280134620411055, "compression_ratio": 1.6359832635983265, "no_speech_prob": 0.04022216796875, "words": [ { "start": 1443.5, "end": 1443.96, "word": " So", "probability": 0.83056640625 }, { "start": 1443.96, "end": 1444.2, "word": " we're", "probability": 0.816650390625 }, { "start": 1444.2, "end": 1444.28, "word": " going", "probability": 0.411865234375 }, { "start": 1444.28, "end": 1444.32, "word": " to", "probability": 0.90576171875 }, { "start": 1444.32, "end": 1444.46, "word": " go", "probability": 0.8974609375 }, { "start": 1444.46, "end": 1444.92, "word": " ahead", "probability": 0.84619140625 }, { "start": 1444.92, "end": 1445.58, "word": " and", "probability": 0.8876953125 }, { "start": 1445.58, "end": 1446.46, "word": " install", "probability": 0.8203125 }, { "start": 1446.62, "end": 1446.78, "word": " a couple", "probability": 0.796875 }, { "start": 1446.78, "end": 1447.28, "word": " tools", "probability": 0.58203125 }, { "start": 1447.28, "end": 1447.74, "word": ".", "probability": 0.97021484375 } ] }, { "id": 446, "seek": 140404, "start": 1447.9, "end": 1451.58, "text": " So for these blocks, in order to run them,", "tokens": [ 51014, 407, 337, 613, 8474, 11, 294, 1668, 281, 1190, 552, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.19280134620411055, "compression_ratio": 1.6359832635983265, "no_speech_prob": 0.04022216796875, "words": [ { "start": 1447.9, "end": 1448.0, "word": " So", "probability": 0.80908203125 }, { "start": 1448.0, "end": 1449.24, "word": " for", "probability": 0.74072265625 }, { "start": 1449.24, "end": 1449.44, "word": " these", "probability": 0.705078125 }, { "start": 1449.44, "end": 1449.96, "word": " blocks", "probability": 0.80908203125 }, { "start": 1449.96, "end": 1450.12, "word": ",", "probability": 0.875 }, { "start": 1450.12, "end": 1450.32, "word": " in", "probability": 0.90478515625 }, { "start": 1450.32, "end": 1450.46, "word": " order", "probability": 0.83056640625 }, { "start": 1450.46, "end": 1450.7, "word": " to", "probability": 0.90673828125 }, { "start": 1450.7, "end": 1451.04, "word": " run", "probability": 0.91015625 }, { "start": 1451.04, "end": 1451.38, "word": " them", "probability": 0.73974609375 }, { "start": 1451.38, "end": 1451.58, "word": ",", "probability": 0.935546875 } ] }, { "id": 447, "seek": 140404, "start": 1451.58, "end": 1455.3, "text": " you can click on them and press shift enter,", "tokens": [ 51214, 291, 393, 2052, 322, 552, 293, 1886, 5513, 3242, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.19280134620411055, "compression_ratio": 1.6359832635983265, "no_speech_prob": 0.04022216796875, "words": [ { "start": 1451.58, "end": 1451.72, "word": " you", "probability": 0.8916015625 }, { "start": 1451.72, "end": 1452.02, "word": " can", "probability": 0.89404296875 }, { "start": 1452.02, "end": 1452.32, "word": " click", "probability": 0.81884765625 }, { "start": 1452.32, "end": 1452.5, "word": " on", "probability": 0.91064453125 }, { "start": 1452.5, "end": 1452.76, "word": " them", "probability": 0.7373046875 }, { "start": 1452.76, "end": 1453.14, "word": " and", "probability": 0.85400390625 }, { "start": 1453.14, "end": 1453.62, "word": " press", "probability": 0.71240234375 }, { "start": 1453.62, "end": 1454.12, "word": " shift", "probability": 0.54541015625 }, { "start": 1454.12, "end": 1454.56, "word": " enter", "probability": 0.291259765625 }, { "start": 1454.56, "end": 1455.3, "word": ",", "probability": 0.54248046875 } ] }, { "id": 448, "seek": 140404, "start": 1455.3, "end": 1457.98, "text": " or you can press run button up here.", "tokens": [ 51414, 420, 291, 393, 1886, 1190, 2960, 493, 510, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.19280134620411055, "compression_ratio": 1.6359832635983265, "no_speech_prob": 0.04022216796875, "words": [ { "start": 1455.3, "end": 1455.68, "word": " or", "probability": 0.89794921875 }, { "start": 1455.68, "end": 1455.8, "word": " you", "probability": 0.89501953125 }, { "start": 1455.8, "end": 1455.9, "word": " can", "probability": 0.88818359375 }, { "start": 1455.9, "end": 1456.12, "word": " press", "probability": 0.7001953125 }, { "start": 1456.12, "end": 1456.62, "word": " run", "probability": 0.673828125 }, { "start": 1456.62, "end": 1457.08, "word": " button", "probability": 0.8095703125 }, { "start": 1457.08, "end": 1457.36, "word": " up", "probability": 0.9033203125 }, { "start": 1457.36, "end": 1457.7, "word": " here", "probability": 0.8154296875 }, { "start": 1457.7, "end": 1457.98, "word": ".", "probability": 0.85302734375 } ] }, { "id": 449, "seek": 140404, "start": 1457.98, "end": 1460.26, "text": " You can see that it's running all the Python code.", "tokens": [ 51514, 509, 393, 536, 300, 309, 311, 2614, 439, 264, 15329, 3089, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.19280134620411055, "compression_ratio": 1.6359832635983265, "no_speech_prob": 0.04022216796875, "words": [ { "start": 1457.98, "end": 1458.26, "word": " You", "probability": 0.83642578125 }, { "start": 1458.26, "end": 1458.4, "word": " can", "probability": 0.896484375 }, { "start": 1458.4, "end": 1458.6, "word": " see", "probability": 0.8115234375 }, { "start": 1458.6, "end": 1458.8, "word": " that", "probability": 0.880859375 }, { "start": 1458.8, "end": 1459.0, "word": " it's", "probability": 0.950927734375 }, { "start": 1459.0, "end": 1459.22, "word": " running", "probability": 0.87841796875 }, { "start": 1459.22, "end": 1459.34, "word": " all", "probability": 0.84765625 }, { "start": 1459.34, "end": 1459.44, "word": " the", "probability": 0.81396484375 }, { "start": 1459.44, "end": 1459.72, "word": " Python", "probability": 0.88818359375 }, { "start": 1459.72, "end": 1460.16, "word": " code", "probability": 0.80908203125 }, { "start": 1460.16, "end": 1460.26, "word": ".", "probability": 0.865234375 } ] }, { "id": 450, "seek": 140404, "start": 1460.26, "end": 1462.08, "text": " In this one, I'm just installing the libraries", "tokens": [ 51664, 682, 341, 472, 11, 286, 478, 445, 20762, 264, 15148, 51764 ], "temperature": 0.0, "avg_logprob": -0.19280134620411055, "compression_ratio": 1.6359832635983265, "no_speech_prob": 0.04022216796875, "words": [ { "start": 1460.26, "end": 1460.36, "word": " In", "probability": 0.84228515625 }, { "start": 1460.36, "end": 1460.52, "word": " this", "probability": 0.88330078125 }, { "start": 1460.52, "end": 1460.68, "word": " one", "probability": 0.81787109375 }, { "start": 1460.68, "end": 1460.74, "word": ",", "probability": 0.83447265625 }, { "start": 1460.74, "end": 1460.8, "word": " I'm", "probability": 0.998291015625 }, { "start": 1460.8, "end": 1460.98, "word": " just", "probability": 0.888671875 }, { "start": 1460.98, "end": 1461.44, "word": " installing", "probability": 0.689453125 }, { "start": 1461.44, "end": 1461.64, "word": " the", "probability": 0.814453125 }, { "start": 1461.64, "end": 1462.08, "word": " libraries", "probability": 0.88037109375 } ] }, { "id": 451, "seek": 143078, "start": 1462.08, "end": 1465.14, "text": " and I am configuring the data directory", "tokens": [ 50364, 293, 286, 669, 6662, 1345, 264, 1412, 21120, 50564 ], "temperature": 0.0, "avg_logprob": -0.17057291775320968, "compression_ratio": 1.5666666666666667, "no_speech_prob": 0.030670166015625, "words": [ { "start": 1462.08, "end": 1462.5, "word": " and", "probability": 0.1734619140625 }, { "start": 1462.5, "end": 1462.78, "word": " I", "probability": 0.82421875 }, { "start": 1462.78, "end": 1463.0, "word": " am", "probability": 0.77490234375 }, { "start": 1463.0, "end": 1464.08, "word": " configuring", "probability": 0.87939453125 }, { "start": 1464.08, "end": 1464.34, "word": " the", "probability": 0.8095703125 }, { "start": 1464.34, "end": 1464.64, "word": " data", "probability": 0.7353515625 }, { "start": 1464.64, "end": 1465.14, "word": " directory", "probability": 0.80419921875 } ] }, { "id": 452, "seek": 143078, "start": 1465.88, "end": 1470.14, "text": " where all of our spam and our ham emails will be located.", "tokens": [ 50564, 689, 439, 295, 527, 24028, 293, 527, 7852, 12524, 486, 312, 6870, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.17057291775320968, "compression_ratio": 1.5666666666666667, "no_speech_prob": 0.030670166015625, "words": [ { "start": 1465.88, "end": 1466.4, "word": " where", "probability": 0.82958984375 }, { "start": 1466.4, "end": 1466.6, "word": " all", "probability": 0.89404296875 }, { "start": 1466.6, "end": 1466.72, "word": " of", "probability": 0.88720703125 }, { "start": 1466.72, "end": 1466.86, "word": " our", "probability": 0.82861328125 }, { "start": 1466.86, "end": 1467.24, "word": " spam", "probability": 0.87109375 }, { "start": 1467.24, "end": 1467.54, "word": " and", "probability": 0.8857421875 }, { "start": 1467.54, "end": 1467.74, "word": " our", "probability": 0.77099609375 }, { "start": 1467.74, "end": 1468.04, "word": " ham", "probability": 0.68994140625 }, { "start": 1468.04, "end": 1468.58, "word": " emails", "probability": 0.74853515625 }, { "start": 1468.58, "end": 1469.06, "word": " will", "probability": 0.81591796875 }, { "start": 1469.06, "end": 1469.18, "word": " be", "probability": 0.8984375 }, { "start": 1469.18, "end": 1469.62, "word": " located", "probability": 0.8916015625 }, { "start": 1469.62, "end": 1470.14, "word": ".", "probability": 0.91015625 } ] }, { "id": 453, "seek": 143078, "start": 1471.68, "end": 1476.9, "text": " So that's going to take a little bit while that is going.", "tokens": [ 50864, 407, 300, 311, 516, 281, 747, 257, 707, 857, 1339, 300, 307, 516, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.17057291775320968, "compression_ratio": 1.5666666666666667, "no_speech_prob": 0.030670166015625, "words": [ { "start": 1471.68, "end": 1472.2, "word": " So", "probability": 0.72216796875 }, { "start": 1472.2, "end": 1472.42, "word": " that's", "probability": 0.900634765625 }, { "start": 1472.42, "end": 1472.5, "word": " going", "probability": 0.52880859375 }, { "start": 1472.5, "end": 1472.58, "word": " to", "probability": 0.90234375 }, { "start": 1472.58, "end": 1472.72, "word": " take", "probability": 0.82080078125 }, { "start": 1472.82, "end": 1472.94, "word": " a little", "probability": 0.80908203125 }, { "start": 1472.94, "end": 1473.26, "word": " bit", "probability": 0.8720703125 }, { "start": 1473.26, "end": 1475.36, "word": " while", "probability": 0.720703125 }, { "start": 1475.36, "end": 1475.66, "word": " that", "probability": 0.84375 }, { "start": 1475.66, "end": 1476.02, "word": " is", "probability": 0.88427734375 }, { "start": 1476.02, "end": 1476.38, "word": " going", "probability": 0.8505859375 }, { "start": 1476.38, "end": 1476.9, "word": ".", "probability": 0.88525390625 } ] }, { "id": 454, "seek": 143078, "start": 1477.82, "end": 1481.38, "text": " Just kind of a quick overview of this first block.", "tokens": [ 51164, 1449, 733, 295, 257, 1702, 12492, 295, 341, 700, 3461, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.17057291775320968, "compression_ratio": 1.5666666666666667, "no_speech_prob": 0.030670166015625, "words": [ { "start": 1477.82, "end": 1478.34, "word": " Just", "probability": 0.77490234375 }, { "start": 1478.34, "end": 1478.52, "word": " kind", "probability": 0.73193359375 }, { "start": 1478.52, "end": 1478.56, "word": " of", "probability": 0.90869140625 }, { "start": 1478.68, "end": 1478.86, "word": " a quick", "probability": 0.9208984375 }, { "start": 1478.86, "end": 1479.3, "word": " overview", "probability": 0.81982421875 }, { "start": 1479.3, "end": 1480.02, "word": " of", "probability": 0.90087890625 }, { "start": 1480.02, "end": 1480.6, "word": " this", "probability": 0.87841796875 }, { "start": 1480.6, "end": 1480.84, "word": " first", "probability": 0.81103515625 }, { "start": 1480.84, "end": 1481.22, "word": " block", "probability": 0.8251953125 }, { "start": 1481.22, "end": 1481.38, "word": ".", "probability": 0.607421875 } ] }, { "id": 455, "seek": 143078, "start": 1481.38, "end": 1482.7, "text": " We have our imports.", "tokens": [ 51314, 492, 362, 527, 41596, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.17057291775320968, "compression_ratio": 1.5666666666666667, "no_speech_prob": 0.030670166015625, "words": [ { "start": 1481.38, "end": 1481.74, "word": " We", "probability": 0.8974609375 }, { "start": 1481.74, "end": 1481.88, "word": " have", "probability": 0.87744140625 }, { "start": 1481.88, "end": 1482.0, "word": " our", "probability": 0.81982421875 }, { "start": 1482.0, "end": 1482.44, "word": " imports", "probability": 0.75244140625 }, { "start": 1482.44, "end": 1482.7, "word": ".", "probability": 0.43310546875 } ] }, { "id": 456, "seek": 143078, "start": 1482.7, "end": 1484.58, "text": " So in this case, we're going to use matplotlib.", "tokens": [ 51414, 407, 294, 341, 1389, 11, 321, 434, 516, 281, 764, 3803, 564, 310, 38270, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.17057291775320968, "compression_ratio": 1.5666666666666667, "no_speech_prob": 0.030670166015625, "words": [ { "start": 1482.7, "end": 1482.76, "word": " So", "probability": 0.84521484375 }, { "start": 1482.76, "end": 1482.86, "word": " in", "probability": 0.87109375 }, { "start": 1482.86, "end": 1482.96, "word": " this", "probability": 0.876953125 }, { "start": 1482.96, "end": 1483.12, "word": " case", "probability": 0.80908203125 }, { "start": 1483.12, "end": 1483.14, "word": ",", "probability": 0.55859375 }, { "start": 1483.14, "end": 1483.26, "word": " we're", "probability": 0.919189453125 }, { "start": 1483.26, "end": 1483.32, "word": " going", "probability": 0.70849609375 }, { "start": 1483.32, "end": 1483.34, "word": " to", "probability": 0.90673828125 }, { "start": 1483.34, "end": 1483.5, "word": " use", "probability": 0.8193359375 }, { "start": 1483.5, "end": 1484.4, "word": " matplotlib", "probability": 0.82049560546875 }, { "start": 1484.4, "end": 1484.58, "word": ".", "probability": 0.9306640625 } ] }, { "id": 457, "seek": 143078, "start": 1485.18, "end": 1488.82, "text": " Matplotlib is going to let us print some nice graphs.", "tokens": [ 51514, 6789, 564, 310, 38270, 307, 516, 281, 718, 505, 4482, 512, 1481, 24877, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.17057291775320968, "compression_ratio": 1.5666666666666667, "no_speech_prob": 0.030670166015625, "words": [ { "start": 1485.18, "end": 1485.7, "word": " Matplotlib", "probability": 0.8245849609375 }, { "start": 1485.7, "end": 1485.96, "word": " is", "probability": 0.89208984375 }, { "start": 1485.96, "end": 1486.1, "word": " going", "probability": 0.84912109375 }, { "start": 1486.1, "end": 1486.32, "word": " to", "probability": 0.9052734375 }, { "start": 1486.32, "end": 1486.5, "word": " let", "probability": 0.892578125 }, { "start": 1486.5, "end": 1486.86, "word": " us", "probability": 0.904296875 }, { "start": 1486.86, "end": 1487.42, "word": " print", "probability": 0.86328125 }, { "start": 1487.42, "end": 1487.68, "word": " some", "probability": 0.82568359375 }, { "start": 1487.68, "end": 1488.12, "word": " nice", "probability": 0.82080078125 }, { "start": 1488.12, "end": 1488.58, "word": " graphs", "probability": 0.74951171875 }, { "start": 1488.58, "end": 1488.82, "word": ".", "probability": 0.798828125 } ] }, { "id": 458, "seek": 145892, "start": 1488.82, "end": 1490.36, "text": " NumPy and Pandas is going to let us", "tokens": [ 50364, 22592, 47, 88, 293, 16995, 296, 307, 516, 281, 718, 505, 50464 ], "temperature": 0.0, "avg_logprob": -0.18642241071010457, "compression_ratio": 1.6033755274261603, "no_speech_prob": 0.018829345703125, "words": [ { "start": 1488.82, "end": 1489.12, "word": " NumPy", "probability": 0.7715657552083334 }, { "start": 1489.12, "end": 1489.24, "word": " and", "probability": 0.80126953125 }, { "start": 1489.24, "end": 1489.6, "word": " Pandas", "probability": 0.771728515625 }, { "start": 1489.6, "end": 1489.72, "word": " is", "probability": 0.61328125 }, { "start": 1489.72, "end": 1489.86, "word": " going", "probability": 0.57421875 }, { "start": 1489.86, "end": 1489.94, "word": " to", "probability": 0.90234375 }, { "start": 1489.94, "end": 1490.08, "word": " let", "probability": 0.8720703125 }, { "start": 1490.08, "end": 1490.36, "word": " us", "probability": 0.91357421875 } ] }, { "id": 459, "seek": 145892, "start": 1490.36, "end": 1493.02, "text": " grab some of the information that we need.", "tokens": [ 50464, 4444, 512, 295, 264, 1589, 300, 321, 643, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.18642241071010457, "compression_ratio": 1.6033755274261603, "no_speech_prob": 0.018829345703125, "words": [ { "start": 1490.36, "end": 1491.02, "word": " grab", "probability": 0.7724609375 }, { "start": 1491.02, "end": 1491.2, "word": " some", "probability": 0.77294921875 }, { "start": 1491.2, "end": 1491.28, "word": " of", "probability": 0.8740234375 }, { "start": 1491.28, "end": 1491.34, "word": " the", "probability": 0.8095703125 }, { "start": 1491.34, "end": 1491.76, "word": " information", "probability": 0.74560546875 }, { "start": 1491.76, "end": 1491.96, "word": " that", "probability": 0.80908203125 }, { "start": 1491.96, "end": 1492.06, "word": " we", "probability": 0.90625 }, { "start": 1492.06, "end": 1492.46, "word": " need", "probability": 0.8193359375 }, { "start": 1492.46, "end": 1493.02, "word": ".", "probability": 0.8984375 } ] }, { "id": 460, "seek": 145892, "start": 1493.38, "end": 1496.28, "text": " We're going to use a couple of the others", "tokens": [ 50564, 492, 434, 516, 281, 764, 257, 1916, 295, 264, 2357, 50764 ], "temperature": 0.0, "avg_logprob": -0.18642241071010457, "compression_ratio": 1.6033755274261603, "no_speech_prob": 0.018829345703125, "words": [ { "start": 1493.38, "end": 1493.62, "word": " We're", "probability": 0.906494140625 }, { "start": 1493.62, "end": 1493.7, "word": " going", "probability": 0.77197265625 }, { "start": 1493.7, "end": 1493.78, "word": " to", "probability": 0.9052734375 }, { "start": 1493.78, "end": 1494.3, "word": " use", "probability": 0.82421875 }, { "start": 1495.32, "end": 1495.48, "word": " a couple", "probability": 0.78857421875 }, { "start": 1495.48, "end": 1495.64, "word": " of", "probability": 0.90625 }, { "start": 1495.64, "end": 1495.78, "word": " the", "probability": 0.8017578125 }, { "start": 1495.78, "end": 1496.28, "word": " others", "probability": 0.76318359375 } ] }, { "id": 461, "seek": 145892, "start": 1497.52, "end": 1499.66, "text": " as some support libraries.", "tokens": [ 50764, 382, 512, 1406, 15148, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.18642241071010457, "compression_ratio": 1.6033755274261603, "no_speech_prob": 0.018829345703125, "words": [ { "start": 1497.52, "end": 1498.08, "word": " as", "probability": 0.85498046875 }, { "start": 1498.08, "end": 1498.64, "word": " some", "probability": 0.70263671875 }, { "start": 1498.64, "end": 1499.0, "word": " support", "probability": 0.919921875 }, { "start": 1499.0, "end": 1499.48, "word": " libraries", "probability": 0.89306640625 }, { "start": 1499.48, "end": 1499.66, "word": ".", "probability": 0.416015625 } ] }, { "id": 462, "seek": 145892, "start": 1499.66, "end": 1501.56, "text": " For example, OS, we're going to use that later", "tokens": [ 50914, 1171, 1365, 11, 12731, 11, 321, 434, 516, 281, 764, 300, 1780, 51014 ], "temperature": 0.0, "avg_logprob": -0.18642241071010457, "compression_ratio": 1.6033755274261603, "no_speech_prob": 0.018829345703125, "words": [ { "start": 1499.66, "end": 1499.74, "word": " For", "probability": 0.8994140625 }, { "start": 1499.74, "end": 1500.04, "word": " example", "probability": 0.91796875 }, { "start": 1500.04, "end": 1500.18, "word": ",", "probability": 0.85205078125 }, { "start": 1500.18, "end": 1500.58, "word": " OS", "probability": 0.7099609375 }, { "start": 1500.58, "end": 1500.64, "word": ",", "probability": 0.43359375 }, { "start": 1500.64, "end": 1500.78, "word": " we're", "probability": 0.90576171875 }, { "start": 1500.78, "end": 1500.84, "word": " going", "probability": 0.8359375 }, { "start": 1500.84, "end": 1500.88, "word": " to", "probability": 0.90771484375 }, { "start": 1500.88, "end": 1501.08, "word": " use", "probability": 0.822265625 }, { "start": 1501.08, "end": 1501.3, "word": " that", "probability": 0.87255859375 }, { "start": 1501.3, "end": 1501.56, "word": " later", "probability": 0.8662109375 } ] }, { "id": 463, "seek": 145892, "start": 1501.56, "end": 1504.58, "text": " to kind of grab all of the files.", "tokens": [ 51014, 281, 733, 295, 4444, 439, 295, 264, 7098, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.18642241071010457, "compression_ratio": 1.6033755274261603, "no_speech_prob": 0.018829345703125, "words": [ { "start": 1501.56, "end": 1501.76, "word": " to", "probability": 0.888671875 }, { "start": 1501.76, "end": 1501.94, "word": " kind", "probability": 0.47021484375 }, { "start": 1501.94, "end": 1502.42, "word": " of", "probability": 0.90576171875 }, { "start": 1502.42, "end": 1503.04, "word": " grab", "probability": 0.81884765625 }, { "start": 1503.04, "end": 1503.36, "word": " all", "probability": 0.90185546875 }, { "start": 1503.36, "end": 1503.48, "word": " of", "probability": 0.890625 }, { "start": 1503.48, "end": 1503.62, "word": " the", "probability": 0.80908203125 }, { "start": 1503.62, "end": 1504.02, "word": " files", "probability": 0.8173828125 }, { "start": 1504.02, "end": 1504.58, "word": ".", "probability": 0.9775390625 } ] }, { "id": 464, "seek": 145892, "start": 1505.42, "end": 1507.48, "text": " We want to use NLTK.", "tokens": [ 51214, 492, 528, 281, 764, 426, 43, 51, 42, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.18642241071010457, "compression_ratio": 1.6033755274261603, "no_speech_prob": 0.018829345703125, "words": [ { "start": 1505.42, "end": 1505.9, "word": " We", "probability": 0.888671875 }, { "start": 1505.9, "end": 1506.12, "word": " want", "probability": 0.79443359375 }, { "start": 1506.12, "end": 1506.32, "word": " to", "probability": 0.900390625 }, { "start": 1506.32, "end": 1506.66, "word": " use", "probability": 0.8369140625 }, { "start": 1506.66, "end": 1507.36, "word": " NLTK", "probability": 0.929443359375 }, { "start": 1507.36, "end": 1507.48, "word": ".", "probability": 0.81787109375 } ] }, { "id": 465, "seek": 145892, "start": 1507.48, "end": 1510.58, "text": " NLTK stands for Natural Language Toolkit.", "tokens": [ 51314, 426, 43, 51, 42, 7382, 337, 20137, 24445, 15934, 22681, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.18642241071010457, "compression_ratio": 1.6033755274261603, "no_speech_prob": 0.018829345703125, "words": [ { "start": 1507.48, "end": 1508.04, "word": " NLTK", "probability": 0.9830322265625 }, { "start": 1508.04, "end": 1508.36, "word": " stands", "probability": 0.72216796875 }, { "start": 1508.36, "end": 1508.56, "word": " for", "probability": 0.8916015625 }, { "start": 1508.56, "end": 1508.88, "word": " Natural", "probability": 0.54345703125 }, { "start": 1508.88, "end": 1509.3, "word": " Language", "probability": 0.85791015625 }, { "start": 1509.3, "end": 1510.02, "word": " Toolkit", "probability": 0.883544921875 }, { "start": 1510.02, "end": 1510.58, "word": ".", "probability": 0.7744140625 } ] }, { "id": 466, "seek": 145892, "start": 1510.82, "end": 1514.22, "text": " And so this will allow us to identify our stop words", "tokens": [ 51464, 400, 370, 341, 486, 2089, 505, 281, 5876, 527, 1590, 2283, 51614 ], "temperature": 0.0, "avg_logprob": -0.18642241071010457, "compression_ratio": 1.6033755274261603, "no_speech_prob": 0.018829345703125, "words": [ { "start": 1510.82, "end": 1510.9, "word": " And", "probability": 0.6533203125 }, { "start": 1510.9, "end": 1511.32, "word": " so", "probability": 0.8916015625 }, { "start": 1511.32, "end": 1512.08, "word": " this", "probability": 0.6904296875 }, { "start": 1512.08, "end": 1512.28, "word": " will", "probability": 0.8203125 }, { "start": 1512.28, "end": 1512.5, "word": " allow", "probability": 0.8701171875 }, { "start": 1512.5, "end": 1512.7, "word": " us", "probability": 0.9091796875 }, { "start": 1512.7, "end": 1512.9, "word": " to", "probability": 0.90673828125 }, { "start": 1512.9, "end": 1513.36, "word": " identify", "probability": 0.8916015625 }, { "start": 1513.36, "end": 1513.64, "word": " our", "probability": 0.80224609375 }, { "start": 1513.64, "end": 1513.94, "word": " stop", "probability": 0.89111328125 }, { "start": 1513.94, "end": 1514.22, "word": " words", "probability": 0.623046875 } ] }, { "id": 467, "seek": 145892, "start": 1514.22, "end": 1516.96, "text": " and perform our stemming functions.", "tokens": [ 51614, 293, 2042, 527, 12312, 2810, 6828, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.18642241071010457, "compression_ratio": 1.6033755274261603, "no_speech_prob": 0.018829345703125, "words": [ { "start": 1514.22, "end": 1514.5, "word": " and", "probability": 0.8740234375 }, { "start": 1514.5, "end": 1515.0, "word": " perform", "probability": 0.76416015625 }, { "start": 1515.0, "end": 1515.54, "word": " our", "probability": 0.80029296875 }, { "start": 1515.54, "end": 1516.02, "word": " stemming", "probability": 0.92626953125 }, { "start": 1516.02, "end": 1516.4, "word": " functions", "probability": 0.84765625 }, { "start": 1516.4, "end": 1516.96, "word": ".", "probability": 0.994140625 } ] }, { "id": 468, "seek": 148792, "start": 1518.1, "end": 1521.82, "text": " From scikit-learn, we're going to use a train-test split.", "tokens": [ 50414, 3358, 2180, 22681, 12, 306, 1083, 11, 321, 434, 516, 281, 764, 257, 3847, 12, 31636, 7472, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.18926221132278442, "compression_ratio": 1.7408759124087592, "no_speech_prob": 0.00885009765625, "words": [ { "start": 1518.1, "end": 1518.58, "word": " From", "probability": 0.30029296875 }, { "start": 1518.58, "end": 1518.88, "word": " scikit", "probability": 0.6845703125 }, { "start": 1518.88, "end": 1519.12, "word": "-learn", "probability": 0.9298502604166666 }, { "start": 1519.12, "end": 1519.28, "word": ",", "probability": 0.37548828125 }, { "start": 1519.28, "end": 1519.38, "word": " we're", "probability": 0.863525390625 }, { "start": 1519.38, "end": 1519.58, "word": " going", "probability": 0.8515625 }, { "start": 1519.58, "end": 1519.74, "word": " to", "probability": 0.9052734375 }, { "start": 1519.74, "end": 1519.98, "word": " use", "probability": 0.82568359375 }, { "start": 1520.26, "end": 1520.58, "word": " a train", "probability": 0.58154296875 }, { "start": 1520.58, "end": 1520.98, "word": "-test", "probability": 0.669677734375 }, { "start": 1520.98, "end": 1521.54, "word": " split", "probability": 0.5625 }, { "start": 1521.54, "end": 1521.82, "word": ".", "probability": 0.82763671875 } ] }, { "id": 469, "seek": 148792, "start": 1521.82, "end": 1525.44, "text": " The way that you typically want to train a machine learning model", "tokens": [ 50614, 440, 636, 300, 291, 5850, 528, 281, 3847, 257, 3479, 2539, 2316, 50764 ], "temperature": 0.0, "avg_logprob": -0.18926221132278442, "compression_ratio": 1.7408759124087592, "no_speech_prob": 0.00885009765625, "words": [ { "start": 1521.82, "end": 1521.94, "word": " The", "probability": 0.76806640625 }, { "start": 1521.94, "end": 1522.18, "word": " way", "probability": 0.89599609375 }, { "start": 1522.18, "end": 1522.64, "word": " that", "probability": 0.7666015625 }, { "start": 1522.64, "end": 1522.96, "word": " you", "probability": 0.89453125 }, { "start": 1522.96, "end": 1523.54, "word": " typically", "probability": 0.85400390625 }, { "start": 1523.54, "end": 1523.76, "word": " want", "probability": 0.74658203125 }, { "start": 1523.76, "end": 1523.86, "word": " to", "probability": 0.90234375 }, { "start": 1523.86, "end": 1524.16, "word": " train", "probability": 0.79833984375 }, { "start": 1524.58, "end": 1524.9, "word": " a machine", "probability": 0.66259765625 }, { "start": 1524.9, "end": 1525.18, "word": " learning", "probability": 0.79833984375 }, { "start": 1525.18, "end": 1525.44, "word": " model", "probability": 0.81005859375 } ] }, { "id": 470, "seek": 148792, "start": 1525.44, "end": 1528.58, "text": " is you have a bunch of clean labeled data", "tokens": [ 50764, 307, 291, 362, 257, 3840, 295, 2541, 21335, 1412, 50964 ], "temperature": 0.0, "avg_logprob": -0.18926221132278442, "compression_ratio": 1.7408759124087592, "no_speech_prob": 0.00885009765625, "words": [ { "start": 1525.44, "end": 1525.84, "word": " is", "probability": 0.84521484375 }, { "start": 1525.84, "end": 1526.06, "word": " you", "probability": 0.76904296875 }, { "start": 1526.06, "end": 1526.42, "word": " have", "probability": 0.87646484375 }, { "start": 1526.72, "end": 1527.08, "word": " a bunch", "probability": 0.818359375 }, { "start": 1527.08, "end": 1527.38, "word": " of", "probability": 0.90478515625 }, { "start": 1527.38, "end": 1527.76, "word": " clean", "probability": 0.8408203125 }, { "start": 1527.76, "end": 1528.16, "word": " labeled", "probability": 0.405517578125 }, { "start": 1528.16, "end": 1528.58, "word": " data", "probability": 0.82080078125 } ] }, { "id": 471, "seek": 148792, "start": 1529.34, "end": 1533.28, "text": " and you're going to take probably about 80 or 70% of that", "tokens": [ 50964, 293, 291, 434, 516, 281, 747, 1391, 466, 4688, 420, 5285, 4, 295, 300, 51164 ], "temperature": 0.0, "avg_logprob": -0.18926221132278442, "compression_ratio": 1.7408759124087592, "no_speech_prob": 0.00885009765625, "words": [ { "start": 1529.34, "end": 1529.82, "word": " and", "probability": 0.51513671875 }, { "start": 1529.82, "end": 1530.3, "word": " you're", "probability": 0.885498046875 }, { "start": 1530.3, "end": 1530.48, "word": " going", "probability": 0.859375 }, { "start": 1530.48, "end": 1530.74, "word": " to", "probability": 0.89990234375 }, { "start": 1530.74, "end": 1531.1, "word": " take", "probability": 0.8359375 }, { "start": 1531.1, "end": 1531.48, "word": " probably", "probability": 0.8427734375 }, { "start": 1531.48, "end": 1531.72, "word": " about", "probability": 0.81005859375 }, { "start": 1531.72, "end": 1532.06, "word": " 80", "probability": 0.7978515625 }, { "start": 1532.06, "end": 1532.24, "word": " or", "probability": 0.7646484375 }, { "start": 1532.24, "end": 1532.54, "word": " 70", "probability": 0.89697265625 }, { "start": 1532.54, "end": 1532.82, "word": "%", "probability": 0.45068359375 }, { "start": 1532.82, "end": 1533.02, "word": " of", "probability": 0.90283203125 }, { "start": 1533.02, "end": 1533.28, "word": " that", "probability": 0.87939453125 } ] }, { "id": 472, "seek": 148792, "start": 1533.28, "end": 1535.84, "text": " and use it to train the model.", "tokens": [ 51164, 293, 764, 309, 281, 3847, 264, 2316, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.18926221132278442, "compression_ratio": 1.7408759124087592, "no_speech_prob": 0.00885009765625, "words": [ { "start": 1533.28, "end": 1534.0, "word": " and", "probability": 0.85107421875 }, { "start": 1534.0, "end": 1534.26, "word": " use", "probability": 0.81494140625 }, { "start": 1534.26, "end": 1534.38, "word": " it", "probability": 0.8994140625 }, { "start": 1534.38, "end": 1534.56, "word": " to", "probability": 0.90087890625 }, { "start": 1534.56, "end": 1534.9, "word": " train", "probability": 0.81494140625 }, { "start": 1534.9, "end": 1535.06, "word": " the", "probability": 0.81494140625 }, { "start": 1535.06, "end": 1535.38, "word": " model", "probability": 0.8095703125 }, { "start": 1535.38, "end": 1535.84, "word": ".", "probability": 0.37109375 } ] }, { "id": 473, "seek": 148792, "start": 1535.84, "end": 1537.7, "text": " But then you want to see how well the model is doing.", "tokens": [ 51314, 583, 550, 291, 528, 281, 536, 577, 731, 264, 2316, 307, 884, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.18926221132278442, "compression_ratio": 1.7408759124087592, "no_speech_prob": 0.00885009765625, "words": [ { "start": 1535.84, "end": 1536.06, "word": " But", "probability": 0.80029296875 }, { "start": 1536.06, "end": 1536.16, "word": " then", "probability": 0.71533203125 }, { "start": 1536.16, "end": 1536.24, "word": " you", "probability": 0.85302734375 }, { "start": 1536.24, "end": 1536.34, "word": " want", "probability": 0.7939453125 }, { "start": 1536.34, "end": 1536.4, "word": " to", "probability": 0.90087890625 }, { "start": 1536.4, "end": 1536.5, "word": " see", "probability": 0.80859375 }, { "start": 1536.5, "end": 1536.64, "word": " how", "probability": 0.9033203125 }, { "start": 1536.64, "end": 1536.82, "word": " well", "probability": 0.8662109375 }, { "start": 1536.82, "end": 1536.94, "word": " the", "probability": 0.8125 }, { "start": 1536.94, "end": 1537.12, "word": " model", "probability": 0.7734375 }, { "start": 1537.12, "end": 1537.24, "word": " is", "probability": 0.49365234375 }, { "start": 1537.24, "end": 1537.48, "word": " doing", "probability": 0.91748046875 }, { "start": 1537.48, "end": 1537.7, "word": ".", "probability": 0.587890625 } ] }, { "id": 474, "seek": 148792, "start": 1537.7, "end": 1541.26, "text": " So you're going to use the other 20 or 30% as your testing", "tokens": [ 51414, 407, 291, 434, 516, 281, 764, 264, 661, 945, 420, 2217, 4, 382, 428, 4997, 51564 ], "temperature": 0.0, "avg_logprob": -0.18926221132278442, "compression_ratio": 1.7408759124087592, "no_speech_prob": 0.00885009765625, "words": [ { "start": 1537.7, "end": 1537.8, "word": " So", "probability": 0.8388671875 }, { "start": 1537.8, "end": 1537.96, "word": " you're", "probability": 0.8759765625 }, { "start": 1537.96, "end": 1537.98, "word": " going", "probability": 0.69482421875 }, { "start": 1537.98, "end": 1538.02, "word": " to", "probability": 0.9033203125 }, { "start": 1538.02, "end": 1538.2, "word": " use", "probability": 0.82275390625 }, { "start": 1538.2, "end": 1538.56, "word": " the", "probability": 0.8134765625 }, { "start": 1538.56, "end": 1539.0, "word": " other", "probability": 0.77685546875 }, { "start": 1539.0, "end": 1539.36, "word": " 20", "probability": 0.8896484375 }, { "start": 1539.36, "end": 1539.5, "word": " or", "probability": 0.80029296875 }, { "start": 1539.5, "end": 1539.74, "word": " 30", "probability": 0.9091796875 }, { "start": 1539.74, "end": 1540.06, "word": "%", "probability": 0.9150390625 }, { "start": 1540.06, "end": 1540.54, "word": " as", "probability": 0.89892578125 }, { "start": 1540.54, "end": 1540.78, "word": " your", "probability": 0.61181640625 }, { "start": 1540.78, "end": 1541.26, "word": " testing", "probability": 0.73486328125 } ] }, { "id": 475, "seek": 148792, "start": 1541.26, "end": 1543.06, "text": " and you're going to use this as evaluation.", "tokens": [ 51564, 293, 291, 434, 516, 281, 764, 341, 382, 13344, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.18926221132278442, "compression_ratio": 1.7408759124087592, "no_speech_prob": 0.00885009765625, "words": [ { "start": 1541.26, "end": 1541.54, "word": " and", "probability": 0.58740234375 }, { "start": 1541.54, "end": 1541.66, "word": " you're", "probability": 0.912109375 }, { "start": 1541.66, "end": 1541.74, "word": " going", "probability": 0.82373046875 }, { "start": 1541.74, "end": 1541.78, "word": " to", "probability": 0.90234375 }, { "start": 1541.78, "end": 1541.94, "word": " use", "probability": 0.81884765625 }, { "start": 1541.94, "end": 1542.06, "word": " this", "probability": 0.8466796875 }, { "start": 1542.06, "end": 1542.22, "word": " as", "probability": 0.90185546875 }, { "start": 1542.22, "end": 1542.58, "word": " evaluation", "probability": 0.61181640625 }, { "start": 1542.58, "end": 1543.06, "word": ".", "probability": 0.98486328125 } ] }, { "id": 476, "seek": 148792, "start": 1543.44, "end": 1545.96, "text": " It's kind of the same way we teach students in elementary school.", "tokens": [ 51664, 467, 311, 733, 295, 264, 912, 636, 321, 2924, 1731, 294, 16429, 1395, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.18926221132278442, "compression_ratio": 1.7408759124087592, "no_speech_prob": 0.00885009765625, "words": [ { "start": 1543.44, "end": 1543.64, "word": " It's", "probability": 0.941162109375 }, { "start": 1543.64, "end": 1543.74, "word": " kind", "probability": 0.77490234375 }, { "start": 1543.74, "end": 1543.8, "word": " of", "probability": 0.90673828125 }, { "start": 1543.8, "end": 1543.92, "word": " the", "probability": 0.8125 }, { "start": 1543.92, "end": 1544.06, "word": " same", "probability": 0.818359375 }, { "start": 1544.06, "end": 1544.22, "word": " way", "probability": 0.90234375 }, { "start": 1544.22, "end": 1544.36, "word": " we", "probability": 0.8994140625 }, { "start": 1544.36, "end": 1544.58, "word": " teach", "probability": 0.85791015625 }, { "start": 1544.58, "end": 1544.9, "word": " students", "probability": 0.9150390625 }, { "start": 1544.9, "end": 1545.06, "word": " in", "probability": 0.89990234375 }, { "start": 1545.06, "end": 1545.38, "word": " elementary", "probability": 0.86328125 }, { "start": 1545.38, "end": 1545.78, "word": " school", "probability": 0.9169921875 }, { "start": 1545.78, "end": 1545.96, "word": ".", "probability": 0.8525390625 } ] }, { "id": 477, "seek": 151360, "start": 1545.96, "end": 1548.52, "text": " Here's the bulk of the information and now we're going to test you", "tokens": [ 50364, 1692, 311, 264, 16139, 295, 264, 1589, 293, 586, 321, 434, 516, 281, 1500, 291, 50464 ], "temperature": 0.0, "avg_logprob": -0.2043478294559147, "compression_ratio": 1.6775510204081632, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 1545.96, "end": 1546.24, "word": " Here's", "probability": 0.61083984375 }, { "start": 1546.24, "end": 1546.36, "word": " the", "probability": 0.80810546875 }, { "start": 1546.36, "end": 1546.54, "word": " bulk", "probability": 0.7939453125 }, { "start": 1546.54, "end": 1546.66, "word": " of", "probability": 0.900390625 }, { "start": 1546.66, "end": 1546.78, "word": " the", "probability": 0.80908203125 }, { "start": 1546.78, "end": 1547.26, "word": " information", "probability": 0.73828125 }, { "start": 1547.26, "end": 1547.5, "word": " and", "probability": 0.37060546875 }, { "start": 1547.5, "end": 1547.64, "word": " now", "probability": 0.8564453125 }, { "start": 1547.64, "end": 1547.76, "word": " we're", "probability": 0.91357421875 }, { "start": 1547.76, "end": 1547.94, "word": " going", "probability": 0.84912109375 }, { "start": 1547.94, "end": 1548.08, "word": " to", "probability": 0.90380859375 }, { "start": 1548.08, "end": 1548.38, "word": " test", "probability": 0.81689453125 }, { "start": 1548.38, "end": 1548.52, "word": " you", "probability": 0.88525390625 } ] }, { "id": 478, "seek": 151360, "start": 1548.52, "end": 1550.84, "text": " to see how well you understand it.", "tokens": [ 50464, 281, 536, 577, 731, 291, 1223, 309, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.2043478294559147, "compression_ratio": 1.6775510204081632, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 1548.52, "end": 1548.66, "word": " to", "probability": 0.88134765625 }, { "start": 1548.66, "end": 1548.8, "word": " see", "probability": 0.80810546875 }, { "start": 1548.8, "end": 1548.98, "word": " how", "probability": 0.89453125 }, { "start": 1548.98, "end": 1549.22, "word": " well", "probability": 0.875 }, { "start": 1549.22, "end": 1549.7, "word": " you", "probability": 0.88916015625 }, { "start": 1549.7, "end": 1550.14, "word": " understand", "probability": 0.75146484375 }, { "start": 1550.14, "end": 1550.42, "word": " it", "probability": 0.89404296875 }, { "start": 1550.42, "end": 1550.84, "word": ".", "probability": 0.9443359375 } ] }, { "id": 479, "seek": 151360, "start": 1552.62, "end": 1555.88, "text": " And then our TF-IDF and count vectorizers,", "tokens": [ 50664, 400, 550, 527, 40964, 12, 2777, 37, 293, 1207, 8062, 22525, 11, 50864 ], "temperature": 0.0, "avg_logprob": -0.2043478294559147, "compression_ratio": 1.6775510204081632, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 1552.62, "end": 1552.72, "word": " And", "probability": 0.71728515625 }, { "start": 1552.72, "end": 1552.96, "word": " then", "probability": 0.7294921875 }, { "start": 1552.96, "end": 1553.38, "word": " our", "probability": 0.77490234375 }, { "start": 1553.38, "end": 1553.7, "word": " TF", "probability": 0.74560546875 }, { "start": 1553.7, "end": 1554.12, "word": "-IDF", "probability": 0.8375651041666666 }, { "start": 1554.12, "end": 1554.36, "word": " and", "probability": 0.87548828125 }, { "start": 1554.36, "end": 1554.76, "word": " count", "probability": 0.5615234375 }, { "start": 1554.76, "end": 1555.58, "word": " vectorizers", "probability": 0.927734375 }, { "start": 1555.58, "end": 1555.88, "word": ",", "probability": 0.55126953125 } ] }, { "id": 480, "seek": 151360, "start": 1555.88, "end": 1557.84, "text": " we will get into that in a bit.", "tokens": [ 50864, 321, 486, 483, 666, 300, 294, 257, 857, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.2043478294559147, "compression_ratio": 1.6775510204081632, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 1555.88, "end": 1556.06, "word": " we", "probability": 0.8896484375 }, { "start": 1556.06, "end": 1556.24, "word": " will", "probability": 0.80615234375 }, { "start": 1556.24, "end": 1556.46, "word": " get", "probability": 0.8984375 }, { "start": 1556.46, "end": 1556.72, "word": " into", "probability": 0.73095703125 }, { "start": 1556.72, "end": 1556.98, "word": " that", "probability": 0.88134765625 }, { "start": 1556.98, "end": 1557.14, "word": " in", "probability": 0.89892578125 }, { "start": 1557.3, "end": 1557.5, "word": " a bit", "probability": 0.904296875 }, { "start": 1557.5, "end": 1557.84, "word": ".", "probability": 0.9228515625 } ] }, { "id": 481, "seek": 151360, "start": 1557.84, "end": 1561.22, "text": " These are going to be used for transforming our words", "tokens": [ 50964, 1981, 366, 516, 281, 312, 1143, 337, 27210, 527, 2283, 51114 ], "temperature": 0.0, "avg_logprob": -0.2043478294559147, "compression_ratio": 1.6775510204081632, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 1557.84, "end": 1558.14, "word": " These", "probability": 0.9140625 }, { "start": 1558.14, "end": 1558.32, "word": " are", "probability": 0.89404296875 }, { "start": 1558.32, "end": 1558.5, "word": " going", "probability": 0.86083984375 }, { "start": 1558.5, "end": 1558.62, "word": " to", "probability": 0.90625 }, { "start": 1558.62, "end": 1558.76, "word": " be", "probability": 0.90087890625 }, { "start": 1558.76, "end": 1558.98, "word": " used", "probability": 0.818359375 }, { "start": 1558.98, "end": 1559.28, "word": " for", "probability": 0.89892578125 }, { "start": 1559.28, "end": 1560.0, "word": " transforming", "probability": 0.7802734375 }, { "start": 1560.0, "end": 1560.6, "word": " our", "probability": 0.80078125 }, { "start": 1560.6, "end": 1561.22, "word": " words", "probability": 0.71630859375 } ] }, { "id": 482, "seek": 151360, "start": 1561.22, "end": 1563.88, "text": " into numbers that we can work with.", "tokens": [ 51114, 666, 3547, 300, 321, 393, 589, 365, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.2043478294559147, "compression_ratio": 1.6775510204081632, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 1561.22, "end": 1561.74, "word": " into", "probability": 0.7314453125 }, { "start": 1561.74, "end": 1562.48, "word": " numbers", "probability": 0.86865234375 }, { "start": 1562.48, "end": 1562.78, "word": " that", "probability": 0.87158203125 }, { "start": 1562.78, "end": 1562.9, "word": " we", "probability": 0.904296875 }, { "start": 1562.9, "end": 1563.04, "word": " can", "probability": 0.8955078125 }, { "start": 1563.04, "end": 1563.24, "word": " work", "probability": 0.8203125 }, { "start": 1563.24, "end": 1563.46, "word": " with", "probability": 0.814453125 }, { "start": 1563.46, "end": 1563.88, "word": ".", "probability": 0.9873046875 } ] }, { "id": 483, "seek": 151360, "start": 1564.96, "end": 1567.28, "text": " And then the two models that we're actually going to build out", "tokens": [ 51314, 400, 550, 264, 732, 5245, 300, 321, 434, 767, 516, 281, 1322, 484, 51414 ], "temperature": 0.0, "avg_logprob": -0.2043478294559147, "compression_ratio": 1.6775510204081632, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 1564.96, "end": 1565.38, "word": " And", "probability": 0.841796875 }, { "start": 1565.38, "end": 1565.48, "word": " then", "probability": 0.72412109375 }, { "start": 1565.48, "end": 1565.6, "word": " the", "probability": 0.8037109375 }, { "start": 1565.6, "end": 1565.74, "word": " two", "probability": 0.81640625 }, { "start": 1565.74, "end": 1565.98, "word": " models", "probability": 0.79345703125 }, { "start": 1565.98, "end": 1566.12, "word": " that", "probability": 0.8798828125 }, { "start": 1566.12, "end": 1566.24, "word": " we're", "probability": 0.923095703125 }, { "start": 1566.24, "end": 1566.48, "word": " actually", "probability": 0.78369140625 }, { "start": 1566.48, "end": 1566.7, "word": " going", "probability": 0.8662109375 }, { "start": 1566.7, "end": 1566.82, "word": " to", "probability": 0.90625 }, { "start": 1566.82, "end": 1567.0, "word": " build", "probability": 0.86865234375 }, { "start": 1567.0, "end": 1567.28, "word": " out", "probability": 0.822265625 } ] }, { "id": 484, "seek": 151360, "start": 1567.28, "end": 1570.28, "text": " are going to be the multinomial Naive Bayesian,", "tokens": [ 51414, 366, 516, 281, 312, 264, 45872, 47429, 6056, 488, 7840, 42434, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.2043478294559147, "compression_ratio": 1.6775510204081632, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 1567.28, "end": 1567.78, "word": " are", "probability": 0.86767578125 }, { "start": 1567.78, "end": 1568.08, "word": " going", "probability": 0.84814453125 }, { "start": 1568.08, "end": 1568.22, "word": " to", "probability": 0.90380859375 }, { "start": 1568.22, "end": 1568.34, "word": " be", "probability": 0.90283203125 }, { "start": 1568.34, "end": 1568.5, "word": " the", "probability": 0.79052734375 }, { "start": 1568.5, "end": 1569.4, "word": " multinomial", "probability": 0.8720703125 }, { "start": 1569.4, "end": 1569.78, "word": " Naive", "probability": 0.5908203125 }, { "start": 1569.78, "end": 1570.14, "word": " Bayesian", "probability": 0.9287109375 }, { "start": 1570.14, "end": 1570.28, "word": ",", "probability": 0.7431640625 } ] }, { "id": 485, "seek": 151360, "start": 1570.28, "end": 1571.64, "text": " which we went over in the slides,", "tokens": [ 51564, 597, 321, 1437, 670, 294, 264, 9788, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.2043478294559147, "compression_ratio": 1.6775510204081632, "no_speech_prob": 0.0005526542663574219, "words": [ { "start": 1570.28, "end": 1570.38, "word": " which", "probability": 0.9150390625 }, { "start": 1570.38, "end": 1570.52, "word": " we", "probability": 0.90283203125 }, { "start": 1570.52, "end": 1570.68, "word": " went", "probability": 0.80029296875 }, { "start": 1570.68, "end": 1570.86, "word": " over", "probability": 0.880859375 }, { "start": 1570.86, "end": 1571.0, "word": " in", "probability": 0.9033203125 }, { "start": 1571.0, "end": 1571.12, "word": " the", "probability": 0.810546875 }, { "start": 1571.12, "end": 1571.5, "word": " slides", "probability": 0.9052734375 }, { "start": 1571.5, "end": 1571.64, "word": ",", "probability": 0.5322265625 } ] }, { "id": 486, "seek": 154062, "start": 1571.64, "end": 1575.98, "text": " and then one that is completely unfamiliar, logistic regression.", "tokens": [ 50364, 293, 550, 472, 300, 307, 2584, 29415, 11, 3565, 3142, 24590, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.21030890153742385, "compression_ratio": 1.5454545454545454, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 1571.64, "end": 1571.8, "word": " and", "probability": 0.51220703125 }, { "start": 1571.8, "end": 1571.94, "word": " then", "probability": 0.587890625 }, { "start": 1571.94, "end": 1572.28, "word": " one", "probability": 0.80859375 }, { "start": 1572.28, "end": 1572.74, "word": " that", "probability": 0.86376953125 }, { "start": 1572.74, "end": 1573.08, "word": " is", "probability": 0.90576171875 }, { "start": 1573.08, "end": 1573.56, "word": " completely", "probability": 0.64892578125 }, { "start": 1573.56, "end": 1574.1, "word": " unfamiliar", "probability": 0.80859375 }, { "start": 1574.1, "end": 1574.54, "word": ",", "probability": 0.78076171875 }, { "start": 1574.54, "end": 1574.92, "word": " logistic", "probability": 0.893798828125 }, { "start": 1574.92, "end": 1575.38, "word": " regression", "probability": 0.87744140625 }, { "start": 1575.38, "end": 1575.98, "word": ".", "probability": 0.826171875 } ] }, { "id": 487, "seek": 154062, "start": 1576.02, "end": 1581.24, "text": " And this is to show how incredible machine learning can be", "tokens": [ 50564, 400, 341, 307, 281, 855, 577, 4651, 3479, 2539, 393, 312, 50814 ], "temperature": 0.0, "avg_logprob": -0.21030890153742385, "compression_ratio": 1.5454545454545454, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 1576.02, "end": 1576.08, "word": " And", "probability": 0.6708984375 }, { "start": 1576.08, "end": 1576.22, "word": " this", "probability": 0.87841796875 }, { "start": 1576.22, "end": 1576.36, "word": " is", "probability": 0.9033203125 }, { "start": 1576.36, "end": 1576.5, "word": " to", "probability": 0.9072265625 }, { "start": 1576.5, "end": 1576.9, "word": " show", "probability": 0.8837890625 }, { "start": 1576.9, "end": 1578.38, "word": " how", "probability": 0.87548828125 }, { "start": 1578.38, "end": 1579.78, "word": " incredible", "probability": 0.75634765625 }, { "start": 1579.78, "end": 1580.34, "word": " machine", "probability": 0.69970703125 }, { "start": 1580.34, "end": 1580.62, "word": " learning", "probability": 0.8349609375 }, { "start": 1580.62, "end": 1580.86, "word": " can", "probability": 0.8916015625 }, { "start": 1580.86, "end": 1581.24, "word": " be", "probability": 0.904296875 } ] }, { "id": 488, "seek": 154062, "start": 1581.24, "end": 1583.72, "text": " where you can just swap out algorithms.", "tokens": [ 50814, 689, 291, 393, 445, 18135, 484, 14642, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.21030890153742385, "compression_ratio": 1.5454545454545454, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 1581.24, "end": 1581.7, "word": " where", "probability": 0.50146484375 }, { "start": 1581.7, "end": 1581.8, "word": " you", "probability": 0.88818359375 }, { "start": 1581.8, "end": 1581.9, "word": " can", "probability": 0.892578125 }, { "start": 1581.9, "end": 1582.1, "word": " just", "probability": 0.875 }, { "start": 1582.1, "end": 1582.48, "word": " swap", "probability": 0.9443359375 }, { "start": 1582.48, "end": 1582.7, "word": " out", "probability": 0.81298828125 }, { "start": 1582.7, "end": 1583.34, "word": " algorithms", "probability": 0.87548828125 }, { "start": 1583.34, "end": 1583.72, "word": ".", "probability": 0.426025390625 } ] }, { "id": 489, "seek": 154062, "start": 1583.78, "end": 1588.68, "text": " So we can use SVM, random forest, neural networks,", "tokens": [ 50964, 407, 321, 393, 764, 31910, 44, 11, 4974, 6719, 11, 18161, 9590, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.21030890153742385, "compression_ratio": 1.5454545454545454, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 1583.78, "end": 1584.38, "word": " So", "probability": 0.88232421875 }, { "start": 1584.38, "end": 1584.5, "word": " we", "probability": 0.84423828125 }, { "start": 1584.5, "end": 1584.66, "word": " can", "probability": 0.896484375 }, { "start": 1584.66, "end": 1585.2, "word": " use", "probability": 0.82568359375 }, { "start": 1585.2, "end": 1586.26, "word": " SVM", "probability": 0.942138671875 }, { "start": 1586.26, "end": 1586.42, "word": ",", "probability": 0.93701171875 }, { "start": 1586.42, "end": 1586.6, "word": " random", "probability": 0.6318359375 }, { "start": 1586.6, "end": 1587.26, "word": " forest", "probability": 0.70556640625 }, { "start": 1587.26, "end": 1587.38, "word": ",", "probability": 0.8203125 }, { "start": 1587.38, "end": 1587.68, "word": " neural", "probability": 0.69091796875 }, { "start": 1587.68, "end": 1588.38, "word": " networks", "probability": 0.66015625 }, { "start": 1588.38, "end": 1588.68, "word": ",", "probability": 0.927734375 } ] }, { "id": 490, "seek": 154062, "start": 1588.68, "end": 1591.46, "text": " things of that nature without massively changing the way", "tokens": [ 51214, 721, 295, 300, 3687, 1553, 29379, 4473, 264, 636, 51364 ], "temperature": 0.0, "avg_logprob": -0.21030890153742385, "compression_ratio": 1.5454545454545454, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 1588.68, "end": 1588.96, "word": " things", "probability": 0.70654296875 }, { "start": 1588.96, "end": 1589.1, "word": " of", "probability": 0.90283203125 }, { "start": 1589.1, "end": 1589.24, "word": " that", "probability": 0.880859375 }, { "start": 1589.24, "end": 1589.5, "word": " nature", "probability": 0.79541015625 }, { "start": 1589.5, "end": 1589.76, "word": " without", "probability": 0.60107421875 }, { "start": 1589.76, "end": 1590.66, "word": " massively", "probability": 0.7939453125 }, { "start": 1590.66, "end": 1591.1, "word": " changing", "probability": 0.77685546875 }, { "start": 1591.1, "end": 1591.3, "word": " the", "probability": 0.81298828125 }, { "start": 1591.3, "end": 1591.46, "word": " way", "probability": 0.89453125 } ] }, { "id": 491, "seek": 154062, "start": 1591.46, "end": 1593.18, "text": " that our data is represented.", "tokens": [ 51364, 300, 527, 1412, 307, 10379, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.21030890153742385, "compression_ratio": 1.5454545454545454, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 1591.46, "end": 1591.62, "word": " that", "probability": 0.86865234375 }, { "start": 1591.62, "end": 1591.74, "word": " our", "probability": 0.8251953125 }, { "start": 1591.74, "end": 1591.96, "word": " data", "probability": 0.82568359375 }, { "start": 1591.96, "end": 1592.14, "word": " is", "probability": 0.9052734375 }, { "start": 1592.14, "end": 1592.58, "word": " represented", "probability": 0.71044921875 }, { "start": 1592.58, "end": 1593.18, "word": ".", "probability": 0.99267578125 } ] }, { "id": 492, "seek": 154062, "start": 1593.98, "end": 1598.66, "text": " And then to kind of represent how our models are doing,", "tokens": [ 51464, 400, 550, 281, 733, 295, 2906, 577, 527, 5245, 366, 884, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.21030890153742385, "compression_ratio": 1.5454545454545454, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 1593.98, "end": 1594.14, "word": " And", "probability": 0.87744140625 }, { "start": 1594.14, "end": 1594.36, "word": " then", "probability": 0.7236328125 }, { "start": 1594.36, "end": 1594.8, "word": " to", "probability": 0.85693359375 }, { "start": 1594.8, "end": 1595.1, "word": " kind", "probability": 0.5732421875 }, { "start": 1595.1, "end": 1595.18, "word": " of", "probability": 0.90283203125 }, { "start": 1595.18, "end": 1595.54, "word": " represent", "probability": 0.74609375 }, { "start": 1595.54, "end": 1596.42, "word": " how", "probability": 0.892578125 }, { "start": 1596.42, "end": 1597.12, "word": " our", "probability": 0.81787109375 }, { "start": 1597.12, "end": 1598.14, "word": " models", "probability": 0.7705078125 }, { "start": 1598.14, "end": 1598.28, "word": " are", "probability": 0.89794921875 }, { "start": 1598.28, "end": 1598.54, "word": " doing", "probability": 0.9150390625 }, { "start": 1598.54, "end": 1598.66, "word": ",", "probability": 0.79833984375 } ] }, { "id": 493, "seek": 156906, "start": 1598.66, "end": 1601.98, "text": " we're going to use Seaborn as a graphic representation,", "tokens": [ 50364, 321, 434, 516, 281, 764, 1100, 455, 1865, 382, 257, 14089, 10290, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.20385742816142738, "compression_ratio": 1.7153558052434457, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1598.66, "end": 1598.7, "word": " we're", "probability": 0.422637939453125 }, { "start": 1598.7, "end": 1598.84, "word": " going", "probability": 0.541015625 }, { "start": 1598.84, "end": 1598.88, "word": " to", "probability": 0.90283203125 }, { "start": 1598.88, "end": 1599.2, "word": " use", "probability": 0.80419921875 }, { "start": 1599.2, "end": 1599.74, "word": " Seaborn", "probability": 0.72705078125 }, { "start": 1599.74, "end": 1600.54, "word": " as", "probability": 0.8486328125 }, { "start": 1600.78, "end": 1601.08, "word": " a graphic", "probability": 0.640625 }, { "start": 1601.08, "end": 1601.7, "word": " representation", "probability": 0.75927734375 }, { "start": 1601.7, "end": 1601.98, "word": ",", "probability": 0.3857421875 } ] }, { "id": 494, "seek": 156906, "start": 1601.98, "end": 1603.16, "text": " and we're going to use a confusion matrix", "tokens": [ 50514, 293, 321, 434, 516, 281, 764, 257, 15075, 8141, 50614 ], "temperature": 0.0, "avg_logprob": -0.20385742816142738, "compression_ratio": 1.7153558052434457, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1601.98, "end": 1601.98, "word": " and", "probability": 0.56640625 }, { "start": 1601.98, "end": 1602.1, "word": " we're", "probability": 0.83203125 }, { "start": 1602.1, "end": 1602.18, "word": " going", "probability": 0.76025390625 }, { "start": 1602.18, "end": 1602.2, "word": " to", "probability": 0.9072265625 }, { "start": 1602.2, "end": 1602.34, "word": " use", "probability": 0.82080078125 }, { "start": 1602.42, "end": 1602.78, "word": " a confusion", "probability": 0.7255859375 }, { "start": 1602.78, "end": 1603.16, "word": " matrix", "probability": 0.85009765625 } ] }, { "id": 495, "seek": 156906, "start": 1603.59, "end": 1606.67, "text": " and a classification report to identify exactly", "tokens": [ 50614, 293, 257, 21538, 2275, 281, 5876, 2293, 50764 ], "temperature": 0.0, "avg_logprob": -0.20385742816142738, "compression_ratio": 1.7153558052434457, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1603.59, "end": 1603.82, "word": " and", "probability": 0.76416015625 }, { "start": 1604.04, "end": 1604.46, "word": " a classification", "probability": 0.93115234375 }, { "start": 1604.46, "end": 1605.12, "word": " report", "probability": 0.83837890625 }, { "start": 1605.12, "end": 1605.84, "word": " to", "probability": 0.88330078125 }, { "start": 1605.84, "end": 1606.44, "word": " identify", "probability": 0.888671875 }, { "start": 1606.44, "end": 1606.67, "word": " exactly", "probability": 0.76904296875 } ] }, { "id": 496, "seek": 156906, "start": 1607.2, "end": 1609.88, "text": " where our model is doing well, where it's not doing well,", "tokens": [ 50764, 689, 527, 2316, 307, 884, 731, 11, 689, 309, 311, 406, 884, 731, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.20385742816142738, "compression_ratio": 1.7153558052434457, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1607.2, "end": 1607.5, "word": " where", "probability": 0.9072265625 }, { "start": 1607.5, "end": 1607.64, "word": " our", "probability": 0.6328125 }, { "start": 1607.64, "end": 1607.78, "word": " model", "probability": 0.7392578125 }, { "start": 1607.78, "end": 1607.88, "word": " is", "probability": 0.443359375 }, { "start": 1607.88, "end": 1608.06, "word": " doing", "probability": 0.9091796875 }, { "start": 1608.06, "end": 1608.38, "word": " well", "probability": 0.8857421875 }, { "start": 1608.38, "end": 1608.5, "word": ",", "probability": 0.94677734375 }, { "start": 1608.5, "end": 1608.88, "word": " where", "probability": 0.892578125 }, { "start": 1608.88, "end": 1609.02, "word": " it's", "probability": 0.945068359375 }, { "start": 1609.02, "end": 1609.18, "word": " not", "probability": 0.89599609375 }, { "start": 1609.18, "end": 1609.4, "word": " doing", "probability": 0.9130859375 }, { "start": 1609.4, "end": 1609.78, "word": " well", "probability": 0.88427734375 }, { "start": 1609.78, "end": 1609.88, "word": ",", "probability": 0.9208984375 } ] }, { "id": 497, "seek": 156906, "start": 1609.88, "end": 1613.92, "text": " and how mild changes are going to affect it.", "tokens": [ 50914, 293, 577, 15154, 2962, 366, 516, 281, 3345, 309, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.20385742816142738, "compression_ratio": 1.7153558052434457, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1609.88, "end": 1610.28, "word": " and", "probability": 0.8916015625 }, { "start": 1610.28, "end": 1610.7, "word": " how", "probability": 0.89453125 }, { "start": 1610.7, "end": 1611.26, "word": " mild", "probability": 0.79345703125 }, { "start": 1611.26, "end": 1611.86, "word": " changes", "probability": 0.794921875 }, { "start": 1611.86, "end": 1612.5, "word": " are", "probability": 0.8974609375 }, { "start": 1612.5, "end": 1612.72, "word": " going", "probability": 0.857421875 }, { "start": 1612.72, "end": 1612.88, "word": " to", "probability": 0.90380859375 }, { "start": 1612.88, "end": 1613.22, "word": " affect", "probability": 0.7939453125 }, { "start": 1613.22, "end": 1613.46, "word": " it", "probability": 0.90380859375 }, { "start": 1613.46, "end": 1613.92, "word": ".", "probability": 0.98779296875 } ] }, { "id": 498, "seek": 156906, "start": 1614.58, "end": 1617.54, "text": " So I'm going to go ahead, shift-enter, run that.", "tokens": [ 51164, 407, 286, 478, 516, 281, 352, 2286, 11, 5513, 12, 14278, 11, 1190, 300, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.20385742816142738, "compression_ratio": 1.7153558052434457, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1614.58, "end": 1615.04, "word": " So", "probability": 0.63818359375 }, { "start": 1615.04, "end": 1615.16, "word": " I'm", "probability": 0.947998046875 }, { "start": 1615.16, "end": 1615.22, "word": " going", "probability": 0.79736328125 }, { "start": 1615.22, "end": 1615.24, "word": " to", "probability": 0.9013671875 }, { "start": 1615.24, "end": 1615.34, "word": " go", "probability": 0.880859375 }, { "start": 1615.34, "end": 1615.58, "word": " ahead", "probability": 0.84619140625 }, { "start": 1615.58, "end": 1615.68, "word": ",", "probability": 0.47265625 }, { "start": 1615.68, "end": 1615.94, "word": " shift", "probability": 0.501953125 }, { "start": 1615.94, "end": 1616.32, "word": "-enter", "probability": 0.54119873046875 }, { "start": 1616.32, "end": 1616.52, "word": ",", "probability": 0.9462890625 }, { "start": 1616.52, "end": 1616.74, "word": " run", "probability": 0.84912109375 }, { "start": 1616.74, "end": 1617.08, "word": " that", "probability": 0.88427734375 }, { "start": 1617.08, "end": 1617.54, "word": ".", "probability": 0.68017578125 } ] }, { "id": 499, "seek": 156906, "start": 1618.16, "end": 1619.94, "text": " And that's just going to do the import,", "tokens": [ 51314, 400, 300, 311, 445, 516, 281, 360, 264, 974, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.20385742816142738, "compression_ratio": 1.7153558052434457, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1618.16, "end": 1618.34, "word": " And", "probability": 0.4169921875 }, { "start": 1618.34, "end": 1618.5, "word": " that's", "probability": 0.927490234375 }, { "start": 1618.5, "end": 1618.62, "word": " just", "probability": 0.8603515625 }, { "start": 1618.62, "end": 1618.72, "word": " going", "probability": 0.85107421875 }, { "start": 1618.72, "end": 1618.78, "word": " to", "probability": 0.90576171875 }, { "start": 1618.78, "end": 1618.88, "word": " do", "probability": 0.90771484375 }, { "start": 1618.88, "end": 1619.02, "word": " the", "probability": 0.7998046875 }, { "start": 1619.02, "end": 1619.44, "word": " import", "probability": 0.4169921875 }, { "start": 1619.44, "end": 1619.94, "word": ",", "probability": 0.591796875 } ] }, { "id": 500, "seek": 156906, "start": 1619.94, "end": 1622.04, "text": " and we'll see libraries imported.", "tokens": [ 51414, 293, 321, 603, 536, 15148, 25524, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.20385742816142738, "compression_ratio": 1.7153558052434457, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1619.94, "end": 1620.4, "word": " and", "probability": 0.890625 }, { "start": 1620.4, "end": 1620.58, "word": " we'll", "probability": 0.92041015625 }, { "start": 1620.58, "end": 1620.76, "word": " see", "probability": 0.79931640625 }, { "start": 1620.76, "end": 1621.16, "word": " libraries", "probability": 0.310791015625 }, { "start": 1621.16, "end": 1621.58, "word": " imported", "probability": 0.64599609375 }, { "start": 1621.58, "end": 1622.04, "word": ".", "probability": 0.90869140625 } ] }, { "id": 501, "seek": 156906, "start": 1622.44, "end": 1624.66, "text": " And then here's our test email from the slides.", "tokens": [ 51564, 400, 550, 510, 311, 527, 1500, 3796, 490, 264, 9788, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.20385742816142738, "compression_ratio": 1.7153558052434457, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1622.44, "end": 1622.64, "word": " And", "probability": 0.845703125 }, { "start": 1622.64, "end": 1622.74, "word": " then", "probability": 0.71435546875 }, { "start": 1622.74, "end": 1622.96, "word": " here's", "probability": 0.873779296875 }, { "start": 1622.96, "end": 1623.08, "word": " our", "probability": 0.81591796875 }, { "start": 1623.08, "end": 1623.3, "word": " test", "probability": 0.8349609375 }, { "start": 1623.3, "end": 1623.58, "word": " email", "probability": 0.875 }, { "start": 1623.58, "end": 1623.88, "word": " from", "probability": 0.8115234375 }, { "start": 1623.88, "end": 1624.04, "word": " the", "probability": 0.8125 }, { "start": 1624.04, "end": 1624.44, "word": " slides", "probability": 0.900390625 }, { "start": 1624.44, "end": 1624.66, "word": ".", "probability": 0.85546875 } ] }, { "id": 502, "seek": 156906, "start": 1624.66, "end": 1627.1, "text": " This is the East Asian fonts in Lenny.", "tokens": [ 51664, 639, 307, 264, 6747, 10645, 35316, 294, 23009, 1634, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.20385742816142738, "compression_ratio": 1.7153558052434457, "no_speech_prob": 0.002323150634765625, "words": [ { "start": 1624.66, "end": 1624.84, "word": " This", "probability": 0.81005859375 }, { "start": 1624.84, "end": 1624.98, "word": " is", "probability": 0.90625 }, { "start": 1624.98, "end": 1625.18, "word": " the", "probability": 0.81103515625 }, { "start": 1625.18, "end": 1625.44, "word": " East", "probability": 0.73876953125 }, { "start": 1625.44, "end": 1625.7, "word": " Asian", "probability": 0.8388671875 }, { "start": 1625.7, "end": 1626.12, "word": " fonts", "probability": 0.76416015625 }, { "start": 1626.12, "end": 1626.34, "word": " in", "probability": 0.8828125 }, { "start": 1626.34, "end": 1626.64, "word": " Lenny", "probability": 0.6929931640625 }, { "start": 1626.64, "end": 1627.1, "word": ".", "probability": 0.97216796875 } ] }, { "id": 503, "seek": 159730, "start": 1627.1, "end": 1630.56, "text": " We're going to see every step of the way how this email is manipulated", "tokens": [ 50364, 492, 434, 516, 281, 536, 633, 1823, 295, 264, 636, 577, 341, 3796, 307, 37161, 50514 ], "temperature": 0.0, "avg_logprob": -0.1801985922817872, "compression_ratio": 1.5607843137254902, "no_speech_prob": 0.0079345703125, "words": [ { "start": 1627.1, "end": 1627.66, "word": " We're", "probability": 0.649169921875 }, { "start": 1627.66, "end": 1627.76, "word": " going", "probability": 0.52001953125 }, { "start": 1627.76, "end": 1627.82, "word": " to", "probability": 0.9052734375 }, { "start": 1627.82, "end": 1628.0, "word": " see", "probability": 0.81005859375 }, { "start": 1628.0, "end": 1628.26, "word": " every", "probability": 0.72021484375 }, { "start": 1628.26, "end": 1628.5, "word": " step", "probability": 0.814453125 }, { "start": 1628.5, "end": 1628.6, "word": " of", "probability": 0.900390625 }, { "start": 1628.6, "end": 1628.68, "word": " the", "probability": 0.81787109375 }, { "start": 1628.68, "end": 1628.92, "word": " way", "probability": 0.89990234375 }, { "start": 1628.92, "end": 1629.18, "word": " how", "probability": 0.81591796875 }, { "start": 1629.18, "end": 1629.42, "word": " this", "probability": 0.8837890625 }, { "start": 1629.42, "end": 1629.74, "word": " email", "probability": 0.87060546875 }, { "start": 1629.74, "end": 1630.04, "word": " is", "probability": 0.9013671875 }, { "start": 1630.04, "end": 1630.56, "word": " manipulated", "probability": 0.9140625 } ] }, { "id": 504, "seek": 159730, "start": 1630.56, "end": 1634.44, "text": " and transformed into workable data for our machine learning models.", "tokens": [ 50514, 293, 16894, 666, 589, 712, 1412, 337, 527, 3479, 2539, 5245, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.1801985922817872, "compression_ratio": 1.5607843137254902, "no_speech_prob": 0.0079345703125, "words": [ { "start": 1630.56, "end": 1631.02, "word": " and", "probability": 0.87890625 }, { "start": 1631.02, "end": 1631.56, "word": " transformed", "probability": 0.79736328125 }, { "start": 1631.56, "end": 1632.06, "word": " into", "probability": 0.751953125 }, { "start": 1632.06, "end": 1632.52, "word": " workable", "probability": 0.94775390625 }, { "start": 1632.52, "end": 1632.76, "word": " data", "probability": 0.8095703125 }, { "start": 1632.76, "end": 1632.96, "word": " for", "probability": 0.88818359375 }, { "start": 1632.96, "end": 1633.08, "word": " our", "probability": 0.61474609375 }, { "start": 1633.08, "end": 1633.28, "word": " machine", "probability": 0.67431640625 }, { "start": 1633.28, "end": 1633.52, "word": " learning", "probability": 0.81494140625 }, { "start": 1633.52, "end": 1633.96, "word": " models", "probability": 0.740234375 }, { "start": 1633.96, "end": 1634.44, "word": ".", "probability": 0.8720703125 } ] }, { "id": 505, "seek": 159730, "start": 1634.66, "end": 1638.08, "text": " So I'm going to hit shift-enter and run that.", "tokens": [ 50714, 407, 286, 478, 516, 281, 2045, 5513, 12, 14278, 293, 1190, 300, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.1801985922817872, "compression_ratio": 1.5607843137254902, "no_speech_prob": 0.0079345703125, "words": [ { "start": 1634.66, "end": 1634.9, "word": " So", "probability": 0.73193359375 }, { "start": 1634.9, "end": 1635.14, "word": " I'm", "probability": 0.86669921875 }, { "start": 1635.14, "end": 1635.14, "word": " going", "probability": 0.75146484375 }, { "start": 1635.14, "end": 1635.14, "word": " to", "probability": 0.8984375 }, { "start": 1635.14, "end": 1635.3, "word": " hit", "probability": 0.853515625 }, { "start": 1635.3, "end": 1635.52, "word": " shift", "probability": 0.521484375 }, { "start": 1635.52, "end": 1635.86, "word": "-enter", "probability": 0.4796142578125 }, { "start": 1635.86, "end": 1636.76, "word": " and", "probability": 0.80078125 }, { "start": 1636.76, "end": 1637.18, "word": " run", "probability": 0.8974609375 }, { "start": 1637.18, "end": 1637.6, "word": " that", "probability": 0.8837890625 }, { "start": 1637.6, "end": 1638.08, "word": ".", "probability": 0.97119140625 } ] }, { "id": 506, "seek": 159730, "start": 1640.84, "end": 1642.84, "text": " TAs, are there any questions so far?", "tokens": [ 51014, 314, 10884, 11, 366, 456, 604, 1651, 370, 1400, 30, 51114 ], "temperature": 0.0, "avg_logprob": -0.1801985922817872, "compression_ratio": 1.5607843137254902, "no_speech_prob": 0.0079345703125, "words": [ { "start": 1640.84, "end": 1641.32, "word": " TAs", "probability": 0.63232421875 }, { "start": 1641.32, "end": 1641.34, "word": ",", "probability": 0.82568359375 }, { "start": 1641.34, "end": 1641.42, "word": " are", "probability": 0.88427734375 }, { "start": 1641.42, "end": 1641.54, "word": " there", "probability": 0.85498046875 }, { "start": 1641.54, "end": 1641.76, "word": " any", "probability": 0.82568359375 }, { "start": 1641.76, "end": 1642.18, "word": " questions", "probability": 0.912109375 }, { "start": 1642.18, "end": 1642.44, "word": " so", "probability": 0.89697265625 }, { "start": 1642.44, "end": 1642.68, "word": " far", "probability": 0.88671875 }, { "start": 1642.68, "end": 1642.84, "word": "?", "probability": 0.91259765625 } ] }, { "id": 507, "seek": 159730, "start": 1642.84, "end": 1645.74, "text": " Is everybody able to get their stuff set up?", "tokens": [ 51114, 1119, 2201, 1075, 281, 483, 641, 1507, 992, 493, 30, 51314 ], "temperature": 0.0, "avg_logprob": -0.1801985922817872, "compression_ratio": 1.5607843137254902, "no_speech_prob": 0.0079345703125, "words": [ { "start": 1642.84, "end": 1642.9, "word": " Is", "probability": 0.90380859375 }, { "start": 1642.9, "end": 1643.22, "word": " everybody", "probability": 0.76806640625 }, { "start": 1643.22, "end": 1643.54, "word": " able", "probability": 0.869140625 }, { "start": 1643.54, "end": 1643.96, "word": " to", "probability": 0.90673828125 }, { "start": 1643.96, "end": 1644.54, "word": " get", "probability": 0.8671875 }, { "start": 1644.54, "end": 1644.68, "word": " their", "probability": 0.9052734375 }, { "start": 1644.68, "end": 1644.86, "word": " stuff", "probability": 0.8046875 }, { "start": 1644.86, "end": 1645.06, "word": " set", "probability": 0.88037109375 }, { "start": 1645.06, "end": 1645.26, "word": " up", "probability": 0.90966796875 }, { "start": 1645.26, "end": 1645.74, "word": "?", "probability": 0.98828125 } ] }, { "id": 508, "seek": 159730, "start": 1646.66, "end": 1649.66, "text": " No questions so far. Looks like everything is going well.", "tokens": [ 51314, 883, 1651, 370, 1400, 13, 10027, 411, 1203, 307, 516, 731, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.1801985922817872, "compression_ratio": 1.5607843137254902, "no_speech_prob": 0.0079345703125, "words": [ { "start": 1646.66, "end": 1647.14, "word": " No", "probability": 0.41650390625 }, { "start": 1647.14, "end": 1647.52, "word": " questions", "probability": 0.88818359375 }, { "start": 1647.52, "end": 1647.76, "word": " so", "probability": 0.892578125 }, { "start": 1647.76, "end": 1647.96, "word": " far", "probability": 0.89306640625 }, { "start": 1647.96, "end": 1648.06, "word": ".", "probability": 0.80810546875 }, { "start": 1648.06, "end": 1648.28, "word": " Looks", "probability": 0.64697265625 }, { "start": 1648.28, "end": 1648.44, "word": " like", "probability": 0.88134765625 }, { "start": 1648.44, "end": 1648.66, "word": " everything", "probability": 0.89501953125 }, { "start": 1648.66, "end": 1648.84, "word": " is", "probability": 0.51123046875 }, { "start": 1648.84, "end": 1649.0, "word": " going", "probability": 0.853515625 }, { "start": 1649.0, "end": 1649.28, "word": " well", "probability": 0.8828125 }, { "start": 1649.28, "end": 1649.66, "word": ".", "probability": 0.986328125 } ] }, { "id": 509, "seek": 159730, "start": 1649.66, "end": 1650.54, "text": " Perfect.", "tokens": [ 51464, 10246, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.1801985922817872, "compression_ratio": 1.5607843137254902, "no_speech_prob": 0.0079345703125, "words": [ { "start": 1649.66, "end": 1650.06, "word": " Perfect", "probability": 0.83447265625 }, { "start": 1650.06, "end": 1650.54, "word": ".", "probability": 0.9541015625 } ] }, { "id": 510, "seek": 159730, "start": 1651.72, "end": 1655.34, "text": " So the tokenizer, this is the first step where we want to define", "tokens": [ 51564, 407, 264, 14862, 6545, 11, 341, 307, 264, 700, 1823, 689, 321, 528, 281, 6964, 51764 ], "temperature": 0.0, "avg_logprob": -0.1801985922817872, "compression_ratio": 1.5607843137254902, "no_speech_prob": 0.0079345703125, "words": [ { "start": 1651.72, "end": 1652.2, "word": " So", "probability": 0.86962890625 }, { "start": 1652.2, "end": 1652.48, "word": " the", "probability": 0.69384765625 }, { "start": 1652.48, "end": 1652.96, "word": " tokenizer", "probability": 0.73828125 }, { "start": 1652.96, "end": 1653.18, "word": ",", "probability": 0.71826171875 }, { "start": 1653.18, "end": 1653.32, "word": " this", "probability": 0.880859375 }, { "start": 1653.32, "end": 1653.44, "word": " is", "probability": 0.90380859375 }, { "start": 1653.44, "end": 1653.58, "word": " the", "probability": 0.81640625 }, { "start": 1653.58, "end": 1653.78, "word": " first", "probability": 0.8193359375 }, { "start": 1653.78, "end": 1654.1, "word": " step", "probability": 0.8134765625 }, { "start": 1654.1, "end": 1654.46, "word": " where", "probability": 0.84814453125 }, { "start": 1654.46, "end": 1654.68, "word": " we", "probability": 0.9091796875 }, { "start": 1654.68, "end": 1654.84, "word": " want", "probability": 0.81201171875 }, { "start": 1654.84, "end": 1654.96, "word": " to", "probability": 0.904296875 }, { "start": 1654.96, "end": 1655.34, "word": " define", "probability": 0.8896484375 } ] }, { "id": 511, "seek": 162412, "start": 1656.0, "end": 1659.26, "text": " a function that will pre-process our information.", "tokens": [ 50364, 257, 2445, 300, 486, 659, 12, 41075, 527, 1589, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.2088883166186145, "compression_ratio": 1.8354430379746836, "no_speech_prob": 0.0316162109375, "words": [ { "start": 1656.0, "end": 1656.46, "word": " a function", "probability": 0.85498046875 }, { "start": 1656.46, "end": 1656.88, "word": " that", "probability": 0.87158203125 }, { "start": 1656.88, "end": 1657.08, "word": " will", "probability": 0.77978515625 }, { "start": 1657.08, "end": 1657.46, "word": " pre", "probability": 0.62255859375 }, { "start": 1657.46, "end": 1657.88, "word": "-process", "probability": 0.845458984375 }, { "start": 1657.88, "end": 1658.3, "word": " our", "probability": 0.810546875 }, { "start": 1658.3, "end": 1658.8, "word": " information", "probability": 0.72900390625 }, { "start": 1658.8, "end": 1659.26, "word": ".", "probability": 0.93798828125 } ] }, { "id": 512, "seek": 162412, "start": 1659.74, "end": 1662.92, "text": " So, as we saw in the slides, we want to make everything lowercase,", "tokens": [ 50564, 407, 11, 382, 321, 1866, 294, 264, 9788, 11, 321, 528, 281, 652, 1203, 3126, 9765, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.2088883166186145, "compression_ratio": 1.8354430379746836, "no_speech_prob": 0.0316162109375, "words": [ { "start": 1659.74, "end": 1659.9, "word": " So", "probability": 0.6259765625 }, { "start": 1659.9, "end": 1660.08, "word": ",", "probability": 0.3662109375 }, { "start": 1660.08, "end": 1660.28, "word": " as", "probability": 0.90771484375 }, { "start": 1660.28, "end": 1660.4, "word": " we", "probability": 0.9013671875 }, { "start": 1660.4, "end": 1660.54, "word": " saw", "probability": 0.828125 }, { "start": 1660.54, "end": 1660.66, "word": " in", "probability": 0.55517578125 }, { "start": 1660.66, "end": 1660.76, "word": " the", "probability": 0.79443359375 }, { "start": 1660.76, "end": 1661.04, "word": " slides", "probability": 0.89404296875 }, { "start": 1661.04, "end": 1661.18, "word": ",", "probability": 0.88134765625 }, { "start": 1661.18, "end": 1661.24, "word": " we", "probability": 0.90234375 }, { "start": 1661.24, "end": 1661.44, "word": " want", "probability": 0.81494140625 }, { "start": 1661.44, "end": 1661.64, "word": " to", "probability": 0.90283203125 }, { "start": 1661.64, "end": 1661.84, "word": " make", "probability": 0.86669921875 }, { "start": 1661.84, "end": 1662.22, "word": " everything", "probability": 0.90283203125 }, { "start": 1662.22, "end": 1662.8, "word": " lowercase", "probability": 0.73291015625 }, { "start": 1662.8, "end": 1662.92, "word": ",", "probability": 0.611328125 } ] }, { "id": 513, "seek": 162412, "start": 1662.92, "end": 1666.3, "text": " we want to remove the stop words, and we want to stem the words.", "tokens": [ 50714, 321, 528, 281, 4159, 264, 1590, 2283, 11, 293, 321, 528, 281, 12312, 264, 2283, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.2088883166186145, "compression_ratio": 1.8354430379746836, "no_speech_prob": 0.0316162109375, "words": [ { "start": 1662.92, "end": 1663.02, "word": " we", "probability": 0.8935546875 }, { "start": 1663.02, "end": 1663.18, "word": " want", "probability": 0.677734375 }, { "start": 1663.18, "end": 1663.26, "word": " to", "probability": 0.9033203125 }, { "start": 1663.26, "end": 1663.56, "word": " remove", "probability": 0.86181640625 }, { "start": 1663.56, "end": 1663.78, "word": " the", "probability": 0.8125 }, { "start": 1663.78, "end": 1664.08, "word": " stop", "probability": 0.88916015625 }, { "start": 1664.08, "end": 1664.38, "word": " words", "probability": 0.61474609375 }, { "start": 1664.38, "end": 1664.48, "word": ",", "probability": 0.75048828125 }, { "start": 1664.48, "end": 1664.56, "word": " and", "probability": 0.88818359375 }, { "start": 1664.56, "end": 1664.66, "word": " we", "probability": 0.9013671875 }, { "start": 1664.66, "end": 1664.82, "word": " want", "probability": 0.80859375 }, { "start": 1664.82, "end": 1665.0, "word": " to", "probability": 0.89697265625 }, { "start": 1665.0, "end": 1665.28, "word": " stem", "probability": 0.80322265625 }, { "start": 1665.28, "end": 1665.48, "word": " the", "probability": 0.80078125 }, { "start": 1665.48, "end": 1665.84, "word": " words", "probability": 0.720703125 }, { "start": 1665.84, "end": 1666.3, "word": ".", "probability": 0.9736328125 } ] }, { "id": 514, "seek": 162412, "start": 1666.88, "end": 1669.18, "text": " So this function is already defined for you,", "tokens": [ 50914, 407, 341, 2445, 307, 1217, 7642, 337, 291, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.2088883166186145, "compression_ratio": 1.8354430379746836, "no_speech_prob": 0.0316162109375, "words": [ { "start": 1666.88, "end": 1667.2, "word": " So", "probability": 0.826171875 }, { "start": 1667.2, "end": 1667.34, "word": " this", "probability": 0.64111328125 }, { "start": 1667.34, "end": 1667.6, "word": " function", "probability": 0.86328125 }, { "start": 1667.6, "end": 1667.72, "word": " is", "probability": 0.417724609375 }, { "start": 1667.72, "end": 1667.9, "word": " already", "probability": 0.82421875 }, { "start": 1667.9, "end": 1668.26, "word": " defined", "probability": 0.7158203125 }, { "start": 1668.26, "end": 1668.52, "word": " for", "probability": 0.89599609375 }, { "start": 1668.52, "end": 1668.82, "word": " you", "probability": 0.89306640625 }, { "start": 1668.82, "end": 1669.18, "word": ",", "probability": 0.75390625 } ] }, { "id": 515, "seek": 162412, "start": 1669.18, "end": 1671.66, "text": " but we can see that we grab all the punctuation,", "tokens": [ 51064, 457, 321, 393, 536, 300, 321, 4444, 439, 264, 27006, 16073, 11, 51164 ], "temperature": 0.0, "avg_logprob": -0.2088883166186145, "compression_ratio": 1.8354430379746836, "no_speech_prob": 0.0316162109375, "words": [ { "start": 1669.18, "end": 1669.42, "word": " but", "probability": 0.8994140625 }, { "start": 1669.42, "end": 1669.54, "word": " we", "probability": 0.8984375 }, { "start": 1669.54, "end": 1669.66, "word": " can", "probability": 0.8984375 }, { "start": 1669.66, "end": 1669.84, "word": " see", "probability": 0.798828125 }, { "start": 1669.84, "end": 1669.96, "word": " that", "probability": 0.87158203125 }, { "start": 1669.96, "end": 1670.08, "word": " we", "probability": 0.89990234375 }, { "start": 1670.08, "end": 1670.36, "word": " grab", "probability": 0.80029296875 }, { "start": 1670.36, "end": 1670.6, "word": " all", "probability": 0.8994140625 }, { "start": 1670.6, "end": 1670.74, "word": " the", "probability": 0.63330078125 }, { "start": 1670.74, "end": 1671.34, "word": " punctuation", "probability": 0.903564453125 }, { "start": 1671.34, "end": 1671.66, "word": ",", "probability": 0.9306640625 } ] }, { "id": 516, "seek": 162412, "start": 1671.66, "end": 1674.22, "text": " we grab all the stop words using nl2k,", "tokens": [ 51164, 321, 4444, 439, 264, 1590, 2283, 1228, 297, 75, 17, 74, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.2088883166186145, "compression_ratio": 1.8354430379746836, "no_speech_prob": 0.0316162109375, "words": [ { "start": 1671.66, "end": 1671.76, "word": " we", "probability": 0.8974609375 }, { "start": 1671.76, "end": 1671.98, "word": " grab", "probability": 0.810546875 }, { "start": 1671.98, "end": 1672.18, "word": " all", "probability": 0.88916015625 }, { "start": 1672.18, "end": 1672.36, "word": " the", "probability": 0.7666015625 }, { "start": 1672.36, "end": 1672.66, "word": " stop", "probability": 0.8291015625 }, { "start": 1672.66, "end": 1672.96, "word": " words", "probability": 0.71142578125 }, { "start": 1672.96, "end": 1673.26, "word": " using", "probability": 0.7216796875 }, { "start": 1673.26, "end": 1673.84, "word": " nl2k", "probability": 0.7105712890625 }, { "start": 1673.84, "end": 1674.22, "word": ",", "probability": 0.89599609375 } ] }, { "id": 517, "seek": 162412, "start": 1674.22, "end": 1679.28, "text": " and then we define the porter stemmer, which is going to stem our words.", "tokens": [ 51314, 293, 550, 321, 6964, 264, 41628, 12312, 936, 11, 597, 307, 516, 281, 12312, 527, 2283, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.2088883166186145, "compression_ratio": 1.8354430379746836, "no_speech_prob": 0.0316162109375, "words": [ { "start": 1674.22, "end": 1674.54, "word": " and", "probability": 0.8798828125 }, { "start": 1674.54, "end": 1674.64, "word": " then", "probability": 0.716796875 }, { "start": 1674.64, "end": 1674.86, "word": " we", "probability": 0.89697265625 }, { "start": 1674.86, "end": 1675.52, "word": " define", "probability": 0.880859375 }, { "start": 1675.52, "end": 1675.86, "word": " the", "probability": 0.78759765625 }, { "start": 1675.86, "end": 1676.12, "word": " porter", "probability": 0.2493896484375 }, { "start": 1676.12, "end": 1676.66, "word": " stemmer", "probability": 0.595947265625 }, { "start": 1676.66, "end": 1677.12, "word": ",", "probability": 0.82470703125 }, { "start": 1677.12, "end": 1677.48, "word": " which", "probability": 0.9150390625 }, { "start": 1677.48, "end": 1677.6, "word": " is", "probability": 0.90625 }, { "start": 1677.6, "end": 1677.74, "word": " going", "probability": 0.86083984375 }, { "start": 1677.74, "end": 1677.96, "word": " to", "probability": 0.90087890625 }, { "start": 1677.96, "end": 1678.22, "word": " stem", "probability": 0.80224609375 }, { "start": 1678.22, "end": 1678.46, "word": " our", "probability": 0.806640625 }, { "start": 1678.46, "end": 1678.82, "word": " words", "probability": 0.73486328125 }, { "start": 1678.82, "end": 1679.28, "word": ".", "probability": 0.95263671875 } ] }, { "id": 518, "seek": 162412, "start": 1679.78, "end": 1682.16, "text": " And then we're going to create a list of tokens", "tokens": [ 51564, 400, 550, 321, 434, 516, 281, 1884, 257, 1329, 295, 22667, 51714 ], "temperature": 0.0, "avg_logprob": -0.2088883166186145, "compression_ratio": 1.8354430379746836, "no_speech_prob": 0.0316162109375, "words": [ { "start": 1679.78, "end": 1680.1, "word": " And", "probability": 0.861328125 }, { "start": 1680.1, "end": 1680.24, "word": " then", "probability": 0.71875 }, { "start": 1680.24, "end": 1680.46, "word": " we're", "probability": 0.898193359375 }, { "start": 1680.46, "end": 1680.68, "word": " going", "probability": 0.85400390625 }, { "start": 1680.68, "end": 1680.98, "word": " to", "probability": 0.90380859375 }, { "start": 1680.98, "end": 1681.3, "word": " create", "probability": 0.83349609375 }, { "start": 1681.5, "end": 1681.66, "word": " a list", "probability": 0.896484375 }, { "start": 1681.66, "end": 1681.82, "word": " of", "probability": 0.8984375 }, { "start": 1681.82, "end": 1682.16, "word": " tokens", "probability": 0.76171875 } ] }, { "id": 519, "seek": 165214, "start": 1682.16, "end": 1686.92, "text": " by taking all of our words, setting them to lowercase,", "tokens": [ 50364, 538, 1940, 439, 295, 527, 2283, 11, 3287, 552, 281, 3126, 9765, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.17934182048898883, "compression_ratio": 1.775330396475771, "no_speech_prob": 0.108154296875, "words": [ { "start": 1682.16, "end": 1682.54, "word": " by", "probability": 0.1898193359375 }, { "start": 1682.54, "end": 1684.46, "word": " taking", "probability": 0.6875 }, { "start": 1684.46, "end": 1684.88, "word": " all", "probability": 0.89404296875 }, { "start": 1684.88, "end": 1685.0, "word": " of", "probability": 0.8876953125 }, { "start": 1685.0, "end": 1685.12, "word": " our", "probability": 0.81103515625 }, { "start": 1685.12, "end": 1685.4, "word": " words", "probability": 0.68310546875 }, { "start": 1685.4, "end": 1685.58, "word": ",", "probability": 0.74267578125 }, { "start": 1685.58, "end": 1685.7, "word": " setting", "probability": 0.79296875 }, { "start": 1685.7, "end": 1685.86, "word": " them", "probability": 0.74072265625 }, { "start": 1685.86, "end": 1686.02, "word": " to", "probability": 0.87109375 }, { "start": 1686.02, "end": 1686.66, "word": " lowercase", "probability": 0.7353515625 }, { "start": 1686.66, "end": 1686.92, "word": ",", "probability": 0.52294921875 } ] }, { "id": 520, "seek": 165214, "start": 1686.92, "end": 1690.46, "text": " and using the word tokenizer,", "tokens": [ 50564, 293, 1228, 264, 1349, 14862, 6545, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.17934182048898883, "compression_ratio": 1.775330396475771, "no_speech_prob": 0.108154296875, "words": [ { "start": 1686.92, "end": 1687.16, "word": " and", "probability": 0.8564453125 }, { "start": 1687.16, "end": 1687.86, "word": " using", "probability": 0.82177734375 }, { "start": 1687.86, "end": 1688.08, "word": " the", "probability": 0.80419921875 }, { "start": 1688.08, "end": 1688.28, "word": " word", "probability": 0.60498046875 }, { "start": 1688.28, "end": 1689.96, "word": " tokenizer", "probability": 0.761962890625 }, { "start": 1689.96, "end": 1690.46, "word": ",", "probability": 0.7080078125 } ] }, { "id": 521, "seek": 165214, "start": 1690.46, "end": 1694.34, "text": " which will just take a sentence, split it up by its individual words,", "tokens": [ 50764, 597, 486, 445, 747, 257, 8174, 11, 7472, 309, 493, 538, 1080, 2609, 2283, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.17934182048898883, "compression_ratio": 1.775330396475771, "no_speech_prob": 0.108154296875, "words": [ { "start": 1690.46, "end": 1690.82, "word": " which", "probability": 0.92578125 }, { "start": 1690.82, "end": 1691.0, "word": " will", "probability": 0.798828125 }, { "start": 1691.0, "end": 1691.26, "word": " just", "probability": 0.83935546875 }, { "start": 1691.26, "end": 1691.56, "word": " take", "probability": 0.8173828125 }, { "start": 1691.78, "end": 1692.12, "word": " a sentence", "probability": 0.83203125 }, { "start": 1692.12, "end": 1692.3, "word": ",", "probability": 0.87548828125 }, { "start": 1692.3, "end": 1692.54, "word": " split", "probability": 0.83544921875 }, { "start": 1692.54, "end": 1692.64, "word": " it", "probability": 0.89697265625 }, { "start": 1692.64, "end": 1692.74, "word": " up", "probability": 0.892578125 }, { "start": 1692.74, "end": 1692.88, "word": " by", "probability": 0.89892578125 }, { "start": 1692.88, "end": 1693.02, "word": " its", "probability": 0.744140625 }, { "start": 1693.02, "end": 1693.4, "word": " individual", "probability": 0.77197265625 }, { "start": 1693.4, "end": 1693.9, "word": " words", "probability": 0.72607421875 }, { "start": 1693.9, "end": 1694.34, "word": ",", "probability": 0.458740234375 } ] }, { "id": 522, "seek": 165214, "start": 1694.34, "end": 1696.34, "text": " we're going to strip out the punctuations,", "tokens": [ 50964, 321, 434, 516, 281, 12828, 484, 264, 27006, 37570, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.17934182048898883, "compression_ratio": 1.775330396475771, "no_speech_prob": 0.108154296875, "words": [ { "start": 1694.34, "end": 1694.72, "word": " we're", "probability": 0.85107421875 }, { "start": 1694.72, "end": 1694.72, "word": " going", "probability": 0.32568359375 }, { "start": 1694.72, "end": 1694.78, "word": " to", "probability": 0.90234375 }, { "start": 1694.78, "end": 1694.96, "word": " strip", "probability": 0.7197265625 }, { "start": 1694.96, "end": 1695.08, "word": " out", "probability": 0.806640625 }, { "start": 1695.08, "end": 1695.2, "word": " the", "probability": 0.8046875 }, { "start": 1695.2, "end": 1695.82, "word": " punctuations", "probability": 0.851318359375 }, { "start": 1695.82, "end": 1696.34, "word": ",", "probability": 0.88427734375 } ] }, { "id": 523, "seek": 165214, "start": 1696.34, "end": 1699.7, "text": " and then we are going to merge everything together.", "tokens": [ 51064, 293, 550, 321, 366, 516, 281, 22183, 1203, 1214, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.17934182048898883, "compression_ratio": 1.775330396475771, "no_speech_prob": 0.108154296875, "words": [ { "start": 1696.34, "end": 1696.88, "word": " and", "probability": 0.89111328125 }, { "start": 1696.88, "end": 1697.12, "word": " then", "probability": 0.732421875 }, { "start": 1697.12, "end": 1697.34, "word": " we", "probability": 0.88330078125 }, { "start": 1697.34, "end": 1697.48, "word": " are", "probability": 0.798828125 }, { "start": 1697.48, "end": 1697.72, "word": " going", "probability": 0.86474609375 }, { "start": 1697.72, "end": 1698.1, "word": " to", "probability": 0.90625 }, { "start": 1698.1, "end": 1698.36, "word": " merge", "probability": 0.896484375 }, { "start": 1698.36, "end": 1698.7, "word": " everything", "probability": 0.88720703125 }, { "start": 1698.7, "end": 1699.22, "word": " together", "probability": 0.7802734375 }, { "start": 1699.22, "end": 1699.7, "word": ".", "probability": 0.98291015625 } ] }, { "id": 524, "seek": 165214, "start": 1700.48, "end": 1702.36, "text": " So we're going to go ahead and run that.", "tokens": [ 51264, 407, 321, 434, 516, 281, 352, 2286, 293, 1190, 300, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.17934182048898883, "compression_ratio": 1.775330396475771, "no_speech_prob": 0.108154296875, "words": [ { "start": 1700.48, "end": 1700.9, "word": " So", "probability": 0.75048828125 }, { "start": 1700.9, "end": 1701.14, "word": " we're", "probability": 0.82568359375 }, { "start": 1701.14, "end": 1701.22, "word": " going", "probability": 0.748046875 }, { "start": 1701.22, "end": 1701.26, "word": " to", "probability": 0.9052734375 }, { "start": 1701.26, "end": 1701.36, "word": " go", "probability": 0.89794921875 }, { "start": 1701.36, "end": 1701.5, "word": " ahead", "probability": 0.84765625 }, { "start": 1701.5, "end": 1701.6, "word": " and", "probability": 0.8955078125 }, { "start": 1701.6, "end": 1701.72, "word": " run", "probability": 0.8974609375 }, { "start": 1701.72, "end": 1702.0, "word": " that", "probability": 0.880859375 }, { "start": 1702.0, "end": 1702.36, "word": ".", "probability": 0.609375 } ] }, { "id": 525, "seek": 165214, "start": 1702.36, "end": 1703.92, "text": " It's going to define our function,", "tokens": [ 51364, 467, 311, 516, 281, 6964, 527, 2445, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.17934182048898883, "compression_ratio": 1.775330396475771, "no_speech_prob": 0.108154296875, "words": [ { "start": 1702.36, "end": 1702.58, "word": " It's", "probability": 0.9326171875 }, { "start": 1702.58, "end": 1702.68, "word": " going", "probability": 0.8349609375 }, { "start": 1702.68, "end": 1702.74, "word": " to", "probability": 0.90380859375 }, { "start": 1702.74, "end": 1703.0, "word": " define", "probability": 0.88037109375 }, { "start": 1703.0, "end": 1703.12, "word": " our", "probability": 0.81787109375 }, { "start": 1703.12, "end": 1703.46, "word": " function", "probability": 0.8671875 }, { "start": 1703.46, "end": 1703.92, "word": ",", "probability": 0.55859375 } ] }, { "id": 526, "seek": 165214, "start": 1703.92, "end": 1708.36, "text": " and we're going to hop into our first task.", "tokens": [ 51464, 293, 321, 434, 516, 281, 3818, 666, 527, 700, 5633, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.17934182048898883, "compression_ratio": 1.775330396475771, "no_speech_prob": 0.108154296875, "words": [ { "start": 1703.92, "end": 1704.34, "word": " and", "probability": 0.89599609375 }, { "start": 1704.34, "end": 1704.62, "word": " we're", "probability": 0.92724609375 }, { "start": 1704.62, "end": 1704.84, "word": " going", "probability": 0.857421875 }, { "start": 1704.84, "end": 1705.3, "word": " to", "probability": 0.912109375 }, { "start": 1705.3, "end": 1705.86, "word": " hop", "probability": 0.91748046875 }, { "start": 1705.86, "end": 1706.26, "word": " into", "probability": 0.73486328125 }, { "start": 1706.26, "end": 1706.62, "word": " our", "probability": 0.81982421875 }, { "start": 1706.62, "end": 1707.04, "word": " first", "probability": 0.81689453125 }, { "start": 1707.04, "end": 1707.88, "word": " task", "probability": 0.7890625 }, { "start": 1707.88, "end": 1708.36, "word": ".", "probability": 0.9697265625 } ] }, { "id": 527, "seek": 165214, "start": 1708.56, "end": 1710.18, "text": " So our first task is really easy.", "tokens": [ 51664, 407, 527, 700, 5633, 307, 534, 1858, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.17934182048898883, "compression_ratio": 1.775330396475771, "no_speech_prob": 0.108154296875, "words": [ { "start": 1708.56, "end": 1709.02, "word": " So", "probability": 0.83740234375 }, { "start": 1709.02, "end": 1709.12, "word": " our", "probability": 0.62451171875 }, { "start": 1709.12, "end": 1709.24, "word": " first", "probability": 0.814453125 }, { "start": 1709.24, "end": 1709.46, "word": " task", "probability": 0.81494140625 }, { "start": 1709.46, "end": 1709.58, "word": " is", "probability": 0.89892578125 }, { "start": 1709.58, "end": 1709.76, "word": " really", "probability": 0.78125 }, { "start": 1709.76, "end": 1710.02, "word": " easy", "probability": 0.81884765625 }, { "start": 1710.02, "end": 1710.18, "word": ".", "probability": 0.77001953125 } ] }, { "id": 528, "seek": 168030, "start": 1710.18, "end": 1713.8, "text": " It's just print the full test email,", "tokens": [ 50364, 467, 311, 445, 4482, 264, 1577, 1500, 3796, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.24325980888862236, "compression_ratio": 1.8090452261306533, "no_speech_prob": 0.025177001953125, "words": [ { "start": 1710.18, "end": 1710.44, "word": " It's", "probability": 0.53668212890625 }, { "start": 1710.44, "end": 1710.72, "word": " just", "probability": 0.86181640625 }, { "start": 1710.72, "end": 1711.12, "word": " print", "probability": 0.6416015625 }, { "start": 1711.12, "end": 1711.44, "word": " the", "probability": 0.8056640625 }, { "start": 1711.44, "end": 1711.8, "word": " full", "probability": 0.791015625 }, { "start": 1711.8, "end": 1712.14, "word": " test", "probability": 0.7744140625 }, { "start": 1712.14, "end": 1712.58, "word": " email", "probability": 0.8955078125 }, { "start": 1712.58, "end": 1713.8, "word": ",", "probability": 0.383544921875 } ] }, { "id": 529, "seek": 168030, "start": 1713.8, "end": 1717.68, "text": " and then we're going to print the tokenized version of the test email.", "tokens": [ 50564, 293, 550, 321, 434, 516, 281, 4482, 264, 14862, 1602, 3037, 295, 264, 1500, 3796, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.24325980888862236, "compression_ratio": 1.8090452261306533, "no_speech_prob": 0.025177001953125, "words": [ { "start": 1713.8, "end": 1713.8, "word": " and", "probability": 0.5185546875 }, { "start": 1713.8, "end": 1714.32, "word": " then", "probability": 0.70166015625 }, { "start": 1714.32, "end": 1714.44, "word": " we're", "probability": 0.855224609375 }, { "start": 1714.44, "end": 1714.58, "word": " going", "probability": 0.84326171875 }, { "start": 1714.58, "end": 1714.72, "word": " to", "probability": 0.91015625 }, { "start": 1714.72, "end": 1714.94, "word": " print", "probability": 0.8837890625 }, { "start": 1714.94, "end": 1715.22, "word": " the", "probability": 0.80908203125 }, { "start": 1715.22, "end": 1715.86, "word": " tokenized", "probability": 0.833740234375 }, { "start": 1715.86, "end": 1716.16, "word": " version", "probability": 0.712890625 }, { "start": 1716.16, "end": 1716.46, "word": " of", "probability": 0.89013671875 }, { "start": 1716.46, "end": 1716.58, "word": " the", "probability": 0.8095703125 }, { "start": 1716.58, "end": 1716.84, "word": " test", "probability": 0.78369140625 }, { "start": 1716.84, "end": 1717.16, "word": " email", "probability": 0.91796875 }, { "start": 1717.16, "end": 1717.68, "word": ".", "probability": 0.9267578125 } ] }, { "id": 530, "seek": 168030, "start": 1717.82, "end": 1723.22, "text": " So in Python we can just do print test email,", "tokens": [ 50714, 407, 294, 15329, 321, 393, 445, 360, 4482, 1500, 3796, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.24325980888862236, "compression_ratio": 1.8090452261306533, "no_speech_prob": 0.025177001953125, "words": [ { "start": 1717.82, "end": 1717.96, "word": " So", "probability": 0.62451171875 }, { "start": 1717.96, "end": 1718.26, "word": " in", "probability": 0.7431640625 }, { "start": 1718.26, "end": 1718.48, "word": " Python", "probability": 0.8818359375 }, { "start": 1718.48, "end": 1718.7, "word": " we", "probability": 0.5322265625 }, { "start": 1718.7, "end": 1718.8, "word": " can", "probability": 0.88623046875 }, { "start": 1718.8, "end": 1718.96, "word": " just", "probability": 0.84521484375 }, { "start": 1718.96, "end": 1719.24, "word": " do", "probability": 0.900390625 }, { "start": 1719.24, "end": 1719.74, "word": " print", "probability": 0.61669921875 }, { "start": 1719.74, "end": 1721.88, "word": " test", "probability": 0.61328125 }, { "start": 1721.88, "end": 1722.46, "word": " email", "probability": 0.8857421875 }, { "start": 1722.46, "end": 1723.22, "word": ",", "probability": 0.46533203125 } ] }, { "id": 531, "seek": 168030, "start": 1723.22, "end": 1729.88, "text": " and then we can do print tokenizer test email.", "tokens": [ 51014, 293, 550, 321, 393, 360, 4482, 14862, 6545, 1500, 3796, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.24325980888862236, "compression_ratio": 1.8090452261306533, "no_speech_prob": 0.025177001953125, "words": [ { "start": 1723.22, "end": 1723.98, "word": " and", "probability": 0.84228515625 }, { "start": 1723.98, "end": 1724.22, "word": " then", "probability": 0.74072265625 }, { "start": 1724.22, "end": 1724.44, "word": " we", "probability": 0.86962890625 }, { "start": 1724.44, "end": 1724.6, "word": " can", "probability": 0.89794921875 }, { "start": 1724.6, "end": 1724.9, "word": " do", "probability": 0.91162109375 }, { "start": 1724.9, "end": 1725.56, "word": " print", "probability": 0.8544921875 }, { "start": 1725.56, "end": 1727.66, "word": " tokenizer", "probability": 0.85205078125 }, { "start": 1727.66, "end": 1728.76, "word": " test", "probability": 0.7841796875 }, { "start": 1728.76, "end": 1729.36, "word": " email", "probability": 0.92041015625 }, { "start": 1729.36, "end": 1729.88, "word": ".", "probability": 0.48486328125 } ] }, { "id": 532, "seek": 168030, "start": 1730.16, "end": 1733.04, "text": " And then shift-enter, going to go ahead and run that.", "tokens": [ 51364, 400, 550, 5513, 12, 14278, 11, 516, 281, 352, 2286, 293, 1190, 300, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.24325980888862236, "compression_ratio": 1.8090452261306533, "no_speech_prob": 0.025177001953125, "words": [ { "start": 1730.16, "end": 1730.48, "word": " And", "probability": 0.64794921875 }, { "start": 1730.48, "end": 1730.7, "word": " then", "probability": 0.72119140625 }, { "start": 1730.7, "end": 1731.26, "word": " shift", "probability": 0.5087890625 }, { "start": 1731.26, "end": 1731.6, "word": "-enter", "probability": 0.498291015625 }, { "start": 1731.6, "end": 1731.74, "word": ",", "probability": 0.52490234375 }, { "start": 1731.74, "end": 1731.9, "word": " going", "probability": 0.1492919921875 }, { "start": 1731.9, "end": 1732.0, "word": " to", "probability": 0.90087890625 }, { "start": 1732.0, "end": 1732.24, "word": " go", "probability": 0.8125 }, { "start": 1732.24, "end": 1732.4, "word": " ahead", "probability": 0.8564453125 }, { "start": 1732.4, "end": 1732.5, "word": " and", "probability": 0.896484375 }, { "start": 1732.5, "end": 1732.66, "word": " run", "probability": 0.904296875 }, { "start": 1732.66, "end": 1732.92, "word": " that", "probability": 0.88134765625 }, { "start": 1732.92, "end": 1733.04, "word": ".", "probability": 0.70947265625 } ] }, { "id": 533, "seek": 168030, "start": 1733.04, "end": 1736.22, "text": " So we see the original email, East Asian fonts in Leni.", "tokens": [ 51514, 407, 321, 536, 264, 3380, 3796, 11, 6747, 10645, 35316, 294, 441, 15711, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.24325980888862236, "compression_ratio": 1.8090452261306533, "no_speech_prob": 0.025177001953125, "words": [ { "start": 1733.04, "end": 1733.12, "word": " So", "probability": 0.84375 }, { "start": 1733.12, "end": 1733.24, "word": " we", "probability": 0.89599609375 }, { "start": 1733.24, "end": 1733.36, "word": " see", "probability": 0.80224609375 }, { "start": 1733.36, "end": 1733.5, "word": " the", "probability": 0.818359375 }, { "start": 1733.5, "end": 1733.78, "word": " original", "probability": 0.83642578125 }, { "start": 1733.78, "end": 1734.18, "word": " email", "probability": 0.93798828125 }, { "start": 1734.18, "end": 1734.32, "word": ",", "probability": 0.73486328125 }, { "start": 1734.32, "end": 1734.48, "word": " East", "probability": 0.66064453125 }, { "start": 1734.48, "end": 1734.78, "word": " Asian", "probability": 0.79248046875 }, { "start": 1734.78, "end": 1735.24, "word": " fonts", "probability": 0.54443359375 }, { "start": 1735.24, "end": 1735.46, "word": " in", "probability": 0.7607421875 }, { "start": 1735.46, "end": 1735.7, "word": " Leni", "probability": 0.5277099609375 }, { "start": 1735.7, "end": 1736.22, "word": ".", "probability": 0.7626953125 } ] }, { "id": 534, "seek": 168030, "start": 1736.38, "end": 1738.34, "text": " Then we can see the stop words have been removed.", "tokens": [ 51664, 1396, 321, 393, 536, 264, 1590, 2283, 362, 668, 7261, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.24325980888862236, "compression_ratio": 1.8090452261306533, "no_speech_prob": 0.025177001953125, "words": [ { "start": 1736.38, "end": 1736.66, "word": " Then", "probability": 0.5322265625 }, { "start": 1736.66, "end": 1736.74, "word": " we", "probability": 0.90283203125 }, { "start": 1736.74, "end": 1736.88, "word": " can", "probability": 0.8935546875 }, { "start": 1736.88, "end": 1737.0, "word": " see", "probability": 0.8134765625 }, { "start": 1737.0, "end": 1737.14, "word": " the", "probability": 0.802734375 }, { "start": 1737.14, "end": 1737.4, "word": " stop", "probability": 0.91015625 }, { "start": 1737.4, "end": 1737.56, "word": " words", "probability": 0.451904296875 }, { "start": 1737.56, "end": 1737.68, "word": " have", "probability": 0.8740234375 }, { "start": 1737.68, "end": 1737.8, "word": " been", "probability": 0.81591796875 }, { "start": 1737.8, "end": 1738.2, "word": " removed", "probability": 0.73388671875 }, { "start": 1738.2, "end": 1738.34, "word": ".", "probability": 0.6357421875 } ] }, { "id": 535, "seek": 170650, "start": 1738.34, "end": 1741.66, "text": " So we're looking at East Asian font Leni.", "tokens": [ 50364, 407, 321, 434, 1237, 412, 6747, 10645, 10703, 441, 15711, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.22594803370786518, "compression_ratio": 1.631578947368421, "no_speech_prob": 0.0094146728515625, "words": [ { "start": 1738.34, "end": 1738.34, "word": " So", "probability": 0.01511383056640625 }, { "start": 1738.34, "end": 1738.42, "word": " we're", "probability": 0.8349609375 }, { "start": 1738.42, "end": 1738.62, "word": " looking", "probability": 0.7998046875 }, { "start": 1738.62, "end": 1738.82, "word": " at", "probability": 0.90380859375 }, { "start": 1738.82, "end": 1739.18, "word": " East", "probability": 0.599609375 }, { "start": 1739.18, "end": 1739.76, "word": " Asian", "probability": 0.44482421875 }, { "start": 1739.76, "end": 1740.4, "word": " font", "probability": 0.75341796875 }, { "start": 1740.4, "end": 1741.06, "word": " Leni", "probability": 0.3360595703125 }, { "start": 1741.06, "end": 1741.66, "word": ".", "probability": 0.630859375 } ] }, { "id": 536, "seek": 170650, "start": 1741.8, "end": 1744.8, "text": " Thanks has been turned into thank.", "tokens": [ 50514, 2561, 575, 668, 3574, 666, 1309, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.22594803370786518, "compression_ratio": 1.631578947368421, "no_speech_prob": 0.0094146728515625, "words": [ { "start": 1741.8, "end": 1742.28, "word": " Thanks", "probability": 0.6845703125 }, { "start": 1742.28, "end": 1742.68, "word": " has", "probability": 0.85595703125 }, { "start": 1742.68, "end": 1742.88, "word": " been", "probability": 0.82177734375 }, { "start": 1742.88, "end": 1743.14, "word": " turned", "probability": 0.77783203125 }, { "start": 1743.14, "end": 1743.5, "word": " into", "probability": 0.74169921875 }, { "start": 1743.5, "end": 1744.2, "word": " thank", "probability": 0.5126953125 }, { "start": 1744.2, "end": 1744.8, "word": ".", "probability": 0.7333984375 } ] }, { "id": 537, "seek": 170650, "start": 1745.24, "end": 1749.98, "text": " Support install. Install is missing an L because we see installing.", "tokens": [ 50714, 18073, 3625, 13, 31982, 307, 5361, 364, 441, 570, 321, 536, 20762, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.22594803370786518, "compression_ratio": 1.631578947368421, "no_speech_prob": 0.0094146728515625, "words": [ { "start": 1745.24, "end": 1745.84, "word": " Support", "probability": 0.8623046875 }, { "start": 1745.84, "end": 1746.6, "word": " install", "probability": 0.5810546875 }, { "start": 1746.6, "end": 1746.78, "word": ".", "probability": 0.326416015625 }, { "start": 1746.78, "end": 1747.1, "word": " Install", "probability": 0.798828125 }, { "start": 1747.1, "end": 1747.42, "word": " is", "probability": 0.8994140625 }, { "start": 1747.42, "end": 1747.84, "word": " missing", "probability": 0.86669921875 }, { "start": 1747.84, "end": 1748.04, "word": " an", "probability": 0.86572265625 }, { "start": 1748.04, "end": 1748.26, "word": " L", "probability": 0.93212890625 }, { "start": 1748.26, "end": 1748.78, "word": " because", "probability": 0.66748046875 }, { "start": 1748.78, "end": 1748.96, "word": " we", "probability": 0.90576171875 }, { "start": 1748.96, "end": 1749.14, "word": " see", "probability": 0.81689453125 }, { "start": 1749.14, "end": 1749.68, "word": " installing", "probability": 0.7119140625 }, { "start": 1749.68, "end": 1749.98, "word": ".", "probability": 0.4091796875 } ] }, { "id": 538, "seek": 170650, "start": 1749.98, "end": 1754.44, "text": " You have I installed something, or I am going to install something.", "tokens": [ 50964, 509, 362, 286, 8899, 746, 11, 420, 286, 669, 516, 281, 3625, 746, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.22594803370786518, "compression_ratio": 1.631578947368421, "no_speech_prob": 0.0094146728515625, "words": [ { "start": 1749.98, "end": 1750.04, "word": " You", "probability": 0.88818359375 }, { "start": 1750.04, "end": 1750.3, "word": " have", "probability": 0.8857421875 }, { "start": 1750.3, "end": 1750.54, "word": " I", "probability": 0.548828125 }, { "start": 1750.54, "end": 1751.0, "word": " installed", "probability": 0.71923828125 }, { "start": 1751.0, "end": 1751.54, "word": " something", "probability": 0.73681640625 }, { "start": 1751.54, "end": 1751.66, "word": ",", "probability": 0.2001953125 }, { "start": 1751.66, "end": 1751.96, "word": " or", "probability": 0.90185546875 }, { "start": 1751.96, "end": 1752.16, "word": " I", "probability": 0.99169921875 }, { "start": 1752.16, "end": 1752.3, "word": " am", "probability": 0.74609375 }, { "start": 1752.3, "end": 1752.58, "word": " going", "probability": 0.8515625 }, { "start": 1752.58, "end": 1752.98, "word": " to", "probability": 0.9091796875 }, { "start": 1752.98, "end": 1753.48, "word": " install", "probability": 0.814453125 }, { "start": 1753.48, "end": 1753.98, "word": " something", "probability": 0.7421875 }, { "start": 1753.98, "end": 1754.44, "word": ".", "probability": 0.86865234375 } ] }, { "id": 539, "seek": 170650, "start": 1754.44, "end": 1758.46, "text": " And so we're going to stem that so that all of those words are counted the same.", "tokens": [ 51164, 400, 370, 321, 434, 516, 281, 12312, 300, 370, 300, 439, 295, 729, 2283, 366, 20150, 264, 912, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.22594803370786518, "compression_ratio": 1.631578947368421, "no_speech_prob": 0.0094146728515625, "words": [ { "start": 1754.44, "end": 1754.62, "word": " And", "probability": 0.86962890625 }, { "start": 1754.62, "end": 1754.72, "word": " so", "probability": 0.900390625 }, { "start": 1754.72, "end": 1754.86, "word": " we're", "probability": 0.910888671875 }, { "start": 1754.86, "end": 1754.92, "word": " going", "probability": 0.245849609375 }, { "start": 1754.92, "end": 1755.06, "word": " to", "probability": 0.90478515625 }, { "start": 1755.06, "end": 1755.28, "word": " stem", "probability": 0.77490234375 }, { "start": 1755.28, "end": 1755.58, "word": " that", "probability": 0.88037109375 }, { "start": 1755.58, "end": 1755.78, "word": " so", "probability": 0.81396484375 }, { "start": 1755.78, "end": 1756.1, "word": " that", "probability": 0.87548828125 }, { "start": 1756.1, "end": 1756.58, "word": " all", "probability": 0.890625 }, { "start": 1756.58, "end": 1756.7, "word": " of", "probability": 0.8193359375 }, { "start": 1756.7, "end": 1756.86, "word": " those", "probability": 0.85546875 }, { "start": 1756.86, "end": 1757.1, "word": " words", "probability": 0.71826171875 }, { "start": 1757.1, "end": 1757.24, "word": " are", "probability": 0.88427734375 }, { "start": 1757.24, "end": 1757.42, "word": " counted", "probability": 0.75390625 }, { "start": 1757.42, "end": 1757.66, "word": " the", "probability": 0.80078125 }, { "start": 1757.66, "end": 1757.86, "word": " same", "probability": 0.818359375 }, { "start": 1757.86, "end": 1758.46, "word": ".", "probability": 0.99462890625 } ] }, { "id": 540, "seek": 170650, "start": 1760.06, "end": 1764.54, "text": " We see unsubscribe. Unsubscribe shows up twice.", "tokens": [ 51464, 492, 536, 2693, 9493, 13, 25017, 9493, 3110, 493, 6091, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.22594803370786518, "compression_ratio": 1.631578947368421, "no_speech_prob": 0.0094146728515625, "words": [ { "start": 1760.06, "end": 1760.66, "word": " We", "probability": 0.8798828125 }, { "start": 1760.66, "end": 1760.92, "word": " see", "probability": 0.81005859375 }, { "start": 1760.92, "end": 1761.66, "word": " unsubscribe", "probability": 0.864501953125 }, { "start": 1761.66, "end": 1761.96, "word": ".", "probability": 0.830078125 }, { "start": 1761.96, "end": 1762.44, "word": " Unsubscribe", "probability": 0.87158203125 }, { "start": 1762.44, "end": 1763.24, "word": " shows", "probability": 0.79541015625 }, { "start": 1763.24, "end": 1763.42, "word": " up", "probability": 0.912109375 }, { "start": 1763.42, "end": 1764.06, "word": " twice", "probability": 0.845703125 }, { "start": 1764.06, "end": 1764.54, "word": ".", "probability": 0.90380859375 } ] }, { "id": 541, "seek": 172680, "start": 1764.54, "end": 1770.7, "text": " And then we see list.debian.org, which also shows up twice.", "tokens": [ 50364, 400, 550, 321, 536, 1329, 13, 1479, 20196, 13, 4646, 11, 597, 611, 3110, 493, 6091, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.22567247099514248, "compression_ratio": 1.5683060109289617, "no_speech_prob": 0.219970703125, "words": [ { "start": 1764.54, "end": 1764.58, "word": " And", "probability": 0.489501953125 }, { "start": 1764.58, "end": 1764.68, "word": " then", "probability": 0.67626953125 }, { "start": 1764.68, "end": 1764.78, "word": " we", "probability": 0.86767578125 }, { "start": 1764.78, "end": 1765.7, "word": " see", "probability": 0.474853515625 }, { "start": 1765.7, "end": 1766.24, "word": " list", "probability": 0.382080078125 }, { "start": 1766.24, "end": 1766.8, "word": ".debian", "probability": 0.8689778645833334 }, { "start": 1766.8, "end": 1767.54, "word": ".org", "probability": 0.9736328125 }, { "start": 1767.54, "end": 1767.7, "word": ",", "probability": 0.806640625 }, { "start": 1767.7, "end": 1768.68, "word": " which", "probability": 0.9111328125 }, { "start": 1768.68, "end": 1769.02, "word": " also", "probability": 0.8193359375 }, { "start": 1769.02, "end": 1769.36, "word": " shows", "probability": 0.82080078125 }, { "start": 1769.36, "end": 1769.58, "word": " up", "probability": 0.91162109375 }, { "start": 1769.58, "end": 1770.26, "word": " twice", "probability": 0.8466796875 }, { "start": 1770.26, "end": 1770.7, "word": ".", "probability": 0.99365234375 } ] }, { "id": 542, "seek": 172680, "start": 1770.7, "end": 1774.96, "text": " So this is the way that our tokenizer modifies the email as we're going through.", "tokens": [ 50664, 407, 341, 307, 264, 636, 300, 527, 14862, 6545, 1072, 11221, 264, 3796, 382, 321, 434, 516, 807, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.22567247099514248, "compression_ratio": 1.5683060109289617, "no_speech_prob": 0.219970703125, "words": [ { "start": 1770.7, "end": 1770.94, "word": " So", "probability": 0.86376953125 }, { "start": 1770.94, "end": 1771.1, "word": " this", "probability": 0.8388671875 }, { "start": 1771.1, "end": 1771.2, "word": " is", "probability": 0.90478515625 }, { "start": 1771.2, "end": 1771.3, "word": " the", "probability": 0.814453125 }, { "start": 1771.3, "end": 1771.4, "word": " way", "probability": 0.8974609375 }, { "start": 1771.4, "end": 1771.52, "word": " that", "probability": 0.86376953125 }, { "start": 1771.52, "end": 1771.64, "word": " our", "probability": 0.794921875 }, { "start": 1771.64, "end": 1772.1, "word": " tokenizer", "probability": 0.7998046875 }, { "start": 1772.1, "end": 1772.86, "word": " modifies", "probability": 0.94970703125 }, { "start": 1772.86, "end": 1773.1, "word": " the", "probability": 0.8125 }, { "start": 1773.1, "end": 1773.42, "word": " email", "probability": 0.90234375 }, { "start": 1773.42, "end": 1773.76, "word": " as", "probability": 0.88671875 }, { "start": 1773.76, "end": 1773.9, "word": " we're", "probability": 0.924560546875 }, { "start": 1773.9, "end": 1774.14, "word": " going", "probability": 0.85595703125 }, { "start": 1774.14, "end": 1774.48, "word": " through", "probability": 0.80078125 }, { "start": 1774.48, "end": 1774.96, "word": ".", "probability": 0.98974609375 } ] }, { "id": 543, "seek": 172680, "start": 1776.42, "end": 1779.28, "text": " And again, just for those that are trying to catch up,", "tokens": [ 50964, 400, 797, 11, 445, 337, 729, 300, 366, 1382, 281, 3745, 493, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.22567247099514248, "compression_ratio": 1.5683060109289617, "no_speech_prob": 0.219970703125, "words": [ { "start": 1776.42, "end": 1776.9, "word": " And", "probability": 0.88720703125 }, { "start": 1776.9, "end": 1777.14, "word": " again", "probability": 0.873046875 }, { "start": 1777.14, "end": 1777.24, "word": ",", "probability": 0.95458984375 }, { "start": 1777.24, "end": 1777.4, "word": " just", "probability": 0.88818359375 }, { "start": 1777.4, "end": 1777.54, "word": " for", "probability": 0.89306640625 }, { "start": 1777.54, "end": 1777.74, "word": " those", "probability": 0.8466796875 }, { "start": 1777.74, "end": 1777.9, "word": " that", "probability": 0.86962890625 }, { "start": 1777.9, "end": 1778.18, "word": " are", "probability": 0.89990234375 }, { "start": 1778.18, "end": 1778.62, "word": " trying", "probability": 0.8056640625 }, { "start": 1778.62, "end": 1778.78, "word": " to", "probability": 0.90087890625 }, { "start": 1778.78, "end": 1778.96, "word": " catch", "probability": 0.81396484375 }, { "start": 1778.96, "end": 1779.16, "word": " up", "probability": 0.91259765625 }, { "start": 1779.16, "end": 1779.28, "word": ",", "probability": 0.9169921875 } ] }, { "id": 544, "seek": 172680, "start": 1779.28, "end": 1784.84, "text": " all we did was print the test email and then print the tokenizer version of the test email.", "tokens": [ 51114, 439, 321, 630, 390, 4482, 264, 1500, 3796, 293, 550, 4482, 264, 14862, 6545, 3037, 295, 264, 1500, 3796, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.22567247099514248, "compression_ratio": 1.5683060109289617, "no_speech_prob": 0.219970703125, "words": [ { "start": 1779.28, "end": 1779.42, "word": " all", "probability": 0.8857421875 }, { "start": 1779.42, "end": 1779.56, "word": " we", "probability": 0.90380859375 }, { "start": 1779.56, "end": 1779.74, "word": " did", "probability": 0.8896484375 }, { "start": 1779.74, "end": 1780.06, "word": " was", "probability": 0.87939453125 }, { "start": 1780.06, "end": 1780.46, "word": " print", "probability": 0.6484375 }, { "start": 1780.46, "end": 1780.78, "word": " the", "probability": 0.80419921875 }, { "start": 1780.78, "end": 1781.06, "word": " test", "probability": 0.81201171875 }, { "start": 1781.06, "end": 1781.36, "word": " email", "probability": 0.91748046875 }, { "start": 1781.36, "end": 1781.66, "word": " and", "probability": 0.51123046875 }, { "start": 1781.66, "end": 1781.82, "word": " then", "probability": 0.73876953125 }, { "start": 1781.82, "end": 1782.08, "word": " print", "probability": 0.6904296875 }, { "start": 1782.08, "end": 1782.8, "word": " the", "probability": 0.54541015625 }, { "start": 1782.8, "end": 1783.26, "word": " tokenizer", "probability": 0.839599609375 }, { "start": 1783.26, "end": 1783.6, "word": " version", "probability": 0.708984375 }, { "start": 1783.6, "end": 1783.78, "word": " of", "probability": 0.90283203125 }, { "start": 1783.78, "end": 1783.92, "word": " the", "probability": 0.8173828125 }, { "start": 1783.92, "end": 1784.18, "word": " test", "probability": 0.7802734375 }, { "start": 1784.18, "end": 1784.4, "word": " email", "probability": 0.92431640625 }, { "start": 1784.4, "end": 1784.84, "word": ".", "probability": 0.97705078125 } ] }, { "id": 545, "seek": 175480, "start": 1786.04, "end": 1790.52, "text": " There's a question from Twitch chat.", "tokens": [ 50414, 821, 311, 257, 1168, 490, 22222, 5081, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.2158717105263158, "compression_ratio": 1.5757575757575757, "no_speech_prob": 0.337890625, "words": [ { "start": 1786.04, "end": 1786.64, "word": " There's", "probability": 0.498016357421875 }, { "start": 1786.74, "end": 1787.08, "word": " a question", "probability": 0.837890625 }, { "start": 1787.08, "end": 1787.76, "word": " from", "probability": 0.7412109375 }, { "start": 1787.76, "end": 1789.26, "word": " Twitch", "probability": 0.57177734375 }, { "start": 1789.26, "end": 1789.92, "word": " chat", "probability": 0.423583984375 }, { "start": 1789.92, "end": 1790.52, "word": ".", "probability": 0.92431640625 } ] }, { "id": 546, "seek": 175480, "start": 1795.22, "end": 1801.52, "text": " So why are we assuming the punctuation is not relevant?", "tokens": [ 50864, 407, 983, 366, 321, 11926, 264, 27006, 16073, 307, 406, 7340, 30, 51214 ], "temperature": 0.0, "avg_logprob": -0.2158717105263158, "compression_ratio": 1.5757575757575757, "no_speech_prob": 0.337890625, "words": [ { "start": 1795.22, "end": 1795.82, "word": " So", "probability": 0.27880859375 }, { "start": 1795.82, "end": 1796.36, "word": " why", "probability": 0.6787109375 }, { "start": 1796.36, "end": 1797.12, "word": " are", "probability": 0.88525390625 }, { "start": 1797.12, "end": 1798.82, "word": " we", "probability": 0.89013671875 }, { "start": 1798.82, "end": 1799.2, "word": " assuming", "probability": 0.79443359375 }, { "start": 1799.2, "end": 1799.4, "word": " the", "probability": 0.7578125 }, { "start": 1799.4, "end": 1800.0, "word": " punctuation", "probability": 0.906005859375 }, { "start": 1800.0, "end": 1800.24, "word": " is", "probability": 0.8994140625 }, { "start": 1800.24, "end": 1800.5, "word": " not", "probability": 0.90380859375 }, { "start": 1800.5, "end": 1800.92, "word": " relevant", "probability": 0.8818359375 }, { "start": 1800.92, "end": 1801.52, "word": "?", "probability": 0.92578125 } ] }, { "id": 547, "seek": 175480, "start": 1801.8, "end": 1805.18, "text": " In our case, we're looking at spam emails.", "tokens": [ 51214, 682, 527, 1389, 11, 321, 434, 1237, 412, 24028, 12524, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.2158717105263158, "compression_ratio": 1.5757575757575757, "no_speech_prob": 0.337890625, "words": [ { "start": 1801.8, "end": 1802.4, "word": " In", "probability": 0.861328125 }, { "start": 1802.4, "end": 1803.08, "word": " our", "probability": 0.81640625 }, { "start": 1803.08, "end": 1803.36, "word": " case", "probability": 0.81689453125 }, { "start": 1803.36, "end": 1803.42, "word": ",", "probability": 0.68017578125 }, { "start": 1803.42, "end": 1803.56, "word": " we're", "probability": 0.913818359375 }, { "start": 1803.56, "end": 1803.78, "word": " looking", "probability": 0.78564453125 }, { "start": 1803.78, "end": 1804.02, "word": " at", "probability": 0.8896484375 }, { "start": 1804.02, "end": 1804.46, "word": " spam", "probability": 0.9501953125 }, { "start": 1804.46, "end": 1804.88, "word": " emails", "probability": 0.75439453125 }, { "start": 1804.88, "end": 1805.18, "word": ".", "probability": 0.48828125 } ] }, { "id": 548, "seek": 175480, "start": 1805.18, "end": 1809.32, "text": " And so the punctuation, you'll look at commas, hyphens, question marks.", "tokens": [ 51364, 400, 370, 264, 27006, 16073, 11, 291, 603, 574, 412, 800, 296, 11, 2477, 950, 694, 11, 1168, 10640, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.2158717105263158, "compression_ratio": 1.5757575757575757, "no_speech_prob": 0.337890625, "words": [ { "start": 1805.18, "end": 1805.26, "word": " And", "probability": 0.448486328125 }, { "start": 1805.26, "end": 1805.38, "word": " so", "probability": 0.89892578125 }, { "start": 1805.38, "end": 1805.54, "word": " the", "probability": 0.791015625 }, { "start": 1805.54, "end": 1806.1, "word": " punctuation", "probability": 0.921142578125 }, { "start": 1806.1, "end": 1806.28, "word": ",", "probability": 0.6845703125 }, { "start": 1806.28, "end": 1806.36, "word": " you'll", "probability": 0.683837890625 }, { "start": 1806.36, "end": 1806.48, "word": " look", "probability": 0.91650390625 }, { "start": 1806.48, "end": 1806.62, "word": " at", "probability": 0.87841796875 }, { "start": 1806.62, "end": 1807.1, "word": " commas", "probability": 0.871337890625 }, { "start": 1807.1, "end": 1807.26, "word": ",", "probability": 0.9892578125 }, { "start": 1807.26, "end": 1807.72, "word": " hyphens", "probability": 0.8857421875 }, { "start": 1807.72, "end": 1808.2, "word": ",", "probability": 0.98828125 }, { "start": 1808.2, "end": 1808.66, "word": " question", "probability": 0.8037109375 }, { "start": 1808.66, "end": 1809.08, "word": " marks", "probability": 0.7705078125 }, { "start": 1809.08, "end": 1809.32, "word": ".", "probability": 0.94482421875 } ] }, { "id": 549, "seek": 175480, "start": 1809.32, "end": 1812.84, "text": " And so in the context, if we're looking at keywords,", "tokens": [ 51564, 400, 370, 294, 264, 4319, 11, 498, 321, 434, 1237, 412, 21009, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.2158717105263158, "compression_ratio": 1.5757575757575757, "no_speech_prob": 0.337890625, "words": [ { "start": 1809.32, "end": 1809.46, "word": " And", "probability": 0.86376953125 }, { "start": 1809.46, "end": 1809.74, "word": " so", "probability": 0.90185546875 }, { "start": 1809.74, "end": 1810.0, "word": " in", "probability": 0.85498046875 }, { "start": 1810.0, "end": 1810.22, "word": " the", "probability": 0.8154296875 }, { "start": 1810.22, "end": 1810.84, "word": " context", "probability": 0.76708984375 }, { "start": 1810.84, "end": 1810.94, "word": ",", "probability": 0.96044921875 }, { "start": 1810.94, "end": 1811.1, "word": " if", "probability": 0.8955078125 }, { "start": 1811.1, "end": 1811.22, "word": " we're", "probability": 0.929931640625 }, { "start": 1811.22, "end": 1811.44, "word": " looking", "probability": 0.7958984375 }, { "start": 1811.44, "end": 1811.64, "word": " at", "probability": 0.90283203125 }, { "start": 1811.64, "end": 1812.24, "word": " keywords", "probability": 0.6240234375 }, { "start": 1812.24, "end": 1812.84, "word": ",", "probability": 0.98046875 } ] }, { "id": 550, "seek": 178344, "start": 1813.56, "end": 1815.66, "text": " the punctuation doesn't really matter.", "tokens": [ 50364, 264, 27006, 16073, 1177, 380, 534, 1871, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.21636652176157903, "compression_ratio": 1.7302904564315353, "no_speech_prob": 0.0007915496826171875, "words": [ { "start": 1813.56, "end": 1814.08, "word": " the", "probability": 0.2783203125 }, { "start": 1814.08, "end": 1814.54, "word": " punctuation", "probability": 0.89892578125 }, { "start": 1814.54, "end": 1814.82, "word": " doesn't", "probability": 0.922119140625 }, { "start": 1814.82, "end": 1815.0, "word": " really", "probability": 0.77880859375 }, { "start": 1815.0, "end": 1815.32, "word": " matter", "probability": 0.80078125 }, { "start": 1815.32, "end": 1815.66, "word": ".", "probability": 0.4443359375 } ] }, { "id": 551, "seek": 178344, "start": 1815.66, "end": 1818.2, "text": " So if you see buy a Viagra now, period,", "tokens": [ 50464, 407, 498, 291, 536, 2256, 257, 6626, 559, 424, 586, 11, 2896, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.21636652176157903, "compression_ratio": 1.7302904564315353, "no_speech_prob": 0.0007915496826171875, "words": [ { "start": 1815.66, "end": 1815.86, "word": " So", "probability": 0.578125 }, { "start": 1815.86, "end": 1816.0, "word": " if", "probability": 0.822265625 }, { "start": 1816.0, "end": 1816.12, "word": " you", "probability": 0.89599609375 }, { "start": 1816.12, "end": 1816.4, "word": " see", "probability": 0.76220703125 }, { "start": 1816.4, "end": 1816.58, "word": " buy", "probability": 0.08941650390625 }, { "start": 1816.72, "end": 1817.08, "word": " a Viagra", "probability": 0.8772786458333334 }, { "start": 1817.08, "end": 1817.4, "word": " now", "probability": 0.85498046875 }, { "start": 1817.4, "end": 1817.66, "word": ",", "probability": 0.481201171875 }, { "start": 1817.66, "end": 1817.94, "word": " period", "probability": 0.8037109375 }, { "start": 1817.94, "end": 1818.2, "word": ",", "probability": 0.7392578125 } ] }, { "id": 552, "seek": 178344, "start": 1818.2, "end": 1821.94, "text": " it doesn't make any difference between buy Viagra now, exclamation point,", "tokens": [ 50614, 309, 1177, 380, 652, 604, 2649, 1296, 2256, 6626, 559, 424, 586, 11, 1624, 43233, 935, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.21636652176157903, "compression_ratio": 1.7302904564315353, "no_speech_prob": 0.0007915496826171875, "words": [ { "start": 1818.2, "end": 1818.46, "word": " it", "probability": 0.35546875 }, { "start": 1818.46, "end": 1818.58, "word": " doesn't", "probability": 0.928466796875 }, { "start": 1818.58, "end": 1818.74, "word": " make", "probability": 0.8740234375 }, { "start": 1818.74, "end": 1818.94, "word": " any", "probability": 0.80908203125 }, { "start": 1818.94, "end": 1819.4, "word": " difference", "probability": 0.72119140625 }, { "start": 1819.4, "end": 1819.82, "word": " between", "probability": 0.80029296875 }, { "start": 1819.82, "end": 1820.14, "word": " buy", "probability": 0.71240234375 }, { "start": 1820.14, "end": 1820.56, "word": " Viagra", "probability": 0.92138671875 }, { "start": 1820.56, "end": 1820.82, "word": " now", "probability": 0.86572265625 }, { "start": 1820.82, "end": 1820.9, "word": ",", "probability": 0.489013671875 }, { "start": 1820.9, "end": 1821.42, "word": " exclamation", "probability": 0.773681640625 }, { "start": 1821.42, "end": 1821.78, "word": " point", "probability": 0.86083984375 }, { "start": 1821.78, "end": 1821.94, "word": ",", "probability": 0.77734375 } ] }, { "id": 553, "seek": 178344, "start": 1821.94, "end": 1825.26, "text": " or buy Viagra now with a question mark at the end.", "tokens": [ 50814, 420, 2256, 6626, 559, 424, 586, 365, 257, 1168, 1491, 412, 264, 917, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.21636652176157903, "compression_ratio": 1.7302904564315353, "no_speech_prob": 0.0007915496826171875, "words": [ { "start": 1821.94, "end": 1822.12, "word": " or", "probability": 0.9072265625 }, { "start": 1822.12, "end": 1822.48, "word": " buy", "probability": 0.796875 }, { "start": 1822.48, "end": 1822.96, "word": " Viagra", "probability": 0.9402669270833334 }, { "start": 1822.96, "end": 1823.34, "word": " now", "probability": 0.88525390625 }, { "start": 1823.34, "end": 1823.7, "word": " with", "probability": 0.42431640625 }, { "start": 1823.82, "end": 1824.08, "word": " a question", "probability": 0.79541015625 }, { "start": 1824.08, "end": 1824.28, "word": " mark", "probability": 0.8076171875 }, { "start": 1824.28, "end": 1824.42, "word": " at", "probability": 0.9013671875 }, { "start": 1824.42, "end": 1824.52, "word": " the", "probability": 0.81640625 }, { "start": 1824.52, "end": 1824.74, "word": " end", "probability": 0.8134765625 }, { "start": 1824.74, "end": 1825.26, "word": ".", "probability": 0.99267578125 } ] }, { "id": 554, "seek": 178344, "start": 1825.78, "end": 1828.3, "text": " So in the context of the sentence,", "tokens": [ 50964, 407, 294, 264, 4319, 295, 264, 8174, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.21636652176157903, "compression_ratio": 1.7302904564315353, "no_speech_prob": 0.0007915496826171875, "words": [ { "start": 1825.78, "end": 1826.06, "word": " So", "probability": 0.81982421875 }, { "start": 1826.06, "end": 1826.4, "word": " in", "probability": 0.8251953125 }, { "start": 1826.4, "end": 1826.8, "word": " the", "probability": 0.81494140625 }, { "start": 1826.8, "end": 1827.24, "word": " context", "probability": 0.767578125 }, { "start": 1827.24, "end": 1827.44, "word": " of", "probability": 0.90625 }, { "start": 1827.44, "end": 1827.6, "word": " the", "probability": 0.81201171875 }, { "start": 1827.6, "end": 1828.06, "word": " sentence", "probability": 0.8232421875 }, { "start": 1828.06, "end": 1828.3, "word": ",", "probability": 0.81884765625 } ] }, { "id": 555, "seek": 178344, "start": 1831.94, "end": 1834.94, "text": " that one sentence would likely be classified as spam", "tokens": [ 51114, 300, 472, 8174, 576, 3700, 312, 20627, 382, 24028, 51464 ], "temperature": 0.0, "avg_logprob": -0.21636652176157903, "compression_ratio": 1.7302904564315353, "no_speech_prob": 0.0007915496826171875, "words": [ { "start": 1831.94, "end": 1832.46, "word": " that", "probability": 0.280029296875 }, { "start": 1832.46, "end": 1832.98, "word": " one", "probability": 0.794921875 }, { "start": 1832.98, "end": 1833.38, "word": " sentence", "probability": 0.8408203125 }, { "start": 1833.38, "end": 1833.56, "word": " would", "probability": 0.837890625 }, { "start": 1833.56, "end": 1833.8, "word": " likely", "probability": 0.74169921875 }, { "start": 1833.8, "end": 1834.0, "word": " be", "probability": 0.90478515625 }, { "start": 1834.0, "end": 1834.36, "word": " classified", "probability": 0.93701171875 }, { "start": 1834.36, "end": 1834.7, "word": " as", "probability": 0.904296875 }, { "start": 1834.7, "end": 1834.94, "word": " spam", "probability": 0.9306640625 } ] }, { "id": 556, "seek": 178344, "start": 1834.94, "end": 1838.44, "text": " because it's talking about Viagra and it's very unlikely.", "tokens": [ 51464, 570, 309, 311, 1417, 466, 6626, 559, 424, 293, 309, 311, 588, 17518, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.21636652176157903, "compression_ratio": 1.7302904564315353, "no_speech_prob": 0.0007915496826171875, "words": [ { "start": 1834.94, "end": 1835.64, "word": " because", "probability": 0.64306640625 }, { "start": 1835.64, "end": 1836.0, "word": " it's", "probability": 0.952392578125 }, { "start": 1836.0, "end": 1836.28, "word": " talking", "probability": 0.77001953125 }, { "start": 1836.28, "end": 1836.76, "word": " about", "probability": 0.8291015625 }, { "start": 1836.76, "end": 1837.44, "word": " Viagra", "probability": 0.93115234375 }, { "start": 1837.44, "end": 1837.62, "word": " and", "probability": 0.58447265625 }, { "start": 1837.62, "end": 1837.74, "word": " it's", "probability": 0.9052734375 }, { "start": 1837.74, "end": 1837.94, "word": " very", "probability": 0.7236328125 }, { "start": 1837.94, "end": 1838.3, "word": " unlikely", "probability": 0.64599609375 }, { "start": 1838.3, "end": 1838.44, "word": ".", "probability": 0.55419921875 } ] }, { "id": 557, "seek": 178344, "start": 1838.44, "end": 1841.48, "text": " That's a very common spam word we'll see in a lot of spam messages.", "tokens": [ 51614, 663, 311, 257, 588, 2689, 24028, 1349, 321, 603, 536, 294, 257, 688, 295, 24028, 7897, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.21636652176157903, "compression_ratio": 1.7302904564315353, "no_speech_prob": 0.0007915496826171875, "words": [ { "start": 1838.44, "end": 1838.6, "word": " That's", "probability": 0.902587890625 }, { "start": 1838.66, "end": 1838.78, "word": " a very", "probability": 0.73828125 }, { "start": 1838.78, "end": 1839.16, "word": " common", "probability": 0.7587890625 }, { "start": 1839.16, "end": 1839.6, "word": " spam", "probability": 0.90673828125 }, { "start": 1839.6, "end": 1839.88, "word": " word", "probability": 0.7626953125 }, { "start": 1839.88, "end": 1840.06, "word": " we'll", "probability": 0.887939453125 }, { "start": 1840.06, "end": 1840.18, "word": " see", "probability": 0.8193359375 }, { "start": 1840.18, "end": 1840.28, "word": " in", "probability": 0.8779296875 }, { "start": 1840.38, "end": 1840.48, "word": " a lot", "probability": 0.89501953125 }, { "start": 1840.48, "end": 1840.56, "word": " of", "probability": 0.90283203125 }, { "start": 1840.56, "end": 1840.76, "word": " spam", "probability": 0.92822265625 }, { "start": 1840.76, "end": 1841.14, "word": " messages", "probability": 0.82861328125 }, { "start": 1841.14, "end": 1841.48, "word": ".", "probability": 0.98486328125 } ] }, { "id": 558, "seek": 181244, "start": 1841.48, "end": 1844.28, "text": " So punctuation is just not relevant", "tokens": [ 50364, 407, 27006, 16073, 307, 445, 406, 7340, 50514 ], "temperature": 0.0, "avg_logprob": -0.16473599420539264, "compression_ratio": 1.7241379310344827, "no_speech_prob": 0.0015249252319335938, "words": [ { "start": 1841.48, "end": 1842.12, "word": " So", "probability": 0.252685546875 }, { "start": 1842.12, "end": 1843.54, "word": " punctuation", "probability": 0.7252197265625 }, { "start": 1843.54, "end": 1843.7, "word": " is", "probability": 0.7763671875 }, { "start": 1843.7, "end": 1843.84, "word": " just", "probability": 0.83349609375 }, { "start": 1843.84, "end": 1843.98, "word": " not", "probability": 0.900390625 }, { "start": 1843.98, "end": 1844.28, "word": " relevant", "probability": 0.8623046875 } ] }, { "id": 559, "seek": 181244, "start": 1844.28, "end": 1847.48, "text": " because it doesn't add any context to the message.", "tokens": [ 50514, 570, 309, 1177, 380, 909, 604, 4319, 281, 264, 3636, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.16473599420539264, "compression_ratio": 1.7241379310344827, "no_speech_prob": 0.0015249252319335938, "words": [ { "start": 1844.28, "end": 1844.54, "word": " because", "probability": 0.73291015625 }, { "start": 1844.54, "end": 1844.64, "word": " it", "probability": 0.89892578125 }, { "start": 1844.64, "end": 1844.86, "word": " doesn't", "probability": 0.92333984375 }, { "start": 1844.86, "end": 1845.1, "word": " add", "probability": 0.8173828125 }, { "start": 1845.1, "end": 1845.28, "word": " any", "probability": 0.8125 }, { "start": 1845.28, "end": 1845.9, "word": " context", "probability": 0.7666015625 }, { "start": 1845.9, "end": 1846.48, "word": " to", "probability": 0.9033203125 }, { "start": 1846.48, "end": 1846.6, "word": " the", "probability": 0.8125 }, { "start": 1846.6, "end": 1847.04, "word": " message", "probability": 0.83056640625 }, { "start": 1847.04, "end": 1847.48, "word": ".", "probability": 0.7177734375 } ] }, { "id": 560, "seek": 181244, "start": 1848.72, "end": 1850.56, "text": " And so that's something that we can remove.", "tokens": [ 50664, 400, 370, 300, 311, 746, 300, 321, 393, 4159, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.16473599420539264, "compression_ratio": 1.7241379310344827, "no_speech_prob": 0.0015249252319335938, "words": [ { "start": 1848.72, "end": 1848.78, "word": " And", "probability": 0.58544921875 }, { "start": 1848.78, "end": 1848.9, "word": " so", "probability": 0.8896484375 }, { "start": 1848.9, "end": 1849.12, "word": " that's", "probability": 0.913330078125 }, { "start": 1849.12, "end": 1849.3, "word": " something", "probability": 0.748046875 }, { "start": 1849.3, "end": 1849.48, "word": " that", "probability": 0.8046875 }, { "start": 1849.48, "end": 1849.56, "word": " we", "probability": 0.90283203125 }, { "start": 1849.56, "end": 1849.7, "word": " can", "probability": 0.89697265625 }, { "start": 1849.7, "end": 1850.12, "word": " remove", "probability": 0.880859375 }, { "start": 1850.12, "end": 1850.56, "word": ".", "probability": 0.9453125 } ] }, { "id": 561, "seek": 181244, "start": 1850.82, "end": 1854.1, "text": " If you would like, you can follow through on this workbook", "tokens": [ 50814, 759, 291, 576, 411, 11, 291, 393, 1524, 807, 322, 341, 589, 2939, 50964 ], "temperature": 0.0, "avg_logprob": -0.16473599420539264, "compression_ratio": 1.7241379310344827, "no_speech_prob": 0.0015249252319335938, "words": [ { "start": 1850.82, "end": 1851.12, "word": " If", "probability": 0.88232421875 }, { "start": 1851.12, "end": 1851.22, "word": " you", "probability": 0.89599609375 }, { "start": 1851.22, "end": 1851.34, "word": " would", "probability": 0.8115234375 }, { "start": 1851.34, "end": 1851.56, "word": " like", "probability": 0.8740234375 }, { "start": 1851.56, "end": 1851.66, "word": ",", "probability": 0.68017578125 }, { "start": 1851.66, "end": 1851.74, "word": " you", "probability": 0.88671875 }, { "start": 1851.74, "end": 1852.0, "word": " can", "probability": 0.89111328125 }, { "start": 1852.0, "end": 1853.32, "word": " follow", "probability": 0.8515625 }, { "start": 1853.32, "end": 1853.5, "word": " through", "probability": 0.7783203125 }, { "start": 1853.5, "end": 1853.58, "word": " on", "probability": 0.79931640625 }, { "start": 1853.58, "end": 1853.72, "word": " this", "probability": 0.8828125 }, { "start": 1853.72, "end": 1854.1, "word": " workbook", "probability": 0.898193359375 } ] }, { "id": 562, "seek": 181244, "start": 1854.1, "end": 1856.4, "text": " and then try it without removing the punctuation", "tokens": [ 50964, 293, 550, 853, 309, 1553, 12720, 264, 27006, 16073, 51114 ], "temperature": 0.0, "avg_logprob": -0.16473599420539264, "compression_ratio": 1.7241379310344827, "no_speech_prob": 0.0015249252319335938, "words": [ { "start": 1854.1, "end": 1854.32, "word": " and", "probability": 0.73046875 }, { "start": 1854.32, "end": 1854.48, "word": " then", "probability": 0.64013671875 }, { "start": 1854.48, "end": 1854.74, "word": " try", "probability": 0.82373046875 }, { "start": 1854.74, "end": 1855.02, "word": " it", "probability": 0.896484375 }, { "start": 1855.02, "end": 1855.36, "word": " without", "probability": 0.80419921875 }, { "start": 1855.36, "end": 1855.7, "word": " removing", "probability": 0.79443359375 }, { "start": 1855.7, "end": 1855.88, "word": " the", "probability": 0.80224609375 }, { "start": 1855.88, "end": 1856.4, "word": " punctuation", "probability": 0.9111328125 } ] }, { "id": 563, "seek": 181244, "start": 1856.4, "end": 1858.74, "text": " and see if you notice any differences.", "tokens": [ 51114, 293, 536, 498, 291, 3449, 604, 7300, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.16473599420539264, "compression_ratio": 1.7241379310344827, "no_speech_prob": 0.0015249252319335938, "words": [ { "start": 1856.4, "end": 1856.86, "word": " and", "probability": 0.6953125 }, { "start": 1856.86, "end": 1857.14, "word": " see", "probability": 0.81201171875 }, { "start": 1857.14, "end": 1857.38, "word": " if", "probability": 0.9033203125 }, { "start": 1857.38, "end": 1857.5, "word": " you", "probability": 0.89013671875 }, { "start": 1857.5, "end": 1857.74, "word": " notice", "probability": 0.841796875 }, { "start": 1857.74, "end": 1857.94, "word": " any", "probability": 0.82373046875 }, { "start": 1857.94, "end": 1858.3, "word": " differences", "probability": 0.68017578125 }, { "start": 1858.3, "end": 1858.74, "word": ".", "probability": 0.72705078125 } ] }, { "id": 564, "seek": 181244, "start": 1859.96, "end": 1862.22, "text": " But I don't think there would be any differences", "tokens": [ 51264, 583, 286, 500, 380, 519, 456, 576, 312, 604, 7300, 51414 ], "temperature": 0.0, "avg_logprob": -0.16473599420539264, "compression_ratio": 1.7241379310344827, "no_speech_prob": 0.0015249252319335938, "words": [ { "start": 1859.96, "end": 1860.4, "word": " But", "probability": 0.85546875 }, { "start": 1860.4, "end": 1860.84, "word": " I", "probability": 0.93115234375 }, { "start": 1860.84, "end": 1861.1, "word": " don't", "probability": 0.9482421875 }, { "start": 1861.1, "end": 1861.28, "word": " think", "probability": 0.80322265625 }, { "start": 1861.28, "end": 1861.42, "word": " there", "probability": 0.84912109375 }, { "start": 1861.42, "end": 1861.56, "word": " would", "probability": 0.845703125 }, { "start": 1861.56, "end": 1861.68, "word": " be", "probability": 0.9111328125 }, { "start": 1861.68, "end": 1861.86, "word": " any", "probability": 0.8173828125 }, { "start": 1861.86, "end": 1862.22, "word": " differences", "probability": 0.708984375 } ] }, { "id": 565, "seek": 181244, "start": 1862.22, "end": 1864.46, "text": " just because of that context.", "tokens": [ 51414, 445, 570, 295, 300, 4319, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.16473599420539264, "compression_ratio": 1.7241379310344827, "no_speech_prob": 0.0015249252319335938, "words": [ { "start": 1862.22, "end": 1863.08, "word": " just", "probability": 0.666015625 }, { "start": 1863.08, "end": 1863.3, "word": " because", "probability": 0.841796875 }, { "start": 1863.3, "end": 1863.42, "word": " of", "probability": 0.89599609375 }, { "start": 1863.42, "end": 1863.54, "word": " that", "probability": 0.8759765625 }, { "start": 1863.54, "end": 1864.02, "word": " context", "probability": 0.77490234375 }, { "start": 1864.02, "end": 1864.46, "word": ".", "probability": 0.9501953125 } ] }, { "id": 566, "seek": 181244, "start": 1864.64, "end": 1869.32, "text": " There are better things to weigh than periods, question marks, commas,", "tokens": [ 51514, 821, 366, 1101, 721, 281, 13843, 813, 13804, 11, 1168, 10640, 11, 800, 296, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.16473599420539264, "compression_ratio": 1.7241379310344827, "no_speech_prob": 0.0015249252319335938, "words": [ { "start": 1864.64, "end": 1864.66, "word": " There", "probability": 0.79736328125 }, { "start": 1864.66, "end": 1865.08, "word": " are", "probability": 0.8583984375 }, { "start": 1865.08, "end": 1865.86, "word": " better", "probability": 0.83837890625 }, { "start": 1865.86, "end": 1866.28, "word": " things", "probability": 0.7509765625 }, { "start": 1866.28, "end": 1866.5, "word": " to", "probability": 0.90283203125 }, { "start": 1866.5, "end": 1866.8, "word": " weigh", "probability": 0.8564453125 }, { "start": 1866.8, "end": 1867.56, "word": " than", "probability": 0.81591796875 }, { "start": 1867.56, "end": 1868.06, "word": " periods", "probability": 0.76123046875 }, { "start": 1868.06, "end": 1868.16, "word": ",", "probability": 0.97607421875 }, { "start": 1868.16, "end": 1868.36, "word": " question", "probability": 0.791015625 }, { "start": 1868.36, "end": 1868.56, "word": " marks", "probability": 0.75537109375 }, { "start": 1868.56, "end": 1868.74, "word": ",", "probability": 0.98583984375 }, { "start": 1868.74, "end": 1869.12, "word": " commas", "probability": 0.865478515625 }, { "start": 1869.12, "end": 1869.32, "word": ",", "probability": 0.8818359375 } ] }, { "id": 567, "seek": 181244, "start": 1869.32, "end": 1870.48, "text": " things of that nature.", "tokens": [ 51714, 721, 295, 300, 3687, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.16473599420539264, "compression_ratio": 1.7241379310344827, "no_speech_prob": 0.0015249252319335938, "words": [ { "start": 1869.32, "end": 1869.5, "word": " things", "probability": 0.72412109375 }, { "start": 1869.5, "end": 1869.62, "word": " of", "probability": 0.9052734375 }, { "start": 1869.62, "end": 1869.76, "word": " that", "probability": 0.88134765625 }, { "start": 1869.76, "end": 1870.04, "word": " nature", "probability": 0.7900390625 }, { "start": 1870.04, "end": 1870.48, "word": ".", "probability": 0.99462890625 } ] }, { "id": 568, "seek": 183888, "start": 1870.48, "end": 1874.36, "text": " And then as you see, emails or websites,", "tokens": [ 50364, 400, 550, 382, 291, 536, 11, 12524, 420, 12891, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.21469907200446836, "compression_ratio": 1.5972850678733033, "no_speech_prob": 0.0009255409240722656, "words": [ { "start": 1870.48, "end": 1871.24, "word": " And", "probability": 0.556640625 }, { "start": 1871.24, "end": 1871.38, "word": " then", "probability": 0.69482421875 }, { "start": 1871.38, "end": 1871.58, "word": " as", "probability": 0.80859375 }, { "start": 1871.58, "end": 1871.7, "word": " you", "probability": 0.8984375 }, { "start": 1871.7, "end": 1872.02, "word": " see", "probability": 0.81884765625 }, { "start": 1872.02, "end": 1872.2, "word": ",", "probability": 0.273681640625 }, { "start": 1872.2, "end": 1873.14, "word": " emails", "probability": 0.658203125 }, { "start": 1873.14, "end": 1873.68, "word": " or", "probability": 0.8291015625 }, { "start": 1873.68, "end": 1874.24, "word": " websites", "probability": 0.892578125 }, { "start": 1874.24, "end": 1874.36, "word": ",", "probability": 0.525390625 } ] }, { "id": 569, "seek": 183888, "start": 1874.36, "end": 1877.22, "text": " such as lists.debian.org, they still have their punctuation", "tokens": [ 50514, 1270, 382, 14511, 13, 1479, 20196, 13, 4646, 11, 436, 920, 362, 641, 27006, 16073, 50664 ], "temperature": 0.0, "avg_logprob": -0.21469907200446836, "compression_ratio": 1.5972850678733033, "no_speech_prob": 0.0009255409240722656, "words": [ { "start": 1874.36, "end": 1874.62, "word": " such", "probability": 0.39697265625 }, { "start": 1874.62, "end": 1874.94, "word": " as", "probability": 0.8994140625 }, { "start": 1874.94, "end": 1875.2, "word": " lists", "probability": 0.55615234375 }, { "start": 1875.2, "end": 1875.64, "word": ".debian", "probability": 0.87548828125 }, { "start": 1875.64, "end": 1876.04, "word": ".org", "probability": 0.974365234375 }, { "start": 1876.04, "end": 1876.12, "word": ",", "probability": 0.80419921875 }, { "start": 1876.12, "end": 1876.24, "word": " they", "probability": 0.73779296875 }, { "start": 1876.24, "end": 1876.4, "word": " still", "probability": 0.89892578125 }, { "start": 1876.4, "end": 1876.54, "word": " have", "probability": 0.87939453125 }, { "start": 1876.54, "end": 1876.68, "word": " their", "probability": 0.89697265625 }, { "start": 1876.68, "end": 1877.22, "word": " punctuation", "probability": 0.916259765625 } ] }, { "id": 570, "seek": 183888, "start": 1877.22, "end": 1881.08, "text": " because that's not the word lists, debian, and org.", "tokens": [ 50664, 570, 300, 311, 406, 264, 1349, 14511, 11, 3001, 952, 11, 293, 14045, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.21469907200446836, "compression_ratio": 1.5972850678733033, "no_speech_prob": 0.0009255409240722656, "words": [ { "start": 1877.22, "end": 1877.66, "word": " because", "probability": 0.69189453125 }, { "start": 1877.66, "end": 1878.86, "word": " that's", "probability": 0.92529296875 }, { "start": 1878.86, "end": 1879.08, "word": " not", "probability": 0.8955078125 }, { "start": 1879.08, "end": 1879.28, "word": " the", "probability": 0.8154296875 }, { "start": 1879.28, "end": 1879.54, "word": " word", "probability": 0.830078125 }, { "start": 1879.54, "end": 1879.96, "word": " lists", "probability": 0.419677734375 }, { "start": 1879.96, "end": 1880.22, "word": ",", "probability": 0.83984375 }, { "start": 1880.22, "end": 1880.56, "word": " debian", "probability": 0.6448974609375 }, { "start": 1880.56, "end": 1880.72, "word": ",", "probability": 0.50927734375 }, { "start": 1880.72, "end": 1880.78, "word": " and", "probability": 0.7470703125 }, { "start": 1880.78, "end": 1881.04, "word": " org", "probability": 0.78369140625 }, { "start": 1881.04, "end": 1881.08, "word": ".", "probability": 0.36669921875 } ] }, { "id": 571, "seek": 183888, "start": 1881.08, "end": 1884.46, "text": " That is a URL, lists.debian.org.", "tokens": [ 50864, 663, 307, 257, 12905, 11, 14511, 13, 1479, 20196, 13, 4646, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.21469907200446836, "compression_ratio": 1.5972850678733033, "no_speech_prob": 0.0009255409240722656, "words": [ { "start": 1881.08, "end": 1881.42, "word": " That", "probability": 0.7958984375 }, { "start": 1881.42, "end": 1881.72, "word": " is", "probability": 0.90625 }, { "start": 1882.16, "end": 1882.48, "word": " a URL", "probability": 0.7294921875 }, { "start": 1882.48, "end": 1882.9, "word": ",", "probability": 0.6015625 }, { "start": 1882.9, "end": 1883.1, "word": " lists", "probability": 0.50732421875 }, { "start": 1883.1, "end": 1883.5, "word": ".debian", "probability": 0.9112955729166666 }, { "start": 1883.5, "end": 1883.98, "word": ".org", "probability": 0.97021484375 }, { "start": 1883.98, "end": 1884.46, "word": ".", "probability": 0.9013671875 } ] }, { "id": 572, "seek": 183888, "start": 1884.46, "end": 1886.36, "text": " And so that's kind of the difference there.", "tokens": [ 51014, 400, 370, 300, 311, 733, 295, 264, 2649, 456, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.21469907200446836, "compression_ratio": 1.5972850678733033, "no_speech_prob": 0.0009255409240722656, "words": [ { "start": 1884.46, "end": 1884.6, "word": " And", "probability": 0.86376953125 }, { "start": 1884.6, "end": 1884.72, "word": " so", "probability": 0.9013671875 }, { "start": 1884.72, "end": 1884.98, "word": " that's", "probability": 0.9140625 }, { "start": 1884.98, "end": 1885.14, "word": " kind", "probability": 0.6728515625 }, { "start": 1885.14, "end": 1885.22, "word": " of", "probability": 0.90625 }, { "start": 1885.22, "end": 1885.48, "word": " the", "probability": 0.80859375 }, { "start": 1885.48, "end": 1885.96, "word": " difference", "probability": 0.6748046875 }, { "start": 1885.96, "end": 1886.26, "word": " there", "probability": 0.8603515625 }, { "start": 1886.26, "end": 1886.36, "word": ".", "probability": 0.96875 } ] }, { "id": 573, "seek": 183888, "start": 1886.36, "end": 1890.12, "text": " If we had hyphenated words, we would see them included in here as well.", "tokens": [ 51164, 759, 321, 632, 2477, 47059, 770, 2283, 11, 321, 576, 536, 552, 5556, 294, 510, 382, 731, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.21469907200446836, "compression_ratio": 1.5972850678733033, "no_speech_prob": 0.0009255409240722656, "words": [ { "start": 1886.36, "end": 1886.44, "word": " If", "probability": 0.896484375 }, { "start": 1886.44, "end": 1886.56, "word": " we", "probability": 0.90380859375 }, { "start": 1886.56, "end": 1886.82, "word": " had", "probability": 0.81298828125 }, { "start": 1886.82, "end": 1887.32, "word": " hyphenated", "probability": 0.9456380208333334 }, { "start": 1887.32, "end": 1887.66, "word": " words", "probability": 0.72705078125 }, { "start": 1887.66, "end": 1887.7, "word": ",", "probability": 0.92041015625 }, { "start": 1887.7, "end": 1887.8, "word": " we", "probability": 0.9013671875 }, { "start": 1887.8, "end": 1887.96, "word": " would", "probability": 0.84716796875 }, { "start": 1887.96, "end": 1888.14, "word": " see", "probability": 0.818359375 }, { "start": 1888.14, "end": 1888.36, "word": " them", "probability": 0.74267578125 }, { "start": 1888.36, "end": 1888.86, "word": " included", "probability": 0.7666015625 }, { "start": 1888.86, "end": 1889.04, "word": " in", "probability": 0.896484375 }, { "start": 1889.04, "end": 1889.22, "word": " here", "probability": 0.8095703125 }, { "start": 1889.22, "end": 1889.38, "word": " as", "probability": 0.88525390625 }, { "start": 1889.38, "end": 1889.6, "word": " well", "probability": 0.87890625 }, { "start": 1889.6, "end": 1890.12, "word": ".", "probability": 0.9990234375 } ] }, { "id": 574, "seek": 183888, "start": 1893.66, "end": 1896.92, "text": " So we're going to go on and load the training data.", "tokens": [ 51464, 407, 321, 434, 516, 281, 352, 322, 293, 3677, 264, 3097, 1412, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.21469907200446836, "compression_ratio": 1.5972850678733033, "no_speech_prob": 0.0009255409240722656, "words": [ { "start": 1893.66, "end": 1894.18, "word": " So", "probability": 0.84423828125 }, { "start": 1894.18, "end": 1894.7, "word": " we're", "probability": 0.806640625 }, { "start": 1894.7, "end": 1894.76, "word": " going", "probability": 0.298583984375 }, { "start": 1894.76, "end": 1894.8, "word": " to", "probability": 0.9033203125 }, { "start": 1894.8, "end": 1894.94, "word": " go", "probability": 0.90087890625 }, { "start": 1894.94, "end": 1895.14, "word": " on", "probability": 0.90869140625 }, { "start": 1895.14, "end": 1895.54, "word": " and", "probability": 0.8798828125 }, { "start": 1895.54, "end": 1895.9, "word": " load", "probability": 0.9248046875 }, { "start": 1895.9, "end": 1896.06, "word": " the", "probability": 0.8115234375 }, { "start": 1896.06, "end": 1896.3, "word": " training", "probability": 0.802734375 }, { "start": 1896.3, "end": 1896.62, "word": " data", "probability": 0.814453125 }, { "start": 1896.62, "end": 1896.92, "word": ".", "probability": 0.99755859375 } ] }, { "id": 575, "seek": 186608, "start": 1896.92, "end": 1902.82, "text": " This one is just going to give us the counts that we need.", "tokens": [ 50364, 639, 472, 307, 445, 516, 281, 976, 505, 264, 14893, 300, 321, 643, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.20525568222457713, "compression_ratio": 2.1256544502617802, "no_speech_prob": 0.009857177734375, "words": [ { "start": 1896.92, "end": 1897.12, "word": " This", "probability": 0.52001953125 }, { "start": 1897.12, "end": 1897.42, "word": " one", "probability": 0.78076171875 }, { "start": 1897.42, "end": 1897.94, "word": " is", "probability": 0.90185546875 }, { "start": 1897.94, "end": 1898.34, "word": " just", "probability": 0.85009765625 }, { "start": 1898.34, "end": 1898.56, "word": " going", "probability": 0.85400390625 }, { "start": 1898.56, "end": 1898.94, "word": " to", "probability": 0.90283203125 }, { "start": 1898.94, "end": 1901.12, "word": " give", "probability": 0.7783203125 }, { "start": 1901.12, "end": 1901.3, "word": " us", "probability": 0.90576171875 }, { "start": 1901.3, "end": 1901.5, "word": " the", "probability": 0.80908203125 }, { "start": 1901.5, "end": 1901.94, "word": " counts", "probability": 0.7744140625 }, { "start": 1901.94, "end": 1902.16, "word": " that", "probability": 0.87890625 }, { "start": 1902.16, "end": 1902.28, "word": " we", "probability": 0.90673828125 }, { "start": 1902.28, "end": 1902.58, "word": " need", "probability": 0.8115234375 }, { "start": 1902.58, "end": 1902.82, "word": ".", "probability": 0.8779296875 } ] }, { "id": 576, "seek": 186608, "start": 1902.82, "end": 1904.5, "text": " This is just done for you.", "tokens": [ 50614, 639, 307, 445, 1096, 337, 291, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.20525568222457713, "compression_ratio": 2.1256544502617802, "no_speech_prob": 0.009857177734375, "words": [ { "start": 1902.82, "end": 1902.98, "word": " This", "probability": 0.78857421875 }, { "start": 1902.98, "end": 1903.1, "word": " is", "probability": 0.90576171875 }, { "start": 1903.1, "end": 1903.24, "word": " just", "probability": 0.880859375 }, { "start": 1903.24, "end": 1903.48, "word": " done", "probability": 0.853515625 }, { "start": 1903.48, "end": 1903.74, "word": " for", "probability": 0.8994140625 }, { "start": 1903.74, "end": 1904.06, "word": " you", "probability": 0.896484375 }, { "start": 1904.06, "end": 1904.5, "word": ".", "probability": 0.9208984375 } ] }, { "id": 577, "seek": 186608, "start": 1904.5, "end": 1906.86, "text": " Remember, one of those five things that we needed to keep track", "tokens": [ 50714, 5459, 11, 472, 295, 729, 1732, 721, 300, 321, 2978, 281, 1066, 2837, 50864 ], "temperature": 0.0, "avg_logprob": -0.20525568222457713, "compression_ratio": 2.1256544502617802, "no_speech_prob": 0.009857177734375, "words": [ { "start": 1904.5, "end": 1904.92, "word": " Remember", "probability": 0.892578125 }, { "start": 1904.92, "end": 1905.1, "word": ",", "probability": 0.46337890625 }, { "start": 1905.1, "end": 1905.16, "word": " one", "probability": 0.81884765625 }, { "start": 1905.16, "end": 1905.26, "word": " of", "probability": 0.90380859375 }, { "start": 1905.26, "end": 1905.42, "word": " those", "probability": 0.82373046875 }, { "start": 1905.42, "end": 1905.7, "word": " five", "probability": 0.7734375 }, { "start": 1905.7, "end": 1905.92, "word": " things", "probability": 0.73486328125 }, { "start": 1905.92, "end": 1906.04, "word": " that", "probability": 0.85498046875 }, { "start": 1906.04, "end": 1906.12, "word": " we", "probability": 0.90625 }, { "start": 1906.12, "end": 1906.24, "word": " needed", "probability": 0.35400390625 }, { "start": 1906.24, "end": 1906.38, "word": " to", "probability": 0.91064453125 }, { "start": 1906.38, "end": 1906.52, "word": " keep", "probability": 0.7958984375 }, { "start": 1906.52, "end": 1906.86, "word": " track", "probability": 0.8251953125 } ] }, { "id": 578, "seek": 186608, "start": 1906.86, "end": 1912.44, "text": " was all of the word counts in the ham emails,", "tokens": [ 50864, 390, 439, 295, 264, 1349, 14893, 294, 264, 7852, 12524, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.20525568222457713, "compression_ratio": 2.1256544502617802, "no_speech_prob": 0.009857177734375, "words": [ { "start": 1906.86, "end": 1907.44, "word": " was", "probability": 0.822265625 }, { "start": 1907.44, "end": 1909.5, "word": " all", "probability": 0.81201171875 }, { "start": 1909.5, "end": 1909.64, "word": " of", "probability": 0.896484375 }, { "start": 1909.64, "end": 1910.04, "word": " the", "probability": 0.81591796875 }, { "start": 1910.04, "end": 1910.48, "word": " word", "probability": 0.66162109375 }, { "start": 1910.48, "end": 1910.9, "word": " counts", "probability": 0.7646484375 }, { "start": 1910.9, "end": 1911.36, "word": " in", "probability": 0.8447265625 }, { "start": 1911.36, "end": 1911.8, "word": " the", "probability": 0.79345703125 }, { "start": 1911.8, "end": 1911.98, "word": " ham", "probability": 0.32763671875 }, { "start": 1911.98, "end": 1912.34, "word": " emails", "probability": 0.79638671875 }, { "start": 1912.34, "end": 1912.44, "word": ",", "probability": 0.796875 } ] }, { "id": 579, "seek": 186608, "start": 1912.44, "end": 1914.94, "text": " all the word counts in the spam emails.", "tokens": [ 51114, 439, 264, 1349, 14893, 294, 264, 24028, 12524, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.20525568222457713, "compression_ratio": 2.1256544502617802, "no_speech_prob": 0.009857177734375, "words": [ { "start": 1912.44, "end": 1912.56, "word": " all", "probability": 0.87451171875 }, { "start": 1912.56, "end": 1912.68, "word": " the", "probability": 0.5673828125 }, { "start": 1912.68, "end": 1912.88, "word": " word", "probability": 0.80615234375 }, { "start": 1912.88, "end": 1913.16, "word": " counts", "probability": 0.77392578125 }, { "start": 1913.16, "end": 1913.48, "word": " in", "probability": 0.88916015625 }, { "start": 1913.48, "end": 1913.72, "word": " the", "probability": 0.80615234375 }, { "start": 1913.72, "end": 1913.98, "word": " spam", "probability": 0.91845703125 }, { "start": 1913.98, "end": 1914.5, "word": " emails", "probability": 0.8017578125 }, { "start": 1914.5, "end": 1914.94, "word": ".", "probability": 0.68603515625 } ] }, { "id": 580, "seek": 186608, "start": 1915.2, "end": 1918.12, "text": " But what this is going to do is count the number of emails", "tokens": [ 51264, 583, 437, 341, 307, 516, 281, 360, 307, 1207, 264, 1230, 295, 12524, 51414 ], "temperature": 0.0, "avg_logprob": -0.20525568222457713, "compression_ratio": 2.1256544502617802, "no_speech_prob": 0.009857177734375, "words": [ { "start": 1915.2, "end": 1915.64, "word": " But", "probability": 0.8564453125 }, { "start": 1915.64, "end": 1915.78, "word": " what", "probability": 0.86669921875 }, { "start": 1915.78, "end": 1915.94, "word": " this", "probability": 0.88427734375 }, { "start": 1915.94, "end": 1916.06, "word": " is", "probability": 0.90478515625 }, { "start": 1916.06, "end": 1916.2, "word": " going", "probability": 0.85400390625 }, { "start": 1916.2, "end": 1916.34, "word": " to", "probability": 0.90673828125 }, { "start": 1916.34, "end": 1916.54, "word": " do", "probability": 0.9033203125 }, { "start": 1916.54, "end": 1916.76, "word": " is", "probability": 0.88134765625 }, { "start": 1916.76, "end": 1917.12, "word": " count", "probability": 0.7685546875 }, { "start": 1917.12, "end": 1917.34, "word": " the", "probability": 0.7509765625 }, { "start": 1917.34, "end": 1917.6, "word": " number", "probability": 0.88720703125 }, { "start": 1917.6, "end": 1917.8, "word": " of", "probability": 0.908203125 }, { "start": 1917.8, "end": 1918.12, "word": " emails", "probability": 0.77978515625 } ] }, { "id": 581, "seek": 186608, "start": 1918.12, "end": 1921.76, "text": " that we have in ham, count the number of emails that we have in spam,", "tokens": [ 51414, 300, 321, 362, 294, 7852, 11, 1207, 264, 1230, 295, 12524, 300, 321, 362, 294, 24028, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.20525568222457713, "compression_ratio": 2.1256544502617802, "no_speech_prob": 0.009857177734375, "words": [ { "start": 1918.12, "end": 1918.36, "word": " that", "probability": 0.87890625 }, { "start": 1918.36, "end": 1918.48, "word": " we", "probability": 0.90673828125 }, { "start": 1918.48, "end": 1918.94, "word": " have", "probability": 0.87841796875 }, { "start": 1918.94, "end": 1919.22, "word": " in", "probability": 0.896484375 }, { "start": 1919.22, "end": 1919.52, "word": " ham", "probability": 0.7919921875 }, { "start": 1919.52, "end": 1919.66, "word": ",", "probability": 0.82373046875 }, { "start": 1919.66, "end": 1919.84, "word": " count", "probability": 0.77001953125 }, { "start": 1919.84, "end": 1920.0, "word": " the", "probability": 0.80810546875 }, { "start": 1920.0, "end": 1920.18, "word": " number", "probability": 0.89599609375 }, { "start": 1920.18, "end": 1920.34, "word": " of", "probability": 0.90673828125 }, { "start": 1920.34, "end": 1920.58, "word": " emails", "probability": 0.77587890625 }, { "start": 1920.58, "end": 1920.78, "word": " that", "probability": 0.8779296875 }, { "start": 1920.78, "end": 1920.88, "word": " we", "probability": 0.90625 }, { "start": 1920.88, "end": 1921.22, "word": " have", "probability": 0.87060546875 }, { "start": 1921.22, "end": 1921.36, "word": " in", "probability": 0.86669921875 }, { "start": 1921.36, "end": 1921.68, "word": " spam", "probability": 0.87744140625 }, { "start": 1921.68, "end": 1921.76, "word": ",", "probability": 0.69970703125 } ] }, { "id": 582, "seek": 186608, "start": 1921.76, "end": 1924.12, "text": " and then count the total number of emails", "tokens": [ 51564, 293, 550, 1207, 264, 3217, 1230, 295, 12524, 51714 ], "temperature": 0.0, "avg_logprob": -0.20525568222457713, "compression_ratio": 2.1256544502617802, "no_speech_prob": 0.009857177734375, "words": [ { "start": 1921.76, "end": 1921.84, "word": " and", "probability": 0.88720703125 }, { "start": 1921.84, "end": 1922.0, "word": " then", "probability": 0.72509765625 }, { "start": 1922.0, "end": 1922.24, "word": " count", "probability": 0.8115234375 }, { "start": 1922.24, "end": 1922.42, "word": " the", "probability": 0.798828125 }, { "start": 1922.42, "end": 1923.06, "word": " total", "probability": 0.80859375 }, { "start": 1923.06, "end": 1923.38, "word": " number", "probability": 0.8857421875 }, { "start": 1923.38, "end": 1923.66, "word": " of", "probability": 0.90869140625 }, { "start": 1923.66, "end": 1924.12, "word": " emails", "probability": 0.77880859375 } ] }, { "id": 583, "seek": 189520, "start": 1924.12, "end": 1927.6, "text": " that we have in our testing set.", "tokens": [ 50364, 300, 321, 362, 294, 527, 4997, 992, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.19701087137927178, "compression_ratio": 1.6329113924050633, "no_speech_prob": 0.001926422119140625, "words": [ { "start": 1924.12, "end": 1924.54, "word": " that", "probability": 0.24462890625 }, { "start": 1924.54, "end": 1925.32, "word": " we", "probability": 0.8974609375 }, { "start": 1925.32, "end": 1925.68, "word": " have", "probability": 0.87744140625 }, { "start": 1925.68, "end": 1926.04, "word": " in", "probability": 0.9013671875 }, { "start": 1926.04, "end": 1926.38, "word": " our", "probability": 0.818359375 }, { "start": 1926.38, "end": 1926.78, "word": " testing", "probability": 0.69921875 }, { "start": 1926.78, "end": 1927.12, "word": " set", "probability": 0.8759765625 }, { "start": 1927.12, "end": 1927.6, "word": ".", "probability": 0.95068359375 } ] }, { "id": 584, "seek": 189520, "start": 1927.98, "end": 1932.18, "text": " So for here, our testing and training split is already defined.", "tokens": [ 50514, 407, 337, 510, 11, 527, 4997, 293, 3097, 7472, 307, 1217, 7642, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.19701087137927178, "compression_ratio": 1.6329113924050633, "no_speech_prob": 0.001926422119140625, "words": [ { "start": 1927.98, "end": 1927.98, "word": " So", "probability": 0.61572265625 }, { "start": 1927.98, "end": 1928.22, "word": " for", "probability": 0.71337890625 }, { "start": 1928.22, "end": 1928.5, "word": " here", "probability": 0.82373046875 }, { "start": 1928.5, "end": 1928.66, "word": ",", "probability": 0.58251953125 }, { "start": 1928.66, "end": 1928.8, "word": " our", "probability": 0.80126953125 }, { "start": 1928.8, "end": 1929.26, "word": " testing", "probability": 0.7041015625 }, { "start": 1929.26, "end": 1929.42, "word": " and", "probability": 0.8740234375 }, { "start": 1929.42, "end": 1929.62, "word": " training", "probability": 0.81591796875 }, { "start": 1929.62, "end": 1929.88, "word": " split", "probability": 0.68115234375 }, { "start": 1929.88, "end": 1930.02, "word": " is", "probability": 0.89794921875 }, { "start": 1930.02, "end": 1930.28, "word": " already", "probability": 0.8037109375 }, { "start": 1930.28, "end": 1931.86, "word": " defined", "probability": 0.65771484375 }, { "start": 1931.86, "end": 1932.18, "word": ".", "probability": 0.6337890625 } ] }, { "id": 585, "seek": 189520, "start": 1932.18, "end": 1936.66, "text": " It's 80-20, and so we'll see that in a moment.", "tokens": [ 50714, 467, 311, 4688, 12, 2009, 11, 293, 370, 321, 603, 536, 300, 294, 257, 1623, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.19701087137927178, "compression_ratio": 1.6329113924050633, "no_speech_prob": 0.001926422119140625, "words": [ { "start": 1932.18, "end": 1932.44, "word": " It's", "probability": 0.94482421875 }, { "start": 1932.44, "end": 1933.52, "word": " 80", "probability": 0.91162109375 }, { "start": 1933.52, "end": 1933.92, "word": "-20", "probability": 0.6241455078125 }, { "start": 1933.92, "end": 1934.92, "word": ",", "probability": 0.428955078125 }, { "start": 1934.92, "end": 1935.16, "word": " and", "probability": 0.7900390625 }, { "start": 1935.16, "end": 1935.3, "word": " so", "probability": 0.87451171875 }, { "start": 1935.3, "end": 1935.46, "word": " we'll", "probability": 0.914794921875 }, { "start": 1935.46, "end": 1935.62, "word": " see", "probability": 0.8115234375 }, { "start": 1935.62, "end": 1935.8, "word": " that", "probability": 0.88330078125 }, { "start": 1935.8, "end": 1935.9, "word": " in", "probability": 0.90283203125 }, { "start": 1936.0, "end": 1936.18, "word": " a moment", "probability": 0.91748046875 }, { "start": 1936.18, "end": 1936.66, "word": ".", "probability": 0.97900390625 } ] }, { "id": 586, "seek": 189520, "start": 1937.44, "end": 1940.02, "text": " And we go ahead and hop into our second task,", "tokens": [ 50964, 400, 321, 352, 2286, 293, 3818, 666, 527, 1150, 5633, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.19701087137927178, "compression_ratio": 1.6329113924050633, "no_speech_prob": 0.001926422119140625, "words": [ { "start": 1937.44, "end": 1937.92, "word": " And", "probability": 0.673828125 }, { "start": 1937.92, "end": 1938.0, "word": " we", "probability": 0.8662109375 }, { "start": 1938.0, "end": 1938.1, "word": " go", "probability": 0.88525390625 }, { "start": 1938.1, "end": 1938.28, "word": " ahead", "probability": 0.84619140625 }, { "start": 1938.28, "end": 1938.4, "word": " and", "probability": 0.88232421875 }, { "start": 1938.4, "end": 1938.54, "word": " hop", "probability": 0.89501953125 }, { "start": 1938.54, "end": 1938.72, "word": " into", "probability": 0.7236328125 }, { "start": 1938.72, "end": 1939.02, "word": " our", "probability": 0.8134765625 }, { "start": 1939.02, "end": 1939.5, "word": " second", "probability": 0.7802734375 }, { "start": 1939.5, "end": 1939.94, "word": " task", "probability": 0.81298828125 }, { "start": 1939.94, "end": 1940.02, "word": ",", "probability": 0.845703125 } ] }, { "id": 587, "seek": 189520, "start": 1940.02, "end": 1942.2, "text": " which is to load the training data.", "tokens": [ 51114, 597, 307, 281, 3677, 264, 3097, 1412, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.19701087137927178, "compression_ratio": 1.6329113924050633, "no_speech_prob": 0.001926422119140625, "words": [ { "start": 1940.02, "end": 1940.14, "word": " which", "probability": 0.91357421875 }, { "start": 1940.14, "end": 1940.28, "word": " is", "probability": 0.90673828125 }, { "start": 1940.28, "end": 1940.4, "word": " to", "probability": 0.89892578125 }, { "start": 1940.4, "end": 1940.76, "word": " load", "probability": 0.90673828125 }, { "start": 1940.76, "end": 1940.98, "word": " the", "probability": 0.80859375 }, { "start": 1940.98, "end": 1941.3, "word": " training", "probability": 0.814453125 }, { "start": 1941.3, "end": 1941.72, "word": " data", "probability": 0.818359375 }, { "start": 1941.72, "end": 1942.2, "word": ".", "probability": 0.9912109375 } ] }, { "id": 588, "seek": 189520, "start": 1942.6, "end": 1945.9, "text": " So task two, it asks us to create two lists,", "tokens": [ 51264, 407, 5633, 732, 11, 309, 8962, 505, 281, 1884, 732, 14511, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.19701087137927178, "compression_ratio": 1.6329113924050633, "no_speech_prob": 0.001926422119140625, "words": [ { "start": 1942.6, "end": 1942.86, "word": " So", "probability": 0.81982421875 }, { "start": 1942.86, "end": 1943.76, "word": " task", "probability": 0.59130859375 }, { "start": 1943.76, "end": 1943.98, "word": " two", "probability": 0.662109375 }, { "start": 1943.98, "end": 1944.12, "word": ",", "probability": 0.9013671875 }, { "start": 1944.12, "end": 1944.2, "word": " it", "probability": 0.9033203125 }, { "start": 1944.2, "end": 1944.44, "word": " asks", "probability": 0.734375 }, { "start": 1944.44, "end": 1944.62, "word": " us", "probability": 0.90576171875 }, { "start": 1944.62, "end": 1945.0, "word": " to", "probability": 0.9052734375 }, { "start": 1945.0, "end": 1945.42, "word": " create", "probability": 0.8349609375 }, { "start": 1945.42, "end": 1945.62, "word": " two", "probability": 0.82421875 }, { "start": 1945.62, "end": 1945.86, "word": " lists", "probability": 0.80908203125 }, { "start": 1945.86, "end": 1945.9, "word": ",", "probability": 0.54541015625 } ] }, { "id": 589, "seek": 189520, "start": 1945.9, "end": 1947.26, "text": " and we're going to have corpus.", "tokens": [ 51414, 293, 321, 434, 516, 281, 362, 1181, 31624, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.19701087137927178, "compression_ratio": 1.6329113924050633, "no_speech_prob": 0.001926422119140625, "words": [ { "start": 1945.9, "end": 1946.0, "word": " and", "probability": 0.67822265625 }, { "start": 1946.0, "end": 1946.1, "word": " we're", "probability": 0.9248046875 }, { "start": 1946.1, "end": 1946.14, "word": " going", "probability": 0.367919921875 }, { "start": 1946.14, "end": 1946.16, "word": " to", "probability": 0.90087890625 }, { "start": 1946.16, "end": 1946.32, "word": " have", "probability": 0.87890625 }, { "start": 1946.32, "end": 1946.78, "word": " corpus", "probability": 0.735595703125 }, { "start": 1946.78, "end": 1947.26, "word": ".", "probability": 0.7060546875 } ] }, { "id": 590, "seek": 189520, "start": 1948.04, "end": 1951.16, "text": " And it's important to get these words identical", "tokens": [ 51564, 400, 309, 311, 1021, 281, 483, 613, 2283, 14800, 51714 ], "temperature": 0.0, "avg_logprob": -0.19701087137927178, "compression_ratio": 1.6329113924050633, "no_speech_prob": 0.001926422119140625, "words": [ { "start": 1948.04, "end": 1948.38, "word": " And", "probability": 0.84033203125 }, { "start": 1948.38, "end": 1948.5, "word": " it's", "probability": 0.94970703125 }, { "start": 1948.5, "end": 1948.84, "word": " important", "probability": 0.77197265625 }, { "start": 1948.84, "end": 1949.06, "word": " to", "probability": 0.904296875 }, { "start": 1949.06, "end": 1949.22, "word": " get", "probability": 0.90283203125 }, { "start": 1949.22, "end": 1949.66, "word": " these", "probability": 0.703125 }, { "start": 1949.66, "end": 1950.64, "word": " words", "probability": 0.716796875 }, { "start": 1950.64, "end": 1951.16, "word": " identical", "probability": 0.78857421875 } ] }, { "id": 591, "seek": 189520, "start": 1951.16, "end": 1953.24, "text": " because of how we use them later on.", "tokens": [ 51714, 570, 295, 577, 321, 764, 552, 1780, 322, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.19701087137927178, "compression_ratio": 1.6329113924050633, "no_speech_prob": 0.001926422119140625, "words": [ { "start": 1951.16, "end": 1951.58, "word": " because", "probability": 0.68701171875 }, { "start": 1951.58, "end": 1951.78, "word": " of", "probability": 0.9033203125 }, { "start": 1951.78, "end": 1951.9, "word": " how", "probability": 0.8984375 }, { "start": 1951.9, "end": 1952.06, "word": " we", "probability": 0.90087890625 }, { "start": 1952.06, "end": 1952.26, "word": " use", "probability": 0.8017578125 }, { "start": 1952.26, "end": 1952.42, "word": " them", "probability": 0.74462890625 }, { "start": 1952.42, "end": 1952.66, "word": " later", "probability": 0.88623046875 }, { "start": 1952.66, "end": 1953.02, "word": " on", "probability": 0.90625 }, { "start": 1953.02, "end": 1953.24, "word": ".", "probability": 0.8818359375 } ] }, { "id": 592, "seek": 191828, "start": 1953.24, "end": 1955.88, "text": " So we're going to have a list called corpus.", "tokens": [ 50364, 407, 321, 434, 516, 281, 362, 257, 1329, 1219, 1181, 31624, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.19921874361378805, "compression_ratio": 1.7380952380952381, "no_speech_prob": 0.00609588623046875, "words": [ { "start": 1953.24, "end": 1953.98, "word": " So", "probability": 0.5751953125 }, { "start": 1953.98, "end": 1954.14, "word": " we're", "probability": 0.85107421875 }, { "start": 1954.14, "end": 1954.22, "word": " going", "probability": 0.442626953125 }, { "start": 1954.22, "end": 1954.26, "word": " to", "probability": 0.90234375 }, { "start": 1954.26, "end": 1954.42, "word": " have", "probability": 0.87255859375 }, { "start": 1954.52, "end": 1954.66, "word": " a list", "probability": 0.88037109375 }, { "start": 1954.66, "end": 1954.86, "word": " called", "probability": 0.82470703125 }, { "start": 1954.86, "end": 1955.32, "word": " corpus", "probability": 0.7166748046875 }, { "start": 1955.32, "end": 1955.88, "word": ".", "probability": 0.6220703125 } ] }, { "id": 593, "seek": 191828, "start": 1955.88, "end": 1958.7, "text": " We're going to have a list called labels.", "tokens": [ 50514, 492, 434, 516, 281, 362, 257, 1329, 1219, 16949, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.19921874361378805, "compression_ratio": 1.7380952380952381, "no_speech_prob": 0.00609588623046875, "words": [ { "start": 1955.88, "end": 1956.5, "word": " We're", "probability": 0.926513671875 }, { "start": 1956.5, "end": 1956.54, "word": " going", "probability": 0.82080078125 }, { "start": 1956.54, "end": 1956.56, "word": " to", "probability": 0.90283203125 }, { "start": 1956.56, "end": 1956.74, "word": " have", "probability": 0.8759765625 }, { "start": 1956.96, "end": 1957.16, "word": " a list", "probability": 0.88623046875 }, { "start": 1957.16, "end": 1957.52, "word": " called", "probability": 0.81005859375 }, { "start": 1957.52, "end": 1958.06, "word": " labels", "probability": 0.84326171875 }, { "start": 1958.06, "end": 1958.7, "word": ".", "probability": 0.81982421875 } ] }, { "id": 594, "seek": 191828, "start": 1959.3, "end": 1962.42, "text": " And then the next bit is we want to load each of the email bodies", "tokens": [ 50664, 400, 550, 264, 958, 857, 307, 321, 528, 281, 3677, 1184, 295, 264, 3796, 7510, 50814 ], "temperature": 0.0, "avg_logprob": -0.19921874361378805, "compression_ratio": 1.7380952380952381, "no_speech_prob": 0.00609588623046875, "words": [ { "start": 1959.3, "end": 1959.52, "word": " And", "probability": 0.84814453125 }, { "start": 1959.52, "end": 1959.62, "word": " then", "probability": 0.71826171875 }, { "start": 1959.62, "end": 1959.74, "word": " the", "probability": 0.80224609375 }, { "start": 1959.74, "end": 1959.88, "word": " next", "probability": 0.8583984375 }, { "start": 1959.88, "end": 1960.06, "word": " bit", "probability": 0.87060546875 }, { "start": 1960.06, "end": 1960.26, "word": " is", "probability": 0.8994140625 }, { "start": 1960.26, "end": 1960.4, "word": " we", "probability": 0.83154296875 }, { "start": 1960.4, "end": 1960.56, "word": " want", "probability": 0.81640625 }, { "start": 1960.56, "end": 1960.7, "word": " to", "probability": 0.90380859375 }, { "start": 1960.7, "end": 1960.98, "word": " load", "probability": 0.92138671875 }, { "start": 1960.98, "end": 1961.32, "word": " each", "probability": 0.85498046875 }, { "start": 1961.32, "end": 1961.42, "word": " of", "probability": 0.90625 }, { "start": 1961.42, "end": 1961.56, "word": " the", "probability": 0.81787109375 }, { "start": 1961.56, "end": 1961.84, "word": " email", "probability": 0.89697265625 }, { "start": 1961.84, "end": 1962.42, "word": " bodies", "probability": 0.76953125 } ] }, { "id": 595, "seek": 191828, "start": 1962.42, "end": 1967.18, "text": " from the data directory slash ham and data directory slash spam", "tokens": [ 50814, 490, 264, 1412, 21120, 17330, 7852, 293, 1412, 21120, 17330, 24028, 51064 ], "temperature": 0.0, "avg_logprob": -0.19921874361378805, "compression_ratio": 1.7380952380952381, "no_speech_prob": 0.00609588623046875, "words": [ { "start": 1962.42, "end": 1962.96, "word": " from", "probability": 0.80419921875 }, { "start": 1962.96, "end": 1963.62, "word": " the", "probability": 0.81005859375 }, { "start": 1963.62, "end": 1964.06, "word": " data", "probability": 0.70361328125 }, { "start": 1964.06, "end": 1964.44, "word": " directory", "probability": 0.76416015625 }, { "start": 1964.44, "end": 1964.88, "word": " slash", "probability": 0.303955078125 }, { "start": 1964.88, "end": 1965.26, "word": " ham", "probability": 0.75390625 }, { "start": 1965.26, "end": 1965.56, "word": " and", "probability": 0.80859375 }, { "start": 1965.56, "end": 1965.76, "word": " data", "probability": 0.79345703125 }, { "start": 1965.76, "end": 1966.1, "word": " directory", "probability": 0.751953125 }, { "start": 1966.1, "end": 1966.56, "word": " slash", "probability": 0.791015625 }, { "start": 1966.56, "end": 1967.18, "word": " spam", "probability": 0.88232421875 } ] }, { "id": 596, "seek": 191828, "start": 1967.18, "end": 1969.68, "text": " into the corpus array.", "tokens": [ 51064, 666, 264, 1181, 31624, 10225, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.19921874361378805, "compression_ratio": 1.7380952380952381, "no_speech_prob": 0.00609588623046875, "words": [ { "start": 1967.18, "end": 1967.68, "word": " into", "probability": 0.73876953125 }, { "start": 1967.68, "end": 1968.04, "word": " the", "probability": 0.81787109375 }, { "start": 1968.04, "end": 1968.46, "word": " corpus", "probability": 0.911376953125 }, { "start": 1968.46, "end": 1969.04, "word": " array", "probability": 0.751953125 }, { "start": 1969.04, "end": 1969.68, "word": ".", "probability": 0.99462890625 } ] }, { "id": 597, "seek": 191828, "start": 1969.84, "end": 1976.32, "text": " So what we're going to do is for each in os.listdir,", "tokens": [ 51164, 407, 437, 321, 434, 516, 281, 360, 307, 337, 1184, 294, 3003, 13, 8264, 35043, 11, 51514 ], "temperature": 0.0, "avg_logprob": -0.19921874361378805, "compression_ratio": 1.7380952380952381, "no_speech_prob": 0.00609588623046875, "words": [ { "start": 1969.84, "end": 1970.2, "word": " So", "probability": 0.88818359375 }, { "start": 1970.2, "end": 1970.62, "word": " what", "probability": 0.8154296875 }, { "start": 1970.62, "end": 1970.72, "word": " we're", "probability": 0.925048828125 }, { "start": 1970.72, "end": 1970.8, "word": " going", "probability": 0.82470703125 }, { "start": 1970.8, "end": 1970.86, "word": " to", "probability": 0.90625 }, { "start": 1970.86, "end": 1971.12, "word": " do", "probability": 0.90771484375 }, { "start": 1971.12, "end": 1971.76, "word": " is", "probability": 0.89990234375 }, { "start": 1971.76, "end": 1972.78, "word": " for", "probability": 0.82421875 }, { "start": 1972.78, "end": 1973.9, "word": " each", "probability": 0.85693359375 }, { "start": 1973.9, "end": 1974.22, "word": " in", "probability": 0.52099609375 }, { "start": 1974.22, "end": 1974.6, "word": " os", "probability": 0.580078125 }, { "start": 1974.6, "end": 1975.58, "word": ".listdir", "probability": 0.6463216145833334 }, { "start": 1975.58, "end": 1976.32, "word": ",", "probability": 0.33349609375 } ] }, { "id": 598, "seek": 194826, "start": 1976.32, "end": 1982.28, "text": " data.dir, this was defined above, slash ham.", "tokens": [ 50364, 1412, 13, 35043, 11, 341, 390, 7642, 3673, 11, 17330, 7852, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.26994242675994573, "compression_ratio": 1.4870129870129871, "no_speech_prob": 0.027587890625, "words": [ { "start": 1976.32, "end": 1977.2, "word": " data", "probability": 0.1370849609375 }, { "start": 1977.2, "end": 1977.44, "word": ".dir", "probability": 0.568359375 }, { "start": 1977.44, "end": 1977.52, "word": ",", "probability": 0.484375 }, { "start": 1977.52, "end": 1977.7, "word": " this", "probability": 0.87109375 }, { "start": 1977.7, "end": 1977.86, "word": " was", "probability": 0.8818359375 }, { "start": 1977.86, "end": 1978.28, "word": " defined", "probability": 0.75634765625 }, { "start": 1978.28, "end": 1978.98, "word": " above", "probability": 0.8828125 }, { "start": 1978.98, "end": 1979.88, "word": ",", "probability": 0.7978515625 }, { "start": 1979.88, "end": 1981.06, "word": " slash", "probability": 0.360107421875 }, { "start": 1981.06, "end": 1981.54, "word": " ham", "probability": 0.5673828125 }, { "start": 1981.54, "end": 1982.28, "word": ".", "probability": 0.69921875 } ] }, { "id": 599, "seek": 194826, "start": 1983.86, "end": 1989.66, "text": " And then we're going to say with each open file,", "tokens": [ 50714, 400, 550, 321, 434, 516, 281, 584, 365, 1184, 1269, 3991, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.26994242675994573, "compression_ratio": 1.4870129870129871, "no_speech_prob": 0.027587890625, "words": [ { "start": 1983.86, "end": 1984.6, "word": " And", "probability": 0.59033203125 }, { "start": 1984.6, "end": 1984.68, "word": " then", "probability": 0.640625 }, { "start": 1984.68, "end": 1984.78, "word": " we're", "probability": 0.916748046875 }, { "start": 1984.78, "end": 1984.98, "word": " going", "probability": 0.85546875 }, { "start": 1984.98, "end": 1985.16, "word": " to", "probability": 0.90478515625 }, { "start": 1985.16, "end": 1985.58, "word": " say", "probability": 0.89892578125 }, { "start": 1985.58, "end": 1987.54, "word": " with", "probability": 0.411865234375 }, { "start": 1987.54, "end": 1987.84, "word": " each", "probability": 0.75244140625 }, { "start": 1987.84, "end": 1988.16, "word": " open", "probability": 0.79150390625 }, { "start": 1988.16, "end": 1988.72, "word": " file", "probability": 0.77001953125 }, { "start": 1988.72, "end": 1989.66, "word": ",", "probability": 0.6474609375 } ] }, { "id": 600, "seek": 194826, "start": 1995.29, "end": 1998.9, "text": " ham slash plus each,", "tokens": [ 51014, 7852, 17330, 1804, 1184, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.26994242675994573, "compression_ratio": 1.4870129870129871, "no_speech_prob": 0.027587890625, "words": [ { "start": 1995.29, "end": 1996.03, "word": " ham", "probability": 0.8818359375 }, { "start": 1996.03, "end": 1996.77, "word": " slash", "probability": 0.65771484375 }, { "start": 1996.77, "end": 1997.89, "word": " plus", "probability": 0.6923828125 }, { "start": 1997.89, "end": 1998.53, "word": " each", "probability": 0.82958984375 }, { "start": 1998.53, "end": 1998.9, "word": ",", "probability": 0.70361328125 } ] }, { "id": 601, "seek": 194826, "start": 1999.31, "end": 2000.97, "text": " because that's what we defined in our for loop.", "tokens": [ 51264, 570, 300, 311, 437, 321, 7642, 294, 527, 337, 6367, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.26994242675994573, "compression_ratio": 1.4870129870129871, "no_speech_prob": 0.027587890625, "words": [ { "start": 1999.31, "end": 1999.45, "word": " because", "probability": 0.268798828125 }, { "start": 1999.45, "end": 1999.59, "word": " that's", "probability": 0.9384765625 }, { "start": 1999.59, "end": 1999.67, "word": " what", "probability": 0.880859375 }, { "start": 1999.67, "end": 1999.79, "word": " we", "probability": 0.90625 }, { "start": 1999.79, "end": 2000.05, "word": " defined", "probability": 0.61572265625 }, { "start": 2000.05, "end": 2000.17, "word": " in", "probability": 0.876953125 }, { "start": 2000.17, "end": 2000.25, "word": " our", "probability": 0.814453125 }, { "start": 2000.25, "end": 2000.43, "word": " for", "probability": 0.8447265625 }, { "start": 2000.43, "end": 2000.69, "word": " loop", "probability": 0.86767578125 }, { "start": 2000.69, "end": 2000.97, "word": ".", "probability": 0.52783203125 } ] }, { "id": 602, "seek": 194826, "start": 2000.97, "end": 2006.59, "text": " We're going to read them as a file named f,", "tokens": [ 51414, 492, 434, 516, 281, 1401, 552, 382, 257, 3991, 4926, 283, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.26994242675994573, "compression_ratio": 1.4870129870129871, "no_speech_prob": 0.027587890625, "words": [ { "start": 2000.97, "end": 2001.45, "word": " We're", "probability": 0.927001953125 }, { "start": 2001.45, "end": 2001.61, "word": " going", "probability": 0.86083984375 }, { "start": 2001.61, "end": 2001.93, "word": " to", "probability": 0.90869140625 }, { "start": 2001.93, "end": 2002.43, "word": " read", "probability": 0.91259765625 }, { "start": 2002.43, "end": 2002.75, "word": " them", "probability": 0.75048828125 }, { "start": 2002.75, "end": 2003.63, "word": " as", "probability": 0.908203125 }, { "start": 2004.57, "end": 2004.79, "word": " a file", "probability": 0.78759765625 }, { "start": 2004.79, "end": 2005.11, "word": " named", "probability": 0.806640625 }, { "start": 2005.61, "end": 2006.59, "word": " f,", "probability": 0.464111328125 } ] }, { "id": 603, "seek": 194826, "start": 2006.59, "end": 2010.55, "text": " corpus.append, f.read,", "tokens": [ 51614, 1181, 31624, 13, 1746, 521, 11, 283, 13, 2538, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.26994242675994573, "compression_ratio": 1.4870129870129871, "no_speech_prob": 0.027587890625, "words": [ { "start": 2006.59, "end": 2007.23, "word": " corpus", "probability": 0.90478515625 }, { "start": 2007.23, "end": 2008.35, "word": ".append", "probability": 0.8639322916666666 }, { "start": 2008.35, "end": 2008.59, "word": ",", "probability": 0.7822265625 }, { "start": 2008.87, "end": 2009.69, "word": " f.read", "probability": 0.92822265625 }, { "start": 2009.69, "end": 2010.55, "word": ",", "probability": 0.681640625 } ] }, { "id": 604, "seek": 197376, "start": 2010.55, "end": 2016.85, "text": " and then labels.append the word ham.", "tokens": [ 50364, 293, 550, 16949, 13, 1746, 521, 264, 1349, 7852, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.18636067397892475, "compression_ratio": 1.8864864864864865, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 2010.55, "end": 2010.99, "word": " and", "probability": 0.263916015625 }, { "start": 2010.99, "end": 2011.33, "word": " then", "probability": 0.6474609375 }, { "start": 2011.33, "end": 2012.31, "word": " labels", "probability": 0.56494140625 }, { "start": 2012.31, "end": 2013.63, "word": ".append", "probability": 0.9016927083333334 }, { "start": 2013.63, "end": 2015.41, "word": " the", "probability": 0.58154296875 }, { "start": 2015.41, "end": 2015.81, "word": " word", "probability": 0.78125 }, { "start": 2015.81, "end": 2016.33, "word": " ham", "probability": 0.5771484375 }, { "start": 2016.33, "end": 2016.85, "word": ".", "probability": 0.732421875 } ] }, { "id": 605, "seek": 197376, "start": 2017.45, "end": 2019.57, "text": " And the reason why is because this third task", "tokens": [ 50714, 400, 264, 1778, 983, 307, 570, 341, 2636, 5633, 50814 ], "temperature": 0.0, "avg_logprob": -0.18636067397892475, "compression_ratio": 1.8864864864864865, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 2017.45, "end": 2017.97, "word": " And", "probability": 0.63916015625 }, { "start": 2017.97, "end": 2018.05, "word": " the", "probability": 0.81396484375 }, { "start": 2018.05, "end": 2018.19, "word": " reason", "probability": 0.92236328125 }, { "start": 2018.19, "end": 2018.43, "word": " why", "probability": 0.79931640625 }, { "start": 2018.43, "end": 2018.55, "word": " is", "probability": 0.86669921875 }, { "start": 2018.55, "end": 2018.75, "word": " because", "probability": 0.79052734375 }, { "start": 2018.75, "end": 2018.97, "word": " this", "probability": 0.80126953125 }, { "start": 2018.97, "end": 2019.21, "word": " third", "probability": 0.8291015625 }, { "start": 2019.21, "end": 2019.57, "word": " task", "probability": 0.80029296875 } ] }, { "id": 606, "seek": 197376, "start": 2019.57, "end": 2022.95, "text": " is load the labels for each email into the labels array.", "tokens": [ 50814, 307, 3677, 264, 16949, 337, 1184, 3796, 666, 264, 16949, 10225, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.18636067397892475, "compression_ratio": 1.8864864864864865, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 2019.57, "end": 2019.73, "word": " is", "probability": 0.86572265625 }, { "start": 2019.73, "end": 2019.87, "word": " load", "probability": 0.48193359375 }, { "start": 2019.87, "end": 2020.03, "word": " the", "probability": 0.81005859375 }, { "start": 2020.03, "end": 2020.37, "word": " labels", "probability": 0.8642578125 }, { "start": 2020.37, "end": 2020.53, "word": " for", "probability": 0.875 }, { "start": 2020.53, "end": 2020.79, "word": " each", "probability": 0.84375 }, { "start": 2020.79, "end": 2021.21, "word": " email", "probability": 0.8857421875 }, { "start": 2021.21, "end": 2021.89, "word": " into", "probability": 0.724609375 }, { "start": 2021.89, "end": 2022.05, "word": " the", "probability": 0.6298828125 }, { "start": 2022.05, "end": 2022.23, "word": " labels", "probability": 0.83447265625 }, { "start": 2022.23, "end": 2022.51, "word": " array", "probability": 0.744140625 }, { "start": 2022.51, "end": 2022.95, "word": ".", "probability": 0.97607421875 } ] }, { "id": 607, "seek": 197376, "start": 2022.95, "end": 2024.91, "text": " So in this first code block, we're going to read", "tokens": [ 50964, 407, 294, 341, 700, 3089, 3461, 11, 321, 434, 516, 281, 1401, 51064 ], "temperature": 0.0, "avg_logprob": -0.18636067397892475, "compression_ratio": 1.8864864864864865, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 2022.95, "end": 2023.21, "word": " So", "probability": 0.86767578125 }, { "start": 2023.21, "end": 2023.29, "word": " in", "probability": 0.7392578125 }, { "start": 2023.29, "end": 2023.39, "word": " this", "probability": 0.87060546875 }, { "start": 2023.39, "end": 2023.61, "word": " first", "probability": 0.81689453125 }, { "start": 2023.61, "end": 2023.87, "word": " code", "probability": 0.8310546875 }, { "start": 2023.87, "end": 2024.15, "word": " block", "probability": 0.75927734375 }, { "start": 2024.15, "end": 2024.27, "word": ",", "probability": 0.541015625 }, { "start": 2024.27, "end": 2024.35, "word": " we're", "probability": 0.916259765625 }, { "start": 2024.35, "end": 2024.55, "word": " going", "probability": 0.85498046875 }, { "start": 2024.55, "end": 2024.73, "word": " to", "probability": 0.90576171875 }, { "start": 2024.73, "end": 2024.91, "word": " read", "probability": 0.9072265625 } ] }, { "id": 608, "seek": 197376, "start": 2024.91, "end": 2027.71, "text": " every single ham email in the ham directory.", "tokens": [ 51064, 633, 2167, 7852, 3796, 294, 264, 7852, 21120, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.18636067397892475, "compression_ratio": 1.8864864864864865, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 2024.91, "end": 2025.19, "word": " every", "probability": 0.73486328125 }, { "start": 2025.19, "end": 2025.53, "word": " single", "probability": 0.82470703125 }, { "start": 2025.53, "end": 2025.89, "word": " ham", "probability": 0.86865234375 }, { "start": 2025.89, "end": 2026.29, "word": " email", "probability": 0.89404296875 }, { "start": 2026.29, "end": 2026.55, "word": " in", "probability": 0.890625 }, { "start": 2026.55, "end": 2026.69, "word": " the", "probability": 0.8125 }, { "start": 2026.69, "end": 2026.89, "word": " ham", "probability": 0.89404296875 }, { "start": 2026.89, "end": 2027.35, "word": " directory", "probability": 0.8232421875 }, { "start": 2027.35, "end": 2027.71, "word": ".", "probability": 0.65087890625 } ] }, { "id": 609, "seek": 197376, "start": 2027.71, "end": 2030.77, "text": " We're going to add the bodies to the corpus array,", "tokens": [ 51214, 492, 434, 516, 281, 909, 264, 7510, 281, 264, 1181, 31624, 10225, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.18636067397892475, "compression_ratio": 1.8864864864864865, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 2027.71, "end": 2028.07, "word": " We're", "probability": 0.9267578125 }, { "start": 2028.07, "end": 2028.25, "word": " going", "probability": 0.8515625 }, { "start": 2028.25, "end": 2028.51, "word": " to", "probability": 0.90576171875 }, { "start": 2028.51, "end": 2028.73, "word": " add", "probability": 0.83544921875 }, { "start": 2028.73, "end": 2028.89, "word": " the", "probability": 0.81005859375 }, { "start": 2028.89, "end": 2029.21, "word": " bodies", "probability": 0.7431640625 }, { "start": 2029.21, "end": 2029.51, "word": " to", "probability": 0.9052734375 }, { "start": 2029.51, "end": 2029.69, "word": " the", "probability": 0.8125 }, { "start": 2029.69, "end": 2030.09, "word": " corpus", "probability": 0.89404296875 }, { "start": 2030.09, "end": 2030.53, "word": " array", "probability": 0.7587890625 }, { "start": 2030.53, "end": 2030.77, "word": ",", "probability": 0.472900390625 } ] }, { "id": 610, "seek": 197376, "start": 2030.77, "end": 2036.05, "text": " and then we're going to add the label ham into the labels array.", "tokens": [ 51364, 293, 550, 321, 434, 516, 281, 909, 264, 7645, 7852, 666, 264, 16949, 10225, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.18636067397892475, "compression_ratio": 1.8864864864864865, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 2030.77, "end": 2030.93, "word": " and", "probability": 0.8828125 }, { "start": 2030.93, "end": 2031.01, "word": " then", "probability": 0.625 }, { "start": 2031.01, "end": 2031.11, "word": " we're", "probability": 0.927490234375 }, { "start": 2031.11, "end": 2031.27, "word": " going", "probability": 0.85595703125 }, { "start": 2031.27, "end": 2031.45, "word": " to", "probability": 0.90576171875 }, { "start": 2031.45, "end": 2031.61, "word": " add", "probability": 0.82666015625 }, { "start": 2031.61, "end": 2031.81, "word": " the", "probability": 0.814453125 }, { "start": 2031.81, "end": 2032.33, "word": " label", "probability": 0.77978515625 }, { "start": 2032.33, "end": 2033.15, "word": " ham", "probability": 0.79296875 }, { "start": 2033.15, "end": 2033.91, "word": " into", "probability": 0.74560546875 }, { "start": 2033.91, "end": 2034.67, "word": " the", "probability": 0.82080078125 }, { "start": 2034.67, "end": 2035.05, "word": " labels", "probability": 0.83642578125 }, { "start": 2035.05, "end": 2035.53, "word": " array", "probability": 0.76416015625 }, { "start": 2035.53, "end": 2036.05, "word": ".", "probability": 0.96533203125 } ] }, { "id": 611, "seek": 200076, "start": 2036.05, "end": 2040.79, "text": " Then we can go ahead and do the exact same thing for spam.", "tokens": [ 50364, 1396, 321, 393, 352, 2286, 293, 360, 264, 1900, 912, 551, 337, 24028, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.19802631798543427, "compression_ratio": 1.6130653266331658, "no_speech_prob": 0.0164031982421875, "words": [ { "start": 2036.05, "end": 2036.79, "word": " Then", "probability": 0.04388427734375 }, { "start": 2036.79, "end": 2036.87, "word": " we", "probability": 0.59716796875 }, { "start": 2036.87, "end": 2037.01, "word": " can", "probability": 0.84130859375 }, { "start": 2037.01, "end": 2037.15, "word": " go", "probability": 0.7666015625 }, { "start": 2037.15, "end": 2037.59, "word": " ahead", "probability": 0.849609375 }, { "start": 2037.59, "end": 2038.29, "word": " and", "probability": 0.87109375 }, { "start": 2038.29, "end": 2038.61, "word": " do", "probability": 0.89892578125 }, { "start": 2038.61, "end": 2038.87, "word": " the", "probability": 0.8154296875 }, { "start": 2038.87, "end": 2039.47, "word": " exact", "probability": 0.857421875 }, { "start": 2039.47, "end": 2039.79, "word": " same", "probability": 0.822265625 }, { "start": 2039.79, "end": 2040.01, "word": " thing", "probability": 0.80224609375 }, { "start": 2040.01, "end": 2040.21, "word": " for", "probability": 0.8916015625 }, { "start": 2040.21, "end": 2040.57, "word": " spam", "probability": 0.755859375 }, { "start": 2040.57, "end": 2040.79, "word": ".", "probability": 0.5341796875 } ] }, { "id": 612, "seek": 200076, "start": 2040.79, "end": 2045.73, "text": " We're just going to have to change each thing to spam,", "tokens": [ 50564, 492, 434, 445, 516, 281, 362, 281, 1319, 1184, 551, 281, 24028, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.19802631798543427, "compression_ratio": 1.6130653266331658, "no_speech_prob": 0.0164031982421875, "words": [ { "start": 2040.79, "end": 2040.89, "word": " We're", "probability": 0.86669921875 }, { "start": 2040.89, "end": 2041.01, "word": " just", "probability": 0.87548828125 }, { "start": 2041.01, "end": 2041.19, "word": " going", "probability": 0.85693359375 }, { "start": 2041.19, "end": 2041.37, "word": " to", "probability": 0.90478515625 }, { "start": 2041.37, "end": 2041.53, "word": " have", "probability": 0.86669921875 }, { "start": 2041.53, "end": 2041.95, "word": " to", "probability": 0.90234375 }, { "start": 2041.95, "end": 2042.81, "word": " change", "probability": 0.79345703125 }, { "start": 2042.81, "end": 2044.21, "word": " each", "probability": 0.77001953125 }, { "start": 2044.21, "end": 2044.51, "word": " thing", "probability": 0.7890625 }, { "start": 2044.51, "end": 2044.93, "word": " to", "probability": 0.8857421875 }, { "start": 2044.93, "end": 2045.51, "word": " spam", "probability": 0.57373046875 }, { "start": 2045.51, "end": 2045.73, "word": ",", "probability": 0.72900390625 } ] }, { "id": 613, "seek": 200076, "start": 2045.73, "end": 2049.21, "text": " spam, and the labels to spam.", "tokens": [ 50814, 24028, 11, 293, 264, 16949, 281, 24028, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.19802631798543427, "compression_ratio": 1.6130653266331658, "no_speech_prob": 0.0164031982421875, "words": [ { "start": 2045.73, "end": 2046.33, "word": " spam", "probability": 0.80322265625 }, { "start": 2046.33, "end": 2046.57, "word": ",", "probability": 0.7490234375 }, { "start": 2046.57, "end": 2047.09, "word": " and", "probability": 0.88623046875 }, { "start": 2047.09, "end": 2047.51, "word": " the", "probability": 0.80224609375 }, { "start": 2047.51, "end": 2047.89, "word": " labels", "probability": 0.84765625 }, { "start": 2047.89, "end": 2048.29, "word": " to", "probability": 0.90234375 }, { "start": 2048.29, "end": 2048.71, "word": " spam", "probability": 0.90185546875 }, { "start": 2048.71, "end": 2049.21, "word": ".", "probability": 0.64111328125 } ] }, { "id": 614, "seek": 200076, "start": 2049.63, "end": 2052.39, "text": " And this will go through and read all of the emails.", "tokens": [ 51014, 400, 341, 486, 352, 807, 293, 1401, 439, 295, 264, 12524, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.19802631798543427, "compression_ratio": 1.6130653266331658, "no_speech_prob": 0.0164031982421875, "words": [ { "start": 2049.63, "end": 2049.85, "word": " And", "probability": 0.68505859375 }, { "start": 2049.85, "end": 2049.99, "word": " this", "probability": 0.8740234375 }, { "start": 2049.99, "end": 2050.09, "word": " will", "probability": 0.81884765625 }, { "start": 2050.09, "end": 2050.21, "word": " go", "probability": 0.89892578125 }, { "start": 2050.21, "end": 2050.51, "word": " through", "probability": 0.8046875 }, { "start": 2050.51, "end": 2051.01, "word": " and", "probability": 0.88916015625 }, { "start": 2051.01, "end": 2051.19, "word": " read", "probability": 0.91015625 }, { "start": 2051.19, "end": 2051.41, "word": " all", "probability": 0.90625 }, { "start": 2051.41, "end": 2051.53, "word": " of", "probability": 0.85791015625 }, { "start": 2051.53, "end": 2051.65, "word": " the", "probability": 0.81494140625 }, { "start": 2051.65, "end": 2051.89, "word": " emails", "probability": 0.78125 }, { "start": 2051.89, "end": 2052.39, "word": ".", "probability": 0.939453125 } ] }, { "id": 615, "seek": 200076, "start": 2052.49, "end": 2055.09, "text": " So I'm going to leave this up for a moment,", "tokens": [ 51164, 407, 286, 478, 516, 281, 1856, 341, 493, 337, 257, 1623, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.19802631798543427, "compression_ratio": 1.6130653266331658, "no_speech_prob": 0.0164031982421875, "words": [ { "start": 2052.49, "end": 2052.67, "word": " So", "probability": 0.8037109375 }, { "start": 2052.67, "end": 2052.87, "word": " I'm", "probability": 0.889404296875 }, { "start": 2052.87, "end": 2052.95, "word": " going", "probability": 0.5712890625 }, { "start": 2052.95, "end": 2053.01, "word": " to", "probability": 0.89599609375 }, { "start": 2053.01, "end": 2053.65, "word": " leave", "probability": 0.84521484375 }, { "start": 2053.65, "end": 2053.89, "word": " this", "probability": 0.87548828125 }, { "start": 2053.89, "end": 2054.19, "word": " up", "probability": 0.90234375 }, { "start": 2054.19, "end": 2054.49, "word": " for", "probability": 0.89453125 }, { "start": 2054.67, "end": 2054.89, "word": " a moment", "probability": 0.9150390625 }, { "start": 2054.89, "end": 2055.09, "word": ",", "probability": 0.421142578125 } ] }, { "id": 616, "seek": 200076, "start": 2055.09, "end": 2057.29, "text": " let you guys copy that down.", "tokens": [ 51314, 718, 291, 1074, 5055, 300, 760, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.19802631798543427, "compression_ratio": 1.6130653266331658, "no_speech_prob": 0.0164031982421875, "words": [ { "start": 2055.09, "end": 2055.19, "word": " let", "probability": 0.69775390625 }, { "start": 2055.19, "end": 2055.31, "word": " you", "probability": 0.89794921875 }, { "start": 2055.31, "end": 2055.61, "word": " guys", "probability": 0.87744140625 }, { "start": 2055.61, "end": 2056.19, "word": " copy", "probability": 0.79443359375 }, { "start": 2056.19, "end": 2056.45, "word": " that", "probability": 0.87890625 }, { "start": 2056.45, "end": 2056.79, "word": " down", "probability": 0.81982421875 }, { "start": 2056.79, "end": 2057.29, "word": ".", "probability": 0.82177734375 } ] }, { "id": 617, "seek": 200076, "start": 2068.44, "end": 2072.0, "text": " And then I'm going to press shift enter and run it.", "tokens": [ 51514, 400, 550, 286, 478, 516, 281, 1886, 5513, 3242, 293, 1190, 309, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.19802631798543427, "compression_ratio": 1.6130653266331658, "no_speech_prob": 0.0164031982421875, "words": [ { "start": 2068.44, "end": 2068.94, "word": " And", "probability": 0.833984375 }, { "start": 2068.94, "end": 2069.08, "word": " then", "probability": 0.72900390625 }, { "start": 2069.08, "end": 2069.24, "word": " I'm", "probability": 0.99072265625 }, { "start": 2069.24, "end": 2069.26, "word": " going", "probability": 0.81689453125 }, { "start": 2069.26, "end": 2069.34, "word": " to", "probability": 0.90625 }, { "start": 2069.34, "end": 2069.54, "word": " press", "probability": 0.7060546875 }, { "start": 2069.54, "end": 2069.92, "word": " shift", "probability": 0.357177734375 }, { "start": 2069.92, "end": 2070.36, "word": " enter", "probability": 0.28955078125 }, { "start": 2070.36, "end": 2070.86, "word": " and", "probability": 0.8310546875 }, { "start": 2070.86, "end": 2071.32, "word": " run", "probability": 0.89794921875 }, { "start": 2071.32, "end": 2071.52, "word": " it", "probability": 0.9013671875 }, { "start": 2071.52, "end": 2072.0, "word": ".", "probability": 0.98974609375 } ] }, { "id": 618, "seek": 202856, "start": 2072.0, "end": 2075.34, "text": " So this was really quick, just read all the ham emails,", "tokens": [ 50364, 407, 341, 390, 534, 1702, 11, 445, 1401, 439, 264, 7852, 12524, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.18497024263654435, "compression_ratio": 1.6475770925110131, "no_speech_prob": 0.0008559226989746094, "words": [ { "start": 2072.0, "end": 2072.24, "word": " So", "probability": 0.58837890625 }, { "start": 2072.24, "end": 2073.02, "word": " this", "probability": 0.580078125 }, { "start": 2073.02, "end": 2073.16, "word": " was", "probability": 0.85400390625 }, { "start": 2073.16, "end": 2073.34, "word": " really", "probability": 0.78662109375 }, { "start": 2073.34, "end": 2073.6, "word": " quick", "probability": 0.92578125 }, { "start": 2073.6, "end": 2073.74, "word": ",", "probability": 0.479248046875 }, { "start": 2073.74, "end": 2073.92, "word": " just", "probability": 0.81201171875 }, { "start": 2073.92, "end": 2074.26, "word": " read", "probability": 0.90576171875 }, { "start": 2074.26, "end": 2074.48, "word": " all", "probability": 0.89453125 }, { "start": 2074.48, "end": 2074.64, "word": " the", "probability": 0.798828125 }, { "start": 2074.64, "end": 2074.82, "word": " ham", "probability": 0.6123046875 }, { "start": 2074.82, "end": 2075.16, "word": " emails", "probability": 0.7041015625 }, { "start": 2075.16, "end": 2075.34, "word": ",", "probability": 0.8681640625 } ] }, { "id": 619, "seek": 202856, "start": 2075.34, "end": 2079.08, "text": " all the spam emails, and now it's loaded into our arrays.", "tokens": [ 50514, 439, 264, 24028, 12524, 11, 293, 586, 309, 311, 13210, 666, 527, 41011, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.18497024263654435, "compression_ratio": 1.6475770925110131, "no_speech_prob": 0.0008559226989746094, "words": [ { "start": 2075.34, "end": 2075.42, "word": " all", "probability": 0.89697265625 }, { "start": 2075.42, "end": 2075.56, "word": " the", "probability": 0.80322265625 }, { "start": 2075.56, "end": 2075.78, "word": " spam", "probability": 0.939453125 }, { "start": 2075.78, "end": 2076.24, "word": " emails", "probability": 0.7880859375 }, { "start": 2076.24, "end": 2076.46, "word": ",", "probability": 0.63134765625 }, { "start": 2076.46, "end": 2076.52, "word": " and", "probability": 0.8876953125 }, { "start": 2076.52, "end": 2076.72, "word": " now", "probability": 0.8857421875 }, { "start": 2076.72, "end": 2077.0, "word": " it's", "probability": 0.93798828125 }, { "start": 2077.0, "end": 2077.22, "word": " loaded", "probability": 0.796875 }, { "start": 2077.22, "end": 2077.58, "word": " into", "probability": 0.73876953125 }, { "start": 2077.58, "end": 2077.94, "word": " our", "probability": 0.80908203125 }, { "start": 2077.94, "end": 2078.58, "word": " arrays", "probability": 0.6318359375 }, { "start": 2078.58, "end": 2079.08, "word": ".", "probability": 0.9833984375 } ] }, { "id": 620, "seek": 202856, "start": 2079.82, "end": 2084.3, "text": " If we want to get an idea of what our class count looks like,", "tokens": [ 50764, 759, 321, 528, 281, 483, 364, 1558, 295, 437, 527, 1508, 1207, 1542, 411, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.18497024263654435, "compression_ratio": 1.6475770925110131, "no_speech_prob": 0.0008559226989746094, "words": [ { "start": 2079.82, "end": 2080.1, "word": " If", "probability": 0.89111328125 }, { "start": 2080.1, "end": 2080.2, "word": " we", "probability": 0.90087890625 }, { "start": 2080.2, "end": 2080.32, "word": " want", "probability": 0.7236328125 }, { "start": 2080.32, "end": 2080.4, "word": " to", "probability": 0.90576171875 }, { "start": 2080.4, "end": 2080.5, "word": " get", "probability": 0.90087890625 }, { "start": 2080.5, "end": 2080.62, "word": " an", "probability": 0.900390625 }, { "start": 2080.62, "end": 2080.96, "word": " idea", "probability": 0.77587890625 }, { "start": 2080.96, "end": 2081.68, "word": " of", "probability": 0.90087890625 }, { "start": 2081.68, "end": 2082.28, "word": " what", "probability": 0.89013671875 }, { "start": 2082.28, "end": 2082.56, "word": " our", "probability": 0.81396484375 }, { "start": 2082.56, "end": 2082.88, "word": " class", "probability": 0.927734375 }, { "start": 2082.88, "end": 2083.08, "word": " count", "probability": 0.79052734375 }, { "start": 2083.08, "end": 2083.28, "word": " looks", "probability": 0.80322265625 }, { "start": 2083.28, "end": 2083.6, "word": " like", "probability": 0.8798828125 }, { "start": 2083.6, "end": 2084.3, "word": ",", "probability": 0.82958984375 } ] }, { "id": 621, "seek": 202856, "start": 2084.3, "end": 2088.86, "text": " we have a total of 2,359 ham emails,", "tokens": [ 50964, 321, 362, 257, 3217, 295, 568, 11, 8794, 24, 7852, 12524, 11, 51164 ], "temperature": 0.0, "avg_logprob": -0.18497024263654435, "compression_ratio": 1.6475770925110131, "no_speech_prob": 0.0008559226989746094, "words": [ { "start": 2084.3, "end": 2084.72, "word": " we", "probability": 0.875 }, { "start": 2084.72, "end": 2084.84, "word": " have", "probability": 0.873046875 }, { "start": 2084.96, "end": 2085.16, "word": " a total", "probability": 0.80712890625 }, { "start": 2085.16, "end": 2085.88, "word": " of", "probability": 0.89697265625 }, { "start": 2085.88, "end": 2086.38, "word": " 2", "probability": 0.5673828125 }, { "start": 2086.38, "end": 2087.46, "word": ",359", "probability": 0.9269205729166666 }, { "start": 2087.46, "end": 2087.78, "word": " ham", "probability": 0.8193359375 }, { "start": 2087.78, "end": 2088.24, "word": " emails", "probability": 0.73828125 }, { "start": 2088.24, "end": 2088.86, "word": ",", "probability": 0.962890625 } ] }, { "id": 622, "seek": 202856, "start": 2088.86, "end": 2093.88, "text": " 1,100 spam emails, and then just as a graph we can see here.", "tokens": [ 51164, 502, 11, 6879, 24028, 12524, 11, 293, 550, 445, 382, 257, 4295, 321, 393, 536, 510, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.18497024263654435, "compression_ratio": 1.6475770925110131, "no_speech_prob": 0.0008559226989746094, "words": [ { "start": 2088.86, "end": 2089.02, "word": " 1", "probability": 0.859375 }, { "start": 2089.02, "end": 2089.46, "word": ",100", "probability": 0.9619140625 }, { "start": 2089.46, "end": 2090.4, "word": " spam", "probability": 0.89453125 }, { "start": 2090.4, "end": 2090.92, "word": " emails", "probability": 0.7490234375 }, { "start": 2090.92, "end": 2091.14, "word": ",", "probability": 0.783203125 }, { "start": 2091.14, "end": 2091.34, "word": " and", "probability": 0.89013671875 }, { "start": 2091.34, "end": 2091.5, "word": " then", "probability": 0.69482421875 }, { "start": 2091.5, "end": 2091.68, "word": " just", "probability": 0.83447265625 }, { "start": 2091.68, "end": 2091.9, "word": " as", "probability": 0.90283203125 }, { "start": 2092.0, "end": 2092.42, "word": " a graph", "probability": 0.74853515625 }, { "start": 2092.42, "end": 2092.7, "word": " we", "probability": 0.4150390625 }, { "start": 2092.7, "end": 2092.84, "word": " can", "probability": 0.8974609375 }, { "start": 2092.84, "end": 2093.04, "word": " see", "probability": 0.80908203125 }, { "start": 2093.04, "end": 2093.38, "word": " here", "probability": 0.8154296875 }, { "start": 2093.38, "end": 2093.88, "word": ".", "probability": 0.8681640625 } ] }, { "id": 623, "seek": 202856, "start": 2094.34, "end": 2097.32, "text": " And I think it's important to graph these counts", "tokens": [ 51464, 400, 286, 519, 309, 311, 1021, 281, 4295, 613, 14893, 51614 ], "temperature": 0.0, "avg_logprob": -0.18497024263654435, "compression_ratio": 1.6475770925110131, "no_speech_prob": 0.0008559226989746094, "words": [ { "start": 2094.34, "end": 2094.58, "word": " And", "probability": 0.64990234375 }, { "start": 2094.58, "end": 2094.78, "word": " I", "probability": 0.98583984375 }, { "start": 2094.78, "end": 2094.94, "word": " think", "probability": 0.81103515625 }, { "start": 2094.94, "end": 2095.1, "word": " it's", "probability": 0.948974609375 }, { "start": 2095.1, "end": 2095.42, "word": " important", "probability": 0.7646484375 }, { "start": 2095.42, "end": 2096.0, "word": " to", "probability": 0.904296875 }, { "start": 2096.0, "end": 2096.68, "word": " graph", "probability": 0.7802734375 }, { "start": 2096.68, "end": 2096.96, "word": " these", "probability": 0.70654296875 }, { "start": 2096.96, "end": 2097.32, "word": " counts", "probability": 0.76025390625 } ] }, { "id": 624, "seek": 202856, "start": 2097.32, "end": 2099.8, "text": " because sometimes you will have what are considered", "tokens": [ 51614, 570, 2171, 291, 486, 362, 437, 366, 4888, 51764 ], "temperature": 0.0, "avg_logprob": -0.18497024263654435, "compression_ratio": 1.6475770925110131, "no_speech_prob": 0.0008559226989746094, "words": [ { "start": 2097.32, "end": 2097.78, "word": " because", "probability": 0.58642578125 }, { "start": 2097.78, "end": 2098.18, "word": " sometimes", "probability": 0.90283203125 }, { "start": 2098.18, "end": 2098.58, "word": " you", "probability": 0.89013671875 }, { "start": 2098.58, "end": 2098.72, "word": " will", "probability": 0.767578125 }, { "start": 2098.72, "end": 2099.12, "word": " have", "probability": 0.8798828125 }, { "start": 2099.12, "end": 2099.32, "word": " what", "probability": 0.86865234375 }, { "start": 2099.32, "end": 2099.42, "word": " are", "probability": 0.89111328125 }, { "start": 2099.42, "end": 2099.8, "word": " considered", "probability": 0.609375 } ] }, { "id": 625, "seek": 205668, "start": 2099.8, "end": 2103.16, "text": " unbalanced data sets, and so you need to", "tokens": [ 50364, 517, 40251, 1412, 6352, 11, 293, 370, 291, 643, 281, 50514 ], "temperature": 0.0, "avg_logprob": -0.1908185798509986, "compression_ratio": 1.7413127413127414, "no_speech_prob": 0.05499267578125, "words": [ { "start": 2099.8, "end": 2100.52, "word": " unbalanced", "probability": 0.69921875 }, { "start": 2100.52, "end": 2100.92, "word": " data", "probability": 0.5166015625 }, { "start": 2100.92, "end": 2101.38, "word": " sets", "probability": 0.810546875 }, { "start": 2101.38, "end": 2101.82, "word": ",", "probability": 0.232177734375 }, { "start": 2101.82, "end": 2102.0, "word": " and", "probability": 0.8095703125 }, { "start": 2102.0, "end": 2102.22, "word": " so", "probability": 0.90283203125 }, { "start": 2102.22, "end": 2102.5, "word": " you", "probability": 0.88134765625 }, { "start": 2102.5, "end": 2102.72, "word": " need", "probability": 0.80712890625 }, { "start": 2102.72, "end": 2103.16, "word": " to", "probability": 0.9091796875 } ] }, { "id": 626, "seek": 205668, "start": 2103.16, "end": 2105.72, "text": " perform other changes here and there", "tokens": [ 50514, 2042, 661, 2962, 510, 293, 456, 50664 ], "temperature": 0.0, "avg_logprob": -0.1908185798509986, "compression_ratio": 1.7413127413127414, "no_speech_prob": 0.05499267578125, "words": [ { "start": 2103.16, "end": 2104.14, "word": " perform", "probability": 0.74658203125 }, { "start": 2104.14, "end": 2104.48, "word": " other", "probability": 0.7939453125 }, { "start": 2104.48, "end": 2104.94, "word": " changes", "probability": 0.78955078125 }, { "start": 2104.94, "end": 2105.24, "word": " here", "probability": 0.8076171875 }, { "start": 2105.24, "end": 2105.42, "word": " and", "probability": 0.89208984375 }, { "start": 2105.42, "end": 2105.72, "word": " there", "probability": 0.85400390625 } ] }, { "id": 627, "seek": 205668, "start": 2105.72, "end": 2108.24, "text": " just to make sure that the data sets are balanced.", "tokens": [ 50664, 445, 281, 652, 988, 300, 264, 1412, 6352, 366, 13902, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.1908185798509986, "compression_ratio": 1.7413127413127414, "no_speech_prob": 0.05499267578125, "words": [ { "start": 2105.72, "end": 2106.28, "word": " just", "probability": 0.7197265625 }, { "start": 2106.28, "end": 2106.42, "word": " to", "probability": 0.90869140625 }, { "start": 2106.42, "end": 2106.56, "word": " make", "probability": 0.88037109375 }, { "start": 2106.56, "end": 2106.76, "word": " sure", "probability": 0.8203125 }, { "start": 2106.76, "end": 2106.94, "word": " that", "probability": 0.85888671875 }, { "start": 2106.94, "end": 2107.06, "word": " the", "probability": 0.8193359375 }, { "start": 2107.06, "end": 2107.26, "word": " data", "probability": 0.75390625 }, { "start": 2107.26, "end": 2107.5, "word": " sets", "probability": 0.78125 }, { "start": 2107.5, "end": 2107.64, "word": " are", "probability": 0.896484375 }, { "start": 2107.64, "end": 2108.1, "word": " balanced", "probability": 0.896484375 }, { "start": 2108.1, "end": 2108.24, "word": ".", "probability": 0.3740234375 } ] }, { "id": 628, "seek": 205668, "start": 2108.42, "end": 2112.4, "text": " Especially for things like credit card fraud,", "tokens": [ 50814, 8545, 337, 721, 411, 5397, 2920, 14560, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.1908185798509986, "compression_ratio": 1.7413127413127414, "no_speech_prob": 0.05499267578125, "words": [ { "start": 2108.42, "end": 2108.98, "word": " Especially", "probability": 0.7822265625 }, { "start": 2108.98, "end": 2109.18, "word": " for", "probability": 0.88916015625 }, { "start": 2109.18, "end": 2109.52, "word": " things", "probability": 0.73681640625 }, { "start": 2109.52, "end": 2110.02, "word": " like", "probability": 0.88134765625 }, { "start": 2110.02, "end": 2111.12, "word": " credit", "probability": 0.8173828125 }, { "start": 2111.12, "end": 2111.4, "word": " card", "probability": 0.81103515625 }, { "start": 2111.4, "end": 2112.2, "word": " fraud", "probability": 0.85791015625 }, { "start": 2112.2, "end": 2112.4, "word": ",", "probability": 0.52734375 } ] }, { "id": 629, "seek": 205668, "start": 2112.4, "end": 2115.82, "text": " where that happens less than a percent of the time.", "tokens": [ 50964, 689, 300, 2314, 1570, 813, 257, 3043, 295, 264, 565, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.1908185798509986, "compression_ratio": 1.7413127413127414, "no_speech_prob": 0.05499267578125, "words": [ { "start": 2112.4, "end": 2112.78, "word": " where", "probability": 0.8955078125 }, { "start": 2112.78, "end": 2113.16, "word": " that", "probability": 0.8798828125 }, { "start": 2113.16, "end": 2113.52, "word": " happens", "probability": 0.9140625 }, { "start": 2113.52, "end": 2113.92, "word": " less", "probability": 0.8828125 }, { "start": 2113.92, "end": 2114.12, "word": " than", "probability": 0.87744140625 }, { "start": 2114.28, "end": 2114.54, "word": " a percent", "probability": 0.86376953125 }, { "start": 2114.54, "end": 2114.78, "word": " of", "probability": 0.900390625 }, { "start": 2114.78, "end": 2114.9, "word": " the", "probability": 0.8154296875 }, { "start": 2114.9, "end": 2115.34, "word": " time", "probability": 0.79931640625 }, { "start": 2115.34, "end": 2115.82, "word": ".", "probability": 0.6162109375 } ] }, { "id": 630, "seek": 205668, "start": 2115.82, "end": 2118.28, "text": " You can build a model that's 99% accurate", "tokens": [ 51114, 509, 393, 1322, 257, 2316, 300, 311, 11803, 4, 8559, 51264 ], "temperature": 0.0, "avg_logprob": -0.1908185798509986, "compression_ratio": 1.7413127413127414, "no_speech_prob": 0.05499267578125, "words": [ { "start": 2115.82, "end": 2116.2, "word": " You", "probability": 0.88818359375 }, { "start": 2116.2, "end": 2116.36, "word": " can", "probability": 0.89697265625 }, { "start": 2116.36, "end": 2116.54, "word": " build", "probability": 0.86962890625 }, { "start": 2116.7, "end": 2116.88, "word": " a model", "probability": 0.7998046875 }, { "start": 2116.88, "end": 2117.14, "word": " that's", "probability": 0.927490234375 }, { "start": 2117.14, "end": 2117.48, "word": " 99", "probability": 0.8251953125 }, { "start": 2117.48, "end": 2117.84, "word": "%", "probability": 0.79296875 }, { "start": 2117.84, "end": 2118.28, "word": " accurate", "probability": 0.70361328125 } ] }, { "id": 631, "seek": 205668, "start": 2118.28, "end": 2121.08, "text": " by just saying everything is a legitimate transaction,", "tokens": [ 51264, 538, 445, 1566, 1203, 307, 257, 17956, 14425, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.1908185798509986, "compression_ratio": 1.7413127413127414, "no_speech_prob": 0.05499267578125, "words": [ { "start": 2118.28, "end": 2118.6, "word": " by", "probability": 0.8125 }, { "start": 2118.6, "end": 2118.8, "word": " just", "probability": 0.87548828125 }, { "start": 2118.8, "end": 2119.04, "word": " saying", "probability": 0.81298828125 }, { "start": 2119.04, "end": 2119.46, "word": " everything", "probability": 0.75244140625 }, { "start": 2119.46, "end": 2119.64, "word": " is", "probability": 0.303466796875 }, { "start": 2119.76, "end": 2120.02, "word": " a legitimate", "probability": 0.75732421875 }, { "start": 2120.02, "end": 2120.7, "word": " transaction", "probability": 0.7822265625 }, { "start": 2120.7, "end": 2121.08, "word": ",", "probability": 0.77685546875 } ] }, { "id": 632, "seek": 205668, "start": 2121.08, "end": 2123.1, "text": " but unfortunately that doesn't really help", "tokens": [ 51414, 457, 7015, 300, 1177, 380, 534, 854, 51514 ], "temperature": 0.0, "avg_logprob": -0.1908185798509986, "compression_ratio": 1.7413127413127414, "no_speech_prob": 0.05499267578125, "words": [ { "start": 2121.08, "end": 2121.38, "word": " but", "probability": 0.9013671875 }, { "start": 2121.38, "end": 2121.86, "word": " unfortunately", "probability": 0.8154296875 }, { "start": 2121.86, "end": 2122.14, "word": " that", "probability": 0.76171875 }, { "start": 2122.14, "end": 2122.42, "word": " doesn't", "probability": 0.934326171875 }, { "start": 2122.42, "end": 2122.66, "word": " really", "probability": 0.77294921875 }, { "start": 2122.66, "end": 2123.1, "word": " help", "probability": 0.8203125 } ] }, { "id": 633, "seek": 205668, "start": 2123.1, "end": 2125.8, "text": " when you're trying to stop credit card fraud.", "tokens": [ 51514, 562, 291, 434, 1382, 281, 1590, 5397, 2920, 14560, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.1908185798509986, "compression_ratio": 1.7413127413127414, "no_speech_prob": 0.05499267578125, "words": [ { "start": 2123.1, "end": 2123.34, "word": " when", "probability": 0.86865234375 }, { "start": 2123.34, "end": 2123.48, "word": " you're", "probability": 0.923583984375 }, { "start": 2123.48, "end": 2123.68, "word": " trying", "probability": 0.7939453125 }, { "start": 2123.68, "end": 2123.9, "word": " to", "probability": 0.90673828125 }, { "start": 2123.9, "end": 2124.32, "word": " stop", "probability": 0.81201171875 }, { "start": 2124.32, "end": 2124.64, "word": " credit", "probability": 0.81298828125 }, { "start": 2124.64, "end": 2124.88, "word": " card", "probability": 0.81396484375 }, { "start": 2124.88, "end": 2125.24, "word": " fraud", "probability": 0.85009765625 }, { "start": 2125.24, "end": 2125.8, "word": ".", "probability": 0.97607421875 } ] }, { "id": 634, "seek": 205668, "start": 2126.08, "end": 2127.92, "text": " So when you have imbalanced data sets,", "tokens": [ 51664, 407, 562, 291, 362, 566, 40251, 1412, 6352, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.1908185798509986, "compression_ratio": 1.7413127413127414, "no_speech_prob": 0.05499267578125, "words": [ { "start": 2126.08, "end": 2126.64, "word": " So", "probability": 0.83984375 }, { "start": 2126.64, "end": 2126.72, "word": " when", "probability": 0.8173828125 }, { "start": 2126.72, "end": 2126.78, "word": " you", "probability": 0.89404296875 }, { "start": 2126.78, "end": 2126.92, "word": " have", "probability": 0.8896484375 }, { "start": 2126.92, "end": 2127.32, "word": " imbalanced", "probability": 0.846923828125 }, { "start": 2127.32, "end": 2127.58, "word": " data", "probability": 0.759765625 }, { "start": 2127.58, "end": 2127.9, "word": " sets", "probability": 0.78662109375 }, { "start": 2127.9, "end": 2127.92, "word": ",", "probability": 0.54443359375 } ] }, { "id": 635, "seek": 208514, "start": 2127.92, "end": 2129.66, "text": " there's additional things that you do.", "tokens": [ 50364, 456, 311, 4497, 721, 300, 291, 360, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.19822761004985268, "compression_ratio": 1.7718631178707225, "no_speech_prob": 0.060089111328125, "words": [ { "start": 2127.92, "end": 2128.14, "word": " there's", "probability": 0.42681884765625 }, { "start": 2128.14, "end": 2128.44, "word": " additional", "probability": 0.85791015625 }, { "start": 2128.44, "end": 2128.76, "word": " things", "probability": 0.71875 }, { "start": 2128.76, "end": 2128.88, "word": " that", "probability": 0.8505859375 }, { "start": 2128.88, "end": 2128.98, "word": " you", "probability": 0.89794921875 }, { "start": 2128.98, "end": 2129.28, "word": " do", "probability": 0.884765625 }, { "start": 2129.28, "end": 2129.66, "word": ".", "probability": 0.8388671875 } ] }, { "id": 636, "seek": 208514, "start": 2129.66, "end": 2131.78, "text": " In this case, it looks a little unbalanced,", "tokens": [ 50464, 682, 341, 1389, 11, 309, 1542, 257, 707, 517, 40251, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.19822761004985268, "compression_ratio": 1.7718631178707225, "no_speech_prob": 0.060089111328125, "words": [ { "start": 2129.66, "end": 2129.82, "word": " In", "probability": 0.8818359375 }, { "start": 2129.82, "end": 2130.0, "word": " this", "probability": 0.8857421875 }, { "start": 2130.0, "end": 2130.32, "word": " case", "probability": 0.8115234375 }, { "start": 2130.32, "end": 2130.4, "word": ",", "probability": 0.56298828125 }, { "start": 2130.4, "end": 2130.54, "word": " it", "probability": 0.896484375 }, { "start": 2130.54, "end": 2130.78, "word": " looks", "probability": 0.79541015625 }, { "start": 2130.9, "end": 2131.02, "word": " a little", "probability": 0.8017578125 }, { "start": 2131.02, "end": 2131.52, "word": " unbalanced", "probability": 0.6474609375 }, { "start": 2131.52, "end": 2131.78, "word": ",", "probability": 0.59326171875 } ] }, { "id": 637, "seek": 208514, "start": 2131.78, "end": 2135.9, "text": " but we'll be able to work with it no problems.", "tokens": [ 50564, 457, 321, 603, 312, 1075, 281, 589, 365, 309, 572, 2740, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.19822761004985268, "compression_ratio": 1.7718631178707225, "no_speech_prob": 0.060089111328125, "words": [ { "start": 2131.78, "end": 2131.94, "word": " but", "probability": 0.89599609375 }, { "start": 2131.94, "end": 2132.8, "word": " we'll", "probability": 0.900634765625 }, { "start": 2132.8, "end": 2132.92, "word": " be", "probability": 0.90869140625 }, { "start": 2132.92, "end": 2133.06, "word": " able", "probability": 0.88671875 }, { "start": 2133.06, "end": 2133.24, "word": " to", "probability": 0.90380859375 }, { "start": 2133.24, "end": 2133.44, "word": " work", "probability": 0.81494140625 }, { "start": 2133.44, "end": 2133.64, "word": " with", "probability": 0.81396484375 }, { "start": 2133.64, "end": 2133.84, "word": " it", "probability": 0.8994140625 }, { "start": 2133.84, "end": 2134.98, "word": " no", "probability": 0.3564453125 }, { "start": 2134.98, "end": 2135.5, "word": " problems", "probability": 0.64208984375 }, { "start": 2135.5, "end": 2135.9, "word": ".", "probability": 0.9755859375 } ] }, { "id": 638, "seek": 208514, "start": 2138.36, "end": 2141.12, "text": " So we are on task 2A.", "tokens": [ 50864, 407, 321, 366, 322, 5633, 568, 32, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.19822761004985268, "compression_ratio": 1.7718631178707225, "no_speech_prob": 0.060089111328125, "words": [ { "start": 2138.36, "end": 2138.76, "word": " So", "probability": 0.69677734375 }, { "start": 2138.76, "end": 2138.9, "word": " we", "probability": 0.79638671875 }, { "start": 2138.9, "end": 2139.04, "word": " are", "probability": 0.82470703125 }, { "start": 2139.04, "end": 2139.48, "word": " on", "probability": 0.916015625 }, { "start": 2139.48, "end": 2139.96, "word": " task", "probability": 0.509765625 }, { "start": 2139.96, "end": 2140.72, "word": " 2A", "probability": 0.71630859375 }, { "start": 2140.72, "end": 2141.12, "word": ".", "probability": 0.72705078125 } ] }, { "id": 639, "seek": 208514, "start": 2141.46, "end": 2143.7, "text": " In this one we want to see the full text body", "tokens": [ 51014, 682, 341, 472, 321, 528, 281, 536, 264, 1577, 2487, 1772, 51164 ], "temperature": 0.0, "avg_logprob": -0.19822761004985268, "compression_ratio": 1.7718631178707225, "no_speech_prob": 0.060089111328125, "words": [ { "start": 2141.46, "end": 2141.86, "word": " In", "probability": 0.88623046875 }, { "start": 2141.86, "end": 2142.02, "word": " this", "probability": 0.8857421875 }, { "start": 2142.02, "end": 2142.18, "word": " one", "probability": 0.81640625 }, { "start": 2142.18, "end": 2142.34, "word": " we", "probability": 0.2841796875 }, { "start": 2142.34, "end": 2142.46, "word": " want", "probability": 0.76171875 }, { "start": 2142.46, "end": 2142.52, "word": " to", "probability": 0.90625 }, { "start": 2142.52, "end": 2142.68, "word": " see", "probability": 0.80859375 }, { "start": 2142.68, "end": 2142.96, "word": " the", "probability": 0.81103515625 }, { "start": 2142.96, "end": 2143.18, "word": " full", "probability": 0.80224609375 }, { "start": 2143.18, "end": 2143.44, "word": " text", "probability": 0.84375 }, { "start": 2143.44, "end": 2143.7, "word": " body", "probability": 0.78955078125 } ] }, { "id": 640, "seek": 208514, "start": 2143.7, "end": 2145.62, "text": " of a random email in our corpus array,", "tokens": [ 51164, 295, 257, 4974, 3796, 294, 527, 1181, 31624, 10225, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.19822761004985268, "compression_ratio": 1.7718631178707225, "no_speech_prob": 0.060089111328125, "words": [ { "start": 2143.7, "end": 2143.86, "word": " of", "probability": 0.9052734375 }, { "start": 2143.96, "end": 2144.18, "word": " a random", "probability": 0.72509765625 }, { "start": 2144.18, "end": 2144.54, "word": " email", "probability": 0.8662109375 }, { "start": 2144.54, "end": 2144.8, "word": " in", "probability": 0.88623046875 }, { "start": 2144.8, "end": 2144.92, "word": " our", "probability": 0.81494140625 }, { "start": 2144.92, "end": 2145.2, "word": " corpus", "probability": 0.79931640625 }, { "start": 2145.2, "end": 2145.5, "word": " array", "probability": 0.72021484375 }, { "start": 2145.5, "end": 2145.62, "word": ",", "probability": 0.47802734375 } ] }, { "id": 641, "seek": 208514, "start": 2145.62, "end": 2148.4, "text": " and then we want to see the tokenized result of that same email.", "tokens": [ 51264, 293, 550, 321, 528, 281, 536, 264, 14862, 1602, 1874, 295, 300, 912, 3796, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.19822761004985268, "compression_ratio": 1.7718631178707225, "no_speech_prob": 0.060089111328125, "words": [ { "start": 2145.62, "end": 2145.7, "word": " and", "probability": 0.8896484375 }, { "start": 2145.7, "end": 2145.8, "word": " then", "probability": 0.7021484375 }, { "start": 2145.8, "end": 2145.88, "word": " we", "probability": 0.900390625 }, { "start": 2145.88, "end": 2146.0, "word": " want", "probability": 0.79931640625 }, { "start": 2146.0, "end": 2146.06, "word": " to", "probability": 0.90625 }, { "start": 2146.06, "end": 2146.16, "word": " see", "probability": 0.810546875 }, { "start": 2146.16, "end": 2146.36, "word": " the", "probability": 0.80615234375 }, { "start": 2146.36, "end": 2146.98, "word": " tokenized", "probability": 0.886962890625 }, { "start": 2146.98, "end": 2147.38, "word": " result", "probability": 0.7939453125 }, { "start": 2147.38, "end": 2147.6, "word": " of", "probability": 0.89306640625 }, { "start": 2147.6, "end": 2147.74, "word": " that", "probability": 0.87890625 }, { "start": 2147.74, "end": 2148.02, "word": " same", "probability": 0.8115234375 }, { "start": 2148.02, "end": 2148.28, "word": " email", "probability": 0.900390625 }, { "start": 2148.28, "end": 2148.4, "word": ".", "probability": 0.91015625 } ] }, { "id": 642, "seek": 208514, "start": 2148.4, "end": 2152.3, "text": " So this is going to be very similar to what we did for task 1,", "tokens": [ 51414, 407, 341, 307, 516, 281, 312, 588, 2531, 281, 437, 321, 630, 337, 5633, 502, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.19822761004985268, "compression_ratio": 1.7718631178707225, "no_speech_prob": 0.060089111328125, "words": [ { "start": 2148.4, "end": 2148.5, "word": " So", "probability": 0.84228515625 }, { "start": 2148.5, "end": 2148.64, "word": " this", "probability": 0.87109375 }, { "start": 2148.64, "end": 2148.72, "word": " is", "probability": 0.9072265625 }, { "start": 2148.72, "end": 2148.82, "word": " going", "probability": 0.7314453125 }, { "start": 2148.82, "end": 2148.84, "word": " to", "probability": 0.90576171875 }, { "start": 2148.84, "end": 2148.94, "word": " be", "probability": 0.904296875 }, { "start": 2148.94, "end": 2149.14, "word": " very", "probability": 0.73046875 }, { "start": 2149.14, "end": 2149.54, "word": " similar", "probability": 0.9267578125 }, { "start": 2149.54, "end": 2150.5, "word": " to", "probability": 0.90185546875 }, { "start": 2150.5, "end": 2150.82, "word": " what", "probability": 0.87744140625 }, { "start": 2150.82, "end": 2150.94, "word": " we", "probability": 0.904296875 }, { "start": 2150.94, "end": 2151.16, "word": " did", "probability": 0.89501953125 }, { "start": 2151.16, "end": 2151.44, "word": " for", "probability": 0.89111328125 }, { "start": 2151.44, "end": 2151.86, "word": " task", "probability": 0.7705078125 }, { "start": 2151.86, "end": 2152.16, "word": " 1", "probability": 0.7119140625 }, { "start": 2152.16, "end": 2152.3, "word": ",", "probability": 0.8330078125 } ] }, { "id": 643, "seek": 208514, "start": 2152.3, "end": 2153.76, "text": " which was printing out the test email,", "tokens": [ 51564, 597, 390, 14699, 484, 264, 1500, 3796, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.19822761004985268, "compression_ratio": 1.7718631178707225, "no_speech_prob": 0.060089111328125, "words": [ { "start": 2152.3, "end": 2152.46, "word": " which", "probability": 0.91845703125 }, { "start": 2152.46, "end": 2152.6, "word": " was", "probability": 0.88671875 }, { "start": 2152.6, "end": 2152.78, "word": " printing", "probability": 0.861328125 }, { "start": 2152.78, "end": 2152.94, "word": " out", "probability": 0.7802734375 }, { "start": 2152.94, "end": 2153.06, "word": " the", "probability": 0.80615234375 }, { "start": 2153.06, "end": 2153.3, "word": " test", "probability": 0.84765625 }, { "start": 2153.3, "end": 2153.58, "word": " email", "probability": 0.92822265625 }, { "start": 2153.58, "end": 2153.76, "word": ",", "probability": 0.335693359375 } ] }, { "id": 644, "seek": 208514, "start": 2153.76, "end": 2156.38, "text": " and then printing out the tokenized version of the test email.", "tokens": [ 51664, 293, 550, 14699, 484, 264, 14862, 1602, 3037, 295, 264, 1500, 3796, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.19822761004985268, "compression_ratio": 1.7718631178707225, "no_speech_prob": 0.060089111328125, "words": [ { "start": 2153.76, "end": 2153.96, "word": " and", "probability": 0.88330078125 }, { "start": 2153.96, "end": 2154.1, "word": " then", "probability": 0.73486328125 }, { "start": 2154.1, "end": 2154.3, "word": " printing", "probability": 0.85009765625 }, { "start": 2154.3, "end": 2154.44, "word": " out", "probability": 0.80517578125 }, { "start": 2154.44, "end": 2154.58, "word": " the", "probability": 0.81201171875 }, { "start": 2154.58, "end": 2154.98, "word": " tokenized", "probability": 0.89501953125 }, { "start": 2154.98, "end": 2155.22, "word": " version", "probability": 0.71826171875 }, { "start": 2155.22, "end": 2155.34, "word": " of", "probability": 0.90869140625 }, { "start": 2155.34, "end": 2155.46, "word": " the", "probability": 0.81591796875 }, { "start": 2155.46, "end": 2155.68, "word": " test", "probability": 0.8037109375 }, { "start": 2155.68, "end": 2155.98, "word": " email", "probability": 0.91943359375 }, { "start": 2155.98, "end": 2156.38, "word": ".", "probability": 0.892578125 } ] }, { "id": 645, "seek": 211414, "start": 2156.38, "end": 2158.72, "text": " So we'll just go ahead and grab a random email.", "tokens": [ 50364, 407, 321, 603, 445, 352, 2286, 293, 4444, 257, 4974, 3796, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.2133969883951876, "compression_ratio": 1.6600985221674878, "no_speech_prob": 0.1329345703125, "words": [ { "start": 2156.38, "end": 2156.7, "word": " So", "probability": 0.1380615234375 }, { "start": 2156.7, "end": 2156.92, "word": " we'll", "probability": 0.723388671875 }, { "start": 2156.92, "end": 2157.06, "word": " just", "probability": 0.8310546875 }, { "start": 2157.06, "end": 2157.2, "word": " go", "probability": 0.85302734375 }, { "start": 2157.2, "end": 2157.36, "word": " ahead", "probability": 0.81982421875 }, { "start": 2157.36, "end": 2157.44, "word": " and", "probability": 0.88330078125 }, { "start": 2157.44, "end": 2157.64, "word": " grab", "probability": 0.81982421875 }, { "start": 2157.76, "end": 2158.06, "word": " a random", "probability": 0.73974609375 }, { "start": 2158.06, "end": 2158.42, "word": " email", "probability": 0.85546875 }, { "start": 2158.42, "end": 2158.72, "word": ".", "probability": 0.397216796875 } ] }, { "id": 646, "seek": 211414, "start": 2158.72, "end": 2162.14, "text": " So email equals corpus.", "tokens": [ 50464, 407, 3796, 6915, 1181, 31624, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.2133969883951876, "compression_ratio": 1.6600985221674878, "no_speech_prob": 0.1329345703125, "words": [ { "start": 2158.72, "end": 2158.82, "word": " So", "probability": 0.638671875 }, { "start": 2158.82, "end": 2159.22, "word": " email", "probability": 0.787109375 }, { "start": 2159.22, "end": 2160.08, "word": " equals", "probability": 0.6337890625 }, { "start": 2160.08, "end": 2161.72, "word": " corpus", "probability": 0.7412109375 }, { "start": 2161.72, "end": 2162.14, "word": ".", "probability": 0.497314453125 } ] }, { "id": 647, "seek": 211414, "start": 2163.24, "end": 2164.98, "text": " Actually, let me go ahead and do this.", "tokens": [ 50714, 5135, 11, 718, 385, 352, 2286, 293, 360, 341, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.2133969883951876, "compression_ratio": 1.6600985221674878, "no_speech_prob": 0.1329345703125, "words": [ { "start": 2163.24, "end": 2163.66, "word": " Actually", "probability": 0.3515625 }, { "start": 2163.66, "end": 2163.72, "word": ",", "probability": 0.482666015625 }, { "start": 2163.72, "end": 2163.82, "word": " let", "probability": 0.79638671875 }, { "start": 2163.82, "end": 2163.86, "word": " me", "probability": 0.88232421875 }, { "start": 2163.86, "end": 2164.0, "word": " go", "probability": 0.8916015625 }, { "start": 2164.0, "end": 2164.16, "word": " ahead", "probability": 0.8447265625 }, { "start": 2164.16, "end": 2164.24, "word": " and", "probability": 0.88720703125 }, { "start": 2164.24, "end": 2164.38, "word": " do", "probability": 0.9033203125 }, { "start": 2164.38, "end": 2164.82, "word": " this", "probability": 0.87890625 }, { "start": 2164.82, "end": 2164.98, "word": ".", "probability": 0.857421875 } ] }, { "id": 648, "seek": 211414, "start": 2164.98, "end": 2169.5, "text": " Let's have email ID equals just the number 5.", "tokens": [ 50814, 961, 311, 362, 3796, 7348, 6915, 445, 264, 1230, 1025, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.2133969883951876, "compression_ratio": 1.6600985221674878, "no_speech_prob": 0.1329345703125, "words": [ { "start": 2164.98, "end": 2165.14, "word": " Let's", "probability": 0.92333984375 }, { "start": 2165.14, "end": 2165.46, "word": " have", "probability": 0.8955078125 }, { "start": 2165.46, "end": 2166.22, "word": " email", "probability": 0.794921875 }, { "start": 2166.22, "end": 2167.32, "word": " ID", "probability": 0.43359375 }, { "start": 2167.32, "end": 2168.04, "word": " equals", "probability": 0.83984375 }, { "start": 2168.04, "end": 2168.32, "word": " just", "probability": 0.81201171875 }, { "start": 2168.32, "end": 2168.48, "word": " the", "probability": 0.80810546875 }, { "start": 2168.48, "end": 2168.64, "word": " number", "probability": 0.88916015625 }, { "start": 2168.64, "end": 2169.18, "word": " 5", "probability": 0.356201171875 }, { "start": 2169.18, "end": 2169.5, "word": ".", "probability": 0.82763671875 } ] }, { "id": 649, "seek": 211414, "start": 2169.5, "end": 2170.28, "text": " Why not?", "tokens": [ 51014, 1545, 406, 30, 51114 ], "temperature": 0.0, "avg_logprob": -0.2133969883951876, "compression_ratio": 1.6600985221674878, "no_speech_prob": 0.1329345703125, "words": [ { "start": 2169.5, "end": 2169.62, "word": " Why", "probability": 0.6298828125 }, { "start": 2169.62, "end": 2169.86, "word": " not", "probability": 0.8935546875 }, { "start": 2169.86, "end": 2170.28, "word": "?", "probability": 0.71435546875 } ] }, { "id": 650, "seek": 211414, "start": 2170.92, "end": 2175.06, "text": " And then we're going to grab email ID.", "tokens": [ 51114, 400, 550, 321, 434, 516, 281, 4444, 3796, 7348, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.2133969883951876, "compression_ratio": 1.6600985221674878, "no_speech_prob": 0.1329345703125, "words": [ { "start": 2170.92, "end": 2171.24, "word": " And", "probability": 0.8505859375 }, { "start": 2171.24, "end": 2171.38, "word": " then", "probability": 0.72119140625 }, { "start": 2171.38, "end": 2171.54, "word": " we're", "probability": 0.913330078125 }, { "start": 2171.54, "end": 2171.76, "word": " going", "probability": 0.85693359375 }, { "start": 2171.76, "end": 2171.98, "word": " to", "probability": 0.908203125 }, { "start": 2171.98, "end": 2172.38, "word": " grab", "probability": 0.80224609375 }, { "start": 2172.38, "end": 2174.04, "word": " email", "probability": 0.77734375 }, { "start": 2174.04, "end": 2174.64, "word": " ID", "probability": 0.87646484375 }, { "start": 2174.64, "end": 2175.06, "word": ".", "probability": 0.85205078125 } ] }, { "id": 651, "seek": 211414, "start": 2175.76, "end": 2177.82, "text": " So this is going to be our random email.", "tokens": [ 51314, 407, 341, 307, 516, 281, 312, 527, 4974, 3796, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.2133969883951876, "compression_ratio": 1.6600985221674878, "no_speech_prob": 0.1329345703125, "words": [ { "start": 2175.76, "end": 2175.98, "word": " So", "probability": 0.7392578125 }, { "start": 2175.98, "end": 2176.12, "word": " this", "probability": 0.87548828125 }, { "start": 2176.12, "end": 2176.22, "word": " is", "probability": 0.90478515625 }, { "start": 2176.22, "end": 2176.3, "word": " going", "probability": 0.75048828125 }, { "start": 2176.3, "end": 2176.34, "word": " to", "probability": 0.90380859375 }, { "start": 2176.34, "end": 2176.44, "word": " be", "probability": 0.90625 }, { "start": 2176.44, "end": 2176.6, "word": " our", "probability": 0.81640625 }, { "start": 2176.6, "end": 2176.94, "word": " random", "probability": 0.73486328125 }, { "start": 2176.94, "end": 2177.4, "word": " email", "probability": 0.91845703125 }, { "start": 2177.4, "end": 2177.82, "word": ".", "probability": 0.97705078125 } ] }, { "id": 652, "seek": 211414, "start": 2178.48, "end": 2180.34, "text": " We're going to...", "tokens": [ 51464, 492, 434, 516, 281, 485, 51564 ], "temperature": 0.0, "avg_logprob": -0.2133969883951876, "compression_ratio": 1.6600985221674878, "no_speech_prob": 0.1329345703125, "words": [ { "start": 2178.48, "end": 2178.58, "word": " We're", "probability": 0.897705078125 }, { "start": 2178.58, "end": 2178.8, "word": " going", "probability": 0.7626953125 }, { "start": 2178.8, "end": 2180.34, "word": " to...", "probability": 0.5390625 } ] }, { "id": 653, "seek": 211414, "start": 2180.34, "end": 2183.28, "text": " probably going to print a...", "tokens": [ 51564, 1391, 516, 281, 4482, 257, 485, 51714 ], "temperature": 0.0, "avg_logprob": -0.2133969883951876, "compression_ratio": 1.6600985221674878, "no_speech_prob": 0.1329345703125, "words": [ { "start": 2180.34, "end": 2180.94, "word": " probably", "probability": 0.3740234375 }, { "start": 2180.94, "end": 2181.06, "word": " going", "probability": 0.76416015625 }, { "start": 2181.06, "end": 2181.2, "word": " to", "probability": 0.9130859375 }, { "start": 2181.2, "end": 2181.64, "word": " print", "probability": 0.86865234375 }, { "start": 2181.64, "end": 2183.28, "word": " a...", "probability": 0.885009765625 } ] }, { "id": 654, "seek": 211414, "start": 2183.28, "end": 2185.38, "text": " No, I already have a divider in there. Cool.", "tokens": [ 51714, 883, 11, 286, 1217, 362, 257, 3414, 1438, 294, 456, 13, 8561, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.2133969883951876, "compression_ratio": 1.6600985221674878, "no_speech_prob": 0.1329345703125, "words": [ { "start": 2183.28, "end": 2183.54, "word": " No", "probability": 0.3134765625 }, { "start": 2183.54, "end": 2183.58, "word": ",", "probability": 0.8701171875 }, { "start": 2183.58, "end": 2183.68, "word": " I", "probability": 0.994140625 }, { "start": 2183.68, "end": 2183.82, "word": " already", "probability": 0.84033203125 }, { "start": 2183.82, "end": 2183.98, "word": " have", "probability": 0.875 }, { "start": 2184.06, "end": 2184.34, "word": " a divider", "probability": 0.899169921875 }, { "start": 2184.34, "end": 2184.5, "word": " in", "probability": 0.890625 }, { "start": 2184.5, "end": 2184.66, "word": " there", "probability": 0.86181640625 }, { "start": 2184.66, "end": 2184.78, "word": ".", "probability": 0.79931640625 }, { "start": 2184.78, "end": 2184.96, "word": " Cool", "probability": 0.76611328125 }, { "start": 2184.96, "end": 2185.38, "word": ".", "probability": 0.921875 } ] }, { "id": 655, "seek": 214028, "start": 2185.38, "end": 2187.1, "text": " So let's just print that email.", "tokens": [ 50364, 407, 718, 311, 445, 4482, 300, 3796, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.20495495146459286, "compression_ratio": 1.643835616438356, "no_speech_prob": 0.0013246536254882812, "words": [ { "start": 2185.38, "end": 2185.56, "word": " So", "probability": 0.57177734375 }, { "start": 2185.56, "end": 2185.78, "word": " let's", "probability": 0.880615234375 }, { "start": 2185.78, "end": 2185.92, "word": " just", "probability": 0.880859375 }, { "start": 2185.92, "end": 2186.2, "word": " print", "probability": 0.86865234375 }, { "start": 2186.2, "end": 2186.36, "word": " that", "probability": 0.8876953125 }, { "start": 2186.36, "end": 2186.62, "word": " email", "probability": 0.86962890625 }, { "start": 2186.62, "end": 2187.1, "word": ".", "probability": 0.8427734375 } ] }, { "id": 656, "seek": 214028, "start": 2188.18, "end": 2193.66, "text": " And then, same thing, we're going to do print tokenizer,", "tokens": [ 50514, 400, 550, 11, 912, 551, 11, 321, 434, 516, 281, 360, 4482, 14862, 6545, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.20495495146459286, "compression_ratio": 1.643835616438356, "no_speech_prob": 0.0013246536254882812, "words": [ { "start": 2188.18, "end": 2188.3, "word": " And", "probability": 0.744140625 }, { "start": 2188.3, "end": 2188.62, "word": " then", "probability": 0.73095703125 }, { "start": 2188.62, "end": 2189.04, "word": ",", "probability": 0.41845703125 }, { "start": 2189.04, "end": 2189.64, "word": " same", "probability": 0.80322265625 }, { "start": 2189.64, "end": 2189.88, "word": " thing", "probability": 0.806640625 }, { "start": 2189.88, "end": 2190.04, "word": ",", "probability": 0.6767578125 }, { "start": 2190.04, "end": 2190.12, "word": " we're", "probability": 0.919189453125 }, { "start": 2190.12, "end": 2190.3, "word": " going", "probability": 0.84912109375 }, { "start": 2190.3, "end": 2190.46, "word": " to", "probability": 0.91162109375 }, { "start": 2190.46, "end": 2190.84, "word": " do", "probability": 0.90283203125 }, { "start": 2190.84, "end": 2191.46, "word": " print", "probability": 0.61669921875 }, { "start": 2191.46, "end": 2193.24, "word": " tokenizer", "probability": 0.6875 }, { "start": 2193.24, "end": 2193.66, "word": ",", "probability": 0.3828125 } ] }, { "id": 657, "seek": 214028, "start": 2194.36, "end": 2196.5, "text": " and then that same email.", "tokens": [ 50814, 293, 550, 300, 912, 3796, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.20495495146459286, "compression_ratio": 1.643835616438356, "no_speech_prob": 0.0013246536254882812, "words": [ { "start": 2194.36, "end": 2194.6, "word": " and", "probability": 0.88818359375 }, { "start": 2194.6, "end": 2194.86, "word": " then", "probability": 0.734375 }, { "start": 2194.86, "end": 2195.28, "word": " that", "probability": 0.83349609375 }, { "start": 2195.28, "end": 2195.66, "word": " same", "probability": 0.8037109375 }, { "start": 2195.66, "end": 2196.02, "word": " email", "probability": 0.91259765625 }, { "start": 2196.02, "end": 2196.5, "word": ".", "probability": 0.97705078125 } ] }, { "id": 658, "seek": 214028, "start": 2196.68, "end": 2201.36, "text": " So this line and this line is exactly the same that we did in task 1.", "tokens": [ 50914, 407, 341, 1622, 293, 341, 1622, 307, 2293, 264, 912, 300, 321, 630, 294, 5633, 502, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.20495495146459286, "compression_ratio": 1.643835616438356, "no_speech_prob": 0.0013246536254882812, "words": [ { "start": 2196.68, "end": 2196.94, "word": " So", "probability": 0.849609375 }, { "start": 2196.94, "end": 2197.24, "word": " this", "probability": 0.7900390625 }, { "start": 2197.24, "end": 2197.48, "word": " line", "probability": 0.87890625 }, { "start": 2197.48, "end": 2197.58, "word": " and", "probability": 0.869140625 }, { "start": 2197.58, "end": 2197.74, "word": " this", "probability": 0.8857421875 }, { "start": 2197.74, "end": 2197.92, "word": " line", "probability": 0.87255859375 }, { "start": 2197.92, "end": 2198.04, "word": " is", "probability": 0.8798828125 }, { "start": 2198.04, "end": 2198.34, "word": " exactly", "probability": 0.77978515625 }, { "start": 2198.34, "end": 2198.58, "word": " the", "probability": 0.8134765625 }, { "start": 2198.58, "end": 2198.8, "word": " same", "probability": 0.8115234375 }, { "start": 2198.8, "end": 2198.94, "word": " that", "probability": 0.81396484375 }, { "start": 2198.94, "end": 2199.06, "word": " we", "probability": 0.9013671875 }, { "start": 2199.06, "end": 2199.36, "word": " did", "probability": 0.90185546875 }, { "start": 2199.36, "end": 2200.08, "word": " in", "probability": 0.90087890625 }, { "start": 2200.08, "end": 2200.72, "word": " task", "probability": 0.72119140625 }, { "start": 2200.72, "end": 2201.1, "word": " 1", "probability": 0.165283203125 }, { "start": 2201.1, "end": 2201.36, "word": ".", "probability": 0.7626953125 } ] }, { "id": 659, "seek": 214028, "start": 2201.36, "end": 2204.26, "text": " This is the only thing that changes so that we grab a random email.", "tokens": [ 51164, 639, 307, 264, 787, 551, 300, 2962, 370, 300, 321, 4444, 257, 4974, 3796, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.20495495146459286, "compression_ratio": 1.643835616438356, "no_speech_prob": 0.0013246536254882812, "words": [ { "start": 2201.36, "end": 2201.7, "word": " This", "probability": 0.8056640625 }, { "start": 2201.7, "end": 2201.8, "word": " is", "probability": 0.9033203125 }, { "start": 2201.8, "end": 2201.92, "word": " the", "probability": 0.8154296875 }, { "start": 2201.92, "end": 2202.04, "word": " only", "probability": 0.85595703125 }, { "start": 2202.04, "end": 2202.22, "word": " thing", "probability": 0.8125 }, { "start": 2202.22, "end": 2202.36, "word": " that", "probability": 0.88671875 }, { "start": 2202.36, "end": 2202.68, "word": " changes", "probability": 0.80224609375 }, { "start": 2202.68, "end": 2202.88, "word": " so", "probability": 0.496826171875 }, { "start": 2202.88, "end": 2202.98, "word": " that", "probability": 0.74365234375 }, { "start": 2202.98, "end": 2203.04, "word": " we", "probability": 0.90283203125 }, { "start": 2203.04, "end": 2203.3, "word": " grab", "probability": 0.8193359375 }, { "start": 2203.42, "end": 2203.64, "word": " a random", "probability": 0.7236328125 }, { "start": 2203.64, "end": 2203.96, "word": " email", "probability": 0.90869140625 }, { "start": 2203.96, "end": 2204.26, "word": ".", "probability": 0.71044921875 } ] }, { "id": 660, "seek": 214028, "start": 2204.26, "end": 2206.98, "text": " And then you don't have to put 5, you can put any number,", "tokens": [ 51314, 400, 550, 291, 500, 380, 362, 281, 829, 1025, 11, 291, 393, 829, 604, 1230, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.20495495146459286, "compression_ratio": 1.643835616438356, "no_speech_prob": 0.0013246536254882812, "words": [ { "start": 2204.26, "end": 2204.32, "word": " And", "probability": 0.75048828125 }, { "start": 2204.32, "end": 2204.46, "word": " then", "probability": 0.6669921875 }, { "start": 2204.46, "end": 2204.62, "word": " you", "probability": 0.82080078125 }, { "start": 2204.62, "end": 2204.74, "word": " don't", "probability": 0.94677734375 }, { "start": 2204.74, "end": 2204.94, "word": " have", "probability": 0.8828125 }, { "start": 2204.94, "end": 2205.06, "word": " to", "probability": 0.9033203125 }, { "start": 2205.06, "end": 2205.2, "word": " put", "probability": 0.8828125 }, { "start": 2205.2, "end": 2205.54, "word": " 5", "probability": 0.59814453125 }, { "start": 2205.54, "end": 2205.58, "word": ",", "probability": 0.7216796875 }, { "start": 2205.58, "end": 2205.68, "word": " you", "probability": 0.89404296875 }, { "start": 2205.68, "end": 2205.78, "word": " can", "probability": 0.892578125 }, { "start": 2205.78, "end": 2205.96, "word": " put", "probability": 0.89599609375 }, { "start": 2205.96, "end": 2206.18, "word": " any", "probability": 0.80126953125 }, { "start": 2206.18, "end": 2206.5, "word": " number", "probability": 0.88623046875 }, { "start": 2206.5, "end": 2206.98, "word": ",", "probability": 0.759765625 } ] }, { "id": 661, "seek": 214028, "start": 2206.98, "end": 2209.0, "text": " but I'm just picking 5.", "tokens": [ 51464, 457, 286, 478, 445, 8867, 1025, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.20495495146459286, "compression_ratio": 1.643835616438356, "no_speech_prob": 0.0013246536254882812, "words": [ { "start": 2206.98, "end": 2207.24, "word": " but", "probability": 0.89501953125 }, { "start": 2207.24, "end": 2207.54, "word": " I'm", "probability": 0.99462890625 }, { "start": 2207.54, "end": 2207.7, "word": " just", "probability": 0.89208984375 }, { "start": 2207.7, "end": 2208.14, "word": " picking", "probability": 0.71533203125 }, { "start": 2208.14, "end": 2208.52, "word": " 5", "probability": 0.9541015625 }, { "start": 2208.52, "end": 2209.0, "word": ".", "probability": 0.98046875 } ] }, { "id": 662, "seek": 214028, "start": 2209.28, "end": 2211.52, "text": " So go ahead, Shift-Enter.", "tokens": [ 51564, 407, 352, 2286, 11, 28304, 12, 16257, 391, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.20495495146459286, "compression_ratio": 1.643835616438356, "no_speech_prob": 0.0013246536254882812, "words": [ { "start": 2209.28, "end": 2209.74, "word": " So", "probability": 0.88525390625 }, { "start": 2209.74, "end": 2209.94, "word": " go", "probability": 0.7705078125 }, { "start": 2209.94, "end": 2210.18, "word": " ahead", "probability": 0.84326171875 }, { "start": 2210.18, "end": 2210.34, "word": ",", "probability": 0.7431640625 }, { "start": 2210.34, "end": 2210.62, "word": " Shift", "probability": 0.307373046875 }, { "start": 2210.62, "end": 2211.04, "word": "-Enter", "probability": 0.6932373046875 }, { "start": 2211.04, "end": 2211.52, "word": ".", "probability": 0.5869140625 } ] }, { "id": 663, "seek": 216810, "start": 2212.44, "end": 2214.8, "text": " And this one's pretty nice.", "tokens": [ 50414, 400, 341, 472, 311, 1238, 1481, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.23381023880947066, "compression_ratio": 1.5857988165680474, "no_speech_prob": 0.00284576416015625, "words": [ { "start": 2212.44, "end": 2213.2, "word": " And", "probability": 0.45703125 }, { "start": 2213.2, "end": 2213.32, "word": " this", "probability": 0.865234375 }, { "start": 2213.32, "end": 2213.5, "word": " one's", "probability": 0.814453125 }, { "start": 2213.5, "end": 2213.66, "word": " pretty", "probability": 0.880859375 }, { "start": 2213.66, "end": 2214.04, "word": " nice", "probability": 0.806640625 }, { "start": 2214.04, "end": 2214.8, "word": ".", "probability": 0.59130859375 } ] }, { "id": 664, "seek": 216810, "start": 2214.8, "end": 2221.62, "text": " So we see the body of the email, product review, virttools, dev, URL,", "tokens": [ 50514, 407, 321, 536, 264, 1772, 295, 264, 3796, 11, 1674, 3131, 11, 4480, 83, 29298, 11, 1905, 11, 12905, 11, 50864 ], "temperature": 0.0, "avg_logprob": -0.23381023880947066, "compression_ratio": 1.5857988165680474, "no_speech_prob": 0.00284576416015625, "words": [ { "start": 2214.8, "end": 2215.5, "word": " So", "probability": 0.7890625 }, { "start": 2215.5, "end": 2215.86, "word": " we", "probability": 0.72705078125 }, { "start": 2215.86, "end": 2216.24, "word": " see", "probability": 0.810546875 }, { "start": 2216.24, "end": 2216.74, "word": " the", "probability": 0.8046875 }, { "start": 2216.74, "end": 2217.06, "word": " body", "probability": 0.79736328125 }, { "start": 2217.06, "end": 2217.2, "word": " of", "probability": 0.90234375 }, { "start": 2217.2, "end": 2217.3, "word": " the", "probability": 0.80615234375 }, { "start": 2217.3, "end": 2217.62, "word": " email", "probability": 0.88232421875 }, { "start": 2217.62, "end": 2217.82, "word": ",", "probability": 0.7060546875 }, { "start": 2217.82, "end": 2218.06, "word": " product", "probability": 0.6806640625 }, { "start": 2218.06, "end": 2218.5, "word": " review", "probability": 0.65771484375 }, { "start": 2218.5, "end": 2218.68, "word": ",", "probability": 0.77490234375 }, { "start": 2218.68, "end": 2219.14, "word": " virttools", "probability": 0.5503743489583334 }, { "start": 2219.14, "end": 2219.28, "word": ",", "probability": 0.75634765625 }, { "start": 2219.28, "end": 2219.72, "word": " dev", "probability": 0.787109375 }, { "start": 2219.72, "end": 2220.32, "word": ",", "probability": 0.84619140625 }, { "start": 2220.32, "end": 2221.16, "word": " URL", "probability": 0.68896484375 }, { "start": 2221.16, "end": 2221.62, "word": ",", "probability": 0.57421875 } ] }, { "id": 665, "seek": 216810, "start": 2221.62, "end": 2226.38, "text": " product review, virttool, dev, 2.0 URL.", "tokens": [ 50864, 1674, 3131, 11, 4480, 83, 1092, 11, 1905, 11, 568, 13, 15, 12905, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.23381023880947066, "compression_ratio": 1.5857988165680474, "no_speech_prob": 0.00284576416015625, "words": [ { "start": 2221.62, "end": 2221.94, "word": " product", "probability": 0.78173828125 }, { "start": 2221.94, "end": 2222.42, "word": " review", "probability": 0.6650390625 }, { "start": 2222.42, "end": 2222.62, "word": ",", "probability": 0.91162109375 }, { "start": 2222.62, "end": 2223.16, "word": " virttool", "probability": 0.90380859375 }, { "start": 2223.16, "end": 2223.7, "word": ",", "probability": 0.9765625 }, { "start": 2223.7, "end": 2224.3, "word": " dev", "probability": 0.78173828125 }, { "start": 2224.3, "end": 2224.8, "word": ",", "probability": 0.916015625 }, { "start": 2224.8, "end": 2225.02, "word": " 2", "probability": 0.98291015625 }, { "start": 2225.02, "end": 2225.28, "word": ".0", "probability": 0.997802734375 }, { "start": 2225.28, "end": 2225.62, "word": " URL", "probability": 0.7568359375 }, { "start": 2225.62, "end": 2226.38, "word": ".", "probability": 0.86572265625 } ] }, { "id": 666, "seek": 216810, "start": 2226.6, "end": 2232.42, "text": " We see the full path for the URL here.", "tokens": [ 51114, 492, 536, 264, 1577, 3100, 337, 264, 12905, 510, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.23381023880947066, "compression_ratio": 1.5857988165680474, "no_speech_prob": 0.00284576416015625, "words": [ { "start": 2226.6, "end": 2227.12, "word": " We", "probability": 0.896484375 }, { "start": 2227.12, "end": 2227.3, "word": " see", "probability": 0.81298828125 }, { "start": 2227.3, "end": 2227.7, "word": " the", "probability": 0.814453125 }, { "start": 2227.7, "end": 2229.28, "word": " full", "probability": 0.77587890625 }, { "start": 2229.28, "end": 2229.96, "word": " path", "probability": 0.857421875 }, { "start": 2229.96, "end": 2230.64, "word": " for", "probability": 0.875 }, { "start": 2230.64, "end": 2230.94, "word": " the", "probability": 0.81494140625 }, { "start": 2230.94, "end": 2231.38, "word": " URL", "probability": 0.88037109375 }, { "start": 2231.38, "end": 2231.66, "word": " here", "probability": 0.80908203125 }, { "start": 2231.66, "end": 2232.42, "word": ".", "probability": 0.97265625 } ] }, { "id": 667, "seek": 216810, "start": 2232.94, "end": 2235.6, "text": " Let's see if there's anything interesting.", "tokens": [ 51414, 961, 311, 536, 498, 456, 311, 1340, 1880, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.23381023880947066, "compression_ratio": 1.5857988165680474, "no_speech_prob": 0.00284576416015625, "words": [ { "start": 2232.94, "end": 2233.7, "word": " Let's", "probability": 0.93505859375 }, { "start": 2233.7, "end": 2233.78, "word": " see", "probability": 0.8056640625 }, { "start": 2233.78, "end": 2233.86, "word": " if", "probability": 0.89990234375 }, { "start": 2233.86, "end": 2234.02, "word": " there's", "probability": 0.922119140625 }, { "start": 2234.02, "end": 2234.34, "word": " anything", "probability": 0.84423828125 }, { "start": 2234.34, "end": 2234.84, "word": " interesting", "probability": 0.64208984375 }, { "start": 2234.84, "end": 2235.6, "word": ".", "probability": 0.65185546875 } ] }, { "id": 668, "seek": 216810, "start": 2235.78, "end": 2239.34, "text": " Maybe features, feature is shortened to feature,", "tokens": [ 51564, 2704, 4122, 11, 4111, 307, 45183, 281, 4111, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.23381023880947066, "compression_ratio": 1.5857988165680474, "no_speech_prob": 0.00284576416015625, "words": [ { "start": 2235.78, "end": 2236.04, "word": " Maybe", "probability": 0.9130859375 }, { "start": 2236.04, "end": 2236.82, "word": " features", "probability": 0.626953125 }, { "start": 2236.82, "end": 2236.98, "word": ",", "probability": 0.82373046875 }, { "start": 2236.98, "end": 2237.24, "word": " feature", "probability": 0.336181640625 }, { "start": 2237.24, "end": 2237.4, "word": " is", "probability": 0.60205078125 }, { "start": 2237.4, "end": 2237.62, "word": " shortened", "probability": 0.69189453125 }, { "start": 2237.62, "end": 2237.82, "word": " to", "probability": 0.8818359375 }, { "start": 2237.82, "end": 2238.3, "word": " feature", "probability": 0.7861328125 }, { "start": 2238.3, "end": 2239.34, "word": ",", "probability": 0.392822265625 } ] }, { "id": 669, "seek": 219636, "start": 2240.0, "end": 2243.78, "text": " because you can say featured in a motion picture with an ed at the end,", "tokens": [ 50364, 570, 291, 393, 584, 13822, 294, 257, 5394, 3036, 365, 364, 1257, 412, 264, 917, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.19733296771501674, "compression_ratio": 1.8432203389830508, "no_speech_prob": 0.0007672309875488281, "words": [ { "start": 2240.0, "end": 2240.44, "word": " because", "probability": 0.40966796875 }, { "start": 2240.44, "end": 2240.56, "word": " you", "probability": 0.82421875 }, { "start": 2240.56, "end": 2240.68, "word": " can", "probability": 0.89501953125 }, { "start": 2240.68, "end": 2240.92, "word": " say", "probability": 0.87451171875 }, { "start": 2240.92, "end": 2241.42, "word": " featured", "probability": 0.3037109375 }, { "start": 2241.42, "end": 2241.76, "word": " in", "probability": 0.85791015625 }, { "start": 2241.88, "end": 2242.08, "word": " a motion", "probability": 0.83056640625 }, { "start": 2242.08, "end": 2242.38, "word": " picture", "probability": 0.7783203125 }, { "start": 2242.38, "end": 2242.58, "word": " with", "probability": 0.794921875 }, { "start": 2242.58, "end": 2242.72, "word": " an", "probability": 0.90673828125 }, { "start": 2242.72, "end": 2242.9, "word": " ed", "probability": 0.296630859375 }, { "start": 2242.9, "end": 2243.14, "word": " at", "probability": 0.88427734375 }, { "start": 2243.14, "end": 2243.28, "word": " the", "probability": 0.81298828125 }, { "start": 2243.28, "end": 2243.54, "word": " end", "probability": 0.81005859375 }, { "start": 2243.54, "end": 2243.78, "word": ",", "probability": 0.65478515625 } ] }, { "id": 670, "seek": 219636, "start": 2243.78, "end": 2250.1, "text": " features as they have here, or we will feature with just an e at the end.", "tokens": [ 50564, 4122, 382, 436, 362, 510, 11, 420, 321, 486, 4111, 365, 445, 364, 308, 412, 264, 917, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.19733296771501674, "compression_ratio": 1.8432203389830508, "no_speech_prob": 0.0007672309875488281, "words": [ { "start": 2243.78, "end": 2244.14, "word": " features", "probability": 0.66015625 }, { "start": 2244.14, "end": 2244.48, "word": " as", "probability": 0.81640625 }, { "start": 2244.48, "end": 2244.62, "word": " they", "probability": 0.73828125 }, { "start": 2244.62, "end": 2244.82, "word": " have", "probability": 0.87890625 }, { "start": 2244.82, "end": 2245.22, "word": " here", "probability": 0.8173828125 }, { "start": 2245.22, "end": 2245.5, "word": ",", "probability": 0.748046875 }, { "start": 2245.5, "end": 2245.76, "word": " or", "probability": 0.8974609375 }, { "start": 2245.76, "end": 2246.66, "word": " we", "probability": 0.85205078125 }, { "start": 2246.66, "end": 2246.9, "word": " will", "probability": 0.80322265625 }, { "start": 2246.9, "end": 2247.46, "word": " feature", "probability": 0.86962890625 }, { "start": 2247.46, "end": 2248.6, "word": " with", "probability": 0.77880859375 }, { "start": 2248.6, "end": 2248.84, "word": " just", "probability": 0.8896484375 }, { "start": 2248.84, "end": 2249.02, "word": " an", "probability": 0.90234375 }, { "start": 2249.14, "end": 2249.32, "word": " e at", "probability": 0.88427734375 }, { "start": 2249.32, "end": 2249.44, "word": " the", "probability": 0.81298828125 }, { "start": 2249.44, "end": 2249.66, "word": " end", "probability": 0.818359375 }, { "start": 2249.66, "end": 2250.1, "word": ".", "probability": 0.95751953125 } ] }, { "id": 671, "seek": 219636, "start": 2251.32, "end": 2254.06, "text": " So this is the way that our tokenizer operates,", "tokens": [ 50914, 407, 341, 307, 264, 636, 300, 527, 14862, 6545, 22577, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.19733296771501674, "compression_ratio": 1.8432203389830508, "no_speech_prob": 0.0007672309875488281, "words": [ { "start": 2251.32, "end": 2251.76, "word": " So", "probability": 0.61669921875 }, { "start": 2251.76, "end": 2251.98, "word": " this", "probability": 0.8017578125 }, { "start": 2251.98, "end": 2252.1, "word": " is", "probability": 0.90625 }, { "start": 2252.1, "end": 2252.18, "word": " the", "probability": 0.79833984375 }, { "start": 2252.18, "end": 2252.28, "word": " way", "probability": 0.8984375 }, { "start": 2252.28, "end": 2252.4, "word": " that", "probability": 0.85546875 }, { "start": 2252.4, "end": 2252.54, "word": " our", "probability": 0.80517578125 }, { "start": 2252.54, "end": 2253.04, "word": " tokenizer", "probability": 0.830322265625 }, { "start": 2253.04, "end": 2253.8, "word": " operates", "probability": 0.74072265625 }, { "start": 2253.8, "end": 2254.06, "word": ",", "probability": 0.53759765625 } ] }, { "id": 672, "seek": 219636, "start": 2254.06, "end": 2257.46, "text": " but we still need to turn these words into numbers,", "tokens": [ 51064, 457, 321, 920, 643, 281, 1261, 613, 2283, 666, 3547, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.19733296771501674, "compression_ratio": 1.8432203389830508, "no_speech_prob": 0.0007672309875488281, "words": [ { "start": 2254.06, "end": 2254.32, "word": " but", "probability": 0.89697265625 }, { "start": 2254.32, "end": 2254.56, "word": " we", "probability": 0.908203125 }, { "start": 2254.56, "end": 2254.9, "word": " still", "probability": 0.90087890625 }, { "start": 2254.9, "end": 2255.1, "word": " need", "probability": 0.81591796875 }, { "start": 2255.1, "end": 2255.26, "word": " to", "probability": 0.904296875 }, { "start": 2255.26, "end": 2255.54, "word": " turn", "probability": 0.81396484375 }, { "start": 2255.54, "end": 2255.96, "word": " these", "probability": 0.7060546875 }, { "start": 2255.96, "end": 2256.5, "word": " words", "probability": 0.7177734375 }, { "start": 2256.5, "end": 2256.9, "word": " into", "probability": 0.7314453125 }, { "start": 2256.9, "end": 2257.44, "word": " numbers", "probability": 0.8701171875 }, { "start": 2257.44, "end": 2257.46, "word": ",", "probability": 0.362548828125 } ] }, { "id": 673, "seek": 219636, "start": 2257.46, "end": 2261.44, "text": " and this is where our vectorizers come in.", "tokens": [ 51264, 293, 341, 307, 689, 527, 8062, 22525, 808, 294, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.19733296771501674, "compression_ratio": 1.8432203389830508, "no_speech_prob": 0.0007672309875488281, "words": [ { "start": 2257.46, "end": 2257.88, "word": " and", "probability": 0.89306640625 }, { "start": 2257.88, "end": 2258.04, "word": " this", "probability": 0.88232421875 }, { "start": 2258.04, "end": 2258.22, "word": " is", "probability": 0.90625 }, { "start": 2258.22, "end": 2258.5, "word": " where", "probability": 0.9111328125 }, { "start": 2258.5, "end": 2259.0, "word": " our", "probability": 0.80859375 }, { "start": 2259.0, "end": 2259.92, "word": " vectorizers", "probability": 0.939697265625 }, { "start": 2259.92, "end": 2260.64, "word": " come", "probability": 0.8046875 }, { "start": 2260.64, "end": 2261.0, "word": " in", "probability": 0.90478515625 }, { "start": 2261.0, "end": 2261.44, "word": ".", "probability": 0.97607421875 } ] }, { "id": 674, "seek": 219636, "start": 2261.98, "end": 2264.44, "text": " So our vectorizers, we're going to use two kinds of vectorizer.", "tokens": [ 51464, 407, 527, 8062, 22525, 11, 321, 434, 516, 281, 764, 732, 3685, 295, 8062, 6545, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.19733296771501674, "compression_ratio": 1.8432203389830508, "no_speech_prob": 0.0007672309875488281, "words": [ { "start": 2261.98, "end": 2262.24, "word": " So", "probability": 0.79833984375 }, { "start": 2262.24, "end": 2262.36, "word": " our", "probability": 0.6875 }, { "start": 2262.36, "end": 2262.82, "word": " vectorizers", "probability": 0.93310546875 }, { "start": 2262.82, "end": 2262.88, "word": ",", "probability": 0.52294921875 }, { "start": 2262.88, "end": 2263.02, "word": " we're", "probability": 0.91943359375 }, { "start": 2263.02, "end": 2263.04, "word": " going", "probability": 0.833984375 }, { "start": 2263.04, "end": 2263.12, "word": " to", "probability": 0.90673828125 }, { "start": 2263.12, "end": 2263.42, "word": " use", "probability": 0.8046875 }, { "start": 2263.42, "end": 2263.56, "word": " two", "probability": 0.8173828125 }, { "start": 2263.56, "end": 2263.76, "word": " kinds", "probability": 0.78271484375 }, { "start": 2263.76, "end": 2263.86, "word": " of", "probability": 0.9033203125 }, { "start": 2263.86, "end": 2264.32, "word": " vectorizer", "probability": 0.87744140625 }, { "start": 2264.32, "end": 2264.44, "word": ".", "probability": 0.77197265625 } ] }, { "id": 675, "seek": 219636, "start": 2264.44, "end": 2267.6, "text": " We're going to use the count vectorizer, which just takes the straight word count.", "tokens": [ 51614, 492, 434, 516, 281, 764, 264, 1207, 8062, 6545, 11, 597, 445, 2516, 264, 2997, 1349, 1207, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.19733296771501674, "compression_ratio": 1.8432203389830508, "no_speech_prob": 0.0007672309875488281, "words": [ { "start": 2264.44, "end": 2264.56, "word": " We're", "probability": 0.924560546875 }, { "start": 2264.56, "end": 2264.72, "word": " going", "probability": 0.85400390625 }, { "start": 2264.72, "end": 2264.88, "word": " to", "probability": 0.90673828125 }, { "start": 2264.88, "end": 2265.02, "word": " use", "probability": 0.822265625 }, { "start": 2265.02, "end": 2265.14, "word": " the", "probability": 0.5537109375 }, { "start": 2265.14, "end": 2265.34, "word": " count", "probability": 0.72216796875 }, { "start": 2265.34, "end": 2265.86, "word": " vectorizer", "probability": 0.958984375 }, { "start": 2265.86, "end": 2265.86, "word": ",", "probability": 0.64453125 }, { "start": 2265.86, "end": 2266.02, "word": " which", "probability": 0.91943359375 }, { "start": 2266.02, "end": 2266.24, "word": " just", "probability": 0.8798828125 }, { "start": 2266.24, "end": 2266.44, "word": " takes", "probability": 0.73291015625 }, { "start": 2266.44, "end": 2266.64, "word": " the", "probability": 0.8056640625 }, { "start": 2266.64, "end": 2266.88, "word": " straight", "probability": 0.81005859375 }, { "start": 2266.88, "end": 2267.1, "word": " word", "probability": 0.8232421875 }, { "start": 2267.1, "end": 2267.44, "word": " count", "probability": 0.818359375 }, { "start": 2267.44, "end": 2267.6, "word": ".", "probability": 0.80322265625 } ] }, { "id": 676, "seek": 222526, "start": 2267.6, "end": 2269.76, "text": " It's exactly what we did in the slides.", "tokens": [ 50364, 467, 311, 2293, 437, 321, 630, 294, 264, 9788, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.21345557260119224, "compression_ratio": 1.773076923076923, "no_speech_prob": 0.0015010833740234375, "words": [ { "start": 2267.6, "end": 2267.92, "word": " It's", "probability": 0.594970703125 }, { "start": 2267.92, "end": 2268.24, "word": " exactly", "probability": 0.77490234375 }, { "start": 2268.24, "end": 2268.44, "word": " what", "probability": 0.88330078125 }, { "start": 2268.44, "end": 2268.56, "word": " we", "probability": 0.9033203125 }, { "start": 2268.56, "end": 2268.7, "word": " did", "probability": 0.89306640625 }, { "start": 2268.7, "end": 2268.82, "word": " in", "probability": 0.8984375 }, { "start": 2268.82, "end": 2268.96, "word": " the", "probability": 0.81103515625 }, { "start": 2268.96, "end": 2269.3, "word": " slides", "probability": 0.9072265625 }, { "start": 2269.3, "end": 2269.76, "word": ".", "probability": 0.77978515625 } ] }, { "id": 677, "seek": 222526, "start": 2269.76, "end": 2276.46, "text": " Then we're going to use a TF-IDF vectorizer that applies a mathematical weight to each of the words.", "tokens": [ 50464, 1396, 321, 434, 516, 281, 764, 257, 40964, 12, 2777, 37, 8062, 6545, 300, 13165, 257, 18894, 3364, 281, 1184, 295, 264, 2283, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.21345557260119224, "compression_ratio": 1.773076923076923, "no_speech_prob": 0.0015010833740234375, "words": [ { "start": 2269.76, "end": 2269.84, "word": " Then", "probability": 0.405517578125 }, { "start": 2269.84, "end": 2270.02, "word": " we're", "probability": 0.853271484375 }, { "start": 2270.02, "end": 2270.02, "word": " going", "probability": 0.7685546875 }, { "start": 2270.02, "end": 2270.02, "word": " to", "probability": 0.9072265625 }, { "start": 2270.02, "end": 2270.14, "word": " use", "probability": 0.8349609375 }, { "start": 2270.26, "end": 2270.54, "word": " a TF", "probability": 0.57958984375 }, { "start": 2270.54, "end": 2271.02, "word": "-IDF", "probability": 0.83837890625 }, { "start": 2271.02, "end": 2271.62, "word": " vectorizer", "probability": 0.91748046875 }, { "start": 2271.62, "end": 2272.38, "word": " that", "probability": 0.83251953125 }, { "start": 2272.38, "end": 2273.02, "word": " applies", "probability": 0.77294921875 }, { "start": 2273.42, "end": 2273.94, "word": " a mathematical", "probability": 0.67822265625 }, { "start": 2273.94, "end": 2274.54, "word": " weight", "probability": 0.8603515625 }, { "start": 2274.54, "end": 2275.1, "word": " to", "probability": 0.9013671875 }, { "start": 2275.1, "end": 2275.3, "word": " each", "probability": 0.86083984375 }, { "start": 2275.3, "end": 2275.4, "word": " of", "probability": 0.90673828125 }, { "start": 2275.4, "end": 2275.5, "word": " the", "probability": 0.68896484375 }, { "start": 2275.5, "end": 2275.94, "word": " words", "probability": 0.6787109375 }, { "start": 2275.94, "end": 2276.46, "word": ".", "probability": 0.5341796875 } ] }, { "id": 678, "seek": 222526, "start": 2276.68, "end": 2280.82, "text": " And they work slightly different, but let's go ahead and define them,", "tokens": [ 50814, 400, 436, 589, 4748, 819, 11, 457, 718, 311, 352, 2286, 293, 6964, 552, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.21345557260119224, "compression_ratio": 1.773076923076923, "no_speech_prob": 0.0015010833740234375, "words": [ { "start": 2276.68, "end": 2276.8, "word": " And", "probability": 0.315185546875 }, { "start": 2276.8, "end": 2277.06, "word": " they", "probability": 0.72314453125 }, { "start": 2277.06, "end": 2277.24, "word": " work", "probability": 0.76953125 }, { "start": 2277.24, "end": 2277.86, "word": " slightly", "probability": 0.7939453125 }, { "start": 2277.86, "end": 2278.28, "word": " different", "probability": 0.55419921875 }, { "start": 2278.28, "end": 2278.74, "word": ",", "probability": 0.60888671875 }, { "start": 2278.74, "end": 2279.2, "word": " but", "probability": 0.89794921875 }, { "start": 2279.2, "end": 2279.42, "word": " let's", "probability": 0.94482421875 }, { "start": 2279.42, "end": 2279.56, "word": " go", "probability": 0.9130859375 }, { "start": 2279.56, "end": 2279.7, "word": " ahead", "probability": 0.8515625 }, { "start": 2279.7, "end": 2279.8, "word": " and", "probability": 0.89892578125 }, { "start": 2279.8, "end": 2280.12, "word": " define", "probability": 0.8798828125 }, { "start": 2280.12, "end": 2280.42, "word": " them", "probability": 0.73681640625 }, { "start": 2280.42, "end": 2280.82, "word": ",", "probability": 0.2939453125 } ] }, { "id": 679, "seek": 222526, "start": 2280.82, "end": 2284.44, "text": " and we'll show you what the difference looks like.", "tokens": [ 51014, 293, 321, 603, 855, 291, 437, 264, 2649, 1542, 411, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.21345557260119224, "compression_ratio": 1.773076923076923, "no_speech_prob": 0.0015010833740234375, "words": [ { "start": 2280.82, "end": 2281.4, "word": " and", "probability": 0.89208984375 }, { "start": 2281.4, "end": 2282.4, "word": " we'll", "probability": 0.911865234375 }, { "start": 2282.4, "end": 2282.64, "word": " show", "probability": 0.8896484375 }, { "start": 2282.64, "end": 2282.82, "word": " you", "probability": 0.8935546875 }, { "start": 2282.82, "end": 2283.04, "word": " what", "probability": 0.884765625 }, { "start": 2283.04, "end": 2283.24, "word": " the", "probability": 0.81787109375 }, { "start": 2283.24, "end": 2283.56, "word": " difference", "probability": 0.724609375 }, { "start": 2283.56, "end": 2283.96, "word": " looks", "probability": 0.79296875 }, { "start": 2283.96, "end": 2284.26, "word": " like", "probability": 0.87744140625 }, { "start": 2284.26, "end": 2284.44, "word": ".", "probability": 0.986328125 } ] }, { "id": 680, "seek": 222526, "start": 2284.44, "end": 2288.14, "text": " So we're going to name this CVEC as our count vectorizer.", "tokens": [ 51214, 407, 321, 434, 516, 281, 1315, 341, 383, 7540, 34, 382, 527, 1207, 8062, 6545, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.21345557260119224, "compression_ratio": 1.773076923076923, "no_speech_prob": 0.0015010833740234375, "words": [ { "start": 2284.44, "end": 2284.6, "word": " So", "probability": 0.77001953125 }, { "start": 2284.6, "end": 2284.82, "word": " we're", "probability": 0.88037109375 }, { "start": 2284.82, "end": 2285.02, "word": " going", "probability": 0.8544921875 }, { "start": 2285.02, "end": 2285.18, "word": " to", "probability": 0.904296875 }, { "start": 2285.18, "end": 2285.36, "word": " name", "probability": 0.796875 }, { "start": 2285.36, "end": 2285.6, "word": " this", "probability": 0.876953125 }, { "start": 2285.6, "end": 2286.16, "word": " CVEC", "probability": 0.6826578776041666 }, { "start": 2286.16, "end": 2286.62, "word": " as", "probability": 0.802734375 }, { "start": 2286.62, "end": 2286.76, "word": " our", "probability": 0.81103515625 }, { "start": 2286.76, "end": 2286.94, "word": " count", "probability": 0.70703125 }, { "start": 2286.94, "end": 2287.62, "word": " vectorizer", "probability": 0.95263671875 }, { "start": 2287.62, "end": 2288.14, "word": ".", "probability": 0.6552734375 } ] }, { "id": 681, "seek": 222526, "start": 2288.46, "end": 2292.58, "text": " Count vectorizer, and the capitalizations are important.", "tokens": [ 51414, 5247, 8062, 6545, 11, 293, 264, 4238, 14455, 366, 1021, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.21345557260119224, "compression_ratio": 1.773076923076923, "no_speech_prob": 0.0015010833740234375, "words": [ { "start": 2288.46, "end": 2288.98, "word": " Count", "probability": 0.36865234375 }, { "start": 2288.98, "end": 2290.58, "word": " vectorizer", "probability": 0.8974609375 }, { "start": 2290.58, "end": 2290.66, "word": ",", "probability": 0.35205078125 }, { "start": 2290.66, "end": 2290.7, "word": " and", "probability": 0.76123046875 }, { "start": 2290.7, "end": 2290.82, "word": " the", "probability": 0.7919921875 }, { "start": 2290.82, "end": 2291.42, "word": " capitalizations", "probability": 0.927734375 }, { "start": 2291.42, "end": 2291.66, "word": " are", "probability": 0.8984375 }, { "start": 2291.66, "end": 2292.06, "word": " important", "probability": 0.7724609375 }, { "start": 2292.06, "end": 2292.58, "word": ".", "probability": 0.91455078125 } ] }, { "id": 682, "seek": 222526, "start": 2292.68, "end": 2296.5, "text": " Then we're going to use our tokenizer function above as our tokenizer function here.", "tokens": [ 51614, 1396, 321, 434, 516, 281, 764, 527, 14862, 6545, 2445, 3673, 382, 527, 14862, 6545, 2445, 510, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.21345557260119224, "compression_ratio": 1.773076923076923, "no_speech_prob": 0.0015010833740234375, "words": [ { "start": 2292.68, "end": 2292.84, "word": " Then", "probability": 0.302978515625 }, { "start": 2292.84, "end": 2292.96, "word": " we're", "probability": 0.9287109375 }, { "start": 2292.96, "end": 2293.12, "word": " going", "probability": 0.85595703125 }, { "start": 2293.12, "end": 2293.28, "word": " to", "probability": 0.904296875 }, { "start": 2293.28, "end": 2293.44, "word": " use", "probability": 0.82275390625 }, { "start": 2293.44, "end": 2293.62, "word": " our", "probability": 0.814453125 }, { "start": 2293.62, "end": 2294.1, "word": " tokenizer", "probability": 0.85107421875 }, { "start": 2294.1, "end": 2294.46, "word": " function", "probability": 0.9033203125 }, { "start": 2294.46, "end": 2294.8, "word": " above", "probability": 0.87646484375 }, { "start": 2294.8, "end": 2295.12, "word": " as", "probability": 0.83447265625 }, { "start": 2295.12, "end": 2295.26, "word": " our", "probability": 0.81591796875 }, { "start": 2295.26, "end": 2295.72, "word": " tokenizer", "probability": 0.904052734375 }, { "start": 2295.72, "end": 2296.1, "word": " function", "probability": 0.8974609375 }, { "start": 2296.1, "end": 2296.42, "word": " here", "probability": 0.80029296875 }, { "start": 2296.42, "end": 2296.5, "word": ".", "probability": 0.68701171875 } ] }, { "id": 683, "seek": 224768, "start": 2296.5, "end": 2300.84, "text": " So we're going to have tokenizer equals tokenizer.", "tokens": [ 50364, 407, 321, 434, 516, 281, 362, 14862, 6545, 6915, 14862, 6545, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.21208639442920685, "compression_ratio": 1.5328947368421053, "no_speech_prob": 0.0014104843139648438, "words": [ { "start": 2296.5, "end": 2296.62, "word": " So", "probability": 0.4375 }, { "start": 2296.62, "end": 2296.76, "word": " we're", "probability": 0.88623046875 }, { "start": 2296.76, "end": 2296.8, "word": " going", "probability": 0.521484375 }, { "start": 2296.8, "end": 2296.82, "word": " to", "probability": 0.90185546875 }, { "start": 2296.82, "end": 2297.08, "word": " have", "probability": 0.8740234375 }, { "start": 2297.08, "end": 2298.24, "word": " tokenizer", "probability": 0.76904296875 }, { "start": 2298.24, "end": 2299.12, "word": " equals", "probability": 0.654296875 }, { "start": 2299.12, "end": 2300.32, "word": " tokenizer", "probability": 0.86962890625 }, { "start": 2300.32, "end": 2300.84, "word": ".", "probability": 0.82958984375 } ] }, { "id": 684, "seek": 224768, "start": 2301.62, "end": 2302.66, "text": " Awesome.", "tokens": [ 50614, 10391, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.21208639442920685, "compression_ratio": 1.5328947368421053, "no_speech_prob": 0.0014104843139648438, "words": [ { "start": 2301.62, "end": 2302.14, "word": " Awesome", "probability": 0.8876953125 }, { "start": 2302.14, "end": 2302.66, "word": ".", "probability": 0.85400390625 } ] }, { "id": 685, "seek": 224768, "start": 2303.18, "end": 2310.98, "text": " And then we want to vectorize our words, so this is going to be saved as countX.", "tokens": [ 50714, 400, 550, 321, 528, 281, 8062, 1125, 527, 2283, 11, 370, 341, 307, 516, 281, 312, 6624, 382, 1207, 55, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.21208639442920685, "compression_ratio": 1.5328947368421053, "no_speech_prob": 0.0014104843139648438, "words": [ { "start": 2303.18, "end": 2303.7, "word": " And", "probability": 0.763671875 }, { "start": 2303.7, "end": 2303.84, "word": " then", "probability": 0.72705078125 }, { "start": 2303.84, "end": 2304.0, "word": " we", "probability": 0.8935546875 }, { "start": 2304.0, "end": 2304.24, "word": " want", "probability": 0.80810546875 }, { "start": 2304.24, "end": 2304.76, "word": " to", "probability": 0.90673828125 }, { "start": 2304.76, "end": 2306.14, "word": " vectorize", "probability": 0.885986328125 }, { "start": 2306.14, "end": 2306.4, "word": " our", "probability": 0.81689453125 }, { "start": 2306.4, "end": 2306.9, "word": " words", "probability": 0.74951171875 }, { "start": 2306.9, "end": 2307.12, "word": ",", "probability": 0.1700439453125 }, { "start": 2307.12, "end": 2307.32, "word": " so", "probability": 0.8984375 }, { "start": 2307.32, "end": 2307.5, "word": " this", "probability": 0.88232421875 }, { "start": 2307.5, "end": 2307.64, "word": " is", "probability": 0.9072265625 }, { "start": 2307.64, "end": 2307.82, "word": " going", "probability": 0.865234375 }, { "start": 2307.82, "end": 2308.02, "word": " to", "probability": 0.90673828125 }, { "start": 2308.02, "end": 2308.34, "word": " be", "probability": 0.90087890625 }, { "start": 2308.34, "end": 2308.98, "word": " saved", "probability": 0.705078125 }, { "start": 2308.98, "end": 2309.6, "word": " as", "probability": 0.90087890625 }, { "start": 2309.6, "end": 2310.6, "word": " countX", "probability": 0.529052734375 }, { "start": 2310.6, "end": 2310.98, "word": ".", "probability": 0.7099609375 } ] }, { "id": 686, "seek": 224768, "start": 2310.98, "end": 2316.5, "text": " So we're going to have count underscore capital X equals...", "tokens": [ 51064, 407, 321, 434, 516, 281, 362, 1207, 37556, 4238, 1783, 6915, 485, 51364 ], "temperature": 0.0, "avg_logprob": -0.21208639442920685, "compression_ratio": 1.5328947368421053, "no_speech_prob": 0.0014104843139648438, "words": [ { "start": 2310.98, "end": 2311.12, "word": " So", "probability": 0.8212890625 }, { "start": 2311.12, "end": 2311.24, "word": " we're", "probability": 0.921875 }, { "start": 2311.24, "end": 2311.38, "word": " going", "probability": 0.859375 }, { "start": 2311.38, "end": 2311.54, "word": " to", "probability": 0.9013671875 }, { "start": 2311.54, "end": 2311.88, "word": " have", "probability": 0.86865234375 }, { "start": 2311.88, "end": 2312.62, "word": " count", "probability": 0.7353515625 }, { "start": 2312.62, "end": 2313.44, "word": " underscore", "probability": 0.40771484375 }, { "start": 2313.44, "end": 2314.22, "word": " capital", "probability": 0.654296875 }, { "start": 2314.22, "end": 2314.74, "word": " X", "probability": 0.9716796875 }, { "start": 2314.74, "end": 2316.5, "word": " equals...", "probability": 0.416900634765625 } ] }, { "id": 687, "seek": 224768, "start": 2317.02, "end": 2318.92, "text": " Oops, did not mean to open that.", "tokens": [ 51364, 21726, 11, 630, 406, 914, 281, 1269, 300, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.21208639442920685, "compression_ratio": 1.5328947368421053, "no_speech_prob": 0.0014104843139648438, "words": [ { "start": 2317.02, "end": 2317.18, "word": " Oops", "probability": 0.468994140625 }, { "start": 2317.18, "end": 2317.4, "word": ",", "probability": 0.7392578125 }, { "start": 2317.4, "end": 2317.54, "word": " did", "probability": 0.599609375 }, { "start": 2317.54, "end": 2317.7, "word": " not", "probability": 0.9013671875 }, { "start": 2317.7, "end": 2317.86, "word": " mean", "probability": 0.89013671875 }, { "start": 2317.86, "end": 2317.96, "word": " to", "probability": 0.9013671875 }, { "start": 2317.96, "end": 2318.12, "word": " open", "probability": 0.80810546875 }, { "start": 2318.12, "end": 2318.4, "word": " that", "probability": 0.88525390625 }, { "start": 2318.4, "end": 2318.92, "word": ".", "probability": 0.84228515625 } ] }, { "id": 688, "seek": 227540, "start": 2322.86, "end": 2326.66, "text": " CVEC, our vectorizer, and then we're going to use fit transform.", "tokens": [ 50414, 383, 7540, 34, 11, 527, 8062, 6545, 11, 293, 550, 321, 434, 516, 281, 764, 3318, 4088, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.19035617702750748, "compression_ratio": 1.734463276836158, "no_speech_prob": 0.00388336181640625, "words": [ { "start": 2322.86, "end": 2323.38, "word": " CVEC", "probability": 0.6374918619791666 }, { "start": 2323.38, "end": 2323.46, "word": ",", "probability": 0.6650390625 }, { "start": 2323.46, "end": 2323.58, "word": " our", "probability": 0.80419921875 }, { "start": 2323.58, "end": 2324.1, "word": " vectorizer", "probability": 0.91064453125 }, { "start": 2324.1, "end": 2324.28, "word": ",", "probability": 0.720703125 }, { "start": 2324.28, "end": 2324.34, "word": " and", "probability": 0.88330078125 }, { "start": 2324.34, "end": 2324.44, "word": " then", "probability": 0.70947265625 }, { "start": 2324.44, "end": 2324.54, "word": " we're", "probability": 0.921875 }, { "start": 2324.54, "end": 2324.6, "word": " going", "probability": 0.71826171875 }, { "start": 2324.6, "end": 2324.68, "word": " to", "probability": 0.90625 }, { "start": 2324.68, "end": 2324.86, "word": " use", "probability": 0.810546875 }, { "start": 2324.86, "end": 2325.34, "word": " fit", "probability": 0.292724609375 }, { "start": 2325.34, "end": 2326.14, "word": " transform", "probability": 0.482666015625 }, { "start": 2326.14, "end": 2326.66, "word": ".", "probability": 0.88916015625 } ] }, { "id": 689, "seek": 227540, "start": 2327.9, "end": 2331.32, "text": " Fit is Scikit-learn's way of saying train.", "tokens": [ 50764, 29263, 307, 16942, 22681, 12, 306, 1083, 311, 636, 295, 1566, 3847, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.19035617702750748, "compression_ratio": 1.734463276836158, "no_speech_prob": 0.00388336181640625, "words": [ { "start": 2327.9, "end": 2328.42, "word": " Fit", "probability": 0.61474609375 }, { "start": 2328.42, "end": 2328.78, "word": " is", "probability": 0.890625 }, { "start": 2328.78, "end": 2329.12, "word": " Scikit", "probability": 0.6190185546875 }, { "start": 2329.12, "end": 2329.6, "word": "-learn's", "probability": 0.874267578125 }, { "start": 2329.6, "end": 2329.88, "word": " way", "probability": 0.90087890625 }, { "start": 2329.88, "end": 2330.14, "word": " of", "probability": 0.9091796875 }, { "start": 2330.14, "end": 2330.4, "word": " saying", "probability": 0.82666015625 }, { "start": 2330.4, "end": 2330.8, "word": " train", "probability": 0.55810546875 }, { "start": 2330.8, "end": 2331.32, "word": ".", "probability": 0.63525390625 } ] }, { "id": 690, "seek": 227540, "start": 2331.36, "end": 2336.0, "text": " So in this instance, we're going to train our vectorizer.", "tokens": [ 50964, 407, 294, 341, 5197, 11, 321, 434, 516, 281, 3847, 527, 8062, 6545, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.19035617702750748, "compression_ratio": 1.734463276836158, "no_speech_prob": 0.00388336181640625, "words": [ { "start": 2331.36, "end": 2331.54, "word": " So", "probability": 0.56982421875 }, { "start": 2331.54, "end": 2331.86, "word": " in", "probability": 0.79931640625 }, { "start": 2331.86, "end": 2332.08, "word": " this", "probability": 0.87890625 }, { "start": 2332.08, "end": 2332.86, "word": " instance", "probability": 0.68603515625 }, { "start": 2332.86, "end": 2332.88, "word": ",", "probability": 0.43505859375 }, { "start": 2332.88, "end": 2333.1, "word": " we're", "probability": 0.93115234375 }, { "start": 2333.1, "end": 2333.28, "word": " going", "probability": 0.85498046875 }, { "start": 2333.28, "end": 2333.5, "word": " to", "probability": 0.90087890625 }, { "start": 2333.5, "end": 2334.18, "word": " train", "probability": 0.80029296875 }, { "start": 2334.18, "end": 2334.88, "word": " our", "probability": 0.81640625 }, { "start": 2334.88, "end": 2335.48, "word": " vectorizer", "probability": 0.947265625 }, { "start": 2335.48, "end": 2336.0, "word": ".", "probability": 0.91259765625 } ] }, { "id": 691, "seek": 227540, "start": 2336.32, "end": 2342.58, "text": " So fit transform, and then our purpose, which is just our list of words.", "tokens": [ 51214, 407, 3318, 4088, 11, 293, 550, 527, 4334, 11, 597, 307, 445, 527, 1329, 295, 2283, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.19035617702750748, "compression_ratio": 1.734463276836158, "no_speech_prob": 0.00388336181640625, "words": [ { "start": 2336.32, "end": 2336.78, "word": " So", "probability": 0.86572265625 }, { "start": 2336.78, "end": 2337.0, "word": " fit", "probability": 0.76171875 }, { "start": 2337.0, "end": 2337.38, "word": " transform", "probability": 0.89794921875 }, { "start": 2337.38, "end": 2337.58, "word": ",", "probability": 0.380126953125 }, { "start": 2337.58, "end": 2337.74, "word": " and", "probability": 0.8994140625 }, { "start": 2337.74, "end": 2337.92, "word": " then", "probability": 0.73193359375 }, { "start": 2337.92, "end": 2338.44, "word": " our", "probability": 0.84033203125 }, { "start": 2338.44, "end": 2339.56, "word": " purpose", "probability": 0.53466796875 }, { "start": 2339.56, "end": 2340.4, "word": ",", "probability": 0.9052734375 }, { "start": 2340.4, "end": 2340.78, "word": " which", "probability": 0.9140625 }, { "start": 2340.78, "end": 2340.9, "word": " is", "probability": 0.90625 }, { "start": 2340.9, "end": 2341.06, "word": " just", "probability": 0.88037109375 }, { "start": 2341.06, "end": 2341.22, "word": " our", "probability": 0.80908203125 }, { "start": 2341.22, "end": 2341.5, "word": " list", "probability": 0.8857421875 }, { "start": 2341.5, "end": 2341.7, "word": " of", "probability": 0.90380859375 }, { "start": 2341.7, "end": 2342.06, "word": " words", "probability": 0.740234375 }, { "start": 2342.06, "end": 2342.58, "word": ".", "probability": 0.68212890625 } ] }, { "id": 692, "seek": 227540, "start": 2342.98, "end": 2346.64, "text": " And then we're going to do the same thing for our TF-IDF vectorizer.", "tokens": [ 51514, 400, 550, 321, 434, 516, 281, 360, 264, 912, 551, 337, 527, 40964, 12, 2777, 37, 8062, 6545, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.19035617702750748, "compression_ratio": 1.734463276836158, "no_speech_prob": 0.00388336181640625, "words": [ { "start": 2342.98, "end": 2343.24, "word": " And", "probability": 0.8173828125 }, { "start": 2343.24, "end": 2343.46, "word": " then", "probability": 0.7255859375 }, { "start": 2343.46, "end": 2343.66, "word": " we're", "probability": 0.915771484375 }, { "start": 2343.66, "end": 2343.78, "word": " going", "probability": 0.85498046875 }, { "start": 2343.78, "end": 2343.92, "word": " to", "probability": 0.90673828125 }, { "start": 2343.92, "end": 2344.04, "word": " do", "probability": 0.912109375 }, { "start": 2344.04, "end": 2344.22, "word": " the", "probability": 0.81396484375 }, { "start": 2344.22, "end": 2344.44, "word": " same", "probability": 0.8173828125 }, { "start": 2344.44, "end": 2344.74, "word": " thing", "probability": 0.8134765625 }, { "start": 2344.74, "end": 2345.12, "word": " for", "probability": 0.896484375 }, { "start": 2345.12, "end": 2345.46, "word": " our", "probability": 0.80615234375 }, { "start": 2345.46, "end": 2345.66, "word": " TF", "probability": 0.6025390625 }, { "start": 2345.66, "end": 2345.98, "word": "-IDF", "probability": 0.8447265625 }, { "start": 2345.98, "end": 2346.4, "word": " vectorizer", "probability": 0.8759765625 }, { "start": 2346.4, "end": 2346.64, "word": ".", "probability": 0.87451171875 } ] }, { "id": 693, "seek": 230222, "start": 2346.64, "end": 2350.92, "text": " So we're going to take TVEC equals TF-IDF.", "tokens": [ 50364, 407, 321, 434, 516, 281, 747, 314, 7540, 34, 6915, 40964, 12, 2777, 37, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.24903846153846154, "compression_ratio": 1.3669064748201438, "no_speech_prob": 0.1710205078125, "words": [ { "start": 2346.64, "end": 2346.64, "word": " So", "probability": 0.093994140625 }, { "start": 2346.64, "end": 2346.68, "word": " we're", "probability": 0.487548828125 }, { "start": 2346.68, "end": 2346.74, "word": " going", "probability": 0.34912109375 }, { "start": 2346.74, "end": 2346.74, "word": " to", "probability": 0.8828125 }, { "start": 2346.74, "end": 2346.9, "word": " take", "probability": 0.4658203125 }, { "start": 2346.9, "end": 2347.92, "word": " TVEC", "probability": 0.597900390625 }, { "start": 2347.92, "end": 2348.68, "word": " equals", "probability": 0.49658203125 }, { "start": 2348.68, "end": 2349.84, "word": " TF", "probability": 0.7138671875 }, { "start": 2349.84, "end": 2350.68, "word": "-IDF", "probability": 0.7256673177083334 }, { "start": 2350.68, "end": 2350.92, "word": ".", "probability": 0.1932373046875 } ] }, { "id": 694, "seek": 230222, "start": 2351.46, "end": 2354.42, "text": " Vectorizer and capitalization is important.", "tokens": [ 50614, 691, 20814, 6545, 293, 4238, 2144, 307, 1021, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.24903846153846154, "compression_ratio": 1.3669064748201438, "no_speech_prob": 0.1710205078125, "words": [ { "start": 2351.46, "end": 2352.06, "word": " Vectorizer", "probability": 0.9025065104166666 }, { "start": 2352.06, "end": 2352.28, "word": " and", "probability": 0.5166015625 }, { "start": 2352.28, "end": 2352.84, "word": " capitalization", "probability": 0.941650390625 }, { "start": 2352.84, "end": 2353.14, "word": " is", "probability": 0.88525390625 }, { "start": 2353.14, "end": 2353.54, "word": " important", "probability": 0.76953125 }, { "start": 2353.54, "end": 2354.42, "word": ".", "probability": 0.9638671875 } ] }, { "id": 695, "seek": 230222, "start": 2354.42, "end": 2357.72, "text": " Tokenizer equals tokenizer.", "tokens": [ 50764, 314, 8406, 6545, 6915, 14862, 6545, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.24903846153846154, "compression_ratio": 1.3669064748201438, "no_speech_prob": 0.1710205078125, "words": [ { "start": 2354.42, "end": 2354.94, "word": " Tokenizer", "probability": 0.9401041666666666 }, { "start": 2354.94, "end": 2355.72, "word": " equals", "probability": 0.8486328125 }, { "start": 2355.72, "end": 2357.12, "word": " tokenizer", "probability": 0.7626953125 }, { "start": 2357.12, "end": 2357.72, "word": ".", "probability": 0.69140625 } ] }, { "id": 696, "seek": 230222, "start": 2357.72, "end": 2371.28, "text": " And then our TF-IDF X capital X equals TVEC dot fit transform corpus.", "tokens": [ 50914, 400, 550, 527, 40964, 12, 2777, 37, 1783, 4238, 1783, 6915, 314, 7540, 34, 5893, 3318, 4088, 1181, 31624, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.24903846153846154, "compression_ratio": 1.3669064748201438, "no_speech_prob": 0.1710205078125, "words": [ { "start": 2357.72, "end": 2357.74, "word": " And", "probability": 0.80224609375 }, { "start": 2357.74, "end": 2358.0, "word": " then", "probability": 0.74755859375 }, { "start": 2358.0, "end": 2358.58, "word": " our", "probability": 0.7890625 }, { "start": 2358.58, "end": 2359.9, "word": " TF", "probability": 0.88525390625 }, { "start": 2359.9, "end": 2360.66, "word": "-IDF", "probability": 0.97412109375 }, { "start": 2360.66, "end": 2361.32, "word": " X", "probability": 0.359130859375 }, { "start": 2361.32, "end": 2361.76, "word": " capital", "probability": 0.298828125 }, { "start": 2361.76, "end": 2362.22, "word": " X", "probability": 0.9814453125 }, { "start": 2362.22, "end": 2362.82, "word": " equals", "probability": 0.8515625 }, { "start": 2362.82, "end": 2364.28, "word": " TVEC", "probability": 0.8313802083333334 }, { "start": 2364.28, "end": 2365.4, "word": " dot", "probability": 0.53076171875 }, { "start": 2365.4, "end": 2366.0, "word": " fit", "probability": 0.57373046875 }, { "start": 2366.0, "end": 2367.84, "word": " transform", "probability": 0.70068359375 }, { "start": 2367.84, "end": 2370.08, "word": " corpus", "probability": 0.73388671875 }, { "start": 2370.08, "end": 2371.28, "word": ".", "probability": 0.93896484375 } ] }, { "id": 697, "seek": 230222, "start": 2372.18, "end": 2373.46, "text": " Cool.", "tokens": [ 51664, 8561, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.24903846153846154, "compression_ratio": 1.3669064748201438, "no_speech_prob": 0.1710205078125, "words": [ { "start": 2372.18, "end": 2372.96, "word": " Cool", "probability": 0.732421875 }, { "start": 2372.96, "end": 2373.46, "word": ".", "probability": 0.6474609375 } ] }, { "id": 698, "seek": 233058, "start": 2373.46, "end": 2377.52, "text": " So I'm going to let that sit there for a second while you guys are typing in.", "tokens": [ 50364, 407, 286, 478, 516, 281, 718, 300, 1394, 456, 337, 257, 1150, 1339, 291, 1074, 366, 18444, 294, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.19015067629516125, "compression_ratio": 1.7966101694915255, "no_speech_prob": 0.048858642578125, "words": [ { "start": 2373.46, "end": 2373.6, "word": " So", "probability": 0.2060546875 }, { "start": 2373.6, "end": 2373.7, "word": " I'm", "probability": 0.802734375 }, { "start": 2373.7, "end": 2373.76, "word": " going", "probability": 0.5810546875 }, { "start": 2373.76, "end": 2373.76, "word": " to", "probability": 0.89794921875 }, { "start": 2373.76, "end": 2373.86, "word": " let", "probability": 0.880859375 }, { "start": 2373.86, "end": 2374.04, "word": " that", "probability": 0.86083984375 }, { "start": 2374.04, "end": 2374.18, "word": " sit", "probability": 0.87109375 }, { "start": 2374.18, "end": 2374.34, "word": " there", "probability": 0.82861328125 }, { "start": 2374.34, "end": 2374.44, "word": " for", "probability": 0.884765625 }, { "start": 2374.56, "end": 2374.8, "word": " a second", "probability": 0.779296875 }, { "start": 2374.8, "end": 2375.18, "word": " while", "probability": 0.8115234375 }, { "start": 2375.18, "end": 2375.58, "word": " you", "probability": 0.88623046875 }, { "start": 2375.58, "end": 2375.8, "word": " guys", "probability": 0.8671875 }, { "start": 2375.8, "end": 2376.14, "word": " are", "probability": 0.8994140625 }, { "start": 2376.14, "end": 2376.6, "word": " typing", "probability": 0.73095703125 }, { "start": 2376.6, "end": 2377.04, "word": " in", "probability": 0.8935546875 }, { "start": 2377.04, "end": 2377.52, "word": ".", "probability": 0.6796875 } ] }, { "id": 699, "seek": 233058, "start": 2383.58, "end": 2386.0, "text": " And then I'm going to go ahead and run it.", "tokens": [ 50614, 400, 550, 286, 478, 516, 281, 352, 2286, 293, 1190, 309, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.19015067629516125, "compression_ratio": 1.7966101694915255, "no_speech_prob": 0.048858642578125, "words": [ { "start": 2383.58, "end": 2383.94, "word": " And", "probability": 0.474609375 }, { "start": 2383.94, "end": 2384.04, "word": " then", "probability": 0.62255859375 }, { "start": 2384.04, "end": 2384.16, "word": " I'm", "probability": 0.97216796875 }, { "start": 2384.16, "end": 2384.2, "word": " going", "probability": 0.78271484375 }, { "start": 2384.2, "end": 2384.22, "word": " to", "probability": 0.9033203125 }, { "start": 2384.22, "end": 2384.34, "word": " go", "probability": 0.89453125 }, { "start": 2384.34, "end": 2384.58, "word": " ahead", "probability": 0.86328125 }, { "start": 2384.58, "end": 2384.9, "word": " and", "probability": 0.89697265625 }, { "start": 2384.9, "end": 2385.22, "word": " run", "probability": 0.90478515625 }, { "start": 2385.22, "end": 2385.52, "word": " it", "probability": 0.90869140625 }, { "start": 2385.52, "end": 2386.0, "word": ".", "probability": 0.93310546875 } ] }, { "id": 700, "seek": 233058, "start": 2386.6, "end": 2396.38, "text": " So this takes about a minute because what it's doing is it is counting all of the words across all of the emails, the ham emails and the spam emails.", "tokens": [ 50764, 407, 341, 2516, 466, 257, 3456, 570, 437, 309, 311, 884, 307, 309, 307, 13251, 439, 295, 264, 2283, 2108, 439, 295, 264, 12524, 11, 264, 7852, 12524, 293, 264, 24028, 12524, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.19015067629516125, "compression_ratio": 1.7966101694915255, "no_speech_prob": 0.048858642578125, "words": [ { "start": 2386.6, "end": 2387.08, "word": " So", "probability": 0.775390625 }, { "start": 2387.08, "end": 2387.48, "word": " this", "probability": 0.71142578125 }, { "start": 2387.48, "end": 2387.64, "word": " takes", "probability": 0.7509765625 }, { "start": 2387.64, "end": 2387.8, "word": " about", "probability": 0.82763671875 }, { "start": 2388.0, "end": 2388.18, "word": " a minute", "probability": 0.880859375 }, { "start": 2388.18, "end": 2388.56, "word": " because", "probability": 0.60205078125 }, { "start": 2388.56, "end": 2388.8, "word": " what", "probability": 0.8701171875 }, { "start": 2388.8, "end": 2388.96, "word": " it's", "probability": 0.933349609375 }, { "start": 2388.96, "end": 2389.2, "word": " doing", "probability": 0.9130859375 }, { "start": 2389.2, "end": 2389.48, "word": " is", "probability": 0.88134765625 }, { "start": 2389.48, "end": 2389.62, "word": " it", "probability": 0.83642578125 }, { "start": 2389.62, "end": 2389.86, "word": " is", "probability": 0.86474609375 }, { "start": 2389.86, "end": 2390.16, "word": " counting", "probability": 0.7646484375 }, { "start": 2390.16, "end": 2390.74, "word": " all", "probability": 0.90234375 }, { "start": 2390.74, "end": 2390.88, "word": " of", "probability": 0.8984375 }, { "start": 2390.88, "end": 2391.04, "word": " the", "probability": 0.81396484375 }, { "start": 2391.04, "end": 2391.52, "word": " words", "probability": 0.67626953125 }, { "start": 2391.52, "end": 2392.9, "word": " across", "probability": 0.64892578125 }, { "start": 2392.9, "end": 2393.28, "word": " all", "probability": 0.90283203125 }, { "start": 2393.28, "end": 2393.4, "word": " of", "probability": 0.89697265625 }, { "start": 2393.4, "end": 2393.52, "word": " the", "probability": 0.81103515625 }, { "start": 2393.52, "end": 2393.84, "word": " emails", "probability": 0.76953125 }, { "start": 2393.84, "end": 2394.02, "word": ",", "probability": 0.634765625 }, { "start": 2394.02, "end": 2394.14, "word": " the", "probability": 0.8125 }, { "start": 2394.14, "end": 2394.34, "word": " ham", "probability": 0.55517578125 }, { "start": 2394.34, "end": 2394.7, "word": " emails", "probability": 0.7890625 }, { "start": 2394.7, "end": 2394.96, "word": " and", "probability": 0.81494140625 }, { "start": 2394.96, "end": 2395.1, "word": " the", "probability": 0.79443359375 }, { "start": 2395.1, "end": 2395.36, "word": " spam", "probability": 0.95703125 }, { "start": 2395.36, "end": 2395.9, "word": " emails", "probability": 0.8076171875 }, { "start": 2395.9, "end": 2396.38, "word": ".", "probability": 0.85791015625 } ] }, { "id": 701, "seek": 233058, "start": 2396.66, "end": 2406.46, "text": " And so as it's counting each of these words, it's applying a word count for the count vectorizer, and then it applies a weight for the TF-IDF vectorizer.", "tokens": [ 51264, 400, 370, 382, 309, 311, 13251, 1184, 295, 613, 2283, 11, 309, 311, 9275, 257, 1349, 1207, 337, 264, 1207, 8062, 6545, 11, 293, 550, 309, 13165, 257, 3364, 337, 264, 40964, 12, 2777, 37, 8062, 6545, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.19015067629516125, "compression_ratio": 1.7966101694915255, "no_speech_prob": 0.048858642578125, "words": [ { "start": 2396.66, "end": 2396.9, "word": " And", "probability": 0.84814453125 }, { "start": 2396.9, "end": 2397.16, "word": " so", "probability": 0.89990234375 }, { "start": 2397.16, "end": 2397.44, "word": " as", "probability": 0.802734375 }, { "start": 2397.44, "end": 2397.58, "word": " it's", "probability": 0.936767578125 }, { "start": 2397.58, "end": 2397.8, "word": " counting", "probability": 0.74853515625 }, { "start": 2397.8, "end": 2398.04, "word": " each", "probability": 0.84814453125 }, { "start": 2398.04, "end": 2398.12, "word": " of", "probability": 0.90625 }, { "start": 2398.12, "end": 2398.26, "word": " these", "probability": 0.6982421875 }, { "start": 2398.26, "end": 2398.66, "word": " words", "probability": 0.724609375 }, { "start": 2398.66, "end": 2398.76, "word": ",", "probability": 0.83642578125 }, { "start": 2398.76, "end": 2399.06, "word": " it's", "probability": 0.947265625 }, { "start": 2399.06, "end": 2399.54, "word": " applying", "probability": 0.74072265625 }, { "start": 2399.94, "end": 2400.16, "word": " a word", "probability": 0.794921875 }, { "start": 2400.16, "end": 2400.38, "word": " count", "probability": 0.7841796875 }, { "start": 2400.38, "end": 2400.56, "word": " for", "probability": 0.8955078125 }, { "start": 2400.56, "end": 2400.68, "word": " the", "probability": 0.81298828125 }, { "start": 2400.68, "end": 2400.86, "word": " count", "probability": 0.71728515625 }, { "start": 2400.86, "end": 2401.38, "word": " vectorizer", "probability": 0.92822265625 }, { "start": 2401.38, "end": 2401.62, "word": ",", "probability": 0.367919921875 }, { "start": 2401.62, "end": 2402.06, "word": " and", "probability": 0.888671875 }, { "start": 2402.06, "end": 2402.26, "word": " then", "probability": 0.73876953125 }, { "start": 2402.26, "end": 2402.68, "word": " it", "probability": 0.89306640625 }, { "start": 2402.68, "end": 2403.32, "word": " applies", "probability": 0.775390625 }, { "start": 2403.78, "end": 2404.3, "word": " a weight", "probability": 0.73046875 }, { "start": 2404.3, "end": 2404.52, "word": " for", "probability": 0.89501953125 }, { "start": 2404.52, "end": 2404.66, "word": " the", "probability": 0.81005859375 }, { "start": 2404.66, "end": 2404.96, "word": " TF", "probability": 0.45263671875 }, { "start": 2404.96, "end": 2405.44, "word": "-IDF", "probability": 0.8092447916666666 }, { "start": 2405.44, "end": 2406.14, "word": " vectorizer", "probability": 0.936767578125 }, { "start": 2406.14, "end": 2406.46, "word": ".", "probability": 0.440673828125 } ] }, { "id": 702, "seek": 235882, "start": 2406.46, "end": 2408.9, "text": " And the weight takes all the words into account.", "tokens": [ 50364, 400, 264, 3364, 2516, 439, 264, 2283, 666, 2696, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.1669100497927621, "compression_ratio": 1.5691056910569106, "no_speech_prob": 0.07476806640625, "words": [ { "start": 2406.46, "end": 2406.66, "word": " And", "probability": 0.1038818359375 }, { "start": 2406.66, "end": 2406.78, "word": " the", "probability": 0.75830078125 }, { "start": 2406.78, "end": 2407.02, "word": " weight", "probability": 0.04718017578125 }, { "start": 2407.02, "end": 2407.36, "word": " takes", "probability": 0.73876953125 }, { "start": 2407.36, "end": 2407.56, "word": " all", "probability": 0.8896484375 }, { "start": 2407.56, "end": 2407.72, "word": " the", "probability": 0.70849609375 }, { "start": 2407.72, "end": 2407.94, "word": " words", "probability": 0.71142578125 }, { "start": 2407.94, "end": 2408.08, "word": " into", "probability": 0.71142578125 }, { "start": 2408.08, "end": 2408.48, "word": " account", "probability": 0.7802734375 }, { "start": 2408.48, "end": 2408.9, "word": ".", "probability": 0.61767578125 } ] }, { "id": 703, "seek": 235882, "start": 2408.9, "end": 2410.62, "text": " So it becomes a whole process.", "tokens": [ 50464, 407, 309, 3643, 257, 1379, 1399, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.1669100497927621, "compression_ratio": 1.5691056910569106, "no_speech_prob": 0.07476806640625, "words": [ { "start": 2408.9, "end": 2408.92, "word": " So", "probability": 0.73828125 }, { "start": 2408.92, "end": 2409.18, "word": " it", "probability": 0.8046875 }, { "start": 2409.18, "end": 2409.56, "word": " becomes", "probability": 0.8212890625 }, { "start": 2409.7, "end": 2409.84, "word": " a whole", "probability": 0.7958984375 }, { "start": 2409.84, "end": 2410.32, "word": " process", "probability": 0.87890625 }, { "start": 2410.32, "end": 2410.62, "word": ".", "probability": 0.61083984375 } ] }, { "id": 704, "seek": 235882, "start": 2410.62, "end": 2415.72, "text": " But this takes about 60 to 120 seconds.", "tokens": [ 50564, 583, 341, 2516, 466, 4060, 281, 10411, 3949, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.1669100497927621, "compression_ratio": 1.5691056910569106, "no_speech_prob": 0.07476806640625, "words": [ { "start": 2410.62, "end": 2410.64, "word": " But", "probability": 0.6376953125 }, { "start": 2410.64, "end": 2410.86, "word": " this", "probability": 0.83837890625 }, { "start": 2410.86, "end": 2411.06, "word": " takes", "probability": 0.76953125 }, { "start": 2411.06, "end": 2411.48, "word": " about", "probability": 0.822265625 }, { "start": 2411.48, "end": 2413.4, "word": " 60", "probability": 0.75732421875 }, { "start": 2413.4, "end": 2413.98, "word": " to", "probability": 0.830078125 }, { "start": 2413.98, "end": 2414.66, "word": " 120", "probability": 0.89208984375 }, { "start": 2414.66, "end": 2415.2, "word": " seconds", "probability": 0.7265625 }, { "start": 2415.2, "end": 2415.72, "word": ".", "probability": 0.77880859375 } ] }, { "id": 705, "seek": 235882, "start": 2415.96, "end": 2418.52, "text": " So we'll go ahead and let that run.", "tokens": [ 50814, 407, 321, 603, 352, 2286, 293, 718, 300, 1190, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.1669100497927621, "compression_ratio": 1.5691056910569106, "no_speech_prob": 0.07476806640625, "words": [ { "start": 2415.96, "end": 2416.3, "word": " So", "probability": 0.84716796875 }, { "start": 2416.3, "end": 2416.44, "word": " we'll", "probability": 0.915283203125 }, { "start": 2416.44, "end": 2416.58, "word": " go", "probability": 0.9052734375 }, { "start": 2416.58, "end": 2416.92, "word": " ahead", "probability": 0.8505859375 }, { "start": 2416.92, "end": 2417.18, "word": " and", "probability": 0.89453125 }, { "start": 2417.18, "end": 2417.4, "word": " let", "probability": 0.8984375 }, { "start": 2417.4, "end": 2417.66, "word": " that", "probability": 0.88623046875 }, { "start": 2417.66, "end": 2418.0, "word": " run", "probability": 0.89990234375 }, { "start": 2418.0, "end": 2418.52, "word": ".", "probability": 0.91064453125 } ] }, { "id": 706, "seek": 235882, "start": 2418.6, "end": 2427.32, "text": " While that's running, we're just going to get started on task 3A, which is just to print each token from the test email.", "tokens": [ 50964, 3987, 300, 311, 2614, 11, 321, 434, 445, 516, 281, 483, 1409, 322, 5633, 805, 32, 11, 597, 307, 445, 281, 4482, 1184, 14862, 490, 264, 1500, 3796, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.1669100497927621, "compression_ratio": 1.5691056910569106, "no_speech_prob": 0.07476806640625, "words": [ { "start": 2418.6, "end": 2419.04, "word": " While", "probability": 0.8115234375 }, { "start": 2419.04, "end": 2419.42, "word": " that's", "probability": 0.93798828125 }, { "start": 2419.42, "end": 2419.76, "word": " running", "probability": 0.876953125 }, { "start": 2419.76, "end": 2419.96, "word": ",", "probability": 0.78076171875 }, { "start": 2419.96, "end": 2420.1, "word": " we're", "probability": 0.913330078125 }, { "start": 2420.1, "end": 2420.26, "word": " just", "probability": 0.87744140625 }, { "start": 2420.26, "end": 2420.48, "word": " going", "probability": 0.85888671875 }, { "start": 2420.48, "end": 2420.84, "word": " to", "probability": 0.90380859375 }, { "start": 2420.84, "end": 2421.6, "word": " get", "probability": 0.88818359375 }, { "start": 2421.6, "end": 2422.1, "word": " started", "probability": 0.80712890625 }, { "start": 2422.1, "end": 2422.72, "word": " on", "probability": 0.9052734375 }, { "start": 2422.72, "end": 2423.08, "word": " task", "probability": 0.61962890625 }, { "start": 2423.08, "end": 2423.72, "word": " 3A", "probability": 0.73779296875 }, { "start": 2423.72, "end": 2423.92, "word": ",", "probability": 0.75634765625 }, { "start": 2423.92, "end": 2424.1, "word": " which", "probability": 0.92578125 }, { "start": 2424.1, "end": 2424.24, "word": " is", "probability": 0.9091796875 }, { "start": 2424.24, "end": 2424.44, "word": " just", "probability": 0.853515625 }, { "start": 2424.44, "end": 2424.68, "word": " to", "probability": 0.9072265625 }, { "start": 2424.68, "end": 2425.1, "word": " print", "probability": 0.853515625 }, { "start": 2425.1, "end": 2425.42, "word": " each", "probability": 0.84912109375 }, { "start": 2425.42, "end": 2425.76, "word": " token", "probability": 0.82861328125 }, { "start": 2425.76, "end": 2426.02, "word": " from", "probability": 0.8173828125 }, { "start": 2426.02, "end": 2426.16, "word": " the", "probability": 0.81591796875 }, { "start": 2426.16, "end": 2426.42, "word": " test", "probability": 0.81787109375 }, { "start": 2426.42, "end": 2426.8, "word": " email", "probability": 0.87109375 }, { "start": 2426.8, "end": 2427.32, "word": ".", "probability": 0.994140625 } ] }, { "id": 707, "seek": 235882, "start": 2427.84, "end": 2429.46, "text": " Now this one can be a little tricky.", "tokens": [ 51414, 823, 341, 472, 393, 312, 257, 707, 12414, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.1669100497927621, "compression_ratio": 1.5691056910569106, "no_speech_prob": 0.07476806640625, "words": [ { "start": 2427.84, "end": 2428.28, "word": " Now", "probability": 0.8798828125 }, { "start": 2428.28, "end": 2428.4, "word": " this", "probability": 0.5615234375 }, { "start": 2428.4, "end": 2428.52, "word": " one", "probability": 0.80810546875 }, { "start": 2428.52, "end": 2428.64, "word": " can", "probability": 0.890625 }, { "start": 2428.64, "end": 2428.74, "word": " be", "probability": 0.904296875 }, { "start": 2428.84, "end": 2428.94, "word": " a little", "probability": 0.802734375 }, { "start": 2428.94, "end": 2429.26, "word": " tricky", "probability": 0.7587890625 }, { "start": 2429.26, "end": 2429.46, "word": ".", "probability": 0.708984375 } ] }, { "id": 708, "seek": 235882, "start": 2429.46, "end": 2434.7, "text": " So there's a bit of a trick to identify the unique words and the counts.", "tokens": [ 51514, 407, 456, 311, 257, 857, 295, 257, 4282, 281, 5876, 264, 3845, 2283, 293, 264, 14893, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.1669100497927621, "compression_ratio": 1.5691056910569106, "no_speech_prob": 0.07476806640625, "words": [ { "start": 2429.46, "end": 2429.66, "word": " So", "probability": 0.86865234375 }, { "start": 2429.66, "end": 2429.98, "word": " there's", "probability": 0.916748046875 }, { "start": 2430.08, "end": 2430.16, "word": " a bit", "probability": 0.89990234375 }, { "start": 2430.16, "end": 2430.26, "word": " of", "probability": 0.904296875 }, { "start": 2430.62, "end": 2431.14, "word": " a trick", "probability": 0.8564453125 }, { "start": 2431.14, "end": 2431.82, "word": " to", "probability": 0.89892578125 }, { "start": 2431.82, "end": 2432.4, "word": " identify", "probability": 0.90576171875 }, { "start": 2432.4, "end": 2432.64, "word": " the", "probability": 0.81103515625 }, { "start": 2432.64, "end": 2432.96, "word": " unique", "probability": 0.77001953125 }, { "start": 2432.96, "end": 2433.38, "word": " words", "probability": 0.7646484375 }, { "start": 2433.38, "end": 2433.58, "word": " and", "probability": 0.87646484375 }, { "start": 2433.58, "end": 2433.74, "word": " the", "probability": 0.65869140625 }, { "start": 2433.74, "end": 2434.18, "word": " counts", "probability": 0.78466796875 }, { "start": 2434.18, "end": 2434.7, "word": ".", "probability": 0.9775390625 } ] }, { "id": 709, "seek": 238540, "start": 2434.7, "end": 2439.8, "text": " So what we're going to do is create a list of dictionary keys.", "tokens": [ 50364, 407, 437, 321, 434, 516, 281, 360, 307, 1884, 257, 1329, 295, 25890, 9317, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.20126487598532722, "compression_ratio": 1.6141304347826086, "no_speech_prob": 0.006290435791015625, "words": [ { "start": 2434.7, "end": 2435.1, "word": " So", "probability": 0.477294921875 }, { "start": 2435.1, "end": 2435.2, "word": " what", "probability": 0.7744140625 }, { "start": 2435.2, "end": 2435.32, "word": " we're", "probability": 0.902099609375 }, { "start": 2435.32, "end": 2435.42, "word": " going", "probability": 0.46044921875 }, { "start": 2435.42, "end": 2435.46, "word": " to", "probability": 0.908203125 }, { "start": 2435.46, "end": 2435.7, "word": " do", "probability": 0.91259765625 }, { "start": 2435.7, "end": 2436.1, "word": " is", "probability": 0.8935546875 }, { "start": 2436.1, "end": 2436.46, "word": " create", "probability": 0.802734375 }, { "start": 2436.74, "end": 2437.22, "word": " a list", "probability": 0.89208984375 }, { "start": 2437.22, "end": 2437.76, "word": " of", "probability": 0.8984375 }, { "start": 2437.76, "end": 2438.66, "word": " dictionary", "probability": 0.7734375 }, { "start": 2438.66, "end": 2439.14, "word": " keys", "probability": 0.78759765625 }, { "start": 2439.14, "end": 2439.8, "word": ".", "probability": 0.7265625 } ] }, { "id": 710, "seek": 238540, "start": 2439.8, "end": 2447.1, "text": " So what that's going to look like is for i in list dict from keys.", "tokens": [ 50614, 407, 437, 300, 311, 516, 281, 574, 411, 307, 337, 741, 294, 1329, 12569, 490, 9317, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.20126487598532722, "compression_ratio": 1.6141304347826086, "no_speech_prob": 0.006290435791015625, "words": [ { "start": 2439.8, "end": 2439.84, "word": " So", "probability": 0.787109375 }, { "start": 2439.84, "end": 2439.94, "word": " what", "probability": 0.83984375 }, { "start": 2439.94, "end": 2440.12, "word": " that's", "probability": 0.919921875 }, { "start": 2440.12, "end": 2440.22, "word": " going", "probability": 0.80615234375 }, { "start": 2440.22, "end": 2440.28, "word": " to", "probability": 0.90771484375 }, { "start": 2440.28, "end": 2440.4, "word": " look", "probability": 0.9140625 }, { "start": 2440.4, "end": 2440.62, "word": " like", "probability": 0.87548828125 }, { "start": 2440.62, "end": 2440.96, "word": " is", "probability": 0.89892578125 }, { "start": 2440.96, "end": 2441.34, "word": " for", "probability": 0.351318359375 }, { "start": 2441.34, "end": 2441.84, "word": " i", "probability": 0.70556640625 }, { "start": 2441.84, "end": 2442.76, "word": " in", "probability": 0.85693359375 }, { "start": 2442.76, "end": 2443.48, "word": " list", "probability": 0.7734375 }, { "start": 2443.48, "end": 2444.52, "word": " dict", "probability": 0.47265625 }, { "start": 2444.52, "end": 2445.76, "word": " from", "probability": 0.63818359375 }, { "start": 2445.76, "end": 2446.42, "word": " keys", "probability": 0.7705078125 }, { "start": 2446.42, "end": 2447.1, "word": ".", "probability": 0.5322265625 } ] }, { "id": 711, "seek": 238540, "start": 2448.48, "end": 2455.44, "text": " Tokenized email was defined above, and what that is is the tokenized version of our test email.", "tokens": [ 51064, 314, 8406, 1602, 3796, 390, 7642, 3673, 11, 293, 437, 300, 307, 307, 264, 14862, 1602, 3037, 295, 527, 1500, 3796, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.20126487598532722, "compression_ratio": 1.6141304347826086, "no_speech_prob": 0.006290435791015625, "words": [ { "start": 2448.48, "end": 2449.1, "word": " Tokenized", "probability": 0.8797200520833334 }, { "start": 2449.1, "end": 2449.46, "word": " email", "probability": 0.8544921875 }, { "start": 2449.46, "end": 2449.96, "word": " was", "probability": 0.89453125 }, { "start": 2449.96, "end": 2450.58, "word": " defined", "probability": 0.748046875 }, { "start": 2450.58, "end": 2451.42, "word": " above", "probability": 0.88134765625 }, { "start": 2451.42, "end": 2451.7, "word": ",", "probability": 0.359619140625 }, { "start": 2451.7, "end": 2451.8, "word": " and", "probability": 0.89208984375 }, { "start": 2451.8, "end": 2451.98, "word": " what", "probability": 0.86474609375 }, { "start": 2451.98, "end": 2452.16, "word": " that", "probability": 0.8779296875 }, { "start": 2452.16, "end": 2452.32, "word": " is", "probability": 0.90869140625 }, { "start": 2452.32, "end": 2452.44, "word": " is", "probability": 0.6201171875 }, { "start": 2452.44, "end": 2452.62, "word": " the", "probability": 0.8017578125 }, { "start": 2452.62, "end": 2453.14, "word": " tokenized", "probability": 0.886962890625 }, { "start": 2453.14, "end": 2453.5, "word": " version", "probability": 0.72021484375 }, { "start": 2453.5, "end": 2453.86, "word": " of", "probability": 0.9111328125 }, { "start": 2453.86, "end": 2454.04, "word": " our", "probability": 0.82373046875 }, { "start": 2454.04, "end": 2454.4, "word": " test", "probability": 0.82568359375 }, { "start": 2454.4, "end": 2454.76, "word": " email", "probability": 0.91943359375 }, { "start": 2454.76, "end": 2455.44, "word": ".", "probability": 0.96337890625 } ] }, { "id": 712, "seek": 238540, "start": 2455.82, "end": 2457.9, "text": " So we're going to go ahead and print.", "tokens": [ 51414, 407, 321, 434, 516, 281, 352, 2286, 293, 4482, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.20126487598532722, "compression_ratio": 1.6141304347826086, "no_speech_prob": 0.006290435791015625, "words": [ { "start": 2455.82, "end": 2456.12, "word": " So", "probability": 0.8681640625 }, { "start": 2456.12, "end": 2456.22, "word": " we're", "probability": 0.923583984375 }, { "start": 2456.22, "end": 2456.28, "word": " going", "probability": 0.8076171875 }, { "start": 2456.28, "end": 2456.32, "word": " to", "probability": 0.904296875 }, { "start": 2456.32, "end": 2456.44, "word": " go", "probability": 0.9013671875 }, { "start": 2456.44, "end": 2456.62, "word": " ahead", "probability": 0.849609375 }, { "start": 2456.62, "end": 2456.76, "word": " and", "probability": 0.8896484375 }, { "start": 2456.76, "end": 2457.22, "word": " print", "probability": 0.87060546875 }, { "start": 2457.22, "end": 2457.9, "word": ".", "probability": 0.5283203125 } ] }, { "id": 713, "seek": 238540, "start": 2458.48, "end": 2461.28, "text": " I'm just using the Python format.", "tokens": [ 51564, 286, 478, 445, 1228, 264, 15329, 7877, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.20126487598532722, "compression_ratio": 1.6141304347826086, "no_speech_prob": 0.006290435791015625, "words": [ { "start": 2458.48, "end": 2459.1, "word": " I'm", "probability": 0.860595703125 }, { "start": 2459.1, "end": 2459.22, "word": " just", "probability": 0.88623046875 }, { "start": 2459.22, "end": 2459.42, "word": " using", "probability": 0.8056640625 }, { "start": 2459.42, "end": 2459.6, "word": " the", "probability": 0.80517578125 }, { "start": 2459.6, "end": 2459.9, "word": " Python", "probability": 0.857421875 }, { "start": 2459.9, "end": 2460.6, "word": " format", "probability": 0.72509765625 }, { "start": 2460.6, "end": 2461.28, "word": ".", "probability": 0.9560546875 } ] }, { "id": 714, "seek": 241284, "start": 2464.22, "end": 2472.52, "text": " Tokenized email dot count of each word, and then the word in the tokenized email.", "tokens": [ 50414, 314, 8406, 1602, 3796, 5893, 1207, 295, 1184, 1349, 11, 293, 550, 264, 1349, 294, 264, 14862, 1602, 3796, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.22631047874368648, "compression_ratio": 1.6464646464646464, "no_speech_prob": 0.05499267578125, "words": [ { "start": 2464.22, "end": 2464.66, "word": " Tokenized", "probability": 0.6386311848958334 }, { "start": 2464.66, "end": 2465.06, "word": " email", "probability": 0.52392578125 }, { "start": 2465.06, "end": 2465.48, "word": " dot", "probability": 0.46142578125 }, { "start": 2465.48, "end": 2466.14, "word": " count", "probability": 0.7294921875 }, { "start": 2466.14, "end": 2466.54, "word": " of", "probability": 0.89306640625 }, { "start": 2466.54, "end": 2466.76, "word": " each", "probability": 0.86279296875 }, { "start": 2466.76, "end": 2467.12, "word": " word", "probability": 0.79541015625 }, { "start": 2467.12, "end": 2467.3, "word": ",", "probability": 0.279541015625 }, { "start": 2467.3, "end": 2467.36, "word": " and", "probability": 0.88330078125 }, { "start": 2467.36, "end": 2467.7, "word": " then", "probability": 0.71826171875 }, { "start": 2467.7, "end": 2469.08, "word": " the", "probability": 0.7353515625 }, { "start": 2469.08, "end": 2470.74, "word": " word", "probability": 0.79736328125 }, { "start": 2470.74, "end": 2471.08, "word": " in", "probability": 0.90234375 }, { "start": 2471.08, "end": 2471.22, "word": " the", "probability": 0.8017578125 }, { "start": 2471.22, "end": 2471.7, "word": " tokenized", "probability": 0.901611328125 }, { "start": 2471.7, "end": 2472.08, "word": " email", "probability": 0.9033203125 }, { "start": 2472.08, "end": 2472.52, "word": ".", "probability": 0.94189453125 } ] }, { "id": 715, "seek": 241284, "start": 2472.88, "end": 2476.22, "text": " So I'm going to verify vectorizing is complete.", "tokens": [ 50914, 407, 286, 478, 516, 281, 16888, 8062, 3319, 307, 3566, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.22631047874368648, "compression_ratio": 1.6464646464646464, "no_speech_prob": 0.05499267578125, "words": [ { "start": 2472.88, "end": 2473.04, "word": " So", "probability": 0.7578125 }, { "start": 2473.04, "end": 2473.16, "word": " I'm", "probability": 0.614990234375 }, { "start": 2473.16, "end": 2473.26, "word": " going", "probability": 0.419677734375 }, { "start": 2473.26, "end": 2473.26, "word": " to", "probability": 0.90283203125 }, { "start": 2473.26, "end": 2473.66, "word": " verify", "probability": 0.8369140625 }, { "start": 2473.66, "end": 2474.28, "word": " vectorizing", "probability": 0.77978515625 }, { "start": 2474.28, "end": 2474.72, "word": " is", "probability": 0.89990234375 }, { "start": 2474.72, "end": 2475.78, "word": " complete", "probability": 0.6240234375 }, { "start": 2475.78, "end": 2476.22, "word": ".", "probability": 0.72412109375 } ] }, { "id": 716, "seek": 241284, "start": 2477.36, "end": 2482.1, "text": " And I'm going to let you guys run your vectorizers, let that sit for a little bit.", "tokens": [ 51114, 400, 286, 478, 516, 281, 718, 291, 1074, 1190, 428, 8062, 22525, 11, 718, 300, 1394, 337, 257, 707, 857, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.22631047874368648, "compression_ratio": 1.6464646464646464, "no_speech_prob": 0.05499267578125, "words": [ { "start": 2477.36, "end": 2477.62, "word": " And", "probability": 0.7978515625 }, { "start": 2477.62, "end": 2477.74, "word": " I'm", "probability": 0.971923828125 }, { "start": 2477.74, "end": 2477.84, "word": " going", "probability": 0.79052734375 }, { "start": 2477.84, "end": 2477.86, "word": " to", "probability": 0.9013671875 }, { "start": 2477.86, "end": 2478.02, "word": " let", "probability": 0.8974609375 }, { "start": 2478.02, "end": 2478.16, "word": " you", "probability": 0.8984375 }, { "start": 2478.16, "end": 2478.52, "word": " guys", "probability": 0.87158203125 }, { "start": 2478.52, "end": 2479.64, "word": " run", "probability": 0.89013671875 }, { "start": 2479.64, "end": 2479.76, "word": " your", "probability": 0.8134765625 }, { "start": 2479.76, "end": 2480.34, "word": " vectorizers", "probability": 0.949951171875 }, { "start": 2480.34, "end": 2480.56, "word": ",", "probability": 0.712890625 }, { "start": 2480.56, "end": 2480.7, "word": " let", "probability": 0.87744140625 }, { "start": 2480.7, "end": 2480.88, "word": " that", "probability": 0.88134765625 }, { "start": 2480.88, "end": 2481.06, "word": " sit", "probability": 0.89892578125 }, { "start": 2481.06, "end": 2481.22, "word": " for", "probability": 0.89453125 }, { "start": 2481.34, "end": 2481.46, "word": " a little", "probability": 0.8046875 }, { "start": 2481.46, "end": 2481.78, "word": " bit", "probability": 0.8974609375 }, { "start": 2481.78, "end": 2482.1, "word": ".", "probability": 0.32275390625 } ] }, { "id": 717, "seek": 241284, "start": 2482.1, "end": 2484.28, "text": " And then we're going to run this, because we need...", "tokens": [ 51364, 400, 550, 321, 434, 516, 281, 1190, 341, 11, 570, 321, 643, 485, 51514 ], "temperature": 0.0, "avg_logprob": -0.22631047874368648, "compression_ratio": 1.6464646464646464, "no_speech_prob": 0.05499267578125, "words": [ { "start": 2482.1, "end": 2482.2, "word": " And", "probability": 0.4306640625 }, { "start": 2482.2, "end": 2482.26, "word": " then", "probability": 0.5810546875 }, { "start": 2482.26, "end": 2482.38, "word": " we're", "probability": 0.8896484375 }, { "start": 2482.38, "end": 2482.4, "word": " going", "probability": 0.82763671875 }, { "start": 2482.4, "end": 2482.46, "word": " to", "probability": 0.90283203125 }, { "start": 2482.46, "end": 2482.64, "word": " run", "probability": 0.8955078125 }, { "start": 2482.64, "end": 2482.96, "word": " this", "probability": 0.87939453125 }, { "start": 2482.96, "end": 2483.04, "word": ",", "probability": 0.311767578125 }, { "start": 2483.04, "end": 2483.3, "word": " because", "probability": 0.8359375 }, { "start": 2483.3, "end": 2483.52, "word": " we", "probability": 0.89404296875 }, { "start": 2483.52, "end": 2484.28, "word": " need...", "probability": 0.48944091796875 } ] }, { "id": 718, "seek": 241284, "start": 2485.68, "end": 2488.72, "text": " Oh, I don't believe we do need the previous one to run this.", "tokens": [ 51514, 876, 11, 286, 500, 380, 1697, 321, 360, 643, 264, 3894, 472, 281, 1190, 341, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.22631047874368648, "compression_ratio": 1.6464646464646464, "no_speech_prob": 0.05499267578125, "words": [ { "start": 2485.68, "end": 2486.1, "word": " Oh", "probability": 0.7158203125 }, { "start": 2486.1, "end": 2486.2, "word": ",", "probability": 0.90185546875 }, { "start": 2486.2, "end": 2486.34, "word": " I", "probability": 0.998046875 }, { "start": 2486.34, "end": 2486.44, "word": " don't", "probability": 0.94775390625 }, { "start": 2486.44, "end": 2486.66, "word": " believe", "probability": 0.70751953125 }, { "start": 2486.66, "end": 2486.78, "word": " we", "probability": 0.904296875 }, { "start": 2486.78, "end": 2486.88, "word": " do", "probability": 0.89208984375 }, { "start": 2486.88, "end": 2487.02, "word": " need", "probability": 0.81201171875 }, { "start": 2487.02, "end": 2487.18, "word": " the", "probability": 0.8173828125 }, { "start": 2487.18, "end": 2487.46, "word": " previous", "probability": 0.7734375 }, { "start": 2487.46, "end": 2487.7, "word": " one", "probability": 0.81005859375 }, { "start": 2487.7, "end": 2487.86, "word": " to", "probability": 0.90185546875 }, { "start": 2487.86, "end": 2488.0, "word": " run", "probability": 0.9013671875 }, { "start": 2488.0, "end": 2488.28, "word": " this", "probability": 0.87939453125 }, { "start": 2488.28, "end": 2488.72, "word": ".", "probability": 0.96240234375 } ] }, { "id": 719, "seek": 243826, "start": 2488.72, "end": 2494.84, "text": " So if your vectorizer is still going, your code here will not run right away,", "tokens": [ 50364, 407, 498, 428, 8062, 6545, 307, 920, 516, 11, 428, 3089, 510, 486, 406, 1190, 558, 1314, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.21448863365433432, "compression_ratio": 1.7014925373134329, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 2488.72, "end": 2488.98, "word": " So", "probability": 0.443115234375 }, { "start": 2488.98, "end": 2489.66, "word": " if", "probability": 0.58056640625 }, { "start": 2489.66, "end": 2489.8, "word": " your", "probability": 0.7509765625 }, { "start": 2489.8, "end": 2490.1, "word": " vectorizer", "probability": 0.882080078125 }, { "start": 2490.1, "end": 2490.22, "word": " is", "probability": 0.6572265625 }, { "start": 2490.22, "end": 2490.4, "word": " still", "probability": 0.908203125 }, { "start": 2490.4, "end": 2490.76, "word": " going", "probability": 0.85888671875 }, { "start": 2490.76, "end": 2491.42, "word": ",", "probability": 0.78173828125 }, { "start": 2491.42, "end": 2492.66, "word": " your", "probability": 0.79248046875 }, { "start": 2492.66, "end": 2493.08, "word": " code", "probability": 0.83154296875 }, { "start": 2493.08, "end": 2493.34, "word": " here", "probability": 0.8125 }, { "start": 2493.34, "end": 2493.56, "word": " will", "probability": 0.810546875 }, { "start": 2493.56, "end": 2493.78, "word": " not", "probability": 0.89013671875 }, { "start": 2493.78, "end": 2494.1, "word": " run", "probability": 0.8916015625 }, { "start": 2494.1, "end": 2494.44, "word": " right", "probability": 0.880859375 }, { "start": 2494.44, "end": 2494.72, "word": " away", "probability": 0.81884765625 }, { "start": 2494.72, "end": 2494.84, "word": ",", "probability": 0.70947265625 } ] }, { "id": 720, "seek": 243826, "start": 2494.84, "end": 2498.2, "text": " but it will run as soon as the vectorizer completes.", "tokens": [ 50664, 457, 309, 486, 1190, 382, 2321, 382, 264, 8062, 6545, 36362, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.21448863365433432, "compression_ratio": 1.7014925373134329, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 2494.84, "end": 2495.08, "word": " but", "probability": 0.89697265625 }, { "start": 2495.08, "end": 2495.22, "word": " it", "probability": 0.90087890625 }, { "start": 2495.22, "end": 2495.34, "word": " will", "probability": 0.80908203125 }, { "start": 2495.34, "end": 2495.62, "word": " run", "probability": 0.88427734375 }, { "start": 2495.62, "end": 2495.84, "word": " as", "probability": 0.89599609375 }, { "start": 2495.84, "end": 2495.98, "word": " soon", "probability": 0.8779296875 }, { "start": 2495.98, "end": 2496.08, "word": " as", "probability": 0.89990234375 }, { "start": 2496.08, "end": 2496.2, "word": " the", "probability": 0.80224609375 }, { "start": 2496.2, "end": 2496.66, "word": " vectorizer", "probability": 0.952880859375 }, { "start": 2496.66, "end": 2497.68, "word": " completes", "probability": 0.6767578125 }, { "start": 2497.68, "end": 2498.2, "word": ".", "probability": 0.9814453125 } ] }, { "id": 721, "seek": 243826, "start": 2498.44, "end": 2500.54, "text": " So I'm going to go ahead and run mine.", "tokens": [ 50864, 407, 286, 478, 516, 281, 352, 2286, 293, 1190, 3892, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.21448863365433432, "compression_ratio": 1.7014925373134329, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 2498.44, "end": 2498.78, "word": " So", "probability": 0.83056640625 }, { "start": 2498.78, "end": 2499.04, "word": " I'm", "probability": 0.9697265625 }, { "start": 2499.04, "end": 2499.08, "word": " going", "probability": 0.54296875 }, { "start": 2499.08, "end": 2499.12, "word": " to", "probability": 0.9052734375 }, { "start": 2499.12, "end": 2499.22, "word": " go", "probability": 0.904296875 }, { "start": 2499.22, "end": 2499.4, "word": " ahead", "probability": 0.85791015625 }, { "start": 2499.4, "end": 2499.54, "word": " and", "probability": 0.89404296875 }, { "start": 2499.54, "end": 2499.7, "word": " run", "probability": 0.88671875 }, { "start": 2499.7, "end": 2500.02, "word": " mine", "probability": 0.86669921875 }, { "start": 2500.02, "end": 2500.54, "word": ".", "probability": 0.76953125 } ] }, { "id": 722, "seek": 243826, "start": 2500.56, "end": 2505.9, "text": " So shift-enter, and tokenizer email is not correct.", "tokens": [ 50964, 407, 5513, 12, 14278, 11, 293, 14862, 6545, 3796, 307, 406, 3006, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.21448863365433432, "compression_ratio": 1.7014925373134329, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 2500.56, "end": 2500.7, "word": " So", "probability": 0.85009765625 }, { "start": 2500.7, "end": 2501.06, "word": " shift", "probability": 0.429931640625 }, { "start": 2501.06, "end": 2501.46, "word": "-enter", "probability": 0.49493408203125 }, { "start": 2501.46, "end": 2502.72, "word": ",", "probability": 0.345947265625 }, { "start": 2502.72, "end": 2503.16, "word": " and", "probability": 0.8779296875 }, { "start": 2503.16, "end": 2503.94, "word": " tokenizer", "probability": 0.73291015625 }, { "start": 2503.94, "end": 2504.32, "word": " email", "probability": 0.7109375 }, { "start": 2504.32, "end": 2504.92, "word": " is", "probability": 0.9072265625 }, { "start": 2504.92, "end": 2505.26, "word": " not", "probability": 0.90478515625 }, { "start": 2505.26, "end": 2505.62, "word": " correct", "probability": 0.89453125 }, { "start": 2505.62, "end": 2505.9, "word": ".", "probability": 0.89892578125 } ] }, { "id": 723, "seek": 243826, "start": 2505.9, "end": 2510.4, "text": " I think it's tokenized email, that makes a little bit more sense.", "tokens": [ 51214, 286, 519, 309, 311, 14862, 1602, 3796, 11, 300, 1669, 257, 707, 857, 544, 2020, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.21448863365433432, "compression_ratio": 1.7014925373134329, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 2505.9, "end": 2505.94, "word": " I", "probability": 0.91015625 }, { "start": 2505.94, "end": 2506.08, "word": " think", "probability": 0.826171875 }, { "start": 2506.08, "end": 2506.28, "word": " it's", "probability": 0.934814453125 }, { "start": 2506.28, "end": 2507.22, "word": " tokenized", "probability": 0.85546875 }, { "start": 2507.22, "end": 2508.4, "word": " email", "probability": 0.89453125 }, { "start": 2508.4, "end": 2508.68, "word": ",", "probability": 0.2249755859375 }, { "start": 2508.68, "end": 2508.82, "word": " that", "probability": 0.80078125 }, { "start": 2508.82, "end": 2508.98, "word": " makes", "probability": 0.71240234375 }, { "start": 2509.08, "end": 2509.18, "word": " a little", "probability": 0.81005859375 }, { "start": 2509.18, "end": 2509.32, "word": " bit", "probability": 0.87353515625 }, { "start": 2509.32, "end": 2509.52, "word": " more", "probability": 0.880859375 }, { "start": 2509.52, "end": 2509.88, "word": " sense", "probability": 0.74365234375 }, { "start": 2509.88, "end": 2510.4, "word": ".", "probability": 0.9208984375 } ] }, { "id": 724, "seek": 243826, "start": 2510.58, "end": 2514.14, "text": " I'm going to run that. Tokenized email is not defined.", "tokens": [ 51464, 286, 478, 516, 281, 1190, 300, 13, 314, 8406, 1602, 3796, 307, 406, 7642, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.21448863365433432, "compression_ratio": 1.7014925373134329, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 2510.58, "end": 2510.8, "word": " I'm", "probability": 0.66650390625 }, { "start": 2510.8, "end": 2510.8, "word": " going", "probability": 0.74462890625 }, { "start": 2510.8, "end": 2510.8, "word": " to", "probability": 0.9072265625 }, { "start": 2510.8, "end": 2511.0, "word": " run", "probability": 0.8828125 }, { "start": 2511.0, "end": 2511.26, "word": " that", "probability": 0.88232421875 }, { "start": 2511.26, "end": 2511.4, "word": ".", "probability": 0.70361328125 }, { "start": 2511.44, "end": 2511.96, "word": " Tokenized", "probability": 0.9103190104166666 }, { "start": 2511.96, "end": 2512.38, "word": " email", "probability": 0.8984375 }, { "start": 2512.38, "end": 2512.92, "word": " is", "probability": 0.89892578125 }, { "start": 2512.92, "end": 2513.12, "word": " not", "probability": 0.89697265625 }, { "start": 2513.12, "end": 2513.62, "word": " defined", "probability": 0.69580078125 }, { "start": 2513.62, "end": 2514.14, "word": ".", "probability": 0.99365234375 } ] }, { "id": 725, "seek": 246316, "start": 2515.14, "end": 2521.22, "text": " Okay, give me a second. I'm going to scroll up to our tokenizer.", "tokens": [ 50414, 1033, 11, 976, 385, 257, 1150, 13, 286, 478, 516, 281, 11369, 493, 281, 527, 14862, 6545, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.20645680629155216, "compression_ratio": 1.3225806451612903, "no_speech_prob": 0.01016998291015625, "words": [ { "start": 2515.14, "end": 2515.72, "word": " Okay", "probability": 0.1300048828125 }, { "start": 2515.72, "end": 2515.88, "word": ",", "probability": 0.76513671875 }, { "start": 2515.88, "end": 2516.06, "word": " give", "probability": 0.6923828125 }, { "start": 2516.06, "end": 2516.12, "word": " me", "probability": 0.89697265625 }, { "start": 2516.26, "end": 2516.48, "word": " a second", "probability": 0.7841796875 }, { "start": 2516.48, "end": 2516.66, "word": ".", "probability": 0.464599609375 }, { "start": 2516.66, "end": 2516.74, "word": " I'm", "probability": 0.962158203125 }, { "start": 2516.74, "end": 2516.82, "word": " going", "probability": 0.244140625 }, { "start": 2516.82, "end": 2516.9, "word": " to", "probability": 0.9052734375 }, { "start": 2516.9, "end": 2517.28, "word": " scroll", "probability": 0.8974609375 }, { "start": 2517.28, "end": 2517.66, "word": " up", "probability": 0.90576171875 }, { "start": 2517.66, "end": 2518.84, "word": " to", "probability": 0.8759765625 }, { "start": 2518.84, "end": 2519.94, "word": " our", "probability": 0.78125 }, { "start": 2519.94, "end": 2520.64, "word": " tokenizer", "probability": 0.781982421875 }, { "start": 2520.64, "end": 2521.22, "word": ".", "probability": 0.884765625 } ] }, { "id": 726, "seek": 246316, "start": 2527.04, "end": 2529.68, "text": " I guess I don't have that defined.", "tokens": [ 50814, 286, 2041, 286, 500, 380, 362, 300, 7642, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.20645680629155216, "compression_ratio": 1.3225806451612903, "no_speech_prob": 0.01016998291015625, "words": [ { "start": 2527.04, "end": 2527.62, "word": " I", "probability": 0.8662109375 }, { "start": 2527.62, "end": 2527.78, "word": " guess", "probability": 0.87841796875 }, { "start": 2527.78, "end": 2527.94, "word": " I", "probability": 0.990234375 }, { "start": 2527.94, "end": 2528.14, "word": " don't", "probability": 0.949462890625 }, { "start": 2528.14, "end": 2528.46, "word": " have", "probability": 0.88818359375 }, { "start": 2528.46, "end": 2528.64, "word": " that", "probability": 0.8818359375 }, { "start": 2528.64, "end": 2529.1, "word": " defined", "probability": 0.7314453125 }, { "start": 2529.1, "end": 2529.68, "word": ".", "probability": 0.96337890625 } ] }, { "id": 727, "seek": 246316, "start": 2532.82, "end": 2534.94, "text": " Where is that?", "tokens": [ 51014, 2305, 307, 300, 30, 51214 ], "temperature": 0.0, "avg_logprob": -0.20645680629155216, "compression_ratio": 1.3225806451612903, "no_speech_prob": 0.01016998291015625, "words": [ { "start": 2532.82, "end": 2533.4, "word": " Where", "probability": 0.72998046875 }, { "start": 2533.4, "end": 2533.98, "word": " is", "probability": 0.85205078125 }, { "start": 2533.98, "end": 2534.36, "word": " that", "probability": 0.880859375 }, { "start": 2534.36, "end": 2534.94, "word": "?", "probability": 0.96875 } ] }, { "id": 728, "seek": 246316, "start": 2542.37, "end": 2545.55, "text": " Ah, I was supposed to save it up above. That's okay.", "tokens": [ 51314, 2438, 11, 286, 390, 3442, 281, 3155, 309, 493, 3673, 13, 663, 311, 1392, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.20645680629155216, "compression_ratio": 1.3225806451612903, "no_speech_prob": 0.01016998291015625, "words": [ { "start": 2542.37, "end": 2542.87, "word": " Ah", "probability": 0.2171630859375 }, { "start": 2542.87, "end": 2542.87, "word": ",", "probability": 0.94384765625 }, { "start": 2542.87, "end": 2542.97, "word": " I", "probability": 0.9404296875 }, { "start": 2542.97, "end": 2543.03, "word": " was", "probability": 0.82568359375 }, { "start": 2543.03, "end": 2543.15, "word": " supposed", "probability": 0.89013671875 }, { "start": 2543.15, "end": 2543.33, "word": " to", "probability": 0.90625 }, { "start": 2543.33, "end": 2543.61, "word": " save", "probability": 0.8662109375 }, { "start": 2543.61, "end": 2543.73, "word": " it", "probability": 0.89501953125 }, { "start": 2543.73, "end": 2543.91, "word": " up", "probability": 0.90283203125 }, { "start": 2543.91, "end": 2544.23, "word": " above", "probability": 0.90087890625 }, { "start": 2544.23, "end": 2544.53, "word": ".", "probability": 0.71240234375 }, { "start": 2544.53, "end": 2544.75, "word": " That's", "probability": 0.908447265625 }, { "start": 2544.75, "end": 2544.97, "word": " okay", "probability": 0.79833984375 }, { "start": 2544.97, "end": 2545.55, "word": ".", "probability": 0.9052734375 } ] }, { "id": 729, "seek": 246316, "start": 2545.69, "end": 2548.59, "text": " So we'll go ahead and create it here.", "tokens": [ 51464, 407, 321, 603, 352, 2286, 293, 1884, 309, 510, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.20645680629155216, "compression_ratio": 1.3225806451612903, "no_speech_prob": 0.01016998291015625, "words": [ { "start": 2545.69, "end": 2545.99, "word": " So", "probability": 0.84130859375 }, { "start": 2545.99, "end": 2546.11, "word": " we'll", "probability": 0.86279296875 }, { "start": 2546.11, "end": 2546.25, "word": " go", "probability": 0.90283203125 }, { "start": 2546.25, "end": 2546.57, "word": " ahead", "probability": 0.85595703125 }, { "start": 2546.57, "end": 2547.01, "word": " and", "probability": 0.892578125 }, { "start": 2547.01, "end": 2547.53, "word": " create", "probability": 0.828125 }, { "start": 2547.53, "end": 2547.67, "word": " it", "probability": 0.89599609375 }, { "start": 2547.67, "end": 2548.01, "word": " here", "probability": 0.81103515625 }, { "start": 2548.01, "end": 2548.59, "word": ".", "probability": 0.97314453125 } ] }, { "id": 730, "seek": 249126, "start": 2549.75, "end": 2556.37, "text": " Tokenized email equals tokenizer test email.", "tokens": [ 50414, 314, 8406, 1602, 3796, 6915, 14862, 6545, 1500, 3796, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.19815340858291497, "compression_ratio": 1.6010362694300517, "no_speech_prob": 0.0020198822021484375, "words": [ { "start": 2549.75, "end": 2550.39, "word": " Tokenized", "probability": 0.6867268880208334 }, { "start": 2550.39, "end": 2550.97, "word": " email", "probability": 0.73974609375 }, { "start": 2550.97, "end": 2551.99, "word": " equals", "probability": 0.61181640625 }, { "start": 2551.99, "end": 2554.09, "word": " tokenizer", "probability": 0.77099609375 }, { "start": 2554.09, "end": 2555.43, "word": " test", "probability": 0.6484375 }, { "start": 2555.43, "end": 2555.99, "word": " email", "probability": 0.81884765625 }, { "start": 2555.99, "end": 2556.37, "word": ".", "probability": 0.78662109375 } ] }, { "id": 731, "seek": 249126, "start": 2556.37, "end": 2558.45, "text": " So we're going to go ahead and save that.", "tokens": [ 50714, 407, 321, 434, 516, 281, 352, 2286, 293, 3155, 300, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.19815340858291497, "compression_ratio": 1.6010362694300517, "no_speech_prob": 0.0020198822021484375, "words": [ { "start": 2556.37, "end": 2556.51, "word": " So", "probability": 0.521484375 }, { "start": 2556.51, "end": 2556.71, "word": " we're", "probability": 0.68017578125 }, { "start": 2556.71, "end": 2556.71, "word": " going", "probability": 0.310546875 }, { "start": 2556.71, "end": 2556.71, "word": " to", "probability": 0.89697265625 }, { "start": 2556.71, "end": 2556.81, "word": " go", "probability": 0.88818359375 }, { "start": 2556.81, "end": 2556.99, "word": " ahead", "probability": 0.8271484375 }, { "start": 2556.99, "end": 2557.15, "word": " and", "probability": 0.89404296875 }, { "start": 2557.15, "end": 2557.45, "word": " save", "probability": 0.81298828125 }, { "start": 2557.45, "end": 2557.81, "word": " that", "probability": 0.8818359375 }, { "start": 2557.81, "end": 2558.45, "word": ".", "probability": 0.96484375 } ] }, { "id": 732, "seek": 249126, "start": 2560.79, "end": 2563.91, "text": " And here we have the word counts of our test email.", "tokens": [ 50964, 400, 510, 321, 362, 264, 1349, 14893, 295, 527, 1500, 3796, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.19815340858291497, "compression_ratio": 1.6010362694300517, "no_speech_prob": 0.0020198822021484375, "words": [ { "start": 2560.79, "end": 2561.43, "word": " And", "probability": 0.80029296875 }, { "start": 2561.43, "end": 2561.65, "word": " here", "probability": 0.81298828125 }, { "start": 2561.65, "end": 2561.77, "word": " we", "probability": 0.88037109375 }, { "start": 2561.77, "end": 2561.91, "word": " have", "probability": 0.87744140625 }, { "start": 2561.91, "end": 2562.07, "word": " the", "probability": 0.81298828125 }, { "start": 2562.07, "end": 2562.27, "word": " word", "probability": 0.82470703125 }, { "start": 2562.27, "end": 2562.61, "word": " counts", "probability": 0.70947265625 }, { "start": 2562.61, "end": 2562.99, "word": " of", "probability": 0.9072265625 }, { "start": 2562.99, "end": 2563.19, "word": " our", "probability": 0.81884765625 }, { "start": 2563.19, "end": 2563.45, "word": " test", "probability": 0.80078125 }, { "start": 2563.45, "end": 2563.77, "word": " email", "probability": 0.92333984375 }, { "start": 2563.77, "end": 2563.91, "word": ".", "probability": 0.69921875 } ] }, { "id": 733, "seek": 249126, "start": 2563.91, "end": 2566.55, "text": " We see the familiar East Asian font, Lenny.", "tokens": [ 51114, 492, 536, 264, 4963, 6747, 10645, 10703, 11, 23009, 1634, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.19815340858291497, "compression_ratio": 1.6010362694300517, "no_speech_prob": 0.0020198822021484375, "words": [ { "start": 2563.91, "end": 2563.99, "word": " We", "probability": 0.84716796875 }, { "start": 2563.99, "end": 2564.13, "word": " see", "probability": 0.81298828125 }, { "start": 2564.13, "end": 2564.27, "word": " the", "probability": 0.796875 }, { "start": 2564.27, "end": 2564.51, "word": " familiar", "probability": 0.74267578125 }, { "start": 2564.51, "end": 2564.83, "word": " East", "probability": 0.68798828125 }, { "start": 2564.83, "end": 2565.15, "word": " Asian", "probability": 0.81298828125 }, { "start": 2565.15, "end": 2565.61, "word": " font", "probability": 0.83642578125 }, { "start": 2565.61, "end": 2565.75, "word": ",", "probability": 0.19482421875 }, { "start": 2565.75, "end": 2566.09, "word": " Lenny", "probability": 0.645263671875 }, { "start": 2566.09, "end": 2566.55, "word": ".", "probability": 0.92919921875 } ] }, { "id": 734, "seek": 249126, "start": 2566.55, "end": 2573.11, "text": " We know unsubscribe showed up twice, and we know list.debian.org showed up twice.", "tokens": [ 51264, 492, 458, 2693, 9493, 4712, 493, 6091, 11, 293, 321, 458, 1329, 13, 1479, 20196, 13, 4646, 4712, 493, 6091, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.19815340858291497, "compression_ratio": 1.6010362694300517, "no_speech_prob": 0.0020198822021484375, "words": [ { "start": 2566.55, "end": 2566.91, "word": " We", "probability": 0.89404296875 }, { "start": 2566.91, "end": 2567.15, "word": " know", "probability": 0.82470703125 }, { "start": 2567.15, "end": 2567.91, "word": " unsubscribe", "probability": 0.79296875 }, { "start": 2567.91, "end": 2568.59, "word": " showed", "probability": 0.775390625 }, { "start": 2568.59, "end": 2568.77, "word": " up", "probability": 0.912109375 }, { "start": 2568.77, "end": 2569.25, "word": " twice", "probability": 0.84765625 }, { "start": 2569.25, "end": 2569.35, "word": ",", "probability": 0.36181640625 }, { "start": 2569.35, "end": 2569.49, "word": " and", "probability": 0.88671875 }, { "start": 2569.49, "end": 2569.61, "word": " we", "probability": 0.890625 }, { "start": 2569.61, "end": 2569.95, "word": " know", "probability": 0.79931640625 }, { "start": 2569.95, "end": 2570.39, "word": " list", "probability": 0.66650390625 }, { "start": 2570.39, "end": 2571.01, "word": ".debian", "probability": 0.8922526041666666 }, { "start": 2571.01, "end": 2571.77, "word": ".org", "probability": 0.95458984375 }, { "start": 2571.77, "end": 2572.41, "word": " showed", "probability": 0.80224609375 }, { "start": 2572.41, "end": 2572.57, "word": " up", "probability": 0.90966796875 }, { "start": 2572.57, "end": 2572.93, "word": " twice", "probability": 0.85400390625 }, { "start": 2572.93, "end": 2573.11, "word": ".", "probability": 0.978515625 } ] }, { "id": 735, "seek": 249126, "start": 2573.11, "end": 2576.69, "text": " Everything else in here only showed up once.", "tokens": [ 51564, 5471, 1646, 294, 510, 787, 4712, 493, 1564, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.19815340858291497, "compression_ratio": 1.6010362694300517, "no_speech_prob": 0.0020198822021484375, "words": [ { "start": 2573.11, "end": 2573.45, "word": " Everything", "probability": 0.8876953125 }, { "start": 2573.45, "end": 2573.77, "word": " else", "probability": 0.8388671875 }, { "start": 2573.77, "end": 2573.97, "word": " in", "probability": 0.89990234375 }, { "start": 2573.97, "end": 2574.27, "word": " here", "probability": 0.814453125 }, { "start": 2574.27, "end": 2575.21, "word": " only", "probability": 0.81005859375 }, { "start": 2575.21, "end": 2575.59, "word": " showed", "probability": 0.796875 }, { "start": 2575.59, "end": 2575.83, "word": " up", "probability": 0.912109375 }, { "start": 2575.83, "end": 2576.47, "word": " once", "probability": 0.828125 }, { "start": 2576.47, "end": 2576.69, "word": ".", "probability": 0.935546875 } ] }, { "id": 736, "seek": 252070, "start": 2576.69, "end": 2582.79, "text": " I know I went very quickly, but this was the line that I needed to add.", "tokens": [ 50414, 286, 458, 286, 1437, 588, 2661, 11, 457, 341, 390, 264, 1622, 300, 286, 2978, 281, 909, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.23163660285399132, "compression_ratio": 1.6854460093896713, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 2576.69, "end": 2577.49, "word": " I", "probability": 0.122314453125 }, { "start": 2577.49, "end": 2578.41, "word": " know", "probability": 0.59033203125 }, { "start": 2578.41, "end": 2578.77, "word": " I", "probability": 0.95751953125 }, { "start": 2578.77, "end": 2579.35, "word": " went", "probability": 0.77978515625 }, { "start": 2579.35, "end": 2579.65, "word": " very", "probability": 0.69140625 }, { "start": 2579.65, "end": 2580.01, "word": " quickly", "probability": 0.890625 }, { "start": 2580.01, "end": 2580.99, "word": ",", "probability": 0.6484375 }, { "start": 2580.99, "end": 2581.11, "word": " but", "probability": 0.84716796875 }, { "start": 2581.11, "end": 2581.31, "word": " this", "probability": 0.8662109375 }, { "start": 2581.31, "end": 2581.49, "word": " was", "probability": 0.79541015625 }, { "start": 2581.49, "end": 2581.65, "word": " the", "probability": 0.80908203125 }, { "start": 2581.65, "end": 2581.85, "word": " line", "probability": 0.89453125 }, { "start": 2581.85, "end": 2581.99, "word": " that", "probability": 0.603515625 }, { "start": 2581.99, "end": 2582.07, "word": " I", "probability": 0.99072265625 }, { "start": 2582.07, "end": 2582.25, "word": " needed", "probability": 0.732421875 }, { "start": 2582.25, "end": 2582.41, "word": " to", "probability": 0.89111328125 }, { "start": 2582.41, "end": 2582.65, "word": " add", "probability": 0.83447265625 }, { "start": 2582.65, "end": 2582.79, "word": ".", "probability": 0.48388671875 } ] }, { "id": 737, "seek": 252070, "start": 2582.79, "end": 2586.13, "text": " Tokenized email equals tokenizer test email.", "tokens": [ 50664, 314, 8406, 1602, 3796, 6915, 14862, 6545, 1500, 3796, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.23163660285399132, "compression_ratio": 1.6854460093896713, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 2582.79, "end": 2583.17, "word": " Tokenized", "probability": 0.7683919270833334 }, { "start": 2583.17, "end": 2583.53, "word": " email", "probability": 0.66943359375 }, { "start": 2583.53, "end": 2583.95, "word": " equals", "probability": 0.444580078125 }, { "start": 2583.95, "end": 2584.61, "word": " tokenizer", "probability": 0.817626953125 }, { "start": 2584.61, "end": 2585.29, "word": " test", "probability": 0.6435546875 }, { "start": 2585.29, "end": 2585.65, "word": " email", "probability": 0.8203125 }, { "start": 2585.65, "end": 2586.13, "word": ".", "probability": 0.89404296875 } ] }, { "id": 738, "seek": 252070, "start": 2587.13, "end": 2595.11, "text": " And then we grab the list of the dictionary from that list of the tokenized email, and we print out the word counts.", "tokens": [ 50864, 400, 550, 321, 4444, 264, 1329, 295, 264, 25890, 490, 300, 1329, 295, 264, 14862, 1602, 3796, 11, 293, 321, 4482, 484, 264, 1349, 14893, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.23163660285399132, "compression_ratio": 1.6854460093896713, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 2587.13, "end": 2587.27, "word": " And", "probability": 0.497802734375 }, { "start": 2587.27, "end": 2587.55, "word": " then", "probability": 0.70849609375 }, { "start": 2587.55, "end": 2588.65, "word": " we", "probability": 0.77783203125 }, { "start": 2588.65, "end": 2589.03, "word": " grab", "probability": 0.5849609375 }, { "start": 2589.03, "end": 2589.15, "word": " the", "probability": 0.8134765625 }, { "start": 2589.15, "end": 2589.45, "word": " list", "probability": 0.88671875 }, { "start": 2589.45, "end": 2589.71, "word": " of", "probability": 0.90380859375 }, { "start": 2589.71, "end": 2589.83, "word": " the", "probability": 0.8076171875 }, { "start": 2589.83, "end": 2590.09, "word": " dictionary", "probability": 0.7822265625 }, { "start": 2590.09, "end": 2590.79, "word": " from", "probability": 0.791015625 }, { "start": 2590.79, "end": 2591.57, "word": " that", "probability": 0.87353515625 }, { "start": 2591.57, "end": 2591.87, "word": " list", "probability": 0.8896484375 }, { "start": 2591.87, "end": 2592.05, "word": " of", "probability": 0.8974609375 }, { "start": 2592.05, "end": 2592.15, "word": " the", "probability": 0.77734375 }, { "start": 2592.15, "end": 2592.57, "word": " tokenized", "probability": 0.8837890625 }, { "start": 2592.57, "end": 2592.91, "word": " email", "probability": 0.88330078125 }, { "start": 2592.91, "end": 2593.25, "word": ",", "probability": 0.404541015625 }, { "start": 2593.25, "end": 2593.55, "word": " and", "probability": 0.88427734375 }, { "start": 2593.55, "end": 2593.73, "word": " we", "probability": 0.88037109375 }, { "start": 2593.73, "end": 2593.91, "word": " print", "probability": 0.89404296875 }, { "start": 2593.91, "end": 2594.05, "word": " out", "probability": 0.8115234375 }, { "start": 2594.05, "end": 2594.23, "word": " the", "probability": 0.81494140625 }, { "start": 2594.23, "end": 2594.37, "word": " word", "probability": 0.83203125 }, { "start": 2594.37, "end": 2594.63, "word": " counts", "probability": 0.7080078125 }, { "start": 2594.63, "end": 2595.11, "word": ".", "probability": 0.994140625 } ] }, { "id": 739, "seek": 252070, "start": 2598.39, "end": 2606.13, "text": " So going on to 3b, what we want to see is, okay, we know what the word count looks like if we just did a straight word count.", "tokens": [ 51464, 407, 516, 322, 281, 805, 65, 11, 437, 321, 528, 281, 536, 307, 11, 1392, 11, 321, 458, 437, 264, 1349, 1207, 1542, 411, 498, 321, 445, 630, 257, 2997, 1349, 1207, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.23163660285399132, "compression_ratio": 1.6854460093896713, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 2598.39, "end": 2598.87, "word": " So", "probability": 0.744140625 }, { "start": 2598.87, "end": 2599.27, "word": " going", "probability": 0.65283203125 }, { "start": 2599.27, "end": 2599.59, "word": " on", "probability": 0.83203125 }, { "start": 2599.59, "end": 2599.83, "word": " to", "probability": 0.9013671875 }, { "start": 2599.83, "end": 2600.55, "word": " 3b", "probability": 0.71337890625 }, { "start": 2600.55, "end": 2600.75, "word": ",", "probability": 0.8662109375 }, { "start": 2600.75, "end": 2600.85, "word": " what", "probability": 0.86865234375 }, { "start": 2600.85, "end": 2600.97, "word": " we", "probability": 0.90625 }, { "start": 2600.97, "end": 2601.09, "word": " want", "probability": 0.73193359375 }, { "start": 2601.09, "end": 2601.19, "word": " to", "probability": 0.90673828125 }, { "start": 2601.19, "end": 2601.49, "word": " see", "probability": 0.81591796875 }, { "start": 2601.49, "end": 2602.09, "word": " is", "probability": 0.8994140625 }, { "start": 2602.09, "end": 2602.31, "word": ",", "probability": 0.57080078125 }, { "start": 2602.31, "end": 2602.47, "word": " okay", "probability": 0.4560546875 }, { "start": 2602.47, "end": 2602.97, "word": ",", "probability": 0.84423828125 }, { "start": 2602.97, "end": 2603.47, "word": " we", "probability": 0.89697265625 }, { "start": 2603.47, "end": 2603.61, "word": " know", "probability": 0.81640625 }, { "start": 2603.61, "end": 2603.73, "word": " what", "probability": 0.88720703125 }, { "start": 2603.73, "end": 2603.85, "word": " the", "probability": 0.814453125 }, { "start": 2603.85, "end": 2604.05, "word": " word", "probability": 0.8125 }, { "start": 2604.05, "end": 2604.29, "word": " count", "probability": 0.7861328125 }, { "start": 2604.29, "end": 2604.55, "word": " looks", "probability": 0.79443359375 }, { "start": 2604.55, "end": 2604.75, "word": " like", "probability": 0.8759765625 }, { "start": 2604.75, "end": 2604.87, "word": " if", "probability": 0.78173828125 }, { "start": 2604.87, "end": 2604.95, "word": " we", "probability": 0.89794921875 }, { "start": 2604.95, "end": 2605.11, "word": " just", "probability": 0.87890625 }, { "start": 2605.11, "end": 2605.23, "word": " did", "probability": 0.87158203125 }, { "start": 2605.33, "end": 2605.49, "word": " a straight", "probability": 0.80322265625 }, { "start": 2605.49, "end": 2605.71, "word": " word", "probability": 0.81982421875 }, { "start": 2605.71, "end": 2605.99, "word": " count", "probability": 0.8037109375 }, { "start": 2605.99, "end": 2606.13, "word": ".", "probability": 0.7451171875 } ] }, { "id": 740, "seek": 254888, "start": 2606.13, "end": 2614.13, "text": " How does the count vectorizer and the tf.idf vectorizer transform our test email as we're going through?", "tokens": [ 50364, 1012, 775, 264, 1207, 8062, 6545, 293, 264, 256, 69, 13, 327, 69, 8062, 6545, 4088, 527, 1500, 3796, 382, 321, 434, 516, 807, 30, 50764 ], "temperature": 0.0, "avg_logprob": -0.20971386152577687, "compression_ratio": 1.6368421052631579, "no_speech_prob": 0.0006875991821289062, "words": [ { "start": 2606.13, "end": 2606.43, "word": " How", "probability": 0.30859375 }, { "start": 2606.43, "end": 2606.75, "word": " does", "probability": 0.89990234375 }, { "start": 2606.75, "end": 2606.99, "word": " the", "probability": 0.80126953125 }, { "start": 2606.99, "end": 2607.25, "word": " count", "probability": 0.0972900390625 }, { "start": 2607.25, "end": 2607.83, "word": " vectorizer", "probability": 0.844482421875 }, { "start": 2607.83, "end": 2608.25, "word": " and", "probability": 0.86669921875 }, { "start": 2608.25, "end": 2608.51, "word": " the", "probability": 0.7119140625 }, { "start": 2608.51, "end": 2608.89, "word": " tf", "probability": 0.756103515625 }, { "start": 2608.89, "end": 2609.35, "word": ".idf", "probability": 0.7220865885416666 }, { "start": 2609.35, "end": 2610.07, "word": " vectorizer", "probability": 0.870361328125 }, { "start": 2610.07, "end": 2611.21, "word": " transform", "probability": 0.880859375 }, { "start": 2611.21, "end": 2611.99, "word": " our", "probability": 0.802734375 }, { "start": 2611.99, "end": 2612.37, "word": " test", "probability": 0.810546875 }, { "start": 2612.37, "end": 2612.67, "word": " email", "probability": 0.8828125 }, { "start": 2612.67, "end": 2612.91, "word": " as", "probability": 0.859375 }, { "start": 2612.91, "end": 2613.03, "word": " we're", "probability": 0.9013671875 }, { "start": 2613.03, "end": 2613.23, "word": " going", "probability": 0.861328125 }, { "start": 2613.23, "end": 2613.49, "word": " through", "probability": 0.79541015625 }, { "start": 2613.49, "end": 2614.13, "word": "?", "probability": 0.775390625 } ] }, { "id": 741, "seek": 254888, "start": 2614.61, "end": 2621.59, "text": " So we're going to go ahead and use our example CVEC.", "tokens": [ 50764, 407, 321, 434, 516, 281, 352, 2286, 293, 764, 527, 1365, 383, 7540, 34, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.20971386152577687, "compression_ratio": 1.6368421052631579, "no_speech_prob": 0.0006875991821289062, "words": [ { "start": 2614.61, "end": 2614.97, "word": " So", "probability": 0.449462890625 }, { "start": 2614.97, "end": 2615.21, "word": " we're", "probability": 0.828857421875 }, { "start": 2615.21, "end": 2615.27, "word": " going", "probability": 0.62841796875 }, { "start": 2615.27, "end": 2615.31, "word": " to", "probability": 0.9052734375 }, { "start": 2615.31, "end": 2615.43, "word": " go", "probability": 0.8759765625 }, { "start": 2615.43, "end": 2615.75, "word": " ahead", "probability": 0.841796875 }, { "start": 2615.75, "end": 2616.27, "word": " and", "probability": 0.89306640625 }, { "start": 2616.27, "end": 2617.41, "word": " use", "probability": 0.798828125 }, { "start": 2617.41, "end": 2617.97, "word": " our", "probability": 0.81103515625 }, { "start": 2617.97, "end": 2620.17, "word": " example", "probability": 0.87158203125 }, { "start": 2620.17, "end": 2621.35, "word": " CVEC", "probability": 0.7350260416666666 }, { "start": 2621.35, "end": 2621.59, "word": ".", "probability": 0.37548828125 } ] }, { "id": 742, "seek": 254888, "start": 2621.59, "end": 2628.11, "text": " And the reason why we're using a separate example version is because we want to redefine a count vectorizer.", "tokens": [ 51114, 400, 264, 1778, 983, 321, 434, 1228, 257, 4994, 1365, 3037, 307, 570, 321, 528, 281, 38818, 533, 257, 1207, 8062, 6545, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.20971386152577687, "compression_ratio": 1.6368421052631579, "no_speech_prob": 0.0006875991821289062, "words": [ { "start": 2621.59, "end": 2621.63, "word": " And", "probability": 0.7001953125 }, { "start": 2621.63, "end": 2621.77, "word": " the", "probability": 0.814453125 }, { "start": 2621.77, "end": 2621.97, "word": " reason", "probability": 0.9091796875 }, { "start": 2621.97, "end": 2622.15, "word": " why", "probability": 0.79443359375 }, { "start": 2622.15, "end": 2622.29, "word": " we're", "probability": 0.9296875 }, { "start": 2622.29, "end": 2622.63, "word": " using", "probability": 0.826171875 }, { "start": 2623.17, "end": 2623.67, "word": " a separate", "probability": 0.8408203125 }, { "start": 2623.67, "end": 2624.13, "word": " example", "probability": 0.9365234375 }, { "start": 2624.13, "end": 2624.47, "word": " version", "probability": 0.6875 }, { "start": 2624.47, "end": 2624.63, "word": " is", "probability": 0.88134765625 }, { "start": 2624.63, "end": 2624.83, "word": " because", "probability": 0.81640625 }, { "start": 2624.83, "end": 2624.97, "word": " we", "probability": 0.904296875 }, { "start": 2624.97, "end": 2625.09, "word": " want", "probability": 0.806640625 }, { "start": 2625.09, "end": 2625.25, "word": " to", "probability": 0.90673828125 }, { "start": 2625.25, "end": 2626.17, "word": " redefine", "probability": 0.816162109375 }, { "start": 2626.67, "end": 2626.89, "word": " a count", "probability": 0.76416015625 }, { "start": 2626.89, "end": 2627.47, "word": " vectorizer", "probability": 0.953369140625 }, { "start": 2627.47, "end": 2628.11, "word": ".", "probability": 0.97216796875 } ] }, { "id": 743, "seek": 254888, "start": 2630.33, "end": 2634.31, "text": " Don't forget our tokenizer equals tokenizer.", "tokens": [ 51564, 1468, 380, 2870, 527, 14862, 6545, 6915, 14862, 6545, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.20971386152577687, "compression_ratio": 1.6368421052631579, "no_speech_prob": 0.0006875991821289062, "words": [ { "start": 2630.33, "end": 2630.97, "word": " Don't", "probability": 0.8974609375 }, { "start": 2630.97, "end": 2631.23, "word": " forget", "probability": 0.87646484375 }, { "start": 2631.23, "end": 2631.47, "word": " our", "probability": 0.63720703125 }, { "start": 2631.47, "end": 2631.93, "word": " tokenizer", "probability": 0.85595703125 }, { "start": 2631.93, "end": 2632.61, "word": " equals", "probability": 0.6689453125 }, { "start": 2632.61, "end": 2634.03, "word": " tokenizer", "probability": 0.8212890625 }, { "start": 2634.03, "end": 2634.31, "word": ".", "probability": 0.69580078125 } ] }, { "id": 744, "seek": 257888, "start": 2635.33, "end": 2648.29, "text": " And then we're going to have our exampleX using our exampleCVEC.fitTransform.", "tokens": [ 50414, 400, 550, 321, 434, 516, 281, 362, 527, 1365, 55, 1228, 527, 1365, 34, 7540, 34, 13, 6845, 33339, 837, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.21354167262713114, "compression_ratio": 1.7254901960784315, "no_speech_prob": 0.0005440711975097656, "words": [ { "start": 2635.33, "end": 2635.97, "word": " And", "probability": 0.5078125 }, { "start": 2635.97, "end": 2636.17, "word": " then", "probability": 0.72314453125 }, { "start": 2636.17, "end": 2636.53, "word": " we're", "probability": 0.873779296875 }, { "start": 2636.53, "end": 2636.71, "word": " going", "probability": 0.82373046875 }, { "start": 2636.71, "end": 2636.85, "word": " to", "probability": 0.900390625 }, { "start": 2636.85, "end": 2637.13, "word": " have", "probability": 0.884765625 }, { "start": 2637.13, "end": 2637.69, "word": " our", "probability": 0.8134765625 }, { "start": 2637.69, "end": 2639.53, "word": " exampleX", "probability": 0.584716796875 }, { "start": 2639.53, "end": 2641.53, "word": " using", "probability": 0.66552734375 }, { "start": 2641.53, "end": 2642.11, "word": " our", "probability": 0.8154296875 }, { "start": 2642.11, "end": 2645.01, "word": " exampleCVEC", "probability": 0.60565185546875 }, { "start": 2645.01, "end": 2647.65, "word": ".fitTransform", "probability": 0.851318359375 }, { "start": 2647.65, "end": 2648.29, "word": ".", "probability": 0.52880859375 } ] }, { "id": 745, "seek": 257888, "start": 2648.45, "end": 2651.51, "text": " And then it expects a list.", "tokens": [ 51064, 400, 550, 309, 33280, 257, 1329, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.21354167262713114, "compression_ratio": 1.7254901960784315, "no_speech_prob": 0.0005440711975097656, "words": [ { "start": 2648.45, "end": 2649.09, "word": " And", "probability": 0.87744140625 }, { "start": 2649.09, "end": 2649.35, "word": " then", "probability": 0.73583984375 }, { "start": 2649.35, "end": 2649.81, "word": " it", "probability": 0.81640625 }, { "start": 2649.81, "end": 2650.21, "word": " expects", "probability": 0.7685546875 }, { "start": 2650.41, "end": 2650.87, "word": " a list", "probability": 0.88720703125 }, { "start": 2650.87, "end": 2651.51, "word": ".", "probability": 0.91943359375 } ] }, { "id": 746, "seek": 257888, "start": 2652.11, "end": 2660.33, "text": " Our test email is a simple string, so we're going to have to wrap it in these brackets so that it becomes a list.", "tokens": [ 51214, 2621, 1500, 3796, 307, 257, 2199, 6798, 11, 370, 321, 434, 516, 281, 362, 281, 7019, 309, 294, 613, 26179, 370, 300, 309, 3643, 257, 1329, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.21354167262713114, "compression_ratio": 1.7254901960784315, "no_speech_prob": 0.0005440711975097656, "words": [ { "start": 2652.11, "end": 2652.75, "word": " Our", "probability": 0.91015625 }, { "start": 2652.75, "end": 2653.11, "word": " test", "probability": 0.8291015625 }, { "start": 2653.11, "end": 2653.25, "word": " email", "probability": 0.8125 }, { "start": 2653.25, "end": 2653.61, "word": " is", "probability": 0.90576171875 }, { "start": 2653.75, "end": 2653.97, "word": " a simple", "probability": 0.89208984375 }, { "start": 2653.97, "end": 2654.31, "word": " string", "probability": 0.728515625 }, { "start": 2654.31, "end": 2654.41, "word": ",", "probability": 0.62353515625 }, { "start": 2654.41, "end": 2654.47, "word": " so", "probability": 0.8994140625 }, { "start": 2654.47, "end": 2654.61, "word": " we're", "probability": 0.92578125 }, { "start": 2654.61, "end": 2654.65, "word": " going", "probability": 0.359375 }, { "start": 2654.65, "end": 2654.73, "word": " to", "probability": 0.90478515625 }, { "start": 2654.73, "end": 2654.87, "word": " have", "probability": 0.87841796875 }, { "start": 2654.87, "end": 2655.01, "word": " to", "probability": 0.912109375 }, { "start": 2655.01, "end": 2655.33, "word": " wrap", "probability": 0.841796875 }, { "start": 2655.33, "end": 2655.47, "word": " it", "probability": 0.89990234375 }, { "start": 2655.47, "end": 2655.65, "word": " in", "probability": 0.91162109375 }, { "start": 2655.65, "end": 2655.89, "word": " these", "probability": 0.72314453125 }, { "start": 2655.89, "end": 2657.09, "word": " brackets", "probability": 0.79638671875 }, { "start": 2657.09, "end": 2658.03, "word": " so", "probability": 0.76025390625 }, { "start": 2658.03, "end": 2658.37, "word": " that", "probability": 0.88232421875 }, { "start": 2658.37, "end": 2658.59, "word": " it", "probability": 0.90576171875 }, { "start": 2658.59, "end": 2659.27, "word": " becomes", "probability": 0.80029296875 }, { "start": 2659.59, "end": 2659.91, "word": " a list", "probability": 0.888671875 }, { "start": 2659.91, "end": 2660.33, "word": ".", "probability": 0.9052734375 } ] }, { "id": 747, "seek": 257888, "start": 2660.33, "end": 2662.97, "text": " And then we're going to have our test email.", "tokens": [ 51664, 400, 550, 321, 434, 516, 281, 362, 527, 1500, 3796, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.21354167262713114, "compression_ratio": 1.7254901960784315, "no_speech_prob": 0.0005440711975097656, "words": [ { "start": 2660.33, "end": 2660.51, "word": " And", "probability": 0.84912109375 }, { "start": 2660.51, "end": 2660.59, "word": " then", "probability": 0.72216796875 }, { "start": 2660.59, "end": 2660.73, "word": " we're", "probability": 0.927001953125 }, { "start": 2660.73, "end": 2660.77, "word": " going", "probability": 0.8330078125 }, { "start": 2660.77, "end": 2660.83, "word": " to", "probability": 0.9013671875 }, { "start": 2660.83, "end": 2661.13, "word": " have", "probability": 0.8828125 }, { "start": 2661.13, "end": 2661.53, "word": " our", "probability": 0.8154296875 }, { "start": 2661.53, "end": 2662.15, "word": " test", "probability": 0.8232421875 }, { "start": 2662.15, "end": 2662.65, "word": " email", "probability": 0.80126953125 }, { "start": 2662.65, "end": 2662.97, "word": ".", "probability": 0.94921875 } ] }, { "id": 748, "seek": 260600, "start": 2664.31, "end": 2665.41, "text": " Cool.", "tokens": [ 50364, 8561, 13, 50414 ], "temperature": 0.0, "avg_logprob": -0.22985692196581736, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.030670166015625, "words": [ { "start": 2664.31, "end": 2664.51, "word": " Cool", "probability": 0.035552978515625 }, { "start": 2664.51, "end": 2665.41, "word": ".", "probability": 0.7548828125 } ] }, { "id": 749, "seek": 260600, "start": 2665.69, "end": 2671.56, "text": " And then we're going to go ahead and print our example email.", "tokens": [ 50414, 400, 550, 321, 434, 516, 281, 352, 2286, 293, 4482, 527, 1365, 3796, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.22985692196581736, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.030670166015625, "words": [ { "start": 2665.69, "end": 2666.03, "word": " And", "probability": 0.74609375 }, { "start": 2666.03, "end": 2666.15, "word": " then", "probability": 0.72216796875 }, { "start": 2666.15, "end": 2666.39, "word": " we're", "probability": 0.88232421875 }, { "start": 2666.39, "end": 2666.43, "word": " going", "probability": 0.381103515625 }, { "start": 2666.43, "end": 2666.45, "word": " to", "probability": 0.9072265625 }, { "start": 2666.45, "end": 2666.57, "word": " go", "probability": 0.89599609375 }, { "start": 2666.57, "end": 2666.85, "word": " ahead", "probability": 0.8515625 }, { "start": 2666.85, "end": 2667.33, "word": " and", "probability": 0.88037109375 }, { "start": 2667.33, "end": 2667.99, "word": " print", "probability": 0.8671875 }, { "start": 2667.99, "end": 2668.63, "word": " our", "probability": 0.81103515625 }, { "start": 2668.63, "end": 2670.31, "word": " example", "probability": 0.86865234375 }, { "start": 2670.31, "end": 2671.11, "word": " email", "probability": 0.81689453125 }, { "start": 2671.11, "end": 2671.56, "word": ".", "probability": 0.80126953125 } ] }, { "id": 750, "seek": 260600, "start": 2672.47, "end": 2673.51, "text": " Oops.", "tokens": [ 50764, 21726, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.22985692196581736, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.030670166015625, "words": [ { "start": 2672.47, "end": 2672.81, "word": " Oops", "probability": 0.71728515625 }, { "start": 2672.81, "end": 2673.51, "word": ".", "probability": 0.58251953125 } ] }, { "id": 751, "seek": 260600, "start": 2673.77, "end": 2675.37, "text": " ExampleX.", "tokens": [ 50814, 24755, 781, 55, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.22985692196581736, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.030670166015625, "words": [ { "start": 2673.77, "end": 2674.67, "word": " ExampleX", "probability": 0.6509602864583334 }, { "start": 2674.67, "end": 2675.37, "word": ".", "probability": 0.908203125 } ] }, { "id": 752, "seek": 260600, "start": 2676.05, "end": 2680.17, "text": " And then here, we're going to do the same thing.", "tokens": [ 50964, 400, 550, 510, 11, 321, 434, 516, 281, 360, 264, 912, 551, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.22985692196581736, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.030670166015625, "words": [ { "start": 2676.05, "end": 2676.95, "word": " And", "probability": 0.88134765625 }, { "start": 2676.95, "end": 2677.35, "word": " then", "probability": 0.72509765625 }, { "start": 2677.35, "end": 2678.13, "word": " here", "probability": 0.75390625 }, { "start": 2678.13, "end": 2678.63, "word": ",", "probability": 0.59130859375 }, { "start": 2678.63, "end": 2679.31, "word": " we're", "probability": 0.927490234375 }, { "start": 2679.31, "end": 2679.39, "word": " going", "probability": 0.79443359375 }, { "start": 2679.39, "end": 2679.45, "word": " to", "probability": 0.90869140625 }, { "start": 2679.45, "end": 2679.55, "word": " do", "probability": 0.9072265625 }, { "start": 2679.55, "end": 2679.71, "word": " the", "probability": 0.8134765625 }, { "start": 2679.71, "end": 2679.87, "word": " same", "probability": 0.81591796875 }, { "start": 2679.87, "end": 2680.09, "word": " thing", "probability": 0.81787109375 }, { "start": 2680.09, "end": 2680.17, "word": ".", "probability": 0.7978515625 } ] }, { "id": 753, "seek": 260600, "start": 2680.17, "end": 2687.27, "text": " We're going to have exampleTVEC equals tf.idf vectorizer.", "tokens": [ 51164, 492, 434, 516, 281, 362, 1365, 51, 7540, 34, 6915, 256, 69, 13, 327, 69, 8062, 6545, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.22985692196581736, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.030670166015625, "words": [ { "start": 2680.17, "end": 2680.29, "word": " We're", "probability": 0.928955078125 }, { "start": 2680.29, "end": 2680.31, "word": " going", "probability": 0.8017578125 }, { "start": 2680.31, "end": 2680.31, "word": " to", "probability": 0.90576171875 }, { "start": 2680.31, "end": 2680.55, "word": " have", "probability": 0.892578125 }, { "start": 2680.55, "end": 2683.33, "word": " exampleTVEC", "probability": 0.466064453125 }, { "start": 2683.33, "end": 2684.27, "word": " equals", "probability": 0.38916015625 }, { "start": 2684.27, "end": 2685.03, "word": " tf", "probability": 0.52935791015625 }, { "start": 2685.03, "end": 2685.59, "word": ".idf", "probability": 0.6288248697916666 }, { "start": 2685.59, "end": 2686.61, "word": " vectorizer", "probability": 0.54315185546875 }, { "start": 2686.61, "end": 2687.27, "word": ".", "probability": 0.470703125 } ] }, { "id": 754, "seek": 260600, "start": 2687.27, "end": 2689.31, "text": " Capitals are important.", "tokens": [ 51514, 8363, 11118, 366, 1021, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.22985692196581736, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.030670166015625, "words": [ { "start": 2687.27, "end": 2687.63, "word": " Capitals", "probability": 0.918212890625 }, { "start": 2687.63, "end": 2687.91, "word": " are", "probability": 0.90673828125 }, { "start": 2687.91, "end": 2688.41, "word": " important", "probability": 0.7685546875 }, { "start": 2688.41, "end": 2689.31, "word": ".", "probability": 0.97021484375 } ] }, { "id": 755, "seek": 260600, "start": 2689.35, "end": 2691.43, "text": " Tokenizer equals tokenizer.", "tokens": [ 51614, 314, 8406, 6545, 6915, 14862, 6545, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.22985692196581736, "compression_ratio": 1.5714285714285714, "no_speech_prob": 0.030670166015625, "words": [ { "start": 2689.35, "end": 2689.73, "word": " Tokenizer", "probability": 0.9064127604166666 }, { "start": 2689.73, "end": 2690.15, "word": " equals", "probability": 0.8125 }, { "start": 2690.15, "end": 2690.91, "word": " tokenizer", "probability": 0.854736328125 }, { "start": 2690.91, "end": 2691.43, "word": ".", "probability": 0.65625 } ] }, { "id": 756, "seek": 263246, "start": 2691.43, "end": 2697.71, "text": " And then our example, tf.idf.", "tokens": [ 50364, 400, 550, 527, 1365, 11, 256, 69, 13, 327, 69, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.23392857440880366, "compression_ratio": 1.37012987012987, "no_speech_prob": 0.00885009765625, "words": [ { "start": 2691.43, "end": 2692.03, "word": " And", "probability": 0.35791015625 }, { "start": 2692.03, "end": 2692.25, "word": " then", "probability": 0.72705078125 }, { "start": 2692.25, "end": 2692.63, "word": " our", "probability": 0.7861328125 }, { "start": 2692.63, "end": 2695.55, "word": " example", "probability": 0.75244140625 }, { "start": 2695.55, "end": 2695.97, "word": ",", "probability": 0.223388671875 }, { "start": 2695.97, "end": 2696.75, "word": " tf", "probability": 0.764404296875 }, { "start": 2696.75, "end": 2697.35, "word": ".idf", "probability": 0.6981608072916666 }, { "start": 2697.35, "end": 2697.71, "word": ".", "probability": 0.343994140625 } ] }, { "id": 757, "seek": 263246, "start": 2697.71, "end": 2700.11, "text": " I'll just call it exampleX because it doesn't matter.", "tokens": [ 50664, 286, 603, 445, 818, 309, 1365, 55, 570, 309, 1177, 380, 1871, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.23392857440880366, "compression_ratio": 1.37012987012987, "no_speech_prob": 0.00885009765625, "words": [ { "start": 2697.71, "end": 2698.15, "word": " I'll", "probability": 0.838623046875 }, { "start": 2698.15, "end": 2698.27, "word": " just", "probability": 0.8876953125 }, { "start": 2698.27, "end": 2698.45, "word": " call", "probability": 0.8330078125 }, { "start": 2698.45, "end": 2698.55, "word": " it", "probability": 0.89892578125 }, { "start": 2698.55, "end": 2699.23, "word": " exampleX", "probability": 0.58447265625 }, { "start": 2699.23, "end": 2699.43, "word": " because", "probability": 0.337646484375 }, { "start": 2699.43, "end": 2699.53, "word": " it", "probability": 0.89990234375 }, { "start": 2699.53, "end": 2699.69, "word": " doesn't", "probability": 0.883056640625 }, { "start": 2699.69, "end": 2699.89, "word": " matter", "probability": 0.80419921875 }, { "start": 2699.89, "end": 2700.11, "word": ".", "probability": 0.76611328125 } ] }, { "id": 758, "seek": 263246, "start": 2700.11, "end": 2703.79, "text": " Once we print out our original exampleX, we don't need it anymore.", "tokens": [ 50764, 3443, 321, 4482, 484, 527, 3380, 1365, 55, 11, 321, 500, 380, 643, 309, 3602, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.23392857440880366, "compression_ratio": 1.37012987012987, "no_speech_prob": 0.00885009765625, "words": [ { "start": 2700.11, "end": 2700.13, "word": " Once", "probability": 0.85888671875 }, { "start": 2700.13, "end": 2700.71, "word": " we", "probability": 0.90185546875 }, { "start": 2700.71, "end": 2700.95, "word": " print", "probability": 0.865234375 }, { "start": 2700.95, "end": 2701.11, "word": " out", "probability": 0.7900390625 }, { "start": 2701.11, "end": 2701.31, "word": " our", "probability": 0.82177734375 }, { "start": 2701.31, "end": 2701.63, "word": " original", "probability": 0.83349609375 }, { "start": 2701.63, "end": 2702.23, "word": " exampleX", "probability": 0.94091796875 }, { "start": 2702.23, "end": 2702.27, "word": ",", "probability": 0.7109375 }, { "start": 2702.27, "end": 2702.35, "word": " we", "probability": 0.90478515625 }, { "start": 2702.35, "end": 2702.47, "word": " don't", "probability": 0.947509765625 }, { "start": 2702.47, "end": 2702.63, "word": " need", "probability": 0.81494140625 }, { "start": 2702.63, "end": 2702.73, "word": " it", "probability": 0.89892578125 }, { "start": 2702.73, "end": 2703.07, "word": " anymore", "probability": 0.7939453125 }, { "start": 2703.07, "end": 2703.79, "word": ".", "probability": 0.984375 } ] }, { "id": 759, "seek": 263246, "start": 2707.83, "end": 2709.89, "text": " ExampleTVEC.fitTransform.", "tokens": [ 50964, 24755, 781, 51, 7540, 34, 13, 6845, 33339, 837, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.23392857440880366, "compression_ratio": 1.37012987012987, "no_speech_prob": 0.00885009765625, "words": [ { "start": 2707.83, "end": 2708.55, "word": " ExampleTVEC", "probability": 0.606201171875 }, { "start": 2708.55, "end": 2709.27, "word": ".fitTransform", "probability": 0.80950927734375 }, { "start": 2709.27, "end": 2709.89, "word": ".", "probability": 0.51708984375 } ] }, { "id": 760, "seek": 263246, "start": 2713.63, "end": 2717.89, "text": " And then the brackets, test email.", "tokens": [ 51514, 400, 550, 264, 26179, 11, 1500, 3796, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.23392857440880366, "compression_ratio": 1.37012987012987, "no_speech_prob": 0.00885009765625, "words": [ { "start": 2713.63, "end": 2714.35, "word": " And", "probability": 0.391357421875 }, { "start": 2714.35, "end": 2715.07, "word": " then", "probability": 0.72607421875 }, { "start": 2715.07, "end": 2715.19, "word": " the", "probability": 0.78515625 }, { "start": 2715.19, "end": 2715.57, "word": " brackets", "probability": 0.83544921875 }, { "start": 2715.57, "end": 2716.05, "word": ",", "probability": 0.634765625 }, { "start": 2716.05, "end": 2716.65, "word": " test", "probability": 0.7890625 }, { "start": 2716.65, "end": 2717.17, "word": " email", "probability": 0.405029296875 }, { "start": 2717.17, "end": 2717.89, "word": ".", "probability": 0.88623046875 } ] }, { "id": 761, "seek": 265692, "start": 2718.47, "end": 2722.75, "text": " And then we can print our exampleX.", "tokens": [ 50414, 400, 550, 321, 393, 4482, 527, 1365, 55, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.24237805150630998, "compression_ratio": 1.4545454545454546, "no_speech_prob": 0.004680633544921875, "words": [ { "start": 2718.47, "end": 2718.95, "word": " And", "probability": 0.389404296875 }, { "start": 2718.95, "end": 2719.07, "word": " then", "probability": 0.71142578125 }, { "start": 2719.07, "end": 2719.17, "word": " we", "probability": 0.88134765625 }, { "start": 2719.17, "end": 2719.33, "word": " can", "probability": 0.888671875 }, { "start": 2719.33, "end": 2719.75, "word": " print", "probability": 0.87939453125 }, { "start": 2719.75, "end": 2720.25, "word": " our", "probability": 0.81005859375 }, { "start": 2720.25, "end": 2722.27, "word": " exampleX", "probability": 0.4344024658203125 }, { "start": 2722.27, "end": 2722.75, "word": ".", "probability": 0.81201171875 } ] }, { "id": 762, "seek": 265692, "start": 2723.67, "end": 2726.03, "text": " So I'm going to let that sit for a moment.", "tokens": [ 50664, 407, 286, 478, 516, 281, 718, 300, 1394, 337, 257, 1623, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.24237805150630998, "compression_ratio": 1.4545454545454546, "no_speech_prob": 0.004680633544921875, "words": [ { "start": 2723.67, "end": 2724.15, "word": " So", "probability": 0.830078125 }, { "start": 2724.15, "end": 2724.37, "word": " I'm", "probability": 0.836181640625 }, { "start": 2724.37, "end": 2724.43, "word": " going", "probability": 0.47314453125 }, { "start": 2724.43, "end": 2724.43, "word": " to", "probability": 0.89599609375 }, { "start": 2724.43, "end": 2724.57, "word": " let", "probability": 0.89306640625 }, { "start": 2724.57, "end": 2724.77, "word": " that", "probability": 0.87890625 }, { "start": 2724.77, "end": 2724.97, "word": " sit", "probability": 0.91015625 }, { "start": 2724.97, "end": 2725.17, "word": " for", "probability": 0.89501953125 }, { "start": 2725.31, "end": 2725.55, "word": " a moment", "probability": 0.9140625 }, { "start": 2725.55, "end": 2726.03, "word": ".", "probability": 0.392333984375 } ] }, { "id": 763, "seek": 265692, "start": 2726.13, "end": 2728.23, "text": " Let you guys copy that down.", "tokens": [ 50764, 961, 291, 1074, 5055, 300, 760, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.24237805150630998, "compression_ratio": 1.4545454545454546, "no_speech_prob": 0.004680633544921875, "words": [ { "start": 2726.13, "end": 2726.31, "word": " Let", "probability": 0.7373046875 }, { "start": 2726.31, "end": 2726.45, "word": " you", "probability": 0.8974609375 }, { "start": 2726.45, "end": 2726.67, "word": " guys", "probability": 0.8818359375 }, { "start": 2726.67, "end": 2727.11, "word": " copy", "probability": 0.779296875 }, { "start": 2727.11, "end": 2727.37, "word": " that", "probability": 0.88134765625 }, { "start": 2727.37, "end": 2727.75, "word": " down", "probability": 0.81787109375 }, { "start": 2727.75, "end": 2728.23, "word": ".", "probability": 0.9638671875 } ] }, { "id": 764, "seek": 265692, "start": 2732.69, "end": 2735.21, "text": " I'm going to just look ahead real quick.", "tokens": [ 50964, 286, 478, 516, 281, 445, 574, 2286, 957, 1702, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.24237805150630998, "compression_ratio": 1.4545454545454546, "no_speech_prob": 0.004680633544921875, "words": [ { "start": 2732.69, "end": 2733.17, "word": " I'm", "probability": 0.552734375 }, { "start": 2733.17, "end": 2733.17, "word": " going", "probability": 0.6435546875 }, { "start": 2733.17, "end": 2733.19, "word": " to", "probability": 0.89990234375 }, { "start": 2733.19, "end": 2733.37, "word": " just", "probability": 0.85986328125 }, { "start": 2733.37, "end": 2733.77, "word": " look", "probability": 0.91259765625 }, { "start": 2733.77, "end": 2734.11, "word": " ahead", "probability": 0.81689453125 }, { "start": 2734.11, "end": 2734.35, "word": " real", "probability": 0.8466796875 }, { "start": 2734.35, "end": 2734.73, "word": " quick", "probability": 0.916015625 }, { "start": 2734.73, "end": 2735.21, "word": ".", "probability": 0.91162109375 } ] }, { "id": 765, "seek": 265692, "start": 2735.31, "end": 2736.99, "text": " We are doing great.", "tokens": [ 51114, 492, 366, 884, 869, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.24237805150630998, "compression_ratio": 1.4545454545454546, "no_speech_prob": 0.004680633544921875, "words": [ { "start": 2735.31, "end": 2735.43, "word": " We", "probability": 0.74560546875 }, { "start": 2735.43, "end": 2735.53, "word": " are", "probability": 0.74755859375 }, { "start": 2735.53, "end": 2735.79, "word": " doing", "probability": 0.9169921875 }, { "start": 2735.79, "end": 2736.51, "word": " great", "probability": 0.87841796875 }, { "start": 2736.51, "end": 2736.99, "word": ".", "probability": 0.95654296875 } ] }, { "id": 766, "seek": 265692, "start": 2740.67, "end": 2741.37, "text": " Okay.", "tokens": [ 51364, 1033, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.24237805150630998, "compression_ratio": 1.4545454545454546, "no_speech_prob": 0.004680633544921875, "words": [ { "start": 2740.67, "end": 2741.15, "word": " Okay", "probability": 0.673828125 }, { "start": 2741.15, "end": 2741.37, "word": ".", "probability": 0.5458984375 } ] }, { "id": 767, "seek": 265692, "start": 2741.37, "end": 2743.31, "text": " So I'm going to go ahead and run this now.", "tokens": [ 51414, 407, 286, 478, 516, 281, 352, 2286, 293, 1190, 341, 586, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.24237805150630998, "compression_ratio": 1.4545454545454546, "no_speech_prob": 0.004680633544921875, "words": [ { "start": 2741.37, "end": 2741.73, "word": " So", "probability": 0.89990234375 }, { "start": 2741.73, "end": 2741.89, "word": " I'm", "probability": 0.98046875 }, { "start": 2741.89, "end": 2741.89, "word": " going", "probability": 0.8515625 }, { "start": 2741.89, "end": 2741.91, "word": " to", "probability": 0.90478515625 }, { "start": 2741.91, "end": 2742.03, "word": " go", "probability": 0.89404296875 }, { "start": 2742.03, "end": 2742.23, "word": " ahead", "probability": 0.85107421875 }, { "start": 2742.23, "end": 2742.55, "word": " and", "probability": 0.89599609375 }, { "start": 2742.55, "end": 2742.83, "word": " run", "probability": 0.9111328125 }, { "start": 2742.83, "end": 2743.07, "word": " this", "probability": 0.8837890625 }, { "start": 2743.07, "end": 2743.27, "word": " now", "probability": 0.8681640625 }, { "start": 2743.27, "end": 2743.31, "word": ".", "probability": 0.93994140625 } ] }, { "id": 768, "seek": 265692, "start": 2743.31, "end": 2744.87, "text": " I pressed Shift-Enter.", "tokens": [ 51514, 286, 17355, 28304, 12, 16257, 391, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.24237805150630998, "compression_ratio": 1.4545454545454546, "no_speech_prob": 0.004680633544921875, "words": [ { "start": 2743.31, "end": 2743.39, "word": " I", "probability": 0.99560546875 }, { "start": 2743.39, "end": 2743.63, "word": " pressed", "probability": 0.36474609375 }, { "start": 2743.63, "end": 2743.99, "word": " Shift", "probability": 0.378662109375 }, { "start": 2743.99, "end": 2744.39, "word": "-Enter", "probability": 0.6866861979166666 }, { "start": 2744.39, "end": 2744.87, "word": ".", "probability": 0.83984375 } ] }, { "id": 769, "seek": 268390, "start": 2745.91, "end": 2753.09, "text": " And if we look at our count vectorizer of test email, we see these different numbers.", "tokens": [ 50414, 400, 498, 321, 574, 412, 527, 1207, 8062, 6545, 295, 1500, 3796, 11, 321, 536, 613, 819, 3547, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.19883578592071346, "compression_ratio": 1.6093023255813954, "no_speech_prob": 0.0018968582153320312, "words": [ { "start": 2745.91, "end": 2746.43, "word": " And", "probability": 0.26953125 }, { "start": 2746.43, "end": 2746.69, "word": " if", "probability": 0.85546875 }, { "start": 2746.69, "end": 2746.77, "word": " we", "probability": 0.89892578125 }, { "start": 2746.77, "end": 2746.99, "word": " look", "probability": 0.91357421875 }, { "start": 2746.99, "end": 2747.27, "word": " at", "probability": 0.90185546875 }, { "start": 2747.27, "end": 2747.51, "word": " our", "probability": 0.7939453125 }, { "start": 2747.51, "end": 2747.95, "word": " count", "probability": 0.59375 }, { "start": 2747.95, "end": 2748.53, "word": " vectorizer", "probability": 0.913818359375 }, { "start": 2748.53, "end": 2748.87, "word": " of", "probability": 0.89111328125 }, { "start": 2748.87, "end": 2749.21, "word": " test", "probability": 0.60693359375 }, { "start": 2749.21, "end": 2749.53, "word": " email", "probability": 0.69482421875 }, { "start": 2749.53, "end": 2750.05, "word": ",", "probability": 0.77783203125 }, { "start": 2750.05, "end": 2750.93, "word": " we", "probability": 0.88037109375 }, { "start": 2750.93, "end": 2751.29, "word": " see", "probability": 0.8203125 }, { "start": 2751.29, "end": 2751.71, "word": " these", "probability": 0.72021484375 }, { "start": 2751.71, "end": 2752.03, "word": " different", "probability": 0.69287109375 }, { "start": 2752.03, "end": 2752.59, "word": " numbers", "probability": 0.87158203125 }, { "start": 2752.59, "end": 2753.09, "word": ".", "probability": 0.409423828125 } ] }, { "id": 770, "seek": 268390, "start": 2753.09, "end": 2756.15, "text": " And what these numbers represent are tokens.", "tokens": [ 50764, 400, 437, 613, 3547, 2906, 366, 22667, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.19883578592071346, "compression_ratio": 1.6093023255813954, "no_speech_prob": 0.0018968582153320312, "words": [ { "start": 2753.09, "end": 2753.13, "word": " And", "probability": 0.81005859375 }, { "start": 2753.13, "end": 2753.31, "word": " what", "probability": 0.8779296875 }, { "start": 2753.31, "end": 2753.57, "word": " these", "probability": 0.70263671875 }, { "start": 2753.57, "end": 2753.89, "word": " numbers", "probability": 0.861328125 }, { "start": 2753.89, "end": 2754.35, "word": " represent", "probability": 0.740234375 }, { "start": 2754.35, "end": 2754.91, "word": " are", "probability": 0.87841796875 }, { "start": 2754.91, "end": 2755.63, "word": " tokens", "probability": 0.73681640625 }, { "start": 2755.63, "end": 2756.15, "word": ".", "probability": 0.9345703125 } ] }, { "id": 771, "seek": 268390, "start": 2756.15, "end": 2759.39, "text": " So, for example, a very nice game.", "tokens": [ 50914, 407, 11, 337, 1365, 11, 257, 588, 1481, 1216, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.19883578592071346, "compression_ratio": 1.6093023255813954, "no_speech_prob": 0.0018968582153320312, "words": [ { "start": 2756.15, "end": 2756.35, "word": " So", "probability": 0.8251953125 }, { "start": 2756.35, "end": 2756.97, "word": ",", "probability": 0.33056640625 }, { "start": 2756.97, "end": 2757.35, "word": " for", "probability": 0.888671875 }, { "start": 2757.35, "end": 2757.71, "word": " example", "probability": 0.9345703125 }, { "start": 2757.71, "end": 2757.97, "word": ",", "probability": 0.92724609375 }, { "start": 2758.09, "end": 2758.33, "word": " a very", "probability": 0.6318359375 }, { "start": 2758.33, "end": 2758.67, "word": " nice", "probability": 0.80078125 }, { "start": 2758.67, "end": 2759.17, "word": " game", "probability": 0.80322265625 }, { "start": 2759.17, "end": 2759.39, "word": ".", "probability": 0.1893310546875 } ] }, { "id": 772, "seek": 268390, "start": 2759.39, "end": 2761.17, "text": " A would be token 1.", "tokens": [ 51064, 316, 576, 312, 14862, 502, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.19883578592071346, "compression_ratio": 1.6093023255813954, "no_speech_prob": 0.0018968582153320312, "words": [ { "start": 2759.39, "end": 2759.51, "word": " A", "probability": 0.796875 }, { "start": 2759.51, "end": 2759.69, "word": " would", "probability": 0.84130859375 }, { "start": 2759.69, "end": 2759.87, "word": " be", "probability": 0.90283203125 }, { "start": 2759.87, "end": 2760.11, "word": " token", "probability": 0.80712890625 }, { "start": 2760.11, "end": 2760.65, "word": " 1", "probability": 0.2626953125 }, { "start": 2760.65, "end": 2761.17, "word": ".", "probability": 0.666015625 } ] }, { "id": 773, "seek": 268390, "start": 2761.17, "end": 2762.75, "text": " Very would be token 2.", "tokens": [ 51164, 4372, 576, 312, 14862, 568, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.19883578592071346, "compression_ratio": 1.6093023255813954, "no_speech_prob": 0.0018968582153320312, "words": [ { "start": 2761.17, "end": 2761.39, "word": " Very", "probability": 0.869140625 }, { "start": 2761.39, "end": 2761.59, "word": " would", "probability": 0.83203125 }, { "start": 2761.59, "end": 2761.77, "word": " be", "probability": 0.9033203125 }, { "start": 2761.77, "end": 2761.99, "word": " token", "probability": 0.8291015625 }, { "start": 2761.99, "end": 2762.51, "word": " 2", "probability": 0.986328125 }, { "start": 2762.51, "end": 2762.75, "word": ".", "probability": 0.97509765625 } ] }, { "id": 774, "seek": 268390, "start": 2762.75, "end": 2764.13, "text": " Nice would be token 3.", "tokens": [ 51264, 5490, 576, 312, 14862, 805, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.19883578592071346, "compression_ratio": 1.6093023255813954, "no_speech_prob": 0.0018968582153320312, "words": [ { "start": 2762.75, "end": 2763.01, "word": " Nice", "probability": 0.84375 }, { "start": 2763.01, "end": 2763.17, "word": " would", "probability": 0.85400390625 }, { "start": 2763.17, "end": 2763.33, "word": " be", "probability": 0.90283203125 }, { "start": 2763.33, "end": 2763.53, "word": " token", "probability": 0.830078125 }, { "start": 2763.53, "end": 2763.97, "word": " 3", "probability": 0.99365234375 }, { "start": 2763.97, "end": 2764.13, "word": ".", "probability": 0.96337890625 } ] }, { "id": 775, "seek": 268390, "start": 2764.13, "end": 2765.97, "text": " Game would be token 4.", "tokens": [ 51314, 7522, 576, 312, 14862, 1017, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.19883578592071346, "compression_ratio": 1.6093023255813954, "no_speech_prob": 0.0018968582153320312, "words": [ { "start": 2764.13, "end": 2764.35, "word": " Game", "probability": 0.8125 }, { "start": 2764.35, "end": 2764.51, "word": " would", "probability": 0.85009765625 }, { "start": 2764.51, "end": 2764.73, "word": " be", "probability": 0.90283203125 }, { "start": 2764.73, "end": 2764.97, "word": " token", "probability": 0.82275390625 }, { "start": 2764.97, "end": 2765.45, "word": " 4", "probability": 0.994140625 }, { "start": 2765.45, "end": 2765.97, "word": ".", "probability": 0.9951171875 } ] }, { "id": 776, "seek": 268390, "start": 2766.53, "end": 2771.85, "text": " So in this case, Scikit-Learn actually knows the best way that it wants to tokenize things.", "tokens": [ 51414, 407, 294, 341, 1389, 11, 16942, 22681, 12, 11020, 1083, 767, 3255, 264, 1151, 636, 300, 309, 2738, 281, 14862, 1125, 721, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.19883578592071346, "compression_ratio": 1.6093023255813954, "no_speech_prob": 0.0018968582153320312, "words": [ { "start": 2766.53, "end": 2766.81, "word": " So", "probability": 0.8525390625 }, { "start": 2766.81, "end": 2766.93, "word": " in", "probability": 0.6875 }, { "start": 2766.93, "end": 2767.07, "word": " this", "probability": 0.8759765625 }, { "start": 2767.07, "end": 2767.31, "word": " case", "probability": 0.82080078125 }, { "start": 2767.31, "end": 2767.39, "word": ",", "probability": 0.74072265625 }, { "start": 2767.39, "end": 2767.57, "word": " Scikit", "probability": 0.74658203125 }, { "start": 2767.57, "end": 2767.89, "word": "-Learn", "probability": 0.7422688802083334 }, { "start": 2767.89, "end": 2768.97, "word": " actually", "probability": 0.75048828125 }, { "start": 2768.97, "end": 2769.19, "word": " knows", "probability": 0.7685546875 }, { "start": 2769.19, "end": 2769.35, "word": " the", "probability": 0.81396484375 }, { "start": 2769.35, "end": 2769.57, "word": " best", "probability": 0.810546875 }, { "start": 2769.57, "end": 2769.85, "word": " way", "probability": 0.88916015625 }, { "start": 2769.85, "end": 2769.99, "word": " that", "probability": 0.85986328125 }, { "start": 2769.99, "end": 2770.09, "word": " it", "probability": 0.89990234375 }, { "start": 2770.09, "end": 2770.27, "word": " wants", "probability": 0.7275390625 }, { "start": 2770.27, "end": 2770.45, "word": " to", "probability": 0.9013671875 }, { "start": 2770.45, "end": 2770.93, "word": " tokenize", "probability": 0.850830078125 }, { "start": 2770.93, "end": 2771.41, "word": " things", "probability": 0.72802734375 }, { "start": 2771.41, "end": 2771.85, "word": ".", "probability": 0.923828125 } ] }, { "id": 777, "seek": 270454, "start": 2771.85, "end": 2777.81, "text": " So the letters, for example, 0, this does not necessarily represent East.", "tokens": [ 50364, 407, 264, 7825, 11, 337, 1365, 11, 1958, 11, 341, 775, 406, 4725, 2906, 6747, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.2074999976158142, "compression_ratio": 1.547486033519553, "no_speech_prob": 0.005641937255859375, "words": [ { "start": 2771.85, "end": 2772.03, "word": " So", "probability": 0.3603515625 }, { "start": 2772.03, "end": 2772.51, "word": " the", "probability": 0.61376953125 }, { "start": 2772.51, "end": 2773.91, "word": " letters", "probability": 0.72705078125 }, { "start": 2773.91, "end": 2773.99, "word": ",", "probability": 0.64208984375 }, { "start": 2773.99, "end": 2774.09, "word": " for", "probability": 0.89306640625 }, { "start": 2774.09, "end": 2774.35, "word": " example", "probability": 0.921875 }, { "start": 2774.35, "end": 2774.49, "word": ",", "probability": 0.80224609375 }, { "start": 2774.49, "end": 2774.73, "word": " 0", "probability": 0.2474365234375 }, { "start": 2774.73, "end": 2774.89, "word": ",", "probability": 0.6298828125 }, { "start": 2774.89, "end": 2774.99, "word": " this", "probability": 0.80908203125 }, { "start": 2774.99, "end": 2775.17, "word": " does", "probability": 0.9140625 }, { "start": 2775.17, "end": 2775.39, "word": " not", "probability": 0.8896484375 }, { "start": 2775.39, "end": 2776.01, "word": " necessarily", "probability": 0.81201171875 }, { "start": 2776.01, "end": 2776.73, "word": " represent", "probability": 0.74658203125 }, { "start": 2776.73, "end": 2777.33, "word": " East", "probability": 0.417236328125 }, { "start": 2777.33, "end": 2777.81, "word": ".", "probability": 0.86962890625 } ] }, { "id": 778, "seek": 270454, "start": 2778.93, "end": 2783.31, "text": " And so, basically, Scikit-Learn knows how these tokens are used.", "tokens": [ 50664, 400, 370, 11, 1936, 11, 16942, 22681, 12, 11020, 1083, 3255, 577, 613, 22667, 366, 1143, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.2074999976158142, "compression_ratio": 1.547486033519553, "no_speech_prob": 0.005641937255859375, "words": [ { "start": 2778.93, "end": 2778.95, "word": " And", "probability": 0.67431640625 }, { "start": 2778.95, "end": 2779.29, "word": " so", "probability": 0.8916015625 }, { "start": 2779.29, "end": 2779.43, "word": ",", "probability": 0.13818359375 }, { "start": 2779.43, "end": 2779.89, "word": " basically", "probability": 0.8935546875 }, { "start": 2779.89, "end": 2780.77, "word": ",", "probability": 0.84765625 }, { "start": 2780.77, "end": 2781.09, "word": " Scikit", "probability": 0.76416015625 }, { "start": 2781.09, "end": 2781.31, "word": "-Learn", "probability": 0.736572265625 }, { "start": 2781.31, "end": 2781.89, "word": " knows", "probability": 0.7548828125 }, { "start": 2781.89, "end": 2782.21, "word": " how", "probability": 0.90185546875 }, { "start": 2782.21, "end": 2782.43, "word": " these", "probability": 0.7138671875 }, { "start": 2782.43, "end": 2782.63, "word": " tokens", "probability": 0.767578125 }, { "start": 2782.63, "end": 2782.83, "word": " are", "probability": 0.90185546875 }, { "start": 2782.83, "end": 2783.15, "word": " used", "probability": 0.8232421875 }, { "start": 2783.15, "end": 2783.31, "word": ".", "probability": 0.63037109375 } ] }, { "id": 779, "seek": 270454, "start": 2783.31, "end": 2784.95, "text": " We don't know how these tokens are used.", "tokens": [ 50914, 492, 500, 380, 458, 577, 613, 22667, 366, 1143, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.2074999976158142, "compression_ratio": 1.547486033519553, "no_speech_prob": 0.005641937255859375, "words": [ { "start": 2783.31, "end": 2783.51, "word": " We", "probability": 0.9013671875 }, { "start": 2783.51, "end": 2783.71, "word": " don't", "probability": 0.945556640625 }, { "start": 2783.71, "end": 2783.87, "word": " know", "probability": 0.8154296875 }, { "start": 2783.87, "end": 2784.01, "word": " how", "probability": 0.900390625 }, { "start": 2784.01, "end": 2784.19, "word": " these", "probability": 0.71484375 }, { "start": 2784.19, "end": 2784.43, "word": " tokens", "probability": 0.744140625 }, { "start": 2784.43, "end": 2784.61, "word": " are", "probability": 0.9013671875 }, { "start": 2784.61, "end": 2784.83, "word": " used", "probability": 0.82080078125 }, { "start": 2784.83, "end": 2784.95, "word": ".", "probability": 0.69189453125 } ] }, { "id": 780, "seek": 270454, "start": 2784.95, "end": 2792.49, "text": " But something that we can point out is we see token 16 shows up twice and token 9 shows up twice.", "tokens": [ 51014, 583, 746, 300, 321, 393, 935, 484, 307, 321, 536, 14862, 3165, 3110, 493, 6091, 293, 14862, 1722, 3110, 493, 6091, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.2074999976158142, "compression_ratio": 1.547486033519553, "no_speech_prob": 0.005641937255859375, "words": [ { "start": 2784.95, "end": 2785.07, "word": " But", "probability": 0.88330078125 }, { "start": 2785.07, "end": 2785.33, "word": " something", "probability": 0.72314453125 }, { "start": 2785.33, "end": 2785.51, "word": " that", "probability": 0.85546875 }, { "start": 2785.51, "end": 2785.63, "word": " we", "probability": 0.904296875 }, { "start": 2785.63, "end": 2786.01, "word": " can", "probability": 0.89306640625 }, { "start": 2786.01, "end": 2786.29, "word": " point", "probability": 0.8623046875 }, { "start": 2786.29, "end": 2786.65, "word": " out", "probability": 0.8212890625 }, { "start": 2786.65, "end": 2787.23, "word": " is", "probability": 0.78564453125 }, { "start": 2787.23, "end": 2787.35, "word": " we", "probability": 0.82470703125 }, { "start": 2787.35, "end": 2787.61, "word": " see", "probability": 0.79638671875 }, { "start": 2787.61, "end": 2787.93, "word": " token", "probability": 0.59814453125 }, { "start": 2787.93, "end": 2788.39, "word": " 16", "probability": 0.7099609375 }, { "start": 2788.39, "end": 2788.99, "word": " shows", "probability": 0.79443359375 }, { "start": 2788.99, "end": 2789.17, "word": " up", "probability": 0.9091796875 }, { "start": 2789.17, "end": 2789.61, "word": " twice", "probability": 0.85791015625 }, { "start": 2789.61, "end": 2789.93, "word": " and", "probability": 0.5830078125 }, { "start": 2789.93, "end": 2790.19, "word": " token", "probability": 0.81298828125 }, { "start": 2790.19, "end": 2790.69, "word": " 9", "probability": 0.78759765625 }, { "start": 2790.69, "end": 2791.37, "word": " shows", "probability": 0.78173828125 }, { "start": 2791.37, "end": 2791.55, "word": " up", "probability": 0.912109375 }, { "start": 2791.55, "end": 2792.01, "word": " twice", "probability": 0.869140625 }, { "start": 2792.01, "end": 2792.49, "word": ".", "probability": 0.98681640625 } ] }, { "id": 781, "seek": 273088, "start": 2792.49, "end": 2801.85, "text": " So based on what we saw up above, we can guarantee that either token 16 or token 9 is unsubscribe.", "tokens": [ 50364, 407, 2361, 322, 437, 321, 1866, 493, 3673, 11, 321, 393, 10815, 300, 2139, 14862, 3165, 420, 14862, 1722, 307, 2693, 9493, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.17670294943820225, "compression_ratio": 1.4759615384615385, "no_speech_prob": 0.093994140625, "words": [ { "start": 2792.49, "end": 2792.89, "word": " So", "probability": 0.438232421875 }, { "start": 2792.89, "end": 2793.29, "word": " based", "probability": 0.6240234375 }, { "start": 2793.29, "end": 2793.43, "word": " on", "probability": 0.90869140625 }, { "start": 2793.43, "end": 2793.53, "word": " what", "probability": 0.88427734375 }, { "start": 2793.53, "end": 2793.67, "word": " we", "probability": 0.90380859375 }, { "start": 2793.67, "end": 2793.95, "word": " saw", "probability": 0.81298828125 }, { "start": 2793.95, "end": 2794.23, "word": " up", "probability": 0.8935546875 }, { "start": 2794.23, "end": 2794.79, "word": " above", "probability": 0.90283203125 }, { "start": 2794.79, "end": 2795.43, "word": ",", "probability": 0.7412109375 }, { "start": 2795.43, "end": 2795.73, "word": " we", "probability": 0.8681640625 }, { "start": 2795.73, "end": 2795.91, "word": " can", "probability": 0.8876953125 }, { "start": 2795.91, "end": 2796.31, "word": " guarantee", "probability": 0.828125 }, { "start": 2796.31, "end": 2796.97, "word": " that", "probability": 0.873046875 }, { "start": 2796.97, "end": 2797.61, "word": " either", "probability": 0.7685546875 }, { "start": 2797.61, "end": 2797.85, "word": " token", "probability": 0.66357421875 }, { "start": 2797.85, "end": 2798.23, "word": " 16", "probability": 0.54541015625 }, { "start": 2798.23, "end": 2798.61, "word": " or", "probability": 0.876953125 }, { "start": 2798.61, "end": 2798.91, "word": " token", "probability": 0.748046875 }, { "start": 2798.91, "end": 2799.37, "word": " 9", "probability": 0.78466796875 }, { "start": 2799.37, "end": 2800.53, "word": " is", "probability": 0.88720703125 }, { "start": 2800.53, "end": 2801.27, "word": " unsubscribe", "probability": 0.6953125 }, { "start": 2801.27, "end": 2801.85, "word": ".", "probability": 0.2471923828125 } ] }, { "id": 782, "seek": 273088, "start": 2801.85, "end": 2805.95, "text": " And then the other one is list.debian.org.", "tokens": [ 50814, 400, 550, 264, 661, 472, 307, 1329, 13, 1479, 20196, 13, 4646, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.17670294943820225, "compression_ratio": 1.4759615384615385, "no_speech_prob": 0.093994140625, "words": [ { "start": 2801.85, "end": 2802.03, "word": " And", "probability": 0.8427734375 }, { "start": 2802.03, "end": 2802.17, "word": " then", "probability": 0.7158203125 }, { "start": 2802.17, "end": 2802.41, "word": " the", "probability": 0.80615234375 }, { "start": 2802.41, "end": 2802.69, "word": " other", "probability": 0.78125 }, { "start": 2802.69, "end": 2803.11, "word": " one", "probability": 0.81787109375 }, { "start": 2803.11, "end": 2804.03, "word": " is", "probability": 0.89306640625 }, { "start": 2804.03, "end": 2804.43, "word": " list", "probability": 0.76513671875 }, { "start": 2804.43, "end": 2804.85, "word": ".debian", "probability": 0.84423828125 }, { "start": 2804.85, "end": 2805.35, "word": ".org", "probability": 0.970458984375 }, { "start": 2805.35, "end": 2805.95, "word": ".", "probability": 0.89111328125 } ] }, { "id": 783, "seek": 273088, "start": 2806.35, "end": 2807.51, "text": " And so these show up twice.", "tokens": [ 51014, 400, 370, 613, 855, 493, 6091, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.17670294943820225, "compression_ratio": 1.4759615384615385, "no_speech_prob": 0.093994140625, "words": [ { "start": 2806.35, "end": 2806.53, "word": " And", "probability": 0.81689453125 }, { "start": 2806.53, "end": 2806.65, "word": " so", "probability": 0.89111328125 }, { "start": 2806.65, "end": 2806.83, "word": " these", "probability": 0.64794921875 }, { "start": 2806.83, "end": 2807.05, "word": " show", "probability": 0.87548828125 }, { "start": 2807.05, "end": 2807.15, "word": " up", "probability": 0.89501953125 }, { "start": 2807.15, "end": 2807.39, "word": " twice", "probability": 0.86669921875 }, { "start": 2807.39, "end": 2807.51, "word": ".", "probability": 0.869140625 } ] }, { "id": 784, "seek": 273088, "start": 2807.51, "end": 2810.73, "text": " So this is exactly the same as if we had done the word count ourselves.", "tokens": [ 51114, 407, 341, 307, 2293, 264, 912, 382, 498, 321, 632, 1096, 264, 1349, 1207, 4175, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.17670294943820225, "compression_ratio": 1.4759615384615385, "no_speech_prob": 0.093994140625, "words": [ { "start": 2807.51, "end": 2807.57, "word": " So", "probability": 0.73681640625 }, { "start": 2807.57, "end": 2807.69, "word": " this", "probability": 0.87060546875 }, { "start": 2807.69, "end": 2807.81, "word": " is", "probability": 0.90478515625 }, { "start": 2807.81, "end": 2808.11, "word": " exactly", "probability": 0.77978515625 }, { "start": 2808.11, "end": 2808.33, "word": " the", "probability": 0.81103515625 }, { "start": 2808.33, "end": 2808.51, "word": " same", "probability": 0.8173828125 }, { "start": 2808.51, "end": 2808.65, "word": " as", "probability": 0.8955078125 }, { "start": 2808.65, "end": 2808.77, "word": " if", "probability": 0.90185546875 }, { "start": 2808.77, "end": 2808.85, "word": " we", "probability": 0.90380859375 }, { "start": 2808.85, "end": 2808.95, "word": " had", "probability": 0.80712890625 }, { "start": 2808.95, "end": 2809.09, "word": " done", "probability": 0.78515625 }, { "start": 2809.09, "end": 2809.23, "word": " the", "probability": 0.81689453125 }, { "start": 2809.23, "end": 2809.39, "word": " word", "probability": 0.79150390625 }, { "start": 2809.39, "end": 2809.63, "word": " count", "probability": 0.78955078125 }, { "start": 2809.63, "end": 2810.13, "word": " ourselves", "probability": 0.73681640625 }, { "start": 2810.13, "end": 2810.73, "word": ".", "probability": 0.97802734375 } ] }, { "id": 785, "seek": 273088, "start": 2811.39, "end": 2818.83, "text": " The TF-IDF vectorizer, however, uses a bit of a weight algorithm.", "tokens": [ 51264, 440, 40964, 12, 2777, 37, 8062, 6545, 11, 4461, 11, 4960, 257, 857, 295, 257, 3364, 9284, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.17670294943820225, "compression_ratio": 1.4759615384615385, "no_speech_prob": 0.093994140625, "words": [ { "start": 2811.39, "end": 2811.99, "word": " The", "probability": 0.8212890625 }, { "start": 2811.99, "end": 2812.21, "word": " TF", "probability": 0.5283203125 }, { "start": 2812.21, "end": 2812.61, "word": "-IDF", "probability": 0.88818359375 }, { "start": 2812.61, "end": 2813.35, "word": " vectorizer", "probability": 0.872314453125 }, { "start": 2813.35, "end": 2813.55, "word": ",", "probability": 0.76025390625 }, { "start": 2813.55, "end": 2813.93, "word": " however", "probability": 0.89013671875 }, { "start": 2813.93, "end": 2814.23, "word": ",", "probability": 0.97314453125 }, { "start": 2814.23, "end": 2814.65, "word": " uses", "probability": 0.78759765625 }, { "start": 2814.99, "end": 2815.23, "word": " a bit", "probability": 0.91064453125 }, { "start": 2815.23, "end": 2815.53, "word": " of", "probability": 0.9091796875 }, { "start": 2816.03, "end": 2817.87, "word": " a weight", "probability": 0.67919921875 }, { "start": 2817.87, "end": 2818.39, "word": " algorithm", "probability": 0.82080078125 }, { "start": 2818.39, "end": 2818.83, "word": ".", "probability": 0.84716796875 } ] }, { "id": 786, "seek": 276008, "start": 2818.83, "end": 2823.27, "text": " And so everything that was set as 1 has this 0.204 weight.", "tokens": [ 50364, 400, 370, 1203, 300, 390, 992, 382, 502, 575, 341, 1958, 13, 2009, 19, 3364, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.16626213707970183, "compression_ratio": 1.6055045871559632, "no_speech_prob": 0.058319091796875, "words": [ { "start": 2818.83, "end": 2819.15, "word": " And", "probability": 0.58837890625 }, { "start": 2819.15, "end": 2819.43, "word": " so", "probability": 0.89404296875 }, { "start": 2819.43, "end": 2819.77, "word": " everything", "probability": 0.75146484375 }, { "start": 2819.77, "end": 2820.03, "word": " that", "probability": 0.8779296875 }, { "start": 2820.03, "end": 2820.21, "word": " was", "probability": 0.89306640625 }, { "start": 2820.21, "end": 2820.49, "word": " set", "probability": 0.88623046875 }, { "start": 2820.49, "end": 2820.79, "word": " as", "probability": 0.89892578125 }, { "start": 2820.79, "end": 2821.07, "word": " 1", "probability": 0.399658203125 }, { "start": 2821.07, "end": 2821.35, "word": " has", "probability": 0.85791015625 }, { "start": 2821.35, "end": 2821.57, "word": " this", "probability": 0.8759765625 }, { "start": 2821.57, "end": 2821.77, "word": " 0", "probability": 0.70361328125 }, { "start": 2821.77, "end": 2822.51, "word": ".204", "probability": 0.9788411458333334 }, { "start": 2822.51, "end": 2822.87, "word": " weight", "probability": 0.6923828125 }, { "start": 2822.87, "end": 2823.27, "word": ".", "probability": 0.68115234375 } ] }, { "id": 787, "seek": 276008, "start": 2823.45, "end": 2830.41, "text": " The 2, which is token 9 and token 16, have this 0.408 weight.", "tokens": [ 50564, 440, 568, 11, 597, 307, 14862, 1722, 293, 14862, 3165, 11, 362, 341, 1958, 13, 5254, 23, 3364, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.16626213707970183, "compression_ratio": 1.6055045871559632, "no_speech_prob": 0.058319091796875, "words": [ { "start": 2823.45, "end": 2824.01, "word": " The", "probability": 0.79248046875 }, { "start": 2824.01, "end": 2824.37, "word": " 2", "probability": 0.8017578125 }, { "start": 2824.37, "end": 2824.55, "word": ",", "probability": 0.744140625 }, { "start": 2824.55, "end": 2824.75, "word": " which", "probability": 0.90576171875 }, { "start": 2824.75, "end": 2824.93, "word": " is", "probability": 0.89453125 }, { "start": 2824.93, "end": 2825.13, "word": " token", "probability": 0.64697265625 }, { "start": 2825.13, "end": 2825.53, "word": " 9", "probability": 0.8759765625 }, { "start": 2825.53, "end": 2825.75, "word": " and", "probability": 0.79443359375 }, { "start": 2825.75, "end": 2825.97, "word": " token", "probability": 0.75927734375 }, { "start": 2825.97, "end": 2826.45, "word": " 16", "probability": 0.892578125 }, { "start": 2826.45, "end": 2826.83, "word": ",", "probability": 0.66748046875 }, { "start": 2826.83, "end": 2827.17, "word": " have", "probability": 0.8466796875 }, { "start": 2827.17, "end": 2827.69, "word": " this", "probability": 0.88525390625 }, { "start": 2827.69, "end": 2828.47, "word": " 0", "probability": 0.98779296875 }, { "start": 2828.47, "end": 2829.55, "word": ".408", "probability": 0.951171875 }, { "start": 2829.55, "end": 2829.85, "word": " weight", "probability": 0.8447265625 }, { "start": 2829.85, "end": 2830.41, "word": ".", "probability": 0.90771484375 } ] }, { "id": 788, "seek": 276008, "start": 2830.65, "end": 2834.81, "text": " And this doesn't necessarily happen in every instance.", "tokens": [ 50914, 400, 341, 1177, 380, 4725, 1051, 294, 633, 5197, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.16626213707970183, "compression_ratio": 1.6055045871559632, "no_speech_prob": 0.058319091796875, "words": [ { "start": 2830.65, "end": 2830.93, "word": " And", "probability": 0.81201171875 }, { "start": 2830.93, "end": 2831.21, "word": " this", "probability": 0.873046875 }, { "start": 2831.21, "end": 2831.47, "word": " doesn't", "probability": 0.932373046875 }, { "start": 2831.47, "end": 2832.21, "word": " necessarily", "probability": 0.77294921875 }, { "start": 2832.21, "end": 2833.49, "word": " happen", "probability": 0.7734375 }, { "start": 2833.49, "end": 2833.89, "word": " in", "probability": 0.900390625 }, { "start": 2833.89, "end": 2834.23, "word": " every", "probability": 0.748046875 }, { "start": 2834.23, "end": 2834.69, "word": " instance", "probability": 0.91796875 }, { "start": 2834.69, "end": 2834.81, "word": ".", "probability": 0.2239990234375 } ] }, { "id": 789, "seek": 276008, "start": 2834.81, "end": 2842.09, "text": " But in this instance, you can see the 0.408 shows up twice as much as the 0.204 exactly.", "tokens": [ 51164, 583, 294, 341, 5197, 11, 291, 393, 536, 264, 1958, 13, 5254, 23, 3110, 493, 6091, 382, 709, 382, 264, 1958, 13, 2009, 19, 2293, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.16626213707970183, "compression_ratio": 1.6055045871559632, "no_speech_prob": 0.058319091796875, "words": [ { "start": 2834.81, "end": 2834.97, "word": " But", "probability": 0.88916015625 }, { "start": 2834.97, "end": 2835.13, "word": " in", "probability": 0.89501953125 }, { "start": 2835.13, "end": 2835.41, "word": " this", "probability": 0.87744140625 }, { "start": 2835.41, "end": 2835.81, "word": " instance", "probability": 0.908203125 }, { "start": 2835.81, "end": 2835.89, "word": ",", "probability": 0.72607421875 }, { "start": 2835.89, "end": 2836.03, "word": " you", "probability": 0.89501953125 }, { "start": 2836.03, "end": 2836.17, "word": " can", "probability": 0.89892578125 }, { "start": 2836.17, "end": 2836.37, "word": " see", "probability": 0.81591796875 }, { "start": 2836.37, "end": 2836.57, "word": " the", "probability": 0.791015625 }, { "start": 2836.57, "end": 2836.81, "word": " 0", "probability": 0.97705078125 }, { "start": 2836.81, "end": 2837.57, "word": ".408", "probability": 0.9632161458333334 }, { "start": 2837.57, "end": 2837.85, "word": " shows", "probability": 0.75830078125 }, { "start": 2837.85, "end": 2838.01, "word": " up", "probability": 0.91357421875 }, { "start": 2838.01, "end": 2838.31, "word": " twice", "probability": 0.8310546875 }, { "start": 2838.31, "end": 2838.53, "word": " as", "probability": 0.90380859375 }, { "start": 2838.53, "end": 2838.77, "word": " much", "probability": 0.8046875 }, { "start": 2838.77, "end": 2838.99, "word": " as", "probability": 0.900390625 }, { "start": 2838.99, "end": 2839.15, "word": " the", "probability": 0.80859375 }, { "start": 2839.15, "end": 2839.35, "word": " 0", "probability": 0.9912109375 }, { "start": 2839.35, "end": 2840.23, "word": ".204", "probability": 0.9767252604166666 }, { "start": 2840.23, "end": 2841.81, "word": " exactly", "probability": 0.45361328125 }, { "start": 2841.81, "end": 2842.09, "word": ".", "probability": 0.990234375 } ] }, { "id": 790, "seek": 276008, "start": 2842.71, "end": 2848.03, "text": " And so this is the way that count vectorizer operates and TF-IDF vectorizer operates.", "tokens": [ 51514, 400, 370, 341, 307, 264, 636, 300, 1207, 8062, 6545, 22577, 293, 40964, 12, 2777, 37, 8062, 6545, 22577, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.16626213707970183, "compression_ratio": 1.6055045871559632, "no_speech_prob": 0.058319091796875, "words": [ { "start": 2842.71, "end": 2842.83, "word": " And", "probability": 0.86376953125 }, { "start": 2842.83, "end": 2843.25, "word": " so", "probability": 0.9013671875 }, { "start": 2843.25, "end": 2843.85, "word": " this", "probability": 0.79345703125 }, { "start": 2843.85, "end": 2843.99, "word": " is", "probability": 0.90673828125 }, { "start": 2843.99, "end": 2844.09, "word": " the", "probability": 0.81103515625 }, { "start": 2844.09, "end": 2844.37, "word": " way", "probability": 0.89794921875 }, { "start": 2844.37, "end": 2844.75, "word": " that", "probability": 0.880859375 }, { "start": 2844.75, "end": 2844.99, "word": " count", "probability": 0.478271484375 }, { "start": 2844.99, "end": 2845.45, "word": " vectorizer", "probability": 0.724609375 }, { "start": 2845.45, "end": 2845.97, "word": " operates", "probability": 0.744140625 }, { "start": 2845.97, "end": 2846.19, "word": " and", "probability": 0.69287109375 }, { "start": 2846.19, "end": 2846.43, "word": " TF", "probability": 0.310302734375 }, { "start": 2846.43, "end": 2846.79, "word": "-IDF", "probability": 0.89501953125 }, { "start": 2846.79, "end": 2847.33, "word": " vectorizer", "probability": 0.93017578125 }, { "start": 2847.33, "end": 2847.99, "word": " operates", "probability": 0.763671875 }, { "start": 2847.99, "end": 2848.03, "word": ".", "probability": 0.953125 } ] }, { "id": 791, "seek": 278618, "start": 2849.27, "end": 2853.81, "text": " The underlying, what happens underneath the hood, we don't really need to worry about.", "tokens": [ 50414, 440, 14217, 11, 437, 2314, 7223, 264, 13376, 11, 321, 500, 380, 534, 643, 281, 3292, 466, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.19632353151545806, "compression_ratio": 1.6153846153846154, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 2849.27, "end": 2849.79, "word": " The", "probability": 0.314453125 }, { "start": 2849.79, "end": 2850.31, "word": " underlying", "probability": 0.759765625 }, { "start": 2850.31, "end": 2850.47, "word": ",", "probability": 0.4912109375 }, { "start": 2850.47, "end": 2850.57, "word": " what", "probability": 0.869140625 }, { "start": 2850.57, "end": 2850.97, "word": " happens", "probability": 0.89501953125 }, { "start": 2850.97, "end": 2851.27, "word": " underneath", "probability": 0.80322265625 }, { "start": 2851.27, "end": 2851.49, "word": " the", "probability": 0.810546875 }, { "start": 2851.49, "end": 2851.75, "word": " hood", "probability": 0.875 }, { "start": 2851.75, "end": 2851.89, "word": ",", "probability": 0.845703125 }, { "start": 2851.89, "end": 2851.97, "word": " we", "probability": 0.89794921875 }, { "start": 2851.97, "end": 2852.15, "word": " don't", "probability": 0.943115234375 }, { "start": 2852.15, "end": 2852.37, "word": " really", "probability": 0.751953125 }, { "start": 2852.37, "end": 2852.63, "word": " need", "probability": 0.82080078125 }, { "start": 2852.63, "end": 2852.93, "word": " to", "probability": 0.90576171875 }, { "start": 2852.93, "end": 2853.31, "word": " worry", "probability": 0.90771484375 }, { "start": 2853.31, "end": 2853.61, "word": " about", "probability": 0.8173828125 }, { "start": 2853.61, "end": 2853.81, "word": ".", "probability": 0.66162109375 } ] }, { "id": 792, "seek": 278618, "start": 2853.81, "end": 2860.07, "text": " We just need to know how these work and the differences between the two.", "tokens": [ 50664, 492, 445, 643, 281, 458, 577, 613, 589, 293, 264, 7300, 1296, 264, 732, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.19632353151545806, "compression_ratio": 1.6153846153846154, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 2853.81, "end": 2853.89, "word": " We", "probability": 0.90478515625 }, { "start": 2853.89, "end": 2854.23, "word": " just", "probability": 0.8857421875 }, { "start": 2854.23, "end": 2854.55, "word": " need", "probability": 0.81494140625 }, { "start": 2854.55, "end": 2855.09, "word": " to", "probability": 0.90478515625 }, { "start": 2855.09, "end": 2856.81, "word": " know", "probability": 0.806640625 }, { "start": 2856.81, "end": 2857.39, "word": " how", "probability": 0.90234375 }, { "start": 2857.39, "end": 2857.65, "word": " these", "probability": 0.7080078125 }, { "start": 2857.65, "end": 2858.03, "word": " work", "probability": 0.81298828125 }, { "start": 2858.03, "end": 2858.23, "word": " and", "probability": 0.7822265625 }, { "start": 2858.23, "end": 2858.37, "word": " the", "probability": 0.8046875 }, { "start": 2858.37, "end": 2858.71, "word": " differences", "probability": 0.70068359375 }, { "start": 2858.71, "end": 2859.15, "word": " between", "probability": 0.79052734375 }, { "start": 2859.15, "end": 2859.37, "word": " the", "probability": 0.810546875 }, { "start": 2859.37, "end": 2859.55, "word": " two", "probability": 0.818359375 }, { "start": 2859.55, "end": 2860.07, "word": ".", "probability": 0.9921875 } ] }, { "id": 793, "seek": 278618, "start": 2862.95, "end": 2866.03, "text": " So moving on, we're going to load the testing data.", "tokens": [ 51114, 407, 2684, 322, 11, 321, 434, 516, 281, 3677, 264, 4997, 1412, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.19632353151545806, "compression_ratio": 1.6153846153846154, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 2862.95, "end": 2863.47, "word": " So", "probability": 0.59228515625 }, { "start": 2863.47, "end": 2863.69, "word": " moving", "probability": 0.7080078125 }, { "start": 2863.69, "end": 2863.93, "word": " on", "probability": 0.90576171875 }, { "start": 2863.93, "end": 2864.09, "word": ",", "probability": 0.8359375 }, { "start": 2864.09, "end": 2864.23, "word": " we're", "probability": 0.918212890625 }, { "start": 2864.23, "end": 2864.43, "word": " going", "probability": 0.8505859375 }, { "start": 2864.43, "end": 2864.79, "word": " to", "probability": 0.9033203125 }, { "start": 2864.79, "end": 2865.17, "word": " load", "probability": 0.92236328125 }, { "start": 2865.17, "end": 2865.35, "word": " the", "probability": 0.810546875 }, { "start": 2865.35, "end": 2865.63, "word": " testing", "probability": 0.69775390625 }, { "start": 2865.63, "end": 2865.89, "word": " data", "probability": 0.8134765625 }, { "start": 2865.89, "end": 2866.03, "word": ".", "probability": 0.8759765625 } ] }, { "id": 794, "seek": 278618, "start": 2866.03, "end": 2867.39, "text": " This is already written for us.", "tokens": [ 51264, 639, 307, 1217, 3720, 337, 505, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.19632353151545806, "compression_ratio": 1.6153846153846154, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 2866.03, "end": 2866.11, "word": " This", "probability": 0.796875 }, { "start": 2866.11, "end": 2866.21, "word": " is", "probability": 0.90087890625 }, { "start": 2866.21, "end": 2866.39, "word": " already", "probability": 0.83056640625 }, { "start": 2866.39, "end": 2866.61, "word": " written", "probability": 0.84130859375 }, { "start": 2866.61, "end": 2866.89, "word": " for", "probability": 0.89111328125 }, { "start": 2866.89, "end": 2867.15, "word": " us", "probability": 0.90673828125 }, { "start": 2867.15, "end": 2867.39, "word": ".", "probability": 0.66455078125 } ] }, { "id": 795, "seek": 278618, "start": 2867.39, "end": 2874.13, "text": " So we're just going to grab the first 10 files in the testing directory and print those out.", "tokens": [ 51314, 407, 321, 434, 445, 516, 281, 4444, 264, 700, 1266, 7098, 294, 264, 4997, 21120, 293, 4482, 729, 484, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.19632353151545806, "compression_ratio": 1.6153846153846154, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 2867.39, "end": 2867.51, "word": " So", "probability": 0.7998046875 }, { "start": 2867.51, "end": 2867.73, "word": " we're", "probability": 0.90185546875 }, { "start": 2867.73, "end": 2867.85, "word": " just", "probability": 0.87255859375 }, { "start": 2867.85, "end": 2868.09, "word": " going", "probability": 0.86083984375 }, { "start": 2868.09, "end": 2868.77, "word": " to", "probability": 0.908203125 }, { "start": 2868.77, "end": 2870.29, "word": " grab", "probability": 0.80322265625 }, { "start": 2870.29, "end": 2870.47, "word": " the", "probability": 0.81591796875 }, { "start": 2870.47, "end": 2870.83, "word": " first", "probability": 0.8115234375 }, { "start": 2870.83, "end": 2871.13, "word": " 10", "probability": 0.68701171875 }, { "start": 2871.13, "end": 2871.61, "word": " files", "probability": 0.80078125 }, { "start": 2871.61, "end": 2871.87, "word": " in", "probability": 0.892578125 }, { "start": 2871.87, "end": 2871.99, "word": " the", "probability": 0.81103515625 }, { "start": 2871.99, "end": 2872.27, "word": " testing", "probability": 0.6474609375 }, { "start": 2872.27, "end": 2872.69, "word": " directory", "probability": 0.796875 }, { "start": 2872.69, "end": 2873.21, "word": " and", "probability": 0.83837890625 }, { "start": 2873.21, "end": 2873.57, "word": " print", "probability": 0.8671875 }, { "start": 2873.57, "end": 2873.77, "word": " those", "probability": 0.865234375 }, { "start": 2873.77, "end": 2873.99, "word": " out", "probability": 0.82470703125 }, { "start": 2873.99, "end": 2874.13, "word": ".", "probability": 0.8046875 } ] }, { "id": 796, "seek": 281500, "start": 2874.13, "end": 2877.93, "text": " So we see we just have all these test emails.", "tokens": [ 50364, 407, 321, 536, 321, 445, 362, 439, 613, 1500, 12524, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.21670081722931783, "compression_ratio": 1.9134199134199135, "no_speech_prob": 0.007232666015625, "words": [ { "start": 2874.13, "end": 2874.19, "word": " So", "probability": 0.328857421875 }, { "start": 2874.19, "end": 2874.33, "word": " we", "probability": 0.810546875 }, { "start": 2874.33, "end": 2874.65, "word": " see", "probability": 0.64501953125 }, { "start": 2874.65, "end": 2875.93, "word": " we", "probability": 0.50732421875 }, { "start": 2875.93, "end": 2876.07, "word": " just", "probability": 0.81103515625 }, { "start": 2876.07, "end": 2876.33, "word": " have", "probability": 0.87744140625 }, { "start": 2876.33, "end": 2876.53, "word": " all", "probability": 0.89111328125 }, { "start": 2876.53, "end": 2876.77, "word": " these", "probability": 0.6435546875 }, { "start": 2876.77, "end": 2877.17, "word": " test", "probability": 0.779296875 }, { "start": 2877.17, "end": 2877.49, "word": " emails", "probability": 0.732421875 }, { "start": 2877.49, "end": 2877.93, "word": ".", "probability": 0.10369873046875 } ] }, { "id": 797, "seek": 281500, "start": 2877.97, "end": 2882.87, "text": " And at the end of the file name, we have the label that it's supposed to belong to.", "tokens": [ 50514, 400, 412, 264, 917, 295, 264, 3991, 1315, 11, 321, 362, 264, 7645, 300, 309, 311, 3442, 281, 5784, 281, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.21670081722931783, "compression_ratio": 1.9134199134199135, "no_speech_prob": 0.007232666015625, "words": [ { "start": 2877.97, "end": 2877.99, "word": " And", "probability": 0.73828125 }, { "start": 2877.99, "end": 2878.09, "word": " at", "probability": 0.8955078125 }, { "start": 2878.09, "end": 2878.23, "word": " the", "probability": 0.8134765625 }, { "start": 2878.23, "end": 2878.47, "word": " end", "probability": 0.80859375 }, { "start": 2878.47, "end": 2878.67, "word": " of", "probability": 0.90380859375 }, { "start": 2878.67, "end": 2879.05, "word": " the", "probability": 0.810546875 }, { "start": 2879.05, "end": 2879.61, "word": " file", "probability": 0.63671875 }, { "start": 2879.61, "end": 2879.97, "word": " name", "probability": 0.8037109375 }, { "start": 2879.97, "end": 2880.17, "word": ",", "probability": 0.63330078125 }, { "start": 2880.17, "end": 2880.35, "word": " we", "probability": 0.90283203125 }, { "start": 2880.35, "end": 2880.59, "word": " have", "probability": 0.8798828125 }, { "start": 2880.59, "end": 2880.81, "word": " the", "probability": 0.8134765625 }, { "start": 2880.81, "end": 2881.13, "word": " label", "probability": 0.82568359375 }, { "start": 2881.13, "end": 2881.37, "word": " that", "probability": 0.873046875 }, { "start": 2881.37, "end": 2881.63, "word": " it's", "probability": 0.936279296875 }, { "start": 2881.63, "end": 2882.03, "word": " supposed", "probability": 0.912109375 }, { "start": 2882.03, "end": 2882.23, "word": " to", "probability": 0.9091796875 }, { "start": 2882.23, "end": 2882.49, "word": " belong", "probability": 0.716796875 }, { "start": 2882.49, "end": 2882.73, "word": " to", "probability": 0.8994140625 }, { "start": 2882.73, "end": 2882.87, "word": ".", "probability": 0.96484375 } ] }, { "id": 798, "seek": 281500, "start": 2882.87, "end": 2886.11, "text": " So we have ham, ham, spam, spam, spam, ham.", "tokens": [ 50764, 407, 321, 362, 7852, 11, 7852, 11, 24028, 11, 24028, 11, 24028, 11, 7852, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.21670081722931783, "compression_ratio": 1.9134199134199135, "no_speech_prob": 0.007232666015625, "words": [ { "start": 2882.87, "end": 2882.97, "word": " So", "probability": 0.86767578125 }, { "start": 2882.97, "end": 2883.11, "word": " we", "probability": 0.87939453125 }, { "start": 2883.11, "end": 2883.31, "word": " have", "probability": 0.87744140625 }, { "start": 2883.31, "end": 2883.67, "word": " ham", "probability": 0.48388671875 }, { "start": 2883.67, "end": 2883.81, "word": ",", "probability": 0.74609375 }, { "start": 2883.81, "end": 2884.11, "word": " ham", "probability": 0.7880859375 }, { "start": 2884.11, "end": 2884.23, "word": ",", "probability": 0.95751953125 }, { "start": 2884.23, "end": 2884.41, "word": " spam", "probability": 0.88232421875 }, { "start": 2884.41, "end": 2884.59, "word": ",", "probability": 0.97265625 }, { "start": 2884.59, "end": 2884.79, "word": " spam", "probability": 0.8974609375 }, { "start": 2884.79, "end": 2884.93, "word": ",", "probability": 0.986328125 }, { "start": 2884.93, "end": 2885.23, "word": " spam", "probability": 0.86962890625 }, { "start": 2885.23, "end": 2885.41, "word": ",", "probability": 0.96044921875 }, { "start": 2885.41, "end": 2885.67, "word": " ham", "probability": 0.8359375 }, { "start": 2885.67, "end": 2886.11, "word": ".", "probability": 0.87548828125 } ] }, { "id": 799, "seek": 281500, "start": 2888.83, "end": 2892.13, "text": " And so what we're going to do is read each of these emails.", "tokens": [ 51064, 400, 370, 437, 321, 434, 516, 281, 360, 307, 1401, 1184, 295, 613, 12524, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.21670081722931783, "compression_ratio": 1.9134199134199135, "no_speech_prob": 0.007232666015625, "words": [ { "start": 2888.83, "end": 2889.27, "word": " And", "probability": 0.56787109375 }, { "start": 2889.27, "end": 2889.71, "word": " so", "probability": 0.8662109375 }, { "start": 2889.71, "end": 2889.91, "word": " what", "probability": 0.833984375 }, { "start": 2889.91, "end": 2890.07, "word": " we're", "probability": 0.921875 }, { "start": 2890.07, "end": 2890.25, "word": " going", "probability": 0.8564453125 }, { "start": 2890.25, "end": 2890.37, "word": " to", "probability": 0.9091796875 }, { "start": 2890.37, "end": 2890.59, "word": " do", "probability": 0.90625 }, { "start": 2890.59, "end": 2890.81, "word": " is", "probability": 0.888671875 }, { "start": 2890.81, "end": 2891.03, "word": " read", "probability": 0.89404296875 }, { "start": 2891.03, "end": 2891.29, "word": " each", "probability": 0.8232421875 }, { "start": 2891.29, "end": 2891.37, "word": " of", "probability": 0.90625 }, { "start": 2891.37, "end": 2891.57, "word": " these", "probability": 0.708984375 }, { "start": 2891.57, "end": 2891.97, "word": " emails", "probability": 0.79833984375 }, { "start": 2891.97, "end": 2892.13, "word": ".", "probability": 0.263427734375 } ] }, { "id": 800, "seek": 281500, "start": 2892.13, "end": 2897.89, "text": " And then we're going to pull off the last little bit of the file name and use that as our label.", "tokens": [ 51214, 400, 550, 321, 434, 516, 281, 2235, 766, 264, 1036, 707, 857, 295, 264, 3991, 1315, 293, 764, 300, 382, 527, 7645, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.21670081722931783, "compression_ratio": 1.9134199134199135, "no_speech_prob": 0.007232666015625, "words": [ { "start": 2892.13, "end": 2892.29, "word": " And", "probability": 0.8916015625 }, { "start": 2892.29, "end": 2892.41, "word": " then", "probability": 0.7177734375 }, { "start": 2892.41, "end": 2892.51, "word": " we're", "probability": 0.91943359375 }, { "start": 2892.51, "end": 2892.67, "word": " going", "probability": 0.8564453125 }, { "start": 2892.67, "end": 2892.85, "word": " to", "probability": 0.9033203125 }, { "start": 2892.85, "end": 2893.31, "word": " pull", "probability": 0.82177734375 }, { "start": 2893.31, "end": 2893.73, "word": " off", "probability": 0.80615234375 }, { "start": 2893.73, "end": 2894.37, "word": " the", "probability": 0.81689453125 }, { "start": 2894.37, "end": 2894.83, "word": " last", "probability": 0.82763671875 }, { "start": 2894.83, "end": 2895.07, "word": " little", "probability": 0.79931640625 }, { "start": 2895.07, "end": 2895.25, "word": " bit", "probability": 0.8857421875 }, { "start": 2895.25, "end": 2895.35, "word": " of", "probability": 0.90625 }, { "start": 2895.35, "end": 2895.47, "word": " the", "probability": 0.81494140625 }, { "start": 2895.47, "end": 2895.71, "word": " file", "probability": 0.78662109375 }, { "start": 2895.71, "end": 2895.99, "word": " name", "probability": 0.80810546875 }, { "start": 2895.99, "end": 2896.21, "word": " and", "probability": 0.78759765625 }, { "start": 2896.21, "end": 2896.49, "word": " use", "probability": 0.79833984375 }, { "start": 2896.49, "end": 2896.73, "word": " that", "probability": 0.884765625 }, { "start": 2896.73, "end": 2896.97, "word": " as", "probability": 0.9091796875 }, { "start": 2896.97, "end": 2897.13, "word": " our", "probability": 0.8173828125 }, { "start": 2897.13, "end": 2897.45, "word": " label", "probability": 0.80615234375 }, { "start": 2897.45, "end": 2897.89, "word": ".", "probability": 0.98583984375 } ] }, { "id": 801, "seek": 281500, "start": 2897.95, "end": 2902.95, "text": " And we want to have the testing separate from the training so that we can evaluate how well our model is doing.", "tokens": [ 51514, 400, 321, 528, 281, 362, 264, 4997, 4994, 490, 264, 3097, 370, 300, 321, 393, 13059, 577, 731, 527, 2316, 307, 884, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.21670081722931783, "compression_ratio": 1.9134199134199135, "no_speech_prob": 0.007232666015625, "words": [ { "start": 2897.95, "end": 2898.21, "word": " And", "probability": 0.890625 }, { "start": 2898.21, "end": 2898.33, "word": " we", "probability": 0.88525390625 }, { "start": 2898.33, "end": 2898.47, "word": " want", "probability": 0.66552734375 }, { "start": 2898.47, "end": 2898.55, "word": " to", "probability": 0.90380859375 }, { "start": 2898.55, "end": 2898.71, "word": " have", "probability": 0.88330078125 }, { "start": 2898.71, "end": 2898.89, "word": " the", "probability": 0.8046875 }, { "start": 2898.89, "end": 2899.23, "word": " testing", "probability": 0.7255859375 }, { "start": 2899.23, "end": 2899.55, "word": " separate", "probability": 0.8642578125 }, { "start": 2899.55, "end": 2899.75, "word": " from", "probability": 0.82421875 }, { "start": 2899.75, "end": 2899.87, "word": " the", "probability": 0.81103515625 }, { "start": 2899.87, "end": 2900.17, "word": " training", "probability": 0.7900390625 }, { "start": 2900.17, "end": 2900.51, "word": " so", "probability": 0.7607421875 }, { "start": 2900.51, "end": 2900.65, "word": " that", "probability": 0.87158203125 }, { "start": 2900.65, "end": 2900.77, "word": " we", "probability": 0.90673828125 }, { "start": 2900.77, "end": 2900.89, "word": " can", "probability": 0.8916015625 }, { "start": 2900.89, "end": 2901.37, "word": " evaluate", "probability": 0.744140625 }, { "start": 2901.37, "end": 2901.65, "word": " how", "probability": 0.90087890625 }, { "start": 2901.65, "end": 2901.83, "word": " well", "probability": 0.873046875 }, { "start": 2901.83, "end": 2901.97, "word": " our", "probability": 0.81982421875 }, { "start": 2901.97, "end": 2902.17, "word": " model", "probability": 0.81591796875 }, { "start": 2902.17, "end": 2902.35, "word": " is", "probability": 0.888671875 }, { "start": 2902.35, "end": 2902.57, "word": " doing", "probability": 0.91552734375 }, { "start": 2902.57, "end": 2902.95, "word": ".", "probability": 0.99853515625 } ] }, { "id": 802, "seek": 284070, "start": 2903.45, "end": 2906.31, "text": " So we're going to load the testing data.", "tokens": [ 50364, 407, 321, 434, 516, 281, 3677, 264, 4997, 1412, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.19008152044337728, "compression_ratio": 1.9004524886877827, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 2903.45, "end": 2903.85, "word": " So", "probability": 0.4638671875 }, { "start": 2903.85, "end": 2903.95, "word": " we're", "probability": 0.864013671875 }, { "start": 2903.95, "end": 2904.11, "word": " going", "probability": 0.85205078125 }, { "start": 2904.11, "end": 2904.29, "word": " to", "probability": 0.9033203125 }, { "start": 2904.29, "end": 2904.85, "word": " load", "probability": 0.916015625 }, { "start": 2904.85, "end": 2905.43, "word": " the", "probability": 0.80810546875 }, { "start": 2905.43, "end": 2905.77, "word": " testing", "probability": 0.6865234375 }, { "start": 2905.77, "end": 2906.11, "word": " data", "probability": 0.81689453125 }, { "start": 2906.11, "end": 2906.31, "word": ".", "probability": 0.3857421875 } ] }, { "id": 803, "seek": 284070, "start": 2906.31, "end": 2910.63, "text": " And this one's a little complicated, so we have a couple tasks to run through.", "tokens": [ 50514, 400, 341, 472, 311, 257, 707, 6179, 11, 370, 321, 362, 257, 1916, 9608, 281, 1190, 807, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.19008152044337728, "compression_ratio": 1.9004524886877827, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 2906.31, "end": 2906.37, "word": " And", "probability": 0.634765625 }, { "start": 2906.37, "end": 2906.47, "word": " this", "probability": 0.8779296875 }, { "start": 2906.47, "end": 2906.67, "word": " one's", "probability": 0.87451171875 }, { "start": 2906.73, "end": 2906.81, "word": " a little", "probability": 0.80322265625 }, { "start": 2906.81, "end": 2907.37, "word": " complicated", "probability": 0.8154296875 }, { "start": 2907.37, "end": 2907.63, "word": ",", "probability": 0.29052734375 }, { "start": 2907.63, "end": 2907.79, "word": " so", "probability": 0.87451171875 }, { "start": 2907.79, "end": 2908.27, "word": " we", "probability": 0.845703125 }, { "start": 2908.27, "end": 2908.35, "word": " have", "probability": 0.87841796875 }, { "start": 2908.45, "end": 2908.63, "word": " a couple", "probability": 0.77294921875 }, { "start": 2908.63, "end": 2909.99, "word": " tasks", "probability": 0.41650390625 }, { "start": 2909.99, "end": 2910.19, "word": " to", "probability": 0.9052734375 }, { "start": 2910.19, "end": 2910.33, "word": " run", "probability": 0.89501953125 }, { "start": 2910.33, "end": 2910.53, "word": " through", "probability": 0.79638671875 }, { "start": 2910.53, "end": 2910.63, "word": ".", "probability": 0.93359375 } ] }, { "id": 804, "seek": 284070, "start": 2910.63, "end": 2912.97, "text": " So we're going to create two list arrays, kind of like we did earlier.", "tokens": [ 50714, 407, 321, 434, 516, 281, 1884, 732, 1329, 41011, 11, 733, 295, 411, 321, 630, 3071, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.19008152044337728, "compression_ratio": 1.9004524886877827, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 2910.63, "end": 2910.71, "word": " So", "probability": 0.84521484375 }, { "start": 2910.71, "end": 2910.83, "word": " we're", "probability": 0.918212890625 }, { "start": 2910.83, "end": 2910.89, "word": " going", "probability": 0.2978515625 }, { "start": 2910.89, "end": 2910.95, "word": " to", "probability": 0.90234375 }, { "start": 2910.95, "end": 2911.15, "word": " create", "probability": 0.83154296875 }, { "start": 2911.15, "end": 2911.35, "word": " two", "probability": 0.7841796875 }, { "start": 2911.35, "end": 2911.57, "word": " list", "probability": 0.76904296875 }, { "start": 2911.57, "end": 2911.83, "word": " arrays", "probability": 0.55126953125 }, { "start": 2911.83, "end": 2911.97, "word": ",", "probability": 0.68994140625 }, { "start": 2911.97, "end": 2912.11, "word": " kind", "probability": 0.73583984375 }, { "start": 2912.11, "end": 2912.21, "word": " of", "probability": 0.90380859375 }, { "start": 2912.21, "end": 2912.35, "word": " like", "probability": 0.87109375 }, { "start": 2912.35, "end": 2912.47, "word": " we", "probability": 0.8984375 }, { "start": 2912.47, "end": 2912.59, "word": " did", "probability": 0.89599609375 }, { "start": 2912.59, "end": 2912.89, "word": " earlier", "probability": 0.91064453125 }, { "start": 2912.89, "end": 2912.97, "word": ".", "probability": 0.8525390625 } ] }, { "id": 805, "seek": 284070, "start": 2912.97, "end": 2917.15, "text": " We're going to have test corpus, and we're going to set that as an empty list.", "tokens": [ 50864, 492, 434, 516, 281, 362, 1500, 1181, 31624, 11, 293, 321, 434, 516, 281, 992, 300, 382, 364, 6707, 1329, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.19008152044337728, "compression_ratio": 1.9004524886877827, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 2912.97, "end": 2913.17, "word": " We're", "probability": 0.90625 }, { "start": 2913.17, "end": 2913.17, "word": " going", "probability": 0.69091796875 }, { "start": 2913.17, "end": 2913.17, "word": " to", "probability": 0.9033203125 }, { "start": 2913.17, "end": 2913.37, "word": " have", "probability": 0.87548828125 }, { "start": 2913.37, "end": 2913.71, "word": " test", "probability": 0.62646484375 }, { "start": 2913.71, "end": 2914.13, "word": " corpus", "probability": 0.6983642578125 }, { "start": 2914.13, "end": 2914.93, "word": ",", "probability": 0.6025390625 }, { "start": 2914.93, "end": 2915.21, "word": " and", "probability": 0.88037109375 }, { "start": 2915.21, "end": 2915.99, "word": " we're", "probability": 0.9267578125 }, { "start": 2915.99, "end": 2916.05, "word": " going", "probability": 0.8173828125 }, { "start": 2916.05, "end": 2916.13, "word": " to", "probability": 0.90283203125 }, { "start": 2916.13, "end": 2916.25, "word": " set", "probability": 0.875 }, { "start": 2916.25, "end": 2916.43, "word": " that", "probability": 0.8857421875 }, { "start": 2916.43, "end": 2916.59, "word": " as", "probability": 0.90087890625 }, { "start": 2916.59, "end": 2916.67, "word": " an", "probability": 0.85693359375 }, { "start": 2916.67, "end": 2916.81, "word": " empty", "probability": 0.72265625 }, { "start": 2916.81, "end": 2917.07, "word": " list", "probability": 0.87451171875 }, { "start": 2917.07, "end": 2917.15, "word": ".", "probability": 0.377685546875 } ] }, { "id": 806, "seek": 284070, "start": 2917.15, "end": 2922.61, "text": " And we're going to have test labels, which is also going to be an empty list.", "tokens": [ 51064, 400, 321, 434, 516, 281, 362, 1500, 16949, 11, 597, 307, 611, 516, 281, 312, 364, 6707, 1329, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.19008152044337728, "compression_ratio": 1.9004524886877827, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 2917.15, "end": 2917.21, "word": " And", "probability": 0.55859375 }, { "start": 2917.21, "end": 2917.29, "word": " we're", "probability": 0.924072265625 }, { "start": 2917.29, "end": 2917.35, "word": " going", "probability": 0.83056640625 }, { "start": 2917.35, "end": 2917.39, "word": " to", "probability": 0.90380859375 }, { "start": 2917.39, "end": 2917.61, "word": " have", "probability": 0.8798828125 }, { "start": 2917.61, "end": 2918.19, "word": " test", "probability": 0.80126953125 }, { "start": 2918.19, "end": 2919.05, "word": " labels", "probability": 0.83154296875 }, { "start": 2919.05, "end": 2919.61, "word": ",", "probability": 0.96142578125 }, { "start": 2919.61, "end": 2919.85, "word": " which", "probability": 0.91357421875 }, { "start": 2919.85, "end": 2920.03, "word": " is", "probability": 0.9052734375 }, { "start": 2920.03, "end": 2920.35, "word": " also", "probability": 0.826171875 }, { "start": 2920.35, "end": 2920.69, "word": " going", "probability": 0.8623046875 }, { "start": 2920.69, "end": 2920.87, "word": " to", "probability": 0.9013671875 }, { "start": 2920.87, "end": 2921.11, "word": " be", "probability": 0.90673828125 }, { "start": 2921.11, "end": 2921.53, "word": " an", "probability": 0.8994140625 }, { "start": 2921.53, "end": 2921.77, "word": " empty", "probability": 0.71533203125 }, { "start": 2921.77, "end": 2922.21, "word": " list", "probability": 0.88037109375 }, { "start": 2922.21, "end": 2922.61, "word": ".", "probability": 0.99267578125 } ] }, { "id": 807, "seek": 284070, "start": 2923.39, "end": 2928.65, "text": " And then we are going to load all of the emails from the test directory.", "tokens": [ 51364, 400, 550, 321, 366, 516, 281, 3677, 439, 295, 264, 12524, 490, 264, 1500, 21120, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.19008152044337728, "compression_ratio": 1.9004524886877827, "no_speech_prob": 0.00037407875061035156, "words": [ { "start": 2923.39, "end": 2923.63, "word": " And", "probability": 0.89111328125 }, { "start": 2923.63, "end": 2923.75, "word": " then", "probability": 0.7216796875 }, { "start": 2923.75, "end": 2923.91, "word": " we", "probability": 0.87890625 }, { "start": 2923.91, "end": 2924.03, "word": " are", "probability": 0.80615234375 }, { "start": 2924.03, "end": 2924.25, "word": " going", "probability": 0.85546875 }, { "start": 2924.25, "end": 2924.75, "word": " to", "probability": 0.9013671875 }, { "start": 2924.75, "end": 2925.37, "word": " load", "probability": 0.9169921875 }, { "start": 2925.37, "end": 2925.65, "word": " all", "probability": 0.8994140625 }, { "start": 2925.65, "end": 2925.77, "word": " of", "probability": 0.89697265625 }, { "start": 2925.77, "end": 2925.91, "word": " the", "probability": 0.8115234375 }, { "start": 2925.91, "end": 2926.31, "word": " emails", "probability": 0.76513671875 }, { "start": 2926.31, "end": 2927.09, "word": " from", "probability": 0.80908203125 }, { "start": 2927.09, "end": 2927.33, "word": " the", "probability": 0.8115234375 }, { "start": 2927.33, "end": 2927.67, "word": " test", "probability": 0.81103515625 }, { "start": 2927.67, "end": 2928.25, "word": " directory", "probability": 0.72265625 }, { "start": 2928.25, "end": 2928.65, "word": ".", "probability": 0.94287109375 } ] }, { "id": 808, "seek": 285770, "start": 2928.65, "end": 2945.65, "text": " So we're going to say, for filename in os.listdir, our data directory, plus test, which is where it's located, with each file that is open.", "tokens": [ 50364, 407, 321, 434, 516, 281, 584, 11, 337, 1387, 268, 529, 294, 3003, 13, 8264, 35043, 11, 527, 1412, 21120, 11, 1804, 1500, 11, 597, 307, 689, 309, 311, 6870, 11, 365, 1184, 3991, 300, 307, 1269, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.25130206914175124, "compression_ratio": 1.2636363636363637, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 2928.65, "end": 2929.01, "word": " So", "probability": 0.5341796875 }, { "start": 2929.01, "end": 2929.11, "word": " we're", "probability": 0.873291015625 }, { "start": 2929.11, "end": 2929.31, "word": " going", "probability": 0.8603515625 }, { "start": 2929.31, "end": 2929.53, "word": " to", "probability": 0.90625 }, { "start": 2929.53, "end": 2929.91, "word": " say", "probability": 0.88671875 }, { "start": 2929.91, "end": 2930.19, "word": ",", "probability": 0.2490234375 }, { "start": 2930.19, "end": 2930.93, "word": " for", "probability": 0.7021484375 }, { "start": 2930.93, "end": 2932.43, "word": " filename", "probability": 0.7811686197916666 }, { "start": 2932.43, "end": 2932.85, "word": " in", "probability": 0.8603515625 }, { "start": 2932.85, "end": 2933.27, "word": " os", "probability": 0.61279296875 }, { "start": 2933.27, "end": 2935.07, "word": ".listdir", "probability": 0.8447265625 }, { "start": 2935.07, "end": 2935.79, "word": ",", "probability": 0.54736328125 }, { "start": 2935.79, "end": 2936.37, "word": " our", "probability": 0.7685546875 }, { "start": 2936.37, "end": 2936.89, "word": " data", "probability": 0.70556640625 }, { "start": 2936.89, "end": 2937.41, "word": " directory", "probability": 0.78173828125 }, { "start": 2937.41, "end": 2937.75, "word": ",", "probability": 0.50341796875 }, { "start": 2937.75, "end": 2938.29, "word": " plus", "probability": 0.826171875 }, { "start": 2938.29, "end": 2939.65, "word": " test", "probability": 0.73486328125 }, { "start": 2939.65, "end": 2939.87, "word": ",", "probability": 0.80712890625 }, { "start": 2939.87, "end": 2940.15, "word": " which", "probability": 0.91015625 }, { "start": 2940.15, "end": 2940.25, "word": " is", "probability": 0.90625 }, { "start": 2940.25, "end": 2940.39, "word": " where", "probability": 0.9140625 }, { "start": 2940.39, "end": 2940.57, "word": " it's", "probability": 0.945068359375 }, { "start": 2940.57, "end": 2940.91, "word": " located", "probability": 0.892578125 }, { "start": 2940.91, "end": 2942.27, "word": ",", "probability": 0.80908203125 }, { "start": 2942.27, "end": 2943.11, "word": " with", "probability": 0.80908203125 }, { "start": 2943.11, "end": 2943.51, "word": " each", "probability": 0.8642578125 }, { "start": 2943.51, "end": 2944.05, "word": " file", "probability": 0.8056640625 }, { "start": 2944.05, "end": 2944.25, "word": " that", "probability": 0.88037109375 }, { "start": 2944.25, "end": 2944.39, "word": " is", "probability": 0.90673828125 }, { "start": 2944.39, "end": 2944.83, "word": " open", "probability": 0.80322265625 }, { "start": 2944.83, "end": 2945.65, "word": ".", "probability": 0.489990234375 } ] }, { "id": 809, "seek": 288466, "start": 2945.65, "end": 2954.83, "text": " And we need to tell it which file test plus filename are.", "tokens": [ 50364, 400, 321, 643, 281, 980, 309, 597, 3991, 1500, 1804, 1387, 268, 529, 366, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.27698863636363635, "compression_ratio": 1.5147058823529411, "no_speech_prob": 0.2042236328125, "words": [ { "start": 2945.65, "end": 2946.09, "word": " And", "probability": 0.252685546875 }, { "start": 2946.09, "end": 2946.25, "word": " we", "probability": 0.85595703125 }, { "start": 2946.25, "end": 2946.47, "word": " need", "probability": 0.8017578125 }, { "start": 2946.47, "end": 2946.93, "word": " to", "probability": 0.9013671875 }, { "start": 2946.93, "end": 2947.99, "word": " tell", "probability": 0.77392578125 }, { "start": 2947.99, "end": 2948.11, "word": " it", "probability": 0.89892578125 }, { "start": 2948.11, "end": 2948.31, "word": " which", "probability": 0.8974609375 }, { "start": 2948.31, "end": 2948.85, "word": " file", "probability": 0.76171875 }, { "start": 2948.85, "end": 2950.97, "word": " test", "probability": 0.2447509765625 }, { "start": 2950.97, "end": 2952.43, "word": " plus", "probability": 0.55615234375 }, { "start": 2952.43, "end": 2953.71, "word": " filename", "probability": 0.7611490885416666 }, { "start": 2953.71, "end": 2954.49, "word": " are", "probability": 0.6298828125 }, { "start": 2954.49, "end": 2954.83, "word": ".", "probability": 0.2122802734375 } ] }, { "id": 810, "seek": 288466, "start": 2955.47, "end": 2966.05, "text": " For read, as filenamed f, we are going to do test corpus.append, f.read.", "tokens": [ 50814, 1171, 1401, 11, 382, 1387, 268, 3475, 283, 11, 321, 366, 516, 281, 360, 1500, 1181, 31624, 13, 1746, 521, 11, 283, 13, 2538, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.27698863636363635, "compression_ratio": 1.5147058823529411, "no_speech_prob": 0.2042236328125, "words": [ { "start": 2955.47, "end": 2956.05, "word": " For", "probability": 0.80908203125 }, { "start": 2956.05, "end": 2956.45, "word": " read", "probability": 0.751953125 }, { "start": 2956.45, "end": 2956.69, "word": ",", "probability": 0.29638671875 }, { "start": 2956.69, "end": 2957.19, "word": " as", "probability": 0.90478515625 }, { "start": 2957.19, "end": 2958.03, "word": " filenamed", "probability": 0.615234375 }, { "start": 2958.51, "end": 2958.61, "word": " f,", "probability": 0.7568359375 }, { "start": 2958.61, "end": 2958.77, "word": " we", "probability": 0.89208984375 }, { "start": 2958.77, "end": 2958.87, "word": " are", "probability": 0.630859375 }, { "start": 2958.87, "end": 2959.09, "word": " going", "probability": 0.86181640625 }, { "start": 2959.09, "end": 2959.25, "word": " to", "probability": 0.9052734375 }, { "start": 2959.25, "end": 2959.53, "word": " do", "probability": 0.82958984375 }, { "start": 2959.53, "end": 2960.29, "word": " test", "probability": 0.8056640625 }, { "start": 2960.29, "end": 2961.83, "word": " corpus", "probability": 0.785400390625 }, { "start": 2961.83, "end": 2964.09, "word": ".append", "probability": 0.8468424479166666 }, { "start": 2964.09, "end": 2964.35, "word": ",", "probability": 0.308837890625 }, { "start": 2964.65, "end": 2965.37, "word": " f.read", "probability": 0.9267578125 }, { "start": 2965.37, "end": 2966.05, "word": ".", "probability": 0.6162109375 } ] }, { "id": 811, "seek": 288466, "start": 2966.69, "end": 2972.61, "text": " And then we are going to do something a little weird here, so bear with me.", "tokens": [ 51364, 400, 550, 321, 366, 516, 281, 360, 746, 257, 707, 3657, 510, 11, 370, 6155, 365, 385, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.27698863636363635, "compression_ratio": 1.5147058823529411, "no_speech_prob": 0.2042236328125, "words": [ { "start": 2966.69, "end": 2967.37, "word": " And", "probability": 0.87890625 }, { "start": 2967.37, "end": 2967.51, "word": " then", "probability": 0.72265625 }, { "start": 2967.51, "end": 2967.65, "word": " we", "probability": 0.87841796875 }, { "start": 2967.65, "end": 2967.77, "word": " are", "probability": 0.80078125 }, { "start": 2967.77, "end": 2967.99, "word": " going", "probability": 0.86181640625 }, { "start": 2967.99, "end": 2968.57, "word": " to", "probability": 0.9052734375 }, { "start": 2968.57, "end": 2969.73, "word": " do", "probability": 0.89013671875 }, { "start": 2969.73, "end": 2969.95, "word": " something", "probability": 0.7431640625 }, { "start": 2970.15, "end": 2970.41, "word": " a little", "probability": 0.8076171875 }, { "start": 2970.41, "end": 2970.83, "word": " weird", "probability": 0.87646484375 }, { "start": 2970.83, "end": 2971.21, "word": " here", "probability": 0.810546875 }, { "start": 2971.21, "end": 2971.41, "word": ",", "probability": 0.49560546875 }, { "start": 2971.41, "end": 2971.51, "word": " so", "probability": 0.89013671875 }, { "start": 2971.51, "end": 2971.73, "word": " bear", "probability": 0.77490234375 }, { "start": 2971.73, "end": 2971.93, "word": " with", "probability": 0.81298828125 }, { "start": 2971.93, "end": 2972.21, "word": " me", "probability": 0.90673828125 }, { "start": 2972.21, "end": 2972.61, "word": ".", "probability": 0.798828125 } ] }, { "id": 812, "seek": 290926, "start": 2972.61, "end": 2977.11, "text": " I'm just going to use re.split, just to split this up.", "tokens": [ 50364, 286, 478, 445, 516, 281, 764, 319, 13, 46535, 270, 11, 445, 281, 7472, 341, 493, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.2385165669831885, "compression_ratio": 1.7364864864864864, "no_speech_prob": 0.214599609375, "words": [ { "start": 2972.61, "end": 2972.69, "word": " I'm", "probability": 0.464996337890625 }, { "start": 2972.69, "end": 2972.81, "word": " just", "probability": 0.52294921875 }, { "start": 2972.81, "end": 2972.97, "word": " going", "probability": 0.58544921875 }, { "start": 2972.97, "end": 2972.97, "word": " to", "probability": 0.90380859375 }, { "start": 2972.97, "end": 2973.15, "word": " use", "probability": 0.83154296875 }, { "start": 2973.15, "end": 2973.55, "word": " re", "probability": 0.2183837890625 }, { "start": 2973.55, "end": 2974.67, "word": ".split", "probability": 0.8885091145833334 }, { "start": 2974.67, "end": 2974.81, "word": ",", "probability": 0.1611328125 }, { "start": 2974.81, "end": 2975.11, "word": " just", "probability": 0.82958984375 }, { "start": 2975.11, "end": 2975.41, "word": " to", "probability": 0.88330078125 }, { "start": 2975.41, "end": 2976.09, "word": " split", "probability": 0.84716796875 }, { "start": 2976.09, "end": 2976.29, "word": " this", "probability": 0.87744140625 }, { "start": 2976.29, "end": 2976.55, "word": " up", "probability": 0.90576171875 }, { "start": 2976.55, "end": 2977.11, "word": ".", "probability": 0.85693359375 } ] }, { "id": 813, "seek": 290926, "start": 2977.31, "end": 2979.69, "text": " I'm looking for txt.", "tokens": [ 50564, 286, 478, 1237, 337, 256, 734, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.2385165669831885, "compression_ratio": 1.7364864864864864, "no_speech_prob": 0.214599609375, "words": [ { "start": 2977.31, "end": 2977.65, "word": " I'm", "probability": 0.9501953125 }, { "start": 2977.65, "end": 2977.87, "word": " looking", "probability": 0.7900390625 }, { "start": 2977.87, "end": 2978.25, "word": " for", "probability": 0.89794921875 }, { "start": 2978.25, "end": 2979.13, "word": " txt", "probability": 0.802978515625 }, { "start": 2979.13, "end": 2979.69, "word": ".", "probability": 0.478515625 } ] }, { "id": 814, "seek": 290926, "start": 2981.75, "end": 2986.25, "text": " And then we're just going to grab the last bit in that split.", "tokens": [ 50814, 400, 550, 321, 434, 445, 516, 281, 4444, 264, 1036, 857, 294, 300, 7472, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.2385165669831885, "compression_ratio": 1.7364864864864864, "no_speech_prob": 0.214599609375, "words": [ { "start": 2981.75, "end": 2982.31, "word": " And", "probability": 0.43896484375 }, { "start": 2982.31, "end": 2982.87, "word": " then", "probability": 0.6357421875 }, { "start": 2982.87, "end": 2982.99, "word": " we're", "probability": 0.901123046875 }, { "start": 2982.99, "end": 2983.17, "word": " just", "probability": 0.8662109375 }, { "start": 2983.17, "end": 2983.31, "word": " going", "probability": 0.8037109375 }, { "start": 2983.31, "end": 2983.39, "word": " to", "probability": 0.9052734375 }, { "start": 2983.39, "end": 2983.85, "word": " grab", "probability": 0.78515625 }, { "start": 2983.85, "end": 2984.43, "word": " the", "probability": 0.810546875 }, { "start": 2984.43, "end": 2984.93, "word": " last", "probability": 0.81640625 }, { "start": 2984.93, "end": 2985.29, "word": " bit", "probability": 0.88916015625 }, { "start": 2985.29, "end": 2985.69, "word": " in", "probability": 0.88427734375 }, { "start": 2985.69, "end": 2985.87, "word": " that", "probability": 0.875 }, { "start": 2985.87, "end": 2986.13, "word": " split", "probability": 0.83056640625 }, { "start": 2986.13, "end": 2986.25, "word": ".", "probability": 0.85595703125 } ] }, { "id": 815, "seek": 290926, "start": 2986.25, "end": 2991.99, "text": " So this is going to split the file trainemail.txt.", "tokens": [ 51014, 407, 341, 307, 516, 281, 7472, 264, 3991, 3847, 443, 864, 13, 83, 734, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.2385165669831885, "compression_ratio": 1.7364864864864864, "no_speech_prob": 0.214599609375, "words": [ { "start": 2986.25, "end": 2986.33, "word": " So", "probability": 0.72900390625 }, { "start": 2986.33, "end": 2986.45, "word": " this", "probability": 0.81689453125 }, { "start": 2986.45, "end": 2986.59, "word": " is", "probability": 0.90234375 }, { "start": 2986.59, "end": 2986.73, "word": " going", "probability": 0.8447265625 }, { "start": 2986.73, "end": 2986.95, "word": " to", "probability": 0.900390625 }, { "start": 2986.95, "end": 2987.27, "word": " split", "probability": 0.83447265625 }, { "start": 2987.27, "end": 2987.55, "word": " the", "probability": 0.8037109375 }, { "start": 2987.55, "end": 2988.15, "word": " file", "probability": 0.81494140625 }, { "start": 2988.15, "end": 2990.59, "word": " trainemail", "probability": 0.5438639322916666 }, { "start": 2990.59, "end": 2991.43, "word": ".txt", "probability": 0.9300130208333334 }, { "start": 2991.43, "end": 2991.99, "word": ".", "probability": 0.88525390625 } ] }, { "id": 816, "seek": 290926, "start": 2992.45, "end": 2997.21, "text": " So it's going to split it to this section, and then to this section.", "tokens": [ 51364, 407, 309, 311, 516, 281, 7472, 309, 281, 341, 3541, 11, 293, 550, 281, 341, 3541, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.2385165669831885, "compression_ratio": 1.7364864864864864, "no_speech_prob": 0.214599609375, "words": [ { "start": 2992.45, "end": 2993.01, "word": " So", "probability": 0.771484375 }, { "start": 2993.01, "end": 2993.17, "word": " it's", "probability": 0.93896484375 }, { "start": 2993.17, "end": 2993.33, "word": " going", "probability": 0.85791015625 }, { "start": 2993.33, "end": 2993.51, "word": " to", "probability": 0.90576171875 }, { "start": 2993.51, "end": 2993.79, "word": " split", "probability": 0.85107421875 }, { "start": 2993.79, "end": 2993.97, "word": " it", "probability": 0.89990234375 }, { "start": 2993.97, "end": 2994.19, "word": " to", "probability": 0.88330078125 }, { "start": 2994.19, "end": 2994.57, "word": " this", "probability": 0.88330078125 }, { "start": 2994.57, "end": 2994.99, "word": " section", "probability": 0.8212890625 }, { "start": 2994.99, "end": 2995.15, "word": ",", "probability": 0.34033203125 }, { "start": 2995.15, "end": 2995.39, "word": " and", "probability": 0.89306640625 }, { "start": 2995.39, "end": 2995.69, "word": " then", "probability": 0.73291015625 }, { "start": 2995.69, "end": 2995.99, "word": " to", "probability": 0.88037109375 }, { "start": 2995.99, "end": 2996.27, "word": " this", "probability": 0.88525390625 }, { "start": 2996.27, "end": 2996.65, "word": " section", "probability": 0.8193359375 }, { "start": 2996.65, "end": 2997.21, "word": ".", "probability": 0.88916015625 } ] }, { "id": 817, "seek": 293914, "start": 2998.05, "end": 3005.83, "text": " So this would be considered index 0, and this last little bit would be considered index 1, which is why we have this 1 here at the end.", "tokens": [ 50414, 407, 341, 576, 312, 4888, 8186, 1958, 11, 293, 341, 1036, 707, 857, 576, 312, 4888, 8186, 502, 11, 597, 307, 983, 321, 362, 341, 502, 510, 412, 264, 917, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.24657738435836066, "compression_ratio": 1.6916299559471366, "no_speech_prob": 0.2042236328125, "words": [ { "start": 2998.05, "end": 2998.51, "word": " So", "probability": 0.2705078125 }, { "start": 2998.51, "end": 2998.83, "word": " this", "probability": 0.8017578125 }, { "start": 2998.83, "end": 2999.05, "word": " would", "probability": 0.7529296875 }, { "start": 2999.05, "end": 2999.23, "word": " be", "probability": 0.90234375 }, { "start": 2999.23, "end": 2999.71, "word": " considered", "probability": 0.62744140625 }, { "start": 2999.71, "end": 3000.23, "word": " index", "probability": 0.65625 }, { "start": 3000.23, "end": 3000.55, "word": " 0", "probability": 0.66455078125 }, { "start": 3000.55, "end": 3000.97, "word": ",", "probability": 0.419189453125 }, { "start": 3000.97, "end": 3001.17, "word": " and", "probability": 0.86328125 }, { "start": 3001.17, "end": 3001.45, "word": " this", "probability": 0.8544921875 }, { "start": 3001.45, "end": 3001.73, "word": " last", "probability": 0.7998046875 }, { "start": 3001.73, "end": 3001.91, "word": " little", "probability": 0.7578125 }, { "start": 3001.91, "end": 3002.07, "word": " bit", "probability": 0.89501953125 }, { "start": 3002.07, "end": 3002.19, "word": " would", "probability": 0.53369140625 }, { "start": 3002.19, "end": 3002.31, "word": " be", "probability": 0.90087890625 }, { "start": 3002.31, "end": 3002.61, "word": " considered", "probability": 0.57666015625 }, { "start": 3002.61, "end": 3002.95, "word": " index", "probability": 0.70751953125 }, { "start": 3002.95, "end": 3003.31, "word": " 1", "probability": 0.98388671875 }, { "start": 3003.31, "end": 3003.45, "word": ",", "probability": 0.74853515625 }, { "start": 3003.45, "end": 3003.61, "word": " which", "probability": 0.90087890625 }, { "start": 3003.61, "end": 3003.71, "word": " is", "probability": 0.9033203125 }, { "start": 3003.71, "end": 3003.83, "word": " why", "probability": 0.828125 }, { "start": 3003.83, "end": 3003.95, "word": " we", "probability": 0.90185546875 }, { "start": 3003.95, "end": 3004.11, "word": " have", "probability": 0.8720703125 }, { "start": 3004.11, "end": 3004.29, "word": " this", "probability": 0.857421875 }, { "start": 3004.29, "end": 3004.69, "word": " 1", "probability": 0.83740234375 }, { "start": 3004.69, "end": 3004.95, "word": " here", "probability": 0.771484375 }, { "start": 3004.95, "end": 3005.07, "word": " at", "probability": 0.87841796875 }, { "start": 3005.07, "end": 3005.17, "word": " the", "probability": 0.818359375 }, { "start": 3005.17, "end": 3005.37, "word": " end", "probability": 0.82080078125 }, { "start": 3005.37, "end": 3005.83, "word": ".", "probability": 0.984375 } ] }, { "id": 818, "seek": 293914, "start": 3007.57, "end": 3009.29, "text": " And then we're going to append the labels.", "tokens": [ 50864, 400, 550, 321, 434, 516, 281, 34116, 264, 16949, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.24657738435836066, "compression_ratio": 1.6916299559471366, "no_speech_prob": 0.2042236328125, "words": [ { "start": 3007.57, "end": 3008.03, "word": " And", "probability": 0.72705078125 }, { "start": 3008.03, "end": 3008.13, "word": " then", "probability": 0.71728515625 }, { "start": 3008.13, "end": 3008.27, "word": " we're", "probability": 0.89404296875 }, { "start": 3008.27, "end": 3008.39, "word": " going", "probability": 0.859375 }, { "start": 3008.39, "end": 3008.49, "word": " to", "probability": 0.90625 }, { "start": 3008.49, "end": 3008.67, "word": " append", "probability": 0.890625 }, { "start": 3008.67, "end": 3008.83, "word": " the", "probability": 0.79833984375 }, { "start": 3008.83, "end": 3009.07, "word": " labels", "probability": 0.84423828125 }, { "start": 3009.07, "end": 3009.29, "word": ".", "probability": 0.7119140625 } ] }, { "id": 819, "seek": 293914, "start": 3009.29, "end": 3014.19, "text": " So test.labels.appendLabel", "tokens": [ 50964, 407, 1500, 13, 44990, 1625, 13, 1746, 521, 43, 18657, 51314 ], "temperature": 0.0, "avg_logprob": -0.24657738435836066, "compression_ratio": 1.6916299559471366, "no_speech_prob": 0.2042236328125, "words": [ { "start": 3009.29, "end": 3009.31, "word": " So", "probability": 0.63134765625 }, { "start": 3009.31, "end": 3009.73, "word": " test", "probability": 0.56005859375 }, { "start": 3009.73, "end": 3011.59, "word": ".labels", "probability": 0.5666707356770834 }, { "start": 3011.59, "end": 3014.19, "word": ".appendLabel", "probability": 0.7896484375 } ] }, { "id": 820, "seek": 293914, "start": 3016.43, "end": 3021.29, "text": " And so I'm going to give you guys a little bit to go ahead and get this all written up.", "tokens": [ 51314, 400, 370, 286, 478, 516, 281, 976, 291, 1074, 257, 707, 857, 281, 352, 2286, 293, 483, 341, 439, 3720, 493, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.24657738435836066, "compression_ratio": 1.6916299559471366, "no_speech_prob": 0.2042236328125, "words": [ { "start": 3016.43, "end": 3016.89, "word": " And", "probability": 0.1226806640625 }, { "start": 3016.89, "end": 3017.17, "word": " so", "probability": 0.83837890625 }, { "start": 3017.17, "end": 3017.41, "word": " I'm", "probability": 0.830322265625 }, { "start": 3017.41, "end": 3017.45, "word": " going", "probability": 0.7255859375 }, { "start": 3017.45, "end": 3017.45, "word": " to", "probability": 0.9013671875 }, { "start": 3017.45, "end": 3017.61, "word": " give", "probability": 0.8193359375 }, { "start": 3017.61, "end": 3017.69, "word": " you", "probability": 0.890625 }, { "start": 3017.69, "end": 3017.85, "word": " guys", "probability": 0.875 }, { "start": 3018.01, "end": 3018.15, "word": " a little", "probability": 0.8056640625 }, { "start": 3018.15, "end": 3018.41, "word": " bit", "probability": 0.8916015625 }, { "start": 3018.41, "end": 3018.67, "word": " to", "probability": 0.82421875 }, { "start": 3018.67, "end": 3018.87, "word": " go", "probability": 0.8076171875 }, { "start": 3018.87, "end": 3019.17, "word": " ahead", "probability": 0.85302734375 }, { "start": 3019.17, "end": 3019.49, "word": " and", "probability": 0.55224609375 }, { "start": 3019.49, "end": 3019.67, "word": " get", "probability": 0.90185546875 }, { "start": 3019.67, "end": 3019.95, "word": " this", "probability": 0.85107421875 }, { "start": 3019.95, "end": 3020.23, "word": " all", "probability": 0.9013671875 }, { "start": 3020.23, "end": 3020.45, "word": " written", "probability": 0.8388671875 }, { "start": 3020.45, "end": 3020.83, "word": " up", "probability": 0.90576171875 }, { "start": 3020.83, "end": 3021.29, "word": ".", "probability": 0.9150390625 } ] }, { "id": 821, "seek": 293914, "start": 3021.41, "end": 3027.09, "text": " Be careful, there is a backslash before this period, because this is a regular expression.", "tokens": [ 51564, 879, 5026, 11, 456, 307, 257, 646, 10418, 1299, 949, 341, 2896, 11, 570, 341, 307, 257, 3890, 6114, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.24657738435836066, "compression_ratio": 1.6916299559471366, "no_speech_prob": 0.2042236328125, "words": [ { "start": 3021.41, "end": 3021.69, "word": " Be", "probability": 0.9013671875 }, { "start": 3021.69, "end": 3022.29, "word": " careful", "probability": 0.900390625 }, { "start": 3022.29, "end": 3022.41, "word": ",", "probability": 0.485595703125 }, { "start": 3022.41, "end": 3022.55, "word": " there", "probability": 0.853515625 }, { "start": 3022.55, "end": 3022.67, "word": " is", "probability": 0.41064453125 }, { "start": 3022.85, "end": 3023.69, "word": " a backslash", "probability": 0.888671875 }, { "start": 3023.69, "end": 3024.07, "word": " before", "probability": 0.78271484375 }, { "start": 3024.07, "end": 3024.33, "word": " this", "probability": 0.88427734375 }, { "start": 3024.33, "end": 3024.75, "word": " period", "probability": 0.91455078125 }, { "start": 3024.75, "end": 3025.07, "word": ",", "probability": 0.60693359375 }, { "start": 3025.07, "end": 3025.49, "word": " because", "probability": 0.83544921875 }, { "start": 3025.49, "end": 3025.67, "word": " this", "probability": 0.87353515625 }, { "start": 3025.67, "end": 3025.75, "word": " is", "probability": 0.90087890625 }, { "start": 3025.91, "end": 3026.15, "word": " a regular", "probability": 0.9013671875 }, { "start": 3026.15, "end": 3026.63, "word": " expression", "probability": 0.84814453125 }, { "start": 3026.63, "end": 3027.09, "word": ".", "probability": 0.9521484375 } ] }, { "id": 822, "seek": 296094, "start": 3029.65, "end": 3031.59, "text": " And everything should be good.", "tokens": [ 50414, 400, 1203, 820, 312, 665, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.19406959803944285, "compression_ratio": 1.5759162303664922, "no_speech_prob": 0.0147247314453125, "words": [ { "start": 3029.65, "end": 3029.99, "word": " And", "probability": 0.37451171875 }, { "start": 3029.99, "end": 3030.33, "word": " everything", "probability": 0.7607421875 }, { "start": 3030.33, "end": 3030.77, "word": " should", "probability": 0.9208984375 }, { "start": 3030.77, "end": 3030.99, "word": " be", "probability": 0.90673828125 }, { "start": 3030.99, "end": 3031.25, "word": " good", "probability": 0.88671875 }, { "start": 3031.25, "end": 3031.59, "word": ".", "probability": 0.94921875 } ] }, { "id": 823, "seek": 296094, "start": 3032.39, "end": 3035.67, "text": " So I'm just going to let that sit for a little bit, let you guys do your thing.", "tokens": [ 50614, 407, 286, 478, 445, 516, 281, 718, 300, 1394, 337, 257, 707, 857, 11, 718, 291, 1074, 360, 428, 551, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.19406959803944285, "compression_ratio": 1.5759162303664922, "no_speech_prob": 0.0147247314453125, "words": [ { "start": 3032.39, "end": 3032.73, "word": " So", "probability": 0.88720703125 }, { "start": 3032.73, "end": 3032.83, "word": " I'm", "probability": 0.927978515625 }, { "start": 3032.83, "end": 3032.93, "word": " just", "probability": 0.88134765625 }, { "start": 3032.93, "end": 3033.05, "word": " going", "probability": 0.28857421875 }, { "start": 3033.05, "end": 3033.07, "word": " to", "probability": 0.896484375 }, { "start": 3033.07, "end": 3033.21, "word": " let", "probability": 0.884765625 }, { "start": 3033.21, "end": 3033.37, "word": " that", "probability": 0.880859375 }, { "start": 3033.37, "end": 3033.53, "word": " sit", "probability": 0.89404296875 }, { "start": 3033.53, "end": 3033.67, "word": " for", "probability": 0.8935546875 }, { "start": 3033.79, "end": 3033.89, "word": " a little", "probability": 0.806640625 }, { "start": 3033.89, "end": 3034.15, "word": " bit", "probability": 0.89697265625 }, { "start": 3034.15, "end": 3034.53, "word": ",", "probability": 0.467529296875 }, { "start": 3034.53, "end": 3034.67, "word": " let", "probability": 0.5966796875 }, { "start": 3034.67, "end": 3034.75, "word": " you", "probability": 0.89697265625 }, { "start": 3034.75, "end": 3034.89, "word": " guys", "probability": 0.89013671875 }, { "start": 3034.89, "end": 3035.01, "word": " do", "probability": 0.91162109375 }, { "start": 3035.01, "end": 3035.13, "word": " your", "probability": 0.81201171875 }, { "start": 3035.13, "end": 3035.45, "word": " thing", "probability": 0.82080078125 }, { "start": 3035.45, "end": 3035.67, "word": ".", "probability": 0.82177734375 } ] }, { "id": 824, "seek": 296094, "start": 3035.67, "end": 3037.85, "text": " In the meantime, I'm just going to look ahead real quick.", "tokens": [ 50814, 682, 264, 14991, 11, 286, 478, 445, 516, 281, 574, 2286, 957, 1702, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.19406959803944285, "compression_ratio": 1.5759162303664922, "no_speech_prob": 0.0147247314453125, "words": [ { "start": 3035.67, "end": 3035.83, "word": " In", "probability": 0.67822265625 }, { "start": 3035.83, "end": 3035.91, "word": " the", "probability": 0.80908203125 }, { "start": 3035.91, "end": 3036.09, "word": " meantime", "probability": 0.8369140625 }, { "start": 3036.09, "end": 3036.19, "word": ",", "probability": 0.86279296875 }, { "start": 3036.19, "end": 3036.33, "word": " I'm", "probability": 0.99658203125 }, { "start": 3036.33, "end": 3036.47, "word": " just", "probability": 0.87353515625 }, { "start": 3036.47, "end": 3036.59, "word": " going", "probability": 0.79931640625 }, { "start": 3036.59, "end": 3036.65, "word": " to", "probability": 0.90283203125 }, { "start": 3036.65, "end": 3036.79, "word": " look", "probability": 0.9169921875 }, { "start": 3036.79, "end": 3037.05, "word": " ahead", "probability": 0.8330078125 }, { "start": 3037.05, "end": 3037.25, "word": " real", "probability": 0.84619140625 }, { "start": 3037.25, "end": 3037.51, "word": " quick", "probability": 0.91357421875 }, { "start": 3037.51, "end": 3037.85, "word": ".", "probability": 0.939453125 } ] }, { "id": 825, "seek": 296094, "start": 3039.95, "end": 3041.85, "text": " The rest of this gets so much easier.", "tokens": [ 51014, 440, 1472, 295, 341, 2170, 370, 709, 3571, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.19406959803944285, "compression_ratio": 1.5759162303664922, "no_speech_prob": 0.0147247314453125, "words": [ { "start": 3039.95, "end": 3040.29, "word": " The", "probability": 0.5078125 }, { "start": 3040.29, "end": 3040.49, "word": " rest", "probability": 0.802734375 }, { "start": 3040.49, "end": 3040.59, "word": " of", "probability": 0.900390625 }, { "start": 3040.59, "end": 3040.71, "word": " this", "probability": 0.8740234375 }, { "start": 3040.71, "end": 3040.87, "word": " gets", "probability": 0.80712890625 }, { "start": 3040.87, "end": 3041.05, "word": " so", "probability": 0.9033203125 }, { "start": 3041.05, "end": 3041.21, "word": " much", "probability": 0.83251953125 }, { "start": 3041.21, "end": 3041.51, "word": " easier", "probability": 0.91943359375 }, { "start": 3041.51, "end": 3041.85, "word": ".", "probability": 0.89013671875 } ] }, { "id": 826, "seek": 296094, "start": 3042.03, "end": 3044.75, "text": " It's pretty crazy how easy it gets.", "tokens": [ 51164, 467, 311, 1238, 3219, 577, 1858, 309, 2170, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.19406959803944285, "compression_ratio": 1.5759162303664922, "no_speech_prob": 0.0147247314453125, "words": [ { "start": 3042.03, "end": 3042.11, "word": " It's", "probability": 0.897216796875 }, { "start": 3042.11, "end": 3043.31, "word": " pretty", "probability": 0.8818359375 }, { "start": 3043.31, "end": 3043.63, "word": " crazy", "probability": 0.8515625 }, { "start": 3043.63, "end": 3043.83, "word": " how", "probability": 0.87548828125 }, { "start": 3043.83, "end": 3044.01, "word": " easy", "probability": 0.818359375 }, { "start": 3044.01, "end": 3044.17, "word": " it", "probability": 0.89990234375 }, { "start": 3044.17, "end": 3044.41, "word": " gets", "probability": 0.7744140625 }, { "start": 3044.41, "end": 3044.75, "word": ".", "probability": 0.99072265625 } ] }, { "id": 827, "seek": 296094, "start": 3046.03, "end": 3048.89, "text": " In the meantime, TAs, are there any questions in the chat?", "tokens": [ 51314, 682, 264, 14991, 11, 314, 10884, 11, 366, 456, 604, 1651, 294, 264, 5081, 30, 51564 ], "temperature": 0.0, "avg_logprob": -0.19406959803944285, "compression_ratio": 1.5759162303664922, "no_speech_prob": 0.0147247314453125, "words": [ { "start": 3046.03, "end": 3046.37, "word": " In", "probability": 0.908203125 }, { "start": 3046.37, "end": 3046.45, "word": " the", "probability": 0.80908203125 }, { "start": 3046.45, "end": 3046.71, "word": " meantime", "probability": 0.85302734375 }, { "start": 3046.71, "end": 3047.15, "word": ",", "probability": 0.95263671875 }, { "start": 3047.15, "end": 3047.41, "word": " TAs", "probability": 0.853515625 }, { "start": 3047.41, "end": 3047.45, "word": ",", "probability": 0.86474609375 }, { "start": 3047.45, "end": 3047.51, "word": " are", "probability": 0.892578125 }, { "start": 3047.51, "end": 3047.63, "word": " there", "probability": 0.85107421875 }, { "start": 3047.63, "end": 3047.77, "word": " any", "probability": 0.81884765625 }, { "start": 3047.77, "end": 3048.09, "word": " questions", "probability": 0.90966796875 }, { "start": 3048.09, "end": 3048.27, "word": " in", "probability": 0.90576171875 }, { "start": 3048.27, "end": 3048.35, "word": " the", "probability": 0.81396484375 }, { "start": 3048.35, "end": 3048.55, "word": " chat", "probability": 0.8193359375 }, { "start": 3048.55, "end": 3048.89, "word": "?", "probability": 0.9873046875 } ] }, { "id": 828, "seek": 299004, "start": 3057.32, "end": 3059.62, "text": " We appear to be good so far.", "tokens": [ 50414, 492, 4204, 281, 312, 665, 370, 1400, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.247443180734461, "compression_ratio": 1.7466666666666666, "no_speech_prob": 0.2479248046875, "words": [ { "start": 3057.32, "end": 3057.8, "word": " We", "probability": 0.341552734375 }, { "start": 3057.8, "end": 3058.14, "word": " appear", "probability": 0.64306640625 }, { "start": 3058.14, "end": 3058.24, "word": " to", "probability": 0.90478515625 }, { "start": 3058.24, "end": 3058.36, "word": " be", "probability": 0.9033203125 }, { "start": 3058.36, "end": 3058.58, "word": " good", "probability": 0.8720703125 }, { "start": 3058.58, "end": 3058.88, "word": " so", "probability": 0.8779296875 }, { "start": 3058.88, "end": 3059.18, "word": " far", "probability": 0.90673828125 }, { "start": 3059.18, "end": 3059.62, "word": ".", "probability": 0.93505859375 } ] }, { "id": 829, "seek": 299004, "start": 3060.06, "end": 3061.02, "text": " Awesome.", "tokens": [ 50614, 10391, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.247443180734461, "compression_ratio": 1.7466666666666666, "no_speech_prob": 0.2479248046875, "words": [ { "start": 3060.06, "end": 3060.54, "word": " Awesome", "probability": 0.19287109375 }, { "start": 3060.54, "end": 3061.02, "word": ".", "probability": 0.75146484375 } ] }, { "id": 830, "seek": 299004, "start": 3063.2, "end": 3066.26, "text": " So I'm going to go ahead and move on.", "tokens": [ 50714, 407, 286, 478, 516, 281, 352, 2286, 293, 1286, 322, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.247443180734461, "compression_ratio": 1.7466666666666666, "no_speech_prob": 0.2479248046875, "words": [ { "start": 3063.2, "end": 3063.68, "word": " So", "probability": 0.66943359375 }, { "start": 3063.68, "end": 3064.16, "word": " I'm", "probability": 0.857177734375 }, { "start": 3064.16, "end": 3064.22, "word": " going", "probability": 0.61474609375 }, { "start": 3064.22, "end": 3064.22, "word": " to", "probability": 0.89794921875 }, { "start": 3064.22, "end": 3064.32, "word": " go", "probability": 0.880859375 }, { "start": 3064.32, "end": 3064.62, "word": " ahead", "probability": 0.8544921875 }, { "start": 3064.62, "end": 3065.08, "word": " and", "probability": 0.888671875 }, { "start": 3065.08, "end": 3065.64, "word": " move", "probability": 0.8515625 }, { "start": 3065.64, "end": 3066.12, "word": " on", "probability": 0.908203125 }, { "start": 3066.12, "end": 3066.26, "word": ".", "probability": 0.70166015625 } ] }, { "id": 831, "seek": 299004, "start": 3066.26, "end": 3067.72, "text": " I'm going to press Shift-Enter.", "tokens": [ 50914, 286, 478, 516, 281, 1886, 28304, 12, 16257, 391, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.247443180734461, "compression_ratio": 1.7466666666666666, "no_speech_prob": 0.2479248046875, "words": [ { "start": 3066.26, "end": 3066.42, "word": " I'm", "probability": 0.947021484375 }, { "start": 3066.42, "end": 3066.44, "word": " going", "probability": 0.78173828125 }, { "start": 3066.44, "end": 3066.5, "word": " to", "probability": 0.9052734375 }, { "start": 3066.5, "end": 3066.7, "word": " press", "probability": 0.73876953125 }, { "start": 3066.7, "end": 3067.1, "word": " Shift", "probability": 0.2413330078125 }, { "start": 3067.1, "end": 3067.54, "word": "-Enter", "probability": 0.6593424479166666 }, { "start": 3067.54, "end": 3067.72, "word": ".", "probability": 0.82177734375 } ] }, { "id": 832, "seek": 299004, "start": 3067.72, "end": 3070.44, "text": " It's going to load all of those emails.", "tokens": [ 51014, 467, 311, 516, 281, 3677, 439, 295, 729, 12524, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.247443180734461, "compression_ratio": 1.7466666666666666, "no_speech_prob": 0.2479248046875, "words": [ { "start": 3067.72, "end": 3067.88, "word": " It's", "probability": 0.941650390625 }, { "start": 3067.88, "end": 3068.1, "word": " going", "probability": 0.8525390625 }, { "start": 3068.1, "end": 3068.62, "word": " to", "probability": 0.90380859375 }, { "start": 3068.62, "end": 3069.42, "word": " load", "probability": 0.92919921875 }, { "start": 3069.42, "end": 3069.66, "word": " all", "probability": 0.8974609375 }, { "start": 3069.66, "end": 3069.78, "word": " of", "probability": 0.5576171875 }, { "start": 3069.78, "end": 3069.9, "word": " those", "probability": 0.79150390625 }, { "start": 3069.9, "end": 3070.22, "word": " emails", "probability": 0.7685546875 }, { "start": 3070.22, "end": 3070.44, "word": ".", "probability": 0.7822265625 } ] }, { "id": 833, "seek": 299004, "start": 3070.44, "end": 3079.66, "text": " So this is just reading all of the test emails into our corpus array and grabbing those labels and putting them into the end of our test labels array.", "tokens": [ 51114, 407, 341, 307, 445, 3760, 439, 295, 264, 1500, 12524, 666, 527, 1181, 31624, 10225, 293, 23771, 729, 16949, 293, 3372, 552, 666, 264, 917, 295, 527, 1500, 16949, 10225, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.247443180734461, "compression_ratio": 1.7466666666666666, "no_speech_prob": 0.2479248046875, "words": [ { "start": 3070.44, "end": 3070.52, "word": " So", "probability": 0.7802734375 }, { "start": 3070.52, "end": 3070.64, "word": " this", "probability": 0.87353515625 }, { "start": 3070.64, "end": 3070.76, "word": " is", "probability": 0.90185546875 }, { "start": 3070.76, "end": 3070.9, "word": " just", "probability": 0.88671875 }, { "start": 3070.9, "end": 3071.14, "word": " reading", "probability": 0.810546875 }, { "start": 3071.14, "end": 3071.4, "word": " all", "probability": 0.8974609375 }, { "start": 3071.4, "end": 3071.48, "word": " of", "probability": 0.47021484375 }, { "start": 3071.48, "end": 3071.6, "word": " the", "probability": 0.80908203125 }, { "start": 3071.6, "end": 3071.86, "word": " test", "probability": 0.80517578125 }, { "start": 3071.86, "end": 3072.3, "word": " emails", "probability": 0.79931640625 }, { "start": 3072.3, "end": 3072.88, "word": " into", "probability": 0.72802734375 }, { "start": 3072.88, "end": 3073.2, "word": " our", "probability": 0.81103515625 }, { "start": 3073.2, "end": 3073.54, "word": " corpus", "probability": 0.727783203125 }, { "start": 3073.54, "end": 3073.82, "word": " array", "probability": 0.74267578125 }, { "start": 3073.82, "end": 3074.24, "word": " and", "probability": 0.69140625 }, { "start": 3074.24, "end": 3074.72, "word": " grabbing", "probability": 0.806640625 }, { "start": 3074.72, "end": 3074.98, "word": " those", "probability": 0.8349609375 }, { "start": 3074.98, "end": 3075.28, "word": " labels", "probability": 0.83251953125 }, { "start": 3075.28, "end": 3075.48, "word": " and", "probability": 0.873046875 }, { "start": 3075.48, "end": 3075.7, "word": " putting", "probability": 0.904296875 }, { "start": 3075.7, "end": 3075.86, "word": " them", "probability": 0.72509765625 }, { "start": 3075.86, "end": 3076.28, "word": " into", "probability": 0.73046875 }, { "start": 3076.28, "end": 3076.98, "word": " the", "probability": 0.81884765625 }, { "start": 3076.98, "end": 3077.24, "word": " end", "probability": 0.79248046875 }, { "start": 3077.24, "end": 3077.56, "word": " of", "probability": 0.9052734375 }, { "start": 3077.56, "end": 3077.92, "word": " our", "probability": 0.8115234375 }, { "start": 3077.92, "end": 3078.32, "word": " test", "probability": 0.7626953125 }, { "start": 3078.32, "end": 3078.8, "word": " labels", "probability": 0.68896484375 }, { "start": 3078.8, "end": 3079.18, "word": " array", "probability": 0.7451171875 }, { "start": 3079.18, "end": 3079.66, "word": ".", "probability": 0.95751953125 } ] }, { "id": 834, "seek": 299004, "start": 3080.16, "end": 3084.06, "text": " And then just like last time, what this is going to do is print out the number of test emails.", "tokens": [ 51564, 400, 550, 445, 411, 1036, 565, 11, 437, 341, 307, 516, 281, 360, 307, 4482, 484, 264, 1230, 295, 1500, 12524, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.247443180734461, "compression_ratio": 1.7466666666666666, "no_speech_prob": 0.2479248046875, "words": [ { "start": 3080.16, "end": 3080.28, "word": " And", "probability": 0.78125 }, { "start": 3080.28, "end": 3080.36, "word": " then", "probability": 0.6669921875 }, { "start": 3080.36, "end": 3080.48, "word": " just", "probability": 0.74560546875 }, { "start": 3080.48, "end": 3080.62, "word": " like", "probability": 0.880859375 }, { "start": 3080.62, "end": 3080.86, "word": " last", "probability": 0.81201171875 }, { "start": 3080.86, "end": 3081.16, "word": " time", "probability": 0.806640625 }, { "start": 3081.16, "end": 3081.26, "word": ",", "probability": 0.76611328125 }, { "start": 3081.26, "end": 3081.36, "word": " what", "probability": 0.86572265625 }, { "start": 3081.36, "end": 3081.48, "word": " this", "probability": 0.8828125 }, { "start": 3081.48, "end": 3081.6, "word": " is", "probability": 0.9052734375 }, { "start": 3081.6, "end": 3081.68, "word": " going", "probability": 0.83984375 }, { "start": 3081.68, "end": 3081.76, "word": " to", "probability": 0.90625 }, { "start": 3081.76, "end": 3081.9, "word": " do", "probability": 0.90576171875 }, { "start": 3081.9, "end": 3082.02, "word": " is", "probability": 0.896484375 }, { "start": 3082.02, "end": 3082.26, "word": " print", "probability": 0.9033203125 }, { "start": 3082.26, "end": 3082.54, "word": " out", "probability": 0.814453125 }, { "start": 3082.54, "end": 3083.02, "word": " the", "probability": 0.81103515625 }, { "start": 3083.02, "end": 3083.2, "word": " number", "probability": 0.884765625 }, { "start": 3083.2, "end": 3083.34, "word": " of", "probability": 0.90625 }, { "start": 3083.34, "end": 3083.6, "word": " test", "probability": 0.78955078125 }, { "start": 3083.6, "end": 3083.94, "word": " emails", "probability": 0.7890625 }, { "start": 3083.94, "end": 3084.06, "word": ".", "probability": 0.83349609375 } ] }, { "id": 835, "seek": 301744, "start": 3084.06, "end": 3087.78, "text": " We have 590 ham emails, 276 spam emails.", "tokens": [ 50364, 492, 362, 1025, 7771, 7852, 12524, 11, 7634, 21, 24028, 12524, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.20113357843137256, "compression_ratio": 1.620253164556962, "no_speech_prob": 0.0021820068359375, "words": [ { "start": 3084.06, "end": 3084.14, "word": " We", "probability": 0.51513671875 }, { "start": 3084.14, "end": 3084.3, "word": " have", "probability": 0.8701171875 }, { "start": 3084.3, "end": 3085.0, "word": " 590", "probability": 0.93994140625 }, { "start": 3085.0, "end": 3085.34, "word": " ham", "probability": 0.515625 }, { "start": 3085.34, "end": 3085.78, "word": " emails", "probability": 0.73291015625 }, { "start": 3085.78, "end": 3086.04, "word": ",", "probability": 0.97900390625 }, { "start": 3086.04, "end": 3086.86, "word": " 276", "probability": 0.897705078125 }, { "start": 3086.86, "end": 3087.16, "word": " spam", "probability": 0.947265625 }, { "start": 3087.16, "end": 3087.62, "word": " emails", "probability": 0.76708984375 }, { "start": 3087.62, "end": 3087.78, "word": ".", "probability": 0.36962890625 } ] }, { "id": 836, "seek": 301744, "start": 3087.78, "end": 3091.2, "text": " And here's just a nice pretty graph representing what that looks like.", "tokens": [ 50514, 400, 510, 311, 445, 257, 1481, 1238, 4295, 13460, 437, 300, 1542, 411, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.20113357843137256, "compression_ratio": 1.620253164556962, "no_speech_prob": 0.0021820068359375, "words": [ { "start": 3087.78, "end": 3087.84, "word": " And", "probability": 0.67626953125 }, { "start": 3087.84, "end": 3088.0, "word": " here's", "probability": 0.77587890625 }, { "start": 3088.0, "end": 3088.22, "word": " just", "probability": 0.8779296875 }, { "start": 3088.5, "end": 3088.74, "word": " a nice", "probability": 0.8017578125 }, { "start": 3088.74, "end": 3089.0, "word": " pretty", "probability": 0.59326171875 }, { "start": 3089.0, "end": 3089.48, "word": " graph", "probability": 0.78564453125 }, { "start": 3089.48, "end": 3089.92, "word": " representing", "probability": 0.67578125 }, { "start": 3089.92, "end": 3090.1, "word": " what", "probability": 0.88818359375 }, { "start": 3090.1, "end": 3090.24, "word": " that", "probability": 0.8798828125 }, { "start": 3090.24, "end": 3090.44, "word": " looks", "probability": 0.7890625 }, { "start": 3090.44, "end": 3090.72, "word": " like", "probability": 0.8798828125 }, { "start": 3090.72, "end": 3091.2, "word": ".", "probability": 0.986328125 } ] }, { "id": 837, "seek": 301744, "start": 3091.86, "end": 3097.9, "text": " And as I said earlier, this information or this data has already been split up in an 80-20 split.", "tokens": [ 50714, 400, 382, 286, 848, 3071, 11, 341, 1589, 420, 341, 1412, 575, 1217, 668, 7472, 493, 294, 364, 4688, 12, 2009, 7472, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.20113357843137256, "compression_ratio": 1.620253164556962, "no_speech_prob": 0.0021820068359375, "words": [ { "start": 3091.86, "end": 3092.34, "word": " And", "probability": 0.83837890625 }, { "start": 3092.34, "end": 3092.82, "word": " as", "probability": 0.83056640625 }, { "start": 3092.82, "end": 3092.9, "word": " I", "probability": 0.9990234375 }, { "start": 3092.9, "end": 3093.04, "word": " said", "probability": 0.87841796875 }, { "start": 3093.04, "end": 3093.26, "word": " earlier", "probability": 0.91455078125 }, { "start": 3093.26, "end": 3093.42, "word": ",", "probability": 0.916015625 }, { "start": 3093.42, "end": 3093.62, "word": " this", "probability": 0.88232421875 }, { "start": 3093.62, "end": 3094.14, "word": " information", "probability": 0.64990234375 }, { "start": 3094.14, "end": 3094.5, "word": " or", "probability": 0.705078125 }, { "start": 3094.5, "end": 3094.66, "word": " this", "probability": 0.884765625 }, { "start": 3094.66, "end": 3094.88, "word": " data", "probability": 0.8212890625 }, { "start": 3094.88, "end": 3095.04, "word": " has", "probability": 0.8798828125 }, { "start": 3095.04, "end": 3095.24, "word": " already", "probability": 0.826171875 }, { "start": 3095.24, "end": 3095.42, "word": " been", "probability": 0.82666015625 }, { "start": 3095.42, "end": 3095.7, "word": " split", "probability": 0.83740234375 }, { "start": 3095.7, "end": 3095.98, "word": " up", "probability": 0.90625 }, { "start": 3095.98, "end": 3096.74, "word": " in", "probability": 0.76416015625 }, { "start": 3096.74, "end": 3096.94, "word": " an", "probability": 0.8759765625 }, { "start": 3096.94, "end": 3097.16, "word": " 80", "probability": 0.9521484375 }, { "start": 3097.16, "end": 3097.4, "word": "-20", "probability": 0.6048583984375 }, { "start": 3097.4, "end": 3097.74, "word": " split", "probability": 0.853515625 }, { "start": 3097.74, "end": 3097.9, "word": ".", "probability": 0.7060546875 } ] }, { "id": 838, "seek": 301744, "start": 3097.9, "end": 3103.9, "text": " So 80% of it is being used for our training and then 20% of it is being used for our testing.", "tokens": [ 51014, 407, 4688, 4, 295, 309, 307, 885, 1143, 337, 527, 3097, 293, 550, 945, 4, 295, 309, 307, 885, 1143, 337, 527, 4997, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.20113357843137256, "compression_ratio": 1.620253164556962, "no_speech_prob": 0.0021820068359375, "words": [ { "start": 3097.9, "end": 3097.96, "word": " So", "probability": 0.89013671875 }, { "start": 3097.96, "end": 3098.24, "word": " 80", "probability": 0.84716796875 }, { "start": 3098.24, "end": 3098.48, "word": "%", "probability": 0.9619140625 }, { "start": 3098.48, "end": 3098.7, "word": " of", "probability": 0.9013671875 }, { "start": 3098.7, "end": 3098.92, "word": " it", "probability": 0.90283203125 }, { "start": 3098.92, "end": 3099.36, "word": " is", "probability": 0.89990234375 }, { "start": 3099.36, "end": 3099.52, "word": " being", "probability": 0.88134765625 }, { "start": 3099.52, "end": 3099.7, "word": " used", "probability": 0.82861328125 }, { "start": 3099.7, "end": 3099.86, "word": " for", "probability": 0.8974609375 }, { "start": 3099.86, "end": 3100.66, "word": " our", "probability": 0.78955078125 }, { "start": 3100.66, "end": 3101.02, "word": " training", "probability": 0.78076171875 }, { "start": 3101.02, "end": 3101.3, "word": " and", "probability": 0.486083984375 }, { "start": 3101.3, "end": 3101.44, "word": " then", "probability": 0.71728515625 }, { "start": 3101.44, "end": 3101.7, "word": " 20", "probability": 0.865234375 }, { "start": 3101.7, "end": 3101.9, "word": "%", "probability": 0.998046875 }, { "start": 3101.9, "end": 3102.02, "word": " of", "probability": 0.89794921875 }, { "start": 3102.02, "end": 3102.12, "word": " it", "probability": 0.904296875 }, { "start": 3102.12, "end": 3102.28, "word": " is", "probability": 0.88623046875 }, { "start": 3102.28, "end": 3102.6, "word": " being", "probability": 0.85595703125 }, { "start": 3102.6, "end": 3102.8, "word": " used", "probability": 0.81787109375 }, { "start": 3102.8, "end": 3102.96, "word": " for", "probability": 0.89599609375 }, { "start": 3102.96, "end": 3103.12, "word": " our", "probability": 0.787109375 }, { "start": 3103.12, "end": 3103.42, "word": " testing", "probability": 0.7275390625 }, { "start": 3103.42, "end": 3103.9, "word": ".", "probability": 0.9951171875 } ] }, { "id": 839, "seek": 301744, "start": 3106.08, "end": 3111.46, "text": " And then this one, it might sound complicated, but this is actually really easy.", "tokens": [ 51464, 400, 550, 341, 472, 11, 309, 1062, 1626, 6179, 11, 457, 341, 307, 767, 534, 1858, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.20113357843137256, "compression_ratio": 1.620253164556962, "no_speech_prob": 0.0021820068359375, "words": [ { "start": 3106.08, "end": 3106.56, "word": " And", "probability": 0.8837890625 }, { "start": 3106.56, "end": 3106.66, "word": " then", "probability": 0.7265625 }, { "start": 3106.66, "end": 3106.88, "word": " this", "probability": 0.87548828125 }, { "start": 3106.88, "end": 3107.16, "word": " one", "probability": 0.81103515625 }, { "start": 3107.16, "end": 3107.22, "word": ",", "probability": 0.88818359375 }, { "start": 3107.22, "end": 3107.4, "word": " it", "probability": 0.9013671875 }, { "start": 3107.4, "end": 3107.64, "word": " might", "probability": 0.82275390625 }, { "start": 3107.64, "end": 3108.12, "word": " sound", "probability": 0.814453125 }, { "start": 3108.12, "end": 3108.76, "word": " complicated", "probability": 0.80908203125 }, { "start": 3108.76, "end": 3109.14, "word": ",", "probability": 0.638671875 }, { "start": 3109.14, "end": 3109.62, "word": " but", "probability": 0.8984375 }, { "start": 3109.62, "end": 3110.04, "word": " this", "probability": 0.884765625 }, { "start": 3110.04, "end": 3110.22, "word": " is", "probability": 0.90283203125 }, { "start": 3110.22, "end": 3110.52, "word": " actually", "probability": 0.7958984375 }, { "start": 3110.52, "end": 3110.92, "word": " really", "probability": 0.78271484375 }, { "start": 3110.92, "end": 3111.28, "word": " easy", "probability": 0.80517578125 }, { "start": 3111.28, "end": 3111.46, "word": ".", "probability": 0.96826171875 } ] }, { "id": 840, "seek": 303478, "start": 3111.46, "end": 3115.76, "text": " We have already trained our CVEC and our TVEC.", "tokens": [ 50364, 492, 362, 1217, 8895, 527, 383, 7540, 34, 293, 527, 3558, 8140, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.2099780743582207, "compression_ratio": 1.5488721804511278, "no_speech_prob": 0.0259552001953125, "words": [ { "start": 3111.46, "end": 3111.54, "word": " We", "probability": 0.64892578125 }, { "start": 3111.54, "end": 3111.72, "word": " have", "probability": 0.86669921875 }, { "start": 3111.72, "end": 3112.14, "word": " already", "probability": 0.8447265625 }, { "start": 3112.14, "end": 3112.78, "word": " trained", "probability": 0.802734375 }, { "start": 3112.78, "end": 3113.74, "word": " our", "probability": 0.806640625 }, { "start": 3113.74, "end": 3114.4, "word": " CVEC", "probability": 0.7762858072916666 }, { "start": 3114.4, "end": 3114.9, "word": " and", "probability": 0.87646484375 }, { "start": 3114.9, "end": 3115.18, "word": " our", "probability": 0.78662109375 }, { "start": 3115.18, "end": 3115.6, "word": " TVEC", "probability": 0.688232421875 }, { "start": 3115.6, "end": 3115.76, "word": ".", "probability": 0.319580078125 } ] }, { "id": 841, "seek": 303478, "start": 3115.76, "end": 3121.7, "text": " And now all we need to do is collect our testing values.", "tokens": [ 50564, 400, 586, 439, 321, 643, 281, 360, 307, 2500, 527, 4997, 4190, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.2099780743582207, "compression_ratio": 1.5488721804511278, "no_speech_prob": 0.0259552001953125, "words": [ { "start": 3115.76, "end": 3115.82, "word": " And", "probability": 0.654296875 }, { "start": 3115.82, "end": 3115.98, "word": " now", "probability": 0.8779296875 }, { "start": 3115.98, "end": 3116.18, "word": " all", "probability": 0.8115234375 }, { "start": 3116.18, "end": 3116.32, "word": " we", "probability": 0.904296875 }, { "start": 3116.32, "end": 3116.48, "word": " need", "probability": 0.8154296875 }, { "start": 3116.48, "end": 3116.62, "word": " to", "probability": 0.90673828125 }, { "start": 3116.62, "end": 3116.9, "word": " do", "probability": 0.91162109375 }, { "start": 3116.9, "end": 3117.48, "word": " is", "probability": 0.8935546875 }, { "start": 3117.48, "end": 3118.94, "word": " collect", "probability": 0.701171875 }, { "start": 3118.94, "end": 3120.36, "word": " our", "probability": 0.79248046875 }, { "start": 3120.36, "end": 3121.02, "word": " testing", "probability": 0.71044921875 }, { "start": 3121.02, "end": 3121.6, "word": " values", "probability": 0.908203125 }, { "start": 3121.6, "end": 3121.7, "word": ".", "probability": 0.76611328125 } ] }, { "id": 842, "seek": 303478, "start": 3121.7, "end": 3126.66, "text": " We need to tokenize our testing values using these already trained vectorizers.", "tokens": [ 50864, 492, 643, 281, 14862, 1125, 527, 4997, 4190, 1228, 613, 1217, 8895, 8062, 22525, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.2099780743582207, "compression_ratio": 1.5488721804511278, "no_speech_prob": 0.0259552001953125, "words": [ { "start": 3121.7, "end": 3121.76, "word": " We", "probability": 0.89990234375 }, { "start": 3121.76, "end": 3121.86, "word": " need", "probability": 0.83642578125 }, { "start": 3121.86, "end": 3122.02, "word": " to", "probability": 0.79052734375 }, { "start": 3122.02, "end": 3122.36, "word": " tokenize", "probability": 0.819091796875 }, { "start": 3122.36, "end": 3122.5, "word": " our", "probability": 0.8017578125 }, { "start": 3122.5, "end": 3122.8, "word": " testing", "probability": 0.736328125 }, { "start": 3122.8, "end": 3123.34, "word": " values", "probability": 0.91748046875 }, { "start": 3123.34, "end": 3124.46, "word": " using", "probability": 0.75048828125 }, { "start": 3124.46, "end": 3124.74, "word": " these", "probability": 0.724609375 }, { "start": 3124.74, "end": 3125.1, "word": " already", "probability": 0.83251953125 }, { "start": 3125.1, "end": 3125.66, "word": " trained", "probability": 0.7626953125 }, { "start": 3125.66, "end": 3126.24, "word": " vectorizers", "probability": 0.934326171875 }, { "start": 3126.24, "end": 3126.66, "word": ".", "probability": 0.9765625 } ] }, { "id": 843, "seek": 303478, "start": 3126.66, "end": 3128.8, "text": " So this is super easy.", "tokens": [ 51114, 407, 341, 307, 1687, 1858, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.2099780743582207, "compression_ratio": 1.5488721804511278, "no_speech_prob": 0.0259552001953125, "words": [ { "start": 3126.66, "end": 3126.82, "word": " So", "probability": 0.83544921875 }, { "start": 3126.82, "end": 3127.08, "word": " this", "probability": 0.81884765625 }, { "start": 3127.08, "end": 3127.24, "word": " is", "probability": 0.9111328125 }, { "start": 3127.24, "end": 3127.78, "word": " super", "probability": 0.87109375 }, { "start": 3127.78, "end": 3128.16, "word": " easy", "probability": 0.80322265625 }, { "start": 3128.16, "end": 3128.8, "word": ".", "probability": 0.869140625 } ] }, { "id": 844, "seek": 306472, "start": 3130.8, "end": 3139.86, "text": " testCountX equals CVEC.transformTestCorpus.", "tokens": [ 50364, 1500, 34, 792, 55, 6915, 383, 7540, 34, 13, 24999, 837, 51, 377, 34, 18703, 301, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.2815789580345154, "compression_ratio": 1.4922279792746114, "no_speech_prob": 0.0311279296875, "words": [ { "start": 3130.8, "end": 3131.32, "word": " testCountX", "probability": 0.6287841796875 }, { "start": 3131.32, "end": 3131.84, "word": " equals", "probability": 0.348876953125 }, { "start": 3131.84, "end": 3133.42, "word": " CVEC", "probability": 0.644287109375 }, { "start": 3133.42, "end": 3139.6, "word": ".transformTestCorpus", "probability": 0.7812042236328125 }, { "start": 3139.6, "end": 3139.86, "word": ".", "probability": 0.5576171875 } ] }, { "id": 845, "seek": 306472, "start": 3140.14, "end": 3143.06, "text": " And that's it. That's all we've got to do for that.", "tokens": [ 50914, 400, 300, 311, 309, 13, 663, 311, 439, 321, 600, 658, 281, 360, 337, 300, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.2815789580345154, "compression_ratio": 1.4922279792746114, "no_speech_prob": 0.0311279296875, "words": [ { "start": 3140.14, "end": 3140.66, "word": " And", "probability": 0.548828125 }, { "start": 3140.66, "end": 3140.8, "word": " that's", "probability": 0.936767578125 }, { "start": 3140.8, "end": 3140.94, "word": " it", "probability": 0.89794921875 }, { "start": 3140.94, "end": 3141.46, "word": ".", "probability": 0.83251953125 }, { "start": 3141.58, "end": 3141.9, "word": " That's", "probability": 0.88671875 }, { "start": 3141.9, "end": 3141.98, "word": " all", "probability": 0.9013671875 }, { "start": 3141.98, "end": 3142.1, "word": " we've", "probability": 0.567138671875 }, { "start": 3142.1, "end": 3142.12, "word": " got", "probability": 0.82568359375 }, { "start": 3142.12, "end": 3142.2, "word": " to", "probability": 0.89697265625 }, { "start": 3142.2, "end": 3142.28, "word": " do", "probability": 0.9033203125 }, { "start": 3142.28, "end": 3142.38, "word": " for", "probability": 0.88525390625 }, { "start": 3142.38, "end": 3142.54, "word": " that", "probability": 0.8818359375 }, { "start": 3142.54, "end": 3143.06, "word": ".", "probability": 0.986328125 } ] }, { "id": 846, "seek": 306472, "start": 3143.48, "end": 3145.32, "text": " We can just copy and paste here.", "tokens": [ 51064, 492, 393, 445, 5055, 293, 9163, 510, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.2815789580345154, "compression_ratio": 1.4922279792746114, "no_speech_prob": 0.0311279296875, "words": [ { "start": 3143.48, "end": 3143.66, "word": " We", "probability": 0.462646484375 }, { "start": 3143.66, "end": 3143.78, "word": " can", "probability": 0.8427734375 }, { "start": 3143.78, "end": 3143.92, "word": " just", "probability": 0.84716796875 }, { "start": 3143.92, "end": 3144.14, "word": " copy", "probability": 0.83056640625 }, { "start": 3144.14, "end": 3144.3, "word": " and", "probability": 0.87109375 }, { "start": 3144.3, "end": 3144.48, "word": " paste", "probability": 0.7041015625 }, { "start": 3144.48, "end": 3144.8, "word": " here", "probability": 0.80712890625 }, { "start": 3144.8, "end": 3145.32, "word": ".", "probability": 0.45556640625 } ] }, { "id": 847, "seek": 306472, "start": 3145.58, "end": 3151.76, "text": " Say our testTFIDFX is our TVEC.transformTestCorpus.", "tokens": [ 51164, 6463, 527, 1500, 51, 37, 2777, 36092, 307, 527, 3558, 8140, 13, 24999, 837, 51, 377, 34, 18703, 301, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.2815789580345154, "compression_ratio": 1.4922279792746114, "no_speech_prob": 0.0311279296875, "words": [ { "start": 3145.58, "end": 3145.76, "word": " Say", "probability": 0.4931640625 }, { "start": 3145.76, "end": 3145.94, "word": " our", "probability": 0.7666015625 }, { "start": 3145.94, "end": 3147.54, "word": " testTFIDFX", "probability": 0.518310546875 }, { "start": 3147.54, "end": 3148.8, "word": " is", "probability": 0.853515625 }, { "start": 3148.8, "end": 3149.18, "word": " our", "probability": 0.7998046875 }, { "start": 3149.18, "end": 3149.74, "word": " TVEC", "probability": 0.314697265625 }, { "start": 3149.74, "end": 3151.24, "word": ".transformTestCorpus", "probability": 0.832183837890625 }, { "start": 3151.24, "end": 3151.76, "word": ".", "probability": 0.96240234375 } ] }, { "id": 848, "seek": 306472, "start": 3152.56, "end": 3158.74, "text": " The reason this works is if you remember in the slides how we had the sentences that we already knew about,", "tokens": [ 51514, 440, 1778, 341, 1985, 307, 498, 291, 1604, 294, 264, 9788, 577, 321, 632, 264, 16579, 300, 321, 1217, 2586, 466, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.2815789580345154, "compression_ratio": 1.4922279792746114, "no_speech_prob": 0.0311279296875, "words": [ { "start": 3152.56, "end": 3153.08, "word": " The", "probability": 0.8125 }, { "start": 3153.08, "end": 3153.24, "word": " reason", "probability": 0.9140625 }, { "start": 3153.24, "end": 3153.42, "word": " this", "probability": 0.87939453125 }, { "start": 3153.42, "end": 3153.68, "word": " works", "probability": 0.73388671875 }, { "start": 3153.68, "end": 3154.12, "word": " is", "probability": 0.88916015625 }, { "start": 3154.12, "end": 3154.64, "word": " if", "probability": 0.488037109375 }, { "start": 3154.64, "end": 3154.74, "word": " you", "probability": 0.892578125 }, { "start": 3154.74, "end": 3154.98, "word": " remember", "probability": 0.759765625 }, { "start": 3154.98, "end": 3155.14, "word": " in", "probability": 0.8916015625 }, { "start": 3155.14, "end": 3155.28, "word": " the", "probability": 0.8095703125 }, { "start": 3155.28, "end": 3155.72, "word": " slides", "probability": 0.90380859375 }, { "start": 3155.72, "end": 3156.12, "word": " how", "probability": 0.79345703125 }, { "start": 3156.12, "end": 3156.36, "word": " we", "probability": 0.9033203125 }, { "start": 3156.36, "end": 3156.62, "word": " had", "probability": 0.794921875 }, { "start": 3156.62, "end": 3156.8, "word": " the", "probability": 0.80517578125 }, { "start": 3156.8, "end": 3157.06, "word": " sentences", "probability": 0.83837890625 }, { "start": 3157.06, "end": 3157.3, "word": " that", "probability": 0.86865234375 }, { "start": 3157.3, "end": 3157.4, "word": " we", "probability": 0.90380859375 }, { "start": 3157.4, "end": 3157.66, "word": " already", "probability": 0.82275390625 }, { "start": 3157.66, "end": 3157.92, "word": " knew", "probability": 0.76904296875 }, { "start": 3157.92, "end": 3158.32, "word": " about", "probability": 0.82958984375 }, { "start": 3158.32, "end": 3158.74, "word": ",", "probability": 0.7255859375 } ] }, { "id": 849, "seek": 309048, "start": 3158.74, "end": 3163.12, "text": " and then we had to perform a counting game for a very close game.", "tokens": [ 50364, 293, 550, 321, 632, 281, 2042, 257, 13251, 1216, 337, 257, 588, 1998, 1216, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.1956905297213985, "compression_ratio": 1.9139344262295082, "no_speech_prob": 0.0010814666748046875, "words": [ { "start": 3158.74, "end": 3159.22, "word": " and", "probability": 0.2362060546875 }, { "start": 3159.22, "end": 3159.3, "word": " then", "probability": 0.70751953125 }, { "start": 3159.3, "end": 3159.38, "word": " we", "probability": 0.89404296875 }, { "start": 3159.38, "end": 3159.5, "word": " had", "probability": 0.791015625 }, { "start": 3159.5, "end": 3159.6, "word": " to", "probability": 0.908203125 }, { "start": 3159.6, "end": 3160.0, "word": " perform", "probability": 0.7666015625 }, { "start": 3160.34, "end": 3160.6, "word": " a counting", "probability": 0.748046875 }, { "start": 3160.6, "end": 3161.02, "word": " game", "probability": 0.79833984375 }, { "start": 3161.02, "end": 3161.42, "word": " for", "probability": 0.87646484375 }, { "start": 3161.68, "end": 3161.96, "word": " a very", "probability": 0.67822265625 }, { "start": 3161.96, "end": 3162.32, "word": " close", "probability": 0.837890625 }, { "start": 3162.32, "end": 3162.72, "word": " game", "probability": 0.77001953125 }, { "start": 3162.72, "end": 3163.12, "word": ".", "probability": 0.6240234375 } ] }, { "id": 850, "seek": 309048, "start": 3163.18, "end": 3166.68, "text": " We had to count how many times a showed up in the sentences that we were already aware of,", "tokens": [ 50564, 492, 632, 281, 1207, 577, 867, 1413, 257, 4712, 493, 294, 264, 16579, 300, 321, 645, 1217, 3650, 295, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.1956905297213985, "compression_ratio": 1.9139344262295082, "no_speech_prob": 0.0010814666748046875, "words": [ { "start": 3163.18, "end": 3163.3, "word": " We", "probability": 0.86474609375 }, { "start": 3163.3, "end": 3163.38, "word": " had", "probability": 0.80419921875 }, { "start": 3163.38, "end": 3163.46, "word": " to", "probability": 0.89794921875 }, { "start": 3163.46, "end": 3163.6, "word": " count", "probability": 0.82373046875 }, { "start": 3163.6, "end": 3163.74, "word": " how", "probability": 0.8984375 }, { "start": 3163.74, "end": 3163.88, "word": " many", "probability": 0.80322265625 }, { "start": 3163.88, "end": 3164.14, "word": " times", "probability": 0.81005859375 }, { "start": 3164.32, "end": 3164.62, "word": " a showed", "probability": 0.7705078125 }, { "start": 3164.62, "end": 3164.82, "word": " up", "probability": 0.91015625 }, { "start": 3164.82, "end": 3164.98, "word": " in", "probability": 0.83154296875 }, { "start": 3164.98, "end": 3165.12, "word": " the", "probability": 0.80419921875 }, { "start": 3165.12, "end": 3165.38, "word": " sentences", "probability": 0.85498046875 }, { "start": 3165.38, "end": 3165.58, "word": " that", "probability": 0.84521484375 }, { "start": 3165.58, "end": 3165.66, "word": " we", "probability": 0.8955078125 }, { "start": 3165.66, "end": 3165.78, "word": " were", "probability": 0.87255859375 }, { "start": 3165.78, "end": 3166.06, "word": " already", "probability": 0.798828125 }, { "start": 3166.06, "end": 3166.36, "word": " aware", "probability": 0.833984375 }, { "start": 3166.36, "end": 3166.64, "word": " of", "probability": 0.90283203125 }, { "start": 3166.64, "end": 3166.68, "word": ",", "probability": 0.45458984375 } ] }, { "id": 851, "seek": 309048, "start": 3166.68, "end": 3170.82, "text": " how many times very showed up, how many times close showed up, how many times game showed up.", "tokens": [ 50764, 577, 867, 1413, 588, 4712, 493, 11, 577, 867, 1413, 1998, 4712, 493, 11, 577, 867, 1413, 1216, 4712, 493, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.1956905297213985, "compression_ratio": 1.9139344262295082, "no_speech_prob": 0.0010814666748046875, "words": [ { "start": 3166.68, "end": 3166.8, "word": " how", "probability": 0.87939453125 }, { "start": 3166.8, "end": 3166.94, "word": " many", "probability": 0.80615234375 }, { "start": 3166.94, "end": 3167.32, "word": " times", "probability": 0.8232421875 }, { "start": 3167.32, "end": 3167.64, "word": " very", "probability": 0.66259765625 }, { "start": 3167.64, "end": 3167.94, "word": " showed", "probability": 0.8212890625 }, { "start": 3167.94, "end": 3168.18, "word": " up", "probability": 0.90869140625 }, { "start": 3168.18, "end": 3168.22, "word": ",", "probability": 0.95703125 }, { "start": 3168.22, "end": 3168.3, "word": " how", "probability": 0.89697265625 }, { "start": 3168.3, "end": 3168.44, "word": " many", "probability": 0.80029296875 }, { "start": 3168.44, "end": 3168.64, "word": " times", "probability": 0.77001953125 }, { "start": 3168.64, "end": 3168.92, "word": " close", "probability": 0.8037109375 }, { "start": 3168.92, "end": 3169.16, "word": " showed", "probability": 0.8095703125 }, { "start": 3169.16, "end": 3169.34, "word": " up", "probability": 0.9111328125 }, { "start": 3169.34, "end": 3169.38, "word": ",", "probability": 0.9755859375 }, { "start": 3169.38, "end": 3169.46, "word": " how", "probability": 0.89306640625 }, { "start": 3169.46, "end": 3169.58, "word": " many", "probability": 0.8037109375 }, { "start": 3169.58, "end": 3169.8, "word": " times", "probability": 0.78515625 }, { "start": 3169.8, "end": 3170.02, "word": " game", "probability": 0.78515625 }, { "start": 3170.02, "end": 3170.26, "word": " showed", "probability": 0.8046875 }, { "start": 3170.26, "end": 3170.46, "word": " up", "probability": 0.9091796875 }, { "start": 3170.46, "end": 3170.82, "word": ".", "probability": 0.796875 } ] }, { "id": 852, "seek": 309048, "start": 3170.82, "end": 3174.26, "text": " So this transform allows us to do just that.", "tokens": [ 50964, 407, 341, 4088, 4045, 505, 281, 360, 445, 300, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.1956905297213985, "compression_ratio": 1.9139344262295082, "no_speech_prob": 0.0010814666748046875, "words": [ { "start": 3170.82, "end": 3170.92, "word": " So", "probability": 0.6650390625 }, { "start": 3170.92, "end": 3171.14, "word": " this", "probability": 0.7890625 }, { "start": 3171.14, "end": 3172.14, "word": " transform", "probability": 0.59326171875 }, { "start": 3172.14, "end": 3172.66, "word": " allows", "probability": 0.80126953125 }, { "start": 3172.66, "end": 3172.84, "word": " us", "probability": 0.89794921875 }, { "start": 3172.84, "end": 3173.0, "word": " to", "probability": 0.90625 }, { "start": 3173.0, "end": 3173.18, "word": " do", "probability": 0.90185546875 }, { "start": 3173.18, "end": 3173.52, "word": " just", "probability": 0.87841796875 }, { "start": 3173.52, "end": 3173.86, "word": " that", "probability": 0.880859375 }, { "start": 3173.86, "end": 3174.26, "word": ".", "probability": 0.91064453125 } ] }, { "id": 853, "seek": 309048, "start": 3174.26, "end": 3177.74, "text": " So what this will do is grab each email and it will say,", "tokens": [ 51114, 407, 437, 341, 486, 360, 307, 4444, 1184, 3796, 293, 309, 486, 584, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.1956905297213985, "compression_ratio": 1.9139344262295082, "no_speech_prob": 0.0010814666748046875, "words": [ { "start": 3174.26, "end": 3174.34, "word": " So", "probability": 0.80859375 }, { "start": 3174.34, "end": 3174.46, "word": " what", "probability": 0.8740234375 }, { "start": 3174.46, "end": 3174.58, "word": " this", "probability": 0.87939453125 }, { "start": 3174.58, "end": 3174.7, "word": " will", "probability": 0.81640625 }, { "start": 3174.7, "end": 3174.96, "word": " do", "probability": 0.9013671875 }, { "start": 3174.96, "end": 3175.28, "word": " is", "probability": 0.89208984375 }, { "start": 3175.28, "end": 3175.56, "word": " grab", "probability": 0.79150390625 }, { "start": 3175.56, "end": 3175.86, "word": " each", "probability": 0.85693359375 }, { "start": 3175.86, "end": 3176.2, "word": " email", "probability": 0.89697265625 }, { "start": 3176.2, "end": 3177.1, "word": " and", "probability": 0.65869140625 }, { "start": 3177.1, "end": 3177.28, "word": " it", "probability": 0.900390625 }, { "start": 3177.28, "end": 3177.4, "word": " will", "probability": 0.81298828125 }, { "start": 3177.4, "end": 3177.62, "word": " say", "probability": 0.8935546875 }, { "start": 3177.62, "end": 3177.74, "word": ",", "probability": 0.67333984375 } ] }, { "id": 854, "seek": 309048, "start": 3177.74, "end": 3182.04, "text": " okay, here's the tokenized words of the email that I have.", "tokens": [ 51314, 1392, 11, 510, 311, 264, 14862, 1602, 2283, 295, 264, 3796, 300, 286, 362, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.1956905297213985, "compression_ratio": 1.9139344262295082, "no_speech_prob": 0.0010814666748046875, "words": [ { "start": 3177.74, "end": 3177.88, "word": " okay", "probability": 0.42041015625 }, { "start": 3177.88, "end": 3177.94, "word": ",", "probability": 0.83740234375 }, { "start": 3177.94, "end": 3178.24, "word": " here's", "probability": 0.89794921875 }, { "start": 3178.24, "end": 3179.06, "word": " the", "probability": 0.81103515625 }, { "start": 3179.06, "end": 3180.02, "word": " tokenized", "probability": 0.74169921875 }, { "start": 3180.02, "end": 3180.48, "word": " words", "probability": 0.72607421875 }, { "start": 3180.48, "end": 3181.06, "word": " of", "probability": 0.90185546875 }, { "start": 3181.06, "end": 3181.2, "word": " the", "probability": 0.8115234375 }, { "start": 3181.2, "end": 3181.42, "word": " email", "probability": 0.9140625 }, { "start": 3181.42, "end": 3181.6, "word": " that", "probability": 0.88232421875 }, { "start": 3181.6, "end": 3181.7, "word": " I", "probability": 0.9990234375 }, { "start": 3181.7, "end": 3181.98, "word": " have", "probability": 0.876953125 }, { "start": 3181.98, "end": 3182.04, "word": ".", "probability": 0.56884765625 } ] }, { "id": 855, "seek": 309048, "start": 3182.04, "end": 3184.5, "text": " How many times does it show up in the count vectorizer?", "tokens": [ 51514, 1012, 867, 1413, 775, 309, 855, 493, 294, 264, 1207, 8062, 6545, 30, 51664 ], "temperature": 0.0, "avg_logprob": -0.1956905297213985, "compression_ratio": 1.9139344262295082, "no_speech_prob": 0.0010814666748046875, "words": [ { "start": 3182.04, "end": 3182.14, "word": " How", "probability": 0.8935546875 }, { "start": 3182.14, "end": 3182.3, "word": " many", "probability": 0.8154296875 }, { "start": 3182.3, "end": 3182.56, "word": " times", "probability": 0.81005859375 }, { "start": 3182.56, "end": 3182.72, "word": " does", "probability": 0.9248046875 }, { "start": 3182.72, "end": 3182.84, "word": " it", "probability": 0.90380859375 }, { "start": 3182.84, "end": 3183.04, "word": " show", "probability": 0.88037109375 }, { "start": 3183.04, "end": 3183.2, "word": " up", "probability": 0.90966796875 }, { "start": 3183.2, "end": 3183.28, "word": " in", "probability": 0.90673828125 }, { "start": 3183.28, "end": 3183.38, "word": " the", "probability": 0.80859375 }, { "start": 3183.38, "end": 3183.54, "word": " count", "probability": 0.67626953125 }, { "start": 3183.54, "end": 3184.12, "word": " vectorizer", "probability": 0.93408203125 }, { "start": 3184.12, "end": 3184.5, "word": "?", "probability": 0.66650390625 } ] }, { "id": 856, "seek": 311868, "start": 3184.5, "end": 3188.94, "text": " And then what is the weight that it shows up in the TFIDF vectorizer?", "tokens": [ 50364, 400, 550, 437, 307, 264, 3364, 300, 309, 3110, 493, 294, 264, 40964, 2777, 37, 8062, 6545, 30, 50614 ], "temperature": 0.0, "avg_logprob": -0.18245192135755833, "compression_ratio": 1.6788321167883211, "no_speech_prob": 0.0526123046875, "words": [ { "start": 3184.5, "end": 3184.5, "word": " And", "probability": 0.1043701171875 }, { "start": 3184.5, "end": 3184.6, "word": " then", "probability": 0.53076171875 }, { "start": 3184.6, "end": 3185.12, "word": " what", "probability": 0.66259765625 }, { "start": 3185.12, "end": 3185.46, "word": " is", "probability": 0.876953125 }, { "start": 3185.46, "end": 3185.68, "word": " the", "probability": 0.81787109375 }, { "start": 3185.68, "end": 3186.0, "word": " weight", "probability": 0.83251953125 }, { "start": 3186.0, "end": 3186.46, "word": " that", "probability": 0.85302734375 }, { "start": 3186.46, "end": 3186.6, "word": " it", "probability": 0.81787109375 }, { "start": 3186.6, "end": 3186.84, "word": " shows", "probability": 0.810546875 }, { "start": 3186.84, "end": 3187.04, "word": " up", "probability": 0.8984375 }, { "start": 3187.04, "end": 3187.2, "word": " in", "probability": 0.8818359375 }, { "start": 3187.2, "end": 3187.32, "word": " the", "probability": 0.78759765625 }, { "start": 3187.32, "end": 3188.02, "word": " TFIDF", "probability": 0.5078125 }, { "start": 3188.02, "end": 3188.54, "word": " vectorizer", "probability": 0.778564453125 }, { "start": 3188.54, "end": 3188.94, "word": "?", "probability": 0.464599609375 } ] }, { "id": 857, "seek": 311868, "start": 3189.74, "end": 3192.64, "text": " So I'm going to go ahead, Shift-Enter, run that.", "tokens": [ 50614, 407, 286, 478, 516, 281, 352, 2286, 11, 28304, 12, 16257, 391, 11, 1190, 300, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.18245192135755833, "compression_ratio": 1.6788321167883211, "no_speech_prob": 0.0526123046875, "words": [ { "start": 3189.74, "end": 3189.86, "word": " So", "probability": 0.65478515625 }, { "start": 3189.86, "end": 3190.1, "word": " I'm", "probability": 0.86181640625 }, { "start": 3190.1, "end": 3190.1, "word": " going", "probability": 0.53857421875 }, { "start": 3190.1, "end": 3190.12, "word": " to", "probability": 0.90234375 }, { "start": 3190.12, "end": 3190.22, "word": " go", "probability": 0.88427734375 }, { "start": 3190.22, "end": 3190.42, "word": " ahead", "probability": 0.8251953125 }, { "start": 3190.42, "end": 3190.62, "word": ",", "probability": 0.51318359375 }, { "start": 3190.62, "end": 3190.9, "word": " Shift", "probability": 0.2152099609375 }, { "start": 3190.9, "end": 3191.34, "word": "-Enter", "probability": 0.6708170572916666 }, { "start": 3191.34, "end": 3191.52, "word": ",", "probability": 0.8974609375 }, { "start": 3191.52, "end": 3191.86, "word": " run", "probability": 0.80224609375 }, { "start": 3191.86, "end": 3192.24, "word": " that", "probability": 0.8828125 }, { "start": 3192.24, "end": 3192.64, "word": ".", "probability": 0.80078125 } ] }, { "id": 858, "seek": 311868, "start": 3193.18, "end": 3195.26, "text": " And just like last time, this is going to take a little bit.", "tokens": [ 50764, 400, 445, 411, 1036, 565, 11, 341, 307, 516, 281, 747, 257, 707, 857, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.18245192135755833, "compression_ratio": 1.6788321167883211, "no_speech_prob": 0.0526123046875, "words": [ { "start": 3193.18, "end": 3193.3, "word": " And", "probability": 0.75830078125 }, { "start": 3193.3, "end": 3193.42, "word": " just", "probability": 0.8740234375 }, { "start": 3193.42, "end": 3193.56, "word": " like", "probability": 0.8798828125 }, { "start": 3193.56, "end": 3193.76, "word": " last", "probability": 0.80859375 }, { "start": 3193.76, "end": 3193.94, "word": " time", "probability": 0.796875 }, { "start": 3193.94, "end": 3193.98, "word": ",", "probability": 0.8203125 }, { "start": 3193.98, "end": 3194.08, "word": " this", "probability": 0.87548828125 }, { "start": 3194.08, "end": 3194.18, "word": " is", "probability": 0.90576171875 }, { "start": 3194.18, "end": 3194.26, "word": " going", "probability": 0.83740234375 }, { "start": 3194.26, "end": 3194.32, "word": " to", "probability": 0.9052734375 }, { "start": 3194.32, "end": 3194.46, "word": " take", "probability": 0.82275390625 }, { "start": 3194.58, "end": 3194.68, "word": " a little", "probability": 0.80126953125 }, { "start": 3194.68, "end": 3194.98, "word": " bit", "probability": 0.89111328125 }, { "start": 3194.98, "end": 3195.26, "word": ".", "probability": 0.80126953125 } ] }, { "id": 859, "seek": 311868, "start": 3195.34, "end": 3198.9, "text": " It's counting all the words and associating them with the different tokens.", "tokens": [ 50914, 467, 311, 13251, 439, 264, 2283, 293, 4180, 990, 552, 365, 264, 819, 22667, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.18245192135755833, "compression_ratio": 1.6788321167883211, "no_speech_prob": 0.0526123046875, "words": [ { "start": 3195.34, "end": 3195.74, "word": " It's", "probability": 0.94775390625 }, { "start": 3195.74, "end": 3196.24, "word": " counting", "probability": 0.76318359375 }, { "start": 3196.24, "end": 3196.42, "word": " all", "probability": 0.89892578125 }, { "start": 3196.42, "end": 3196.54, "word": " the", "probability": 0.79931640625 }, { "start": 3196.54, "end": 3196.74, "word": " words", "probability": 0.7177734375 }, { "start": 3196.74, "end": 3196.9, "word": " and", "probability": 0.8671875 }, { "start": 3196.9, "end": 3197.44, "word": " associating", "probability": 0.9375 }, { "start": 3197.44, "end": 3197.66, "word": " them", "probability": 0.74267578125 }, { "start": 3197.66, "end": 3197.84, "word": " with", "probability": 0.8125 }, { "start": 3197.84, "end": 3197.94, "word": " the", "probability": 0.8017578125 }, { "start": 3197.94, "end": 3198.16, "word": " different", "probability": 0.70068359375 }, { "start": 3198.16, "end": 3198.5, "word": " tokens", "probability": 0.74560546875 }, { "start": 3198.5, "end": 3198.9, "word": ".", "probability": 0.98779296875 } ] }, { "id": 860, "seek": 311868, "start": 3199.28, "end": 3201.98, "text": " This is going to be significantly faster than training it.", "tokens": [ 51114, 639, 307, 516, 281, 312, 10591, 4663, 813, 3097, 309, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.18245192135755833, "compression_ratio": 1.6788321167883211, "no_speech_prob": 0.0526123046875, "words": [ { "start": 3199.28, "end": 3199.48, "word": " This", "probability": 0.80419921875 }, { "start": 3199.48, "end": 3199.62, "word": " is", "probability": 0.90869140625 }, { "start": 3199.62, "end": 3199.72, "word": " going", "probability": 0.84814453125 }, { "start": 3199.72, "end": 3199.76, "word": " to", "probability": 0.90380859375 }, { "start": 3199.76, "end": 3199.9, "word": " be", "probability": 0.9140625 }, { "start": 3199.9, "end": 3200.42, "word": " significantly", "probability": 0.88037109375 }, { "start": 3200.42, "end": 3200.94, "word": " faster", "probability": 0.74365234375 }, { "start": 3200.94, "end": 3201.34, "word": " than", "probability": 0.87939453125 }, { "start": 3201.34, "end": 3201.7, "word": " training", "probability": 0.8017578125 }, { "start": 3201.7, "end": 3201.9, "word": " it", "probability": 0.85302734375 }, { "start": 3201.9, "end": 3201.98, "word": ".", "probability": 0.837890625 } ] }, { "id": 861, "seek": 311868, "start": 3201.98, "end": 3203.68, "text": " See, it's almost done already.", "tokens": [ 51214, 3008, 11, 309, 311, 1920, 1096, 1217, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.18245192135755833, "compression_ratio": 1.6788321167883211, "no_speech_prob": 0.0526123046875, "words": [ { "start": 3201.98, "end": 3202.1, "word": " See", "probability": 0.6533203125 }, { "start": 3202.1, "end": 3202.18, "word": ",", "probability": 0.75439453125 }, { "start": 3202.18, "end": 3202.32, "word": " it's", "probability": 0.946533203125 }, { "start": 3202.32, "end": 3202.6, "word": " almost", "probability": 0.68701171875 }, { "start": 3202.6, "end": 3202.86, "word": " done", "probability": 0.79638671875 }, { "start": 3202.86, "end": 3203.28, "word": " already", "probability": 0.837890625 }, { "start": 3203.28, "end": 3203.68, "word": ".", "probability": 0.9619140625 } ] }, { "id": 862, "seek": 311868, "start": 3205.02, "end": 3206.72, "text": " And so we're going to go ahead and move on.", "tokens": [ 51364, 400, 370, 321, 434, 516, 281, 352, 2286, 293, 1286, 322, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.18245192135755833, "compression_ratio": 1.6788321167883211, "no_speech_prob": 0.0526123046875, "words": [ { "start": 3205.02, "end": 3205.24, "word": " And", "probability": 0.7333984375 }, { "start": 3205.24, "end": 3205.34, "word": " so", "probability": 0.89111328125 }, { "start": 3205.34, "end": 3205.44, "word": " we're", "probability": 0.907958984375 }, { "start": 3205.44, "end": 3205.5, "word": " going", "probability": 0.82275390625 }, { "start": 3205.5, "end": 3205.52, "word": " to", "probability": 0.90380859375 }, { "start": 3205.52, "end": 3205.62, "word": " go", "probability": 0.888671875 }, { "start": 3205.62, "end": 3205.78, "word": " ahead", "probability": 0.8505859375 }, { "start": 3205.78, "end": 3205.88, "word": " and", "probability": 0.89794921875 }, { "start": 3205.88, "end": 3206.08, "word": " move", "probability": 0.8837890625 }, { "start": 3206.08, "end": 3206.32, "word": " on", "probability": 0.912109375 }, { "start": 3206.32, "end": 3206.72, "word": ".", "probability": 0.99658203125 } ] }, { "id": 863, "seek": 311868, "start": 3208.58, "end": 3212.7, "text": " So this bit, we're going to get ready to test and evaluate our models.", "tokens": [ 51564, 407, 341, 857, 11, 321, 434, 516, 281, 483, 1919, 281, 1500, 293, 13059, 527, 5245, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.18245192135755833, "compression_ratio": 1.6788321167883211, "no_speech_prob": 0.0526123046875, "words": [ { "start": 3208.58, "end": 3208.98, "word": " So", "probability": 0.85693359375 }, { "start": 3208.98, "end": 3209.34, "word": " this", "probability": 0.76171875 }, { "start": 3209.34, "end": 3209.66, "word": " bit", "probability": 0.9111328125 }, { "start": 3209.66, "end": 3209.9, "word": ",", "probability": 0.82275390625 }, { "start": 3209.9, "end": 3210.28, "word": " we're", "probability": 0.927490234375 }, { "start": 3210.28, "end": 3210.34, "word": " going", "probability": 0.841796875 }, { "start": 3210.34, "end": 3210.38, "word": " to", "probability": 0.90234375 }, { "start": 3210.38, "end": 3210.48, "word": " get", "probability": 0.90478515625 }, { "start": 3210.48, "end": 3210.66, "word": " ready", "probability": 0.81005859375 }, { "start": 3210.66, "end": 3210.96, "word": " to", "probability": 0.90869140625 }, { "start": 3210.96, "end": 3211.38, "word": " test", "probability": 0.8291015625 }, { "start": 3211.38, "end": 3211.58, "word": " and", "probability": 0.88916015625 }, { "start": 3211.58, "end": 3211.94, "word": " evaluate", "probability": 0.75048828125 }, { "start": 3211.94, "end": 3212.18, "word": " our", "probability": 0.8232421875 }, { "start": 3212.18, "end": 3212.48, "word": " models", "probability": 0.78466796875 }, { "start": 3212.48, "end": 3212.7, "word": ".", "probability": 0.9912109375 } ] }, { "id": 864, "seek": 314376, "start": 3212.7, "end": 3216.84, "text": " So this is just a helper function that's going to show us a bunch of really neat statistics.", "tokens": [ 50364, 407, 341, 307, 445, 257, 36133, 2445, 300, 311, 516, 281, 855, 505, 257, 3840, 295, 534, 10654, 12523, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.1624833775010515, "compression_ratio": 1.5701357466063348, "no_speech_prob": 0.0028438568115234375, "words": [ { "start": 3212.7, "end": 3212.88, "word": " So", "probability": 0.7548828125 }, { "start": 3212.88, "end": 3213.14, "word": " this", "probability": 0.76513671875 }, { "start": 3213.14, "end": 3213.26, "word": " is", "probability": 0.9033203125 }, { "start": 3213.26, "end": 3213.44, "word": " just", "probability": 0.89013671875 }, { "start": 3213.58, "end": 3213.76, "word": " a helper", "probability": 0.8564453125 }, { "start": 3213.76, "end": 3214.16, "word": " function", "probability": 0.8828125 }, { "start": 3214.16, "end": 3214.38, "word": " that's", "probability": 0.90087890625 }, { "start": 3214.38, "end": 3214.5, "word": " going", "probability": 0.85595703125 }, { "start": 3214.5, "end": 3214.64, "word": " to", "probability": 0.90869140625 }, { "start": 3214.64, "end": 3214.8, "word": " show", "probability": 0.876953125 }, { "start": 3214.8, "end": 3214.92, "word": " us", "probability": 0.90087890625 }, { "start": 3215.04, "end": 3215.18, "word": " a bunch", "probability": 0.818359375 }, { "start": 3215.18, "end": 3215.28, "word": " of", "probability": 0.90625 }, { "start": 3215.28, "end": 3215.5, "word": " really", "probability": 0.78076171875 }, { "start": 3215.5, "end": 3215.78, "word": " neat", "probability": 0.89306640625 }, { "start": 3215.78, "end": 3216.4, "word": " statistics", "probability": 0.8837890625 }, { "start": 3216.4, "end": 3216.84, "word": ".", "probability": 0.88818359375 } ] }, { "id": 865, "seek": 314376, "start": 3217.1, "end": 3220.94, "text": " The details of this helper function you can look into on your own.", "tokens": [ 50564, 440, 4365, 295, 341, 36133, 2445, 291, 393, 574, 666, 322, 428, 1065, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.1624833775010515, "compression_ratio": 1.5701357466063348, "no_speech_prob": 0.0028438568115234375, "words": [ { "start": 3217.1, "end": 3217.54, "word": " The", "probability": 0.81640625 }, { "start": 3217.54, "end": 3217.86, "word": " details", "probability": 0.72021484375 }, { "start": 3217.86, "end": 3218.02, "word": " of", "probability": 0.8984375 }, { "start": 3218.02, "end": 3218.16, "word": " this", "probability": 0.88330078125 }, { "start": 3218.16, "end": 3218.34, "word": " helper", "probability": 0.861328125 }, { "start": 3218.34, "end": 3218.72, "word": " function", "probability": 0.88427734375 }, { "start": 3218.72, "end": 3218.94, "word": " you", "probability": 0.611328125 }, { "start": 3218.94, "end": 3219.08, "word": " can", "probability": 0.89404296875 }, { "start": 3219.08, "end": 3219.28, "word": " look", "probability": 0.9130859375 }, { "start": 3219.28, "end": 3219.6, "word": " into", "probability": 0.724609375 }, { "start": 3219.6, "end": 3219.96, "word": " on", "probability": 0.9091796875 }, { "start": 3219.96, "end": 3220.12, "word": " your", "probability": 0.81103515625 }, { "start": 3220.12, "end": 3220.5, "word": " own", "probability": 0.82763671875 }, { "start": 3220.5, "end": 3220.94, "word": ".", "probability": 0.399658203125 } ] }, { "id": 866, "seek": 314376, "start": 3221.18, "end": 3227.0, "text": " But for now, what we need to use as an input is our confusion matrix,", "tokens": [ 50764, 583, 337, 586, 11, 437, 321, 643, 281, 764, 382, 364, 4846, 307, 527, 15075, 8141, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.1624833775010515, "compression_ratio": 1.5701357466063348, "no_speech_prob": 0.0028438568115234375, "words": [ { "start": 3221.18, "end": 3221.28, "word": " But", "probability": 0.88330078125 }, { "start": 3221.28, "end": 3221.6, "word": " for", "probability": 0.86181640625 }, { "start": 3221.6, "end": 3222.46, "word": " now", "probability": 0.9033203125 }, { "start": 3222.46, "end": 3222.8, "word": ",", "probability": 0.8046875 }, { "start": 3222.8, "end": 3223.6, "word": " what", "probability": 0.888671875 }, { "start": 3223.6, "end": 3223.72, "word": " we", "probability": 0.904296875 }, { "start": 3223.72, "end": 3223.86, "word": " need", "probability": 0.7646484375 }, { "start": 3223.86, "end": 3223.96, "word": " to", "probability": 0.90771484375 }, { "start": 3223.96, "end": 3224.18, "word": " use", "probability": 0.65087890625 }, { "start": 3224.18, "end": 3224.38, "word": " as", "probability": 0.900390625 }, { "start": 3224.38, "end": 3224.5, "word": " an", "probability": 0.89794921875 }, { "start": 3224.5, "end": 3224.76, "word": " input", "probability": 0.8759765625 }, { "start": 3224.76, "end": 3225.02, "word": " is", "probability": 0.88037109375 }, { "start": 3225.02, "end": 3225.18, "word": " our", "probability": 0.82861328125 }, { "start": 3225.18, "end": 3225.52, "word": " confusion", "probability": 0.86376953125 }, { "start": 3225.52, "end": 3226.7, "word": " matrix", "probability": 0.8623046875 }, { "start": 3226.7, "end": 3227.0, "word": ",", "probability": 0.97265625 } ] }, { "id": 867, "seek": 314376, "start": 3227.0, "end": 3230.4, "text": " our score, and our classification report.", "tokens": [ 51064, 527, 6175, 11, 293, 527, 21538, 2275, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.1624833775010515, "compression_ratio": 1.5701357466063348, "no_speech_prob": 0.0028438568115234375, "words": [ { "start": 3227.0, "end": 3227.12, "word": " our", "probability": 0.82666015625 }, { "start": 3227.12, "end": 3227.58, "word": " score", "probability": 0.80517578125 }, { "start": 3227.58, "end": 3227.84, "word": ",", "probability": 0.58837890625 }, { "start": 3227.84, "end": 3228.04, "word": " and", "probability": 0.8955078125 }, { "start": 3228.04, "end": 3228.36, "word": " our", "probability": 0.8203125 }, { "start": 3228.36, "end": 3229.06, "word": " classification", "probability": 0.94140625 }, { "start": 3229.06, "end": 3229.96, "word": " report", "probability": 0.85302734375 }, { "start": 3229.96, "end": 3230.4, "word": ".", "probability": 0.998046875 } ] }, { "id": 868, "seek": 314376, "start": 3231.66, "end": 3234.6, "text": " So we're just going to go ahead, Shift-Enter, run that.", "tokens": [ 51314, 407, 321, 434, 445, 516, 281, 352, 2286, 11, 28304, 12, 16257, 391, 11, 1190, 300, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.1624833775010515, "compression_ratio": 1.5701357466063348, "no_speech_prob": 0.0028438568115234375, "words": [ { "start": 3231.66, "end": 3232.1, "word": " So", "probability": 0.90087890625 }, { "start": 3232.1, "end": 3232.28, "word": " we're", "probability": 0.9150390625 }, { "start": 3232.28, "end": 3232.38, "word": " just", "probability": 0.87939453125 }, { "start": 3232.38, "end": 3232.48, "word": " going", "probability": 0.28515625 }, { "start": 3232.48, "end": 3232.52, "word": " to", "probability": 0.90576171875 }, { "start": 3232.52, "end": 3232.64, "word": " go", "probability": 0.888671875 }, { "start": 3232.64, "end": 3232.84, "word": " ahead", "probability": 0.8251953125 }, { "start": 3232.84, "end": 3232.94, "word": ",", "probability": 0.6982421875 }, { "start": 3232.94, "end": 3233.14, "word": " Shift", "probability": 0.325439453125 }, { "start": 3233.14, "end": 3233.54, "word": "-Enter", "probability": 0.6317952473958334 }, { "start": 3233.54, "end": 3233.64, "word": ",", "probability": 0.94189453125 }, { "start": 3233.64, "end": 3233.84, "word": " run", "probability": 0.861328125 }, { "start": 3233.84, "end": 3234.16, "word": " that", "probability": 0.884765625 }, { "start": 3234.16, "end": 3234.6, "word": ".", "probability": 0.461181640625 } ] }, { "id": 869, "seek": 314376, "start": 3234.96, "end": 3237.78, "text": " Definition defined.", "tokens": [ 51464, 46245, 849, 7642, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.1624833775010515, "compression_ratio": 1.5701357466063348, "no_speech_prob": 0.0028438568115234375, "words": [ { "start": 3234.96, "end": 3235.4, "word": " Definition", "probability": 0.87548828125 }, { "start": 3235.4, "end": 3237.34, "word": " defined", "probability": 0.677734375 }, { "start": 3237.34, "end": 3237.78, "word": ".", "probability": 0.943359375 } ] }, { "id": 870, "seek": 317254, "start": 3239.22, "end": 3244.74, "text": " And then here's where we get into tasks 6a, 6b, 6c, and 6d,", "tokens": [ 50414, 400, 550, 510, 311, 689, 321, 483, 666, 9608, 1386, 64, 11, 1386, 65, 11, 1386, 66, 11, 293, 1386, 67, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.18920693377486797, "compression_ratio": 1.8266666666666667, "no_speech_prob": 0.01132965087890625, "words": [ { "start": 3239.22, "end": 3239.7, "word": " And", "probability": 0.67626953125 }, { "start": 3239.7, "end": 3239.84, "word": " then", "probability": 0.7197265625 }, { "start": 3239.84, "end": 3240.16, "word": " here's", "probability": 0.8701171875 }, { "start": 3240.16, "end": 3240.28, "word": " where", "probability": 0.904296875 }, { "start": 3240.28, "end": 3240.42, "word": " we", "probability": 0.9033203125 }, { "start": 3240.42, "end": 3240.6, "word": " get", "probability": 0.89990234375 }, { "start": 3240.6, "end": 3240.82, "word": " into", "probability": 0.7421875 }, { "start": 3240.82, "end": 3241.16, "word": " tasks", "probability": 0.67041015625 }, { "start": 3241.16, "end": 3242.06, "word": " 6a", "probability": 0.665283203125 }, { "start": 3242.06, "end": 3242.2, "word": ",", "probability": 0.95703125 }, { "start": 3242.2, "end": 3242.68, "word": " 6b", "probability": 0.995849609375 }, { "start": 3242.68, "end": 3242.82, "word": ",", "probability": 0.9931640625 }, { "start": 3242.82, "end": 3243.44, "word": " 6c", "probability": 0.994140625 }, { "start": 3243.44, "end": 3243.52, "word": ",", "probability": 0.60205078125 }, { "start": 3243.52, "end": 3243.7, "word": " and", "probability": 0.88916015625 }, { "start": 3243.7, "end": 3244.48, "word": " 6d", "probability": 0.998046875 }, { "start": 3244.48, "end": 3244.74, "word": ",", "probability": 0.63232421875 } ] }, { "id": 871, "seek": 317254, "start": 3244.74, "end": 3249.3, "text": " which is going to be us training and evaluating our different models.", "tokens": [ 50714, 597, 307, 516, 281, 312, 505, 3097, 293, 27479, 527, 819, 5245, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.18920693377486797, "compression_ratio": 1.8266666666666667, "no_speech_prob": 0.01132965087890625, "words": [ { "start": 3244.74, "end": 3245.54, "word": " which", "probability": 0.9150390625 }, { "start": 3245.54, "end": 3245.66, "word": " is", "probability": 0.90576171875 }, { "start": 3245.66, "end": 3245.8, "word": " going", "probability": 0.85693359375 }, { "start": 3245.8, "end": 3245.94, "word": " to", "probability": 0.90380859375 }, { "start": 3245.94, "end": 3246.08, "word": " be", "probability": 0.9013671875 }, { "start": 3246.08, "end": 3246.42, "word": " us", "probability": 0.90869140625 }, { "start": 3246.42, "end": 3246.78, "word": " training", "probability": 0.78564453125 }, { "start": 3246.78, "end": 3246.96, "word": " and", "probability": 0.8896484375 }, { "start": 3246.96, "end": 3247.42, "word": " evaluating", "probability": 0.75830078125 }, { "start": 3247.42, "end": 3247.72, "word": " our", "probability": 0.82275390625 }, { "start": 3247.72, "end": 3248.08, "word": " different", "probability": 0.69482421875 }, { "start": 3248.08, "end": 3248.82, "word": " models", "probability": 0.794921875 }, { "start": 3248.82, "end": 3249.3, "word": ".", "probability": 0.98486328125 } ] }, { "id": 872, "seek": 317254, "start": 3249.38, "end": 3253.38, "text": " So we're going to start with multinomial Naive Bayesian with a TF-IDF vectorizer,", "tokens": [ 50914, 407, 321, 434, 516, 281, 722, 365, 45872, 47429, 6056, 488, 7840, 42434, 365, 257, 40964, 12, 2777, 37, 8062, 6545, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.18920693377486797, "compression_ratio": 1.8266666666666667, "no_speech_prob": 0.01132965087890625, "words": [ { "start": 3249.38, "end": 3249.62, "word": " So", "probability": 0.8525390625 }, { "start": 3249.62, "end": 3249.86, "word": " we're", "probability": 0.86865234375 }, { "start": 3249.86, "end": 3249.9, "word": " going", "probability": 0.35791015625 }, { "start": 3249.9, "end": 3249.96, "word": " to", "probability": 0.90283203125 }, { "start": 3249.96, "end": 3250.12, "word": " start", "probability": 0.86474609375 }, { "start": 3250.12, "end": 3250.3, "word": " with", "probability": 0.82080078125 }, { "start": 3250.3, "end": 3250.86, "word": " multinomial", "probability": 0.90966796875 }, { "start": 3250.86, "end": 3251.2, "word": " Naive", "probability": 0.6351318359375 }, { "start": 3251.2, "end": 3251.5, "word": " Bayesian", "probability": 0.915771484375 }, { "start": 3251.5, "end": 3251.74, "word": " with", "probability": 0.744140625 }, { "start": 3251.86, "end": 3252.12, "word": " a TF", "probability": 0.7265625 }, { "start": 3252.12, "end": 3252.44, "word": "-IDF", "probability": 0.9200846354166666 }, { "start": 3252.44, "end": 3253.02, "word": " vectorizer", "probability": 0.88720703125 }, { "start": 3253.02, "end": 3253.38, "word": ",", "probability": 0.763671875 } ] }, { "id": 873, "seek": 317254, "start": 3253.38, "end": 3258.14, "text": " with a count vectorizer, and then we're going to do the same for logistic regression with TF-IDF", "tokens": [ 51114, 365, 257, 1207, 8062, 6545, 11, 293, 550, 321, 434, 516, 281, 360, 264, 912, 337, 3565, 3142, 24590, 365, 40964, 12, 2777, 37, 51364 ], "temperature": 0.0, "avg_logprob": -0.18920693377486797, "compression_ratio": 1.8266666666666667, "no_speech_prob": 0.01132965087890625, "words": [ { "start": 3253.38, "end": 3253.74, "word": " with", "probability": 0.80322265625 }, { "start": 3253.86, "end": 3254.12, "word": " a count", "probability": 0.61083984375 }, { "start": 3254.12, "end": 3254.74, "word": " vectorizer", "probability": 0.95654296875 }, { "start": 3254.74, "end": 3254.94, "word": ",", "probability": 0.76171875 }, { "start": 3254.94, "end": 3255.16, "word": " and", "probability": 0.89111328125 }, { "start": 3255.16, "end": 3255.24, "word": " then", "probability": 0.71240234375 }, { "start": 3255.24, "end": 3255.38, "word": " we're", "probability": 0.924560546875 }, { "start": 3255.38, "end": 3255.44, "word": " going", "probability": 0.720703125 }, { "start": 3255.44, "end": 3255.46, "word": " to", "probability": 0.90234375 }, { "start": 3255.46, "end": 3255.56, "word": " do", "probability": 0.9072265625 }, { "start": 3255.56, "end": 3255.72, "word": " the", "probability": 0.81201171875 }, { "start": 3255.72, "end": 3255.9, "word": " same", "probability": 0.8173828125 }, { "start": 3255.9, "end": 3256.26, "word": " for", "probability": 0.8984375 }, { "start": 3256.26, "end": 3256.7, "word": " logistic", "probability": 0.915283203125 }, { "start": 3256.7, "end": 3257.06, "word": " regression", "probability": 0.9013671875 }, { "start": 3257.06, "end": 3257.36, "word": " with", "probability": 0.802734375 }, { "start": 3257.36, "end": 3257.66, "word": " TF", "probability": 0.89013671875 }, { "start": 3257.66, "end": 3258.14, "word": "-IDF", "probability": 0.98974609375 } ] }, { "id": 874, "seek": 317254, "start": 3258.14, "end": 3262.04, "text": " and logistic regression with a count vectorizer.", "tokens": [ 51364, 293, 3565, 3142, 24590, 365, 257, 1207, 8062, 6545, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.18920693377486797, "compression_ratio": 1.8266666666666667, "no_speech_prob": 0.01132965087890625, "words": [ { "start": 3258.14, "end": 3258.8, "word": " and", "probability": 0.55322265625 }, { "start": 3258.8, "end": 3259.32, "word": " logistic", "probability": 0.933349609375 }, { "start": 3259.32, "end": 3259.74, "word": " regression", "probability": 0.88916015625 }, { "start": 3259.74, "end": 3260.6, "word": " with", "probability": 0.8115234375 }, { "start": 3260.82, "end": 3261.02, "word": " a count", "probability": 0.75732421875 }, { "start": 3261.02, "end": 3261.56, "word": " vectorizer", "probability": 0.95263671875 }, { "start": 3261.56, "end": 3262.04, "word": ".", "probability": 0.99560546875 } ] }, { "id": 875, "seek": 317254, "start": 3264.02, "end": 3266.56, "text": " So we're going to start out just one thing at a time.", "tokens": [ 51614, 407, 321, 434, 516, 281, 722, 484, 445, 472, 551, 412, 257, 565, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.18920693377486797, "compression_ratio": 1.8266666666666667, "no_speech_prob": 0.01132965087890625, "words": [ { "start": 3264.02, "end": 3264.5, "word": " So", "probability": 0.8740234375 }, { "start": 3264.5, "end": 3264.64, "word": " we're", "probability": 0.912109375 }, { "start": 3264.64, "end": 3264.64, "word": " going", "probability": 0.77685546875 }, { "start": 3264.64, "end": 3264.68, "word": " to", "probability": 0.89990234375 }, { "start": 3264.68, "end": 3264.86, "word": " start", "probability": 0.8759765625 }, { "start": 3264.86, "end": 3265.06, "word": " out", "probability": 0.55810546875 }, { "start": 3265.06, "end": 3265.44, "word": " just", "probability": 0.6044921875 }, { "start": 3265.44, "end": 3266.02, "word": " one", "probability": 0.81201171875 }, { "start": 3266.02, "end": 3266.16, "word": " thing", "probability": 0.81103515625 }, { "start": 3266.16, "end": 3266.26, "word": " at", "probability": 0.90283203125 }, { "start": 3266.32, "end": 3266.54, "word": " a time", "probability": 0.80712890625 }, { "start": 3266.54, "end": 3266.56, "word": ".", "probability": 0.83984375 } ] }, { "id": 876, "seek": 319820, "start": 3267.32, "end": 3270.42, "text": " We're going to define our constructor.", "tokens": [ 50414, 492, 434, 516, 281, 6964, 527, 47479, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.2422839476738447, "compression_ratio": 1.5031055900621118, "no_speech_prob": 0.00426483154296875, "words": [ { "start": 3267.32, "end": 3267.94, "word": " We're", "probability": 0.635498046875 }, { "start": 3267.94, "end": 3268.14, "word": " going", "probability": 0.84716796875 }, { "start": 3268.14, "end": 3268.38, "word": " to", "probability": 0.904296875 }, { "start": 3268.38, "end": 3269.08, "word": " define", "probability": 0.8798828125 }, { "start": 3269.08, "end": 3269.48, "word": " our", "probability": 0.80322265625 }, { "start": 3269.48, "end": 3270.2, "word": " constructor", "probability": 0.5654296875 }, { "start": 3270.2, "end": 3270.42, "word": ".", "probability": 0.402587890625 } ] }, { "id": 877, "seek": 319820, "start": 3270.42, "end": 3276.48, "text": " So this is going to be MNB TF-IDF equals multinomial NB.", "tokens": [ 50564, 407, 341, 307, 516, 281, 312, 376, 45, 33, 40964, 12, 2777, 37, 6915, 45872, 47429, 426, 33, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.2422839476738447, "compression_ratio": 1.5031055900621118, "no_speech_prob": 0.00426483154296875, "words": [ { "start": 3270.42, "end": 3270.44, "word": " So", "probability": 0.444091796875 }, { "start": 3270.44, "end": 3270.56, "word": " this", "probability": 0.794921875 }, { "start": 3270.56, "end": 3270.68, "word": " is", "probability": 0.89990234375 }, { "start": 3270.68, "end": 3270.76, "word": " going", "probability": 0.66259765625 }, { "start": 3270.76, "end": 3270.78, "word": " to", "probability": 0.90673828125 }, { "start": 3270.78, "end": 3270.92, "word": " be", "probability": 0.8984375 }, { "start": 3270.92, "end": 3271.38, "word": " MNB", "probability": 0.5694986979166666 }, { "start": 3271.38, "end": 3272.0, "word": " TF", "probability": 0.330322265625 }, { "start": 3272.0, "end": 3272.74, "word": "-IDF", "probability": 0.6936848958333334 }, { "start": 3272.74, "end": 3273.46, "word": " equals", "probability": 0.560546875 }, { "start": 3273.46, "end": 3275.34, "word": " multinomial", "probability": 0.795654296875 }, { "start": 3275.34, "end": 3276.28, "word": " NB", "probability": 0.6351318359375 }, { "start": 3276.28, "end": 3276.48, "word": ".", "probability": 0.41259765625 } ] }, { "id": 878, "seek": 319820, "start": 3276.48, "end": 3278.66, "text": " Watch your capitalization.", "tokens": [ 50864, 7277, 428, 4238, 2144, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.2422839476738447, "compression_ratio": 1.5031055900621118, "no_speech_prob": 0.00426483154296875, "words": [ { "start": 3276.48, "end": 3276.98, "word": " Watch", "probability": 0.88623046875 }, { "start": 3276.98, "end": 3277.24, "word": " your", "probability": 0.8193359375 }, { "start": 3277.24, "end": 3278.04, "word": " capitalization", "probability": 0.935546875 }, { "start": 3278.04, "end": 3278.66, "word": ".", "probability": 0.9287109375 } ] }, { "id": 879, "seek": 319820, "start": 3279.58, "end": 3282.36, "text": " We're going to define that, and then we're going to train it.", "tokens": [ 51014, 492, 434, 516, 281, 6964, 300, 11, 293, 550, 321, 434, 516, 281, 3847, 309, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.2422839476738447, "compression_ratio": 1.5031055900621118, "no_speech_prob": 0.00426483154296875, "words": [ { "start": 3279.58, "end": 3279.98, "word": " We're", "probability": 0.86669921875 }, { "start": 3279.98, "end": 3280.04, "word": " going", "probability": 0.7109375 }, { "start": 3280.04, "end": 3280.08, "word": " to", "probability": 0.904296875 }, { "start": 3280.08, "end": 3280.3, "word": " define", "probability": 0.72998046875 }, { "start": 3280.3, "end": 3280.54, "word": " that", "probability": 0.8818359375 }, { "start": 3280.54, "end": 3280.62, "word": ",", "probability": 0.322021484375 }, { "start": 3280.62, "end": 3280.68, "word": " and", "probability": 0.8798828125 }, { "start": 3280.68, "end": 3280.78, "word": " then", "probability": 0.7265625 }, { "start": 3280.78, "end": 3280.88, "word": " we're", "probability": 0.926025390625 }, { "start": 3280.88, "end": 3281.04, "word": " going", "probability": 0.859375 }, { "start": 3281.04, "end": 3281.2, "word": " to", "probability": 0.89697265625 }, { "start": 3281.2, "end": 3281.56, "word": " train", "probability": 0.79638671875 }, { "start": 3281.56, "end": 3281.74, "word": " it", "probability": 0.8828125 }, { "start": 3281.74, "end": 3282.36, "word": ".", "probability": 0.89306640625 } ] }, { "id": 880, "seek": 319820, "start": 3283.74, "end": 3292.22, "text": " MNB TF-IDF dot fit, which is train in scikit-learn world.", "tokens": [ 51164, 376, 45, 33, 40964, 12, 2777, 37, 5893, 3318, 11, 597, 307, 3847, 294, 2180, 22681, 12, 306, 1083, 1002, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.2422839476738447, "compression_ratio": 1.5031055900621118, "no_speech_prob": 0.00426483154296875, "words": [ { "start": 3283.74, "end": 3284.36, "word": " MNB", "probability": 0.795654296875 }, { "start": 3284.36, "end": 3284.98, "word": " TF", "probability": 0.697265625 }, { "start": 3284.98, "end": 3285.58, "word": "-IDF", "probability": 0.9749348958333334 }, { "start": 3285.58, "end": 3286.92, "word": " dot", "probability": 0.428955078125 }, { "start": 3286.92, "end": 3288.16, "word": " fit", "probability": 0.64697265625 }, { "start": 3288.16, "end": 3288.44, "word": ",", "probability": 0.8203125 }, { "start": 3288.44, "end": 3288.62, "word": " which", "probability": 0.9169921875 }, { "start": 3288.62, "end": 3288.98, "word": " is", "probability": 0.90966796875 }, { "start": 3288.98, "end": 3289.96, "word": " train", "probability": 0.64208984375 }, { "start": 3289.96, "end": 3290.86, "word": " in", "probability": 0.73779296875 }, { "start": 3290.86, "end": 3291.1, "word": " scikit", "probability": 0.701904296875 }, { "start": 3291.1, "end": 3291.26, "word": "-learn", "probability": 0.93994140625 }, { "start": 3291.26, "end": 3291.6, "word": " world", "probability": 0.79931640625 }, { "start": 3291.6, "end": 3292.22, "word": ".", "probability": 0.69091796875 } ] }, { "id": 881, "seek": 322486, "start": 3292.22, "end": 3297.14, "text": " And we're going to use our TF-IDF X, which is our preprocessed information,", "tokens": [ 50364, 400, 321, 434, 516, 281, 764, 527, 40964, 12, 2777, 37, 1783, 11, 597, 307, 527, 2666, 340, 780, 292, 1589, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.1906249965940203, "compression_ratio": 1.7190476190476192, "no_speech_prob": 0.0023593902587890625, "words": [ { "start": 3292.22, "end": 3292.44, "word": " And", "probability": 0.25634765625 }, { "start": 3292.44, "end": 3292.58, "word": " we're", "probability": 0.895263671875 }, { "start": 3292.58, "end": 3292.66, "word": " going", "probability": 0.64697265625 }, { "start": 3292.66, "end": 3292.68, "word": " to", "probability": 0.9052734375 }, { "start": 3292.68, "end": 3292.88, "word": " use", "probability": 0.83984375 }, { "start": 3292.88, "end": 3293.14, "word": " our", "probability": 0.79833984375 }, { "start": 3293.14, "end": 3293.72, "word": " TF", "probability": 0.452392578125 }, { "start": 3293.72, "end": 3294.42, "word": "-IDF", "probability": 0.7760416666666666 }, { "start": 3294.42, "end": 3295.16, "word": " X", "probability": 0.2362060546875 }, { "start": 3295.16, "end": 3295.3, "word": ",", "probability": 0.6748046875 }, { "start": 3295.3, "end": 3295.4, "word": " which", "probability": 0.90966796875 }, { "start": 3295.4, "end": 3295.5, "word": " is", "probability": 0.89892578125 }, { "start": 3295.5, "end": 3295.64, "word": " our", "probability": 0.8232421875 }, { "start": 3295.64, "end": 3296.4, "word": " preprocessed", "probability": 0.82440185546875 }, { "start": 3296.4, "end": 3296.82, "word": " information", "probability": 0.7373046875 }, { "start": 3296.82, "end": 3297.14, "word": ",", "probability": 0.498291015625 } ] }, { "id": 882, "seek": 322486, "start": 3297.14, "end": 3300.08, "text": " and then we're going to compare it to our labels.", "tokens": [ 50614, 293, 550, 321, 434, 516, 281, 6794, 309, 281, 527, 16949, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.1906249965940203, "compression_ratio": 1.7190476190476192, "no_speech_prob": 0.0023593902587890625, "words": [ { "start": 3297.14, "end": 3297.18, "word": " and", "probability": 0.87744140625 }, { "start": 3297.18, "end": 3297.3, "word": " then", "probability": 0.30322265625 }, { "start": 3297.3, "end": 3297.38, "word": " we're", "probability": 0.92431640625 }, { "start": 3297.38, "end": 3297.54, "word": " going", "probability": 0.8662109375 }, { "start": 3297.54, "end": 3297.7, "word": " to", "probability": 0.90576171875 }, { "start": 3297.7, "end": 3298.02, "word": " compare", "probability": 0.87255859375 }, { "start": 3298.02, "end": 3298.18, "word": " it", "probability": 0.89794921875 }, { "start": 3298.18, "end": 3298.38, "word": " to", "probability": 0.9033203125 }, { "start": 3298.38, "end": 3298.82, "word": " our", "probability": 0.8193359375 }, { "start": 3298.82, "end": 3299.68, "word": " labels", "probability": 0.85546875 }, { "start": 3299.68, "end": 3300.08, "word": ".", "probability": 0.986328125 } ] }, { "id": 883, "seek": 322486, "start": 3302.06, "end": 3303.86, "text": " So that's going to train our model.", "tokens": [ 50864, 407, 300, 311, 516, 281, 3847, 527, 2316, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.1906249965940203, "compression_ratio": 1.7190476190476192, "no_speech_prob": 0.0023593902587890625, "words": [ { "start": 3302.06, "end": 3302.46, "word": " So", "probability": 0.85693359375 }, { "start": 3302.46, "end": 3302.64, "word": " that's", "probability": 0.912353515625 }, { "start": 3302.64, "end": 3302.76, "word": " going", "probability": 0.859375 }, { "start": 3302.76, "end": 3302.9, "word": " to", "probability": 0.90380859375 }, { "start": 3302.9, "end": 3303.2, "word": " train", "probability": 0.7890625 }, { "start": 3303.2, "end": 3303.34, "word": " our", "probability": 0.82080078125 }, { "start": 3303.34, "end": 3303.62, "word": " model", "probability": 0.80224609375 }, { "start": 3303.62, "end": 3303.86, "word": ".", "probability": 0.80126953125 } ] }, { "id": 884, "seek": 322486, "start": 3303.86, "end": 3307.3, "text": " Now we're going to grab a couple really neat statistics.", "tokens": [ 50964, 823, 321, 434, 516, 281, 4444, 257, 1916, 534, 10654, 12523, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.1906249965940203, "compression_ratio": 1.7190476190476192, "no_speech_prob": 0.0023593902587890625, "words": [ { "start": 3303.86, "end": 3304.06, "word": " Now", "probability": 0.896484375 }, { "start": 3304.06, "end": 3304.22, "word": " we're", "probability": 0.894287109375 }, { "start": 3304.22, "end": 3304.44, "word": " going", "probability": 0.8544921875 }, { "start": 3304.44, "end": 3304.78, "word": " to", "probability": 0.90625 }, { "start": 3304.78, "end": 3305.14, "word": " grab", "probability": 0.794921875 }, { "start": 3305.36, "end": 3305.66, "word": " a couple", "probability": 0.7939453125 }, { "start": 3305.66, "end": 3306.44, "word": " really", "probability": 0.66796875 }, { "start": 3306.44, "end": 3306.68, "word": " neat", "probability": 0.8818359375 }, { "start": 3306.68, "end": 3307.14, "word": " statistics", "probability": 0.8857421875 }, { "start": 3307.14, "end": 3307.3, "word": ".", "probability": 0.92236328125 } ] }, { "id": 885, "seek": 322486, "start": 3307.3, "end": 3312.02, "text": " So the first one we're going to get is our score, and this wants us to call it score.", "tokens": [ 51114, 407, 264, 700, 472, 321, 434, 516, 281, 483, 307, 527, 6175, 11, 293, 341, 2738, 505, 281, 818, 309, 6175, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.1906249965940203, "compression_ratio": 1.7190476190476192, "no_speech_prob": 0.0023593902587890625, "words": [ { "start": 3307.3, "end": 3307.38, "word": " So", "probability": 0.84130859375 }, { "start": 3307.38, "end": 3307.48, "word": " the", "probability": 0.8037109375 }, { "start": 3307.48, "end": 3307.64, "word": " first", "probability": 0.81640625 }, { "start": 3307.64, "end": 3307.78, "word": " one", "probability": 0.81787109375 }, { "start": 3307.78, "end": 3307.94, "word": " we're", "probability": 0.9140625 }, { "start": 3307.94, "end": 3307.98, "word": " going", "probability": 0.8271484375 }, { "start": 3307.98, "end": 3308.02, "word": " to", "probability": 0.90283203125 }, { "start": 3308.02, "end": 3308.16, "word": " get", "probability": 0.89697265625 }, { "start": 3308.16, "end": 3308.34, "word": " is", "probability": 0.904296875 }, { "start": 3308.34, "end": 3308.5, "word": " our", "probability": 0.82763671875 }, { "start": 3308.5, "end": 3309.02, "word": " score", "probability": 0.77490234375 }, { "start": 3309.02, "end": 3309.54, "word": ",", "probability": 0.5234375 }, { "start": 3309.54, "end": 3309.76, "word": " and", "probability": 0.89208984375 }, { "start": 3309.76, "end": 3309.96, "word": " this", "probability": 0.8779296875 }, { "start": 3309.96, "end": 3310.2, "word": " wants", "probability": 0.6923828125 }, { "start": 3310.2, "end": 3310.34, "word": " us", "probability": 0.90380859375 }, { "start": 3310.34, "end": 3310.48, "word": " to", "probability": 0.90380859375 }, { "start": 3310.48, "end": 3310.68, "word": " call", "probability": 0.80810546875 }, { "start": 3310.68, "end": 3311.02, "word": " it", "probability": 0.8857421875 }, { "start": 3311.02, "end": 3311.94, "word": " score", "probability": 0.407958984375 }, { "start": 3311.94, "end": 3312.02, "word": ".", "probability": 0.06634521484375 } ] }, { "id": 886, "seek": 322486, "start": 3314.38, "end": 3318.88, "text": " Score MNB TF-IDF predictions using our predict function.", "tokens": [ 51464, 47901, 376, 45, 33, 40964, 12, 2777, 37, 21264, 1228, 527, 6069, 2445, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.1906249965940203, "compression_ratio": 1.7190476190476192, "no_speech_prob": 0.0023593902587890625, "words": [ { "start": 3314.38, "end": 3314.78, "word": " Score", "probability": 0.69482421875 }, { "start": 3314.78, "end": 3315.18, "word": " MNB", "probability": 0.6524251302083334 }, { "start": 3315.18, "end": 3315.54, "word": " TF", "probability": 0.5859375 }, { "start": 3315.54, "end": 3315.98, "word": "-IDF", "probability": 0.9781901041666666 }, { "start": 3315.98, "end": 3316.46, "word": " predictions", "probability": 0.6953125 }, { "start": 3316.46, "end": 3317.78, "word": " using", "probability": 0.5947265625 }, { "start": 3317.78, "end": 3317.94, "word": " our", "probability": 0.767578125 }, { "start": 3317.94, "end": 3318.12, "word": " predict", "probability": 0.7900390625 }, { "start": 3318.12, "end": 3318.58, "word": " function", "probability": 0.88037109375 }, { "start": 3318.58, "end": 3318.88, "word": ".", "probability": 0.8388671875 } ] }, { "id": 887, "seek": 324926, "start": 3318.88, "end": 3323.1, "text": " We're going to develop a confusion matrix called C matrix, MNB TF-IDF,", "tokens": [ 50364, 492, 434, 516, 281, 1499, 257, 15075, 8141, 1219, 383, 8141, 11, 376, 45, 33, 40964, 12, 2777, 37, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.18948863568631086, "compression_ratio": 1.7323232323232323, "no_speech_prob": 0.003429412841796875, "words": [ { "start": 3318.88, "end": 3319.1, "word": " We're", "probability": 0.81103515625 }, { "start": 3319.1, "end": 3319.14, "word": " going", "probability": 0.67236328125 }, { "start": 3319.14, "end": 3319.62, "word": " to", "probability": 0.900390625 }, { "start": 3319.62, "end": 3319.9, "word": " develop", "probability": 0.6796875 }, { "start": 3320.04, "end": 3320.32, "word": " a confusion", "probability": 0.7529296875 }, { "start": 3320.32, "end": 3320.58, "word": " matrix", "probability": 0.8701171875 }, { "start": 3320.58, "end": 3320.86, "word": " called", "probability": 0.794921875 }, { "start": 3320.86, "end": 3321.1, "word": " C", "probability": 0.403076171875 }, { "start": 3321.1, "end": 3321.56, "word": " matrix", "probability": 0.41259765625 }, { "start": 3321.56, "end": 3321.76, "word": ",", "probability": 0.6259765625 }, { "start": 3321.76, "end": 3322.1, "word": " MNB", "probability": 0.733642578125 }, { "start": 3322.1, "end": 3322.54, "word": " TF", "probability": 0.08856201171875 }, { "start": 3322.54, "end": 3322.96, "word": "-IDF", "probability": 0.7784830729166666 }, { "start": 3322.96, "end": 3323.1, "word": ",", "probability": 0.61572265625 } ] }, { "id": 888, "seek": 324926, "start": 3323.1, "end": 3327.44, "text": " and then classification report, C report, MNB TF-IDF.", "tokens": [ 50564, 293, 550, 21538, 2275, 11, 383, 2275, 11, 376, 45, 33, 40964, 12, 2777, 37, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.18948863568631086, "compression_ratio": 1.7323232323232323, "no_speech_prob": 0.003429412841796875, "words": [ { "start": 3323.1, "end": 3323.2, "word": " and", "probability": 0.8701171875 }, { "start": 3323.2, "end": 3323.38, "word": " then", "probability": 0.73876953125 }, { "start": 3323.38, "end": 3323.76, "word": " classification", "probability": 0.78125 }, { "start": 3323.76, "end": 3324.32, "word": " report", "probability": 0.783203125 }, { "start": 3324.32, "end": 3324.52, "word": ",", "probability": 0.73291015625 }, { "start": 3324.52, "end": 3324.66, "word": " C", "probability": 0.97119140625 }, { "start": 3324.66, "end": 3325.06, "word": " report", "probability": 0.8271484375 }, { "start": 3325.06, "end": 3325.34, "word": ",", "probability": 0.9560546875 }, { "start": 3325.34, "end": 3325.66, "word": " MNB", "probability": 0.91259765625 }, { "start": 3325.66, "end": 3326.36, "word": " TF", "probability": 0.638671875 }, { "start": 3326.36, "end": 3326.92, "word": "-IDF", "probability": 0.9777018229166666 }, { "start": 3326.92, "end": 3327.44, "word": ".", "probability": 0.9794921875 } ] }, { "id": 889, "seek": 324926, "start": 3328.54, "end": 3330.28, "text": " So we're going to start with our score.", "tokens": [ 50864, 407, 321, 434, 516, 281, 722, 365, 527, 6175, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.18948863568631086, "compression_ratio": 1.7323232323232323, "no_speech_prob": 0.003429412841796875, "words": [ { "start": 3328.54, "end": 3329.06, "word": " So", "probability": 0.572265625 }, { "start": 3329.06, "end": 3329.2, "word": " we're", "probability": 0.8583984375 }, { "start": 3329.2, "end": 3329.22, "word": " going", "probability": 0.78076171875 }, { "start": 3329.22, "end": 3329.22, "word": " to", "probability": 0.8984375 }, { "start": 3329.22, "end": 3329.36, "word": " start", "probability": 0.8671875 }, { "start": 3329.36, "end": 3329.48, "word": " with", "probability": 0.8076171875 }, { "start": 3329.48, "end": 3329.58, "word": " our", "probability": 0.79345703125 }, { "start": 3329.58, "end": 3329.9, "word": " score", "probability": 0.7939453125 }, { "start": 3329.9, "end": 3330.28, "word": ".", "probability": 0.57177734375 } ] }, { "id": 890, "seek": 324926, "start": 3330.28, "end": 3337.38, "text": " Score MNB TF-IDF equals MNB TF-IDF dot score.", "tokens": [ 50914, 47901, 376, 45, 33, 40964, 12, 2777, 37, 6915, 376, 45, 33, 40964, 12, 2777, 37, 5893, 6175, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.18948863568631086, "compression_ratio": 1.7323232323232323, "no_speech_prob": 0.003429412841796875, "words": [ { "start": 3330.28, "end": 3330.58, "word": " Score", "probability": 0.62060546875 }, { "start": 3330.58, "end": 3331.26, "word": " MNB", "probability": 0.80810546875 }, { "start": 3331.26, "end": 3332.02, "word": " TF", "probability": 0.7646484375 }, { "start": 3332.02, "end": 3332.6, "word": "-IDF", "probability": 0.9684244791666666 }, { "start": 3332.6, "end": 3333.2, "word": " equals", "probability": 0.77197265625 }, { "start": 3333.2, "end": 3334.38, "word": " MNB", "probability": 0.8719075520833334 }, { "start": 3334.38, "end": 3335.1, "word": " TF", "probability": 0.6787109375 }, { "start": 3335.1, "end": 3335.78, "word": "-IDF", "probability": 0.9415690104166666 }, { "start": 3335.78, "end": 3336.2, "word": " dot", "probability": 0.60205078125 }, { "start": 3336.2, "end": 3336.86, "word": " score", "probability": 0.810546875 }, { "start": 3336.86, "end": 3337.38, "word": ".", "probability": 0.7666015625 } ] }, { "id": 891, "seek": 324926, "start": 3337.98, "end": 3341.66, "text": " And then we're going to use our test values, because we've trained it on our training data,", "tokens": [ 51314, 400, 550, 321, 434, 516, 281, 764, 527, 1500, 4190, 11, 570, 321, 600, 8895, 309, 322, 527, 3097, 1412, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.18948863568631086, "compression_ratio": 1.7323232323232323, "no_speech_prob": 0.003429412841796875, "words": [ { "start": 3337.98, "end": 3338.26, "word": " And", "probability": 0.71923828125 }, { "start": 3338.26, "end": 3338.32, "word": " then", "probability": 0.72265625 }, { "start": 3338.32, "end": 3338.46, "word": " we're", "probability": 0.92578125 }, { "start": 3338.46, "end": 3338.52, "word": " going", "probability": 0.84521484375 }, { "start": 3338.52, "end": 3338.56, "word": " to", "probability": 0.90625 }, { "start": 3338.56, "end": 3338.74, "word": " use", "probability": 0.822265625 }, { "start": 3338.74, "end": 3338.94, "word": " our", "probability": 0.81689453125 }, { "start": 3338.94, "end": 3339.54, "word": " test", "probability": 0.79833984375 }, { "start": 3339.54, "end": 3340.0, "word": " values", "probability": 0.9111328125 }, { "start": 3340.0, "end": 3340.08, "word": ",", "probability": 0.288818359375 }, { "start": 3340.08, "end": 3340.32, "word": " because", "probability": 0.83642578125 }, { "start": 3340.32, "end": 3340.6, "word": " we've", "probability": 0.918212890625 }, { "start": 3340.6, "end": 3340.86, "word": " trained", "probability": 0.798828125 }, { "start": 3340.86, "end": 3340.98, "word": " it", "probability": 0.8955078125 }, { "start": 3340.98, "end": 3341.08, "word": " on", "probability": 0.912109375 }, { "start": 3341.08, "end": 3341.2, "word": " our", "probability": 0.802734375 }, { "start": 3341.2, "end": 3341.4, "word": " training", "probability": 0.8134765625 }, { "start": 3341.4, "end": 3341.64, "word": " data", "probability": 0.83544921875 }, { "start": 3341.64, "end": 3341.66, "word": ",", "probability": 0.468017578125 } ] }, { "id": 892, "seek": 324926, "start": 3341.66, "end": 3343.28, "text": " and we want to test it with our testing.", "tokens": [ 51464, 293, 321, 528, 281, 1500, 309, 365, 527, 4997, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.18948863568631086, "compression_ratio": 1.7323232323232323, "no_speech_prob": 0.003429412841796875, "words": [ { "start": 3341.66, "end": 3341.74, "word": " and", "probability": 0.1920166015625 }, { "start": 3341.74, "end": 3341.76, "word": " we", "probability": 0.90234375 }, { "start": 3341.76, "end": 3341.92, "word": " want", "probability": 0.81005859375 }, { "start": 3341.92, "end": 3342.04, "word": " to", "probability": 0.90869140625 }, { "start": 3342.04, "end": 3342.28, "word": " test", "probability": 0.80615234375 }, { "start": 3342.28, "end": 3342.36, "word": " it", "probability": 0.8974609375 }, { "start": 3342.36, "end": 3342.46, "word": " with", "probability": 0.8076171875 }, { "start": 3342.46, "end": 3342.56, "word": " our", "probability": 0.79833984375 }, { "start": 3342.56, "end": 3342.82, "word": " testing", "probability": 0.7333984375 }, { "start": 3342.82, "end": 3343.28, "word": ".", "probability": 0.90771484375 } ] }, { "id": 893, "seek": 327118, "start": 3343.28, "end": 3347.42, "text": " So we're going to do test TF-IDF X,", "tokens": [ 50364, 407, 321, 434, 516, 281, 360, 1500, 40964, 12, 2777, 37, 1783, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.1976102913127226, "compression_ratio": 1.6303030303030304, "no_speech_prob": 0.037322998046875, "words": [ { "start": 3343.28, "end": 3343.58, "word": " So", "probability": 0.560546875 }, { "start": 3343.58, "end": 3343.72, "word": " we're", "probability": 0.8994140625 }, { "start": 3343.72, "end": 3343.8, "word": " going", "probability": 0.716796875 }, { "start": 3343.8, "end": 3343.86, "word": " to", "probability": 0.90625 }, { "start": 3343.86, "end": 3344.02, "word": " do", "probability": 0.6552734375 }, { "start": 3344.02, "end": 3344.58, "word": " test", "probability": 0.5771484375 }, { "start": 3344.58, "end": 3346.02, "word": " TF", "probability": 0.053436279296875 }, { "start": 3346.02, "end": 3346.64, "word": "-IDF", "probability": 0.6837972005208334 }, { "start": 3346.64, "end": 3347.26, "word": " X", "probability": 0.2978515625 }, { "start": 3347.26, "end": 3347.42, "word": ",", "probability": 0.27197265625 } ] }, { "id": 894, "seek": 327118, "start": 3347.42, "end": 3354.06, "text": " because that's the way that our system was vectorizing these.", "tokens": [ 50564, 570, 300, 311, 264, 636, 300, 527, 1185, 390, 8062, 3319, 613, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.1976102913127226, "compression_ratio": 1.6303030303030304, "no_speech_prob": 0.037322998046875, "words": [ { "start": 3347.42, "end": 3347.58, "word": " because", "probability": 0.83837890625 }, { "start": 3347.58, "end": 3347.96, "word": " that's", "probability": 0.939208984375 }, { "start": 3347.96, "end": 3348.1, "word": " the", "probability": 0.81494140625 }, { "start": 3348.1, "end": 3348.34, "word": " way", "probability": 0.892578125 }, { "start": 3348.34, "end": 3348.84, "word": " that", "probability": 0.8564453125 }, { "start": 3348.84, "end": 3349.68, "word": " our", "probability": 0.81494140625 }, { "start": 3349.68, "end": 3351.6, "word": " system", "probability": 0.830078125 }, { "start": 3351.6, "end": 3352.76, "word": " was", "probability": 0.75439453125 }, { "start": 3352.76, "end": 3353.38, "word": " vectorizing", "probability": 0.8955078125 }, { "start": 3353.38, "end": 3353.66, "word": " these", "probability": 0.69970703125 }, { "start": 3353.66, "end": 3354.06, "word": ".", "probability": 0.69677734375 } ] }, { "id": 895, "seek": 327118, "start": 3354.5, "end": 3357.52, "text": " So we don't want to use count vectorizer with a TF-IDF train,", "tokens": [ 50914, 407, 321, 500, 380, 528, 281, 764, 1207, 8062, 6545, 365, 257, 40964, 12, 2777, 37, 3847, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.1976102913127226, "compression_ratio": 1.6303030303030304, "no_speech_prob": 0.037322998046875, "words": [ { "start": 3354.5, "end": 3354.84, "word": " So", "probability": 0.78369140625 }, { "start": 3354.84, "end": 3354.94, "word": " we", "probability": 0.8955078125 }, { "start": 3354.94, "end": 3355.06, "word": " don't", "probability": 0.9482421875 }, { "start": 3355.06, "end": 3355.2, "word": " want", "probability": 0.59521484375 }, { "start": 3355.2, "end": 3355.26, "word": " to", "probability": 0.88525390625 }, { "start": 3355.26, "end": 3355.44, "word": " use", "probability": 0.83251953125 }, { "start": 3355.44, "end": 3355.74, "word": " count", "probability": 0.638671875 }, { "start": 3355.74, "end": 3356.28, "word": " vectorizer", "probability": 0.798583984375 }, { "start": 3356.28, "end": 3356.42, "word": " with", "probability": 0.80224609375 }, { "start": 3356.54, "end": 3356.76, "word": " a TF", "probability": 0.791015625 }, { "start": 3356.76, "end": 3357.08, "word": "-IDF", "probability": 0.9720052083333334 }, { "start": 3357.08, "end": 3357.4, "word": " train", "probability": 0.6201171875 }, { "start": 3357.4, "end": 3357.52, "word": ",", "probability": 0.55908203125 } ] }, { "id": 896, "seek": 327118, "start": 3357.52, "end": 3358.84, "text": " because that's not going to work.", "tokens": [ 51064, 570, 300, 311, 406, 516, 281, 589, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.1976102913127226, "compression_ratio": 1.6303030303030304, "no_speech_prob": 0.037322998046875, "words": [ { "start": 3357.52, "end": 3357.68, "word": " because", "probability": 0.84130859375 }, { "start": 3357.68, "end": 3357.92, "word": " that's", "probability": 0.94189453125 }, { "start": 3357.92, "end": 3358.04, "word": " not", "probability": 0.89404296875 }, { "start": 3358.04, "end": 3358.14, "word": " going", "probability": 0.82080078125 }, { "start": 3358.14, "end": 3358.22, "word": " to", "probability": 0.9013671875 }, { "start": 3358.22, "end": 3358.44, "word": " work", "probability": 0.81494140625 }, { "start": 3358.44, "end": 3358.84, "word": ".", "probability": 0.85986328125 } ] }, { "id": 897, "seek": 327118, "start": 3359.14, "end": 3361.54, "text": " And then we're going to use test labels.", "tokens": [ 51164, 400, 550, 321, 434, 516, 281, 764, 1500, 16949, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.1976102913127226, "compression_ratio": 1.6303030303030304, "no_speech_prob": 0.037322998046875, "words": [ { "start": 3359.14, "end": 3359.44, "word": " And", "probability": 0.76416015625 }, { "start": 3359.44, "end": 3359.52, "word": " then", "probability": 0.2208251953125 }, { "start": 3359.52, "end": 3359.6, "word": " we're", "probability": 0.9267578125 }, { "start": 3359.6, "end": 3359.66, "word": " going", "probability": 0.822265625 }, { "start": 3359.66, "end": 3359.66, "word": " to", "probability": 0.908203125 }, { "start": 3359.66, "end": 3359.84, "word": " use", "probability": 0.80126953125 }, { "start": 3359.84, "end": 3360.3, "word": " test", "probability": 0.763671875 }, { "start": 3360.3, "end": 3361.14, "word": " labels", "probability": 0.7666015625 }, { "start": 3361.14, "end": 3361.54, "word": ".", "probability": 0.6728515625 } ] }, { "id": 898, "seek": 327118, "start": 3363.98, "end": 3365.2, "text": " That's going to give us our score.", "tokens": [ 51414, 663, 311, 516, 281, 976, 505, 527, 6175, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.1976102913127226, "compression_ratio": 1.6303030303030304, "no_speech_prob": 0.037322998046875, "words": [ { "start": 3363.98, "end": 3364.38, "word": " That's", "probability": 0.760498046875 }, { "start": 3364.38, "end": 3364.44, "word": " going", "probability": 0.85546875 }, { "start": 3364.44, "end": 3364.48, "word": " to", "probability": 0.9013671875 }, { "start": 3364.48, "end": 3364.58, "word": " give", "probability": 0.8134765625 }, { "start": 3364.58, "end": 3364.68, "word": " us", "probability": 0.90966796875 }, { "start": 3364.68, "end": 3364.82, "word": " our", "probability": 0.8076171875 }, { "start": 3364.82, "end": 3365.1, "word": " score", "probability": 0.80126953125 }, { "start": 3365.1, "end": 3365.2, "word": ".", "probability": 0.650390625 } ] }, { "id": 899, "seek": 329570, "start": 3365.2, "end": 3366.86, "text": " So we're going to get our predictions.", "tokens": [ 50364, 407, 321, 434, 516, 281, 483, 527, 21264, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.16670049088341848, "compression_ratio": 1.6405228758169934, "no_speech_prob": 0.1644287109375, "words": [ { "start": 3365.2, "end": 3365.2, "word": " So", "probability": 0.2110595703125 }, { "start": 3365.2, "end": 3365.32, "word": " we're", "probability": 0.846923828125 }, { "start": 3365.32, "end": 3365.38, "word": " going", "probability": 0.28369140625 }, { "start": 3365.38, "end": 3365.4, "word": " to", "probability": 0.90478515625 }, { "start": 3365.4, "end": 3365.52, "word": " get", "probability": 0.86962890625 }, { "start": 3365.52, "end": 3365.64, "word": " our", "probability": 0.8037109375 }, { "start": 3365.64, "end": 3366.22, "word": " predictions", "probability": 0.7548828125 }, { "start": 3366.22, "end": 3366.86, "word": ".", "probability": 0.405517578125 } ] }, { "id": 900, "seek": 329570, "start": 3367.18, "end": 3374.76, "text": " Predictions MNB TF-IDF equals MNB TF-IDF dot predict.", "tokens": [ 50464, 32969, 15607, 376, 45, 33, 40964, 12, 2777, 37, 6915, 376, 45, 33, 40964, 12, 2777, 37, 5893, 6069, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.16670049088341848, "compression_ratio": 1.6405228758169934, "no_speech_prob": 0.1644287109375, "words": [ { "start": 3367.18, "end": 3367.82, "word": " Predictions", "probability": 0.6483154296875 }, { "start": 3367.82, "end": 3368.58, "word": " MNB", "probability": 0.46307373046875 }, { "start": 3368.58, "end": 3369.68, "word": " TF", "probability": 0.237548828125 }, { "start": 3369.68, "end": 3370.42, "word": "-IDF", "probability": 0.659820556640625 }, { "start": 3370.42, "end": 3370.96, "word": " equals", "probability": 0.7646484375 }, { "start": 3370.96, "end": 3371.54, "word": " MNB", "probability": 0.8673502604166666 }, { "start": 3371.54, "end": 3372.2, "word": " TF", "probability": 0.6123046875 }, { "start": 3372.2, "end": 3372.84, "word": "-IDF", "probability": 0.9532877604166666 }, { "start": 3372.84, "end": 3373.2, "word": " dot", "probability": 0.77099609375 }, { "start": 3373.2, "end": 3374.12, "word": " predict", "probability": 0.82275390625 }, { "start": 3374.12, "end": 3374.76, "word": ".", "probability": 0.72509765625 } ] }, { "id": 901, "seek": 329570, "start": 3374.9, "end": 3378.6, "text": " And this is going to give us our raw predictions.", "tokens": [ 50864, 400, 341, 307, 516, 281, 976, 505, 527, 8936, 21264, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.16670049088341848, "compression_ratio": 1.6405228758169934, "no_speech_prob": 0.1644287109375, "words": [ { "start": 3374.9, "end": 3375.12, "word": " And", "probability": 0.65283203125 }, { "start": 3375.12, "end": 3375.26, "word": " this", "probability": 0.876953125 }, { "start": 3375.26, "end": 3375.36, "word": " is", "probability": 0.9013671875 }, { "start": 3375.36, "end": 3375.44, "word": " going", "probability": 0.7939453125 }, { "start": 3375.44, "end": 3375.5, "word": " to", "probability": 0.9033203125 }, { "start": 3375.5, "end": 3375.64, "word": " give", "probability": 0.828125 }, { "start": 3375.64, "end": 3375.82, "word": " us", "probability": 0.90234375 }, { "start": 3375.82, "end": 3376.28, "word": " our", "probability": 0.8115234375 }, { "start": 3376.28, "end": 3377.34, "word": " raw", "probability": 0.82568359375 }, { "start": 3377.34, "end": 3377.96, "word": " predictions", "probability": 0.75634765625 }, { "start": 3377.96, "end": 3378.6, "word": ".", "probability": 0.95361328125 } ] }, { "id": 902, "seek": 329570, "start": 3381.36, "end": 3386.08, "text": " This is going to tell us what it thinks each email is,", "tokens": [ 51214, 639, 307, 516, 281, 980, 505, 437, 309, 7309, 1184, 3796, 307, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.16670049088341848, "compression_ratio": 1.6405228758169934, "no_speech_prob": 0.1644287109375, "words": [ { "start": 3381.36, "end": 3382.0, "word": " This", "probability": 0.37255859375 }, { "start": 3382.0, "end": 3382.64, "word": " is", "probability": 0.90673828125 }, { "start": 3382.64, "end": 3382.82, "word": " going", "probability": 0.861328125 }, { "start": 3382.82, "end": 3383.24, "word": " to", "probability": 0.9052734375 }, { "start": 3383.24, "end": 3383.78, "word": " tell", "probability": 0.82958984375 }, { "start": 3383.78, "end": 3383.96, "word": " us", "probability": 0.89990234375 }, { "start": 3383.96, "end": 3384.1, "word": " what", "probability": 0.88818359375 }, { "start": 3384.1, "end": 3384.24, "word": " it", "probability": 0.89013671875 }, { "start": 3384.24, "end": 3384.46, "word": " thinks", "probability": 0.7470703125 }, { "start": 3384.46, "end": 3384.74, "word": " each", "probability": 0.85791015625 }, { "start": 3384.74, "end": 3385.04, "word": " email", "probability": 0.88427734375 }, { "start": 3385.04, "end": 3385.56, "word": " is", "probability": 0.90380859375 }, { "start": 3385.56, "end": 3386.08, "word": ",", "probability": 0.58935546875 } ] }, { "id": 903, "seek": 329570, "start": 3386.08, "end": 3389.72, "text": " whereas our score is going to see how accurate it is.", "tokens": [ 51414, 9735, 527, 6175, 307, 516, 281, 536, 577, 8559, 309, 307, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.16670049088341848, "compression_ratio": 1.6405228758169934, "no_speech_prob": 0.1644287109375, "words": [ { "start": 3386.08, "end": 3386.56, "word": " whereas", "probability": 0.85009765625 }, { "start": 3386.56, "end": 3386.74, "word": " our", "probability": 0.76513671875 }, { "start": 3386.74, "end": 3387.0, "word": " score", "probability": 0.7880859375 }, { "start": 3387.0, "end": 3387.16, "word": " is", "probability": 0.888671875 }, { "start": 3387.16, "end": 3387.3, "word": " going", "probability": 0.85693359375 }, { "start": 3387.3, "end": 3387.46, "word": " to", "probability": 0.904296875 }, { "start": 3387.46, "end": 3387.72, "word": " see", "probability": 0.80419921875 }, { "start": 3387.72, "end": 3388.1, "word": " how", "probability": 0.8984375 }, { "start": 3388.1, "end": 3388.56, "word": " accurate", "probability": 0.7099609375 }, { "start": 3388.56, "end": 3388.8, "word": " it", "probability": 0.9052734375 }, { "start": 3388.8, "end": 3389.08, "word": " is", "probability": 0.90673828125 }, { "start": 3389.08, "end": 3389.72, "word": ".", "probability": 0.99365234375 } ] }, { "id": 904, "seek": 332438, "start": 3389.72, "end": 3393.88, "text": " And then this is going to be C matrix.", "tokens": [ 50414, 400, 550, 341, 307, 516, 281, 312, 383, 8141, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.19471154190026796, "compression_ratio": 1.4709677419354839, "no_speech_prob": 0.039642333984375, "words": [ { "start": 3389.72, "end": 3390.08, "word": " And", "probability": 0.1939697265625 }, { "start": 3390.08, "end": 3391.58, "word": " then", "probability": 0.68408203125 }, { "start": 3391.58, "end": 3391.8, "word": " this", "probability": 0.8271484375 }, { "start": 3391.8, "end": 3391.94, "word": " is", "probability": 0.90234375 }, { "start": 3391.94, "end": 3392.08, "word": " going", "probability": 0.86669921875 }, { "start": 3392.08, "end": 3392.22, "word": " to", "probability": 0.90576171875 }, { "start": 3392.22, "end": 3392.46, "word": " be", "probability": 0.90771484375 }, { "start": 3392.46, "end": 3392.7, "word": " C", "probability": 0.27587890625 }, { "start": 3392.7, "end": 3393.18, "word": " matrix", "probability": 0.381103515625 }, { "start": 3393.18, "end": 3393.88, "word": ".", "probability": 0.305908203125 } ] }, { "id": 905, "seek": 332438, "start": 3394.88, "end": 3402.68, "text": " MNB TF-IDF equals confusion matrix.", "tokens": [ 50614, 376, 45, 33, 40964, 12, 2777, 37, 6915, 15075, 8141, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.19471154190026796, "compression_ratio": 1.4709677419354839, "no_speech_prob": 0.039642333984375, "words": [ { "start": 3394.88, "end": 3395.58, "word": " MNB", "probability": 0.611328125 }, { "start": 3395.58, "end": 3396.12, "word": " TF", "probability": 0.17236328125 }, { "start": 3396.12, "end": 3397.14, "word": "-IDF", "probability": 0.6452433268229166 }, { "start": 3397.14, "end": 3398.66, "word": " equals", "probability": 0.775390625 }, { "start": 3398.66, "end": 3400.7, "word": " confusion", "probability": 0.69482421875 }, { "start": 3400.7, "end": 3401.98, "word": " matrix", "probability": 0.794921875 }, { "start": 3401.98, "end": 3402.68, "word": ".", "probability": 0.71044921875 } ] }, { "id": 906, "seek": 332438, "start": 3402.98, "end": 3408.62, "text": " We're going to use our test labels and our predictions.", "tokens": [ 51014, 492, 434, 516, 281, 764, 527, 1500, 16949, 293, 527, 21264, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.19471154190026796, "compression_ratio": 1.4709677419354839, "no_speech_prob": 0.039642333984375, "words": [ { "start": 3402.98, "end": 3403.32, "word": " We're", "probability": 0.29412841796875 }, { "start": 3403.32, "end": 3403.32, "word": " going", "probability": 0.57177734375 }, { "start": 3403.32, "end": 3403.32, "word": " to", "probability": 0.90869140625 }, { "start": 3403.32, "end": 3403.42, "word": " use", "probability": 0.80419921875 }, { "start": 3403.42, "end": 3403.56, "word": " our", "probability": 0.80615234375 }, { "start": 3403.56, "end": 3403.92, "word": " test", "probability": 0.8076171875 }, { "start": 3403.92, "end": 3404.78, "word": " labels", "probability": 0.86572265625 }, { "start": 3404.78, "end": 3405.84, "word": " and", "probability": 0.708984375 }, { "start": 3405.84, "end": 3406.32, "word": " our", "probability": 0.81005859375 }, { "start": 3406.32, "end": 3407.92, "word": " predictions", "probability": 0.71728515625 }, { "start": 3407.92, "end": 3408.62, "word": ".", "probability": 0.67431640625 } ] }, { "id": 907, "seek": 332438, "start": 3408.78, "end": 3411.28, "text": " MNB TF-IDF.", "tokens": [ 51314, 376, 45, 33, 40964, 12, 2777, 37, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.19471154190026796, "compression_ratio": 1.4709677419354839, "no_speech_prob": 0.039642333984375, "words": [ { "start": 3408.78, "end": 3409.48, "word": " MNB", "probability": 0.8546549479166666 }, { "start": 3409.48, "end": 3410.1, "word": " TF", "probability": 0.7734375 }, { "start": 3410.1, "end": 3410.84, "word": "-IDF", "probability": 0.97021484375 }, { "start": 3410.84, "end": 3411.28, "word": ".", "probability": 0.90869140625 } ] }, { "id": 908, "seek": 332438, "start": 3411.28, "end": 3416.8, "text": " So this is going to tell us what it thinks the value is,", "tokens": [ 51414, 407, 341, 307, 516, 281, 980, 505, 437, 309, 7309, 264, 2158, 307, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.19471154190026796, "compression_ratio": 1.4709677419354839, "no_speech_prob": 0.039642333984375, "words": [ { "start": 3411.28, "end": 3411.48, "word": " So", "probability": 0.84130859375 }, { "start": 3411.48, "end": 3411.64, "word": " this", "probability": 0.80908203125 }, { "start": 3411.64, "end": 3411.76, "word": " is", "probability": 0.90234375 }, { "start": 3411.76, "end": 3411.9, "word": " going", "probability": 0.86279296875 }, { "start": 3411.9, "end": 3412.04, "word": " to", "probability": 0.9033203125 }, { "start": 3412.04, "end": 3412.26, "word": " tell", "probability": 0.826171875 }, { "start": 3412.26, "end": 3412.72, "word": " us", "probability": 0.90625 }, { "start": 3412.72, "end": 3414.52, "word": " what", "probability": 0.8671875 }, { "start": 3414.52, "end": 3414.68, "word": " it", "probability": 0.90771484375 }, { "start": 3414.68, "end": 3415.28, "word": " thinks", "probability": 0.76611328125 }, { "start": 3415.28, "end": 3416.2, "word": " the", "probability": 0.81591796875 }, { "start": 3416.2, "end": 3416.5, "word": " value", "probability": 0.91455078125 }, { "start": 3416.5, "end": 3416.76, "word": " is", "probability": 0.9052734375 }, { "start": 3416.76, "end": 3416.8, "word": ",", "probability": 0.5732421875 } ] }, { "id": 909, "seek": 332438, "start": 3416.8, "end": 3418.4, "text": " if it's a spam or ham email,", "tokens": [ 51714, 498, 309, 311, 257, 24028, 420, 7852, 3796, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.19471154190026796, "compression_ratio": 1.4709677419354839, "no_speech_prob": 0.039642333984375, "words": [ { "start": 3416.8, "end": 3416.9, "word": " if", "probability": 0.90576171875 }, { "start": 3416.9, "end": 3417.02, "word": " it's", "probability": 0.947509765625 }, { "start": 3417.14, "end": 3417.36, "word": " a spam", "probability": 0.95947265625 }, { "start": 3417.36, "end": 3417.54, "word": " or", "probability": 0.88232421875 }, { "start": 3417.54, "end": 3417.78, "word": " ham", "probability": 0.68017578125 }, { "start": 3417.78, "end": 3418.0, "word": " email", "probability": 0.86328125 }, { "start": 3418.0, "end": 3418.4, "word": ",", "probability": 0.59765625 } ] }, { "id": 910, "seek": 334982, "start": 3418.4, "end": 3421.3, "text": " and then what it actually is.", "tokens": [ 50364, 293, 550, 437, 309, 767, 307, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.1804199245525524, "compression_ratio": 1.8115384615384615, "no_speech_prob": 0.0017547607421875, "words": [ { "start": 3418.4, "end": 3418.76, "word": " and", "probability": 0.615234375 }, { "start": 3418.76, "end": 3419.04, "word": " then", "probability": 0.7099609375 }, { "start": 3419.04, "end": 3419.58, "word": " what", "probability": 0.85205078125 }, { "start": 3419.58, "end": 3419.78, "word": " it", "probability": 0.90087890625 }, { "start": 3419.78, "end": 3420.32, "word": " actually", "probability": 0.78076171875 }, { "start": 3420.32, "end": 3420.9, "word": " is", "probability": 0.9033203125 }, { "start": 3420.9, "end": 3421.3, "word": ".", "probability": 0.86572265625 } ] }, { "id": 911, "seek": 334982, "start": 3421.5, "end": 3423.94, "text": " So it's going to give us our true positives, our false positives,", "tokens": [ 50464, 407, 309, 311, 516, 281, 976, 505, 527, 2074, 35127, 11, 527, 7908, 35127, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.1804199245525524, "compression_ratio": 1.8115384615384615, "no_speech_prob": 0.0017547607421875, "words": [ { "start": 3421.5, "end": 3421.6, "word": " So", "probability": 0.72802734375 }, { "start": 3421.6, "end": 3421.7, "word": " it's", "probability": 0.880859375 }, { "start": 3421.7, "end": 3421.78, "word": " going", "probability": 0.51025390625 }, { "start": 3421.78, "end": 3421.82, "word": " to", "probability": 0.90478515625 }, { "start": 3421.82, "end": 3421.94, "word": " give", "probability": 0.81787109375 }, { "start": 3421.94, "end": 3422.06, "word": " us", "probability": 0.8916015625 }, { "start": 3422.06, "end": 3422.16, "word": " our", "probability": 0.787109375 }, { "start": 3422.16, "end": 3422.4, "word": " true", "probability": 0.916015625 }, { "start": 3422.4, "end": 3422.82, "word": " positives", "probability": 0.82861328125 }, { "start": 3422.82, "end": 3423.1, "word": ",", "probability": 0.90966796875 }, { "start": 3423.1, "end": 3423.2, "word": " our", "probability": 0.796875 }, { "start": 3423.2, "end": 3423.4, "word": " false", "probability": 0.85546875 }, { "start": 3423.4, "end": 3423.8, "word": " positives", "probability": 0.849609375 }, { "start": 3423.8, "end": 3423.94, "word": ",", "probability": 0.9482421875 } ] }, { "id": 912, "seek": 334982, "start": 3423.94, "end": 3425.74, "text": " our true negatives, and our false negatives.", "tokens": [ 50614, 527, 2074, 40019, 11, 293, 527, 7908, 40019, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.1804199245525524, "compression_ratio": 1.8115384615384615, "no_speech_prob": 0.0017547607421875, "words": [ { "start": 3423.94, "end": 3424.02, "word": " our", "probability": 0.7783203125 }, { "start": 3424.02, "end": 3424.18, "word": " true", "probability": 0.91650390625 }, { "start": 3424.18, "end": 3424.5, "word": " negatives", "probability": 0.8046875 }, { "start": 3424.5, "end": 3424.58, "word": ",", "probability": 0.673828125 }, { "start": 3424.58, "end": 3424.66, "word": " and", "probability": 0.88720703125 }, { "start": 3424.66, "end": 3424.76, "word": " our", "probability": 0.80029296875 }, { "start": 3424.76, "end": 3424.96, "word": " false", "probability": 0.8515625 }, { "start": 3424.96, "end": 3425.34, "word": " negatives", "probability": 0.77734375 }, { "start": 3425.34, "end": 3425.74, "word": ".", "probability": 0.92431640625 } ] }, { "id": 913, "seek": 334982, "start": 3426.08, "end": 3427.7, "text": " And then the C report.", "tokens": [ 50714, 400, 550, 264, 383, 2275, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.1804199245525524, "compression_ratio": 1.8115384615384615, "no_speech_prob": 0.0017547607421875, "words": [ { "start": 3426.08, "end": 3426.16, "word": " And", "probability": 0.77783203125 }, { "start": 3426.16, "end": 3426.32, "word": " then", "probability": 0.720703125 }, { "start": 3426.32, "end": 3426.68, "word": " the", "probability": 0.78955078125 }, { "start": 3426.68, "end": 3427.0, "word": " C", "probability": 0.85302734375 }, { "start": 3427.0, "end": 3427.36, "word": " report", "probability": 0.62353515625 }, { "start": 3427.36, "end": 3427.7, "word": ".", "probability": 0.26416015625 } ] }, { "id": 914, "seek": 334982, "start": 3427.7, "end": 3430.04, "text": " We're not going to do too much with this,", "tokens": [ 50814, 492, 434, 406, 516, 281, 360, 886, 709, 365, 341, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.1804199245525524, "compression_ratio": 1.8115384615384615, "no_speech_prob": 0.0017547607421875, "words": [ { "start": 3427.7, "end": 3427.96, "word": " We're", "probability": 0.921875 }, { "start": 3427.96, "end": 3428.06, "word": " not", "probability": 0.8955078125 }, { "start": 3428.06, "end": 3428.14, "word": " going", "probability": 0.83251953125 }, { "start": 3428.14, "end": 3428.2, "word": " to", "probability": 0.90576171875 }, { "start": 3428.2, "end": 3428.34, "word": " do", "probability": 0.90673828125 }, { "start": 3428.34, "end": 3428.76, "word": " too", "probability": 0.791015625 }, { "start": 3428.76, "end": 3428.98, "word": " much", "probability": 0.81201171875 }, { "start": 3428.98, "end": 3429.18, "word": " with", "probability": 0.81689453125 }, { "start": 3429.18, "end": 3429.6, "word": " this", "probability": 0.88232421875 }, { "start": 3429.6, "end": 3430.04, "word": ",", "probability": 0.619140625 } ] }, { "id": 915, "seek": 334982, "start": 3430.04, "end": 3434.16, "text": " but what a classification report will do is show us some more metrics,", "tokens": [ 50914, 457, 437, 257, 21538, 2275, 486, 360, 307, 855, 505, 512, 544, 16367, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.1804199245525524, "compression_ratio": 1.8115384615384615, "no_speech_prob": 0.0017547607421875, "words": [ { "start": 3430.04, "end": 3430.4, "word": " but", "probability": 0.8896484375 }, { "start": 3430.4, "end": 3430.78, "word": " what", "probability": 0.85693359375 }, { "start": 3431.12, "end": 3431.4, "word": " a classification", "probability": 0.9228515625 }, { "start": 3431.4, "end": 3431.92, "word": " report", "probability": 0.86328125 }, { "start": 3431.92, "end": 3432.12, "word": " will", "probability": 0.8193359375 }, { "start": 3432.12, "end": 3432.4, "word": " do", "probability": 0.89794921875 }, { "start": 3432.4, "end": 3432.74, "word": " is", "probability": 0.888671875 }, { "start": 3432.74, "end": 3432.92, "word": " show", "probability": 0.87158203125 }, { "start": 3432.92, "end": 3433.06, "word": " us", "probability": 0.8486328125 }, { "start": 3433.06, "end": 3433.18, "word": " some", "probability": 0.791015625 }, { "start": 3433.18, "end": 3433.5, "word": " more", "probability": 0.87841796875 }, { "start": 3433.5, "end": 3434.04, "word": " metrics", "probability": 0.767578125 }, { "start": 3434.04, "end": 3434.16, "word": ",", "probability": 0.339111328125 } ] }, { "id": 916, "seek": 334982, "start": 3434.16, "end": 3436.62, "text": " such as the recall and the precision,", "tokens": [ 51114, 1270, 382, 264, 9901, 293, 264, 18356, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.1804199245525524, "compression_ratio": 1.8115384615384615, "no_speech_prob": 0.0017547607421875, "words": [ { "start": 3434.16, "end": 3434.46, "word": " such", "probability": 0.87353515625 }, { "start": 3434.46, "end": 3434.64, "word": " as", "probability": 0.904296875 }, { "start": 3434.64, "end": 3434.94, "word": " the", "probability": 0.81689453125 }, { "start": 3434.94, "end": 3435.46, "word": " recall", "probability": 0.68798828125 }, { "start": 3435.46, "end": 3435.66, "word": " and", "probability": 0.8603515625 }, { "start": 3435.66, "end": 3435.8, "word": " the", "probability": 0.80712890625 }, { "start": 3435.8, "end": 3436.16, "word": " precision", "probability": 0.84912109375 }, { "start": 3436.16, "end": 3436.62, "word": ",", "probability": 0.80224609375 } ] }, { "id": 917, "seek": 334982, "start": 3436.62, "end": 3438.08, "text": " which we don't need to worry about too much.", "tokens": [ 51264, 597, 321, 500, 380, 643, 281, 3292, 466, 886, 709, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.1804199245525524, "compression_ratio": 1.8115384615384615, "no_speech_prob": 0.0017547607421875, "words": [ { "start": 3436.62, "end": 3436.9, "word": " which", "probability": 0.91796875 }, { "start": 3436.9, "end": 3437.0, "word": " we", "probability": 0.90234375 }, { "start": 3437.0, "end": 3437.1, "word": " don't", "probability": 0.94677734375 }, { "start": 3437.1, "end": 3437.24, "word": " need", "probability": 0.822265625 }, { "start": 3437.24, "end": 3437.34, "word": " to", "probability": 0.9072265625 }, { "start": 3437.34, "end": 3437.46, "word": " worry", "probability": 0.90185546875 }, { "start": 3437.46, "end": 3437.68, "word": " about", "probability": 0.8125 }, { "start": 3437.68, "end": 3437.86, "word": " too", "probability": 0.80224609375 }, { "start": 3437.86, "end": 3438.04, "word": " much", "probability": 0.81201171875 }, { "start": 3438.04, "end": 3438.08, "word": ".", "probability": 0.8095703125 } ] }, { "id": 918, "seek": 334982, "start": 3438.08, "end": 3440.34, "text": " We're just going to focus on the accuracy for now.", "tokens": [ 51314, 492, 434, 445, 516, 281, 1879, 322, 264, 14170, 337, 586, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.1804199245525524, "compression_ratio": 1.8115384615384615, "no_speech_prob": 0.0017547607421875, "words": [ { "start": 3438.08, "end": 3438.18, "word": " We're", "probability": 0.927001953125 }, { "start": 3438.18, "end": 3438.32, "word": " just", "probability": 0.8818359375 }, { "start": 3438.32, "end": 3438.44, "word": " going", "probability": 0.83935546875 }, { "start": 3438.44, "end": 3438.52, "word": " to", "probability": 0.90625 }, { "start": 3438.52, "end": 3438.72, "word": " focus", "probability": 0.85205078125 }, { "start": 3438.72, "end": 3438.86, "word": " on", "probability": 0.90673828125 }, { "start": 3438.86, "end": 3439.0, "word": " the", "probability": 0.81494140625 }, { "start": 3439.0, "end": 3439.38, "word": " accuracy", "probability": 0.76953125 }, { "start": 3439.38, "end": 3439.64, "word": " for", "probability": 0.8916015625 }, { "start": 3439.64, "end": 3439.98, "word": " now", "probability": 0.896484375 }, { "start": 3439.98, "end": 3440.34, "word": ".", "probability": 0.53759765625 } ] }, { "id": 919, "seek": 334982, "start": 3440.34, "end": 3443.84, "text": " But for data science, it's important to know what the recall", "tokens": [ 51414, 583, 337, 1412, 3497, 11, 309, 311, 1021, 281, 458, 437, 264, 9901, 51614 ], "temperature": 0.0, "avg_logprob": -0.1804199245525524, "compression_ratio": 1.8115384615384615, "no_speech_prob": 0.0017547607421875, "words": [ { "start": 3440.34, "end": 3440.7, "word": " But", "probability": 0.8837890625 }, { "start": 3440.7, "end": 3441.18, "word": " for", "probability": 0.88818359375 }, { "start": 3441.18, "end": 3441.8, "word": " data", "probability": 0.77880859375 }, { "start": 3441.8, "end": 3442.26, "word": " science", "probability": 0.875 }, { "start": 3442.26, "end": 3442.26, "word": ",", "probability": 0.8525390625 }, { "start": 3442.26, "end": 3442.58, "word": " it's", "probability": 0.949462890625 }, { "start": 3442.58, "end": 3442.92, "word": " important", "probability": 0.765625 }, { "start": 3442.92, "end": 3443.1, "word": " to", "probability": 0.904296875 }, { "start": 3443.1, "end": 3443.24, "word": " know", "probability": 0.82080078125 }, { "start": 3443.24, "end": 3443.42, "word": " what", "probability": 0.8818359375 }, { "start": 3443.42, "end": 3443.58, "word": " the", "probability": 0.818359375 }, { "start": 3443.58, "end": 3443.84, "word": " recall", "probability": 0.6142578125 } ] }, { "id": 920, "seek": 337590, "start": 3443.84, "end": 3448.74, "text": " and the precision are as we go through things.", "tokens": [ 50364, 293, 264, 18356, 366, 382, 321, 352, 807, 721, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.21180556144243406, "compression_ratio": 1.621301775147929, "no_speech_prob": 0.108154296875, "words": [ { "start": 3443.84, "end": 3443.94, "word": " and", "probability": 0.375 }, { "start": 3443.94, "end": 3444.02, "word": " the", "probability": 0.54833984375 }, { "start": 3444.02, "end": 3444.38, "word": " precision", "probability": 0.84619140625 }, { "start": 3444.38, "end": 3446.6, "word": " are", "probability": 0.771484375 }, { "start": 3446.6, "end": 3447.06, "word": " as", "probability": 0.806640625 }, { "start": 3447.06, "end": 3447.22, "word": " we", "probability": 0.904296875 }, { "start": 3447.22, "end": 3447.4, "word": " go", "probability": 0.89990234375 }, { "start": 3447.4, "end": 3447.7, "word": " through", "probability": 0.78662109375 }, { "start": 3447.7, "end": 3448.26, "word": " things", "probability": 0.74072265625 }, { "start": 3448.26, "end": 3448.74, "word": ".", "probability": 0.896484375 } ] }, { "id": 921, "seek": 337590, "start": 3450.34, "end": 3454.8, "text": " Report, test labels, and then we're going to use our predictions again.", "tokens": [ 50664, 16057, 11, 1500, 16949, 11, 293, 550, 321, 434, 516, 281, 764, 527, 21264, 797, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.21180556144243406, "compression_ratio": 1.621301775147929, "no_speech_prob": 0.108154296875, "words": [ { "start": 3450.34, "end": 3450.82, "word": " Report", "probability": 0.479248046875 }, { "start": 3450.82, "end": 3451.08, "word": ",", "probability": 0.409423828125 }, { "start": 3451.08, "end": 3451.74, "word": " test", "probability": 0.7939453125 }, { "start": 3451.74, "end": 3452.5, "word": " labels", "probability": 0.61328125 }, { "start": 3452.5, "end": 3452.8, "word": ",", "probability": 0.720703125 }, { "start": 3452.8, "end": 3452.96, "word": " and", "probability": 0.88623046875 }, { "start": 3452.96, "end": 3453.12, "word": " then", "probability": 0.720703125 }, { "start": 3453.12, "end": 3453.28, "word": " we're", "probability": 0.916015625 }, { "start": 3453.28, "end": 3453.34, "word": " going", "probability": 0.2734375 }, { "start": 3453.34, "end": 3453.36, "word": " to", "probability": 0.9091796875 }, { "start": 3453.36, "end": 3453.5, "word": " use", "probability": 0.818359375 }, { "start": 3453.5, "end": 3453.62, "word": " our", "probability": 0.8046875 }, { "start": 3453.62, "end": 3453.92, "word": " predictions", "probability": 0.74560546875 }, { "start": 3453.92, "end": 3454.32, "word": " again", "probability": 0.904296875 }, { "start": 3454.32, "end": 3454.8, "word": ".", "probability": 0.93896484375 } ] }, { "id": 922, "seek": 337590, "start": 3456.18, "end": 3463.44, "text": " And this is just like our C matrix MNB TF-IDF,", "tokens": [ 50964, 400, 341, 307, 445, 411, 527, 383, 8141, 376, 45, 33, 40964, 12, 2777, 37, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.21180556144243406, "compression_ratio": 1.621301775147929, "no_speech_prob": 0.108154296875, "words": [ { "start": 3456.18, "end": 3456.66, "word": " And", "probability": 0.74169921875 }, { "start": 3456.66, "end": 3456.82, "word": " this", "probability": 0.8671875 }, { "start": 3456.82, "end": 3456.94, "word": " is", "probability": 0.9072265625 }, { "start": 3456.94, "end": 3457.18, "word": " just", "probability": 0.8828125 }, { "start": 3457.18, "end": 3457.74, "word": " like", "probability": 0.88134765625 }, { "start": 3457.74, "end": 3459.52, "word": " our", "probability": 0.82763671875 }, { "start": 3459.52, "end": 3461.38, "word": " C", "probability": 0.32470703125 }, { "start": 3461.38, "end": 3461.84, "word": " matrix", "probability": 0.63720703125 }, { "start": 3461.84, "end": 3462.4, "word": " MNB", "probability": 0.4528401692708333 }, { "start": 3462.4, "end": 3462.7, "word": " TF", "probability": 0.220703125 }, { "start": 3462.7, "end": 3463.08, "word": "-IDF", "probability": 0.6645100911458334 }, { "start": 3463.08, "end": 3463.44, "word": ",", "probability": 0.187255859375 } ] }, { "id": 923, "seek": 337590, "start": 3464.1, "end": 3465.74, "text": " in the order that we put things.", "tokens": [ 51364, 294, 264, 1668, 300, 321, 829, 721, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.21180556144243406, "compression_ratio": 1.621301775147929, "no_speech_prob": 0.108154296875, "words": [ { "start": 3464.1, "end": 3464.58, "word": " in", "probability": 0.875 }, { "start": 3464.58, "end": 3464.74, "word": " the", "probability": 0.81591796875 }, { "start": 3464.74, "end": 3464.98, "word": " order", "probability": 0.81884765625 }, { "start": 3464.98, "end": 3465.12, "word": " that", "probability": 0.876953125 }, { "start": 3465.12, "end": 3465.22, "word": " we", "probability": 0.90625 }, { "start": 3465.22, "end": 3465.4, "word": " put", "probability": 0.888671875 }, { "start": 3465.4, "end": 3465.62, "word": " things", "probability": 0.72412109375 }, { "start": 3465.62, "end": 3465.74, "word": ".", "probability": 0.681640625 } ] }, { "id": 924, "seek": 337590, "start": 3465.74, "end": 3468.02, "text": " We have test labels, test labels, predictions, predictions.", "tokens": [ 51464, 492, 362, 1500, 16949, 11, 1500, 16949, 11, 21264, 11, 21264, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.21180556144243406, "compression_ratio": 1.621301775147929, "no_speech_prob": 0.108154296875, "words": [ { "start": 3465.74, "end": 3465.74, "word": " We", "probability": 0.61328125 }, { "start": 3465.74, "end": 3465.86, "word": " have", "probability": 0.78271484375 }, { "start": 3465.86, "end": 3466.04, "word": " test", "probability": 0.7880859375 }, { "start": 3466.04, "end": 3466.28, "word": " labels", "probability": 0.84375 }, { "start": 3466.28, "end": 3466.36, "word": ",", "probability": 0.9833984375 }, { "start": 3466.36, "end": 3466.5, "word": " test", "probability": 0.83056640625 }, { "start": 3466.5, "end": 3466.72, "word": " labels", "probability": 0.79638671875 }, { "start": 3466.72, "end": 3466.84, "word": ",", "probability": 0.97119140625 }, { "start": 3466.84, "end": 3467.12, "word": " predictions", "probability": 0.7646484375 }, { "start": 3467.12, "end": 3467.32, "word": ",", "probability": 0.99072265625 }, { "start": 3467.32, "end": 3467.54, "word": " predictions", "probability": 0.78271484375 }, { "start": 3467.54, "end": 3468.02, "word": ".", "probability": 0.8095703125 } ] }, { "id": 925, "seek": 337590, "start": 3468.82, "end": 3469.92, "text": " And that is it.", "tokens": [ 51614, 400, 300, 307, 309, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.21180556144243406, "compression_ratio": 1.621301775147929, "no_speech_prob": 0.108154296875, "words": [ { "start": 3468.82, "end": 3469.3, "word": " And", "probability": 0.884765625 }, { "start": 3469.3, "end": 3469.56, "word": " that", "probability": 0.8662109375 }, { "start": 3469.56, "end": 3469.72, "word": " is", "probability": 0.90869140625 }, { "start": 3469.72, "end": 3469.88, "word": " it", "probability": 0.90673828125 }, { "start": 3469.88, "end": 3469.92, "word": ".", "probability": 0.6484375 } ] }, { "id": 926, "seek": 339996, "start": 3469.92, "end": 3472.24, "text": " And then we're going to use our helper function generate report.", "tokens": [ 50364, 400, 550, 321, 434, 516, 281, 764, 527, 36133, 2445, 8460, 2275, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.1755434733370076, "compression_ratio": 1.7004405286343611, "no_speech_prob": 0.14404296875, "words": [ { "start": 3469.92, "end": 3470.0, "word": " And", "probability": 0.301025390625 }, { "start": 3470.0, "end": 3470.1, "word": " then", "probability": 0.72216796875 }, { "start": 3470.1, "end": 3470.22, "word": " we're", "probability": 0.9111328125 }, { "start": 3470.22, "end": 3470.3, "word": " going", "probability": 0.32568359375 }, { "start": 3470.3, "end": 3470.34, "word": " to", "probability": 0.9072265625 }, { "start": 3470.34, "end": 3470.46, "word": " use", "probability": 0.82177734375 }, { "start": 3470.46, "end": 3470.58, "word": " our", "probability": 0.7802734375 }, { "start": 3470.58, "end": 3470.72, "word": " helper", "probability": 0.904296875 }, { "start": 3470.72, "end": 3471.08, "word": " function", "probability": 0.8857421875 }, { "start": 3471.08, "end": 3471.4, "word": " generate", "probability": 0.509765625 }, { "start": 3471.4, "end": 3471.78, "word": " report", "probability": 0.48388671875 }, { "start": 3471.78, "end": 3472.24, "word": ".", "probability": 0.990234375 } ] }, { "id": 927, "seek": 339996, "start": 3473.56, "end": 3475.68, "text": " So I know that's a lot of typing.", "tokens": [ 50564, 407, 286, 458, 300, 311, 257, 688, 295, 18444, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.1755434733370076, "compression_ratio": 1.7004405286343611, "no_speech_prob": 0.14404296875, "words": [ { "start": 3473.56, "end": 3474.02, "word": " So", "probability": 0.8642578125 }, { "start": 3474.02, "end": 3474.2, "word": " I", "probability": 0.85009765625 }, { "start": 3474.2, "end": 3474.28, "word": " know", "probability": 0.81982421875 }, { "start": 3474.28, "end": 3474.5, "word": " that's", "probability": 0.9384765625 }, { "start": 3474.68, "end": 3474.82, "word": " a lot", "probability": 0.8935546875 }, { "start": 3474.82, "end": 3474.94, "word": " of", "probability": 0.90380859375 }, { "start": 3474.94, "end": 3475.22, "word": " typing", "probability": 0.77197265625 }, { "start": 3475.22, "end": 3475.68, "word": ".", "probability": 0.8330078125 } ] }, { "id": 928, "seek": 339996, "start": 3475.72, "end": 3480.42, "text": " I'm going to go ahead and sit here as you guys kind of follow through.", "tokens": [ 50664, 286, 478, 516, 281, 352, 2286, 293, 1394, 510, 382, 291, 1074, 733, 295, 1524, 807, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.1755434733370076, "compression_ratio": 1.7004405286343611, "no_speech_prob": 0.14404296875, "words": [ { "start": 3475.72, "end": 3476.1, "word": " I'm", "probability": 0.99169921875 }, { "start": 3476.1, "end": 3476.14, "word": " going", "probability": 0.78173828125 }, { "start": 3476.14, "end": 3476.18, "word": " to", "probability": 0.90185546875 }, { "start": 3476.18, "end": 3476.28, "word": " go", "probability": 0.892578125 }, { "start": 3476.28, "end": 3476.6, "word": " ahead", "probability": 0.8515625 }, { "start": 3476.6, "end": 3476.94, "word": " and", "probability": 0.9013671875 }, { "start": 3476.94, "end": 3477.36, "word": " sit", "probability": 0.90478515625 }, { "start": 3477.36, "end": 3477.86, "word": " here", "probability": 0.81640625 }, { "start": 3477.86, "end": 3478.78, "word": " as", "probability": 0.28662109375 }, { "start": 3478.78, "end": 3478.88, "word": " you", "probability": 0.89013671875 }, { "start": 3478.88, "end": 3479.04, "word": " guys", "probability": 0.9013671875 }, { "start": 3479.04, "end": 3479.24, "word": " kind", "probability": 0.63818359375 }, { "start": 3479.24, "end": 3479.34, "word": " of", "probability": 0.900390625 }, { "start": 3479.34, "end": 3479.62, "word": " follow", "probability": 0.7861328125 }, { "start": 3479.62, "end": 3479.96, "word": " through", "probability": 0.79052734375 }, { "start": 3479.96, "end": 3480.42, "word": ".", "probability": 0.9921875 } ] }, { "id": 929, "seek": 339996, "start": 3480.42, "end": 3483.88, "text": " So we have our MNB TF-IDF constructor.", "tokens": [ 50914, 407, 321, 362, 527, 376, 45, 33, 40964, 12, 2777, 37, 47479, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.1755434733370076, "compression_ratio": 1.7004405286343611, "no_speech_prob": 0.14404296875, "words": [ { "start": 3480.42, "end": 3480.86, "word": " So", "probability": 0.896484375 }, { "start": 3480.86, "end": 3481.08, "word": " we", "probability": 0.87841796875 }, { "start": 3481.08, "end": 3481.36, "word": " have", "probability": 0.876953125 }, { "start": 3481.36, "end": 3481.7, "word": " our", "probability": 0.81591796875 }, { "start": 3481.7, "end": 3482.08, "word": " MNB", "probability": 0.5630696614583334 }, { "start": 3482.08, "end": 3482.44, "word": " TF", "probability": 0.50439453125 }, { "start": 3482.44, "end": 3482.84, "word": "-IDF", "probability": 0.8313802083333334 }, { "start": 3482.84, "end": 3483.5, "word": " constructor", "probability": 0.74365234375 }, { "start": 3483.5, "end": 3483.88, "word": ".", "probability": 0.8515625 } ] }, { "id": 930, "seek": 339996, "start": 3483.88, "end": 3487.12, "text": " We are going to train it using the fit function.", "tokens": [ 51064, 492, 366, 516, 281, 3847, 309, 1228, 264, 3318, 2445, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.1755434733370076, "compression_ratio": 1.7004405286343611, "no_speech_prob": 0.14404296875, "words": [ { "start": 3483.88, "end": 3484.24, "word": " We", "probability": 0.9033203125 }, { "start": 3484.24, "end": 3484.4, "word": " are", "probability": 0.8876953125 }, { "start": 3484.4, "end": 3484.58, "word": " going", "probability": 0.8603515625 }, { "start": 3484.58, "end": 3484.82, "word": " to", "probability": 0.90380859375 }, { "start": 3484.82, "end": 3485.14, "word": " train", "probability": 0.80419921875 }, { "start": 3485.14, "end": 3485.28, "word": " it", "probability": 0.89697265625 }, { "start": 3485.28, "end": 3485.56, "word": " using", "probability": 0.81005859375 }, { "start": 3485.56, "end": 3485.78, "word": " the", "probability": 0.80029296875 }, { "start": 3485.78, "end": 3486.12, "word": " fit", "probability": 0.802734375 }, { "start": 3486.12, "end": 3486.72, "word": " function", "probability": 0.880859375 }, { "start": 3486.72, "end": 3487.12, "word": ".", "probability": 0.9716796875 } ] }, { "id": 931, "seek": 339996, "start": 3487.12, "end": 3489.44, "text": " We're going to train it on our testing data,", "tokens": [ 51214, 492, 434, 516, 281, 3847, 309, 322, 527, 4997, 1412, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.1755434733370076, "compression_ratio": 1.7004405286343611, "no_speech_prob": 0.14404296875, "words": [ { "start": 3487.12, "end": 3487.32, "word": " We're", "probability": 0.923583984375 }, { "start": 3487.32, "end": 3487.34, "word": " going", "probability": 0.8212890625 }, { "start": 3487.34, "end": 3487.44, "word": " to", "probability": 0.90283203125 }, { "start": 3487.44, "end": 3487.72, "word": " train", "probability": 0.79931640625 }, { "start": 3487.72, "end": 3487.86, "word": " it", "probability": 0.8984375 }, { "start": 3487.86, "end": 3488.1, "word": " on", "probability": 0.91455078125 }, { "start": 3488.1, "end": 3488.42, "word": " our", "probability": 0.80322265625 }, { "start": 3488.42, "end": 3489.02, "word": " testing", "probability": 0.74951171875 }, { "start": 3489.02, "end": 3489.34, "word": " data", "probability": 0.8203125 }, { "start": 3489.34, "end": 3489.44, "word": ",", "probability": 0.779296875 } ] }, { "id": 932, "seek": 339996, "start": 3489.44, "end": 3491.14, "text": " which is stored as TF-IDFX,", "tokens": [ 51314, 597, 307, 12187, 382, 40964, 12, 2777, 37, 55, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.1755434733370076, "compression_ratio": 1.7004405286343611, "no_speech_prob": 0.14404296875, "words": [ { "start": 3489.44, "end": 3489.58, "word": " which", "probability": 0.921875 }, { "start": 3489.58, "end": 3489.72, "word": " is", "probability": 0.89111328125 }, { "start": 3489.72, "end": 3489.94, "word": " stored", "probability": 0.6474609375 }, { "start": 3489.94, "end": 3490.1, "word": " as", "probability": 0.908203125 }, { "start": 3490.1, "end": 3490.38, "word": " TF", "probability": 0.7685546875 }, { "start": 3490.38, "end": 3491.06, "word": "-IDFX", "probability": 0.764404296875 }, { "start": 3491.06, "end": 3491.14, "word": ",", "probability": 0.408203125 } ] }, { "id": 933, "seek": 339996, "start": 3491.14, "end": 3493.98, "text": " and our testing labels, which is just stored as labels.", "tokens": [ 51414, 293, 527, 4997, 16949, 11, 597, 307, 445, 12187, 382, 16949, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.1755434733370076, "compression_ratio": 1.7004405286343611, "no_speech_prob": 0.14404296875, "words": [ { "start": 3491.14, "end": 3491.34, "word": " and", "probability": 0.89111328125 }, { "start": 3491.34, "end": 3491.5, "word": " our", "probability": 0.8017578125 }, { "start": 3491.5, "end": 3491.86, "word": " testing", "probability": 0.7490234375 }, { "start": 3491.86, "end": 3492.24, "word": " labels", "probability": 0.85400390625 }, { "start": 3492.24, "end": 3492.36, "word": ",", "probability": 0.91259765625 }, { "start": 3492.36, "end": 3492.48, "word": " which", "probability": 0.9208984375 }, { "start": 3492.48, "end": 3492.6, "word": " is", "probability": 0.87939453125 }, { "start": 3492.6, "end": 3492.76, "word": " just", "probability": 0.85302734375 }, { "start": 3492.76, "end": 3493.0, "word": " stored", "probability": 0.7265625 }, { "start": 3493.0, "end": 3493.16, "word": " as", "probability": 0.90478515625 }, { "start": 3493.16, "end": 3493.52, "word": " labels", "probability": 0.85205078125 }, { "start": 3493.52, "end": 3493.98, "word": ".", "probability": 0.982421875 } ] }, { "id": 934, "seek": 342996, "start": 3493.98, "end": 3499.96, "text": " We are going to use score, MNB TF-IDF.score,", "tokens": [ 50364, 492, 366, 516, 281, 764, 6175, 11, 376, 45, 33, 40964, 12, 2777, 37, 13, 4417, 418, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.21532738322303407, "compression_ratio": 1.6491228070175439, "no_speech_prob": 0.07476806640625, "words": [ { "start": 3493.98, "end": 3494.72, "word": " We", "probability": 0.58984375 }, { "start": 3494.72, "end": 3494.82, "word": " are", "probability": 0.4541015625 }, { "start": 3494.82, "end": 3495.02, "word": " going", "probability": 0.85693359375 }, { "start": 3495.02, "end": 3495.24, "word": " to", "probability": 0.90576171875 }, { "start": 3495.24, "end": 3495.62, "word": " use", "probability": 0.83056640625 }, { "start": 3495.62, "end": 3497.04, "word": " score", "probability": 0.316650390625 }, { "start": 3497.04, "end": 3497.84, "word": ",", "probability": 0.5673828125 }, { "start": 3497.84, "end": 3498.1, "word": " MNB", "probability": 0.4515787760416667 }, { "start": 3498.1, "end": 3498.38, "word": " TF", "probability": 0.0093536376953125 }, { "start": 3498.38, "end": 3498.8, "word": "-IDF", "probability": 0.6701456705729166 }, { "start": 3498.8, "end": 3499.66, "word": ".score", "probability": 0.678955078125 }, { "start": 3499.66, "end": 3499.96, "word": ",", "probability": 0.4833984375 } ] }, { "id": 935, "seek": 342996, "start": 3499.96, "end": 3502.56, "text": " to evaluate our accuracy.", "tokens": [ 50664, 281, 13059, 527, 14170, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.21532738322303407, "compression_ratio": 1.6491228070175439, "no_speech_prob": 0.07476806640625, "words": [ { "start": 3499.96, "end": 3500.28, "word": " to", "probability": 0.89990234375 }, { "start": 3500.28, "end": 3500.94, "word": " evaluate", "probability": 0.7060546875 }, { "start": 3500.94, "end": 3501.46, "word": " our", "probability": 0.81103515625 }, { "start": 3501.46, "end": 3502.04, "word": " accuracy", "probability": 0.7333984375 }, { "start": 3502.04, "end": 3502.56, "word": ".", "probability": 0.95654296875 } ] }, { "id": 936, "seek": 342996, "start": 3502.88, "end": 3505.74, "text": " We're going to use our predictions to get the raw predictions.", "tokens": [ 50764, 492, 434, 516, 281, 764, 527, 21264, 281, 483, 264, 8936, 21264, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.21532738322303407, "compression_ratio": 1.6491228070175439, "no_speech_prob": 0.07476806640625, "words": [ { "start": 3502.88, "end": 3503.22, "word": " We're", "probability": 0.904052734375 }, { "start": 3503.22, "end": 3503.28, "word": " going", "probability": 0.333251953125 }, { "start": 3503.28, "end": 3503.32, "word": " to", "probability": 0.9052734375 }, { "start": 3503.32, "end": 3503.46, "word": " use", "probability": 0.822265625 }, { "start": 3503.46, "end": 3503.58, "word": " our", "probability": 0.7783203125 }, { "start": 3503.58, "end": 3503.98, "word": " predictions", "probability": 0.7548828125 }, { "start": 3503.98, "end": 3504.28, "word": " to", "probability": 0.8876953125 }, { "start": 3504.28, "end": 3504.4, "word": " get", "probability": 0.89013671875 }, { "start": 3504.4, "end": 3504.56, "word": " the", "probability": 0.81201171875 }, { "start": 3504.56, "end": 3504.8, "word": " raw", "probability": 0.82861328125 }, { "start": 3504.8, "end": 3505.3, "word": " predictions", "probability": 0.74169921875 }, { "start": 3505.3, "end": 3505.74, "word": ".", "probability": 0.405517578125 } ] }, { "id": 937, "seek": 342996, "start": 3505.74, "end": 3507.26, "text": " And then with the raw predictions,", "tokens": [ 50914, 400, 550, 365, 264, 8936, 21264, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.21532738322303407, "compression_ratio": 1.6491228070175439, "no_speech_prob": 0.07476806640625, "words": [ { "start": 3505.74, "end": 3505.78, "word": " And", "probability": 0.85546875 }, { "start": 3505.78, "end": 3505.96, "word": " then", "probability": 0.7236328125 }, { "start": 3505.96, "end": 3506.46, "word": " with", "probability": 0.662109375 }, { "start": 3506.46, "end": 3506.6, "word": " the", "probability": 0.81689453125 }, { "start": 3506.6, "end": 3506.78, "word": " raw", "probability": 0.8369140625 }, { "start": 3506.78, "end": 3507.26, "word": " predictions", "probability": 0.75244140625 }, { "start": 3507.26, "end": 3507.26, "word": ",", "probability": 0.84521484375 } ] }, { "id": 938, "seek": 342996, "start": 3507.26, "end": 3512.26, "text": " we are going to develop a confusion matrix and a classification report,", "tokens": [ 51014, 321, 366, 516, 281, 1499, 257, 15075, 8141, 293, 257, 21538, 2275, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.21532738322303407, "compression_ratio": 1.6491228070175439, "no_speech_prob": 0.07476806640625, "words": [ { "start": 3507.26, "end": 3507.62, "word": " we", "probability": 0.90576171875 }, { "start": 3507.62, "end": 3507.74, "word": " are", "probability": 0.828125 }, { "start": 3507.74, "end": 3507.92, "word": " going", "probability": 0.85888671875 }, { "start": 3507.92, "end": 3508.14, "word": " to", "probability": 0.90380859375 }, { "start": 3508.14, "end": 3508.66, "word": " develop", "probability": 0.69970703125 }, { "start": 3508.8, "end": 3509.34, "word": " a confusion", "probability": 0.1962890625 }, { "start": 3509.34, "end": 3510.72, "word": " matrix", "probability": 0.86865234375 }, { "start": 3510.72, "end": 3510.96, "word": " and", "probability": 0.83984375 }, { "start": 3511.06, "end": 3511.52, "word": " a classification", "probability": 0.94091796875 }, { "start": 3511.52, "end": 3511.98, "word": " report", "probability": 0.7958984375 }, { "start": 3511.98, "end": 3512.26, "word": ",", "probability": 0.724609375 } ] }, { "id": 939, "seek": 342996, "start": 3512.26, "end": 3515.62, "text": " which will tell us how well our model is doing visually.", "tokens": [ 51264, 597, 486, 980, 505, 577, 731, 527, 2316, 307, 884, 19622, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.21532738322303407, "compression_ratio": 1.6491228070175439, "no_speech_prob": 0.07476806640625, "words": [ { "start": 3512.26, "end": 3512.7, "word": " which", "probability": 0.91796875 }, { "start": 3512.7, "end": 3512.9, "word": " will", "probability": 0.81494140625 }, { "start": 3512.9, "end": 3513.12, "word": " tell", "probability": 0.830078125 }, { "start": 3513.12, "end": 3513.26, "word": " us", "probability": 0.9013671875 }, { "start": 3513.26, "end": 3513.4, "word": " how", "probability": 0.90478515625 }, { "start": 3513.4, "end": 3513.62, "word": " well", "probability": 0.88037109375 }, { "start": 3513.62, "end": 3513.78, "word": " our", "probability": 0.81494140625 }, { "start": 3513.78, "end": 3513.98, "word": " model", "probability": 0.814453125 }, { "start": 3513.98, "end": 3514.16, "word": " is", "probability": 0.88037109375 }, { "start": 3514.16, "end": 3514.46, "word": " doing", "probability": 0.91015625 }, { "start": 3514.46, "end": 3515.1, "word": " visually", "probability": 0.6669921875 }, { "start": 3515.1, "end": 3515.62, "word": ".", "probability": 0.9990234375 } ] }, { "id": 940, "seek": 342996, "start": 3518.92, "end": 3521.1, "text": " So I'm going to let that sit for one more minute.", "tokens": [ 51614, 407, 286, 478, 516, 281, 718, 300, 1394, 337, 472, 544, 3456, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.21532738322303407, "compression_ratio": 1.6491228070175439, "no_speech_prob": 0.07476806640625, "words": [ { "start": 3518.92, "end": 3519.44, "word": " So", "probability": 0.81298828125 }, { "start": 3519.44, "end": 3519.54, "word": " I'm", "probability": 0.8935546875 }, { "start": 3519.54, "end": 3519.56, "word": " going", "probability": 0.576171875 }, { "start": 3519.56, "end": 3519.6, "word": " to", "probability": 0.8955078125 }, { "start": 3519.6, "end": 3519.7, "word": " let", "probability": 0.89111328125 }, { "start": 3519.7, "end": 3519.88, "word": " that", "probability": 0.88037109375 }, { "start": 3519.88, "end": 3520.0, "word": " sit", "probability": 0.89404296875 }, { "start": 3520.0, "end": 3520.16, "word": " for", "probability": 0.8984375 }, { "start": 3520.16, "end": 3520.4, "word": " one", "probability": 0.81298828125 }, { "start": 3520.4, "end": 3520.56, "word": " more", "probability": 0.8759765625 }, { "start": 3520.56, "end": 3520.82, "word": " minute", "probability": 0.89404296875 }, { "start": 3520.82, "end": 3521.1, "word": ".", "probability": 0.955078125 } ] }, { "id": 941, "seek": 342996, "start": 3521.1, "end": 3523.22, "text": " TA, are there any questions?", "tokens": [ 51714, 20094, 11, 366, 456, 604, 1651, 30, 51814 ], "temperature": 0.0, "avg_logprob": -0.21532738322303407, "compression_ratio": 1.6491228070175439, "no_speech_prob": 0.07476806640625, "words": [ { "start": 3521.1, "end": 3521.36, "word": " TA", "probability": 0.74462890625 }, { "start": 3521.36, "end": 3521.52, "word": ",", "probability": 0.90966796875 }, { "start": 3521.52, "end": 3521.72, "word": " are", "probability": 0.8916015625 }, { "start": 3521.72, "end": 3522.0, "word": " there", "probability": 0.85302734375 }, { "start": 3522.0, "end": 3522.32, "word": " any", "probability": 0.81591796875 }, { "start": 3522.32, "end": 3522.84, "word": " questions", "probability": 0.90869140625 }, { "start": 3522.84, "end": 3523.22, "word": "?", "probability": 0.990234375 } ] }, { "id": 942, "seek": 345940, "start": 3532.16, "end": 3536.32, "text": " No, I think... well, hang on, let me go back one here.", "tokens": [ 50414, 883, 11, 286, 519, 485, 731, 11, 3967, 322, 11, 718, 385, 352, 646, 472, 510, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.2170138955116272, "compression_ratio": 1.6428571428571428, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 3532.16, "end": 3532.56, "word": " No", "probability": 0.2056884765625 }, { "start": 3532.56, "end": 3532.74, "word": ",", "probability": 0.84765625 }, { "start": 3532.74, "end": 3532.88, "word": " I", "probability": 0.97021484375 }, { "start": 3532.88, "end": 3533.76, "word": " think...", "probability": 0.443756103515625 }, { "start": 3533.76, "end": 3534.08, "word": " well", "probability": 0.2054443359375 }, { "start": 3534.08, "end": 3534.22, "word": ",", "probability": 0.73291015625 }, { "start": 3534.22, "end": 3534.52, "word": " hang", "probability": 0.77880859375 }, { "start": 3534.52, "end": 3534.64, "word": " on", "probability": 0.9052734375 }, { "start": 3534.64, "end": 3534.7, "word": ",", "probability": 0.5634765625 }, { "start": 3534.7, "end": 3534.8, "word": " let", "probability": 0.8857421875 }, { "start": 3534.8, "end": 3534.86, "word": " me", "probability": 0.90380859375 }, { "start": 3534.86, "end": 3535.0, "word": " go", "probability": 0.90283203125 }, { "start": 3535.0, "end": 3535.26, "word": " back", "probability": 0.8251953125 }, { "start": 3535.26, "end": 3535.54, "word": " one", "probability": 0.80859375 }, { "start": 3535.54, "end": 3535.92, "word": " here", "probability": 0.75390625 }, { "start": 3535.92, "end": 3536.32, "word": ".", "probability": 0.912109375 } ] }, { "id": 943, "seek": 345940, "start": 3537.94, "end": 3540.3, "text": " Nope, still got it. So I think we're good.", "tokens": [ 50714, 12172, 11, 920, 658, 309, 13, 407, 286, 519, 321, 434, 665, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.2170138955116272, "compression_ratio": 1.6428571428571428, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 3537.94, "end": 3538.34, "word": " Nope", "probability": 0.76416015625 }, { "start": 3538.34, "end": 3538.44, "word": ",", "probability": 0.8388671875 }, { "start": 3538.44, "end": 3538.62, "word": " still", "probability": 0.8740234375 }, { "start": 3538.62, "end": 3538.84, "word": " got", "probability": 0.47998046875 }, { "start": 3538.84, "end": 3539.0, "word": " it", "probability": 0.90673828125 }, { "start": 3539.0, "end": 3539.06, "word": ".", "probability": 0.474365234375 }, { "start": 3539.06, "end": 3539.16, "word": " So", "probability": 0.78955078125 }, { "start": 3539.16, "end": 3539.34, "word": " I", "probability": 0.71044921875 }, { "start": 3539.34, "end": 3539.52, "word": " think", "probability": 0.80712890625 }, { "start": 3539.52, "end": 3539.68, "word": " we're", "probability": 0.91650390625 }, { "start": 3539.68, "end": 3539.9, "word": " good", "probability": 0.87451171875 }, { "start": 3539.9, "end": 3540.3, "word": ".", "probability": 0.9892578125 } ] }, { "id": 944, "seek": 345940, "start": 3540.34, "end": 3542.46, "text": " Awesome. Awesome. Fantastic.", "tokens": [ 50814, 10391, 13, 10391, 13, 21320, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.2170138955116272, "compression_ratio": 1.6428571428571428, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 3540.34, "end": 3540.52, "word": " Awesome", "probability": 0.76416015625 }, { "start": 3540.52, "end": 3540.92, "word": ".", "probability": 0.64306640625 }, { "start": 3541.14, "end": 3541.54, "word": " Awesome", "probability": 0.8212890625 }, { "start": 3541.54, "end": 3541.68, "word": ".", "probability": 0.68310546875 }, { "start": 3541.68, "end": 3542.06, "word": " Fantastic", "probability": 0.8955078125 }, { "start": 3542.06, "end": 3542.46, "word": ".", "probability": 0.98583984375 } ] }, { "id": 945, "seek": 345940, "start": 3543.5, "end": 3548.1, "text": " So I am going to go ahead and move on.", "tokens": [ 50964, 407, 286, 669, 516, 281, 352, 2286, 293, 1286, 322, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.2170138955116272, "compression_ratio": 1.6428571428571428, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 3543.5, "end": 3543.9, "word": " So", "probability": 0.89208984375 }, { "start": 3543.9, "end": 3544.3, "word": " I", "probability": 0.87109375 }, { "start": 3544.3, "end": 3544.48, "word": " am", "probability": 0.880859375 }, { "start": 3544.48, "end": 3544.74, "word": " going", "probability": 0.85595703125 }, { "start": 3544.74, "end": 3545.3, "word": " to", "probability": 0.904296875 }, { "start": 3545.3, "end": 3546.08, "word": " go", "probability": 0.884765625 }, { "start": 3546.08, "end": 3546.6, "word": " ahead", "probability": 0.85986328125 }, { "start": 3546.6, "end": 3547.06, "word": " and", "probability": 0.8916015625 }, { "start": 3547.06, "end": 3547.58, "word": " move", "probability": 0.87451171875 }, { "start": 3547.58, "end": 3547.9, "word": " on", "probability": 0.9111328125 }, { "start": 3547.9, "end": 3548.1, "word": ".", "probability": 0.391845703125 } ] }, { "id": 946, "seek": 345940, "start": 3548.1, "end": 3550.4, "text": " I'm going to press Shift-Enter. It's going to run.", "tokens": [ 51214, 286, 478, 516, 281, 1886, 28304, 12, 16257, 391, 13, 467, 311, 516, 281, 1190, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.2170138955116272, "compression_ratio": 1.6428571428571428, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 3548.1, "end": 3548.28, "word": " I'm", "probability": 0.8115234375 }, { "start": 3548.28, "end": 3548.28, "word": " going", "probability": 0.61181640625 }, { "start": 3548.28, "end": 3548.34, "word": " to", "probability": 0.90673828125 }, { "start": 3548.34, "end": 3548.52, "word": " press", "probability": 0.6630859375 }, { "start": 3548.52, "end": 3548.78, "word": " Shift", "probability": 0.245849609375 }, { "start": 3548.78, "end": 3549.2, "word": "-Enter", "probability": 0.6526285807291666 }, { "start": 3549.2, "end": 3549.36, "word": ".", "probability": 0.59326171875 }, { "start": 3549.36, "end": 3549.56, "word": " It's", "probability": 0.784423828125 }, { "start": 3549.56, "end": 3549.64, "word": " going", "probability": 0.81005859375 }, { "start": 3549.64, "end": 3549.74, "word": " to", "probability": 0.90576171875 }, { "start": 3549.74, "end": 3550.0, "word": " run", "probability": 0.900390625 }, { "start": 3550.0, "end": 3550.4, "word": ".", "probability": 0.85302734375 } ] }, { "id": 947, "seek": 345940, "start": 3551.26, "end": 3556.8, "text": " And now we have our... up here at the top is our classification report.", "tokens": [ 51364, 400, 586, 321, 362, 527, 485, 493, 510, 412, 264, 1192, 307, 527, 21538, 2275, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.2170138955116272, "compression_ratio": 1.6428571428571428, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 3551.26, "end": 3551.38, "word": " And", "probability": 0.84326171875 }, { "start": 3551.38, "end": 3551.52, "word": " now", "probability": 0.88037109375 }, { "start": 3551.52, "end": 3551.68, "word": " we", "probability": 0.83349609375 }, { "start": 3551.68, "end": 3552.06, "word": " have", "probability": 0.87939453125 }, { "start": 3552.06, "end": 3553.18, "word": " our...", "probability": 0.695068359375 }, { "start": 3553.18, "end": 3553.54, "word": " up", "probability": 0.5712890625 }, { "start": 3553.54, "end": 3553.66, "word": " here", "probability": 0.818359375 }, { "start": 3553.66, "end": 3553.76, "word": " at", "probability": 0.8935546875 }, { "start": 3553.76, "end": 3553.88, "word": " the", "probability": 0.81396484375 }, { "start": 3553.88, "end": 3554.12, "word": " top", "probability": 0.822265625 }, { "start": 3554.12, "end": 3554.36, "word": " is", "probability": 0.88525390625 }, { "start": 3554.36, "end": 3554.58, "word": " our", "probability": 0.82763671875 }, { "start": 3554.58, "end": 3555.0, "word": " classification", "probability": 0.83740234375 }, { "start": 3555.0, "end": 3556.4, "word": " report", "probability": 0.84326171875 }, { "start": 3556.4, "end": 3556.8, "word": ".", "probability": 0.92041015625 } ] }, { "id": 948, "seek": 345940, "start": 3557.28, "end": 3559.78, "text": " And so what this is going to do is show us our precision", "tokens": [ 51664, 400, 370, 437, 341, 307, 516, 281, 360, 307, 855, 505, 527, 18356, 51814 ], "temperature": 0.0, "avg_logprob": -0.2170138955116272, "compression_ratio": 1.6428571428571428, "no_speech_prob": 0.002017974853515625, "words": [ { "start": 3557.28, "end": 3557.38, "word": " And", "probability": 0.779296875 }, { "start": 3557.38, "end": 3558.06, "word": " so", "probability": 0.8798828125 }, { "start": 3558.06, "end": 3558.36, "word": " what", "probability": 0.83349609375 }, { "start": 3558.36, "end": 3558.5, "word": " this", "probability": 0.8818359375 }, { "start": 3558.5, "end": 3558.62, "word": " is", "probability": 0.90380859375 }, { "start": 3558.62, "end": 3558.72, "word": " going", "probability": 0.84326171875 }, { "start": 3558.72, "end": 3558.78, "word": " to", "probability": 0.90625 }, { "start": 3558.78, "end": 3558.92, "word": " do", "probability": 0.90283203125 }, { "start": 3558.92, "end": 3559.04, "word": " is", "probability": 0.8896484375 }, { "start": 3559.04, "end": 3559.16, "word": " show", "probability": 0.88134765625 }, { "start": 3559.16, "end": 3559.28, "word": " us", "probability": 0.88623046875 }, { "start": 3559.28, "end": 3559.42, "word": " our", "probability": 0.81787109375 }, { "start": 3559.42, "end": 3559.78, "word": " precision", "probability": 0.76904296875 } ] }, { "id": 949, "seek": 348538, "start": 3559.78, "end": 3563.46, "text": " and our recall. We don't need to worry too much about this one.", "tokens": [ 50364, 293, 527, 9901, 13, 492, 500, 380, 643, 281, 3292, 886, 709, 466, 341, 472, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.17108586550963045, "compression_ratio": 1.6712962962962963, "no_speech_prob": 0.0007672309875488281, "words": [ { "start": 3559.78, "end": 3560.04, "word": " and", "probability": 0.2213134765625 }, { "start": 3560.04, "end": 3560.18, "word": " our", "probability": 0.70556640625 }, { "start": 3560.18, "end": 3560.62, "word": " recall", "probability": 0.677734375 }, { "start": 3560.62, "end": 3560.94, "word": ".", "probability": 0.1968994140625 }, { "start": 3560.94, "end": 3561.0, "word": " We", "probability": 0.88134765625 }, { "start": 3561.0, "end": 3561.38, "word": " don't", "probability": 0.945068359375 }, { "start": 3561.38, "end": 3561.54, "word": " need", "probability": 0.8134765625 }, { "start": 3561.54, "end": 3561.66, "word": " to", "probability": 0.90234375 }, { "start": 3561.66, "end": 3561.8, "word": " worry", "probability": 0.91552734375 }, { "start": 3561.8, "end": 3562.02, "word": " too", "probability": 0.80224609375 }, { "start": 3562.02, "end": 3562.18, "word": " much", "probability": 0.8212890625 }, { "start": 3562.18, "end": 3562.42, "word": " about", "probability": 0.81884765625 }, { "start": 3562.42, "end": 3562.66, "word": " this", "probability": 0.8857421875 }, { "start": 3562.66, "end": 3562.94, "word": " one", "probability": 0.8203125 }, { "start": 3562.94, "end": 3563.46, "word": ".", "probability": 0.8408203125 } ] }, { "id": 950, "seek": 348538, "start": 3563.62, "end": 3566.14, "text": " Instead, I want you to focus on the lower chart.", "tokens": [ 50514, 7156, 11, 286, 528, 291, 281, 1879, 322, 264, 3126, 6927, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.17108586550963045, "compression_ratio": 1.6712962962962963, "no_speech_prob": 0.0007672309875488281, "words": [ { "start": 3563.62, "end": 3564.14, "word": " Instead", "probability": 0.88916015625 }, { "start": 3564.14, "end": 3564.22, "word": ",", "probability": 0.5234375 }, { "start": 3564.22, "end": 3564.28, "word": " I", "probability": 0.99072265625 }, { "start": 3564.28, "end": 3564.4, "word": " want", "probability": 0.787109375 }, { "start": 3564.4, "end": 3564.56, "word": " you", "probability": 0.8828125 }, { "start": 3564.56, "end": 3564.72, "word": " to", "probability": 0.9052734375 }, { "start": 3564.72, "end": 3565.0, "word": " focus", "probability": 0.83740234375 }, { "start": 3565.0, "end": 3565.28, "word": " on", "probability": 0.9033203125 }, { "start": 3565.28, "end": 3565.48, "word": " the", "probability": 0.79638671875 }, { "start": 3565.48, "end": 3565.7, "word": " lower", "probability": 0.7578125 }, { "start": 3565.7, "end": 3566.04, "word": " chart", "probability": 0.76220703125 }, { "start": 3566.04, "end": 3566.14, "word": ".", "probability": 0.953125 } ] }, { "id": 951, "seek": 348538, "start": 3566.14, "end": 3568.68, "text": " So here we have an accuracy of 87.5%.", "tokens": [ 50664, 407, 510, 321, 362, 364, 14170, 295, 27990, 13, 20, 6856, 50814 ], "temperature": 0.0, "avg_logprob": -0.17108586550963045, "compression_ratio": 1.6712962962962963, "no_speech_prob": 0.0007672309875488281, "words": [ { "start": 3566.14, "end": 3566.22, "word": " So", "probability": 0.79541015625 }, { "start": 3566.22, "end": 3566.4, "word": " here", "probability": 0.705078125 }, { "start": 3566.4, "end": 3566.48, "word": " we", "probability": 0.7900390625 }, { "start": 3566.48, "end": 3566.58, "word": " have", "probability": 0.87890625 }, { "start": 3566.58, "end": 3566.68, "word": " an", "probability": 0.90087890625 }, { "start": 3566.68, "end": 3566.98, "word": " accuracy", "probability": 0.71240234375 }, { "start": 3566.98, "end": 3567.22, "word": " of", "probability": 0.8994140625 }, { "start": 3567.22, "end": 3567.68, "word": " 87", "probability": 0.8427734375 }, { "start": 3567.68, "end": 3568.68, "word": ".5%.", "probability": 0.9410807291666666 } ] }, { "id": 952, "seek": 348538, "start": 3569.42, "end": 3575.84, "text": " We can see that all of the actual ham emails were predicted as ham.", "tokens": [ 50814, 492, 393, 536, 300, 439, 295, 264, 3539, 7852, 12524, 645, 19147, 382, 7852, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.17108586550963045, "compression_ratio": 1.6712962962962963, "no_speech_prob": 0.0007672309875488281, "words": [ { "start": 3569.42, "end": 3569.94, "word": " We", "probability": 0.89013671875 }, { "start": 3569.94, "end": 3570.1, "word": " can", "probability": 0.89892578125 }, { "start": 3570.1, "end": 3570.5, "word": " see", "probability": 0.81640625 }, { "start": 3570.5, "end": 3571.18, "word": " that", "probability": 0.8818359375 }, { "start": 3571.18, "end": 3572.38, "word": " all", "probability": 0.88427734375 }, { "start": 3572.38, "end": 3572.76, "word": " of", "probability": 0.90283203125 }, { "start": 3572.76, "end": 3573.02, "word": " the", "probability": 0.81103515625 }, { "start": 3573.02, "end": 3573.44, "word": " actual", "probability": 0.80029296875 }, { "start": 3573.44, "end": 3573.72, "word": " ham", "probability": 0.34716796875 }, { "start": 3573.72, "end": 3574.18, "word": " emails", "probability": 0.783203125 }, { "start": 3574.18, "end": 3574.6, "word": " were", "probability": 0.873046875 }, { "start": 3574.6, "end": 3575.0, "word": " predicted", "probability": 0.7431640625 }, { "start": 3575.0, "end": 3575.26, "word": " as", "probability": 0.90771484375 }, { "start": 3575.26, "end": 3575.52, "word": " ham", "probability": 0.849609375 }, { "start": 3575.52, "end": 3575.84, "word": ".", "probability": 0.697265625 } ] }, { "id": 953, "seek": 348538, "start": 3575.84, "end": 3577.8, "text": " So these are our true positives.", "tokens": [ 51164, 407, 613, 366, 527, 2074, 35127, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.17108586550963045, "compression_ratio": 1.6712962962962963, "no_speech_prob": 0.0007672309875488281, "words": [ { "start": 3575.84, "end": 3576.02, "word": " So", "probability": 0.8798828125 }, { "start": 3576.02, "end": 3576.16, "word": " these", "probability": 0.67236328125 }, { "start": 3576.16, "end": 3576.28, "word": " are", "probability": 0.890625 }, { "start": 3576.28, "end": 3576.44, "word": " our", "probability": 0.74169921875 }, { "start": 3576.44, "end": 3576.68, "word": " true", "probability": 0.91552734375 }, { "start": 3576.68, "end": 3577.28, "word": " positives", "probability": 0.8076171875 }, { "start": 3577.28, "end": 3577.8, "word": ".", "probability": 0.91357421875 } ] }, { "id": 954, "seek": 348538, "start": 3578.52, "end": 3583.3, "text": " A little more than half of our spam emails were correctly predicted as spam.", "tokens": [ 51264, 316, 707, 544, 813, 1922, 295, 527, 24028, 12524, 645, 8944, 19147, 382, 24028, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.17108586550963045, "compression_ratio": 1.6712962962962963, "no_speech_prob": 0.0007672309875488281, "words": [ { "start": 3578.52, "end": 3579.04, "word": " A", "probability": 0.70263671875 }, { "start": 3579.04, "end": 3579.14, "word": " little", "probability": 0.80712890625 }, { "start": 3579.14, "end": 3579.38, "word": " more", "probability": 0.880859375 }, { "start": 3579.38, "end": 3579.58, "word": " than", "probability": 0.8837890625 }, { "start": 3579.58, "end": 3580.0, "word": " half", "probability": 0.822265625 }, { "start": 3580.0, "end": 3580.14, "word": " of", "probability": 0.908203125 }, { "start": 3580.14, "end": 3580.28, "word": " our", "probability": 0.83203125 }, { "start": 3580.28, "end": 3580.56, "word": " spam", "probability": 0.92529296875 }, { "start": 3580.56, "end": 3580.92, "word": " emails", "probability": 0.7880859375 }, { "start": 3580.92, "end": 3581.2, "word": " were", "probability": 0.8828125 }, { "start": 3581.2, "end": 3581.76, "word": " correctly", "probability": 0.8486328125 }, { "start": 3581.76, "end": 3582.2, "word": " predicted", "probability": 0.7216796875 }, { "start": 3582.2, "end": 3582.46, "word": " as", "probability": 0.90478515625 }, { "start": 3582.46, "end": 3582.8, "word": " spam", "probability": 0.92236328125 }, { "start": 3582.8, "end": 3583.3, "word": ".", "probability": 0.8701171875 } ] }, { "id": 955, "seek": 348538, "start": 3583.3, "end": 3585.76, "text": " So these are our true negatives.", "tokens": [ 51514, 407, 613, 366, 527, 2074, 40019, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.17108586550963045, "compression_ratio": 1.6712962962962963, "no_speech_prob": 0.0007672309875488281, "words": [ { "start": 3583.3, "end": 3583.48, "word": " So", "probability": 0.89453125 }, { "start": 3583.48, "end": 3583.68, "word": " these", "probability": 0.6982421875 }, { "start": 3583.68, "end": 3583.88, "word": " are", "probability": 0.890625 }, { "start": 3583.88, "end": 3584.18, "word": " our", "probability": 0.74462890625 }, { "start": 3584.18, "end": 3584.64, "word": " true", "probability": 0.92626953125 }, { "start": 3584.64, "end": 3585.24, "word": " negatives", "probability": 0.7919921875 }, { "start": 3585.24, "end": 3585.76, "word": ".", "probability": 0.91455078125 } ] }, { "id": 956, "seek": 350820, "start": 3585.76, "end": 3591.02, "text": " And then, unfortunately, it misclassified...", "tokens": [ 50414, 400, 550, 11, 7015, 11, 309, 3346, 11665, 2587, 485, 50664 ], "temperature": 0.0, "avg_logprob": -0.24735576923076924, "compression_ratio": 1.5389610389610389, "no_speech_prob": 0.006389617919921875, "words": [ { "start": 3585.76, "end": 3586.76, "word": " And", "probability": 0.484375 }, { "start": 3586.76, "end": 3587.12, "word": " then", "probability": 0.72265625 }, { "start": 3587.12, "end": 3587.74, "word": ",", "probability": 0.36328125 }, { "start": 3587.74, "end": 3588.26, "word": " unfortunately", "probability": 0.78955078125 }, { "start": 3588.26, "end": 3588.54, "word": ",", "probability": 0.46240234375 }, { "start": 3588.54, "end": 3588.62, "word": " it", "probability": 0.904296875 }, { "start": 3588.62, "end": 3591.02, "word": " misclassified...", "probability": 0.74749755859375 } ] }, { "id": 957, "seek": 350820, "start": 3591.76, "end": 3593.76, "text": " Oh, my mistake. I have that backwards.", "tokens": [ 50664, 876, 11, 452, 6146, 13, 286, 362, 300, 12204, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.24735576923076924, "compression_ratio": 1.5389610389610389, "no_speech_prob": 0.006389617919921875, "words": [ { "start": 3591.76, "end": 3592.18, "word": " Oh", "probability": 0.64990234375 }, { "start": 3592.18, "end": 3592.24, "word": ",", "probability": 0.85205078125 }, { "start": 3592.24, "end": 3592.38, "word": " my", "probability": 0.90625 }, { "start": 3592.38, "end": 3592.66, "word": " mistake", "probability": 0.90673828125 }, { "start": 3592.66, "end": 3592.72, "word": ".", "probability": 0.378173828125 }, { "start": 3592.72, "end": 3592.76, "word": " I", "probability": 0.99267578125 }, { "start": 3592.76, "end": 3592.88, "word": " have", "probability": 0.755859375 }, { "start": 3592.88, "end": 3592.98, "word": " that", "probability": 0.8701171875 }, { "start": 3592.98, "end": 3593.32, "word": " backwards", "probability": 0.794921875 }, { "start": 3593.32, "end": 3593.76, "word": ".", "probability": 0.98193359375 } ] }, { "id": 958, "seek": 350820, "start": 3593.76, "end": 3600.32, "text": " So it says 108 of our ham emails it thinks are spam emails,", "tokens": [ 50764, 407, 309, 1619, 41342, 295, 527, 7852, 12524, 309, 7309, 366, 24028, 12524, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.24735576923076924, "compression_ratio": 1.5389610389610389, "no_speech_prob": 0.006389617919921875, "words": [ { "start": 3593.76, "end": 3593.98, "word": " So", "probability": 0.826171875 }, { "start": 3593.98, "end": 3594.48, "word": " it", "probability": 0.53369140625 }, { "start": 3594.48, "end": 3594.62, "word": " says", "probability": 0.77880859375 }, { "start": 3594.62, "end": 3595.08, "word": " 108", "probability": 0.63818359375 }, { "start": 3595.08, "end": 3595.64, "word": " of", "probability": 0.90234375 }, { "start": 3595.64, "end": 3595.86, "word": " our", "probability": 0.8154296875 }, { "start": 3595.86, "end": 3596.22, "word": " ham", "probability": 0.49951171875 }, { "start": 3596.22, "end": 3596.86, "word": " emails", "probability": 0.73974609375 }, { "start": 3596.86, "end": 3597.56, "word": " it", "probability": 0.368896484375 }, { "start": 3597.56, "end": 3598.08, "word": " thinks", "probability": 0.80615234375 }, { "start": 3598.08, "end": 3598.48, "word": " are", "probability": 0.87841796875 }, { "start": 3598.48, "end": 3598.78, "word": " spam", "probability": 0.9267578125 }, { "start": 3598.78, "end": 3599.46, "word": " emails", "probability": 0.80224609375 }, { "start": 3599.46, "end": 3600.32, "word": ",", "probability": 0.499755859375 } ] }, { "id": 959, "seek": 350820, "start": 3600.32, "end": 3604.86, "text": " whereas all of the spam emails, so the actual spam emails,", "tokens": [ 51114, 9735, 439, 295, 264, 24028, 12524, 11, 370, 264, 3539, 24028, 12524, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.24735576923076924, "compression_ratio": 1.5389610389610389, "no_speech_prob": 0.006389617919921875, "words": [ { "start": 3600.32, "end": 3601.5, "word": " whereas", "probability": 0.8046875 }, { "start": 3601.5, "end": 3601.88, "word": " all", "probability": 0.88525390625 }, { "start": 3601.88, "end": 3602.02, "word": " of", "probability": 0.90185546875 }, { "start": 3602.02, "end": 3602.16, "word": " the", "probability": 0.80712890625 }, { "start": 3602.16, "end": 3602.46, "word": " spam", "probability": 0.8623046875 }, { "start": 3602.46, "end": 3603.06, "word": " emails", "probability": 0.79052734375 }, { "start": 3603.06, "end": 3603.22, "word": ",", "probability": 0.74462890625 }, { "start": 3603.22, "end": 3603.42, "word": " so", "probability": 0.87109375 }, { "start": 3603.42, "end": 3603.56, "word": " the", "probability": 0.80810546875 }, { "start": 3603.56, "end": 3603.94, "word": " actual", "probability": 0.8037109375 }, { "start": 3603.94, "end": 3604.32, "word": " spam", "probability": 0.91943359375 }, { "start": 3604.32, "end": 3604.74, "word": " emails", "probability": 0.77783203125 }, { "start": 3604.74, "end": 3604.86, "word": ",", "probability": 0.5283203125 } ] }, { "id": 960, "seek": 350820, "start": 3604.86, "end": 3608.58, "text": " were correctly classified as spam.", "tokens": [ 51314, 645, 8944, 20627, 382, 24028, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.24735576923076924, "compression_ratio": 1.5389610389610389, "no_speech_prob": 0.006389617919921875, "words": [ { "start": 3604.86, "end": 3605.0, "word": " were", "probability": 0.88037109375 }, { "start": 3605.0, "end": 3605.52, "word": " correctly", "probability": 0.85107421875 }, { "start": 3605.52, "end": 3606.32, "word": " classified", "probability": 0.91796875 }, { "start": 3606.32, "end": 3607.48, "word": " as", "probability": 0.91748046875 }, { "start": 3607.48, "end": 3607.84, "word": " spam", "probability": 0.916015625 }, { "start": 3607.84, "end": 3608.58, "word": ".", "probability": 0.9697265625 } ] }, { "id": 961, "seek": 353642, "start": 3608.58, "end": 3617.88, "text": " And then all of our ham emails, what it thought were ham emails, were ham.", "tokens": [ 50414, 400, 550, 439, 295, 527, 7852, 12524, 11, 437, 309, 1194, 645, 7852, 12524, 11, 645, 7852, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.19228516127914191, "compression_ratio": 1.5941176470588236, "no_speech_prob": 0.115966796875, "words": [ { "start": 3608.58, "end": 3609.4, "word": " And", "probability": 0.176025390625 }, { "start": 3609.4, "end": 3610.62, "word": " then", "probability": 0.650390625 }, { "start": 3610.62, "end": 3610.86, "word": " all", "probability": 0.80859375 }, { "start": 3610.86, "end": 3610.98, "word": " of", "probability": 0.8896484375 }, { "start": 3610.98, "end": 3611.18, "word": " our", "probability": 0.82080078125 }, { "start": 3611.18, "end": 3611.48, "word": " ham", "probability": 0.456298828125 }, { "start": 3611.48, "end": 3612.22, "word": " emails", "probability": 0.75634765625 }, { "start": 3612.22, "end": 3613.26, "word": ",", "probability": 0.303955078125 }, { "start": 3613.26, "end": 3615.42, "word": " what", "probability": 0.7978515625 }, { "start": 3615.42, "end": 3615.52, "word": " it", "probability": 0.0540771484375 }, { "start": 3615.52, "end": 3615.66, "word": " thought", "probability": 0.830078125 }, { "start": 3615.66, "end": 3615.8, "word": " were", "probability": 0.85302734375 }, { "start": 3615.8, "end": 3616.02, "word": " ham", "probability": 0.80224609375 }, { "start": 3616.02, "end": 3616.56, "word": " emails", "probability": 0.77587890625 }, { "start": 3616.56, "end": 3616.74, "word": ",", "probability": 0.43701171875 }, { "start": 3616.74, "end": 3617.1, "word": " were", "probability": 0.82861328125 }, { "start": 3617.1, "end": 3617.36, "word": " ham", "probability": 0.8330078125 }, { "start": 3617.36, "end": 3617.88, "word": ".", "probability": 0.986328125 } ] }, { "id": 962, "seek": 353642, "start": 3620.76, "end": 3626.44, "text": " So we're going to go ahead and do the same thing for 6b, 6c, and 6d.", "tokens": [ 50964, 407, 321, 434, 516, 281, 352, 2286, 293, 360, 264, 912, 551, 337, 1386, 65, 11, 1386, 66, 11, 293, 1386, 67, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.19228516127914191, "compression_ratio": 1.5941176470588236, "no_speech_prob": 0.115966796875, "words": [ { "start": 3620.76, "end": 3621.28, "word": " So", "probability": 0.85400390625 }, { "start": 3621.28, "end": 3621.8, "word": " we're", "probability": 0.79052734375 }, { "start": 3621.8, "end": 3621.88, "word": " going", "probability": 0.431396484375 }, { "start": 3621.88, "end": 3621.9, "word": " to", "probability": 0.90478515625 }, { "start": 3621.9, "end": 3622.02, "word": " go", "probability": 0.8818359375 }, { "start": 3622.02, "end": 3622.38, "word": " ahead", "probability": 0.8505859375 }, { "start": 3622.38, "end": 3622.6, "word": " and", "probability": 0.89208984375 }, { "start": 3622.6, "end": 3622.7, "word": " do", "probability": 0.91015625 }, { "start": 3622.7, "end": 3622.84, "word": " the", "probability": 0.80810546875 }, { "start": 3622.84, "end": 3623.0, "word": " same", "probability": 0.81982421875 }, { "start": 3623.0, "end": 3623.2, "word": " thing", "probability": 0.814453125 }, { "start": 3623.2, "end": 3623.42, "word": " for", "probability": 0.90185546875 }, { "start": 3623.42, "end": 3623.98, "word": " 6b", "probability": 0.80810546875 }, { "start": 3623.98, "end": 3624.4, "word": ",", "probability": 0.96826171875 }, { "start": 3624.4, "end": 3625.12, "word": " 6c", "probability": 0.996337890625 }, { "start": 3625.12, "end": 3625.24, "word": ",", "probability": 0.68115234375 }, { "start": 3625.24, "end": 3625.42, "word": " and", "probability": 0.8916015625 }, { "start": 3625.42, "end": 3625.92, "word": " 6d", "probability": 0.990966796875 }, { "start": 3625.92, "end": 3626.44, "word": ".", "probability": 0.94677734375 } ] }, { "id": 963, "seek": 353642, "start": 3627.46, "end": 3630.46, "text": " One of the beautiful things, and I'm going to show you this", "tokens": [ 51264, 1485, 295, 264, 2238, 721, 11, 293, 286, 478, 516, 281, 855, 291, 341, 51464 ], "temperature": 0.0, "avg_logprob": -0.19228516127914191, "compression_ratio": 1.5941176470588236, "no_speech_prob": 0.115966796875, "words": [ { "start": 3627.46, "end": 3627.98, "word": " One", "probability": 0.890625 }, { "start": 3627.98, "end": 3628.08, "word": " of", "probability": 0.9013671875 }, { "start": 3628.08, "end": 3628.18, "word": " the", "probability": 0.82080078125 }, { "start": 3628.18, "end": 3628.5, "word": " beautiful", "probability": 0.9189453125 }, { "start": 3628.5, "end": 3629.04, "word": " things", "probability": 0.74609375 }, { "start": 3629.04, "end": 3629.2, "word": ",", "probability": 0.69091796875 }, { "start": 3629.2, "end": 3629.38, "word": " and", "probability": 0.89013671875 }, { "start": 3629.38, "end": 3629.62, "word": " I'm", "probability": 0.994140625 }, { "start": 3629.62, "end": 3629.76, "word": " going", "probability": 0.86279296875 }, { "start": 3629.76, "end": 3629.9, "word": " to", "probability": 0.9091796875 }, { "start": 3629.9, "end": 3630.06, "word": " show", "probability": 0.8837890625 }, { "start": 3630.06, "end": 3630.22, "word": " you", "probability": 0.89208984375 }, { "start": 3630.22, "end": 3630.46, "word": " this", "probability": 0.87548828125 } ] }, { "id": 964, "seek": 353642, "start": 3630.46, "end": 3636.8, "text": " just as a super quick and easy way of going about and doing things,", "tokens": [ 51464, 445, 382, 257, 1687, 1702, 293, 1858, 636, 295, 516, 466, 293, 884, 721, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.19228516127914191, "compression_ratio": 1.5941176470588236, "no_speech_prob": 0.115966796875, "words": [ { "start": 3630.46, "end": 3630.82, "word": " just", "probability": 0.74658203125 }, { "start": 3630.82, "end": 3631.16, "word": " as", "probability": 0.87939453125 }, { "start": 3631.48, "end": 3631.8, "word": " a super", "probability": 0.89111328125 }, { "start": 3631.8, "end": 3632.26, "word": " quick", "probability": 0.86376953125 }, { "start": 3632.26, "end": 3632.4, "word": " and", "probability": 0.88671875 }, { "start": 3632.4, "end": 3632.66, "word": " easy", "probability": 0.81494140625 }, { "start": 3632.66, "end": 3633.18, "word": " way", "probability": 0.90380859375 }, { "start": 3633.18, "end": 3634.24, "word": " of", "probability": 0.89306640625 }, { "start": 3634.24, "end": 3635.18, "word": " going", "probability": 0.8486328125 }, { "start": 3635.18, "end": 3635.44, "word": " about", "probability": 0.82373046875 }, { "start": 3635.44, "end": 3635.62, "word": " and", "probability": 0.456298828125 }, { "start": 3635.62, "end": 3635.92, "word": " doing", "probability": 0.91796875 }, { "start": 3635.92, "end": 3636.48, "word": " things", "probability": 0.73974609375 }, { "start": 3636.48, "end": 3636.8, "word": ",", "probability": 0.63427734375 } ] }, { "id": 965, "seek": 356494, "start": 3636.8, "end": 3639.54, "text": " is I'm just going to copy the code that I'd already written.", "tokens": [ 50364, 307, 286, 478, 445, 516, 281, 5055, 264, 3089, 300, 286, 1116, 1217, 3720, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.2287289863374053, "compression_ratio": 1.5889328063241106, "no_speech_prob": 0.0023975372314453125, "words": [ { "start": 3636.8, "end": 3637.02, "word": " is", "probability": 0.17578125 }, { "start": 3637.02, "end": 3637.1, "word": " I'm", "probability": 0.89208984375 }, { "start": 3637.1, "end": 3637.24, "word": " just", "probability": 0.86328125 }, { "start": 3637.24, "end": 3637.38, "word": " going", "probability": 0.64404296875 }, { "start": 3637.38, "end": 3637.52, "word": " to", "probability": 0.91064453125 }, { "start": 3637.52, "end": 3637.8, "word": " copy", "probability": 0.81640625 }, { "start": 3637.8, "end": 3638.0, "word": " the", "probability": 0.8154296875 }, { "start": 3638.0, "end": 3638.2, "word": " code", "probability": 0.80712890625 }, { "start": 3638.2, "end": 3638.34, "word": " that", "probability": 0.87158203125 }, { "start": 3638.34, "end": 3638.5, "word": " I'd", "probability": 0.845458984375 }, { "start": 3638.5, "end": 3638.86, "word": " already", "probability": 0.84228515625 }, { "start": 3638.86, "end": 3639.16, "word": " written", "probability": 0.8720703125 }, { "start": 3639.16, "end": 3639.54, "word": ".", "probability": 0.6640625 } ] }, { "id": 966, "seek": 356494, "start": 3639.54, "end": 3642.36, "text": " This is why machine learning is awesome,", "tokens": [ 50514, 639, 307, 983, 3479, 2539, 307, 3476, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.2287289863374053, "compression_ratio": 1.5889328063241106, "no_speech_prob": 0.0023975372314453125, "words": [ { "start": 3639.54, "end": 3639.68, "word": " This", "probability": 0.77587890625 }, { "start": 3639.68, "end": 3639.82, "word": " is", "probability": 0.90625 }, { "start": 3639.82, "end": 3640.04, "word": " why", "probability": 0.76416015625 }, { "start": 3640.04, "end": 3640.52, "word": " machine", "probability": 0.67138671875 }, { "start": 3640.52, "end": 3640.8, "word": " learning", "probability": 0.8525390625 }, { "start": 3640.8, "end": 3641.2, "word": " is", "probability": 0.90380859375 }, { "start": 3641.2, "end": 3641.88, "word": " awesome", "probability": 0.81494140625 }, { "start": 3641.88, "end": 3642.36, "word": ",", "probability": 0.17431640625 } ] }, { "id": 967, "seek": 356494, "start": 3642.36, "end": 3645.74, "text": " and very different from programming normal algorithms,", "tokens": [ 50664, 293, 588, 819, 490, 9410, 2710, 14642, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.2287289863374053, "compression_ratio": 1.5889328063241106, "no_speech_prob": 0.0023975372314453125, "words": [ { "start": 3642.36, "end": 3642.64, "word": " and", "probability": 0.89794921875 }, { "start": 3642.64, "end": 3642.84, "word": " very", "probability": 0.7236328125 }, { "start": 3642.84, "end": 3643.16, "word": " different", "probability": 0.68798828125 }, { "start": 3643.16, "end": 3643.86, "word": " from", "probability": 0.8154296875 }, { "start": 3643.86, "end": 3644.54, "word": " programming", "probability": 0.7236328125 }, { "start": 3644.54, "end": 3644.98, "word": " normal", "probability": 0.75439453125 }, { "start": 3644.98, "end": 3645.46, "word": " algorithms", "probability": 0.8798828125 }, { "start": 3645.46, "end": 3645.74, "word": ",", "probability": 0.48291015625 } ] }, { "id": 968, "seek": 356494, "start": 3645.74, "end": 3649.24, "text": " is all we need to do is just change these tf.ids to count,", "tokens": [ 50814, 307, 439, 321, 643, 281, 360, 307, 445, 1319, 613, 256, 69, 13, 3742, 281, 1207, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.2287289863374053, "compression_ratio": 1.5889328063241106, "no_speech_prob": 0.0023975372314453125, "words": [ { "start": 3645.74, "end": 3645.84, "word": " is", "probability": 0.7666015625 }, { "start": 3645.84, "end": 3646.0, "word": " all", "probability": 0.88525390625 }, { "start": 3646.0, "end": 3646.1, "word": " we", "probability": 0.90380859375 }, { "start": 3646.1, "end": 3646.22, "word": " need", "probability": 0.818359375 }, { "start": 3646.22, "end": 3646.3, "word": " to", "probability": 0.90966796875 }, { "start": 3646.3, "end": 3646.42, "word": " do", "probability": 0.90966796875 }, { "start": 3646.42, "end": 3646.52, "word": " is", "probability": 0.90234375 }, { "start": 3646.52, "end": 3646.72, "word": " just", "probability": 0.85986328125 }, { "start": 3646.72, "end": 3647.26, "word": " change", "probability": 0.84228515625 }, { "start": 3647.26, "end": 3647.52, "word": " these", "probability": 0.72802734375 }, { "start": 3647.52, "end": 3647.84, "word": " tf", "probability": 0.764404296875 }, { "start": 3647.84, "end": 3648.0, "word": ".ids", "probability": 0.6329345703125 }, { "start": 3648.0, "end": 3648.5, "word": " to", "probability": 0.89111328125 }, { "start": 3648.5, "end": 3649.04, "word": " count", "probability": 0.603515625 }, { "start": 3649.04, "end": 3649.24, "word": ",", "probability": 0.58837890625 } ] }, { "id": 969, "seek": 356494, "start": 3649.24, "end": 3651.74, "text": " and then everything else is the same.", "tokens": [ 51014, 293, 550, 1203, 1646, 307, 264, 912, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.2287289863374053, "compression_ratio": 1.5889328063241106, "no_speech_prob": 0.0023975372314453125, "words": [ { "start": 3649.24, "end": 3649.52, "word": " and", "probability": 0.5126953125 }, { "start": 3649.52, "end": 3649.66, "word": " then", "probability": 0.7216796875 }, { "start": 3649.66, "end": 3649.94, "word": " everything", "probability": 0.87109375 }, { "start": 3649.94, "end": 3650.22, "word": " else", "probability": 0.84326171875 }, { "start": 3650.22, "end": 3650.42, "word": " is", "probability": 0.904296875 }, { "start": 3650.42, "end": 3650.76, "word": " the", "probability": 0.81591796875 }, { "start": 3650.76, "end": 3651.18, "word": " same", "probability": 0.81494140625 }, { "start": 3651.18, "end": 3651.74, "word": ".", "probability": 0.564453125 } ] }, { "id": 970, "seek": 356494, "start": 3652.88, "end": 3657.82, "text": " So we use mnbcount to define our multinomial Naive Bayesian,", "tokens": [ 51164, 407, 321, 764, 275, 77, 65, 26050, 281, 6964, 527, 45872, 47429, 6056, 488, 7840, 42434, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.2287289863374053, "compression_ratio": 1.5889328063241106, "no_speech_prob": 0.0023975372314453125, "words": [ { "start": 3652.88, "end": 3653.44, "word": " So", "probability": 0.5146484375 }, { "start": 3653.44, "end": 3654.0, "word": " we", "probability": 0.80322265625 }, { "start": 3654.0, "end": 3654.3, "word": " use", "probability": 0.81201171875 }, { "start": 3654.3, "end": 3655.14, "word": " mnbcount", "probability": 0.750732421875 }, { "start": 3655.14, "end": 3655.58, "word": " to", "probability": 0.87646484375 }, { "start": 3655.58, "end": 3655.98, "word": " define", "probability": 0.90625 }, { "start": 3655.98, "end": 3656.12, "word": " our", "probability": 0.8056640625 }, { "start": 3656.12, "end": 3656.64, "word": " multinomial", "probability": 0.960693359375 }, { "start": 3656.64, "end": 3656.98, "word": " Naive", "probability": 0.56005859375 }, { "start": 3656.98, "end": 3657.38, "word": " Bayesian", "probability": 0.9189453125 }, { "start": 3657.38, "end": 3657.82, "word": ",", "probability": 0.66162109375 } ] }, { "id": 971, "seek": 356494, "start": 3657.82, "end": 3662.14, "text": " as we have been asked of us here in 6b.", "tokens": [ 51414, 382, 321, 362, 668, 2351, 295, 505, 510, 294, 1386, 65, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.2287289863374053, "compression_ratio": 1.5889328063241106, "no_speech_prob": 0.0023975372314453125, "words": [ { "start": 3657.82, "end": 3658.0, "word": " as", "probability": 0.89501953125 }, { "start": 3658.0, "end": 3658.12, "word": " we", "probability": 0.90380859375 }, { "start": 3658.12, "end": 3658.5, "word": " have", "probability": 0.87451171875 }, { "start": 3658.5, "end": 3659.82, "word": " been", "probability": 0.81787109375 }, { "start": 3659.82, "end": 3660.16, "word": " asked", "probability": 0.732421875 }, { "start": 3660.16, "end": 3660.34, "word": " of", "probability": 0.89501953125 }, { "start": 3660.34, "end": 3660.5, "word": " us", "probability": 0.908203125 }, { "start": 3660.5, "end": 3660.8, "word": " here", "probability": 0.798828125 }, { "start": 3660.8, "end": 3661.12, "word": " in", "probability": 0.8896484375 }, { "start": 3661.12, "end": 3661.58, "word": " 6b", "probability": 0.700927734375 }, { "start": 3661.58, "end": 3662.14, "word": ".", "probability": 0.6767578125 } ] }, { "id": 972, "seek": 356494, "start": 3663.08, "end": 3665.32, "text": " mnbcount.fit, and we're going to use our countX", "tokens": [ 51664, 275, 77, 65, 26050, 13, 6845, 11, 293, 321, 434, 516, 281, 764, 527, 1207, 55, 51814 ], "temperature": 0.0, "avg_logprob": -0.2287289863374053, "compression_ratio": 1.5889328063241106, "no_speech_prob": 0.0023975372314453125, "words": [ { "start": 3663.08, "end": 3663.64, "word": " mnbcount", "probability": 0.884765625 }, { "start": 3663.64, "end": 3664.12, "word": ".fit", "probability": 0.939453125 }, { "start": 3664.12, "end": 3664.16, "word": ",", "probability": 0.57373046875 }, { "start": 3664.16, "end": 3664.24, "word": " and", "probability": 0.82421875 }, { "start": 3664.24, "end": 3664.32, "word": " we're", "probability": 0.9267578125 }, { "start": 3664.32, "end": 3664.4, "word": " going", "probability": 0.76416015625 }, { "start": 3664.4, "end": 3664.42, "word": " to", "probability": 0.90576171875 }, { "start": 3664.42, "end": 3664.58, "word": " use", "probability": 0.84326171875 }, { "start": 3664.58, "end": 3664.7, "word": " our", "probability": 0.81689453125 }, { "start": 3664.7, "end": 3665.32, "word": " countX", "probability": 0.52490234375 } ] }, { "id": 973, "seek": 359288, "start": 3665.32, "end": 3667.56, "text": " because that's how it's been vectorized.", "tokens": [ 50364, 570, 300, 311, 577, 309, 311, 668, 8062, 1602, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.20774873041984987, "compression_ratio": 1.7142857142857142, "no_speech_prob": 0.00016868114471435547, "words": [ { "start": 3665.32, "end": 3665.6, "word": " because", "probability": 0.70166015625 }, { "start": 3665.6, "end": 3665.92, "word": " that's", "probability": 0.9296875 }, { "start": 3665.92, "end": 3666.0, "word": " how", "probability": 0.89501953125 }, { "start": 3666.0, "end": 3666.14, "word": " it's", "probability": 0.943603515625 }, { "start": 3666.14, "end": 3666.28, "word": " been", "probability": 0.833984375 }, { "start": 3666.28, "end": 3666.88, "word": " vectorized", "probability": 0.91259765625 }, { "start": 3666.88, "end": 3667.56, "word": ".", "probability": 0.91552734375 } ] }, { "id": 974, "seek": 359288, "start": 3668.12, "end": 3673.98, "text": " We're going to change our score mnbcount using mnbcount.score.", "tokens": [ 50514, 492, 434, 516, 281, 1319, 527, 6175, 275, 77, 65, 26050, 1228, 275, 77, 65, 26050, 13, 4417, 418, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.20774873041984987, "compression_ratio": 1.7142857142857142, "no_speech_prob": 0.00016868114471435547, "words": [ { "start": 3668.12, "end": 3668.64, "word": " We're", "probability": 0.917236328125 }, { "start": 3668.64, "end": 3668.68, "word": " going", "probability": 0.7421875 }, { "start": 3668.68, "end": 3668.74, "word": " to", "probability": 0.90576171875 }, { "start": 3668.74, "end": 3668.96, "word": " change", "probability": 0.82958984375 }, { "start": 3668.96, "end": 3669.18, "word": " our", "probability": 0.8369140625 }, { "start": 3669.18, "end": 3669.66, "word": " score", "probability": 0.67626953125 }, { "start": 3669.66, "end": 3670.42, "word": " mnbcount", "probability": 0.6119384765625 }, { "start": 3670.42, "end": 3671.5, "word": " using", "probability": 0.8330078125 }, { "start": 3671.5, "end": 3672.78, "word": " mnbcount", "probability": 0.906494140625 }, { "start": 3672.78, "end": 3673.46, "word": ".score", "probability": 0.8587239583333334 }, { "start": 3673.46, "end": 3673.98, "word": ".", "probability": 0.73486328125 } ] }, { "id": 975, "seek": 359288, "start": 3673.98, "end": 3680.74, "text": " We're going to change our tf.idsx to testCountX,", "tokens": [ 50814, 492, 434, 516, 281, 1319, 527, 256, 69, 13, 3742, 87, 281, 1500, 34, 792, 55, 11, 51164 ], "temperature": 0.0, "avg_logprob": -0.20774873041984987, "compression_ratio": 1.7142857142857142, "no_speech_prob": 0.00016868114471435547, "words": [ { "start": 3673.98, "end": 3674.4, "word": " We're", "probability": 0.924560546875 }, { "start": 3674.4, "end": 3674.42, "word": " going", "probability": 0.8427734375 }, { "start": 3674.42, "end": 3674.5, "word": " to", "probability": 0.90625 }, { "start": 3674.5, "end": 3674.76, "word": " change", "probability": 0.83203125 }, { "start": 3674.76, "end": 3675.0, "word": " our", "probability": 0.8056640625 }, { "start": 3675.0, "end": 3677.08, "word": " tf", "probability": 0.610595703125 }, { "start": 3677.08, "end": 3677.6, "word": ".idsx", "probability": 0.3628959655761719 }, { "start": 3677.6, "end": 3677.98, "word": " to", "probability": 0.8876953125 }, { "start": 3677.98, "end": 3680.02, "word": " testCountX", "probability": 0.5261306762695312 }, { "start": 3680.02, "end": 3680.74, "word": ",", "probability": 0.3583984375 } ] }, { "id": 976, "seek": 359288, "start": 3681.32, "end": 3685.58, "text": " and then likewise kind of all throughout here.", "tokens": [ 51164, 293, 550, 32407, 733, 295, 439, 3710, 510, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.20774873041984987, "compression_ratio": 1.7142857142857142, "no_speech_prob": 0.00016868114471435547, "words": [ { "start": 3681.32, "end": 3681.74, "word": " and", "probability": 0.8701171875 }, { "start": 3681.74, "end": 3681.92, "word": " then", "probability": 0.75 }, { "start": 3681.92, "end": 3682.46, "word": " likewise", "probability": 0.7705078125 }, { "start": 3682.46, "end": 3683.24, "word": " kind", "probability": 0.4404296875 }, { "start": 3683.24, "end": 3683.42, "word": " of", "probability": 0.900390625 }, { "start": 3683.42, "end": 3683.78, "word": " all", "probability": 0.88427734375 }, { "start": 3683.78, "end": 3684.46, "word": " throughout", "probability": 0.78955078125 }, { "start": 3684.46, "end": 3684.9, "word": " here", "probability": 0.81982421875 }, { "start": 3684.9, "end": 3685.58, "word": ".", "probability": 0.98193359375 } ] }, { "id": 977, "seek": 359288, "start": 3689.31, "end": 3691.31, "text": " TestLabels is going to stay the same,", "tokens": [ 51464, 9279, 43, 455, 1625, 307, 516, 281, 1754, 264, 912, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.20774873041984987, "compression_ratio": 1.7142857142857142, "no_speech_prob": 0.00016868114471435547, "words": [ { "start": 3689.31, "end": 3689.99, "word": " TestLabels", "probability": 0.6649169921875 }, { "start": 3689.99, "end": 3690.11, "word": " is", "probability": 0.884765625 }, { "start": 3690.11, "end": 3690.25, "word": " going", "probability": 0.8515625 }, { "start": 3690.25, "end": 3690.39, "word": " to", "probability": 0.90673828125 }, { "start": 3690.39, "end": 3690.53, "word": " stay", "probability": 0.9140625 }, { "start": 3690.53, "end": 3690.71, "word": " the", "probability": 0.81884765625 }, { "start": 3690.71, "end": 3691.07, "word": " same", "probability": 0.8154296875 }, { "start": 3691.07, "end": 3691.31, "word": ",", "probability": 0.411376953125 } ] }, { "id": 978, "seek": 359288, "start": 3691.31, "end": 3695.01, "text": " predictions is going to change because it is no longer predictions.tf.ids,", "tokens": [ 51564, 21264, 307, 516, 281, 1319, 570, 309, 307, 572, 2854, 21264, 13, 83, 69, 13, 3742, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.20774873041984987, "compression_ratio": 1.7142857142857142, "no_speech_prob": 0.00016868114471435547, "words": [ { "start": 3691.31, "end": 3691.67, "word": " predictions", "probability": 0.591796875 }, { "start": 3691.67, "end": 3692.01, "word": " is", "probability": 0.8662109375 }, { "start": 3692.01, "end": 3692.21, "word": " going", "probability": 0.85693359375 }, { "start": 3692.21, "end": 3692.41, "word": " to", "probability": 0.904296875 }, { "start": 3692.41, "end": 3692.75, "word": " change", "probability": 0.8408203125 }, { "start": 3692.75, "end": 3693.01, "word": " because", "probability": 0.67626953125 }, { "start": 3693.01, "end": 3693.13, "word": " it", "probability": 0.88525390625 }, { "start": 3693.13, "end": 3693.25, "word": " is", "probability": 0.8818359375 }, { "start": 3693.25, "end": 3693.39, "word": " no", "probability": 0.91748046875 }, { "start": 3693.39, "end": 3693.79, "word": " longer", "probability": 0.83349609375 }, { "start": 3693.79, "end": 3694.33, "word": " predictions", "probability": 0.78125 }, { "start": 3694.33, "end": 3694.67, "word": ".tf", "probability": 0.76611328125 }, { "start": 3694.67, "end": 3694.83, "word": ".ids", "probability": 0.760986328125 }, { "start": 3694.83, "end": 3695.01, "word": ",", "probability": 0.09356689453125 } ] }, { "id": 979, "seek": 362034, "start": 3695.01, "end": 3696.45, "text": " it is predictionsCount,", "tokens": [ 50364, 309, 307, 21264, 34, 792, 11, 50464 ], "temperature": 0.0, "avg_logprob": -0.22273935567825398, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0015010833740234375, "words": [ { "start": 3695.01, "end": 3695.11, "word": " it", "probability": 0.09130859375 }, { "start": 3695.11, "end": 3695.21, "word": " is", "probability": 0.822265625 }, { "start": 3695.21, "end": 3696.03, "word": " predictionsCount", "probability": 0.5478006998697916 }, { "start": 3696.03, "end": 3696.45, "word": ",", "probability": 0.35107421875 } ] }, { "id": 980, "seek": 362034, "start": 3696.81, "end": 3701.31, "text": " and then we have our confusion matrix and our classification report.", "tokens": [ 50464, 293, 550, 321, 362, 527, 15075, 8141, 293, 527, 21538, 2275, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.22273935567825398, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0015010833740234375, "words": [ { "start": 3696.81, "end": 3697.15, "word": " and", "probability": 0.86279296875 }, { "start": 3697.15, "end": 3697.35, "word": " then", "probability": 0.7294921875 }, { "start": 3697.35, "end": 3697.55, "word": " we", "probability": 0.8984375 }, { "start": 3697.55, "end": 3697.95, "word": " have", "probability": 0.8857421875 }, { "start": 3697.95, "end": 3698.45, "word": " our", "probability": 0.8251953125 }, { "start": 3698.45, "end": 3699.05, "word": " confusion", "probability": 0.80908203125 }, { "start": 3699.05, "end": 3699.39, "word": " matrix", "probability": 0.79296875 }, { "start": 3699.39, "end": 3699.63, "word": " and", "probability": 0.7646484375 }, { "start": 3699.63, "end": 3699.75, "word": " our", "probability": 0.8212890625 }, { "start": 3699.75, "end": 3700.15, "word": " classification", "probability": 0.93359375 }, { "start": 3700.15, "end": 3700.63, "word": " report", "probability": 0.78759765625 }, { "start": 3700.63, "end": 3701.31, "word": ".", "probability": 0.98974609375 } ] }, { "id": 981, "seek": 362034, "start": 3701.67, "end": 3703.15, "text": " So just to go over it one more time,", "tokens": [ 50664, 407, 445, 281, 352, 670, 309, 472, 544, 565, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.22273935567825398, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0015010833740234375, "words": [ { "start": 3701.67, "end": 3701.93, "word": " So", "probability": 0.82421875 }, { "start": 3701.93, "end": 3702.19, "word": " just", "probability": 0.708984375 }, { "start": 3702.19, "end": 3702.27, "word": " to", "probability": 0.77099609375 }, { "start": 3702.27, "end": 3702.35, "word": " go", "probability": 0.89453125 }, { "start": 3702.35, "end": 3702.47, "word": " over", "probability": 0.88720703125 }, { "start": 3702.47, "end": 3702.55, "word": " it", "probability": 0.64208984375 }, { "start": 3702.55, "end": 3702.65, "word": " one", "probability": 0.818359375 }, { "start": 3702.65, "end": 3702.77, "word": " more", "probability": 0.87744140625 }, { "start": 3702.77, "end": 3703.07, "word": " time", "probability": 0.80615234375 }, { "start": 3703.07, "end": 3703.15, "word": ",", "probability": 0.86669921875 } ] }, { "id": 982, "seek": 362034, "start": 3703.15, "end": 3706.59, "text": " we define our multinomial Naive Bayesian constructor,", "tokens": [ 50764, 321, 6964, 527, 45872, 47429, 6056, 488, 7840, 42434, 47479, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.22273935567825398, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0015010833740234375, "words": [ { "start": 3703.15, "end": 3703.35, "word": " we", "probability": 0.90283203125 }, { "start": 3703.35, "end": 3703.87, "word": " define", "probability": 0.8994140625 }, { "start": 3703.87, "end": 3704.23, "word": " our", "probability": 0.80712890625 }, { "start": 3704.23, "end": 3704.77, "word": " multinomial", "probability": 0.9150390625 }, { "start": 3704.77, "end": 3705.09, "word": " Naive", "probability": 0.655029296875 }, { "start": 3705.09, "end": 3705.45, "word": " Bayesian", "probability": 0.8837890625 }, { "start": 3705.45, "end": 3706.25, "word": " constructor", "probability": 0.64013671875 }, { "start": 3706.25, "end": 3706.59, "word": ",", "probability": 0.6572265625 } ] }, { "id": 983, "seek": 362034, "start": 3706.59, "end": 3710.67, "text": " we train it using the fit function and the count vectorizer,", "tokens": [ 50914, 321, 3847, 309, 1228, 264, 3318, 2445, 293, 264, 1207, 8062, 6545, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.22273935567825398, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0015010833740234375, "words": [ { "start": 3706.59, "end": 3706.77, "word": " we", "probability": 0.90478515625 }, { "start": 3706.77, "end": 3707.11, "word": " train", "probability": 0.78515625 }, { "start": 3707.11, "end": 3707.23, "word": " it", "probability": 0.90087890625 }, { "start": 3707.23, "end": 3707.47, "word": " using", "probability": 0.81005859375 }, { "start": 3707.47, "end": 3707.71, "word": " the", "probability": 0.81298828125 }, { "start": 3707.71, "end": 3707.91, "word": " fit", "probability": 0.78076171875 }, { "start": 3707.91, "end": 3708.35, "word": " function", "probability": 0.8623046875 }, { "start": 3708.35, "end": 3708.73, "word": " and", "probability": 0.79833984375 }, { "start": 3708.73, "end": 3708.99, "word": " the", "probability": 0.8076171875 }, { "start": 3708.99, "end": 3709.59, "word": " count", "probability": 0.740234375 }, { "start": 3709.59, "end": 3710.47, "word": " vectorizer", "probability": 0.9140625 }, { "start": 3710.47, "end": 3710.67, "word": ",", "probability": 0.9453125 } ] }, { "id": 984, "seek": 362034, "start": 3710.67, "end": 3713.41, "text": " our testing data, our training data.", "tokens": [ 51114, 527, 4997, 1412, 11, 527, 3097, 1412, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.22273935567825398, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0015010833740234375, "words": [ { "start": 3710.67, "end": 3710.81, "word": " our", "probability": 0.8076171875 }, { "start": 3710.81, "end": 3711.19, "word": " testing", "probability": 0.6650390625 }, { "start": 3711.19, "end": 3711.55, "word": " data", "probability": 0.83056640625 }, { "start": 3711.55, "end": 3711.95, "word": ",", "probability": 0.58984375 }, { "start": 3711.95, "end": 3712.07, "word": " our", "probability": 0.462890625 }, { "start": 3712.07, "end": 3712.39, "word": " training", "probability": 0.80419921875 }, { "start": 3712.39, "end": 3712.73, "word": " data", "probability": 0.81298828125 }, { "start": 3712.73, "end": 3713.41, "word": ".", "probability": 0.7587890625 } ] }, { "id": 985, "seek": 362034, "start": 3714.25, "end": 3722.47, "text": " We develop our score off of our testCount data using our testLabels,", "tokens": [ 51314, 492, 1499, 527, 6175, 766, 295, 527, 1500, 34, 792, 1412, 1228, 527, 1500, 43, 455, 1625, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.22273935567825398, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0015010833740234375, "words": [ { "start": 3714.25, "end": 3714.93, "word": " We", "probability": 0.9033203125 }, { "start": 3714.93, "end": 3715.23, "word": " develop", "probability": 0.62353515625 }, { "start": 3715.23, "end": 3715.49, "word": " our", "probability": 0.8193359375 }, { "start": 3715.49, "end": 3715.95, "word": " score", "probability": 0.814453125 }, { "start": 3715.95, "end": 3716.35, "word": " off", "probability": 0.814453125 }, { "start": 3716.35, "end": 3716.47, "word": " of", "probability": 0.90673828125 }, { "start": 3716.47, "end": 3716.73, "word": " our", "probability": 0.8125 }, { "start": 3716.73, "end": 3718.29, "word": " testCount", "probability": 0.7734375 }, { "start": 3718.29, "end": 3719.43, "word": " data", "probability": 0.841796875 }, { "start": 3719.43, "end": 3720.65, "word": " using", "probability": 0.623046875 }, { "start": 3720.65, "end": 3720.85, "word": " our", "probability": 0.81494140625 }, { "start": 3720.85, "end": 3721.93, "word": " testLabels", "probability": 0.674591064453125 }, { "start": 3721.93, "end": 3722.47, "word": ",", "probability": 0.56787109375 } ] }, { "id": 986, "seek": 364666, "start": 3722.47, "end": 3725.91, "text": " and then we have our predictions,", "tokens": [ 50364, 293, 550, 321, 362, 527, 21264, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.2009191169458277, "compression_ratio": 1.5194174757281553, "no_speech_prob": 0.00638580322265625, "words": [ { "start": 3722.47, "end": 3722.69, "word": " and", "probability": 0.407470703125 }, { "start": 3722.69, "end": 3722.83, "word": " then", "probability": 0.712890625 }, { "start": 3722.83, "end": 3722.99, "word": " we", "probability": 0.90576171875 }, { "start": 3722.99, "end": 3723.29, "word": " have", "probability": 0.8798828125 }, { "start": 3723.29, "end": 3723.83, "word": " our", "probability": 0.806640625 }, { "start": 3723.83, "end": 3724.71, "word": " predictions", "probability": 0.70458984375 }, { "start": 3724.71, "end": 3725.91, "word": ",", "probability": 0.5908203125 } ] }, { "id": 987, "seek": 364666, "start": 3725.91, "end": 3728.65, "text": " we have our confusion matrix,", "tokens": [ 50514, 321, 362, 527, 15075, 8141, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.2009191169458277, "compression_ratio": 1.5194174757281553, "no_speech_prob": 0.00638580322265625, "words": [ { "start": 3725.91, "end": 3726.15, "word": " we", "probability": 0.89990234375 }, { "start": 3726.15, "end": 3726.45, "word": " have", "probability": 0.88037109375 }, { "start": 3726.45, "end": 3727.05, "word": " our", "probability": 0.82080078125 }, { "start": 3727.05, "end": 3727.97, "word": " confusion", "probability": 0.8369140625 }, { "start": 3727.97, "end": 3728.33, "word": " matrix", "probability": 0.875 }, { "start": 3728.33, "end": 3728.65, "word": ",", "probability": 0.64697265625 } ] }, { "id": 988, "seek": 364666, "start": 3728.65, "end": 3730.35, "text": " and our classification report.", "tokens": [ 50664, 293, 527, 21538, 2275, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.2009191169458277, "compression_ratio": 1.5194174757281553, "no_speech_prob": 0.00638580322265625, "words": [ { "start": 3728.65, "end": 3728.91, "word": " and", "probability": 0.8984375 }, { "start": 3728.91, "end": 3729.13, "word": " our", "probability": 0.82373046875 }, { "start": 3729.13, "end": 3729.71, "word": " classification", "probability": 0.94482421875 }, { "start": 3729.71, "end": 3730.15, "word": " report", "probability": 0.74951171875 }, { "start": 3730.15, "end": 3730.35, "word": ".", "probability": 0.85107421875 } ] }, { "id": 989, "seek": 364666, "start": 3730.35, "end": 3732.91, "text": " So I'm going to let this sit for just a little bit", "tokens": [ 50764, 407, 286, 478, 516, 281, 718, 341, 1394, 337, 445, 257, 707, 857, 50864 ], "temperature": 0.0, "avg_logprob": -0.2009191169458277, "compression_ratio": 1.5194174757281553, "no_speech_prob": 0.00638580322265625, "words": [ { "start": 3730.35, "end": 3730.41, "word": " So", "probability": 0.76708984375 }, { "start": 3730.41, "end": 3730.65, "word": " I'm", "probability": 0.900634765625 }, { "start": 3730.65, "end": 3730.67, "word": " going", "probability": 0.303466796875 }, { "start": 3730.67, "end": 3730.69, "word": " to", "probability": 0.89990234375 }, { "start": 3730.69, "end": 3730.87, "word": " let", "probability": 0.88623046875 }, { "start": 3730.87, "end": 3731.09, "word": " this", "probability": 0.8779296875 }, { "start": 3731.09, "end": 3731.37, "word": " sit", "probability": 0.890625 }, { "start": 3731.37, "end": 3732.03, "word": " for", "probability": 0.8916015625 }, { "start": 3732.03, "end": 3732.39, "word": " just", "probability": 0.8828125 }, { "start": 3732.55, "end": 3732.65, "word": " a little", "probability": 0.80029296875 }, { "start": 3732.65, "end": 3732.91, "word": " bit", "probability": 0.89208984375 } ] }, { "id": 990, "seek": 364666, "start": 3732.91, "end": 3736.91, "text": " as you guys go through and copy that down.", "tokens": [ 50864, 382, 291, 1074, 352, 807, 293, 5055, 300, 760, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.2009191169458277, "compression_ratio": 1.5194174757281553, "no_speech_prob": 0.00638580322265625, "words": [ { "start": 3732.91, "end": 3733.15, "word": " as", "probability": 0.775390625 }, { "start": 3733.15, "end": 3733.25, "word": " you", "probability": 0.89013671875 }, { "start": 3733.25, "end": 3733.43, "word": " guys", "probability": 0.89306640625 }, { "start": 3733.43, "end": 3733.67, "word": " go", "probability": 0.9033203125 }, { "start": 3733.67, "end": 3734.17, "word": " through", "probability": 0.8037109375 }, { "start": 3734.17, "end": 3735.21, "word": " and", "probability": 0.8701171875 }, { "start": 3735.21, "end": 3735.75, "word": " copy", "probability": 0.791015625 }, { "start": 3735.75, "end": 3735.99, "word": " that", "probability": 0.8837890625 }, { "start": 3735.99, "end": 3736.31, "word": " down", "probability": 0.810546875 }, { "start": 3736.31, "end": 3736.91, "word": ".", "probability": 0.9873046875 } ] }, { "id": 991, "seek": 364666, "start": 3745.81, "end": 3750.29, "text": " What's really cool is in the GitHub repository,", "tokens": [ 51214, 708, 311, 534, 1627, 307, 294, 264, 23331, 25841, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.2009191169458277, "compression_ratio": 1.5194174757281553, "no_speech_prob": 0.00638580322265625, "words": [ { "start": 3745.81, "end": 3746.41, "word": " What's", "probability": 0.90087890625 }, { "start": 3746.41, "end": 3746.57, "word": " really", "probability": 0.77490234375 }, { "start": 3746.57, "end": 3746.93, "word": " cool", "probability": 0.87744140625 }, { "start": 3746.93, "end": 3747.43, "word": " is", "probability": 0.89111328125 }, { "start": 3747.43, "end": 3747.77, "word": " in", "probability": 0.8349609375 }, { "start": 3747.77, "end": 3748.31, "word": " the", "probability": 0.81640625 }, { "start": 3748.31, "end": 3748.63, "word": " GitHub", "probability": 0.501953125 }, { "start": 3748.63, "end": 3749.21, "word": " repository", "probability": 0.85302734375 }, { "start": 3749.21, "end": 3750.29, "word": ",", "probability": 0.47705078125 } ] }, { "id": 992, "seek": 364666, "start": 3750.29, "end": 3752.37, "text": " there are other workbooks.", "tokens": [ 51414, 456, 366, 661, 589, 15170, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.2009191169458277, "compression_ratio": 1.5194174757281553, "no_speech_prob": 0.00638580322265625, "words": [ { "start": 3750.29, "end": 3751.29, "word": " there", "probability": 0.85302734375 }, { "start": 3751.29, "end": 3751.37, "word": " are", "probability": 0.8955078125 }, { "start": 3751.37, "end": 3751.57, "word": " other", "probability": 0.77783203125 }, { "start": 3751.57, "end": 3752.09, "word": " workbooks", "probability": 0.857666015625 }, { "start": 3752.09, "end": 3752.37, "word": ".", "probability": 0.7294921875 } ] }, { "id": 993, "seek": 364666, "start": 3752.37, "end": 3755.63, "text": " So for example, we use the exact same methodology", "tokens": [ 51514, 407, 337, 1365, 11, 321, 764, 264, 1900, 912, 24850, 51714 ], "temperature": 0.0, "avg_logprob": -0.2009191169458277, "compression_ratio": 1.5194174757281553, "no_speech_prob": 0.00638580322265625, "words": [ { "start": 3752.37, "end": 3752.47, "word": " So", "probability": 0.8759765625 }, { "start": 3752.47, "end": 3752.67, "word": " for", "probability": 0.67138671875 }, { "start": 3752.67, "end": 3752.97, "word": " example", "probability": 0.93017578125 }, { "start": 3752.97, "end": 3753.19, "word": ",", "probability": 0.8876953125 }, { "start": 3753.19, "end": 3753.35, "word": " we", "probability": 0.89794921875 }, { "start": 3753.35, "end": 3753.69, "word": " use", "probability": 0.7626953125 }, { "start": 3753.69, "end": 3754.41, "word": " the", "probability": 0.80517578125 }, { "start": 3754.41, "end": 3754.79, "word": " exact", "probability": 0.8779296875 }, { "start": 3754.79, "end": 3755.07, "word": " same", "probability": 0.8056640625 }, { "start": 3755.07, "end": 3755.63, "word": " methodology", "probability": 0.8486328125 } ] }, { "id": 994, "seek": 367664, "start": 3755.63, "end": 3761.01, "text": " to build a malicious URL predictor,", "tokens": [ 50364, 281, 1322, 257, 33496, 12905, 6069, 284, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.19105690451172308, "compression_ratio": 1.6417910447761195, "no_speech_prob": 0.225341796875, "words": [ { "start": 3755.63, "end": 3756.39, "word": " to", "probability": 0.759765625 }, { "start": 3756.39, "end": 3756.89, "word": " build", "probability": 0.87255859375 }, { "start": 3757.55, "end": 3758.69, "word": " a malicious", "probability": 0.8408203125 }, { "start": 3758.69, "end": 3759.39, "word": " URL", "probability": 0.82861328125 }, { "start": 3759.39, "end": 3760.03, "word": " predictor", "probability": 0.84619140625 }, { "start": 3760.03, "end": 3761.01, "word": ",", "probability": 0.3525390625 } ] }, { "id": 995, "seek": 367664, "start": 3761.01, "end": 3765.51, "text": " so things that look like it's possibly part of a botnet.", "tokens": [ 50564, 370, 721, 300, 574, 411, 309, 311, 6264, 644, 295, 257, 10592, 7129, 13, 50814 ], "temperature": 0.0, "avg_logprob": -0.19105690451172308, "compression_ratio": 1.6417910447761195, "no_speech_prob": 0.225341796875, "words": [ { "start": 3761.01, "end": 3761.43, "word": " so", "probability": 0.85107421875 }, { "start": 3761.43, "end": 3761.71, "word": " things", "probability": 0.7177734375 }, { "start": 3761.71, "end": 3761.99, "word": " that", "probability": 0.87158203125 }, { "start": 3761.99, "end": 3762.19, "word": " look", "probability": 0.8916015625 }, { "start": 3762.19, "end": 3762.37, "word": " like", "probability": 0.875 }, { "start": 3762.37, "end": 3762.55, "word": " it's", "probability": 0.945556640625 }, { "start": 3762.55, "end": 3763.01, "word": " possibly", "probability": 0.8955078125 }, { "start": 3763.01, "end": 3763.91, "word": " part", "probability": 0.798828125 }, { "start": 3763.91, "end": 3764.33, "word": " of", "probability": 0.90869140625 }, { "start": 3764.59, "end": 3765.03, "word": " a botnet", "probability": 0.816650390625 }, { "start": 3765.03, "end": 3765.51, "word": ".", "probability": 0.6015625 } ] }, { "id": 996, "seek": 367664, "start": 3767.51, "end": 3769.59, "text": " All of this code is exactly the same.", "tokens": [ 50814, 1057, 295, 341, 3089, 307, 2293, 264, 912, 13, 51014 ], "temperature": 0.0, "avg_logprob": -0.19105690451172308, "compression_ratio": 1.6417910447761195, "no_speech_prob": 0.225341796875, "words": [ { "start": 3767.51, "end": 3767.99, "word": " All", "probability": 0.89697265625 }, { "start": 3767.99, "end": 3768.11, "word": " of", "probability": 0.900390625 }, { "start": 3768.11, "end": 3768.27, "word": " this", "probability": 0.87744140625 }, { "start": 3768.27, "end": 3768.45, "word": " code", "probability": 0.80712890625 }, { "start": 3768.45, "end": 3768.59, "word": " is", "probability": 0.90380859375 }, { "start": 3768.59, "end": 3768.93, "word": " exactly", "probability": 0.77685546875 }, { "start": 3768.93, "end": 3769.15, "word": " the", "probability": 0.81396484375 }, { "start": 3769.15, "end": 3769.35, "word": " same", "probability": 0.81298828125 }, { "start": 3769.35, "end": 3769.59, "word": ".", "probability": 0.9443359375 } ] }, { "id": 997, "seek": 367664, "start": 3769.59, "end": 3771.23, "text": " Once we vectorize our information,", "tokens": [ 51014, 3443, 321, 8062, 1125, 527, 1589, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.19105690451172308, "compression_ratio": 1.6417910447761195, "no_speech_prob": 0.225341796875, "words": [ { "start": 3769.59, "end": 3769.79, "word": " Once", "probability": 0.85546875 }, { "start": 3769.79, "end": 3769.93, "word": " we", "probability": 0.90380859375 }, { "start": 3769.93, "end": 3770.41, "word": " vectorize", "probability": 0.7032470703125 }, { "start": 3770.41, "end": 3770.51, "word": " our", "probability": 0.81640625 }, { "start": 3770.51, "end": 3770.97, "word": " information", "probability": 0.7451171875 }, { "start": 3770.97, "end": 3771.23, "word": ",", "probability": 0.80517578125 } ] }, { "id": 998, "seek": 367664, "start": 3771.23, "end": 3773.23, "text": " we just copy and paste this code in,", "tokens": [ 51114, 321, 445, 5055, 293, 9163, 341, 3089, 294, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.19105690451172308, "compression_ratio": 1.6417910447761195, "no_speech_prob": 0.225341796875, "words": [ { "start": 3771.23, "end": 3771.31, "word": " we", "probability": 0.87158203125 }, { "start": 3771.31, "end": 3771.43, "word": " just", "probability": 0.875 }, { "start": 3771.43, "end": 3771.73, "word": " copy", "probability": 0.8115234375 }, { "start": 3771.73, "end": 3771.89, "word": " and", "probability": 0.888671875 }, { "start": 3771.89, "end": 3772.09, "word": " paste", "probability": 0.76513671875 }, { "start": 3772.09, "end": 3772.41, "word": " this", "probability": 0.876953125 }, { "start": 3772.41, "end": 3772.65, "word": " code", "probability": 0.83056640625 }, { "start": 3772.65, "end": 3772.95, "word": " in", "probability": 0.8974609375 }, { "start": 3772.95, "end": 3773.23, "word": ",", "probability": 0.52978515625 } ] }, { "id": 999, "seek": 367664, "start": 3773.23, "end": 3774.99, "text": " and it does the exact same thing.", "tokens": [ 51214, 293, 309, 775, 264, 1900, 912, 551, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.19105690451172308, "compression_ratio": 1.6417910447761195, "no_speech_prob": 0.225341796875, "words": [ { "start": 3773.23, "end": 3773.35, "word": " and", "probability": 0.8857421875 }, { "start": 3773.35, "end": 3773.45, "word": " it", "probability": 0.90185546875 }, { "start": 3773.45, "end": 3773.59, "word": " does", "probability": 0.7373046875 }, { "start": 3773.59, "end": 3773.75, "word": " the", "probability": 0.8056640625 }, { "start": 3773.75, "end": 3774.01, "word": " exact", "probability": 0.8701171875 }, { "start": 3774.01, "end": 3774.25, "word": " same", "probability": 0.81689453125 }, { "start": 3774.25, "end": 3774.51, "word": " thing", "probability": 0.8134765625 }, { "start": 3774.51, "end": 3774.99, "word": ".", "probability": 0.88037109375 } ] }, { "id": 1000, "seek": 367664, "start": 3775.25, "end": 3777.55, "text": " And so that's the benefit of machine learning,", "tokens": [ 51314, 400, 370, 300, 311, 264, 5121, 295, 3479, 2539, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.19105690451172308, "compression_ratio": 1.6417910447761195, "no_speech_prob": 0.225341796875, "words": [ { "start": 3775.25, "end": 3775.33, "word": " And", "probability": 0.71435546875 }, { "start": 3775.33, "end": 3775.45, "word": " so", "probability": 0.89111328125 }, { "start": 3775.45, "end": 3775.69, "word": " that's", "probability": 0.894775390625 }, { "start": 3775.69, "end": 3775.85, "word": " the", "probability": 0.80859375 }, { "start": 3775.85, "end": 3776.17, "word": " benefit", "probability": 0.71337890625 }, { "start": 3776.17, "end": 3776.91, "word": " of", "probability": 0.90380859375 }, { "start": 3776.91, "end": 3777.19, "word": " machine", "probability": 0.68310546875 }, { "start": 3777.19, "end": 3777.45, "word": " learning", "probability": 0.84423828125 }, { "start": 3777.45, "end": 3777.55, "word": ",", "probability": 0.6044921875 } ] }, { "id": 1001, "seek": 367664, "start": 3777.55, "end": 3778.89, "text": " is it learns from the data itself", "tokens": [ 51414, 307, 309, 27152, 490, 264, 1412, 2564, 51514 ], "temperature": 0.0, "avg_logprob": -0.19105690451172308, "compression_ratio": 1.6417910447761195, "no_speech_prob": 0.225341796875, "words": [ { "start": 3777.55, "end": 3777.63, "word": " is", "probability": 0.79541015625 }, { "start": 3777.63, "end": 3777.73, "word": " it", "probability": 0.86181640625 }, { "start": 3777.73, "end": 3778.03, "word": " learns", "probability": 0.794921875 }, { "start": 3778.03, "end": 3778.19, "word": " from", "probability": 0.81640625 }, { "start": 3778.19, "end": 3778.33, "word": " the", "probability": 0.8154296875 }, { "start": 3778.33, "end": 3778.49, "word": " data", "probability": 0.8134765625 }, { "start": 3778.49, "end": 3778.89, "word": " itself", "probability": 0.7880859375 } ] }, { "id": 1002, "seek": 367664, "start": 3778.89, "end": 3781.11, "text": " instead of us having to manually program,", "tokens": [ 51514, 2602, 295, 505, 1419, 281, 16945, 1461, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.19105690451172308, "compression_ratio": 1.6417910447761195, "no_speech_prob": 0.225341796875, "words": [ { "start": 3778.89, "end": 3779.17, "word": " instead", "probability": 0.491455078125 }, { "start": 3779.17, "end": 3779.35, "word": " of", "probability": 0.9033203125 }, { "start": 3779.35, "end": 3779.51, "word": " us", "probability": 0.888671875 }, { "start": 3779.51, "end": 3779.77, "word": " having", "probability": 0.7802734375 }, { "start": 3779.77, "end": 3779.99, "word": " to", "probability": 0.90869140625 }, { "start": 3779.99, "end": 3780.33, "word": " manually", "probability": 0.8203125 }, { "start": 3780.33, "end": 3780.89, "word": " program", "probability": 0.77001953125 }, { "start": 3780.89, "end": 3781.11, "word": ",", "probability": 0.81591796875 } ] }, { "id": 1003, "seek": 367664, "start": 3781.11, "end": 3782.67, "text": " okay, this solves problem A,", "tokens": [ 51614, 1392, 11, 341, 39890, 1154, 316, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.19105690451172308, "compression_ratio": 1.6417910447761195, "no_speech_prob": 0.225341796875, "words": [ { "start": 3781.11, "end": 3781.25, "word": " okay", "probability": 0.52587890625 }, { "start": 3781.25, "end": 3781.33, "word": ",", "probability": 0.80224609375 }, { "start": 3781.33, "end": 3781.51, "word": " this", "probability": 0.8759765625 }, { "start": 3781.51, "end": 3781.73, "word": " solves", "probability": 0.80517578125 }, { "start": 3781.73, "end": 3782.07, "word": " problem", "probability": 0.748046875 }, { "start": 3782.07, "end": 3782.45, "word": " A", "probability": 0.9541015625 }, { "start": 3782.45, "end": 3782.67, "word": ",", "probability": 0.9228515625 } ] }, { "id": 1004, "seek": 367664, "start": 3782.67, "end": 3785.61, "text": " but now we have to rewrite this to solve problem B.", "tokens": [ 51714, 457, 586, 321, 362, 281, 28132, 341, 281, 5039, 1154, 363, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.19105690451172308, "compression_ratio": 1.6417910447761195, "no_speech_prob": 0.225341796875, "words": [ { "start": 3782.67, "end": 3782.91, "word": " but", "probability": 0.89990234375 }, { "start": 3782.91, "end": 3783.03, "word": " now", "probability": 0.892578125 }, { "start": 3783.03, "end": 3783.13, "word": " we", "probability": 0.89306640625 }, { "start": 3783.13, "end": 3783.23, "word": " have", "probability": 0.88232421875 }, { "start": 3783.23, "end": 3783.37, "word": " to", "probability": 0.908203125 }, { "start": 3783.37, "end": 3783.75, "word": " rewrite", "probability": 0.72021484375 }, { "start": 3783.75, "end": 3784.05, "word": " this", "probability": 0.88330078125 }, { "start": 3784.05, "end": 3784.25, "word": " to", "probability": 0.8994140625 }, { "start": 3784.25, "end": 3784.53, "word": " solve", "probability": 0.837890625 }, { "start": 3784.53, "end": 3784.83, "word": " problem", "probability": 0.7802734375 }, { "start": 3784.83, "end": 3785.15, "word": " B", "probability": 0.9990234375 }, { "start": 3785.15, "end": 3785.61, "word": ".", "probability": 0.9423828125 } ] }, { "id": 1005, "seek": 370128, "start": 3785.61, "end": 3787.45, "text": " It just all does the same thing.", "tokens": [ 50364, 467, 445, 439, 775, 264, 912, 551, 13, 50514 ], "temperature": 0.0, "avg_logprob": -0.18699048443332963, "compression_ratio": 1.3864734299516908, "no_speech_prob": 0.004608154296875, "words": [ { "start": 3785.61, "end": 3785.71, "word": " It", "probability": 0.439453125 }, { "start": 3785.71, "end": 3785.85, "word": " just", "probability": 0.85546875 }, { "start": 3785.85, "end": 3786.13, "word": " all", "probability": 0.90185546875 }, { "start": 3786.13, "end": 3786.35, "word": " does", "probability": 0.93115234375 }, { "start": 3786.35, "end": 3786.55, "word": " the", "probability": 0.8134765625 }, { "start": 3786.55, "end": 3786.73, "word": " same", "probability": 0.8154296875 }, { "start": 3786.73, "end": 3787.01, "word": " thing", "probability": 0.8115234375 }, { "start": 3787.01, "end": 3787.45, "word": ".", "probability": 0.9814453125 } ] }, { "id": 1006, "seek": 370128, "start": 3789.29, "end": 3793.39, "text": " So I am going to go ahead and move on.", "tokens": [ 50514, 407, 286, 669, 516, 281, 352, 2286, 293, 1286, 322, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.18699048443332963, "compression_ratio": 1.3864734299516908, "no_speech_prob": 0.004608154296875, "words": [ { "start": 3789.29, "end": 3789.73, "word": " So", "probability": 0.81396484375 }, { "start": 3789.73, "end": 3790.17, "word": " I", "probability": 0.703125 }, { "start": 3790.17, "end": 3790.41, "word": " am", "probability": 0.89892578125 }, { "start": 3790.41, "end": 3790.63, "word": " going", "probability": 0.853515625 }, { "start": 3790.63, "end": 3790.89, "word": " to", "probability": 0.90380859375 }, { "start": 3790.89, "end": 3791.09, "word": " go", "probability": 0.8955078125 }, { "start": 3791.09, "end": 3791.57, "word": " ahead", "probability": 0.84814453125 }, { "start": 3791.57, "end": 3792.31, "word": " and", "probability": 0.88818359375 }, { "start": 3792.31, "end": 3792.79, "word": " move", "probability": 0.8515625 }, { "start": 3792.79, "end": 3793.27, "word": " on", "probability": 0.90625 }, { "start": 3793.27, "end": 3793.39, "word": ".", "probability": 0.6611328125 } ] }, { "id": 1007, "seek": 370128, "start": 3793.39, "end": 3795.39, "text": " I'm going to press Shift-Enter.", "tokens": [ 50764, 286, 478, 516, 281, 1886, 28304, 12, 16257, 391, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.18699048443332963, "compression_ratio": 1.3864734299516908, "no_speech_prob": 0.004608154296875, "words": [ { "start": 3793.39, "end": 3793.57, "word": " I'm", "probability": 0.938232421875 }, { "start": 3793.57, "end": 3793.57, "word": " going", "probability": 0.18408203125 }, { "start": 3793.57, "end": 3793.63, "word": " to", "probability": 0.9072265625 }, { "start": 3793.63, "end": 3793.87, "word": " press", "probability": 0.69384765625 }, { "start": 3793.87, "end": 3794.45, "word": " Shift", "probability": 0.365966796875 }, { "start": 3794.45, "end": 3794.95, "word": "-Enter", "probability": 0.62506103515625 }, { "start": 3794.95, "end": 3795.39, "word": ".", "probability": 0.91259765625 } ] }, { "id": 1008, "seek": 370128, "start": 3796.71, "end": 3798.71, "text": " And we see that we got a little bit better, right?", "tokens": [ 50914, 400, 321, 536, 300, 321, 658, 257, 707, 857, 1101, 11, 558, 30, 51014 ], "temperature": 0.0, "avg_logprob": -0.18699048443332963, "compression_ratio": 1.3864734299516908, "no_speech_prob": 0.004608154296875, "words": [ { "start": 3796.71, "end": 3796.81, "word": " And", "probability": 0.351806640625 }, { "start": 3796.81, "end": 3796.91, "word": " we", "probability": 0.83203125 }, { "start": 3796.91, "end": 3797.13, "word": " see", "probability": 0.7744140625 }, { "start": 3797.13, "end": 3797.49, "word": " that", "probability": 0.880859375 }, { "start": 3797.49, "end": 3797.59, "word": " we", "probability": 0.89892578125 }, { "start": 3797.59, "end": 3797.69, "word": " got", "probability": 0.87744140625 }, { "start": 3797.77, "end": 3797.87, "word": " a little", "probability": 0.8056640625 }, { "start": 3797.87, "end": 3798.01, "word": " bit", "probability": 0.89892578125 }, { "start": 3798.01, "end": 3798.23, "word": " better", "probability": 0.8193359375 }, { "start": 3798.23, "end": 3798.41, "word": ",", "probability": 0.802734375 }, { "start": 3798.41, "end": 3798.61, "word": " right", "probability": 0.8740234375 }, { "start": 3798.61, "end": 3798.71, "word": "?", "probability": 0.92578125 } ] }, { "id": 1009, "seek": 370128, "start": 3798.71, "end": 3801.09, "text": " We are at a 94% accuracy.", "tokens": [ 51014, 492, 366, 412, 257, 30849, 4, 14170, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.18699048443332963, "compression_ratio": 1.3864734299516908, "no_speech_prob": 0.004608154296875, "words": [ { "start": 3798.71, "end": 3798.89, "word": " We", "probability": 0.89990234375 }, { "start": 3798.89, "end": 3799.05, "word": " are", "probability": 0.89013671875 }, { "start": 3799.05, "end": 3799.23, "word": " at", "probability": 0.857421875 }, { "start": 3799.45, "end": 3799.83, "word": " a 94", "probability": 0.923828125 }, { "start": 3799.83, "end": 3800.19, "word": "%", "probability": 0.93701171875 }, { "start": 3800.19, "end": 3800.65, "word": " accuracy", "probability": 0.705078125 }, { "start": 3800.65, "end": 3801.09, "word": ".", "probability": 0.98876953125 } ] }, { "id": 1010, "seek": 370128, "start": 3801.63, "end": 3807.03, "text": " It thinks that some of our ham emails are still spam,", "tokens": [ 51164, 467, 7309, 300, 512, 295, 527, 7852, 12524, 366, 920, 24028, 11, 51414 ], "temperature": 0.0, "avg_logprob": -0.18699048443332963, "compression_ratio": 1.3864734299516908, "no_speech_prob": 0.004608154296875, "words": [ { "start": 3801.63, "end": 3801.73, "word": " It", "probability": 0.90576171875 }, { "start": 3801.73, "end": 3802.25, "word": " thinks", "probability": 0.74609375 }, { "start": 3802.25, "end": 3802.91, "word": " that", "probability": 0.8798828125 }, { "start": 3802.91, "end": 3803.31, "word": " some", "probability": 0.82275390625 }, { "start": 3803.31, "end": 3803.53, "word": " of", "probability": 0.9033203125 }, { "start": 3803.53, "end": 3804.21, "word": " our", "probability": 0.8173828125 }, { "start": 3804.21, "end": 3806.05, "word": " ham", "probability": 0.5146484375 }, { "start": 3806.05, "end": 3806.33, "word": " emails", "probability": 0.72900390625 }, { "start": 3806.33, "end": 3806.49, "word": " are", "probability": 0.89453125 }, { "start": 3806.49, "end": 3806.67, "word": " still", "probability": 0.9248046875 }, { "start": 3806.67, "end": 3806.95, "word": " spam", "probability": 0.95361328125 }, { "start": 3806.95, "end": 3807.03, "word": ",", "probability": 0.7509765625 } ] }, { "id": 1011, "seek": 370128, "start": 3807.03, "end": 3808.15, "text": " but significantly less.", "tokens": [ 51414, 457, 10591, 1570, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.18699048443332963, "compression_ratio": 1.3864734299516908, "no_speech_prob": 0.004608154296875, "words": [ { "start": 3807.03, "end": 3807.15, "word": " but", "probability": 0.90087890625 }, { "start": 3807.15, "end": 3807.65, "word": " significantly", "probability": 0.859375 }, { "start": 3807.65, "end": 3808.07, "word": " less", "probability": 0.884765625 }, { "start": 3808.07, "end": 3808.15, "word": ".", "probability": 0.923828125 } ] }, { "id": 1012, "seek": 370128, "start": 3808.15, "end": 3810.25, "text": " We went from 108 down to 23,", "tokens": [ 51464, 492, 1437, 490, 41342, 760, 281, 6673, 11, 51614 ], "temperature": 0.0, "avg_logprob": -0.18699048443332963, "compression_ratio": 1.3864734299516908, "no_speech_prob": 0.004608154296875, "words": [ { "start": 3808.15, "end": 3808.23, "word": " We", "probability": 0.896484375 }, { "start": 3808.23, "end": 3808.37, "word": " went", "probability": 0.81591796875 }, { "start": 3808.37, "end": 3808.55, "word": " from", "probability": 0.8173828125 }, { "start": 3808.55, "end": 3808.85, "word": " 108", "probability": 0.76171875 }, { "start": 3808.85, "end": 3809.21, "word": " down", "probability": 0.830078125 }, { "start": 3809.21, "end": 3809.33, "word": " to", "probability": 0.9052734375 }, { "start": 3809.33, "end": 3809.81, "word": " 23", "probability": 0.89404296875 }, { "start": 3809.81, "end": 3810.25, "word": ",", "probability": 0.51318359375 } ] }, { "id": 1013, "seek": 373030, "start": 3810.25, "end": 3815.61, "text": " but now it thinks that some of our spam emails", "tokens": [ 50364, 457, 586, 309, 7309, 300, 512, 295, 527, 24028, 12524, 50614 ], "temperature": 0.0, "avg_logprob": -0.22230816654639668, "compression_ratio": 1.5265486725663717, "no_speech_prob": 0.284423828125, "words": [ { "start": 3810.25, "end": 3810.67, "word": " but", "probability": 0.3818359375 }, { "start": 3810.67, "end": 3810.95, "word": " now", "probability": 0.88330078125 }, { "start": 3810.95, "end": 3811.15, "word": " it", "probability": 0.8984375 }, { "start": 3811.15, "end": 3811.45, "word": " thinks", "probability": 0.7587890625 }, { "start": 3811.45, "end": 3811.85, "word": " that", "probability": 0.865234375 }, { "start": 3811.85, "end": 3812.15, "word": " some", "probability": 0.830078125 }, { "start": 3812.15, "end": 3812.33, "word": " of", "probability": 0.9052734375 }, { "start": 3812.33, "end": 3813.37, "word": " our", "probability": 0.8291015625 }, { "start": 3813.37, "end": 3815.05, "word": " spam", "probability": 0.82666015625 }, { "start": 3815.05, "end": 3815.61, "word": " emails", "probability": 0.73828125 } ] }, { "id": 1014, "seek": 373030, "start": 3815.61, "end": 3817.75, "text": " are actually ham.", "tokens": [ 50614, 366, 767, 7852, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.22230816654639668, "compression_ratio": 1.5265486725663717, "no_speech_prob": 0.284423828125, "words": [ { "start": 3815.61, "end": 3816.15, "word": " are", "probability": 0.89892578125 }, { "start": 3816.15, "end": 3816.63, "word": " actually", "probability": 0.77294921875 }, { "start": 3816.63, "end": 3817.15, "word": " ham", "probability": 0.716796875 }, { "start": 3817.15, "end": 3817.75, "word": ".", "probability": 0.455322265625 } ] }, { "id": 1015, "seek": 373030, "start": 3817.81, "end": 3818.67, "text": " And so that's a problem.", "tokens": [ 50714, 400, 370, 300, 311, 257, 1154, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.22230816654639668, "compression_ratio": 1.5265486725663717, "no_speech_prob": 0.284423828125, "words": [ { "start": 3817.81, "end": 3817.93, "word": " And", "probability": 0.40576171875 }, { "start": 3817.93, "end": 3818.03, "word": " so", "probability": 0.89453125 }, { "start": 3818.03, "end": 3818.23, "word": " that's", "probability": 0.912109375 }, { "start": 3818.31, "end": 3818.55, "word": " a problem", "probability": 0.7744140625 }, { "start": 3818.55, "end": 3818.67, "word": ".", "probability": 0.8505859375 } ] }, { "id": 1016, "seek": 373030, "start": 3818.67, "end": 3821.45, "text": " So we have a few more emails going through our filter", "tokens": [ 50764, 407, 321, 362, 257, 1326, 544, 12524, 516, 807, 527, 6608, 50914 ], "temperature": 0.0, "avg_logprob": -0.22230816654639668, "compression_ratio": 1.5265486725663717, "no_speech_prob": 0.284423828125, "words": [ { "start": 3818.67, "end": 3818.77, "word": " So", "probability": 0.8291015625 }, { "start": 3818.77, "end": 3818.89, "word": " we", "probability": 0.865234375 }, { "start": 3818.89, "end": 3819.03, "word": " have", "probability": 0.87451171875 }, { "start": 3819.17, "end": 3819.45, "word": " a few", "probability": 0.81494140625 }, { "start": 3819.45, "end": 3819.79, "word": " more", "probability": 0.8779296875 }, { "start": 3819.79, "end": 3820.37, "word": " emails", "probability": 0.78515625 }, { "start": 3820.37, "end": 3820.71, "word": " going", "probability": 0.85546875 }, { "start": 3820.71, "end": 3820.99, "word": " through", "probability": 0.78955078125 }, { "start": 3820.99, "end": 3821.15, "word": " our", "probability": 0.81103515625 }, { "start": 3821.15, "end": 3821.45, "word": " filter", "probability": 0.8974609375 } ] }, { "id": 1017, "seek": 373030, "start": 3821.45, "end": 3822.87, "text": " than we would like,", "tokens": [ 50914, 813, 321, 576, 411, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.22230816654639668, "compression_ratio": 1.5265486725663717, "no_speech_prob": 0.284423828125, "words": [ { "start": 3821.45, "end": 3821.67, "word": " than", "probability": 0.861328125 }, { "start": 3821.67, "end": 3821.81, "word": " we", "probability": 0.908203125 }, { "start": 3821.81, "end": 3821.99, "word": " would", "probability": 0.8466796875 }, { "start": 3821.99, "end": 3822.33, "word": " like", "probability": 0.876953125 }, { "start": 3822.33, "end": 3822.87, "word": ",", "probability": 0.71435546875 } ] }, { "id": 1018, "seek": 373030, "start": 3822.87, "end": 3827.59, "text": " but we have significantly fewer of our ham emails", "tokens": [ 50964, 457, 321, 362, 10591, 13366, 295, 527, 7852, 12524, 51214 ], "temperature": 0.0, "avg_logprob": -0.22230816654639668, "compression_ratio": 1.5265486725663717, "no_speech_prob": 0.284423828125, "words": [ { "start": 3822.87, "end": 3823.25, "word": " but", "probability": 0.8974609375 }, { "start": 3823.25, "end": 3823.53, "word": " we", "probability": 0.908203125 }, { "start": 3823.53, "end": 3824.01, "word": " have", "probability": 0.88720703125 }, { "start": 3824.01, "end": 3824.61, "word": " significantly", "probability": 0.8642578125 }, { "start": 3824.61, "end": 3825.21, "word": " fewer", "probability": 0.7451171875 }, { "start": 3825.21, "end": 3825.81, "word": " of", "probability": 0.90478515625 }, { "start": 3825.81, "end": 3826.39, "word": " our", "probability": 0.8173828125 }, { "start": 3826.39, "end": 3827.11, "word": " ham", "probability": 0.86328125 }, { "start": 3827.11, "end": 3827.59, "word": " emails", "probability": 0.771484375 } ] }, { "id": 1019, "seek": 373030, "start": 3827.59, "end": 3829.25, "text": " from being blocked.", "tokens": [ 51214, 490, 885, 15470, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.22230816654639668, "compression_ratio": 1.5265486725663717, "no_speech_prob": 0.284423828125, "words": [ { "start": 3827.59, "end": 3828.07, "word": " from", "probability": 0.7900390625 }, { "start": 3828.07, "end": 3828.27, "word": " being", "probability": 0.888671875 }, { "start": 3828.27, "end": 3828.65, "word": " blocked", "probability": 0.6845703125 }, { "start": 3828.65, "end": 3829.25, "word": ".", "probability": 0.99267578125 } ] }, { "id": 1020, "seek": 373030, "start": 3830.59, "end": 3834.11, "text": " GT, we've got a question from Twitch chat.", "tokens": [ 51364, 17530, 11, 321, 600, 658, 257, 1168, 490, 22222, 5081, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.22230816654639668, "compression_ratio": 1.5265486725663717, "no_speech_prob": 0.284423828125, "words": [ { "start": 3830.59, "end": 3831.19, "word": " GT", "probability": 0.029876708984375 }, { "start": 3831.19, "end": 3831.59, "word": ",", "probability": 0.8505859375 }, { "start": 3831.59, "end": 3831.85, "word": " we've", "probability": 0.49072265625 }, { "start": 3831.85, "end": 3831.95, "word": " got", "probability": 0.86376953125 }, { "start": 3832.05, "end": 3832.27, "word": " a question", "probability": 0.77734375 }, { "start": 3832.27, "end": 3832.61, "word": " from", "probability": 0.79443359375 }, { "start": 3832.61, "end": 3833.63, "word": " Twitch", "probability": 0.6455078125 }, { "start": 3833.63, "end": 3833.97, "word": " chat", "probability": 0.681640625 }, { "start": 3833.97, "end": 3834.11, "word": ".", "probability": 0.94482421875 } ] }, { "id": 1021, "seek": 373030, "start": 3834.11, "end": 3834.65, "text": " Absolutely.", "tokens": [ 51514, 7021, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.22230816654639668, "compression_ratio": 1.5265486725663717, "no_speech_prob": 0.284423828125, "words": [ { "start": 3834.11, "end": 3834.49, "word": " Absolutely", "probability": 0.34423828125 }, { "start": 3834.49, "end": 3834.65, "word": ".", "probability": 0.9404296875 } ] }, { "id": 1022, "seek": 373030, "start": 3834.65, "end": 3836.67, "text": " So Chris...", "tokens": [ 51564, 407, 6688, 485, 51664 ], "temperature": 0.0, "avg_logprob": -0.22230816654639668, "compression_ratio": 1.5265486725663717, "no_speech_prob": 0.284423828125, "words": [ { "start": 3834.65, "end": 3834.89, "word": " So", "probability": 0.66162109375 }, { "start": 3834.89, "end": 3836.67, "word": " Chris...", "probability": 0.43487548828125 } ] }, { "id": 1023, "seek": 373030, "start": 3836.67, "end": 3839.27, "text": " I'm not going to try and pronounce the name.", "tokens": [ 51664, 286, 478, 406, 516, 281, 853, 293, 19567, 264, 1315, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.22230816654639668, "compression_ratio": 1.5265486725663717, "no_speech_prob": 0.284423828125, "words": [ { "start": 3836.67, "end": 3837.33, "word": " I'm", "probability": 0.839111328125 }, { "start": 3837.33, "end": 3837.41, "word": " not", "probability": 0.8642578125 }, { "start": 3837.41, "end": 3837.49, "word": " going", "probability": 0.4541015625 }, { "start": 3837.49, "end": 3837.81, "word": " to", "probability": 0.90380859375 }, { "start": 3837.81, "end": 3838.07, "word": " try", "probability": 0.796875 }, { "start": 3838.07, "end": 3838.19, "word": " and", "probability": 0.73974609375 }, { "start": 3838.19, "end": 3838.41, "word": " pronounce", "probability": 0.87451171875 }, { "start": 3838.41, "end": 3838.53, "word": " the", "probability": 0.802734375 }, { "start": 3838.53, "end": 3838.69, "word": " name", "probability": 0.8203125 }, { "start": 3838.69, "end": 3839.27, "word": ".", "probability": 0.71142578125 } ] }, { "id": 1024, "seek": 375796, "start": 3839.27, "end": 3842.97, "text": " Did you intentionally avoid having spam emails classified as ham", "tokens": [ 50364, 2589, 291, 22062, 5042, 1419, 24028, 12524, 20627, 382, 7852, 50564 ], "temperature": 0.0, "avg_logprob": -0.1590773752757481, "compression_ratio": 1.84037558685446, "no_speech_prob": 0.102294921875, "words": [ { "start": 3839.27, "end": 3839.43, "word": " Did", "probability": 0.6923828125 }, { "start": 3839.43, "end": 3839.57, "word": " you", "probability": 0.8896484375 }, { "start": 3839.57, "end": 3840.07, "word": " intentionally", "probability": 0.86572265625 }, { "start": 3840.07, "end": 3840.73, "word": " avoid", "probability": 0.79150390625 }, { "start": 3840.73, "end": 3841.01, "word": " having", "probability": 0.78564453125 }, { "start": 3841.01, "end": 3841.43, "word": " spam", "probability": 0.93603515625 }, { "start": 3841.43, "end": 3841.77, "word": " emails", "probability": 0.751953125 }, { "start": 3841.77, "end": 3842.39, "word": " classified", "probability": 0.94482421875 }, { "start": 3842.39, "end": 3842.69, "word": " as", "probability": 0.91015625 }, { "start": 3842.69, "end": 3842.97, "word": " ham", "probability": 0.468505859375 } ] }, { "id": 1025, "seek": 375796, "start": 3842.97, "end": 3844.33, "text": " when you created the model,", "tokens": [ 50564, 562, 291, 2942, 264, 2316, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.1590773752757481, "compression_ratio": 1.84037558685446, "no_speech_prob": 0.102294921875, "words": [ { "start": 3842.97, "end": 3843.21, "word": " when", "probability": 0.85595703125 }, { "start": 3843.21, "end": 3843.35, "word": " you", "probability": 0.88916015625 }, { "start": 3843.35, "end": 3843.67, "word": " created", "probability": 0.71826171875 }, { "start": 3843.67, "end": 3843.85, "word": " the", "probability": 0.81201171875 }, { "start": 3843.85, "end": 3844.07, "word": " model", "probability": 0.82763671875 }, { "start": 3844.07, "end": 3844.33, "word": ",", "probability": 0.39306640625 } ] }, { "id": 1026, "seek": 375796, "start": 3844.33, "end": 3847.13, "text": " or is it simply a try and error kind of thing", "tokens": [ 50614, 420, 307, 309, 2935, 257, 853, 293, 6713, 733, 295, 551, 50764 ], "temperature": 0.0, "avg_logprob": -0.1590773752757481, "compression_ratio": 1.84037558685446, "no_speech_prob": 0.102294921875, "words": [ { "start": 3844.33, "end": 3844.43, "word": " or", "probability": 0.900390625 }, { "start": 3844.43, "end": 3844.55, "word": " is", "probability": 0.83837890625 }, { "start": 3844.55, "end": 3844.67, "word": " it", "probability": 0.88720703125 }, { "start": 3844.67, "end": 3845.09, "word": " simply", "probability": 0.822265625 }, { "start": 3845.77, "end": 3846.11, "word": " a try", "probability": 0.673828125 }, { "start": 3846.11, "end": 3846.25, "word": " and", "probability": 0.50048828125 }, { "start": 3846.25, "end": 3846.57, "word": " error", "probability": 0.7744140625 }, { "start": 3846.57, "end": 3846.87, "word": " kind", "probability": 0.74951171875 }, { "start": 3846.87, "end": 3846.95, "word": " of", "probability": 0.90283203125 }, { "start": 3846.95, "end": 3847.13, "word": " thing", "probability": 0.80859375 } ] }, { "id": 1027, "seek": 375796, "start": 3847.13, "end": 3848.61, "text": " when training the model?", "tokens": [ 50764, 562, 3097, 264, 2316, 30, 50864 ], "temperature": 0.0, "avg_logprob": -0.1590773752757481, "compression_ratio": 1.84037558685446, "no_speech_prob": 0.102294921875, "words": [ { "start": 3847.13, "end": 3847.29, "word": " when", "probability": 0.859375 }, { "start": 3847.29, "end": 3847.59, "word": " training", "probability": 0.775390625 }, { "start": 3847.59, "end": 3847.77, "word": " the", "probability": 0.8134765625 }, { "start": 3847.77, "end": 3848.01, "word": " model", "probability": 0.83544921875 }, { "start": 3848.01, "end": 3848.61, "word": "?", "probability": 0.9365234375 } ] }, { "id": 1028, "seek": 375796, "start": 3849.55, "end": 3853.53, "text": " Intentionally avoid having spam emails classified as ham?", "tokens": [ 50864, 5681, 1251, 379, 5042, 1419, 24028, 12524, 20627, 382, 7852, 30, 51114 ], "temperature": 0.0, "avg_logprob": -0.1590773752757481, "compression_ratio": 1.84037558685446, "no_speech_prob": 0.102294921875, "words": [ { "start": 3849.55, "end": 3850.15, "word": " Intentionally", "probability": 0.8375651041666666 }, { "start": 3850.15, "end": 3850.51, "word": " avoid", "probability": 0.7958984375 }, { "start": 3850.51, "end": 3850.81, "word": " having", "probability": 0.783203125 }, { "start": 3850.81, "end": 3851.27, "word": " spam", "probability": 0.92626953125 }, { "start": 3851.27, "end": 3851.69, "word": " emails", "probability": 0.78466796875 }, { "start": 3851.69, "end": 3852.29, "word": " classified", "probability": 0.943359375 }, { "start": 3852.29, "end": 3852.63, "word": " as", "probability": 0.9111328125 }, { "start": 3852.63, "end": 3852.93, "word": " ham", "probability": 0.87060546875 }, { "start": 3852.93, "end": 3853.53, "word": "?", "probability": 0.78515625 } ] }, { "id": 1029, "seek": 375796, "start": 3854.17, "end": 3856.43, "text": " Is that what they said?", "tokens": [ 51114, 1119, 300, 437, 436, 848, 30, 51214 ], "temperature": 0.0, "avg_logprob": -0.1590773752757481, "compression_ratio": 1.84037558685446, "no_speech_prob": 0.102294921875, "words": [ { "start": 3854.17, "end": 3854.77, "word": " Is", "probability": 0.85595703125 }, { "start": 3854.77, "end": 3854.87, "word": " that", "probability": 0.87890625 }, { "start": 3854.87, "end": 3854.97, "word": " what", "probability": 0.85986328125 }, { "start": 3854.97, "end": 3855.09, "word": " they", "probability": 0.734375 }, { "start": 3855.09, "end": 3855.83, "word": " said", "probability": 0.6318359375 }, { "start": 3855.83, "end": 3856.43, "word": "?", "probability": 0.994140625 } ] }, { "id": 1030, "seek": 375796, "start": 3856.43, "end": 3857.31, "text": " Yeah.", "tokens": [ 51214, 865, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.1590773752757481, "compression_ratio": 1.84037558685446, "no_speech_prob": 0.102294921875, "words": [ { "start": 3856.43, "end": 3856.71, "word": " Yeah", "probability": 0.85400390625 }, { "start": 3856.71, "end": 3857.31, "word": ".", "probability": 0.8701171875 } ] }, { "id": 1031, "seek": 375796, "start": 3857.99, "end": 3862.05, "text": " Yeah, we wouldn't want spam emails to be classified as ham.", "tokens": [ 51314, 865, 11, 321, 2759, 380, 528, 24028, 12524, 281, 312, 20627, 382, 7852, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.1590773752757481, "compression_ratio": 1.84037558685446, "no_speech_prob": 0.102294921875, "words": [ { "start": 3857.99, "end": 3858.59, "word": " Yeah", "probability": 0.76904296875 }, { "start": 3858.59, "end": 3858.79, "word": ",", "probability": 0.6611328125 }, { "start": 3858.79, "end": 3859.17, "word": " we", "probability": 0.89599609375 }, { "start": 3859.17, "end": 3859.45, "word": " wouldn't", "probability": 0.90087890625 }, { "start": 3859.45, "end": 3859.81, "word": " want", "probability": 0.79248046875 }, { "start": 3859.81, "end": 3860.17, "word": " spam", "probability": 0.9248046875 }, { "start": 3860.17, "end": 3860.45, "word": " emails", "probability": 0.78466796875 }, { "start": 3860.45, "end": 3860.61, "word": " to", "probability": 0.9111328125 }, { "start": 3860.61, "end": 3860.73, "word": " be", "probability": 0.91162109375 }, { "start": 3860.73, "end": 3861.05, "word": " classified", "probability": 0.9404296875 }, { "start": 3861.05, "end": 3861.43, "word": " as", "probability": 0.91162109375 }, { "start": 3861.43, "end": 3861.67, "word": " ham", "probability": 0.8662109375 }, { "start": 3861.67, "end": 3862.05, "word": ".", "probability": 0.94775390625 } ] }, { "id": 1032, "seek": 375796, "start": 3862.05, "end": 3864.39, "text": " We want to draw a line and separate", "tokens": [ 51514, 492, 528, 281, 2642, 257, 1622, 293, 4994, 51614 ], "temperature": 0.0, "avg_logprob": -0.1590773752757481, "compression_ratio": 1.84037558685446, "no_speech_prob": 0.102294921875, "words": [ { "start": 3862.05, "end": 3862.47, "word": " We", "probability": 0.8955078125 }, { "start": 3862.47, "end": 3862.71, "word": " want", "probability": 0.80517578125 }, { "start": 3862.71, "end": 3863.03, "word": " to", "probability": 0.9052734375 }, { "start": 3863.03, "end": 3863.43, "word": " draw", "probability": 0.79150390625 }, { "start": 3863.61, "end": 3863.85, "word": " a line", "probability": 0.89208984375 }, { "start": 3863.85, "end": 3864.05, "word": " and", "probability": 0.88818359375 }, { "start": 3864.05, "end": 3864.39, "word": " separate", "probability": 0.8701171875 } ] }, { "id": 1033, "seek": 375796, "start": 3864.39, "end": 3866.93, "text": " so that you stop getting emails about Viagra", "tokens": [ 51614, 370, 300, 291, 1590, 1242, 12524, 466, 6626, 559, 424, 51764 ], "temperature": 0.0, "avg_logprob": -0.1590773752757481, "compression_ratio": 1.84037558685446, "no_speech_prob": 0.102294921875, "words": [ { "start": 3864.39, "end": 3864.73, "word": " so", "probability": 0.8203125 }, { "start": 3864.73, "end": 3864.87, "word": " that", "probability": 0.86181640625 }, { "start": 3864.87, "end": 3865.01, "word": " you", "probability": 0.90234375 }, { "start": 3865.01, "end": 3865.29, "word": " stop", "probability": 0.79931640625 }, { "start": 3865.29, "end": 3865.61, "word": " getting", "probability": 0.89794921875 }, { "start": 3865.61, "end": 3866.11, "word": " emails", "probability": 0.79931640625 }, { "start": 3866.11, "end": 3866.41, "word": " about", "probability": 0.826171875 }, { "start": 3866.41, "end": 3866.93, "word": " Viagra", "probability": 0.9402669270833334 } ] }, { "id": 1034, "seek": 378686, "start": 3866.93, "end": 3870.99, "text": " and you start getting the regular emails from your school or your work.", "tokens": [ 50364, 293, 291, 722, 1242, 264, 3890, 12524, 490, 428, 1395, 420, 428, 589, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.17310049209524603, "compression_ratio": 1.7954545454545454, "no_speech_prob": 0.120849609375, "words": [ { "start": 3866.93, "end": 3867.23, "word": " and", "probability": 0.5380859375 }, { "start": 3867.23, "end": 3867.47, "word": " you", "probability": 0.88525390625 }, { "start": 3867.47, "end": 3867.77, "word": " start", "probability": 0.8662109375 }, { "start": 3867.77, "end": 3868.07, "word": " getting", "probability": 0.900390625 }, { "start": 3868.07, "end": 3868.25, "word": " the", "probability": 0.78955078125 }, { "start": 3868.25, "end": 3868.51, "word": " regular", "probability": 0.89013671875 }, { "start": 3868.51, "end": 3868.99, "word": " emails", "probability": 0.71484375 }, { "start": 3868.99, "end": 3869.33, "word": " from", "probability": 0.81494140625 }, { "start": 3869.33, "end": 3869.49, "word": " your", "probability": 0.80859375 }, { "start": 3869.49, "end": 3869.75, "word": " school", "probability": 0.91259765625 }, { "start": 3869.75, "end": 3869.91, "word": " or", "probability": 0.88818359375 }, { "start": 3869.91, "end": 3870.07, "word": " your", "probability": 0.791015625 }, { "start": 3870.07, "end": 3870.43, "word": " work", "probability": 0.802734375 }, { "start": 3870.43, "end": 3870.99, "word": ".", "probability": 0.76953125 } ] }, { "id": 1035, "seek": 378686, "start": 3871.13, "end": 3874.33, "text": " And so this is just kind of the way that spam filters operate.", "tokens": [ 50564, 400, 370, 341, 307, 445, 733, 295, 264, 636, 300, 24028, 15995, 9651, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.17310049209524603, "compression_ratio": 1.7954545454545454, "no_speech_prob": 0.120849609375, "words": [ { "start": 3871.13, "end": 3871.49, "word": " And", "probability": 0.75048828125 }, { "start": 3871.49, "end": 3871.63, "word": " so", "probability": 0.8857421875 }, { "start": 3871.63, "end": 3871.79, "word": " this", "probability": 0.7392578125 }, { "start": 3871.79, "end": 3871.95, "word": " is", "probability": 0.9072265625 }, { "start": 3871.95, "end": 3872.09, "word": " just", "probability": 0.86669921875 }, { "start": 3872.09, "end": 3872.25, "word": " kind", "probability": 0.74462890625 }, { "start": 3872.25, "end": 3872.31, "word": " of", "probability": 0.90673828125 }, { "start": 3872.31, "end": 3872.41, "word": " the", "probability": 0.8154296875 }, { "start": 3872.41, "end": 3872.51, "word": " way", "probability": 0.896484375 }, { "start": 3872.51, "end": 3872.67, "word": " that", "probability": 0.84619140625 }, { "start": 3872.67, "end": 3872.89, "word": " spam", "probability": 0.91162109375 }, { "start": 3872.89, "end": 3873.19, "word": " filters", "probability": 0.8447265625 }, { "start": 3873.19, "end": 3873.77, "word": " operate", "probability": 0.75439453125 }, { "start": 3873.77, "end": 3874.33, "word": ".", "probability": 0.97265625 } ] }, { "id": 1036, "seek": 378686, "start": 3874.87, "end": 3879.61, "text": " So we could build a model that would classify more spam emails", "tokens": [ 50764, 407, 321, 727, 1322, 257, 2316, 300, 576, 33872, 544, 24028, 12524, 51014 ], "temperature": 0.0, "avg_logprob": -0.17310049209524603, "compression_ratio": 1.7954545454545454, "no_speech_prob": 0.120849609375, "words": [ { "start": 3874.87, "end": 3875.15, "word": " So", "probability": 0.88525390625 }, { "start": 3875.15, "end": 3875.37, "word": " we", "probability": 0.80126953125 }, { "start": 3875.37, "end": 3875.51, "word": " could", "probability": 0.65380859375 }, { "start": 3875.51, "end": 3875.73, "word": " build", "probability": 0.853515625 }, { "start": 3875.89, "end": 3876.19, "word": " a model", "probability": 0.79296875 }, { "start": 3876.19, "end": 3876.57, "word": " that", "probability": 0.86279296875 }, { "start": 3876.57, "end": 3876.83, "word": " would", "probability": 0.845703125 }, { "start": 3876.83, "end": 3877.69, "word": " classify", "probability": 0.9365234375 }, { "start": 3877.69, "end": 3878.59, "word": " more", "probability": 0.8798828125 }, { "start": 3878.59, "end": 3879.15, "word": " spam", "probability": 0.93701171875 }, { "start": 3879.15, "end": 3879.61, "word": " emails", "probability": 0.79541015625 } ] }, { "id": 1037, "seek": 378686, "start": 3879.61, "end": 3883.61, "text": " as being part of ham or regular emails,", "tokens": [ 51014, 382, 885, 644, 295, 7852, 420, 3890, 12524, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.17310049209524603, "compression_ratio": 1.7954545454545454, "no_speech_prob": 0.120849609375, "words": [ { "start": 3879.61, "end": 3880.01, "word": " as", "probability": 0.90625 }, { "start": 3880.01, "end": 3880.29, "word": " being", "probability": 0.890625 }, { "start": 3880.29, "end": 3880.81, "word": " part", "probability": 0.81005859375 }, { "start": 3880.81, "end": 3881.31, "word": " of", "probability": 0.90576171875 }, { "start": 3881.31, "end": 3881.97, "word": " ham", "probability": 0.55908203125 }, { "start": 3881.97, "end": 3882.17, "word": " or", "probability": 0.857421875 }, { "start": 3882.17, "end": 3882.43, "word": " regular", "probability": 0.8935546875 }, { "start": 3882.43, "end": 3882.99, "word": " emails", "probability": 0.76220703125 }, { "start": 3882.99, "end": 3883.61, "word": ",", "probability": 0.437744140625 } ] }, { "id": 1038, "seek": 378686, "start": 3883.61, "end": 3887.61, "text": " or we can build a model that says,", "tokens": [ 51214, 420, 321, 393, 1322, 257, 2316, 300, 1619, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.17310049209524603, "compression_ratio": 1.7954545454545454, "no_speech_prob": 0.120849609375, "words": [ { "start": 3883.61, "end": 3884.03, "word": " or", "probability": 0.89599609375 }, { "start": 3884.03, "end": 3884.17, "word": " we", "probability": 0.89990234375 }, { "start": 3884.17, "end": 3884.31, "word": " can", "probability": 0.71630859375 }, { "start": 3884.31, "end": 3884.95, "word": " build", "probability": 0.2215576171875 }, { "start": 3885.77, "end": 3886.01, "word": " a model", "probability": 0.83251953125 }, { "start": 3886.01, "end": 3886.45, "word": " that", "probability": 0.88720703125 }, { "start": 3886.45, "end": 3887.43, "word": " says", "probability": 0.82275390625 }, { "start": 3887.43, "end": 3887.61, "word": ",", "probability": 0.8642578125 } ] }, { "id": 1039, "seek": 378686, "start": 3887.61, "end": 3889.99, "text": " okay, we want absolutely zero spam emails.", "tokens": [ 51364, 1392, 11, 321, 528, 3122, 4018, 24028, 12524, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.17310049209524603, "compression_ratio": 1.7954545454545454, "no_speech_prob": 0.120849609375, "words": [ { "start": 3887.61, "end": 3887.77, "word": " okay", "probability": 0.303466796875 }, { "start": 3887.77, "end": 3887.79, "word": ",", "probability": 0.9208984375 }, { "start": 3887.79, "end": 3887.99, "word": " we", "probability": 0.8994140625 }, { "start": 3887.99, "end": 3888.17, "word": " want", "probability": 0.810546875 }, { "start": 3888.17, "end": 3888.61, "word": " absolutely", "probability": 0.68115234375 }, { "start": 3888.61, "end": 3888.91, "word": " zero", "probability": 0.849609375 }, { "start": 3888.91, "end": 3889.27, "word": " spam", "probability": 0.92724609375 }, { "start": 3889.27, "end": 3889.75, "word": " emails", "probability": 0.83251953125 }, { "start": 3889.75, "end": 3889.99, "word": ".", "probability": 0.77734375 } ] }, { "id": 1040, "seek": 378686, "start": 3889.99, "end": 3893.13, "text": " If we wind up losing regular emails", "tokens": [ 51514, 759, 321, 2468, 493, 7027, 3890, 12524, 51664 ], "temperature": 0.0, "avg_logprob": -0.17310049209524603, "compression_ratio": 1.7954545454545454, "no_speech_prob": 0.120849609375, "words": [ { "start": 3889.99, "end": 3890.53, "word": " If", "probability": 0.8984375 }, { "start": 3890.53, "end": 3890.75, "word": " we", "probability": 0.90673828125 }, { "start": 3890.75, "end": 3891.05, "word": " wind", "probability": 0.8837890625 }, { "start": 3891.05, "end": 3891.25, "word": " up", "probability": 0.9169921875 }, { "start": 3891.25, "end": 3891.79, "word": " losing", "probability": 0.8037109375 }, { "start": 3891.79, "end": 3892.63, "word": " regular", "probability": 0.89306640625 }, { "start": 3892.63, "end": 3893.13, "word": " emails", "probability": 0.76953125 } ] }, { "id": 1041, "seek": 378686, "start": 3893.13, "end": 3895.83, "text": " and classifying those as spam as a mistake,", "tokens": [ 51664, 293, 1508, 5489, 729, 382, 24028, 382, 257, 6146, 11, 51814 ], "temperature": 0.0, "avg_logprob": -0.17310049209524603, "compression_ratio": 1.7954545454545454, "no_speech_prob": 0.120849609375, "words": [ { "start": 3893.13, "end": 3893.33, "word": " and", "probability": 0.87451171875 }, { "start": 3893.33, "end": 3893.89, "word": " classifying", "probability": 0.893798828125 }, { "start": 3893.89, "end": 3894.09, "word": " those", "probability": 0.84130859375 }, { "start": 3894.09, "end": 3894.27, "word": " as", "probability": 0.8994140625 }, { "start": 3894.27, "end": 3894.57, "word": " spam", "probability": 0.93701171875 }, { "start": 3894.57, "end": 3894.85, "word": " as", "probability": 0.8388671875 }, { "start": 3894.97, "end": 3895.47, "word": " a mistake", "probability": 0.90185546875 }, { "start": 3895.47, "end": 3895.83, "word": ",", "probability": 0.9755859375 } ] }, { "id": 1042, "seek": 381182, "start": 3895.83, "end": 3897.39, "text": " we're okay with that.", "tokens": [ 50364, 321, 434, 1392, 365, 300, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.17362499332427977, "compression_ratio": 1.735042735042735, "no_speech_prob": 0.102294921875, "words": [ { "start": 3895.83, "end": 3896.23, "word": " we're", "probability": 0.52618408203125 }, { "start": 3896.23, "end": 3896.51, "word": " okay", "probability": 0.65478515625 }, { "start": 3896.51, "end": 3896.73, "word": " with", "probability": 0.818359375 }, { "start": 3896.73, "end": 3896.99, "word": " that", "probability": 0.88330078125 }, { "start": 3896.99, "end": 3897.39, "word": ".", "probability": 0.91796875 } ] }, { "id": 1043, "seek": 381182, "start": 3897.77, "end": 3900.63, "text": " A really good example, actually I'm glad you brought this up,", "tokens": [ 50464, 316, 534, 665, 1365, 11, 767, 286, 478, 5404, 291, 3038, 341, 493, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.17362499332427977, "compression_ratio": 1.735042735042735, "no_speech_prob": 0.102294921875, "words": [ { "start": 3897.77, "end": 3898.17, "word": " A", "probability": 0.91845703125 }, { "start": 3898.17, "end": 3898.33, "word": " really", "probability": 0.765625 }, { "start": 3898.33, "end": 3898.51, "word": " good", "probability": 0.87158203125 }, { "start": 3898.51, "end": 3898.91, "word": " example", "probability": 0.931640625 }, { "start": 3898.91, "end": 3899.19, "word": ",", "probability": 0.60107421875 }, { "start": 3899.19, "end": 3899.41, "word": " actually", "probability": 0.70703125 }, { "start": 3899.41, "end": 3899.57, "word": " I'm", "probability": 0.80517578125 }, { "start": 3899.57, "end": 3899.73, "word": " glad", "probability": 0.81005859375 }, { "start": 3899.73, "end": 3899.85, "word": " you", "probability": 0.88720703125 }, { "start": 3899.85, "end": 3900.01, "word": " brought", "probability": 0.91552734375 }, { "start": 3900.01, "end": 3900.21, "word": " this", "probability": 0.87646484375 }, { "start": 3900.21, "end": 3900.43, "word": " up", "probability": 0.900390625 }, { "start": 3900.43, "end": 3900.63, "word": ",", "probability": 0.7685546875 } ] }, { "id": 1044, "seek": 381182, "start": 3900.63, "end": 3901.99, "text": " is antivirus.", "tokens": [ 50614, 307, 2511, 592, 9619, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.17362499332427977, "compression_ratio": 1.735042735042735, "no_speech_prob": 0.102294921875, "words": [ { "start": 3900.63, "end": 3900.93, "word": " is", "probability": 0.90380859375 }, { "start": 3900.93, "end": 3901.59, "word": " antivirus", "probability": 0.8377278645833334 }, { "start": 3901.59, "end": 3901.99, "word": ".", "probability": 0.962890625 } ] }, { "id": 1045, "seek": 381182, "start": 3902.17, "end": 3904.15, "text": " So the way that antivirus companies work", "tokens": [ 50664, 407, 264, 636, 300, 2511, 592, 9619, 3431, 589, 50764 ], "temperature": 0.0, "avg_logprob": -0.17362499332427977, "compression_ratio": 1.735042735042735, "no_speech_prob": 0.102294921875, "words": [ { "start": 3902.17, "end": 3902.33, "word": " So", "probability": 0.84375 }, { "start": 3902.33, "end": 3902.45, "word": " the", "probability": 0.751953125 }, { "start": 3902.45, "end": 3902.63, "word": " way", "probability": 0.89990234375 }, { "start": 3902.63, "end": 3902.89, "word": " that", "probability": 0.74853515625 }, { "start": 3902.89, "end": 3903.31, "word": " antivirus", "probability": 0.9142252604166666 }, { "start": 3903.31, "end": 3903.73, "word": " companies", "probability": 0.8251953125 }, { "start": 3903.73, "end": 3904.15, "word": " work", "probability": 0.80712890625 } ] }, { "id": 1046, "seek": 381182, "start": 3904.15, "end": 3907.19, "text": " is they can err on the side of,", "tokens": [ 50764, 307, 436, 393, 45267, 322, 264, 1252, 295, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.17362499332427977, "compression_ratio": 1.735042735042735, "no_speech_prob": 0.102294921875, "words": [ { "start": 3904.15, "end": 3904.47, "word": " is", "probability": 0.8193359375 }, { "start": 3904.47, "end": 3904.63, "word": " they", "probability": 0.7080078125 }, { "start": 3904.63, "end": 3904.83, "word": " can", "probability": 0.8974609375 }, { "start": 3904.83, "end": 3905.11, "word": " err", "probability": 0.66650390625 }, { "start": 3905.11, "end": 3905.35, "word": " on", "probability": 0.89892578125 }, { "start": 3905.35, "end": 3905.53, "word": " the", "probability": 0.8125 }, { "start": 3905.53, "end": 3905.91, "word": " side", "probability": 0.82568359375 }, { "start": 3905.91, "end": 3906.53, "word": " of", "probability": 0.90478515625 }, { "start": 3906.53, "end": 3907.19, "word": ",", "probability": 0.63232421875 } ] }, { "id": 1047, "seek": 381182, "start": 3907.67, "end": 3911.03, "text": " oh, I think this is a virus, therefore it must be a virus,", "tokens": [ 50964, 1954, 11, 286, 519, 341, 307, 257, 5752, 11, 4412, 309, 1633, 312, 257, 5752, 11, 51114 ], "temperature": 0.0, "avg_logprob": -0.17362499332427977, "compression_ratio": 1.735042735042735, "no_speech_prob": 0.102294921875, "words": [ { "start": 3907.67, "end": 3908.07, "word": " oh", "probability": 0.48974609375 }, { "start": 3908.07, "end": 3908.31, "word": ",", "probability": 0.78955078125 }, { "start": 3908.31, "end": 3908.91, "word": " I", "probability": 0.99365234375 }, { "start": 3908.91, "end": 3909.09, "word": " think", "probability": 0.80322265625 }, { "start": 3909.09, "end": 3909.27, "word": " this", "probability": 0.8779296875 }, { "start": 3909.27, "end": 3909.37, "word": " is", "probability": 0.89990234375 }, { "start": 3909.47, "end": 3909.73, "word": " a virus", "probability": 0.81640625 }, { "start": 3909.73, "end": 3909.89, "word": ",", "probability": 0.7392578125 }, { "start": 3909.89, "end": 3910.03, "word": " therefore", "probability": 0.7158203125 }, { "start": 3910.03, "end": 3910.19, "word": " it", "probability": 0.78125 }, { "start": 3910.19, "end": 3910.29, "word": " must", "probability": 0.80615234375 }, { "start": 3910.29, "end": 3910.41, "word": " be", "probability": 0.90576171875 }, { "start": 3910.53, "end": 3910.81, "word": " a virus", "probability": 0.80322265625 }, { "start": 3910.81, "end": 3911.03, "word": ",", "probability": 0.59619140625 } ] }, { "id": 1048, "seek": 381182, "start": 3911.03, "end": 3913.35, "text": " or this could be benign,", "tokens": [ 51114, 420, 341, 727, 312, 3271, 788, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.17362499332427977, "compression_ratio": 1.735042735042735, "no_speech_prob": 0.102294921875, "words": [ { "start": 3911.03, "end": 3911.27, "word": " or", "probability": 0.89697265625 }, { "start": 3911.27, "end": 3911.69, "word": " this", "probability": 0.8408203125 }, { "start": 3911.69, "end": 3911.95, "word": " could", "probability": 0.828125 }, { "start": 3911.95, "end": 3912.13, "word": " be", "probability": 0.89794921875 }, { "start": 3912.13, "end": 3912.65, "word": " benign", "probability": 0.953125 }, { "start": 3912.65, "end": 3913.35, "word": ",", "probability": 0.84765625 } ] }, { "id": 1049, "seek": 381182, "start": 3913.35, "end": 3915.75, "text": " or I kind of think this is a virus,", "tokens": [ 51264, 420, 286, 733, 295, 519, 341, 307, 257, 5752, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.17362499332427977, "compression_ratio": 1.735042735042735, "no_speech_prob": 0.102294921875, "words": [ { "start": 3913.35, "end": 3913.93, "word": " or", "probability": 0.892578125 }, { "start": 3913.93, "end": 3914.15, "word": " I", "probability": 0.9736328125 }, { "start": 3914.15, "end": 3914.69, "word": " kind", "probability": 0.78564453125 }, { "start": 3914.69, "end": 3914.77, "word": " of", "probability": 0.90625 }, { "start": 3914.77, "end": 3914.93, "word": " think", "probability": 0.80810546875 }, { "start": 3914.93, "end": 3915.09, "word": " this", "probability": 0.87744140625 }, { "start": 3915.09, "end": 3915.19, "word": " is", "probability": 0.9033203125 }, { "start": 3915.31, "end": 3915.59, "word": " a virus", "probability": 0.798828125 }, { "start": 3915.59, "end": 3915.75, "word": ",", "probability": 0.77197265625 } ] }, { "id": 1050, "seek": 381182, "start": 3915.75, "end": 3918.25, "text": " but instead of blocking it, I'm just going to let it go through.", "tokens": [ 51364, 457, 2602, 295, 17776, 309, 11, 286, 478, 445, 516, 281, 718, 309, 352, 807, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.17362499332427977, "compression_ratio": 1.735042735042735, "no_speech_prob": 0.102294921875, "words": [ { "start": 3915.75, "end": 3915.85, "word": " but", "probability": 0.89599609375 }, { "start": 3915.85, "end": 3916.11, "word": " instead", "probability": 0.8544921875 }, { "start": 3916.11, "end": 3916.25, "word": " of", "probability": 0.90087890625 }, { "start": 3916.25, "end": 3916.55, "word": " blocking", "probability": 0.751953125 }, { "start": 3916.55, "end": 3916.71, "word": " it", "probability": 0.89599609375 }, { "start": 3916.71, "end": 3916.73, "word": ",", "probability": 0.74267578125 }, { "start": 3916.73, "end": 3916.83, "word": " I'm", "probability": 0.998779296875 }, { "start": 3916.83, "end": 3916.95, "word": " just", "probability": 0.87890625 }, { "start": 3916.95, "end": 3917.07, "word": " going", "probability": 0.24072265625 }, { "start": 3917.07, "end": 3917.13, "word": " to", "probability": 0.90283203125 }, { "start": 3917.13, "end": 3917.27, "word": " let", "probability": 0.89453125 }, { "start": 3917.27, "end": 3917.35, "word": " it", "probability": 0.8974609375 }, { "start": 3917.35, "end": 3917.49, "word": " go", "probability": 0.9091796875 }, { "start": 3917.49, "end": 3917.85, "word": " through", "probability": 0.7919921875 }, { "start": 3917.85, "end": 3918.25, "word": ".", "probability": 0.95263671875 } ] }, { "id": 1051, "seek": 381182, "start": 3918.87, "end": 3920.79, "text": " And so you think about the way that malware works.", "tokens": [ 51514, 400, 370, 291, 519, 466, 264, 636, 300, 40747, 1985, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.17362499332427977, "compression_ratio": 1.735042735042735, "no_speech_prob": 0.102294921875, "words": [ { "start": 3918.87, "end": 3918.97, "word": " And", "probability": 0.8154296875 }, { "start": 3918.97, "end": 3919.05, "word": " so", "probability": 0.89990234375 }, { "start": 3919.05, "end": 3919.15, "word": " you", "probability": 0.8583984375 }, { "start": 3919.15, "end": 3919.29, "word": " think", "probability": 0.78076171875 }, { "start": 3919.29, "end": 3919.45, "word": " about", "probability": 0.392333984375 }, { "start": 3919.45, "end": 3919.57, "word": " the", "probability": 0.78564453125 }, { "start": 3919.57, "end": 3919.65, "word": " way", "probability": 0.90771484375 }, { "start": 3919.65, "end": 3919.81, "word": " that", "probability": 0.85595703125 }, { "start": 3919.81, "end": 3920.03, "word": " malware", "probability": 0.88232421875 }, { "start": 3920.03, "end": 3920.39, "word": " works", "probability": 0.72509765625 }, { "start": 3920.39, "end": 3920.79, "word": ".", "probability": 0.89892578125 } ] }, { "id": 1052, "seek": 383908, "start": 3923.11, "end": 3926.45, "text": " You have malware that will make calls out to the internet,", "tokens": [ 50414, 509, 362, 40747, 300, 486, 652, 5498, 484, 281, 264, 4705, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.16809475806451613, "compression_ratio": 1.5954545454545455, "no_speech_prob": 0.09130859375, "words": [ { "start": 3923.11, "end": 3923.63, "word": " You", "probability": 0.36328125 }, { "start": 3923.63, "end": 3924.15, "word": " have", "probability": 0.85498046875 }, { "start": 3924.15, "end": 3924.47, "word": " malware", "probability": 0.88525390625 }, { "start": 3924.47, "end": 3924.85, "word": " that", "probability": 0.88037109375 }, { "start": 3924.85, "end": 3925.11, "word": " will", "probability": 0.80712890625 }, { "start": 3925.11, "end": 3925.43, "word": " make", "probability": 0.8759765625 }, { "start": 3925.43, "end": 3925.65, "word": " calls", "probability": 0.77294921875 }, { "start": 3925.65, "end": 3925.79, "word": " out", "probability": 0.8095703125 }, { "start": 3925.79, "end": 3925.89, "word": " to", "probability": 0.904296875 }, { "start": 3925.89, "end": 3926.01, "word": " the", "probability": 0.81103515625 }, { "start": 3926.01, "end": 3926.25, "word": " internet", "probability": 0.583984375 }, { "start": 3926.25, "end": 3926.45, "word": ",", "probability": 0.4130859375 } ] }, { "id": 1053, "seek": 383908, "start": 3926.45, "end": 3928.19, "text": " it'll probably take over your webcam,", "tokens": [ 50614, 309, 603, 1391, 747, 670, 428, 39490, 11, 50714 ], "temperature": 0.0, "avg_logprob": -0.16809475806451613, "compression_ratio": 1.5954545454545455, "no_speech_prob": 0.09130859375, "words": [ { "start": 3926.45, "end": 3926.59, "word": " it'll", "probability": 0.813232421875 }, { "start": 3926.59, "end": 3926.83, "word": " probably", "probability": 0.9033203125 }, { "start": 3926.83, "end": 3927.05, "word": " take", "probability": 0.81591796875 }, { "start": 3927.05, "end": 3927.21, "word": " over", "probability": 0.873046875 }, { "start": 3927.21, "end": 3927.35, "word": " your", "probability": 0.8037109375 }, { "start": 3927.35, "end": 3927.69, "word": " webcam", "probability": 0.89013671875 }, { "start": 3927.69, "end": 3928.19, "word": ",", "probability": 0.84375 } ] }, { "id": 1054, "seek": 383908, "start": 3928.19, "end": 3929.65, "text": " it'll try and write files,", "tokens": [ 50714, 309, 603, 853, 293, 2464, 7098, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.16809475806451613, "compression_ratio": 1.5954545454545455, "no_speech_prob": 0.09130859375, "words": [ { "start": 3928.19, "end": 3928.45, "word": " it'll", "probability": 0.912841796875 }, { "start": 3928.45, "end": 3928.75, "word": " try", "probability": 0.79296875 }, { "start": 3928.75, "end": 3928.87, "word": " and", "probability": 0.8623046875 }, { "start": 3928.87, "end": 3929.07, "word": " write", "probability": 0.796875 }, { "start": 3929.07, "end": 3929.55, "word": " files", "probability": 0.8017578125 }, { "start": 3929.55, "end": 3929.65, "word": ",", "probability": 0.68701171875 } ] }, { "id": 1055, "seek": 383908, "start": 3929.65, "end": 3931.49, "text": " it'll probably take over your microphone.", "tokens": [ 50814, 309, 603, 1391, 747, 670, 428, 10952, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.16809475806451613, "compression_ratio": 1.5954545454545455, "no_speech_prob": 0.09130859375, "words": [ { "start": 3929.65, "end": 3929.77, "word": " it'll", "probability": 0.809326171875 }, { "start": 3929.77, "end": 3929.95, "word": " probably", "probability": 0.89404296875 }, { "start": 3929.95, "end": 3930.17, "word": " take", "probability": 0.81494140625 }, { "start": 3930.17, "end": 3930.29, "word": " over", "probability": 0.87353515625 }, { "start": 3930.29, "end": 3930.43, "word": " your", "probability": 0.8125 }, { "start": 3930.43, "end": 3930.97, "word": " microphone", "probability": 0.771484375 }, { "start": 3930.97, "end": 3931.49, "word": ".", "probability": 0.7177734375 } ] }, { "id": 1056, "seek": 383908, "start": 3931.75, "end": 3933.15, "text": " What else does that?", "tokens": [ 50914, 708, 1646, 775, 300, 30, 51014 ], "temperature": 0.0, "avg_logprob": -0.16809475806451613, "compression_ratio": 1.5954545454545455, "no_speech_prob": 0.09130859375, "words": [ { "start": 3931.75, "end": 3932.01, "word": " What", "probability": 0.81982421875 }, { "start": 3932.01, "end": 3932.17, "word": " else", "probability": 0.85693359375 }, { "start": 3932.17, "end": 3932.37, "word": " does", "probability": 0.92822265625 }, { "start": 3932.37, "end": 3932.63, "word": " that", "probability": 0.88720703125 }, { "start": 3932.63, "end": 3933.15, "word": "?", "probability": 0.96337890625 } ] }, { "id": 1057, "seek": 383908, "start": 3933.47, "end": 3937.91, "text": " Chrome, IE, Firefox, browsers.", "tokens": [ 51014, 15327, 11, 286, 36, 11, 46613, 11, 36069, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.16809475806451613, "compression_ratio": 1.5954545454545455, "no_speech_prob": 0.09130859375, "words": [ { "start": 3933.47, "end": 3933.93, "word": " Chrome", "probability": 0.73828125 }, { "start": 3933.93, "end": 3934.57, "word": ",", "probability": 0.970703125 }, { "start": 3934.57, "end": 3935.05, "word": " IE", "probability": 0.9189453125 }, { "start": 3935.05, "end": 3935.69, "word": ",", "probability": 0.9833984375 }, { "start": 3935.69, "end": 3936.07, "word": " Firefox", "probability": 0.80908203125 }, { "start": 3936.07, "end": 3936.95, "word": ",", "probability": 0.89697265625 }, { "start": 3936.95, "end": 3937.39, "word": " browsers", "probability": 0.77392578125 }, { "start": 3937.39, "end": 3937.91, "word": ".", "probability": 0.90283203125 } ] }, { "id": 1058, "seek": 383908, "start": 3938.07, "end": 3940.35, "text": " And so the idea is instead of blocking", "tokens": [ 51214, 400, 370, 264, 1558, 307, 2602, 295, 17776, 51364 ], "temperature": 0.0, "avg_logprob": -0.16809475806451613, "compression_ratio": 1.5954545454545455, "no_speech_prob": 0.09130859375, "words": [ { "start": 3938.07, "end": 3938.17, "word": " And", "probability": 0.82470703125 }, { "start": 3938.17, "end": 3938.29, "word": " so", "probability": 0.89990234375 }, { "start": 3938.29, "end": 3938.43, "word": " the", "probability": 0.76220703125 }, { "start": 3938.43, "end": 3938.71, "word": " idea", "probability": 0.76806640625 }, { "start": 3938.71, "end": 3939.29, "word": " is", "probability": 0.9033203125 }, { "start": 3939.29, "end": 3939.73, "word": " instead", "probability": 0.6318359375 }, { "start": 3939.73, "end": 3939.97, "word": " of", "probability": 0.90673828125 }, { "start": 3939.97, "end": 3940.35, "word": " blocking", "probability": 0.7421875 } ] }, { "id": 1059, "seek": 383908, "start": 3940.35, "end": 3945.17, "text": " what could be legitimate applications,", "tokens": [ 51364, 437, 727, 312, 17956, 5821, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.16809475806451613, "compression_ratio": 1.5954545454545455, "no_speech_prob": 0.09130859375, "words": [ { "start": 3940.35, "end": 3940.71, "word": " what", "probability": 0.8759765625 }, { "start": 3940.71, "end": 3941.07, "word": " could", "probability": 0.81494140625 }, { "start": 3941.07, "end": 3941.61, "word": " be", "probability": 0.89501953125 }, { "start": 3941.61, "end": 3942.69, "word": " legitimate", "probability": 0.728515625 }, { "start": 3942.69, "end": 3944.33, "word": " applications", "probability": 0.7490234375 }, { "start": 3944.33, "end": 3945.17, "word": ",", "probability": 0.68994140625 } ] }, { "id": 1060, "seek": 383908, "start": 3945.17, "end": 3948.05, "text": " and so that would really interrupt the user experience,", "tokens": [ 51564, 293, 370, 300, 576, 534, 12729, 264, 4195, 1752, 11, 51714 ], "temperature": 0.0, "avg_logprob": -0.16809475806451613, "compression_ratio": 1.5954545454545455, "no_speech_prob": 0.09130859375, "words": [ { "start": 3945.17, "end": 3945.45, "word": " and", "probability": 0.8623046875 }, { "start": 3945.45, "end": 3945.55, "word": " so", "probability": 0.89794921875 }, { "start": 3945.55, "end": 3945.67, "word": " that", "probability": 0.880859375 }, { "start": 3945.67, "end": 3945.81, "word": " would", "probability": 0.8525390625 }, { "start": 3945.81, "end": 3946.07, "word": " really", "probability": 0.76611328125 }, { "start": 3946.07, "end": 3946.49, "word": " interrupt", "probability": 0.82763671875 }, { "start": 3946.49, "end": 3946.73, "word": " the", "probability": 0.79736328125 }, { "start": 3946.73, "end": 3946.95, "word": " user", "probability": 0.8095703125 }, { "start": 3946.95, "end": 3947.55, "word": " experience", "probability": 0.80810546875 }, { "start": 3947.55, "end": 3948.05, "word": ",", "probability": 0.85498046875 } ] }, { "id": 1061, "seek": 386676, "start": 3948.05, "end": 3950.93, "text": " they kind of err on the side of,", "tokens": [ 50364, 436, 733, 295, 45267, 322, 264, 1252, 295, 11, 50514 ], "temperature": 0.0, "avg_logprob": -0.18613470179363362, "compression_ratio": 1.6265560165975104, "no_speech_prob": 0.01384735107421875, "words": [ { "start": 3948.05, "end": 3948.13, "word": " they", "probability": 0.314453125 }, { "start": 3948.13, "end": 3948.29, "word": " kind", "probability": 0.75634765625 }, { "start": 3948.29, "end": 3948.43, "word": " of", "probability": 0.9033203125 }, { "start": 3948.43, "end": 3948.71, "word": " err", "probability": 0.64697265625 }, { "start": 3948.71, "end": 3949.17, "word": " on", "probability": 0.89501953125 }, { "start": 3949.17, "end": 3949.41, "word": " the", "probability": 0.810546875 }, { "start": 3949.41, "end": 3949.83, "word": " side", "probability": 0.82373046875 }, { "start": 3949.83, "end": 3950.39, "word": " of", "probability": 0.8984375 }, { "start": 3950.39, "end": 3950.93, "word": ",", "probability": 0.46240234375 } ] }, { "id": 1062, "seek": 386676, "start": 3950.93, "end": 3952.83, "text": " we don't want to block the user experience", "tokens": [ 50514, 321, 500, 380, 528, 281, 3461, 264, 4195, 1752, 50614 ], "temperature": 0.0, "avg_logprob": -0.18613470179363362, "compression_ratio": 1.6265560165975104, "no_speech_prob": 0.01384735107421875, "words": [ { "start": 3950.93, "end": 3951.33, "word": " we", "probability": 0.66015625 }, { "start": 3951.33, "end": 3951.47, "word": " don't", "probability": 0.94677734375 }, { "start": 3951.47, "end": 3951.61, "word": " want", "probability": 0.474853515625 }, { "start": 3951.61, "end": 3951.69, "word": " to", "probability": 0.90380859375 }, { "start": 3951.69, "end": 3951.89, "word": " block", "probability": 0.80224609375 }, { "start": 3951.89, "end": 3952.05, "word": " the", "probability": 0.7509765625 }, { "start": 3952.05, "end": 3952.25, "word": " user", "probability": 0.8076171875 }, { "start": 3952.25, "end": 3952.83, "word": " experience", "probability": 0.8095703125 } ] }, { "id": 1063, "seek": 386676, "start": 3952.83, "end": 3955.87, "text": " because then you'll uninstall the antivirus.", "tokens": [ 50614, 570, 550, 291, 603, 517, 40166, 264, 2511, 592, 9619, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.18613470179363362, "compression_ratio": 1.6265560165975104, "no_speech_prob": 0.01384735107421875, "words": [ { "start": 3952.83, "end": 3953.05, "word": " because", "probability": 0.6884765625 }, { "start": 3953.05, "end": 3953.37, "word": " then", "probability": 0.72802734375 }, { "start": 3953.37, "end": 3954.19, "word": " you'll", "probability": 0.64208984375 }, { "start": 3954.19, "end": 3954.57, "word": " uninstall", "probability": 0.860107421875 }, { "start": 3954.57, "end": 3954.73, "word": " the", "probability": 0.81103515625 }, { "start": 3954.73, "end": 3955.31, "word": " antivirus", "probability": 0.8614908854166666 }, { "start": 3955.31, "end": 3955.87, "word": ".", "probability": 0.927734375 } ] }, { "id": 1064, "seek": 386676, "start": 3955.99, "end": 3961.31, "text": " So they are more willing to let viruses go through", "tokens": [ 50764, 407, 436, 366, 544, 4950, 281, 718, 21785, 352, 807, 51064 ], "temperature": 0.0, "avg_logprob": -0.18613470179363362, "compression_ratio": 1.6265560165975104, "no_speech_prob": 0.01384735107421875, "words": [ { "start": 3955.99, "end": 3956.23, "word": " So", "probability": 0.8544921875 }, { "start": 3956.23, "end": 3956.91, "word": " they", "probability": 0.6181640625 }, { "start": 3956.91, "end": 3957.05, "word": " are", "probability": 0.8193359375 }, { "start": 3957.05, "end": 3957.55, "word": " more", "probability": 0.87890625 }, { "start": 3957.55, "end": 3958.77, "word": " willing", "probability": 0.73486328125 }, { "start": 3958.77, "end": 3959.13, "word": " to", "probability": 0.904296875 }, { "start": 3959.13, "end": 3959.53, "word": " let", "probability": 0.88623046875 }, { "start": 3959.53, "end": 3960.07, "word": " viruses", "probability": 0.73681640625 }, { "start": 3960.07, "end": 3960.79, "word": " go", "probability": 0.90625 }, { "start": 3960.79, "end": 3961.31, "word": " through", "probability": 0.7861328125 } ] }, { "id": 1065, "seek": 386676, "start": 3961.31, "end": 3964.57, "text": " than blocking legitimate applications.", "tokens": [ 51064, 813, 17776, 17956, 5821, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.18613470179363362, "compression_ratio": 1.6265560165975104, "no_speech_prob": 0.01384735107421875, "words": [ { "start": 3961.31, "end": 3961.97, "word": " than", "probability": 0.76123046875 }, { "start": 3961.97, "end": 3962.59, "word": " blocking", "probability": 0.73779296875 }, { "start": 3962.59, "end": 3963.31, "word": " legitimate", "probability": 0.78125 }, { "start": 3963.31, "end": 3964.01, "word": " applications", "probability": 0.74951171875 }, { "start": 3964.01, "end": 3964.57, "word": ".", "probability": 0.97607421875 } ] }, { "id": 1066, "seek": 386676, "start": 3965.45, "end": 3966.63, "text": " And so in this case,", "tokens": [ 51214, 400, 370, 294, 341, 1389, 11, 51314 ], "temperature": 0.0, "avg_logprob": -0.18613470179363362, "compression_ratio": 1.6265560165975104, "no_speech_prob": 0.01384735107421875, "words": [ { "start": 3965.45, "end": 3965.57, "word": " And", "probability": 0.87890625 }, { "start": 3965.57, "end": 3965.75, "word": " so", "probability": 0.900390625 }, { "start": 3965.75, "end": 3965.89, "word": " in", "probability": 0.83984375 }, { "start": 3965.89, "end": 3966.07, "word": " this", "probability": 0.88037109375 }, { "start": 3966.07, "end": 3966.39, "word": " case", "probability": 0.82373046875 }, { "start": 3966.39, "end": 3966.63, "word": ",", "probability": 0.90478515625 } ] }, { "id": 1067, "seek": 386676, "start": 3966.63, "end": 3969.23, "text": " these are trade-offs that we have to make as data scientists", "tokens": [ 51314, 613, 366, 4923, 12, 19231, 300, 321, 362, 281, 652, 382, 1412, 7708, 51464 ], "temperature": 0.0, "avg_logprob": -0.18613470179363362, "compression_ratio": 1.6265560165975104, "no_speech_prob": 0.01384735107421875, "words": [ { "start": 3966.63, "end": 3967.27, "word": " these", "probability": 0.712890625 }, { "start": 3967.27, "end": 3967.37, "word": " are", "probability": 0.89794921875 }, { "start": 3967.37, "end": 3967.63, "word": " trade", "probability": 0.7783203125 }, { "start": 3967.63, "end": 3967.77, "word": "-offs", "probability": 0.779296875 }, { "start": 3967.77, "end": 3967.93, "word": " that", "probability": 0.8798828125 }, { "start": 3967.93, "end": 3968.03, "word": " we", "probability": 0.90673828125 }, { "start": 3968.03, "end": 3968.19, "word": " have", "probability": 0.87939453125 }, { "start": 3968.19, "end": 3968.29, "word": " to", "probability": 0.9091796875 }, { "start": 3968.29, "end": 3968.45, "word": " make", "probability": 0.8740234375 }, { "start": 3968.45, "end": 3968.59, "word": " as", "probability": 0.890625 }, { "start": 3968.59, "end": 3968.85, "word": " data", "probability": 0.82421875 }, { "start": 3968.85, "end": 3969.23, "word": " scientists", "probability": 0.70947265625 } ] }, { "id": 1068, "seek": 386676, "start": 3969.23, "end": 3973.35, "text": " of if we are okay with letting a few spam emails through", "tokens": [ 51464, 295, 498, 321, 366, 1392, 365, 8295, 257, 1326, 24028, 12524, 807, 51664 ], "temperature": 0.0, "avg_logprob": -0.18613470179363362, "compression_ratio": 1.6265560165975104, "no_speech_prob": 0.01384735107421875, "words": [ { "start": 3969.23, "end": 3969.85, "word": " of", "probability": 0.297607421875 }, { "start": 3969.85, "end": 3970.11, "word": " if", "probability": 0.82373046875 }, { "start": 3970.11, "end": 3970.23, "word": " we", "probability": 0.90087890625 }, { "start": 3970.23, "end": 3970.39, "word": " are", "probability": 0.88818359375 }, { "start": 3970.39, "end": 3970.95, "word": " okay", "probability": 0.7783203125 }, { "start": 3970.95, "end": 3971.63, "word": " with", "probability": 0.80810546875 }, { "start": 3971.63, "end": 3971.95, "word": " letting", "probability": 0.81298828125 }, { "start": 3972.15, "end": 3972.31, "word": " a few", "probability": 0.833984375 }, { "start": 3972.31, "end": 3972.61, "word": " spam", "probability": 0.6455078125 }, { "start": 3972.61, "end": 3972.95, "word": " emails", "probability": 0.8046875 }, { "start": 3972.95, "end": 3973.35, "word": " through", "probability": 0.8076171875 } ] }, { "id": 1069, "seek": 386676, "start": 3973.35, "end": 3975.73, "text": " versus blocking all of our regular emails.", "tokens": [ 51664, 5717, 17776, 439, 295, 527, 3890, 12524, 13, 51814 ], "temperature": 0.0, "avg_logprob": -0.18613470179363362, "compression_ratio": 1.6265560165975104, "no_speech_prob": 0.01384735107421875, "words": [ { "start": 3973.35, "end": 3973.83, "word": " versus", "probability": 0.7255859375 }, { "start": 3973.83, "end": 3974.35, "word": " blocking", "probability": 0.73046875 }, { "start": 3974.35, "end": 3974.73, "word": " all", "probability": 0.89892578125 }, { "start": 3974.73, "end": 3974.85, "word": " of", "probability": 0.90185546875 }, { "start": 3974.85, "end": 3974.93, "word": " our", "probability": 0.794921875 }, { "start": 3974.93, "end": 3975.19, "word": " regular", "probability": 0.890625 }, { "start": 3975.19, "end": 3975.53, "word": " emails", "probability": 0.74365234375 }, { "start": 3975.53, "end": 3975.73, "word": ".", "probability": 0.99365234375 } ] }, { "id": 1070, "seek": 389676, "start": 3976.79, "end": 3980.67, "text": " So he's specifically asking about task 6A.", "tokens": [ 50414, 407, 415, 311, 4682, 3365, 466, 5633, 1386, 32, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.2077205910402186, "compression_ratio": 1.49746192893401, "no_speech_prob": 0.004528045654296875, "words": [ { "start": 3976.79, "end": 3977.43, "word": " So", "probability": 0.60546875 }, { "start": 3977.43, "end": 3978.07, "word": " he's", "probability": 0.82080078125 }, { "start": 3978.07, "end": 3978.47, "word": " specifically", "probability": 0.71728515625 }, { "start": 3978.47, "end": 3978.85, "word": " asking", "probability": 0.8154296875 }, { "start": 3978.85, "end": 3979.09, "word": " about", "probability": 0.7978515625 }, { "start": 3979.09, "end": 3979.41, "word": " task", "probability": 0.41259765625 }, { "start": 3979.41, "end": 3980.13, "word": " 6A", "probability": 0.7022705078125 }, { "start": 3980.13, "end": 3980.67, "word": ".", "probability": 0.68408203125 } ] }, { "id": 1071, "seek": 389676, "start": 3980.67, "end": 3982.15, "text": " So if you scroll up a little bit.", "tokens": [ 50564, 407, 498, 291, 11369, 493, 257, 707, 857, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.2077205910402186, "compression_ratio": 1.49746192893401, "no_speech_prob": 0.004528045654296875, "words": [ { "start": 3980.67, "end": 3980.85, "word": " So", "probability": 0.5634765625 }, { "start": 3980.85, "end": 3980.95, "word": " if", "probability": 0.83740234375 }, { "start": 3980.95, "end": 3981.03, "word": " you", "probability": 0.8896484375 }, { "start": 3981.03, "end": 3981.27, "word": " scroll", "probability": 0.912109375 }, { "start": 3981.27, "end": 3981.47, "word": " up", "probability": 0.90869140625 }, { "start": 3981.59, "end": 3981.75, "word": " a little", "probability": 0.79833984375 }, { "start": 3981.75, "end": 3981.89, "word": " bit", "probability": 0.890625 }, { "start": 3981.89, "end": 3982.15, "word": ".", "probability": 0.5947265625 } ] }, { "id": 1072, "seek": 389676, "start": 3982.15, "end": 3983.33, "text": " Task 6A?", "tokens": [ 50664, 30428, 1386, 32, 30, 50764 ], "temperature": 0.0, "avg_logprob": -0.2077205910402186, "compression_ratio": 1.49746192893401, "no_speech_prob": 0.004528045654296875, "words": [ { "start": 3982.15, "end": 3982.29, "word": " Task", "probability": 0.740234375 }, { "start": 3982.29, "end": 3982.69, "word": " 6A", "probability": 0.997802734375 }, { "start": 3982.69, "end": 3983.33, "word": "?", "probability": 0.818359375 } ] }, { "id": 1073, "seek": 389676, "start": 3983.71, "end": 3987.79, "text": " Yeah, I think the answer is a bit of that", "tokens": [ 50764, 865, 11, 286, 519, 264, 1867, 307, 257, 857, 295, 300, 50964 ], "temperature": 0.0, "avg_logprob": -0.2077205910402186, "compression_ratio": 1.49746192893401, "no_speech_prob": 0.004528045654296875, "words": [ { "start": 3983.71, "end": 3984.01, "word": " Yeah", "probability": 0.8642578125 }, { "start": 3984.01, "end": 3984.51, "word": ",", "probability": 0.1815185546875 }, { "start": 3984.51, "end": 3985.07, "word": " I", "probability": 0.9912109375 }, { "start": 3985.07, "end": 3985.51, "word": " think", "probability": 0.80810546875 }, { "start": 3985.51, "end": 3985.75, "word": " the", "probability": 0.79248046875 }, { "start": 3985.75, "end": 3986.07, "word": " answer", "probability": 0.8896484375 }, { "start": 3986.07, "end": 3986.79, "word": " is", "probability": 0.89990234375 }, { "start": 3986.97, "end": 3987.19, "word": " a bit", "probability": 0.88330078125 }, { "start": 3987.19, "end": 3987.49, "word": " of", "probability": 0.89453125 }, { "start": 3987.49, "end": 3987.79, "word": " that", "probability": 0.876953125 } ] }, { "id": 1074, "seek": 389676, "start": 3987.79, "end": 3993.65, "text": " and a bit of the question of when you build these models,", "tokens": [ 50964, 293, 257, 857, 295, 264, 1168, 295, 562, 291, 1322, 613, 5245, 11, 51214 ], "temperature": 0.0, "avg_logprob": -0.2077205910402186, "compression_ratio": 1.49746192893401, "no_speech_prob": 0.004528045654296875, "words": [ { "start": 3987.79, "end": 3987.93, "word": " and", "probability": 0.7578125 }, { "start": 3988.05, "end": 3988.19, "word": " a bit", "probability": 0.8955078125 }, { "start": 3988.19, "end": 3988.59, "word": " of", "probability": 0.89208984375 }, { "start": 3988.59, "end": 3989.15, "word": " the", "probability": 0.5234375 }, { "start": 3989.15, "end": 3990.27, "word": " question", "probability": 0.74951171875 }, { "start": 3990.27, "end": 3990.61, "word": " of", "probability": 0.83203125 }, { "start": 3990.61, "end": 3991.77, "word": " when", "probability": 0.42724609375 }, { "start": 3991.77, "end": 3992.09, "word": " you", "probability": 0.89892578125 }, { "start": 3992.09, "end": 3992.49, "word": " build", "probability": 0.86962890625 }, { "start": 3992.49, "end": 3992.73, "word": " these", "probability": 0.697265625 }, { "start": 3992.73, "end": 3993.19, "word": " models", "probability": 0.80517578125 }, { "start": 3993.19, "end": 3993.65, "word": ",", "probability": 0.87158203125 } ] }, { "id": 1075, "seek": 389676, "start": 3993.65, "end": 3996.17, "text": " the training process literally punishes the model", "tokens": [ 51214, 264, 3097, 1399, 3736, 9842, 279, 264, 2316, 51364 ], "temperature": 0.0, "avg_logprob": -0.2077205910402186, "compression_ratio": 1.49746192893401, "no_speech_prob": 0.004528045654296875, "words": [ { "start": 3993.65, "end": 3993.93, "word": " the", "probability": 0.57763671875 }, { "start": 3993.93, "end": 3994.31, "word": " training", "probability": 0.7587890625 }, { "start": 3994.31, "end": 3994.77, "word": " process", "probability": 0.86962890625 }, { "start": 3994.77, "end": 3995.21, "word": " literally", "probability": 0.75244140625 }, { "start": 3995.21, "end": 3995.79, "word": " punishes", "probability": 0.88818359375 }, { "start": 3995.79, "end": 3995.93, "word": " the", "probability": 0.814453125 }, { "start": 3995.93, "end": 3996.17, "word": " model", "probability": 0.79052734375 } ] }, { "id": 1076, "seek": 389676, "start": 3996.17, "end": 3998.75, "text": " for getting it wrong every single time.", "tokens": [ 51364, 337, 1242, 309, 2085, 633, 2167, 565, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.2077205910402186, "compression_ratio": 1.49746192893401, "no_speech_prob": 0.004528045654296875, "words": [ { "start": 3996.17, "end": 3996.37, "word": " for", "probability": 0.9013671875 }, { "start": 3996.37, "end": 3996.59, "word": " getting", "probability": 0.90576171875 }, { "start": 3996.59, "end": 3996.77, "word": " it", "probability": 0.90087890625 }, { "start": 3996.77, "end": 3997.07, "word": " wrong", "probability": 0.861328125 }, { "start": 3997.07, "end": 3997.47, "word": " every", "probability": 0.72998046875 }, { "start": 3997.47, "end": 3997.69, "word": " single", "probability": 0.87109375 }, { "start": 3997.69, "end": 3998.11, "word": " time", "probability": 0.8017578125 }, { "start": 3998.11, "end": 3998.75, "word": ".", "probability": 0.9482421875 } ] }, { "id": 1077, "seek": 389676, "start": 4001.51, "end": 4003.61, "text": " And in this case...", "tokens": [ 51664, 400, 294, 341, 1389, 485, 51764 ], "temperature": 0.0, "avg_logprob": -0.2077205910402186, "compression_ratio": 1.49746192893401, "no_speech_prob": 0.004528045654296875, "words": [ { "start": 4001.51, "end": 4002.15, "word": " And", "probability": 0.47900390625 }, { "start": 4002.15, "end": 4002.79, "word": " in", "probability": 0.88916015625 }, { "start": 4002.79, "end": 4002.97, "word": " this", "probability": 0.8798828125 }, { "start": 4002.97, "end": 4003.61, "word": " case...", "probability": 0.697509765625 } ] }, { "id": 1078, "seek": 392508, "start": 4005.73, "end": 4010.77, "text": " Yeah, so Chris, you're asking about a false negative.", "tokens": [ 50364, 865, 11, 370, 6688, 11, 291, 434, 3365, 466, 257, 7908, 3671, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.1908967388064965, "compression_ratio": 1.707070707070707, "no_speech_prob": 0.0012826919555664062, "words": [ { "start": 4005.73, "end": 4005.91, "word": " Yeah", "probability": 0.6240234375 }, { "start": 4005.91, "end": 4006.11, "word": ",", "probability": 0.61083984375 }, { "start": 4006.11, "end": 4006.21, "word": " so", "probability": 0.82275390625 }, { "start": 4006.21, "end": 4007.51, "word": " Chris", "probability": 0.50390625 }, { "start": 4007.51, "end": 4007.65, "word": ",", "probability": 0.81640625 }, { "start": 4007.65, "end": 4007.75, "word": " you're", "probability": 0.905029296875 }, { "start": 4007.75, "end": 4007.99, "word": " asking", "probability": 0.81494140625 }, { "start": 4007.99, "end": 4008.37, "word": " about", "probability": 0.82373046875 }, { "start": 4008.79, "end": 4009.05, "word": " a false", "probability": 0.857421875 }, { "start": 4009.05, "end": 4010.25, "word": " negative", "probability": 0.48046875 }, { "start": 4010.25, "end": 4010.77, "word": ".", "probability": 0.94970703125 } ] }, { "id": 1079, "seek": 392508, "start": 4014.01, "end": 4018.93, "text": " A false negative is when you've got something that's malicious,", "tokens": [ 50764, 316, 7908, 3671, 307, 562, 291, 600, 658, 746, 300, 311, 33496, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.1908967388064965, "compression_ratio": 1.707070707070707, "no_speech_prob": 0.0012826919555664062, "words": [ { "start": 4014.01, "end": 4014.53, "word": " A", "probability": 0.509765625 }, { "start": 4014.53, "end": 4014.95, "word": " false", "probability": 0.85302734375 }, { "start": 4014.95, "end": 4015.31, "word": " negative", "probability": 0.8759765625 }, { "start": 4015.31, "end": 4015.89, "word": " is", "probability": 0.8994140625 }, { "start": 4015.89, "end": 4017.31, "word": " when", "probability": 0.83544921875 }, { "start": 4017.31, "end": 4017.63, "word": " you've", "probability": 0.920654296875 }, { "start": 4017.63, "end": 4017.81, "word": " got", "probability": 0.912109375 }, { "start": 4017.81, "end": 4018.11, "word": " something", "probability": 0.7392578125 }, { "start": 4018.11, "end": 4018.39, "word": " that's", "probability": 0.9326171875 }, { "start": 4018.39, "end": 4018.79, "word": " malicious", "probability": 0.85107421875 }, { "start": 4018.79, "end": 4018.93, "word": ",", "probability": 0.72314453125 } ] }, { "id": 1080, "seek": 392508, "start": 4018.93, "end": 4021.67, "text": " that's misclassified as benign,", "tokens": [ 51014, 300, 311, 3346, 11665, 2587, 382, 3271, 788, 11, 51164 ], "temperature": 0.0, "avg_logprob": -0.1908967388064965, "compression_ratio": 1.707070707070707, "no_speech_prob": 0.0012826919555664062, "words": [ { "start": 4018.93, "end": 4019.09, "word": " that's", "probability": 0.863037109375 }, { "start": 4019.09, "end": 4020.05, "word": " misclassified", "probability": 0.9427083333333334 }, { "start": 4020.05, "end": 4020.21, "word": " as", "probability": 0.6572265625 }, { "start": 4020.21, "end": 4020.71, "word": " benign", "probability": 0.947265625 }, { "start": 4020.71, "end": 4021.67, "word": ",", "probability": 0.79833984375 } ] }, { "id": 1081, "seek": 392508, "start": 4021.67, "end": 4024.07, "text": " which is what the point of the model is,", "tokens": [ 51164, 597, 307, 437, 264, 935, 295, 264, 2316, 307, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.1908967388064965, "compression_ratio": 1.707070707070707, "no_speech_prob": 0.0012826919555664062, "words": [ { "start": 4021.67, "end": 4022.63, "word": " which", "probability": 0.91162109375 }, { "start": 4022.63, "end": 4022.77, "word": " is", "probability": 0.90380859375 }, { "start": 4022.77, "end": 4023.01, "word": " what", "probability": 0.88525390625 }, { "start": 4023.01, "end": 4023.23, "word": " the", "probability": 0.80859375 }, { "start": 4023.23, "end": 4023.45, "word": " point", "probability": 0.8740234375 }, { "start": 4023.45, "end": 4023.55, "word": " of", "probability": 0.90771484375 }, { "start": 4023.55, "end": 4023.63, "word": " the", "probability": 0.8154296875 }, { "start": 4023.63, "end": 4023.77, "word": " model", "probability": 0.81005859375 }, { "start": 4023.77, "end": 4023.99, "word": " is", "probability": 0.90087890625 }, { "start": 4023.99, "end": 4024.07, "word": ",", "probability": 0.5458984375 } ] }, { "id": 1082, "seek": 392508, "start": 4024.07, "end": 4028.11, "text": " but what GT brought up is probably more important", "tokens": [ 51264, 457, 437, 17530, 3038, 493, 307, 1391, 544, 1021, 51464 ], "temperature": 0.0, "avg_logprob": -0.1908967388064965, "compression_ratio": 1.707070707070707, "no_speech_prob": 0.0012826919555664062, "words": [ { "start": 4024.07, "end": 4024.19, "word": " but", "probability": 0.88623046875 }, { "start": 4024.19, "end": 4025.19, "word": " what", "probability": 0.8984375 }, { "start": 4025.19, "end": 4026.01, "word": " GT", "probability": 0.8671875 }, { "start": 4026.01, "end": 4026.41, "word": " brought", "probability": 0.9287109375 }, { "start": 4026.41, "end": 4026.73, "word": " up", "probability": 0.9033203125 }, { "start": 4026.73, "end": 4027.03, "word": " is", "probability": 0.861328125 }, { "start": 4027.03, "end": 4027.47, "word": " probably", "probability": 0.9072265625 }, { "start": 4027.47, "end": 4027.77, "word": " more", "probability": 0.88330078125 }, { "start": 4027.77, "end": 4028.11, "word": " important", "probability": 0.79345703125 } ] }, { "id": 1083, "seek": 392508, "start": 4028.11, "end": 4029.53, "text": " is when you have something that's benign", "tokens": [ 51464, 307, 562, 291, 362, 746, 300, 311, 3271, 788, 51564 ], "temperature": 0.0, "avg_logprob": -0.1908967388064965, "compression_ratio": 1.707070707070707, "no_speech_prob": 0.0012826919555664062, "words": [ { "start": 4028.11, "end": 4028.29, "word": " is", "probability": 0.357421875 }, { "start": 4028.29, "end": 4028.41, "word": " when", "probability": 0.84912109375 }, { "start": 4028.41, "end": 4028.51, "word": " you", "probability": 0.89697265625 }, { "start": 4028.51, "end": 4028.69, "word": " have", "probability": 0.884765625 }, { "start": 4028.69, "end": 4028.95, "word": " something", "probability": 0.72509765625 }, { "start": 4028.95, "end": 4029.15, "word": " that's", "probability": 0.873779296875 }, { "start": 4029.15, "end": 4029.53, "word": " benign", "probability": 0.95654296875 } ] }, { "id": 1084, "seek": 392508, "start": 4029.53, "end": 4031.37, "text": " that you classify as malicious,", "tokens": [ 51564, 300, 291, 33872, 382, 33496, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.1908967388064965, "compression_ratio": 1.707070707070707, "no_speech_prob": 0.0012826919555664062, "words": [ { "start": 4029.53, "end": 4029.67, "word": " that", "probability": 0.6279296875 }, { "start": 4029.67, "end": 4029.77, "word": " you", "probability": 0.85107421875 }, { "start": 4029.77, "end": 4030.07, "word": " classify", "probability": 0.9326171875 }, { "start": 4030.07, "end": 4030.29, "word": " as", "probability": 0.91064453125 }, { "start": 4030.29, "end": 4030.63, "word": " malicious", "probability": 0.86083984375 }, { "start": 4030.63, "end": 4031.37, "word": ",", "probability": 0.66845703125 } ] }, { "id": 1085, "seek": 392508, "start": 4031.37, "end": 4034.05, "text": " that is much more common", "tokens": [ 51664, 300, 307, 709, 544, 2689, 51764 ], "temperature": 0.0, "avg_logprob": -0.1908967388064965, "compression_ratio": 1.707070707070707, "no_speech_prob": 0.0012826919555664062, "words": [ { "start": 4031.37, "end": 4031.53, "word": " that", "probability": 0.87353515625 }, { "start": 4031.53, "end": 4032.73, "word": " is", "probability": 0.57373046875 }, { "start": 4032.73, "end": 4033.65, "word": " much", "probability": 0.80029296875 }, { "start": 4033.65, "end": 4033.81, "word": " more", "probability": 0.87841796875 }, { "start": 4033.81, "end": 4034.05, "word": " common", "probability": 0.7294921875 } ] }, { "id": 1086, "seek": 395116, "start": 4034.05, "end": 4039.27, "text": " because you get more benign things on users' devices,", "tokens": [ 50364, 570, 291, 483, 544, 3271, 788, 721, 322, 5022, 6, 5759, 11, 50614 ], "temperature": 0.0, "avg_logprob": -0.19797207732149896, "compression_ratio": 1.5686274509803921, "no_speech_prob": 0.01132965087890625, "words": [ { "start": 4034.05, "end": 4034.35, "word": " because", "probability": 0.73974609375 }, { "start": 4034.35, "end": 4035.33, "word": " you", "probability": 0.81298828125 }, { "start": 4035.33, "end": 4035.55, "word": " get", "probability": 0.8876953125 }, { "start": 4035.55, "end": 4035.93, "word": " more", "probability": 0.8798828125 }, { "start": 4035.93, "end": 4036.81, "word": " benign", "probability": 0.926513671875 }, { "start": 4036.81, "end": 4037.23, "word": " things", "probability": 0.74560546875 }, { "start": 4037.23, "end": 4037.51, "word": " on", "probability": 0.9052734375 }, { "start": 4037.51, "end": 4037.91, "word": " users", "probability": 0.458984375 }, { "start": 4037.91, "end": 4038.03, "word": "'", "probability": 0.74072265625 }, { "start": 4038.03, "end": 4038.37, "word": " devices", "probability": 0.912109375 }, { "start": 4038.37, "end": 4039.27, "word": ",", "probability": 0.3671875 } ] }, { "id": 1087, "seek": 395116, "start": 4039.27, "end": 4040.89, "text": " as GT brought up.", "tokens": [ 50614, 382, 17530, 3038, 493, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.19797207732149896, "compression_ratio": 1.5686274509803921, "no_speech_prob": 0.01132965087890625, "words": [ { "start": 4039.27, "end": 4039.63, "word": " as", "probability": 0.90380859375 }, { "start": 4039.63, "end": 4039.89, "word": " GT", "probability": 0.65771484375 }, { "start": 4039.89, "end": 4040.17, "word": " brought", "probability": 0.91943359375 }, { "start": 4040.17, "end": 4040.41, "word": " up", "probability": 0.884765625 }, { "start": 4040.41, "end": 4040.89, "word": ".", "probability": 0.9658203125 } ] }, { "id": 1088, "seek": 395116, "start": 4042.37, "end": 4045.45, "text": " So in this case, I don't think this was intentional.", "tokens": [ 50764, 407, 294, 341, 1389, 11, 286, 500, 380, 519, 341, 390, 21935, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.19797207732149896, "compression_ratio": 1.5686274509803921, "no_speech_prob": 0.01132965087890625, "words": [ { "start": 4042.37, "end": 4042.79, "word": " So", "probability": 0.450927734375 }, { "start": 4042.79, "end": 4043.17, "word": " in", "probability": 0.57763671875 }, { "start": 4043.17, "end": 4043.31, "word": " this", "probability": 0.8798828125 }, { "start": 4043.31, "end": 4043.53, "word": " case", "probability": 0.81396484375 }, { "start": 4043.53, "end": 4043.55, "word": ",", "probability": 0.91650390625 }, { "start": 4043.55, "end": 4043.67, "word": " I", "probability": 0.9990234375 }, { "start": 4043.67, "end": 4043.85, "word": " don't", "probability": 0.952880859375 }, { "start": 4043.85, "end": 4044.23, "word": " think", "probability": 0.80712890625 }, { "start": 4044.23, "end": 4044.39, "word": " this", "probability": 0.8759765625 }, { "start": 4044.39, "end": 4044.53, "word": " was", "probability": 0.8828125 }, { "start": 4044.53, "end": 4044.97, "word": " intentional", "probability": 0.84765625 }, { "start": 4044.97, "end": 4045.45, "word": ".", "probability": 0.96826171875 } ] }, { "id": 1089, "seek": 395116, "start": 4046.93, "end": 4048.53, "text": " No, this wasn't intentional.", "tokens": [ 51014, 883, 11, 341, 2067, 380, 21935, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.19797207732149896, "compression_ratio": 1.5686274509803921, "no_speech_prob": 0.01132965087890625, "words": [ { "start": 4046.93, "end": 4047.41, "word": " No", "probability": 0.873046875 }, { "start": 4047.41, "end": 4047.49, "word": ",", "probability": 0.96044921875 }, { "start": 4047.49, "end": 4047.67, "word": " this", "probability": 0.880859375 }, { "start": 4047.67, "end": 4047.99, "word": " wasn't", "probability": 0.8935546875 }, { "start": 4047.99, "end": 4048.27, "word": " intentional", "probability": 0.83740234375 }, { "start": 4048.27, "end": 4048.53, "word": ".", "probability": 0.74169921875 } ] }, { "id": 1090, "seek": 395116, "start": 4048.53, "end": 4051.09, "text": " This is just the way that the model learned.", "tokens": [ 51064, 639, 307, 445, 264, 636, 300, 264, 2316, 3264, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.19797207732149896, "compression_ratio": 1.5686274509803921, "no_speech_prob": 0.01132965087890625, "words": [ { "start": 4048.53, "end": 4048.67, "word": " This", "probability": 0.79736328125 }, { "start": 4048.67, "end": 4048.79, "word": " is", "probability": 0.8720703125 }, { "start": 4048.79, "end": 4048.99, "word": " just", "probability": 0.87890625 }, { "start": 4048.99, "end": 4049.15, "word": " the", "probability": 0.794921875 }, { "start": 4049.15, "end": 4049.33, "word": " way", "probability": 0.88623046875 }, { "start": 4049.33, "end": 4049.49, "word": " that", "probability": 0.75634765625 }, { "start": 4049.49, "end": 4049.63, "word": " the", "probability": 0.814453125 }, { "start": 4049.63, "end": 4049.87, "word": " model", "probability": 0.8271484375 }, { "start": 4049.87, "end": 4050.61, "word": " learned", "probability": 0.81689453125 }, { "start": 4050.61, "end": 4051.09, "word": ".", "probability": 0.88720703125 } ] }, { "id": 1091, "seek": 395116, "start": 4052.27, "end": 4053.81, "text": " And then as we go through the other models,", "tokens": [ 51264, 400, 550, 382, 321, 352, 807, 264, 661, 5245, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.19797207732149896, "compression_ratio": 1.5686274509803921, "no_speech_prob": 0.01132965087890625, "words": [ { "start": 4052.27, "end": 4052.47, "word": " And", "probability": 0.77783203125 }, { "start": 4052.47, "end": 4052.57, "word": " then", "probability": 0.55078125 }, { "start": 4052.57, "end": 4052.73, "word": " as", "probability": 0.810546875 }, { "start": 4052.73, "end": 4052.85, "word": " we", "probability": 0.90869140625 }, { "start": 4052.85, "end": 4052.97, "word": " go", "probability": 0.90234375 }, { "start": 4052.97, "end": 4053.11, "word": " through", "probability": 0.8056640625 }, { "start": 4053.11, "end": 4053.25, "word": " the", "probability": 0.80908203125 }, { "start": 4053.25, "end": 4053.41, "word": " other", "probability": 0.78369140625 }, { "start": 4053.41, "end": 4053.73, "word": " models", "probability": 0.8173828125 }, { "start": 4053.73, "end": 4053.81, "word": ",", "probability": 0.95458984375 } ] }, { "id": 1092, "seek": 395116, "start": 4053.81, "end": 4055.81, "text": " you'll see how these shift.", "tokens": [ 51364, 291, 603, 536, 577, 613, 5513, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.19797207732149896, "compression_ratio": 1.5686274509803921, "no_speech_prob": 0.01132965087890625, "words": [ { "start": 4053.81, "end": 4053.97, "word": " you'll", "probability": 0.89306640625 }, { "start": 4053.97, "end": 4054.19, "word": " see", "probability": 0.82275390625 }, { "start": 4054.19, "end": 4054.63, "word": " how", "probability": 0.6904296875 }, { "start": 4054.63, "end": 4054.97, "word": " these", "probability": 0.70703125 }, { "start": 4054.97, "end": 4055.33, "word": " shift", "probability": 0.87060546875 }, { "start": 4055.33, "end": 4055.81, "word": ".", "probability": 0.98974609375 } ] }, { "id": 1093, "seek": 395116, "start": 4056.41, "end": 4060.13, "text": " Yeah, but this is honestly the way it looks like.", "tokens": [ 51464, 865, 11, 457, 341, 307, 6095, 264, 636, 309, 1542, 411, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.19797207732149896, "compression_ratio": 1.5686274509803921, "no_speech_prob": 0.01132965087890625, "words": [ { "start": 4056.41, "end": 4056.63, "word": " Yeah", "probability": 0.6416015625 }, { "start": 4056.63, "end": 4056.91, "word": ",", "probability": 0.669921875 }, { "start": 4056.91, "end": 4057.15, "word": " but", "probability": 0.87353515625 }, { "start": 4057.15, "end": 4057.39, "word": " this", "probability": 0.76806640625 }, { "start": 4057.39, "end": 4057.59, "word": " is", "probability": 0.8974609375 }, { "start": 4057.59, "end": 4057.99, "word": " honestly", "probability": 0.6865234375 }, { "start": 4057.99, "end": 4058.39, "word": " the", "probability": 0.43896484375 }, { "start": 4058.39, "end": 4058.73, "word": " way", "probability": 0.8984375 }, { "start": 4058.73, "end": 4058.97, "word": " it", "probability": 0.8759765625 }, { "start": 4058.97, "end": 4059.67, "word": " looks", "probability": 0.51611328125 }, { "start": 4059.67, "end": 4059.95, "word": " like", "probability": 0.55517578125 }, { "start": 4059.95, "end": 4060.13, "word": ".", "probability": 0.6025390625 } ] }, { "id": 1094, "seek": 397786, "start": 4060.13, "end": 4063.11, "text": " You've got the ham stuff that are classified as spam", "tokens": [ 50364, 509, 600, 658, 264, 7852, 1507, 300, 366, 20627, 382, 24028, 50514 ], "temperature": 0.0, "avg_logprob": -0.2365873914904299, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 4060.13, "end": 4060.63, "word": " You've", "probability": 0.6070556640625 }, { "start": 4060.63, "end": 4060.75, "word": " got", "probability": 0.8955078125 }, { "start": 4060.75, "end": 4060.89, "word": " the", "probability": 0.80615234375 }, { "start": 4060.89, "end": 4061.09, "word": " ham", "probability": 0.49072265625 }, { "start": 4061.09, "end": 4061.41, "word": " stuff", "probability": 0.76416015625 }, { "start": 4061.41, "end": 4062.11, "word": " that", "probability": 0.67431640625 }, { "start": 4062.11, "end": 4062.23, "word": " are", "probability": 0.7197265625 }, { "start": 4062.23, "end": 4062.53, "word": " classified", "probability": 0.92431640625 }, { "start": 4062.53, "end": 4062.77, "word": " as", "probability": 0.90966796875 }, { "start": 4062.77, "end": 4063.11, "word": " spam", "probability": 0.9228515625 } ] }, { "id": 1095, "seek": 397786, "start": 4063.11, "end": 4065.33, "text": " is very low so that all the user experience", "tokens": [ 50514, 307, 588, 2295, 370, 300, 439, 264, 4195, 1752, 50614 ], "temperature": 0.0, "avg_logprob": -0.2365873914904299, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 4063.11, "end": 4063.35, "word": " is", "probability": 0.7197265625 }, { "start": 4063.35, "end": 4063.57, "word": " very", "probability": 0.70751953125 }, { "start": 4063.57, "end": 4063.91, "word": " low", "probability": 0.89599609375 }, { "start": 4063.91, "end": 4064.45, "word": " so", "probability": 0.43359375 }, { "start": 4064.45, "end": 4064.65, "word": " that", "probability": 0.75634765625 }, { "start": 4064.65, "end": 4064.83, "word": " all", "probability": 0.537109375 }, { "start": 4064.83, "end": 4064.91, "word": " the", "probability": 0.7412109375 }, { "start": 4064.91, "end": 4065.09, "word": " user", "probability": 0.73193359375 }, { "start": 4065.09, "end": 4065.33, "word": " experience", "probability": 0.7119140625 } ] }, { "id": 1096, "seek": 397786, "start": 4065.79, "end": 4067.47, "text": " isn't impacted that badly.", "tokens": [ 50614, 1943, 380, 15653, 300, 13425, 13, 50714 ], "temperature": 0.0, "avg_logprob": -0.2365873914904299, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 4065.79, "end": 4066.09, "word": " isn't", "probability": 0.800048828125 }, { "start": 4066.09, "end": 4066.45, "word": " impacted", "probability": 0.87939453125 }, { "start": 4066.45, "end": 4066.69, "word": " that", "probability": 0.861328125 }, { "start": 4066.69, "end": 4066.99, "word": " badly", "probability": 0.90283203125 }, { "start": 4066.99, "end": 4067.47, "word": ".", "probability": 0.492431640625 } ] }, { "id": 1097, "seek": 397786, "start": 4067.51, "end": 4069.25, "text": " And the spam stuff that's classified as ham", "tokens": [ 50714, 400, 264, 24028, 1507, 300, 311, 20627, 382, 7852, 50814 ], "temperature": 0.0, "avg_logprob": -0.2365873914904299, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 4067.51, "end": 4067.55, "word": " And", "probability": 0.488525390625 }, { "start": 4067.55, "end": 4067.67, "word": " the", "probability": 0.79541015625 }, { "start": 4067.67, "end": 4067.95, "word": " spam", "probability": 0.9384765625 }, { "start": 4067.95, "end": 4068.21, "word": " stuff", "probability": 0.7802734375 }, { "start": 4068.21, "end": 4068.39, "word": " that's", "probability": 0.8310546875 }, { "start": 4068.39, "end": 4068.67, "word": " classified", "probability": 0.93310546875 }, { "start": 4068.67, "end": 4068.95, "word": " as", "probability": 0.9130859375 }, { "start": 4068.95, "end": 4069.25, "word": " ham", "probability": 0.8720703125 } ] }, { "id": 1098, "seek": 397786, "start": 4069.25, "end": 4071.29, "text": " is relatively high,", "tokens": [ 50814, 307, 7226, 1090, 11, 50914 ], "temperature": 0.0, "avg_logprob": -0.2365873914904299, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 4069.25, "end": 4069.85, "word": " is", "probability": 0.8837890625 }, { "start": 4069.85, "end": 4070.31, "word": " relatively", "probability": 0.69287109375 }, { "start": 4070.31, "end": 4070.79, "word": " high", "probability": 0.86376953125 }, { "start": 4070.79, "end": 4071.29, "word": ",", "probability": 0.335693359375 } ] }, { "id": 1099, "seek": 397786, "start": 4071.29, "end": 4073.23, "text": " but you've got a trade-off", "tokens": [ 50914, 457, 291, 600, 658, 257, 4923, 12, 4506, 51014 ], "temperature": 0.0, "avg_logprob": -0.2365873914904299, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 4071.29, "end": 4071.47, "word": " but", "probability": 0.86328125 }, { "start": 4071.47, "end": 4072.65, "word": " you've", "probability": 0.887939453125 }, { "start": 4072.65, "end": 4072.77, "word": " got", "probability": 0.88671875 }, { "start": 4072.89, "end": 4073.13, "word": " a trade", "probability": 0.80419921875 }, { "start": 4073.13, "end": 4073.23, "word": "-off", "probability": 0.6837158203125 } ] }, { "id": 1100, "seek": 397786, "start": 4073.23, "end": 4075.79, "text": " between the false positives and the false negatives.", "tokens": [ 51014, 1296, 264, 7908, 35127, 293, 264, 7908, 40019, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.2365873914904299, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 4073.23, "end": 4073.55, "word": " between", "probability": 0.76171875 }, { "start": 4073.55, "end": 4073.77, "word": " the", "probability": 0.8056640625 }, { "start": 4073.77, "end": 4074.01, "word": " false", "probability": 0.8544921875 }, { "start": 4074.01, "end": 4074.45, "word": " positives", "probability": 0.849609375 }, { "start": 4074.45, "end": 4074.65, "word": " and", "probability": 0.88818359375 }, { "start": 4074.65, "end": 4074.77, "word": " the", "probability": 0.77001953125 }, { "start": 4074.77, "end": 4074.97, "word": " false", "probability": 0.83642578125 }, { "start": 4074.97, "end": 4075.31, "word": " negatives", "probability": 0.87548828125 }, { "start": 4075.31, "end": 4075.79, "word": ".", "probability": 0.99072265625 } ] }, { "id": 1101, "seek": 397786, "start": 4075.81, "end": 4076.97, "text": " Yeah, exactly.", "tokens": [ 51114, 865, 11, 2293, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.2365873914904299, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 4075.81, "end": 4075.99, "word": " Yeah", "probability": 0.1822509765625 }, { "start": 4075.99, "end": 4076.21, "word": ",", "probability": 0.87255859375 }, { "start": 4076.21, "end": 4076.49, "word": " exactly", "probability": 0.7744140625 }, { "start": 4076.49, "end": 4076.97, "word": ".", "probability": 0.98779296875 } ] }, { "id": 1102, "seek": 397786, "start": 4077.43, "end": 4081.01, "text": " And I hope that answered your question, Christopher.", "tokens": [ 51214, 400, 286, 1454, 300, 10103, 428, 1168, 11, 20649, 13, 51414 ], "temperature": 0.0, "avg_logprob": -0.2365873914904299, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 4077.43, "end": 4077.75, "word": " And", "probability": 0.397705078125 }, { "start": 4077.75, "end": 4078.07, "word": " I", "probability": 0.96337890625 }, { "start": 4078.07, "end": 4078.25, "word": " hope", "probability": 0.82763671875 }, { "start": 4078.25, "end": 4078.35, "word": " that", "probability": 0.87939453125 }, { "start": 4078.35, "end": 4078.55, "word": " answered", "probability": 0.418701171875 }, { "start": 4078.55, "end": 4078.79, "word": " your", "probability": 0.79248046875 }, { "start": 4078.79, "end": 4079.15, "word": " question", "probability": 0.78857421875 }, { "start": 4079.15, "end": 4080.45, "word": ",", "probability": 0.81689453125 }, { "start": 4080.45, "end": 4080.79, "word": " Christopher", "probability": 0.595703125 }, { "start": 4080.79, "end": 4081.01, "word": ".", "probability": 0.282470703125 } ] }, { "id": 1103, "seek": 397786, "start": 4081.47, "end": 4085.87, "text": " I think going through the other models", "tokens": [ 51464, 286, 519, 516, 807, 264, 661, 5245, 51564 ], "temperature": 0.0, "avg_logprob": -0.2365873914904299, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 4081.47, "end": 4081.95, "word": " I", "probability": 0.9443359375 }, { "start": 4083.51, "end": 4084.79, "word": " think", "probability": 0.802734375 }, { "start": 4084.79, "end": 4085.01, "word": " going", "probability": 0.853515625 }, { "start": 4085.01, "end": 4085.19, "word": " through", "probability": 0.7783203125 }, { "start": 4085.19, "end": 4085.35, "word": " the", "probability": 0.81103515625 }, { "start": 4085.35, "end": 4085.51, "word": " other", "probability": 0.78759765625 }, { "start": 4085.51, "end": 4085.87, "word": " models", "probability": 0.8203125 } ] }, { "id": 1104, "seek": 397786, "start": 4085.87, "end": 4088.39, "text": " will kind of help answer it a little bit more too.", "tokens": [ 51564, 486, 733, 295, 854, 1867, 309, 257, 707, 857, 544, 886, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.2365873914904299, "compression_ratio": 1.6666666666666667, "no_speech_prob": 0.0185394287109375, "words": [ { "start": 4085.87, "end": 4086.01, "word": " will", "probability": 0.7548828125 }, { "start": 4086.01, "end": 4086.17, "word": " kind", "probability": 0.46337890625 }, { "start": 4086.17, "end": 4086.29, "word": " of", "probability": 0.9091796875 }, { "start": 4086.29, "end": 4086.53, "word": " help", "probability": 0.82275390625 }, { "start": 4086.53, "end": 4087.03, "word": " answer", "probability": 0.84326171875 }, { "start": 4087.03, "end": 4087.17, "word": " it", "probability": 0.462890625 }, { "start": 4087.23, "end": 4087.33, "word": " a little", "probability": 0.802734375 }, { "start": 4087.33, "end": 4087.49, "word": " bit", "probability": 0.84814453125 }, { "start": 4087.49, "end": 4087.67, "word": " more", "probability": 0.88623046875 }, { "start": 4087.67, "end": 4087.91, "word": " too", "probability": 0.49169921875 }, { "start": 4087.91, "end": 4088.39, "word": ".", "probability": 0.99560546875 } ] }, { "id": 1105, "seek": 400724, "start": 4090.83, "end": 4092.39, "text": " So accuracy, 87%.", "tokens": [ 50414, 407, 14170, 11, 27990, 6856, 50564 ], "temperature": 0.0, "avg_logprob": -0.1741286044797072, "compression_ratio": 1.373134328358209, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 4090.83, "end": 4091.41, "word": " So", "probability": 0.74169921875 }, { "start": 4091.41, "end": 4091.81, "word": " accuracy", "probability": 0.60986328125 }, { "start": 4091.81, "end": 4092.09, "word": ",", "probability": 0.52978515625 }, { "start": 4092.09, "end": 4092.39, "word": " 87%.", "probability": 0.5291748046875 } ] }, { "id": 1106, "seek": 400724, "start": 4092.95, "end": 4094.63, "text": " 87.5%.", "tokens": [ 50564, 27990, 13, 20, 6856, 50664 ], "temperature": 0.0, "avg_logprob": -0.1741286044797072, "compression_ratio": 1.373134328358209, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 4092.95, "end": 4093.55, "word": " 87", "probability": 0.89111328125 }, { "start": 4093.55, "end": 4094.63, "word": ".5%.", "probability": 0.7913411458333334 } ] }, { "id": 1107, "seek": 400724, "start": 4094.63, "end": 4096.39, "text": " 94.3%.", "tokens": [ 50664, 30849, 13, 18, 6856, 50764 ], "temperature": 0.0, "avg_logprob": -0.1741286044797072, "compression_ratio": 1.373134328358209, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 4094.63, "end": 4095.51, "word": " 94", "probability": 0.93115234375 }, { "start": 4095.51, "end": 4096.39, "word": ".3%.", "probability": 0.9822591145833334 } ] }, { "id": 1108, "seek": 400724, "start": 4097.87, "end": 4099.61, "text": " In this one, we're going to use", "tokens": [ 50814, 682, 341, 472, 11, 321, 434, 516, 281, 764, 50914 ], "temperature": 0.0, "avg_logprob": -0.1741286044797072, "compression_ratio": 1.373134328358209, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 4097.87, "end": 4098.45, "word": " In", "probability": 0.8935546875 }, { "start": 4098.45, "end": 4098.59, "word": " this", "probability": 0.88330078125 }, { "start": 4098.59, "end": 4098.75, "word": " one", "probability": 0.81982421875 }, { "start": 4098.75, "end": 4098.79, "word": ",", "probability": 0.626953125 }, { "start": 4098.79, "end": 4098.89, "word": " we're", "probability": 0.927490234375 }, { "start": 4098.89, "end": 4099.07, "word": " going", "probability": 0.8505859375 }, { "start": 4099.07, "end": 4099.25, "word": " to", "probability": 0.90380859375 }, { "start": 4099.25, "end": 4099.61, "word": " use", "probability": 0.81591796875 } ] }, { "id": 1109, "seek": 400724, "start": 4100.41, "end": 4102.21, "text": " a model that we haven't used before,", "tokens": [ 50914, 257, 2316, 300, 321, 2378, 380, 1143, 949, 11, 51014 ], "temperature": 0.0, "avg_logprob": -0.1741286044797072, "compression_ratio": 1.373134328358209, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 4100.41, "end": 4100.59, "word": " a model", "probability": 0.818359375 }, { "start": 4100.59, "end": 4100.75, "word": " that", "probability": 0.8837890625 }, { "start": 4100.75, "end": 4100.89, "word": " we", "probability": 0.90673828125 }, { "start": 4100.89, "end": 4101.25, "word": " haven't", "probability": 0.940185546875 }, { "start": 4101.25, "end": 4101.45, "word": " used", "probability": 0.8134765625 }, { "start": 4101.45, "end": 4101.87, "word": " before", "probability": 0.80029296875 }, { "start": 4101.87, "end": 4102.21, "word": ",", "probability": 0.86376953125 } ] }, { "id": 1110, "seek": 400724, "start": 4102.21, "end": 4103.45, "text": " logistic regression.", "tokens": [ 51014, 3565, 3142, 24590, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.1741286044797072, "compression_ratio": 1.373134328358209, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 4102.21, "end": 4102.45, "word": " logistic", "probability": 0.926025390625 }, { "start": 4102.45, "end": 4102.87, "word": " regression", "probability": 0.8818359375 }, { "start": 4102.87, "end": 4103.45, "word": ".", "probability": 0.88427734375 } ] }, { "id": 1111, "seek": 400724, "start": 4103.69, "end": 4105.97, "text": " And so with Scikit-learn, it's very easy.", "tokens": [ 51114, 400, 370, 365, 16942, 22681, 12, 306, 1083, 11, 309, 311, 588, 1858, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.1741286044797072, "compression_ratio": 1.373134328358209, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 4103.69, "end": 4103.77, "word": " And", "probability": 0.857421875 }, { "start": 4103.77, "end": 4104.19, "word": " so", "probability": 0.896484375 }, { "start": 4104.19, "end": 4104.55, "word": " with", "probability": 0.72265625 }, { "start": 4104.55, "end": 4104.81, "word": " Scikit", "probability": 0.6993408203125 }, { "start": 4104.81, "end": 4105.01, "word": "-learn", "probability": 0.8525390625 }, { "start": 4105.01, "end": 4105.07, "word": ",", "probability": 0.7958984375 }, { "start": 4105.07, "end": 4105.25, "word": " it's", "probability": 0.950927734375 }, { "start": 4105.25, "end": 4105.53, "word": " very", "probability": 0.7333984375 }, { "start": 4105.53, "end": 4105.79, "word": " easy", "probability": 0.7998046875 }, { "start": 4105.79, "end": 4105.97, "word": ".", "probability": 0.69091796875 } ] }, { "id": 1112, "seek": 400724, "start": 4105.97, "end": 4107.57, "text": " It's the exact same thing.", "tokens": [ 51214, 467, 311, 264, 1900, 912, 551, 13, 51314 ], "temperature": 0.0, "avg_logprob": -0.1741286044797072, "compression_ratio": 1.373134328358209, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 4105.97, "end": 4106.05, "word": " It's", "probability": 0.949462890625 }, { "start": 4106.05, "end": 4106.35, "word": " the", "probability": 0.81005859375 }, { "start": 4106.35, "end": 4106.55, "word": " exact", "probability": 0.87548828125 }, { "start": 4106.55, "end": 4106.79, "word": " same", "probability": 0.8193359375 }, { "start": 4106.79, "end": 4107.09, "word": " thing", "probability": 0.814453125 }, { "start": 4107.09, "end": 4107.57, "word": ".", "probability": 0.99560546875 } ] }, { "id": 1113, "seek": 400724, "start": 4107.57, "end": 4109.59, "text": " The difference is we need to", "tokens": [ 51314, 440, 2649, 307, 321, 643, 281, 51414 ], "temperature": 0.0, "avg_logprob": -0.1741286044797072, "compression_ratio": 1.373134328358209, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 4107.57, "end": 4107.87, "word": " The", "probability": 0.82275390625 }, { "start": 4107.87, "end": 4108.15, "word": " difference", "probability": 0.69140625 }, { "start": 4108.15, "end": 4108.39, "word": " is", "probability": 0.90625 }, { "start": 4108.39, "end": 4108.61, "word": " we", "probability": 0.78759765625 }, { "start": 4108.61, "end": 4108.97, "word": " need", "probability": 0.81103515625 }, { "start": 4108.97, "end": 4109.59, "word": " to", "probability": 0.90673828125 } ] }, { "id": 1114, "seek": 400724, "start": 4112.47, "end": 4114.99, "text": " use a LBFGS solver.", "tokens": [ 51464, 764, 257, 441, 33, 37, 24446, 1404, 331, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.1741286044797072, "compression_ratio": 1.373134328358209, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 4112.47, "end": 4113.05, "word": " use", "probability": 0.791015625 }, { "start": 4113.05, "end": 4113.63, "word": " a LBFGS", "probability": 0.864990234375 }, { "start": 4113.63, "end": 4114.41, "word": " solver", "probability": 0.901123046875 }, { "start": 4114.41, "end": 4114.99, "word": ".", "probability": 0.9697265625 } ] }, { "id": 1115, "seek": 400724, "start": 4115.65, "end": 4117.77, "text": " So what that's going to look like is", "tokens": [ 51714, 407, 437, 300, 311, 516, 281, 574, 411, 307, 51814 ], "temperature": 0.0, "avg_logprob": -0.1741286044797072, "compression_ratio": 1.373134328358209, "no_speech_prob": 0.0020503997802734375, "words": [ { "start": 4115.65, "end": 4116.23, "word": " So", "probability": 0.8935546875 }, { "start": 4116.23, "end": 4116.31, "word": " what", "probability": 0.849609375 }, { "start": 4116.31, "end": 4116.51, "word": " that's", "probability": 0.93408203125 }, { "start": 4116.51, "end": 4116.57, "word": " going", "probability": 0.23974609375 }, { "start": 4116.57, "end": 4116.65, "word": " to", "probability": 0.90087890625 }, { "start": 4116.65, "end": 4116.79, "word": " look", "probability": 0.91650390625 }, { "start": 4116.79, "end": 4117.13, "word": " like", "probability": 0.87548828125 }, { "start": 4117.13, "end": 4117.77, "word": " is", "probability": 0.8935546875 } ] }, { "id": 1116, "seek": 403446, "start": 4119.59, "end": 4120.27, "text": " LGSTFIDF", "tokens": [ 50364, 441, 24446, 20527, 2777, 37, 50464 ], "temperature": 0.0, "avg_logprob": -0.16247106315913024, "compression_ratio": 1.5219512195121951, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 4119.59, "end": 4120.27, "word": " LGSTFIDF", "probability": 0.505078125 } ] }, { "id": 1117, "seek": 403446, "start": 4120.27, "end": 4120.99, "text": " equals", "tokens": [ 50464, 6915, 50564 ], "temperature": 0.0, "avg_logprob": -0.16247106315913024, "compression_ratio": 1.5219512195121951, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 4120.27, "end": 4120.99, "word": " equals", "probability": 0.3896484375 } ] }, { "id": 1118, "seek": 403446, "start": 4122.07, "end": 4122.75, "text": " logistic", "tokens": [ 50564, 3565, 3142, 50664 ], "temperature": 0.0, "avg_logprob": -0.16247106315913024, "compression_ratio": 1.5219512195121951, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 4122.07, "end": 4122.75, "word": " logistic", "probability": 0.828857421875 } ] }, { "id": 1119, "seek": 403446, "start": 4124.21, "end": 4125.17, "text": " regression.", "tokens": [ 50664, 24590, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.16247106315913024, "compression_ratio": 1.5219512195121951, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 4124.21, "end": 4124.89, "word": " regression", "probability": 0.8525390625 }, { "start": 4124.89, "end": 4125.17, "word": ".", "probability": 0.5234375 } ] }, { "id": 1120, "seek": 403446, "start": 4125.39, "end": 4127.39, "text": " Then we're going to set our solver", "tokens": [ 50764, 1396, 321, 434, 516, 281, 992, 527, 1404, 331, 50864 ], "temperature": 0.0, "avg_logprob": -0.16247106315913024, "compression_ratio": 1.5219512195121951, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 4125.39, "end": 4126.07, "word": " Then", "probability": 0.362548828125 }, { "start": 4126.07, "end": 4126.19, "word": " we're", "probability": 0.89697265625 }, { "start": 4126.19, "end": 4126.27, "word": " going", "probability": 0.625 }, { "start": 4126.27, "end": 4126.29, "word": " to", "probability": 0.89892578125 }, { "start": 4126.29, "end": 4126.45, "word": " set", "probability": 0.8701171875 }, { "start": 4126.45, "end": 4126.63, "word": " our", "probability": 0.81396484375 }, { "start": 4126.63, "end": 4127.39, "word": " solver", "probability": 0.891845703125 } ] }, { "id": 1121, "seek": 403446, "start": 4129.01, "end": 4130.03, "text": " LBFGS.", "tokens": [ 50864, 441, 33, 37, 24446, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.16247106315913024, "compression_ratio": 1.5219512195121951, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 4129.01, "end": 4129.69, "word": " LBFGS", "probability": 0.83856201171875 }, { "start": 4129.69, "end": 4130.03, "word": ".", "probability": 0.6162109375 } ] }, { "id": 1122, "seek": 403446, "start": 4130.03, "end": 4131.71, "text": " And this is just a thing with", "tokens": [ 50964, 400, 341, 307, 445, 257, 551, 365, 51064 ], "temperature": 0.0, "avg_logprob": -0.16247106315913024, "compression_ratio": 1.5219512195121951, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 4130.03, "end": 4130.09, "word": " And", "probability": 0.53466796875 }, { "start": 4130.09, "end": 4130.25, "word": " this", "probability": 0.88134765625 }, { "start": 4130.25, "end": 4130.39, "word": " is", "probability": 0.9072265625 }, { "start": 4130.39, "end": 4130.57, "word": " just", "probability": 0.88037109375 }, { "start": 4130.77, "end": 4131.15, "word": " a thing", "probability": 0.82958984375 }, { "start": 4131.15, "end": 4131.71, "word": " with", "probability": 0.80078125 } ] }, { "id": 1123, "seek": 403446, "start": 4131.71, "end": 4134.11, "text": " logistic regression specifically.", "tokens": [ 51064, 3565, 3142, 24590, 4682, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.16247106315913024, "compression_ratio": 1.5219512195121951, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 4131.71, "end": 4132.43, "word": " logistic", "probability": 0.93115234375 }, { "start": 4132.43, "end": 4132.83, "word": " regression", "probability": 0.8173828125 }, { "start": 4132.83, "end": 4133.77, "word": " specifically", "probability": 0.65185546875 }, { "start": 4133.77, "end": 4134.11, "word": ".", "probability": 0.85498046875 } ] }, { "id": 1124, "seek": 403446, "start": 4134.43, "end": 4136.29, "text": " We saw in the slides", "tokens": [ 51164, 492, 1866, 294, 264, 9788, 51264 ], "temperature": 0.0, "avg_logprob": -0.16247106315913024, "compression_ratio": 1.5219512195121951, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 4134.43, "end": 4135.11, "word": " We", "probability": 0.8896484375 }, { "start": 4135.11, "end": 4135.43, "word": " saw", "probability": 0.82861328125 }, { "start": 4135.43, "end": 4135.63, "word": " in", "probability": 0.900390625 }, { "start": 4135.63, "end": 4135.79, "word": " the", "probability": 0.810546875 }, { "start": 4135.79, "end": 4136.29, "word": " slides", "probability": 0.91796875 } ] }, { "id": 1125, "seek": 403446, "start": 4136.29, "end": 4138.15, "text": " that multinomial naivetation", "tokens": [ 51264, 300, 45872, 47429, 1667, 592, 302, 399, 51364 ], "temperature": 0.0, "avg_logprob": -0.16247106315913024, "compression_ratio": 1.5219512195121951, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 4136.29, "end": 4136.85, "word": " that", "probability": 0.86083984375 }, { "start": 4136.85, "end": 4137.53, "word": " multinomial", "probability": 0.906982421875 }, { "start": 4137.53, "end": 4138.15, "word": " naivetation", "probability": 0.67669677734375 } ] }, { "id": 1126, "seek": 403446, "start": 4138.15, "end": 4140.47, "text": " has a variable called alpha.", "tokens": [ 51364, 575, 257, 7006, 1219, 8961, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.16247106315913024, "compression_ratio": 1.5219512195121951, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 4138.15, "end": 4138.49, "word": " has", "probability": 0.90234375 }, { "start": 4138.99, "end": 4139.39, "word": " a variable", "probability": 0.775390625 }, { "start": 4139.39, "end": 4139.73, "word": " called", "probability": 0.810546875 }, { "start": 4139.73, "end": 4140.11, "word": " alpha", "probability": 0.6279296875 }, { "start": 4140.11, "end": 4140.47, "word": ".", "probability": 0.8017578125 } ] }, { "id": 1127, "seek": 403446, "start": 4140.47, "end": 4141.65, "text": " We can tweak that.", "tokens": [ 51464, 492, 393, 29879, 300, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.16247106315913024, "compression_ratio": 1.5219512195121951, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 4140.47, "end": 4140.75, "word": " We", "probability": 0.8916015625 }, { "start": 4140.75, "end": 4140.93, "word": " can", "probability": 0.89892578125 }, { "start": 4140.93, "end": 4141.21, "word": " tweak", "probability": 0.8525390625 }, { "start": 4141.21, "end": 4141.57, "word": " that", "probability": 0.880859375 }, { "start": 4141.57, "end": 4141.65, "word": ".", "probability": 0.2470703125 } ] }, { "id": 1128, "seek": 403446, "start": 4141.65, "end": 4143.05, "text": " That's one of our hyperparameters.", "tokens": [ 51564, 663, 311, 472, 295, 527, 9848, 2181, 335, 6202, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.16247106315913024, "compression_ratio": 1.5219512195121951, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 4141.65, "end": 4141.85, "word": " That's", "probability": 0.6910400390625 }, { "start": 4141.85, "end": 4141.95, "word": " one", "probability": 0.818359375 }, { "start": 4141.95, "end": 4142.03, "word": " of", "probability": 0.9033203125 }, { "start": 4142.03, "end": 4142.13, "word": " our", "probability": 0.822265625 }, { "start": 4142.13, "end": 4142.85, "word": " hyperparameters", "probability": 0.87158203125 }, { "start": 4142.85, "end": 4143.05, "word": ".", "probability": 0.923828125 } ] }, { "id": 1129, "seek": 403446, "start": 4143.05, "end": 4144.99, "text": " This is considered a hyperparameter.", "tokens": [ 51664, 639, 307, 4888, 257, 9848, 2181, 335, 2398, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.16247106315913024, "compression_ratio": 1.5219512195121951, "no_speech_prob": 0.00040435791015625, "words": [ { "start": 4143.05, "end": 4143.19, "word": " This", "probability": 0.79248046875 }, { "start": 4143.19, "end": 4143.39, "word": " is", "probability": 0.91162109375 }, { "start": 4143.39, "end": 4144.03, "word": " considered", "probability": 0.65478515625 }, { "start": 4144.19, "end": 4144.81, "word": " a hyperparameter", "probability": 0.9630126953125 }, { "start": 4144.81, "end": 4144.99, "word": ".", "probability": 0.8291015625 } ] }, { "id": 1130, "seek": 406392, "start": 4144.99, "end": 4146.33, "text": " It's the way that logistic regression", "tokens": [ 50364, 467, 311, 264, 636, 300, 3565, 3142, 24590, 50464 ], "temperature": 0.0, "avg_logprob": -0.21271658415841585, "compression_ratio": 1.583815028901734, "no_speech_prob": 0.030670166015625, "words": [ { "start": 4144.99, "end": 4145.03, "word": " It's", "probability": 0.53643798828125 }, { "start": 4145.03, "end": 4145.15, "word": " the", "probability": 0.802734375 }, { "start": 4145.15, "end": 4145.33, "word": " way", "probability": 0.89697265625 }, { "start": 4145.33, "end": 4145.53, "word": " that", "probability": 0.83544921875 }, { "start": 4145.53, "end": 4145.89, "word": " logistic", "probability": 0.922119140625 }, { "start": 4145.89, "end": 4146.33, "word": " regression", "probability": 0.8720703125 } ] }, { "id": 1131, "seek": 406392, "start": 4146.77, "end": 4148.09, "text": " interprets the information.", "tokens": [ 50464, 17489, 1373, 264, 1589, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.21271658415841585, "compression_ratio": 1.583815028901734, "no_speech_prob": 0.030670166015625, "words": [ { "start": 4146.77, "end": 4147.13, "word": " interprets", "probability": 0.5914306640625 }, { "start": 4147.13, "end": 4147.27, "word": " the", "probability": 0.7998046875 }, { "start": 4147.27, "end": 4147.73, "word": " information", "probability": 0.73583984375 }, { "start": 4147.73, "end": 4148.09, "word": ".", "probability": 0.85888671875 } ] }, { "id": 1132, "seek": 406392, "start": 4148.75, "end": 4150.89, "text": " But for this case, we're just going to use LBFGS.", "tokens": [ 50564, 583, 337, 341, 1389, 11, 321, 434, 445, 516, 281, 764, 441, 33, 37, 24446, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.21271658415841585, "compression_ratio": 1.583815028901734, "no_speech_prob": 0.030670166015625, "words": [ { "start": 4148.75, "end": 4148.87, "word": " But", "probability": 0.60009765625 }, { "start": 4148.87, "end": 4148.99, "word": " for", "probability": 0.85595703125 }, { "start": 4148.99, "end": 4149.13, "word": " this", "probability": 0.88330078125 }, { "start": 4149.13, "end": 4149.31, "word": " case", "probability": 0.80908203125 }, { "start": 4149.31, "end": 4149.35, "word": ",", "probability": 0.7666015625 }, { "start": 4149.35, "end": 4149.45, "word": " we're", "probability": 0.92138671875 }, { "start": 4149.45, "end": 4149.55, "word": " just", "probability": 0.85302734375 }, { "start": 4149.55, "end": 4149.69, "word": " going", "probability": 0.59326171875 }, { "start": 4149.69, "end": 4149.73, "word": " to", "probability": 0.908203125 }, { "start": 4149.73, "end": 4149.89, "word": " use", "probability": 0.8388671875 }, { "start": 4149.89, "end": 4150.53, "word": " LBFGS", "probability": 0.7471923828125 }, { "start": 4150.53, "end": 4150.89, "word": ".", "probability": 0.97119140625 } ] }, { "id": 1133, "seek": 406392, "start": 4151.49, "end": 4152.63, "text": " We're going to do the same thing.", "tokens": [ 50664, 492, 434, 516, 281, 360, 264, 912, 551, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.21271658415841585, "compression_ratio": 1.583815028901734, "no_speech_prob": 0.030670166015625, "words": [ { "start": 4151.49, "end": 4151.85, "word": " We're", "probability": 0.928466796875 }, { "start": 4151.85, "end": 4151.93, "word": " going", "probability": 0.84765625 }, { "start": 4151.93, "end": 4151.99, "word": " to", "probability": 0.90771484375 }, { "start": 4151.99, "end": 4152.07, "word": " do", "probability": 0.90380859375 }, { "start": 4152.07, "end": 4152.19, "word": " the", "probability": 0.80810546875 }, { "start": 4152.19, "end": 4152.33, "word": " same", "probability": 0.81787109375 }, { "start": 4152.33, "end": 4152.53, "word": " thing", "probability": 0.822265625 }, { "start": 4152.53, "end": 4152.63, "word": ".", "probability": 0.87109375 } ] }, { "id": 1134, "seek": 406392, "start": 4152.63, "end": 4154.99, "text": " We're going to fit LGSTFIDF", "tokens": [ 50764, 492, 434, 516, 281, 3318, 441, 24446, 20527, 2777, 37, 50864 ], "temperature": 0.0, "avg_logprob": -0.21271658415841585, "compression_ratio": 1.583815028901734, "no_speech_prob": 0.030670166015625, "words": [ { "start": 4152.63, "end": 4152.65, "word": " We're", "probability": 0.917724609375 }, { "start": 4152.65, "end": 4152.81, "word": " going", "probability": 0.86669921875 }, { "start": 4152.81, "end": 4152.95, "word": " to", "probability": 0.89453125 }, { "start": 4152.95, "end": 4153.21, "word": " fit", "probability": 0.6337890625 }, { "start": 4153.21, "end": 4154.99, "word": " LGSTFIDF", "probability": 0.626824951171875 } ] }, { "id": 1135, "seek": 406392, "start": 4156.73, "end": 4157.09, "text": " dot", "tokens": [ 50864, 5893, 50964 ], "temperature": 0.0, "avg_logprob": -0.21271658415841585, "compression_ratio": 1.583815028901734, "no_speech_prob": 0.030670166015625, "words": [ { "start": 4156.73, "end": 4157.09, "word": " dot", "probability": 0.27392578125 } ] }, { "id": 1136, "seek": 406392, "start": 4157.09, "end": 4157.77, "text": " fit", "tokens": [ 50964, 3318, 51064 ], "temperature": 0.0, "avg_logprob": -0.21271658415841585, "compression_ratio": 1.583815028901734, "no_speech_prob": 0.030670166015625, "words": [ { "start": 4157.09, "end": 4157.77, "word": " fit", "probability": 0.73583984375 } ] }, { "id": 1137, "seek": 406392, "start": 4160.97, "end": 4161.33, "text": " TFIDFX", "tokens": [ 51064, 40964, 2777, 36092, 51164 ], "temperature": 0.0, "avg_logprob": -0.21271658415841585, "compression_ratio": 1.583815028901734, "no_speech_prob": 0.030670166015625, "words": [ { "start": 4160.97, "end": 4161.33, "word": " TFIDFX", "probability": 0.7405598958333334 } ] }, { "id": 1138, "seek": 406392, "start": 4162.39, "end": 4163.01, "text": " and then", "tokens": [ 51164, 293, 550, 51264 ], "temperature": 0.0, "avg_logprob": -0.21271658415841585, "compression_ratio": 1.583815028901734, "no_speech_prob": 0.030670166015625, "words": [ { "start": 4162.39, "end": 4162.75, "word": " and", "probability": 0.317626953125 }, { "start": 4162.75, "end": 4163.01, "word": " then", "probability": 0.69091796875 } ] }, { "id": 1139, "seek": 406392, "start": 4163.01, "end": 4164.11, "text": " it enables.", "tokens": [ 51264, 309, 17077, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.21271658415841585, "compression_ratio": 1.583815028901734, "no_speech_prob": 0.030670166015625, "words": [ { "start": 4163.01, "end": 4163.41, "word": " it", "probability": 0.229248046875 }, { "start": 4163.41, "end": 4163.75, "word": " enables", "probability": 0.640625 }, { "start": 4163.75, "end": 4164.11, "word": ".", "probability": 0.97412109375 } ] }, { "id": 1140, "seek": 406392, "start": 4166.57, "end": 4168.31, "text": " Let me just hop down here.", "tokens": [ 51464, 961, 385, 445, 3818, 760, 510, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.21271658415841585, "compression_ratio": 1.583815028901734, "no_speech_prob": 0.030670166015625, "words": [ { "start": 4166.57, "end": 4166.93, "word": " Let", "probability": 0.400634765625 }, { "start": 4166.93, "end": 4167.01, "word": " me", "probability": 0.89404296875 }, { "start": 4167.01, "end": 4167.15, "word": " just", "probability": 0.8974609375 }, { "start": 4167.15, "end": 4167.33, "word": " hop", "probability": 0.7578125 }, { "start": 4167.33, "end": 4167.53, "word": " down", "probability": 0.79443359375 }, { "start": 4167.53, "end": 4167.95, "word": " here", "probability": 0.814453125 }, { "start": 4167.95, "end": 4168.31, "word": ".", "probability": 0.75390625 } ] }, { "id": 1141, "seek": 406392, "start": 4168.51, "end": 4170.31, "text": " We're going to do score equals", "tokens": [ 51564, 492, 434, 516, 281, 360, 6175, 6915, 51664 ], "temperature": 0.0, "avg_logprob": -0.21271658415841585, "compression_ratio": 1.583815028901734, "no_speech_prob": 0.030670166015625, "words": [ { "start": 4168.51, "end": 4168.69, "word": " We're", "probability": 0.744384765625 }, { "start": 4168.69, "end": 4168.75, "word": " going", "probability": 0.7763671875 }, { "start": 4168.75, "end": 4168.77, "word": " to", "probability": 0.9072265625 }, { "start": 4168.77, "end": 4169.05, "word": " do", "probability": 0.91064453125 }, { "start": 4169.05, "end": 4169.83, "word": " score", "probability": 0.6484375 }, { "start": 4169.83, "end": 4170.31, "word": " equals", "probability": 0.828125 } ] }, { "id": 1142, "seek": 406392, "start": 4174.09, "end": 4174.45, "text": " LG", "tokens": [ 51664, 25449, 51764 ], "temperature": 0.0, "avg_logprob": -0.21271658415841585, "compression_ratio": 1.583815028901734, "no_speech_prob": 0.030670166015625, "words": [ { "start": 4174.09, "end": 4174.45, "word": " LG", "probability": 0.5595703125 } ] }, { "id": 1143, "seek": 409104, "start": 4174.45, "end": 4174.93, "text": " S", "tokens": [ 50364, 318, 50464 ], "temperature": 0.0, "avg_logprob": -0.1642628277723606, "compression_ratio": 1.3801652892561984, "no_speech_prob": 0.0267486572265625, "words": [ { "start": 4174.45, "end": 4174.93, "word": " S", "probability": 0.0031948089599609375 } ] }, { "id": 1144, "seek": 409104, "start": 4176.45, "end": 4177.85, "text": " TFIDF equals", "tokens": [ 50464, 40964, 2777, 37, 6915, 50564 ], "temperature": 0.0, "avg_logprob": -0.1642628277723606, "compression_ratio": 1.3801652892561984, "no_speech_prob": 0.0267486572265625, "words": [ { "start": 4176.45, "end": 4177.25, "word": " TFIDF", "probability": 0.3490651448567708 }, { "start": 4177.25, "end": 4177.85, "word": " equals", "probability": 0.7314453125 } ] }, { "id": 1145, "seek": 409104, "start": 4178.45, "end": 4180.35, "text": " LGSTFIDF dot", "tokens": [ 50564, 441, 24446, 20527, 2777, 37, 5893, 50664 ], "temperature": 0.0, "avg_logprob": -0.1642628277723606, "compression_ratio": 1.3801652892561984, "no_speech_prob": 0.0267486572265625, "words": [ { "start": 4178.45, "end": 4180.01, "word": " LGSTFIDF", "probability": 0.635443115234375 }, { "start": 4180.01, "end": 4180.35, "word": " dot", "probability": 0.576171875 } ] }, { "id": 1146, "seek": 409104, "start": 4180.35, "end": 4181.11, "text": " score", "tokens": [ 50664, 6175, 50764 ], "temperature": 0.0, "avg_logprob": -0.1642628277723606, "compression_ratio": 1.3801652892561984, "no_speech_prob": 0.0267486572265625, "words": [ { "start": 4180.35, "end": 4181.11, "word": " score", "probability": 0.69873046875 } ] }, { "id": 1147, "seek": 409104, "start": 4182.95, "end": 4184.13, "text": " testTFIDFX", "tokens": [ 50764, 1500, 20527, 2777, 36092, 50864 ], "temperature": 0.0, "avg_logprob": -0.1642628277723606, "compression_ratio": 1.3801652892561984, "no_speech_prob": 0.0267486572265625, "words": [ { "start": 4182.95, "end": 4184.13, "word": " testTFIDFX", "probability": 0.5258026123046875 } ] }, { "id": 1148, "seek": 409104, "start": 4184.13, "end": 4186.37, "text": " Pay attention to your capitals.", "tokens": [ 50864, 11431, 3202, 281, 428, 1410, 11118, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.1642628277723606, "compression_ratio": 1.3801652892561984, "no_speech_prob": 0.0267486572265625, "words": [ { "start": 4184.13, "end": 4184.65, "word": " Pay", "probability": 0.32421875 }, { "start": 4184.65, "end": 4184.93, "word": " attention", "probability": 0.833984375 }, { "start": 4184.93, "end": 4185.09, "word": " to", "probability": 0.90869140625 }, { "start": 4185.09, "end": 4185.23, "word": " your", "probability": 0.8115234375 }, { "start": 4185.23, "end": 4185.79, "word": " capitals", "probability": 0.90087890625 }, { "start": 4185.79, "end": 4186.37, "word": ".", "probability": 0.3857421875 } ] }, { "id": 1149, "seek": 409104, "start": 4186.37, "end": 4188.87, "text": " Test labels.", "tokens": [ 50964, 9279, 16949, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.1642628277723606, "compression_ratio": 1.3801652892561984, "no_speech_prob": 0.0267486572265625, "words": [ { "start": 4186.37, "end": 4186.91, "word": " Test", "probability": 0.6240234375 }, { "start": 4186.91, "end": 4187.81, "word": " labels", "probability": 0.66162109375 }, { "start": 4187.81, "end": 4188.87, "word": ".", "probability": 0.70458984375 } ] }, { "id": 1150, "seek": 409104, "start": 4188.87, "end": 4189.77, "text": " Then we're going to do", "tokens": [ 51064, 1396, 321, 434, 516, 281, 360, 51164 ], "temperature": 0.0, "avg_logprob": -0.1642628277723606, "compression_ratio": 1.3801652892561984, "no_speech_prob": 0.0267486572265625, "words": [ { "start": 4188.87, "end": 4189.33, "word": " Then", "probability": 0.1983642578125 }, { "start": 4189.33, "end": 4189.45, "word": " we're", "probability": 0.86767578125 }, { "start": 4189.45, "end": 4189.53, "word": " going", "probability": 0.52490234375 }, { "start": 4189.53, "end": 4189.55, "word": " to", "probability": 0.90771484375 }, { "start": 4189.55, "end": 4189.77, "word": " do", "probability": 0.89697265625 } ] }, { "id": 1151, "seek": 409104, "start": 4189.98, "end": 4190.57, "text": " predictions", "tokens": [ 51164, 21264, 51264 ], "temperature": 0.0, "avg_logprob": -0.1642628277723606, "compression_ratio": 1.3801652892561984, "no_speech_prob": 0.0267486572265625, "words": [ { "start": 4189.98, "end": 4190.57, "word": " predictions", "probability": 0.72412109375 } ] }, { "id": 1152, "seek": 409104, "start": 4193.53, "end": 4194.71, "text": " shuns", "tokens": [ 51264, 402, 26684, 51364 ], "temperature": 0.0, "avg_logprob": -0.1642628277723606, "compression_ratio": 1.3801652892561984, "no_speech_prob": 0.0267486572265625, "words": [ { "start": 4193.53, "end": 4194.71, "word": " shuns", "probability": 0.4215240478515625 } ] }, { "id": 1153, "seek": 409104, "start": 4194.71, "end": 4196.55, "text": " LGSTFIDF", "tokens": [ 51364, 441, 24446, 20527, 2777, 37, 51464 ], "temperature": 0.0, "avg_logprob": -0.1642628277723606, "compression_ratio": 1.3801652892561984, "no_speech_prob": 0.0267486572265625, "words": [ { "start": 4194.71, "end": 4196.55, "word": " LGSTFIDF", "probability": 0.8142578125 } ] }, { "id": 1154, "seek": 409104, "start": 4196.55, "end": 4197.53, "text": " equals", "tokens": [ 51464, 6915, 51564 ], "temperature": 0.0, "avg_logprob": -0.1642628277723606, "compression_ratio": 1.3801652892561984, "no_speech_prob": 0.0267486572265625, "words": [ { "start": 4196.55, "end": 4197.53, "word": " equals", "probability": 0.89208984375 } ] }, { "id": 1155, "seek": 409104, "start": 4198.45, "end": 4199.79, "text": " LGSTFIDF", "tokens": [ 51564, 441, 24446, 20527, 2777, 37, 51664 ], "temperature": 0.0, "avg_logprob": -0.1642628277723606, "compression_ratio": 1.3801652892561984, "no_speech_prob": 0.0267486572265625, "words": [ { "start": 4198.45, "end": 4199.79, "word": " LGSTFIDF", "probability": 0.9173828125 } ] }, { "id": 1156, "seek": 409104, "start": 4199.94, "end": 4201.57, "text": " dot predict", "tokens": [ 51664, 5893, 6069, 51764 ], "temperature": 0.0, "avg_logprob": -0.1642628277723606, "compression_ratio": 1.3801652892561984, "no_speech_prob": 0.0267486572265625, "words": [ { "start": 4199.94, "end": 4200.53, "word": " dot", "probability": 0.9267578125 }, { "start": 4200.53, "end": 4201.57, "word": " predict", "probability": 0.7939453125 } ] }, { "id": 1157, "seek": 411856, "start": 4202.43, "end": 4203.47, "text": " and then", "tokens": [ 50364, 293, 550, 50464 ], "temperature": 0.0, "avg_logprob": -0.20079140229658646, "compression_ratio": 1.416058394160584, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 4202.43, "end": 4203.23, "word": " and", "probability": 0.1732177734375 }, { "start": 4203.23, "end": 4203.47, "word": " then", "probability": 0.685546875 } ] }, { "id": 1158, "seek": 411856, "start": 4203.47, "end": 4204.83, "text": " our test data", "tokens": [ 50464, 527, 1500, 1412, 50564 ], "temperature": 0.0, "avg_logprob": -0.20079140229658646, "compression_ratio": 1.416058394160584, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 4203.47, "end": 4203.85, "word": " our", "probability": 0.802734375 }, { "start": 4203.85, "end": 4204.47, "word": " test", "probability": 0.81494140625 }, { "start": 4204.47, "end": 4204.83, "word": " data", "probability": 0.68798828125 } ] }, { "id": 1159, "seek": 411856, "start": 4207.07, "end": 4209.09, "text": " Typing TFIDF so much", "tokens": [ 50664, 5569, 3381, 40964, 2777, 37, 370, 709, 50764 ], "temperature": 0.0, "avg_logprob": -0.20079140229658646, "compression_ratio": 1.416058394160584, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 4207.07, "end": 4207.87, "word": " Typing", "probability": 0.49996185302734375 }, { "start": 4207.87, "end": 4208.53, "word": " TFIDF", "probability": 0.5397542317708334 }, { "start": 4208.53, "end": 4208.77, "word": " so", "probability": 0.8291015625 }, { "start": 4208.77, "end": 4209.09, "word": " much", "probability": 0.81787109375 } ] }, { "id": 1160, "seek": 411856, "start": 4209.09, "end": 4211.75, "text": " it's very confusing for my hands.", "tokens": [ 50764, 309, 311, 588, 13181, 337, 452, 2377, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.20079140229658646, "compression_ratio": 1.416058394160584, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 4209.09, "end": 4209.73, "word": " it's", "probability": 0.65380859375 }, { "start": 4209.73, "end": 4209.91, "word": " very", "probability": 0.192138671875 }, { "start": 4209.91, "end": 4210.33, "word": " confusing", "probability": 0.93212890625 }, { "start": 4210.33, "end": 4210.49, "word": " for", "probability": 0.86328125 }, { "start": 4210.49, "end": 4210.63, "word": " my", "probability": 0.8896484375 }, { "start": 4210.63, "end": 4210.95, "word": " hands", "probability": 0.78564453125 }, { "start": 4210.95, "end": 4211.75, "word": ".", "probability": 0.5419921875 } ] }, { "id": 1161, "seek": 411856, "start": 4212.01, "end": 4212.71, "text": " T matrix", "tokens": [ 50864, 314, 8141, 50964 ], "temperature": 0.0, "avg_logprob": -0.20079140229658646, "compression_ratio": 1.416058394160584, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 4212.01, "end": 4212.15, "word": " T", "probability": 0.17431640625 }, { "start": 4212.15, "end": 4212.71, "word": " matrix", "probability": 0.5771484375 } ] }, { "id": 1162, "seek": 411856, "start": 4217.85, "end": 4218.97, "text": " we're going to use our", "tokens": [ 50964, 321, 434, 516, 281, 764, 527, 51064 ], "temperature": 0.0, "avg_logprob": -0.20079140229658646, "compression_ratio": 1.416058394160584, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 4217.85, "end": 4218.65, "word": " we're", "probability": 0.30948638916015625 }, { "start": 4218.65, "end": 4218.71, "word": " going", "probability": 0.426025390625 }, { "start": 4218.71, "end": 4218.73, "word": " to", "probability": 0.90625 }, { "start": 4218.73, "end": 4218.81, "word": " use", "probability": 0.79638671875 }, { "start": 4218.81, "end": 4218.97, "word": " our", "probability": 0.814453125 } ] }, { "id": 1163, "seek": 411856, "start": 4218.97, "end": 4219.91, "text": " confusion matrix", "tokens": [ 51064, 15075, 8141, 51164 ], "temperature": 0.0, "avg_logprob": -0.20079140229658646, "compression_ratio": 1.416058394160584, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 4218.97, "end": 4219.35, "word": " confusion", "probability": 0.7470703125 }, { "start": 4219.35, "end": 4219.91, "word": " matrix", "probability": 0.87890625 } ] }, { "id": 1164, "seek": 411856, "start": 4220.93, "end": 4222.53, "text": " test labels", "tokens": [ 51164, 1500, 16949, 51264 ], "temperature": 0.0, "avg_logprob": -0.20079140229658646, "compression_ratio": 1.416058394160584, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 4220.93, "end": 4221.73, "word": " test", "probability": 0.3955078125 }, { "start": 4221.73, "end": 4222.53, "word": " labels", "probability": 0.79541015625 } ] }, { "id": 1165, "seek": 411856, "start": 4223.05, "end": 4225.03, "text": " and predictions", "tokens": [ 51264, 293, 21264, 51364 ], "temperature": 0.0, "avg_logprob": -0.20079140229658646, "compression_ratio": 1.416058394160584, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 4223.05, "end": 4223.67, "word": " and", "probability": 0.49169921875 }, { "start": 4223.67, "end": 4225.03, "word": " predictions", "probability": 0.724609375 } ] }, { "id": 1166, "seek": 411856, "start": 4226.61, "end": 4227.41, "text": " LGSTFIDF", "tokens": [ 51364, 441, 24446, 20527, 2777, 37, 51464 ], "temperature": 0.0, "avg_logprob": -0.20079140229658646, "compression_ratio": 1.416058394160584, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 4226.61, "end": 4227.41, "word": " LGSTFIDF", "probability": 0.55955810546875 } ] }, { "id": 1167, "seek": 411856, "start": 4227.41, "end": 4229.03, "text": " and then our", "tokens": [ 51464, 293, 550, 527, 51564 ], "temperature": 0.0, "avg_logprob": -0.20079140229658646, "compression_ratio": 1.416058394160584, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 4227.41, "end": 4228.57, "word": " and", "probability": 0.650390625 }, { "start": 4228.57, "end": 4228.75, "word": " then", "probability": 0.70751953125 }, { "start": 4228.75, "end": 4229.03, "word": " our", "probability": 0.81005859375 } ] }, { "id": 1168, "seek": 411856, "start": 4229.03, "end": 4230.03, "text": " C report", "tokens": [ 51564, 383, 2275, 51664 ], "temperature": 0.0, "avg_logprob": -0.20079140229658646, "compression_ratio": 1.416058394160584, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 4229.03, "end": 4229.41, "word": " C", "probability": 0.7060546875 }, { "start": 4229.41, "end": 4230.03, "word": " report", "probability": 0.66015625 } ] }, { "id": 1169, "seek": 411856, "start": 4231.77, "end": 4232.57, "text": " LGSTFIDF", "tokens": [ 51664, 441, 24446, 20527, 2777, 37, 51764 ], "temperature": 0.0, "avg_logprob": -0.20079140229658646, "compression_ratio": 1.416058394160584, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 4231.77, "end": 4232.57, "word": " LGSTFIDF", "probability": 0.86875 } ] }, { "id": 1170, "seek": 414692, "start": 4232.57, "end": 4233.27, "text": " equals", "tokens": [ 50364, 6915, 50464 ], "temperature": 0.0, "avg_logprob": -0.17059658386490562, "compression_ratio": 1.2166666666666666, "no_speech_prob": 0.006587982177734375, "words": [ { "start": 4232.57, "end": 4233.27, "word": " equals", "probability": 0.05438232421875 } ] }, { "id": 1171, "seek": 414692, "start": 4234.77, "end": 4235.97, "text": " location", "tokens": [ 50464, 4914, 50564 ], "temperature": 0.0, "avg_logprob": -0.17059658386490562, "compression_ratio": 1.2166666666666666, "no_speech_prob": 0.006587982177734375, "words": [ { "start": 4234.77, "end": 4235.97, "word": " location", "probability": 0.06304931640625 } ] }, { "id": 1172, "seek": 414692, "start": 4236.57, "end": 4237.27, "text": " report", "tokens": [ 50564, 2275, 50664 ], "temperature": 0.0, "avg_logprob": -0.17059658386490562, "compression_ratio": 1.2166666666666666, "no_speech_prob": 0.006587982177734375, "words": [ { "start": 4236.57, "end": 4237.27, "word": " report", "probability": 0.451416015625 } ] }, { "id": 1173, "seek": 414692, "start": 4238.57, "end": 4240.31, "text": " test labels", "tokens": [ 50664, 1500, 16949, 50764 ], "temperature": 0.0, "avg_logprob": -0.17059658386490562, "compression_ratio": 1.2166666666666666, "no_speech_prob": 0.006587982177734375, "words": [ { "start": 4238.57, "end": 4239.39, "word": " test", "probability": 0.74658203125 }, { "start": 4239.39, "end": 4240.31, "word": " labels", "probability": 0.79638671875 } ] }, { "id": 1174, "seek": 414692, "start": 4240.31, "end": 4241.83, "text": " predictions", "tokens": [ 50764, 21264, 50864 ], "temperature": 0.0, "avg_logprob": -0.17059658386490562, "compression_ratio": 1.2166666666666666, "no_speech_prob": 0.006587982177734375, "words": [ { "start": 4240.31, "end": 4241.83, "word": " predictions", "probability": 0.72802734375 } ] }, { "id": 1175, "seek": 414692, "start": 4242.57, "end": 4243.91, "text": " TFIDF", "tokens": [ 50864, 40964, 2777, 37, 50964 ], "temperature": 0.0, "avg_logprob": -0.17059658386490562, "compression_ratio": 1.2166666666666666, "no_speech_prob": 0.006587982177734375, "words": [ { "start": 4242.57, "end": 4243.91, "word": " TFIDF", "probability": 0.3996988932291667 } ] }, { "id": 1176, "seek": 414692, "start": 4246.29, "end": 4248.07, "text": " That should be good.", "tokens": [ 51064, 663, 820, 312, 665, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.17059658386490562, "compression_ratio": 1.2166666666666666, "no_speech_prob": 0.006587982177734375, "words": [ { "start": 4246.29, "end": 4246.89, "word": " That", "probability": 0.38037109375 }, { "start": 4246.89, "end": 4247.21, "word": " should", "probability": 0.92578125 }, { "start": 4247.21, "end": 4247.39, "word": " be", "probability": 0.90380859375 }, { "start": 4247.39, "end": 4247.67, "word": " good", "probability": 0.8818359375 }, { "start": 4247.67, "end": 4248.07, "word": ".", "probability": 0.469970703125 } ] }, { "id": 1177, "seek": 414692, "start": 4248.07, "end": 4251.01, "text": " Just checking for errors.", "tokens": [ 51164, 1449, 8568, 337, 13603, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.17059658386490562, "compression_ratio": 1.2166666666666666, "no_speech_prob": 0.006587982177734375, "words": [ { "start": 4248.07, "end": 4248.35, "word": " Just", "probability": 0.73291015625 }, { "start": 4248.35, "end": 4249.05, "word": " checking", "probability": 0.77880859375 }, { "start": 4249.05, "end": 4249.31, "word": " for", "probability": 0.90087890625 }, { "start": 4249.31, "end": 4249.89, "word": " errors", "probability": 0.8251953125 }, { "start": 4249.89, "end": 4251.01, "word": ".", "probability": 0.70947265625 } ] }, { "id": 1178, "seek": 414692, "start": 4252.55, "end": 4254.71, "text": " That looks right.", "tokens": [ 51364, 663, 1542, 558, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.17059658386490562, "compression_ratio": 1.2166666666666666, "no_speech_prob": 0.006587982177734375, "words": [ { "start": 4252.55, "end": 4253.75, "word": " That", "probability": 0.72900390625 }, { "start": 4253.75, "end": 4253.91, "word": " looks", "probability": 0.7998046875 }, { "start": 4253.91, "end": 4254.11, "word": " right", "probability": 0.755859375 }, { "start": 4254.11, "end": 4254.71, "word": ".", "probability": 0.908203125 } ] }, { "id": 1179, "seek": 414692, "start": 4256.37, "end": 4258.71, "text": " So, go ahead", "tokens": [ 51564, 407, 11, 352, 2286, 51664 ], "temperature": 0.0, "avg_logprob": -0.17059658386490562, "compression_ratio": 1.2166666666666666, "no_speech_prob": 0.006587982177734375, "words": [ { "start": 4256.37, "end": 4256.83, "word": " So", "probability": 0.73583984375 }, { "start": 4256.83, "end": 4257.79, "word": ",", "probability": 0.39599609375 }, { "start": 4257.79, "end": 4258.39, "word": " go", "probability": 0.75048828125 }, { "start": 4258.39, "end": 4258.71, "word": " ahead", "probability": 0.845703125 } ] }, { "id": 1180, "seek": 414692, "start": 4258.71, "end": 4260.93, "text": " copy this down.", "tokens": [ 51664, 5055, 341, 760, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.17059658386490562, "compression_ratio": 1.2166666666666666, "no_speech_prob": 0.006587982177734375, "words": [ { "start": 4258.71, "end": 4259.27, "word": " copy", "probability": 0.1427001953125 }, { "start": 4259.27, "end": 4259.57, "word": " this", "probability": 0.89013671875 }, { "start": 4259.57, "end": 4259.95, "word": " down", "probability": 0.81640625 }, { "start": 4259.95, "end": 4260.93, "word": ".", "probability": 0.80029296875 } ] }, { "id": 1181, "seek": 417528, "start": 4260.93, "end": 4262.93, "text": " I will sit and", "tokens": [ 50364, 286, 486, 1394, 293, 50464 ], "temperature": 0.0, "avg_logprob": -0.19965277523057073, "compression_ratio": 1.618421052631579, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 4260.93, "end": 4261.29, "word": " I", "probability": 0.67626953125 }, { "start": 4261.29, "end": 4261.61, "word": " will", "probability": 0.8125 }, { "start": 4261.61, "end": 4262.67, "word": " sit", "probability": 0.8955078125 }, { "start": 4262.67, "end": 4262.93, "word": " and", "probability": 0.892578125 } ] }, { "id": 1182, "seek": 417528, "start": 4262.93, "end": 4264.91, "text": " wait for a bit, but you'll notice", "tokens": [ 50464, 1699, 337, 257, 857, 11, 457, 291, 603, 3449, 50564 ], "temperature": 0.0, "avg_logprob": -0.19965277523057073, "compression_ratio": 1.618421052631579, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 4262.93, "end": 4263.21, "word": " wait", "probability": 0.83642578125 }, { "start": 4263.21, "end": 4263.39, "word": " for", "probability": 0.892578125 }, { "start": 4263.55, "end": 4263.69, "word": " a bit", "probability": 0.9052734375 }, { "start": 4263.69, "end": 4263.89, "word": ",", "probability": 0.421142578125 }, { "start": 4263.89, "end": 4264.09, "word": " but", "probability": 0.88232421875 }, { "start": 4264.09, "end": 4264.67, "word": " you'll", "probability": 0.899658203125 }, { "start": 4264.67, "end": 4264.91, "word": " notice", "probability": 0.8544921875 } ] }, { "id": 1183, "seek": 417528, "start": 4265.09, "end": 4266.93, "text": " a lot of similarities to the multinomial", "tokens": [ 50564, 257, 688, 295, 24197, 281, 264, 45872, 47429, 50664 ], "temperature": 0.0, "avg_logprob": -0.19965277523057073, "compression_ratio": 1.618421052631579, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 4265.09, "end": 4265.21, "word": " a lot", "probability": 0.8974609375 }, { "start": 4265.21, "end": 4265.33, "word": " of", "probability": 0.89892578125 }, { "start": 4265.33, "end": 4265.83, "word": " similarities", "probability": 0.89697265625 }, { "start": 4265.83, "end": 4266.23, "word": " to", "probability": 0.8935546875 }, { "start": 4266.23, "end": 4266.39, "word": " the", "probability": 0.80859375 }, { "start": 4266.39, "end": 4266.93, "word": " multinomial", "probability": 0.855712890625 } ] }, { "id": 1184, "seek": 417528, "start": 4266.93, "end": 4268.97, "text": " Naive Bayesian. In fact, we could have just copied and", "tokens": [ 50664, 6056, 488, 7840, 42434, 13, 682, 1186, 11, 321, 727, 362, 445, 25365, 293, 50764 ], "temperature": 0.0, "avg_logprob": -0.19965277523057073, "compression_ratio": 1.618421052631579, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 4266.93, "end": 4267.27, "word": " Naive", "probability": 0.664794921875 }, { "start": 4267.27, "end": 4267.55, "word": " Bayesian", "probability": 0.864990234375 }, { "start": 4267.55, "end": 4267.63, "word": ".", "probability": 0.86767578125 }, { "start": 4267.63, "end": 4267.79, "word": " In", "probability": 0.8916015625 }, { "start": 4267.79, "end": 4267.89, "word": " fact", "probability": 0.802734375 }, { "start": 4267.89, "end": 4267.91, "word": ",", "probability": 0.87548828125 }, { "start": 4267.91, "end": 4268.03, "word": " we", "probability": 0.90185546875 }, { "start": 4268.03, "end": 4268.13, "word": " could", "probability": 0.8173828125 }, { "start": 4268.13, "end": 4268.25, "word": " have", "probability": 0.75830078125 }, { "start": 4268.25, "end": 4268.43, "word": " just", "probability": 0.87353515625 }, { "start": 4268.43, "end": 4268.75, "word": " copied", "probability": 0.87109375 }, { "start": 4268.75, "end": 4268.97, "word": " and", "probability": 0.88330078125 } ] }, { "id": 1185, "seek": 417528, "start": 4268.97, "end": 4271.03, "text": " pasted and just changed it from", "tokens": [ 50764, 1791, 292, 293, 445, 3105, 309, 490, 50864 ], "temperature": 0.0, "avg_logprob": -0.19965277523057073, "compression_ratio": 1.618421052631579, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 4268.97, "end": 4269.41, "word": " pasted", "probability": 0.817138671875 }, { "start": 4269.41, "end": 4269.63, "word": " and", "probability": 0.775390625 }, { "start": 4269.63, "end": 4269.81, "word": " just", "probability": 0.8193359375 }, { "start": 4269.81, "end": 4270.41, "word": " changed", "probability": 0.78369140625 }, { "start": 4270.41, "end": 4270.63, "word": " it", "probability": 0.89990234375 }, { "start": 4270.63, "end": 4271.03, "word": " from", "probability": 0.810546875 } ] }, { "id": 1186, "seek": 417528, "start": 4271.03, "end": 4272.59, "text": " LGS to", "tokens": [ 50864, 441, 24446, 281, 50964 ], "temperature": 0.0, "avg_logprob": -0.19965277523057073, "compression_ratio": 1.618421052631579, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 4271.03, "end": 4272.03, "word": " LGS", "probability": 0.87841796875 }, { "start": 4272.03, "end": 4272.59, "word": " to", "probability": 0.888671875 } ] }, { "id": 1187, "seek": 417528, "start": 4272.59, "end": 4274.97, "text": " MNB or from MNB", "tokens": [ 50964, 376, 45, 33, 420, 490, 376, 45, 33, 51064 ], "temperature": 0.0, "avg_logprob": -0.19965277523057073, "compression_ratio": 1.618421052631579, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 4272.59, "end": 4273.25, "word": " MNB", "probability": 0.8592122395833334 }, { "start": 4273.25, "end": 4273.83, "word": " or", "probability": 0.529296875 }, { "start": 4273.83, "end": 4274.09, "word": " from", "probability": 0.78076171875 }, { "start": 4274.09, "end": 4274.97, "word": " MNB", "probability": 0.8912760416666666 } ] }, { "id": 1188, "seek": 417528, "start": 4274.97, "end": 4276.71, "text": " to LGS and then", "tokens": [ 51064, 281, 441, 24446, 293, 550, 51164 ], "temperature": 0.0, "avg_logprob": -0.19965277523057073, "compression_ratio": 1.618421052631579, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 4274.97, "end": 4275.23, "word": " to", "probability": 0.89697265625 }, { "start": 4275.23, "end": 4275.69, "word": " LGS", "probability": 0.943359375 }, { "start": 4275.69, "end": 4276.47, "word": " and", "probability": 0.479248046875 }, { "start": 4276.47, "end": 4276.71, "word": " then", "probability": 0.7158203125 } ] }, { "id": 1189, "seek": 417528, "start": 4276.71, "end": 4278.99, "text": " change our constructor to be a logistic regression", "tokens": [ 51164, 1319, 527, 47479, 281, 312, 257, 3565, 3142, 24590, 51264 ], "temperature": 0.0, "avg_logprob": -0.19965277523057073, "compression_ratio": 1.618421052631579, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 4276.71, "end": 4277.11, "word": " change", "probability": 0.650390625 }, { "start": 4277.11, "end": 4277.25, "word": " our", "probability": 0.80126953125 }, { "start": 4277.25, "end": 4277.75, "word": " constructor", "probability": 0.75732421875 }, { "start": 4277.75, "end": 4278.17, "word": " to", "probability": 0.896484375 }, { "start": 4278.17, "end": 4278.27, "word": " be", "probability": 0.900390625 }, { "start": 4278.39, "end": 4278.65, "word": " a logistic", "probability": 0.925048828125 }, { "start": 4278.65, "end": 4278.99, "word": " regression", "probability": 0.90576171875 } ] }, { "id": 1190, "seek": 417528, "start": 4278.99, "end": 4281.35, "text": " with the LBFGS solver.", "tokens": [ 51264, 365, 264, 441, 33, 37, 24446, 1404, 331, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.19965277523057073, "compression_ratio": 1.618421052631579, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 4278.99, "end": 4279.29, "word": " with", "probability": 0.80859375 }, { "start": 4279.29, "end": 4279.45, "word": " the", "probability": 0.8232421875 }, { "start": 4279.45, "end": 4280.29, "word": " LBFGS", "probability": 0.8260498046875 }, { "start": 4280.29, "end": 4280.79, "word": " solver", "probability": 0.910888671875 }, { "start": 4280.79, "end": 4281.35, "word": ".", "probability": 0.99072265625 } ] }, { "id": 1191, "seek": 417528, "start": 4284.03, "end": 4287.43, "text": " We have our logistic regression constructor.", "tokens": [ 51564, 492, 362, 527, 3565, 3142, 24590, 47479, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.19965277523057073, "compression_ratio": 1.618421052631579, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 4284.03, "end": 4284.59, "word": " We", "probability": 0.12493896484375 }, { "start": 4284.59, "end": 4285.05, "word": " have", "probability": 0.87255859375 }, { "start": 4285.05, "end": 4285.53, "word": " our", "probability": 0.79833984375 }, { "start": 4285.53, "end": 4285.99, "word": " logistic", "probability": 0.93701171875 }, { "start": 4285.99, "end": 4286.37, "word": " regression", "probability": 0.84765625 }, { "start": 4286.37, "end": 4286.93, "word": " constructor", "probability": 0.72705078125 }, { "start": 4286.93, "end": 4287.43, "word": ".", "probability": 0.6669921875 } ] }, { "id": 1192, "seek": 417528, "start": 4287.43, "end": 4289.29, "text": " We train it using the fit function", "tokens": [ 51664, 492, 3847, 309, 1228, 264, 3318, 2445, 51764 ], "temperature": 0.0, "avg_logprob": -0.19965277523057073, "compression_ratio": 1.618421052631579, "no_speech_prob": 0.00208282470703125, "words": [ { "start": 4287.43, "end": 4287.77, "word": " We", "probability": 0.90625 }, { "start": 4287.77, "end": 4288.01, "word": " train", "probability": 0.78125 }, { "start": 4288.01, "end": 4288.15, "word": " it", "probability": 0.900390625 }, { "start": 4288.15, "end": 4288.43, "word": " using", "probability": 0.80810546875 }, { "start": 4288.43, "end": 4288.67, "word": " the", "probability": 0.806640625 }, { "start": 4288.67, "end": 4288.83, "word": " fit", "probability": 0.7109375 }, { "start": 4288.83, "end": 4289.29, "word": " function", "probability": 0.88916015625 } ] }, { "id": 1193, "seek": 420332, "start": 4289.29, "end": 4291.49, "text": " using our TFIDF vectorized", "tokens": [ 50364, 1228, 527, 40964, 2777, 37, 8062, 1602, 50464 ], "temperature": 0.0, "avg_logprob": -0.17844011903810902, "compression_ratio": 1.7553648068669527, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4289.29, "end": 4289.79, "word": " using", "probability": 0.6064453125 }, { "start": 4289.79, "end": 4290.27, "word": " our", "probability": 0.7890625 }, { "start": 4290.27, "end": 4290.99, "word": " TFIDF", "probability": 0.5999755859375 }, { "start": 4290.99, "end": 4291.49, "word": " vectorized", "probability": 0.891357421875 } ] }, { "id": 1194, "seek": 420332, "start": 4291.49, "end": 4293.05, "text": " data and our labels.", "tokens": [ 50464, 1412, 293, 527, 16949, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.17844011903810902, "compression_ratio": 1.7553648068669527, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4291.49, "end": 4291.79, "word": " data", "probability": 0.7958984375 }, { "start": 4291.79, "end": 4292.03, "word": " and", "probability": 0.861328125 }, { "start": 4292.03, "end": 4292.17, "word": " our", "probability": 0.81103515625 }, { "start": 4292.17, "end": 4292.55, "word": " labels", "probability": 0.8515625 }, { "start": 4292.55, "end": 4293.05, "word": ".", "probability": 0.8603515625 } ] }, { "id": 1195, "seek": 420332, "start": 4293.47, "end": 4295.55, "text": " We use our test data", "tokens": [ 50564, 492, 764, 527, 1500, 1412, 50664 ], "temperature": 0.0, "avg_logprob": -0.17844011903810902, "compression_ratio": 1.7553648068669527, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4293.47, "end": 4293.97, "word": " We", "probability": 0.8896484375 }, { "start": 4293.97, "end": 4294.21, "word": " use", "probability": 0.8154296875 }, { "start": 4294.21, "end": 4294.53, "word": " our", "probability": 0.814453125 }, { "start": 4294.53, "end": 4295.03, "word": " test", "probability": 0.80859375 }, { "start": 4295.03, "end": 4295.55, "word": " data", "probability": 0.8095703125 } ] }, { "id": 1196, "seek": 420332, "start": 4295.55, "end": 4296.97, "text": " and our test labels", "tokens": [ 50664, 293, 527, 1500, 16949, 50764 ], "temperature": 0.0, "avg_logprob": -0.17844011903810902, "compression_ratio": 1.7553648068669527, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4295.55, "end": 4295.89, "word": " and", "probability": 0.85693359375 }, { "start": 4295.89, "end": 4296.05, "word": " our", "probability": 0.806640625 }, { "start": 4296.05, "end": 4296.43, "word": " test", "probability": 0.7333984375 }, { "start": 4296.43, "end": 4296.97, "word": " labels", "probability": 0.83447265625 } ] }, { "id": 1197, "seek": 420332, "start": 4296.97, "end": 4299.25, "text": " to generate a score and to", "tokens": [ 50764, 281, 8460, 257, 6175, 293, 281, 50864 ], "temperature": 0.0, "avg_logprob": -0.17844011903810902, "compression_ratio": 1.7553648068669527, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4296.97, "end": 4297.47, "word": " to", "probability": 0.89404296875 }, { "start": 4297.47, "end": 4297.85, "word": " generate", "probability": 0.8251953125 }, { "start": 4298.11, "end": 4298.47, "word": " a score", "probability": 0.7978515625 }, { "start": 4298.47, "end": 4298.97, "word": " and", "probability": 0.83056640625 }, { "start": 4298.97, "end": 4299.25, "word": " to", "probability": 0.90087890625 } ] }, { "id": 1198, "seek": 420332, "start": 4299.25, "end": 4300.67, "text": " generate predictions.", "tokens": [ 50864, 8460, 21264, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.17844011903810902, "compression_ratio": 1.7553648068669527, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4299.25, "end": 4299.63, "word": " generate", "probability": 0.80908203125 }, { "start": 4299.63, "end": 4300.17, "word": " predictions", "probability": 0.72314453125 }, { "start": 4300.17, "end": 4300.67, "word": ".", "probability": 0.75439453125 } ] }, { "id": 1199, "seek": 420332, "start": 4301.15, "end": 4302.99, "text": " And then, off of those predictions, we generate", "tokens": [ 50964, 400, 550, 11, 766, 295, 729, 21264, 11, 321, 8460, 51064 ], "temperature": 0.0, "avg_logprob": -0.17844011903810902, "compression_ratio": 1.7553648068669527, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4301.15, "end": 4301.25, "word": " And", "probability": 0.82861328125 }, { "start": 4301.25, "end": 4301.47, "word": " then", "probability": 0.70751953125 }, { "start": 4301.47, "end": 4301.55, "word": ",", "probability": 0.057373046875 }, { "start": 4301.55, "end": 4301.75, "word": " off", "probability": 0.78076171875 }, { "start": 4301.75, "end": 4301.85, "word": " of", "probability": 0.88671875 }, { "start": 4301.85, "end": 4302.01, "word": " those", "probability": 0.85498046875 }, { "start": 4302.01, "end": 4302.37, "word": " predictions", "probability": 0.7138671875 }, { "start": 4302.37, "end": 4302.59, "word": ",", "probability": 0.8251953125 }, { "start": 4302.59, "end": 4302.67, "word": " we", "probability": 0.90380859375 }, { "start": 4302.67, "end": 4302.99, "word": " generate", "probability": 0.8330078125 } ] }, { "id": 1200, "seek": 420332, "start": 4303.51, "end": 4305.51, "text": " a confusion matrix and a", "tokens": [ 51064, 257, 15075, 8141, 293, 257, 51164 ], "temperature": 0.0, "avg_logprob": -0.17844011903810902, "compression_ratio": 1.7553648068669527, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4303.51, "end": 4303.99, "word": " a confusion", "probability": 0.86181640625 }, { "start": 4303.99, "end": 4304.33, "word": " matrix", "probability": 0.8525390625 }, { "start": 4304.33, "end": 4304.81, "word": " and", "probability": 0.87548828125 }, { "start": 4305.03, "end": 4305.51, "word": " a classification", "probability": 0.93408203125 } ] }, { "id": 1201, "seek": 420332, "start": 4305.51, "end": 4308.47, "text": " classification report.", "tokens": [ 51164, 21538, 2275, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.17844011903810902, "compression_ratio": 1.7553648068669527, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4305.51, "end": 4306.17, "word": " report", "probability": 0.771484375 }, { "start": 4306.17, "end": 4306.67, "word": ".", "probability": 0.9912109375 }, { "start": 4308.07, "end": 4308.47, "word": " And", "probability": 0.84912109375 } ] }, { "id": 1202, "seek": 420332, "start": 4308.47, "end": 4309.45, "text": " And then, of course, our nice", "tokens": [ 51264, 400, 550, 11, 295, 1164, 11, 527, 1481, 51364 ], "temperature": 0.0, "avg_logprob": -0.17844011903810902, "compression_ratio": 1.7553648068669527, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4308.47, "end": 4308.57, "word": " then", "probability": 0.69775390625 }, { "start": 4308.57, "end": 4308.61, "word": ",", "probability": 0.67041015625 }, { "start": 4308.61, "end": 4308.69, "word": " of", "probability": 0.908203125 }, { "start": 4308.69, "end": 4308.81, "word": " course", "probability": 0.86474609375 }, { "start": 4308.81, "end": 4308.85, "word": ",", "probability": 0.98193359375 }, { "start": 4308.85, "end": 4308.97, "word": " our", "probability": 0.79052734375 }, { "start": 4308.97, "end": 4309.31, "word": " nice", "probability": 0.81787109375 }, { "start": 4309.31, "end": 4309.45, "word": " little", "probability": 0.7333984375 } ] }, { "id": 1203, "seek": 420332, "start": 4309.45, "end": 4311.49, "text": " little helper function at the bottom that's going to print us out", "tokens": [ 51364, 707, 36133, 2445, 412, 264, 2767, 300, 311, 516, 281, 4482, 505, 484, 51464 ], "temperature": 0.0, "avg_logprob": -0.17844011903810902, "compression_ratio": 1.7553648068669527, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4309.45, "end": 4309.67, "word": " helper", "probability": 0.87451171875 }, { "start": 4309.67, "end": 4310.01, "word": " function", "probability": 0.87109375 }, { "start": 4310.01, "end": 4310.13, "word": " at", "probability": 0.88427734375 }, { "start": 4310.13, "end": 4310.23, "word": " the", "probability": 0.8115234375 }, { "start": 4310.23, "end": 4310.41, "word": " bottom", "probability": 0.7705078125 }, { "start": 4310.41, "end": 4310.65, "word": " that's", "probability": 0.868408203125 }, { "start": 4310.65, "end": 4310.73, "word": " going", "probability": 0.298095703125 }, { "start": 4310.73, "end": 4310.79, "word": " to", "probability": 0.912109375 }, { "start": 4310.79, "end": 4310.93, "word": " print", "probability": 0.8740234375 }, { "start": 4310.93, "end": 4311.07, "word": " us", "probability": 0.84814453125 }, { "start": 4311.07, "end": 4311.19, "word": " out", "probability": 0.81591796875 }, { "start": 4311.19, "end": 4311.49, "word": " some", "probability": 0.81494140625 } ] }, { "id": 1204, "seek": 420332, "start": 4312.39, "end": 4314.51, "text": " some helpful stats.", "tokens": [ 51464, 512, 4961, 18152, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.17844011903810902, "compression_ratio": 1.7553648068669527, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4312.39, "end": 4312.89, "word": " helpful", "probability": 0.83544921875 }, { "start": 4312.89, "end": 4313.25, "word": " stats", "probability": 0.8564453125 }, { "start": 4313.25, "end": 4313.75, "word": ".", "probability": 0.9951171875 }, { "start": 4314.27, "end": 4314.51, "word": " So", "probability": 0.80419921875 } ] }, { "id": 1205, "seek": 420332, "start": 4314.51, "end": 4315.61, "text": " So, I'm just going to let this", "tokens": [ 51564, 407, 11, 286, 478, 445, 516, 281, 718, 341, 51664 ], "temperature": 0.0, "avg_logprob": -0.17844011903810902, "compression_ratio": 1.7553648068669527, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4314.51, "end": 4314.59, "word": ",", "probability": 0.42919921875 }, { "start": 4314.59, "end": 4314.71, "word": " I'm", "probability": 0.9970703125 }, { "start": 4314.71, "end": 4314.85, "word": " just", "probability": 0.87158203125 }, { "start": 4314.85, "end": 4314.97, "word": " going", "probability": 0.7548828125 }, { "start": 4314.97, "end": 4314.99, "word": " to", "probability": 0.896484375 }, { "start": 4314.99, "end": 4315.15, "word": " let", "probability": 0.8896484375 }, { "start": 4315.15, "end": 4315.37, "word": " this", "probability": 0.87744140625 }, { "start": 4315.37, "end": 4315.61, "word": " sit", "probability": 0.90380859375 } ] }, { "id": 1206, "seek": 420332, "start": 4315.61, "end": 4317.33, "text": " sit for a little bit longer.", "tokens": [ 51664, 1394, 337, 257, 707, 857, 2854, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.17844011903810902, "compression_ratio": 1.7553648068669527, "no_speech_prob": 0.0014324188232421875, "words": [ { "start": 4315.61, "end": 4315.97, "word": " for", "probability": 0.892578125 }, { "start": 4316.19, "end": 4316.29, "word": " a little", "probability": 0.80615234375 }, { "start": 4316.29, "end": 4316.47, "word": " bit", "probability": 0.88623046875 }, { "start": 4316.47, "end": 4316.83, "word": " longer", "probability": 0.84375 }, { "start": 4316.83, "end": 4317.33, "word": ".", "probability": 0.89208984375 } ] }, { "id": 1207, "seek": 423166, "start": 4318.93, "end": 4319.45, "text": " Kometh,", "tokens": [ 50364, 591, 649, 71, 11, 50464 ], "temperature": 0.0, "avg_logprob": -0.24690315395862134, "compression_ratio": 1.5555555555555556, "no_speech_prob": 0.0216064453125, "words": [ { "start": 4318.93, "end": 4319.43, "word": " Kometh", "probability": 0.5614420572916666 }, { "start": 4319.43, "end": 4319.45, "word": ",", "probability": 0.78369140625 } ] }, { "id": 1208, "seek": 423166, "start": 4319.45, "end": 4321.13, "text": " did Chris ask any more", "tokens": [ 50464, 630, 6688, 1029, 604, 544, 50564 ], "temperature": 0.0, "avg_logprob": -0.24690315395862134, "compression_ratio": 1.5555555555555556, "no_speech_prob": 0.0216064453125, "words": [ { "start": 4319.45, "end": 4319.83, "word": " did", "probability": 0.873046875 }, { "start": 4319.83, "end": 4320.29, "word": " Chris", "probability": 0.66162109375 }, { "start": 4320.29, "end": 4320.71, "word": " ask", "probability": 0.822265625 }, { "start": 4320.71, "end": 4320.97, "word": " any", "probability": 0.75341796875 }, { "start": 4320.97, "end": 4321.13, "word": " more", "probability": 0.8359375 } ] }, { "id": 1209, "seek": 423166, "start": 4321.13, "end": 4323.39, "text": " questions, follow-up, or did we take care", "tokens": [ 50564, 1651, 11, 1524, 12, 1010, 11, 420, 630, 321, 747, 1127, 50664 ], "temperature": 0.0, "avg_logprob": -0.24690315395862134, "compression_ratio": 1.5555555555555556, "no_speech_prob": 0.0216064453125, "words": [ { "start": 4321.13, "end": 4321.59, "word": " questions", "probability": 0.9072265625 }, { "start": 4321.59, "end": 4321.71, "word": ",", "probability": 0.397705078125 }, { "start": 4321.71, "end": 4321.89, "word": " follow", "probability": 0.84033203125 }, { "start": 4321.89, "end": 4322.07, "word": "-up", "probability": 0.67822265625 }, { "start": 4322.07, "end": 4322.25, "word": ",", "probability": 0.64599609375 }, { "start": 4322.25, "end": 4322.37, "word": " or", "probability": 0.85791015625 }, { "start": 4322.37, "end": 4322.71, "word": " did", "probability": 0.8408203125 }, { "start": 4322.71, "end": 4322.85, "word": " we", "probability": 0.892578125 }, { "start": 4322.85, "end": 4323.21, "word": " take", "probability": 0.81103515625 }, { "start": 4323.21, "end": 4323.39, "word": " care", "probability": 0.8115234375 } ] }, { "id": 1210, "seek": 423166, "start": 4323.39, "end": 4324.09, "text": " of them?", "tokens": [ 50664, 295, 552, 30, 50764 ], "temperature": 0.0, "avg_logprob": -0.24690315395862134, "compression_ratio": 1.5555555555555556, "no_speech_prob": 0.0216064453125, "words": [ { "start": 4323.39, "end": 4323.49, "word": " of", "probability": 0.9033203125 }, { "start": 4323.49, "end": 4323.59, "word": " them", "probability": 0.31298828125 }, { "start": 4323.59, "end": 4324.09, "word": "?", "probability": 0.98583984375 } ] }, { "id": 1211, "seek": 423166, "start": 4326.01, "end": 4327.13, "text": " A bunch of people", "tokens": [ 50764, 316, 3840, 295, 561, 50864 ], "temperature": 0.0, "avg_logprob": -0.24690315395862134, "compression_ratio": 1.5555555555555556, "no_speech_prob": 0.0216064453125, "words": [ { "start": 4326.01, "end": 4326.51, "word": " A", "probability": 0.6591796875 }, { "start": 4326.51, "end": 4326.79, "word": " bunch", "probability": 0.76708984375 }, { "start": 4326.79, "end": 4326.89, "word": " of", "probability": 0.9013671875 }, { "start": 4326.89, "end": 4327.13, "word": " people", "probability": 0.927734375 } ] }, { "id": 1212, "seek": 423166, "start": 4327.13, "end": 4329.25, "text": " piled on and I helped answer the question", "tokens": [ 50864, 6429, 292, 322, 293, 286, 4254, 1867, 264, 1168, 50964 ], "temperature": 0.0, "avg_logprob": -0.24690315395862134, "compression_ratio": 1.5555555555555556, "no_speech_prob": 0.0216064453125, "words": [ { "start": 4327.13, "end": 4327.53, "word": " piled", "probability": 0.864013671875 }, { "start": 4327.53, "end": 4327.73, "word": " on", "probability": 0.896484375 }, { "start": 4327.73, "end": 4327.85, "word": " and", "probability": 0.75 }, { "start": 4327.85, "end": 4327.99, "word": " I", "probability": 0.70068359375 }, { "start": 4327.99, "end": 4328.25, "word": " helped", "probability": 0.576171875 }, { "start": 4328.25, "end": 4328.79, "word": " answer", "probability": 0.74658203125 }, { "start": 4328.79, "end": 4328.95, "word": " the", "probability": 0.8095703125 }, { "start": 4328.95, "end": 4329.25, "word": " question", "probability": 0.74267578125 } ] }, { "id": 1213, "seek": 423166, "start": 4329.25, "end": 4331.15, "text": " because of what he asked.", "tokens": [ 50964, 570, 295, 437, 415, 2351, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.24690315395862134, "compression_ratio": 1.5555555555555556, "no_speech_prob": 0.0216064453125, "words": [ { "start": 4329.25, "end": 4329.67, "word": " because", "probability": 0.57568359375 }, { "start": 4329.67, "end": 4330.19, "word": " of", "probability": 0.254638671875 }, { "start": 4330.19, "end": 4330.31, "word": " what", "probability": 0.87451171875 }, { "start": 4330.31, "end": 4330.45, "word": " he", "probability": 0.896484375 }, { "start": 4330.45, "end": 4330.65, "word": " asked", "probability": 0.2744140625 }, { "start": 4330.65, "end": 4331.15, "word": ".", "probability": 0.87548828125 } ] }, { "id": 1214, "seek": 423166, "start": 4331.45, "end": 4333.51, "text": " Honestly, one of the most important things", "tokens": [ 51064, 12348, 11, 472, 295, 264, 881, 1021, 721, 51164 ], "temperature": 0.0, "avg_logprob": -0.24690315395862134, "compression_ratio": 1.5555555555555556, "no_speech_prob": 0.0216064453125, "words": [ { "start": 4331.45, "end": 4331.95, "word": " Honestly", "probability": 0.89208984375 }, { "start": 4331.95, "end": 4332.07, "word": ",", "probability": 0.7001953125 }, { "start": 4332.07, "end": 4332.19, "word": " one", "probability": 0.8125 }, { "start": 4332.19, "end": 4332.27, "word": " of", "probability": 0.9052734375 }, { "start": 4332.27, "end": 4332.35, "word": " the", "probability": 0.81494140625 }, { "start": 4332.35, "end": 4332.59, "word": " most", "probability": 0.8232421875 }, { "start": 4332.59, "end": 4332.99, "word": " important", "probability": 0.77685546875 }, { "start": 4332.99, "end": 4333.51, "word": " things", "probability": 0.7421875 } ] }, { "id": 1215, "seek": 423166, "start": 4333.51, "end": 4335.37, "text": " is the false positive", "tokens": [ 51164, 307, 264, 7908, 3353, 51264 ], "temperature": 0.0, "avg_logprob": -0.24690315395862134, "compression_ratio": 1.5555555555555556, "no_speech_prob": 0.0216064453125, "words": [ { "start": 4333.51, "end": 4334.35, "word": " is", "probability": 0.873046875 }, { "start": 4334.35, "end": 4334.85, "word": " the", "probability": 0.48046875 }, { "start": 4334.85, "end": 4335.07, "word": " false", "probability": 0.765625 }, { "start": 4335.07, "end": 4335.37, "word": " positive", "probability": 0.78662109375 } ] }, { "id": 1216, "seek": 423166, "start": 4335.37, "end": 4337.65, "text": " versus false negative trade-off.", "tokens": [ 51264, 5717, 7908, 3671, 4923, 12, 4506, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.24690315395862134, "compression_ratio": 1.5555555555555556, "no_speech_prob": 0.0216064453125, "words": [ { "start": 4335.37, "end": 4335.65, "word": " versus", "probability": 0.6396484375 }, { "start": 4335.65, "end": 4335.93, "word": " false", "probability": 0.82958984375 }, { "start": 4335.93, "end": 4336.37, "word": " negative", "probability": 0.87841796875 }, { "start": 4336.37, "end": 4337.09, "word": " trade", "probability": 0.7080078125 }, { "start": 4337.09, "end": 4337.33, "word": "-off", "probability": 0.74951171875 }, { "start": 4337.33, "end": 4337.65, "word": ".", "probability": 0.9365234375 } ] }, { "id": 1217, "seek": 423166, "start": 4337.65, "end": 4338.17, "text": " Yeah.", "tokens": [ 51364, 865, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.24690315395862134, "compression_ratio": 1.5555555555555556, "no_speech_prob": 0.0216064453125, "words": [ { "start": 4337.65, "end": 4337.79, "word": " Yeah", "probability": 0.333251953125 }, { "start": 4337.79, "end": 4338.17, "word": ".", "probability": 0.54443359375 } ] }, { "id": 1218, "seek": 423166, "start": 4340.71, "end": 4341.33, "text": " Yeah,", "tokens": [ 51464, 865, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.24690315395862134, "compression_ratio": 1.5555555555555556, "no_speech_prob": 0.0216064453125, "words": [ { "start": 4340.71, "end": 4341.21, "word": " Yeah", "probability": 0.33251953125 }, { "start": 4341.21, "end": 4341.33, "word": ",", "probability": 0.791015625 } ] }, { "id": 1219, "seek": 423166, "start": 4341.47, "end": 4343.41, "text": " a lot of people have strong opinions about that", "tokens": [ 51564, 257, 688, 295, 561, 362, 2068, 11819, 466, 300, 51664 ], "temperature": 0.0, "avg_logprob": -0.24690315395862134, "compression_ratio": 1.5555555555555556, "no_speech_prob": 0.0216064453125, "words": [ { "start": 4341.47, "end": 4341.59, "word": " a lot", "probability": 0.890625 }, { "start": 4341.59, "end": 4341.67, "word": " of", "probability": 0.90234375 }, { "start": 4341.67, "end": 4341.85, "word": " people", "probability": 0.92529296875 }, { "start": 4341.85, "end": 4342.09, "word": " have", "probability": 0.87158203125 }, { "start": 4342.09, "end": 4342.65, "word": " strong", "probability": 0.79150390625 }, { "start": 4342.65, "end": 4342.95, "word": " opinions", "probability": 0.80126953125 }, { "start": 4342.95, "end": 4343.21, "word": " about", "probability": 0.82177734375 }, { "start": 4343.21, "end": 4343.41, "word": " that", "probability": 0.88525390625 } ] }, { "id": 1220, "seek": 423166, "start": 4343.41, "end": 4345.67, "text": " because it's a lot of...", "tokens": [ 51664, 570, 309, 311, 257, 688, 295, 485, 51764 ], "temperature": 0.0, "avg_logprob": -0.24690315395862134, "compression_ratio": 1.5555555555555556, "no_speech_prob": 0.0216064453125, "words": [ { "start": 4343.41, "end": 4343.65, "word": " because", "probability": 0.3759765625 }, { "start": 4343.65, "end": 4343.99, "word": " it's", "probability": 0.905029296875 }, { "start": 4345.21, "end": 4345.35, "word": " a lot", "probability": 0.890625 }, { "start": 4345.35, "end": 4345.67, "word": " of...", "probability": 0.620849609375 } ] }, { "id": 1221, "seek": 425964, "start": 4345.67, "end": 4347.71, "text": " It's important. It's definitely", "tokens": [ 50364, 467, 311, 1021, 13, 467, 311, 2138, 50464 ], "temperature": 0.0, "avg_logprob": -0.16553758574532462, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.027587890625, "words": [ { "start": 4345.67, "end": 4345.99, "word": " It's", "probability": 0.7158203125 }, { "start": 4345.99, "end": 4346.35, "word": " important", "probability": 0.69873046875 }, { "start": 4346.35, "end": 4346.83, "word": ".", "probability": 0.67626953125 }, { "start": 4347.11, "end": 4347.41, "word": " It's", "probability": 0.917724609375 }, { "start": 4347.41, "end": 4347.71, "word": " definitely", "probability": 0.73095703125 } ] }, { "id": 1222, "seek": 425964, "start": 4347.71, "end": 4350.09, "text": " important, especially in data science.", "tokens": [ 50464, 1021, 11, 2318, 294, 1412, 3497, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.16553758574532462, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.027587890625, "words": [ { "start": 4347.71, "end": 4348.19, "word": " important", "probability": 0.7578125 }, { "start": 4348.19, "end": 4348.35, "word": ",", "probability": 0.5947265625 }, { "start": 4348.35, "end": 4348.73, "word": " especially", "probability": 0.712890625 }, { "start": 4348.73, "end": 4349.07, "word": " in", "probability": 0.9013671875 }, { "start": 4349.07, "end": 4349.29, "word": " data", "probability": 0.78271484375 }, { "start": 4349.29, "end": 4349.77, "word": " science", "probability": 0.86669921875 }, { "start": 4349.77, "end": 4350.09, "word": ".", "probability": 0.9111328125 } ] }, { "id": 1223, "seek": 425964, "start": 4350.09, "end": 4351.67, "text": " This, I'm...", "tokens": [ 50564, 639, 11, 286, 478, 485, 50664 ], "temperature": 0.0, "avg_logprob": -0.16553758574532462, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.027587890625, "words": [ { "start": 4350.09, "end": 4350.09, "word": " This", "probability": 0.383544921875 }, { "start": 4350.09, "end": 4350.25, "word": ",", "probability": 0.427001953125 }, { "start": 4350.25, "end": 4351.67, "word": " I'm...", "probability": 0.7808430989583334 } ] }, { "id": 1224, "seek": 425964, "start": 4353.03, "end": 4353.69, "text": " That might", "tokens": [ 50664, 663, 1062, 50764 ], "temperature": 0.0, "avg_logprob": -0.16553758574532462, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.027587890625, "words": [ { "start": 4353.03, "end": 4353.51, "word": " That", "probability": 0.432373046875 }, { "start": 4353.51, "end": 4353.69, "word": " might", "probability": 0.7861328125 } ] }, { "id": 1225, "seek": 425964, "start": 4353.69, "end": 4354.97, "text": " have been a good talk.", "tokens": [ 50764, 362, 668, 257, 665, 751, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.16553758574532462, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.027587890625, "words": [ { "start": 4353.69, "end": 4353.77, "word": " have", "probability": 0.6943359375 }, { "start": 4353.77, "end": 4353.89, "word": " been", "probability": 0.79541015625 }, { "start": 4353.99, "end": 4354.13, "word": " a good", "probability": 0.873046875 }, { "start": 4354.13, "end": 4354.49, "word": " talk", "probability": 0.83935546875 }, { "start": 4354.49, "end": 4354.97, "word": ".", "probability": 0.87548828125 } ] }, { "id": 1226, "seek": 425964, "start": 4355.35, "end": 4357.71, "text": " So, here's the interesting thing, is when I", "tokens": [ 50864, 407, 11, 510, 311, 264, 1880, 551, 11, 307, 562, 286, 50964 ], "temperature": 0.0, "avg_logprob": -0.16553758574532462, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.027587890625, "words": [ { "start": 4355.35, "end": 4355.83, "word": " So", "probability": 0.09429931640625 }, { "start": 4355.83, "end": 4356.11, "word": ",", "probability": 0.2939453125 }, { "start": 4356.11, "end": 4356.61, "word": " here's", "probability": 0.881591796875 }, { "start": 4356.61, "end": 4356.71, "word": " the", "probability": 0.814453125 }, { "start": 4356.71, "end": 4357.05, "word": " interesting", "probability": 0.66064453125 }, { "start": 4357.05, "end": 4357.31, "word": " thing", "probability": 0.8212890625 }, { "start": 4357.31, "end": 4357.37, "word": ",", "probability": 0.283203125 }, { "start": 4357.37, "end": 4357.47, "word": " is", "probability": 0.6015625 }, { "start": 4357.47, "end": 4357.59, "word": " when", "probability": 0.82470703125 }, { "start": 4357.59, "end": 4357.71, "word": " I", "probability": 0.994140625 } ] }, { "id": 1227, "seek": 425964, "start": 4357.71, "end": 4359.67, "text": " first started out, this", "tokens": [ 50964, 700, 1409, 484, 11, 341, 51064 ], "temperature": 0.0, "avg_logprob": -0.16553758574532462, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.027587890625, "words": [ { "start": 4357.71, "end": 4357.91, "word": " first", "probability": 0.8173828125 }, { "start": 4357.91, "end": 4358.17, "word": " started", "probability": 0.7958984375 }, { "start": 4358.17, "end": 4358.55, "word": " out", "probability": 0.81298828125 }, { "start": 4358.55, "end": 4359.25, "word": ",", "probability": 0.8095703125 }, { "start": 4359.25, "end": 4359.67, "word": " this", "probability": 0.84033203125 } ] }, { "id": 1228, "seek": 425964, "start": 4359.67, "end": 4361.55, "text": " I thought was amazing.", "tokens": [ 51064, 286, 1194, 390, 2243, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.16553758574532462, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.027587890625, "words": [ { "start": 4359.67, "end": 4360.33, "word": " I", "probability": 0.53955078125 }, { "start": 4360.33, "end": 4360.51, "word": " thought", "probability": 0.84716796875 }, { "start": 4360.51, "end": 4360.69, "word": " was", "probability": 0.892578125 }, { "start": 4360.69, "end": 4361.15, "word": " amazing", "probability": 0.84326171875 }, { "start": 4361.15, "end": 4361.55, "word": ".", "probability": 0.57421875 } ] }, { "id": 1229, "seek": 425964, "start": 4361.55, "end": 4363.53, "text": " Now, as I've learned", "tokens": [ 51164, 823, 11, 382, 286, 600, 3264, 51264 ], "temperature": 0.0, "avg_logprob": -0.16553758574532462, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.027587890625, "words": [ { "start": 4361.55, "end": 4361.97, "word": " Now", "probability": 0.1231689453125 }, { "start": 4361.97, "end": 4362.35, "word": ",", "probability": 0.64697265625 }, { "start": 4362.35, "end": 4362.57, "word": " as", "probability": 0.900390625 }, { "start": 4362.57, "end": 4362.97, "word": " I've", "probability": 0.94140625 }, { "start": 4362.97, "end": 4363.53, "word": " learned", "probability": 0.82373046875 } ] }, { "id": 1230, "seek": 425964, "start": 4363.53, "end": 4365.69, "text": " more over time, I kind of feel like, oh, no, this", "tokens": [ 51264, 544, 670, 565, 11, 286, 733, 295, 841, 411, 11, 1954, 11, 572, 11, 341, 51364 ], "temperature": 0.0, "avg_logprob": -0.16553758574532462, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.027587890625, "words": [ { "start": 4363.53, "end": 4363.87, "word": " more", "probability": 0.8681640625 }, { "start": 4363.87, "end": 4364.15, "word": " over", "probability": 0.86767578125 }, { "start": 4364.15, "end": 4364.49, "word": " time", "probability": 0.8037109375 }, { "start": 4364.49, "end": 4364.55, "word": ",", "probability": 0.92041015625 }, { "start": 4364.55, "end": 4364.65, "word": " I", "probability": 0.9892578125 }, { "start": 4364.65, "end": 4364.79, "word": " kind", "probability": 0.478515625 }, { "start": 4364.79, "end": 4364.87, "word": " of", "probability": 0.90576171875 }, { "start": 4364.87, "end": 4365.05, "word": " feel", "probability": 0.92236328125 }, { "start": 4365.05, "end": 4365.23, "word": " like", "probability": 0.86572265625 }, { "start": 4365.23, "end": 4365.29, "word": ",", "probability": 0.69677734375 }, { "start": 4365.29, "end": 4365.39, "word": " oh", "probability": 0.287841796875 }, { "start": 4365.39, "end": 4365.41, "word": ",", "probability": 0.52978515625 }, { "start": 4365.41, "end": 4365.49, "word": " no", "probability": 0.62939453125 }, { "start": 4365.49, "end": 4365.55, "word": ",", "probability": 0.84375 }, { "start": 4365.55, "end": 4365.69, "word": " this", "probability": 0.87939453125 } ] }, { "id": 1231, "seek": 425964, "start": 4365.69, "end": 4367.57, "text": " is a little clunky and a little ham-fisted.", "tokens": [ 51364, 307, 257, 707, 596, 25837, 293, 257, 707, 7852, 12, 69, 33250, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.16553758574532462, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.027587890625, "words": [ { "start": 4365.69, "end": 4365.81, "word": " is", "probability": 0.8994140625 }, { "start": 4365.89, "end": 4365.99, "word": " a little", "probability": 0.822265625 }, { "start": 4365.99, "end": 4366.37, "word": " clunky", "probability": 0.904541015625 }, { "start": 4366.37, "end": 4366.51, "word": " and", "probability": 0.814453125 }, { "start": 4366.57, "end": 4366.69, "word": " a little", "probability": 0.80810546875 }, { "start": 4366.69, "end": 4367.01, "word": " ham", "probability": 0.6669921875 }, { "start": 4367.01, "end": 4367.33, "word": "-fisted", "probability": 0.8234049479166666 }, { "start": 4367.33, "end": 4367.57, "word": ".", "probability": 0.71435546875 } ] }, { "id": 1232, "seek": 425964, "start": 4367.57, "end": 4369.67, "text": " I'm ignoring this, I'm ignoring this, I'm ignoring this,", "tokens": [ 51464, 286, 478, 26258, 341, 11, 286, 478, 26258, 341, 11, 286, 478, 26258, 341, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.16553758574532462, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.027587890625, "words": [ { "start": 4367.57, "end": 4367.77, "word": " I'm", "probability": 0.74658203125 }, { "start": 4367.77, "end": 4368.09, "word": " ignoring", "probability": 0.81884765625 }, { "start": 4368.09, "end": 4368.39, "word": " this", "probability": 0.87841796875 }, { "start": 4368.39, "end": 4368.47, "word": ",", "probability": 0.7744140625 }, { "start": 4368.47, "end": 4368.55, "word": " I'm", "probability": 0.8515625 }, { "start": 4368.55, "end": 4368.75, "word": " ignoring", "probability": 0.861328125 }, { "start": 4368.75, "end": 4369.03, "word": " this", "probability": 0.8759765625 }, { "start": 4369.03, "end": 4369.07, "word": ",", "probability": 0.7431640625 }, { "start": 4369.07, "end": 4369.17, "word": " I'm", "probability": 0.934326171875 }, { "start": 4369.17, "end": 4369.37, "word": " ignoring", "probability": 0.8681640625 }, { "start": 4369.37, "end": 4369.65, "word": " this", "probability": 0.876953125 }, { "start": 4369.65, "end": 4369.67, "word": ",", "probability": 0.6650390625 } ] }, { "id": 1233, "seek": 425964, "start": 4369.67, "end": 4371.85, "text": " I'm ignoring this. But this is a great", "tokens": [ 51564, 286, 478, 26258, 341, 13, 583, 341, 307, 257, 869, 51664 ], "temperature": 0.0, "avg_logprob": -0.16553758574532462, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.027587890625, "words": [ { "start": 4369.67, "end": 4369.79, "word": " I'm", "probability": 0.9287109375 }, { "start": 4369.79, "end": 4369.95, "word": " ignoring", "probability": 0.87353515625 }, { "start": 4369.95, "end": 4370.35, "word": " this", "probability": 0.8779296875 }, { "start": 4370.35, "end": 4370.77, "word": ".", "probability": 0.8076171875 }, { "start": 4370.77, "end": 4371.09, "word": " But", "probability": 0.79541015625 }, { "start": 4371.09, "end": 4371.25, "word": " this", "probability": 0.841796875 }, { "start": 4371.25, "end": 4371.37, "word": " is", "probability": 0.904296875 }, { "start": 4371.51, "end": 4371.85, "word": " a great", "probability": 0.888671875 } ] }, { "id": 1234, "seek": 425964, "start": 4371.85, "end": 4373.65, "text": " way for beginners to understand machine", "tokens": [ 51664, 636, 337, 26992, 281, 1223, 3479, 51764 ], "temperature": 0.0, "avg_logprob": -0.16553758574532462, "compression_ratio": 1.7653846153846153, "no_speech_prob": 0.027587890625, "words": [ { "start": 4371.85, "end": 4372.09, "word": " way", "probability": 0.90380859375 }, { "start": 4372.09, "end": 4372.27, "word": " for", "probability": 0.89990234375 }, { "start": 4372.27, "end": 4372.65, "word": " beginners", "probability": 0.7177734375 }, { "start": 4372.65, "end": 4372.93, "word": " to", "probability": 0.9091796875 }, { "start": 4372.93, "end": 4373.35, "word": " understand", "probability": 0.75927734375 }, { "start": 4373.35, "end": 4373.65, "word": " machine", "probability": 0.71875 } ] }, { "id": 1235, "seek": 428796, "start": 4373.65, "end": 4375.69, "text": " learning. And then from there,", "tokens": [ 50364, 2539, 13, 400, 550, 490, 456, 11, 50464 ], "temperature": 0.0, "avg_logprob": -0.2136904795964559, "compression_ratio": 1.6066350710900474, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4373.65, "end": 4373.95, "word": " learning", "probability": 0.6123046875 }, { "start": 4373.95, "end": 4374.47, "word": ".", "probability": 0.5888671875 }, { "start": 4375.03, "end": 4375.07, "word": " And", "probability": 0.57080078125 }, { "start": 4375.07, "end": 4375.19, "word": " then", "probability": 0.68359375 }, { "start": 4375.19, "end": 4375.37, "word": " from", "probability": 0.77490234375 }, { "start": 4375.37, "end": 4375.61, "word": " there", "probability": 0.849609375 }, { "start": 4375.61, "end": 4375.69, "word": ",", "probability": 0.440185546875 } ] }, { "id": 1236, "seek": 428796, "start": 4375.69, "end": 4376.97, "text": " you can kind of hop into", "tokens": [ 50464, 291, 393, 733, 295, 3818, 666, 50564 ], "temperature": 0.0, "avg_logprob": -0.2136904795964559, "compression_ratio": 1.6066350710900474, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4375.69, "end": 4375.77, "word": " you", "probability": 0.8984375 }, { "start": 4375.77, "end": 4375.93, "word": " can", "probability": 0.90087890625 }, { "start": 4375.93, "end": 4376.23, "word": " kind", "probability": 0.6826171875 }, { "start": 4376.23, "end": 4376.33, "word": " of", "probability": 0.90673828125 }, { "start": 4376.33, "end": 4376.55, "word": " hop", "probability": 0.76123046875 }, { "start": 4376.55, "end": 4376.97, "word": " into", "probability": 0.716796875 } ] }, { "id": 1237, "seek": 428796, "start": 4378.21, "end": 4379.63, "text": " a little bit more of the data", "tokens": [ 50564, 257, 707, 857, 544, 295, 264, 1412, 50664 ], "temperature": 0.0, "avg_logprob": -0.2136904795964559, "compression_ratio": 1.6066350710900474, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4378.21, "end": 4378.35, "word": " a little", "probability": 0.80322265625 }, { "start": 4378.35, "end": 4378.53, "word": " bit", "probability": 0.89794921875 }, { "start": 4378.53, "end": 4378.89, "word": " more", "probability": 0.888671875 }, { "start": 4378.89, "end": 4379.23, "word": " of", "probability": 0.89794921875 }, { "start": 4379.23, "end": 4379.41, "word": " the", "probability": 0.81494140625 }, { "start": 4379.41, "end": 4379.63, "word": " data", "probability": 0.81982421875 } ] }, { "id": 1238, "seek": 428796, "start": 4379.63, "end": 4381.25, "text": " science considerations, like", "tokens": [ 50664, 3497, 24070, 11, 411, 50764 ], "temperature": 0.0, "avg_logprob": -0.2136904795964559, "compression_ratio": 1.6066350710900474, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4379.63, "end": 4379.95, "word": " science", "probability": 0.86474609375 }, { "start": 4379.95, "end": 4380.57, "word": " considerations", "probability": 0.849609375 }, { "start": 4380.57, "end": 4381.03, "word": ",", "probability": 0.3427734375 }, { "start": 4381.03, "end": 4381.25, "word": " like", "probability": 0.87841796875 } ] }, { "id": 1239, "seek": 428796, "start": 4381.25, "end": 4383.13, "text": " imbalanced data sets, true", "tokens": [ 50764, 566, 40251, 1412, 6352, 11, 2074, 50864 ], "temperature": 0.0, "avg_logprob": -0.2136904795964559, "compression_ratio": 1.6066350710900474, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4381.25, "end": 4382.03, "word": " imbalanced", "probability": 0.747802734375 }, { "start": 4382.03, "end": 4382.31, "word": " data", "probability": 0.448486328125 }, { "start": 4382.31, "end": 4382.85, "word": " sets", "probability": 0.73974609375 }, { "start": 4382.85, "end": 4383.03, "word": ",", "probability": 0.9638671875 }, { "start": 4383.03, "end": 4383.13, "word": " true", "probability": 0.9013671875 } ] }, { "id": 1240, "seek": 428796, "start": 4383.65, "end": 4385.17, "text": " positives, false positives,", "tokens": [ 50864, 35127, 11, 7908, 35127, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.2136904795964559, "compression_ratio": 1.6066350710900474, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4383.65, "end": 4384.01, "word": " positives", "probability": 0.55224609375 }, { "start": 4384.01, "end": 4384.15, "word": ",", "probability": 0.92822265625 }, { "start": 4384.15, "end": 4384.29, "word": " false", "probability": 0.86181640625 }, { "start": 4384.29, "end": 4384.79, "word": " positives", "probability": 0.81005859375 }, { "start": 4384.79, "end": 4385.17, "word": ",", "probability": 0.779296875 } ] }, { "id": 1241, "seek": 428796, "start": 4385.17, "end": 4387.31, "text": " and some of those trade-offs,", "tokens": [ 50964, 293, 512, 295, 729, 4923, 12, 19231, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.2136904795964559, "compression_ratio": 1.6066350710900474, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4385.17, "end": 4385.93, "word": " and", "probability": 0.884765625 }, { "start": 4385.93, "end": 4386.09, "word": " some", "probability": 0.8154296875 }, { "start": 4386.09, "end": 4386.17, "word": " of", "probability": 0.9091796875 }, { "start": 4386.17, "end": 4386.31, "word": " those", "probability": 0.84619140625 }, { "start": 4386.31, "end": 4386.55, "word": " trade", "probability": 0.7900390625 }, { "start": 4386.55, "end": 4386.81, "word": "-offs", "probability": 0.707275390625 }, { "start": 4386.81, "end": 4387.31, "word": ",", "probability": 0.73486328125 } ] }, { "id": 1242, "seek": 428796, "start": 4387.31, "end": 4390.07, "text": " as well as more hyperparameter tuning.", "tokens": [ 51064, 382, 731, 382, 544, 9848, 2181, 335, 2398, 15164, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.2136904795964559, "compression_ratio": 1.6066350710900474, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4387.31, "end": 4387.71, "word": " as", "probability": 0.9052734375 }, { "start": 4387.71, "end": 4387.85, "word": " well", "probability": 0.8720703125 }, { "start": 4387.85, "end": 4387.99, "word": " as", "probability": 0.90087890625 }, { "start": 4387.99, "end": 4388.41, "word": " more", "probability": 0.41162109375 }, { "start": 4388.41, "end": 4389.19, "word": " hyperparameter", "probability": 0.884521484375 }, { "start": 4389.19, "end": 4389.55, "word": " tuning", "probability": 0.81689453125 }, { "start": 4389.55, "end": 4390.07, "word": ".", "probability": 0.994140625 } ] }, { "id": 1243, "seek": 428796, "start": 4393.79, "end": 4395.59, "text": " If you want to look at", "tokens": [ 51364, 759, 291, 528, 281, 574, 412, 51464 ], "temperature": 0.0, "avg_logprob": -0.2136904795964559, "compression_ratio": 1.6066350710900474, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4393.79, "end": 4394.31, "word": " If", "probability": 0.330810546875 }, { "start": 4394.31, "end": 4394.83, "word": " you", "probability": 0.89501953125 }, { "start": 4394.83, "end": 4394.97, "word": " want", "probability": 0.76611328125 }, { "start": 4394.97, "end": 4395.09, "word": " to", "probability": 0.90673828125 }, { "start": 4395.09, "end": 4395.27, "word": " look", "probability": 0.8935546875 }, { "start": 4395.27, "end": 4395.59, "word": " at", "probability": 0.81884765625 } ] }, { "id": 1244, "seek": 428796, "start": 4395.89, "end": 4397.91, "text": " a malware, you keep bringing it up,", "tokens": [ 51464, 257, 40747, 11, 291, 1066, 5062, 309, 493, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.2136904795964559, "compression_ratio": 1.6066350710900474, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4395.89, "end": 4396.31, "word": " a malware", "probability": 0.3154296875 }, { "start": 4396.31, "end": 4396.59, "word": ",", "probability": 0.5322265625 }, { "start": 4396.59, "end": 4396.63, "word": " you", "probability": 0.43359375 }, { "start": 4396.63, "end": 4397.01, "word": " keep", "probability": 0.215576171875 }, { "start": 4397.01, "end": 4397.27, "word": " bringing", "probability": 0.80908203125 }, { "start": 4397.27, "end": 4397.41, "word": " it", "probability": 0.89501953125 }, { "start": 4397.41, "end": 4397.61, "word": " up", "probability": 0.9140625 }, { "start": 4397.61, "end": 4397.91, "word": ",", "probability": 0.74609375 } ] }, { "id": 1245, "seek": 428796, "start": 4397.91, "end": 4398.81, "text": " you can look at the", "tokens": [ 51564, 291, 393, 574, 412, 264, 51664 ], "temperature": 0.0, "avg_logprob": -0.2136904795964559, "compression_ratio": 1.6066350710900474, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4397.91, "end": 4398.01, "word": " you", "probability": 0.8818359375 }, { "start": 4398.01, "end": 4398.17, "word": " can", "probability": 0.89892578125 }, { "start": 4398.17, "end": 4398.37, "word": " look", "probability": 0.8984375 }, { "start": 4398.37, "end": 4398.57, "word": " at", "probability": 0.7998046875 }, { "start": 4398.57, "end": 4398.81, "word": " the", "probability": 0.7470703125 } ] }, { "id": 1246, "seek": 428796, "start": 4399.97, "end": 4401.97, "text": " Google Endgame Ember.", "tokens": [ 51664, 3329, 6967, 15038, 3968, 607, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.2136904795964559, "compression_ratio": 1.6066350710900474, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4399.97, "end": 4400.49, "word": " Google", "probability": 0.78955078125 }, { "start": 4400.49, "end": 4401.01, "word": " Endgame", "probability": 0.52001953125 }, { "start": 4401.01, "end": 4401.45, "word": " Ember", "probability": 0.7008056640625 }, { "start": 4401.45, "end": 4401.97, "word": ".", "probability": 0.80712890625 } ] }, { "id": 1247, "seek": 431592, "start": 4401.97, "end": 4403.85, "text": " I'll drop a link in the", "tokens": [ 50364, 286, 603, 3270, 257, 2113, 294, 264, 50464 ], "temperature": 0.0, "avg_logprob": -0.18799999809265136, "compression_ratio": 1.728448275862069, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 4401.97, "end": 4402.63, "word": " I'll", "probability": 0.927734375 }, { "start": 4402.63, "end": 4402.81, "word": " drop", "probability": 0.828125 }, { "start": 4402.95, "end": 4403.17, "word": " a link", "probability": 0.87841796875 }, { "start": 4403.17, "end": 4403.55, "word": " in", "probability": 0.87841796875 }, { "start": 4403.55, "end": 4403.85, "word": " the", "probability": 0.53662109375 } ] }, { "id": 1248, "seek": 431592, "start": 4403.85, "end": 4406.03, "text": " Twitch chat in a sec. But there's", "tokens": [ 50464, 22222, 5081, 294, 257, 907, 13, 583, 456, 311, 50564 ], "temperature": 0.0, "avg_logprob": -0.18799999809265136, "compression_ratio": 1.728448275862069, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 4403.85, "end": 4404.25, "word": " Twitch", "probability": 0.62109375 }, { "start": 4404.25, "end": 4404.51, "word": " chat", "probability": 0.79296875 }, { "start": 4404.51, "end": 4404.63, "word": " in", "probability": 0.8818359375 }, { "start": 4404.75, "end": 4404.95, "word": " a sec", "probability": 0.7255859375 }, { "start": 4404.95, "end": 4405.47, "word": ".", "probability": 0.55322265625 }, { "start": 4405.51, "end": 4405.87, "word": " But", "probability": 0.748046875 }, { "start": 4405.87, "end": 4406.03, "word": " there's", "probability": 0.911376953125 } ] }, { "id": 1249, "seek": 431592, "start": 4406.15, "end": 4408.01, "text": " a malware model that you can look", "tokens": [ 50564, 257, 40747, 2316, 300, 291, 393, 574, 50664 ], "temperature": 0.0, "avg_logprob": -0.18799999809265136, "compression_ratio": 1.728448275862069, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 4406.15, "end": 4406.39, "word": " a malware", "probability": 0.8779296875 }, { "start": 4406.39, "end": 4406.73, "word": " model", "probability": 0.8046875 }, { "start": 4406.73, "end": 4407.01, "word": " that", "probability": 0.79833984375 }, { "start": 4407.01, "end": 4407.53, "word": " you", "probability": 0.89306640625 }, { "start": 4407.53, "end": 4407.73, "word": " can", "probability": 0.89453125 }, { "start": 4407.73, "end": 4408.01, "word": " look", "probability": 0.919921875 } ] }, { "id": 1250, "seek": 431592, "start": 4408.01, "end": 4409.93, "text": " into, like the open-source code,", "tokens": [ 50664, 666, 11, 411, 264, 1269, 12, 41676, 3089, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.18799999809265136, "compression_ratio": 1.728448275862069, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 4408.01, "end": 4408.31, "word": " into", "probability": 0.7255859375 }, { "start": 4408.31, "end": 4408.43, "word": ",", "probability": 0.53955078125 }, { "start": 4408.43, "end": 4408.57, "word": " like", "probability": 0.69091796875 }, { "start": 4408.57, "end": 4408.73, "word": " the", "probability": 0.73828125 }, { "start": 4408.73, "end": 4408.97, "word": " open", "probability": 0.71142578125 }, { "start": 4408.97, "end": 4409.11, "word": "-source", "probability": 0.5443115234375 }, { "start": 4409.11, "end": 4409.51, "word": " code", "probability": 0.83642578125 }, { "start": 4409.51, "end": 4409.93, "word": ",", "probability": 0.38818359375 } ] }, { "id": 1251, "seek": 431592, "start": 4409.93, "end": 4411.67, "text": " and the final thing at the end of that is", "tokens": [ 50764, 293, 264, 2572, 551, 412, 264, 917, 295, 300, 307, 50864 ], "temperature": 0.0, "avg_logprob": -0.18799999809265136, "compression_ratio": 1.728448275862069, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 4409.93, "end": 4410.05, "word": " and", "probability": 0.888671875 }, { "start": 4410.05, "end": 4410.23, "word": " the", "probability": 0.81689453125 }, { "start": 4410.23, "end": 4410.57, "word": " final", "probability": 0.88818359375 }, { "start": 4410.57, "end": 4410.83, "word": " thing", "probability": 0.814453125 }, { "start": 4410.83, "end": 4410.95, "word": " at", "probability": 0.8974609375 }, { "start": 4410.95, "end": 4411.05, "word": " the", "probability": 0.818359375 }, { "start": 4411.05, "end": 4411.17, "word": " end", "probability": 0.80859375 }, { "start": 4411.17, "end": 4411.25, "word": " of", "probability": 0.90234375 }, { "start": 4411.25, "end": 4411.41, "word": " that", "probability": 0.8759765625 }, { "start": 4411.41, "end": 4411.67, "word": " is", "probability": 0.89599609375 } ] }, { "id": 1252, "seek": 431592, "start": 4411.67, "end": 4413.57, "text": " it sets the false-positive rate to", "tokens": [ 50864, 309, 6352, 264, 7908, 12, 30010, 2187, 3314, 281, 50964 ], "temperature": 0.0, "avg_logprob": -0.18799999809265136, "compression_ratio": 1.728448275862069, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 4411.67, "end": 4412.25, "word": " it", "probability": 0.6220703125 }, { "start": 4412.25, "end": 4412.49, "word": " sets", "probability": 0.78955078125 }, { "start": 4412.49, "end": 4412.65, "word": " the", "probability": 0.80712890625 }, { "start": 4412.65, "end": 4412.81, "word": " false", "probability": 0.83837890625 }, { "start": 4412.81, "end": 4413.11, "word": "-positive", "probability": 0.6385904947916666 }, { "start": 4413.11, "end": 4413.35, "word": " rate", "probability": 0.86279296875 }, { "start": 4413.35, "end": 4413.57, "word": " to", "probability": 0.888671875 } ] }, { "id": 1253, "seek": 431592, "start": 4413.57, "end": 4414.85, "text": " 0.05%", "tokens": [ 50964, 1958, 13, 13328, 4, 51064 ], "temperature": 0.0, "avg_logprob": -0.18799999809265136, "compression_ratio": 1.728448275862069, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 4413.57, "end": 4413.89, "word": " 0", "probability": 0.837890625 }, { "start": 4413.89, "end": 4414.41, "word": ".05", "probability": 0.796142578125 }, { "start": 4414.41, "end": 4414.85, "word": "%", "probability": 0.315185546875 } ] }, { "id": 1254, "seek": 431592, "start": 4416.31, "end": 4418.31, "text": " or 0.5%", "tokens": [ 51064, 420, 1958, 13, 20, 4, 51164 ], "temperature": 0.0, "avg_logprob": -0.18799999809265136, "compression_ratio": 1.728448275862069, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 4416.31, "end": 4416.83, "word": " or", "probability": 0.29638671875 }, { "start": 4416.83, "end": 4417.13, "word": " 0", "probability": 0.96044921875 }, { "start": 4417.13, "end": 4417.97, "word": ".5", "probability": 0.9326171875 }, { "start": 4417.97, "end": 4418.31, "word": "%", "probability": 0.96240234375 } ] }, { "id": 1255, "seek": 431592, "start": 4418.31, "end": 4419.93, "text": " at the end, because that's", "tokens": [ 51164, 412, 264, 917, 11, 570, 300, 311, 51264 ], "temperature": 0.0, "avg_logprob": -0.18799999809265136, "compression_ratio": 1.728448275862069, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 4418.31, "end": 4419.15, "word": " at", "probability": 0.89990234375 }, { "start": 4419.15, "end": 4419.27, "word": " the", "probability": 0.81396484375 }, { "start": 4419.27, "end": 4419.41, "word": " end", "probability": 0.81884765625 }, { "start": 4419.41, "end": 4419.49, "word": ",", "probability": 0.564453125 }, { "start": 4419.49, "end": 4419.61, "word": " because", "probability": 0.8203125 }, { "start": 4419.61, "end": 4419.93, "word": " that's", "probability": 0.934814453125 } ] }, { "id": 1256, "seek": 431592, "start": 4419.93, "end": 4421.61, "text": " what you should do in production,", "tokens": [ 51264, 437, 291, 820, 360, 294, 4265, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.18799999809265136, "compression_ratio": 1.728448275862069, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 4419.93, "end": 4420.29, "word": " what", "probability": 0.8876953125 }, { "start": 4420.29, "end": 4420.49, "word": " you", "probability": 0.89599609375 }, { "start": 4420.49, "end": 4420.77, "word": " should", "probability": 0.9296875 }, { "start": 4420.77, "end": 4420.91, "word": " do", "probability": 0.9130859375 }, { "start": 4420.91, "end": 4421.03, "word": " in", "probability": 0.90185546875 }, { "start": 4421.03, "end": 4421.37, "word": " production", "probability": 0.7880859375 }, { "start": 4421.37, "end": 4421.61, "word": ",", "probability": 0.5673828125 } ] }, { "id": 1257, "seek": 431592, "start": 4421.61, "end": 4423.69, "text": " because customers care more about", "tokens": [ 51364, 570, 4581, 1127, 544, 466, 51464 ], "temperature": 0.0, "avg_logprob": -0.18799999809265136, "compression_ratio": 1.728448275862069, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 4421.61, "end": 4422.01, "word": " because", "probability": 0.59521484375 }, { "start": 4422.01, "end": 4422.99, "word": " customers", "probability": 0.75634765625 }, { "start": 4422.99, "end": 4423.27, "word": " care", "probability": 0.81298828125 }, { "start": 4423.27, "end": 4423.47, "word": " more", "probability": 0.88134765625 }, { "start": 4423.47, "end": 4423.69, "word": " about", "probability": 0.84033203125 } ] }, { "id": 1258, "seek": 431592, "start": 4423.69, "end": 4425.73, "text": " false positives, because", "tokens": [ 51464, 7908, 35127, 11, 570, 51564 ], "temperature": 0.0, "avg_logprob": -0.18799999809265136, "compression_ratio": 1.728448275862069, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 4423.69, "end": 4423.95, "word": " false", "probability": 0.8466796875 }, { "start": 4423.95, "end": 4424.37, "word": " positives", "probability": 0.54052734375 }, { "start": 4424.37, "end": 4425.01, "word": ",", "probability": 0.5546875 }, { "start": 4425.01, "end": 4425.73, "word": " because", "probability": 0.77587890625 } ] }, { "id": 1259, "seek": 431592, "start": 4426.59, "end": 4427.89, "text": " false positives lead to", "tokens": [ 51564, 7908, 35127, 1477, 281, 51664 ], "temperature": 0.0, "avg_logprob": -0.18799999809265136, "compression_ratio": 1.728448275862069, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 4426.59, "end": 4427.11, "word": " false", "probability": 0.85400390625 }, { "start": 4427.11, "end": 4427.39, "word": " positives", "probability": 0.79638671875 }, { "start": 4427.39, "end": 4427.69, "word": " lead", "probability": 0.46533203125 }, { "start": 4427.69, "end": 4427.89, "word": " to", "probability": 0.904296875 } ] }, { "id": 1260, "seek": 431592, "start": 4427.89, "end": 4429.93, "text": " alert fatigue, and alert fatigue leads to", "tokens": [ 51664, 9615, 20574, 11, 293, 9615, 20574, 6689, 281, 51764 ], "temperature": 0.0, "avg_logprob": -0.18799999809265136, "compression_ratio": 1.728448275862069, "no_speech_prob": 0.00183868408203125, "words": [ { "start": 4427.89, "end": 4428.17, "word": " alert", "probability": 0.80517578125 }, { "start": 4428.17, "end": 4428.55, "word": " fatigue", "probability": 0.93408203125 }, { "start": 4428.55, "end": 4428.73, "word": ",", "probability": 0.72705078125 }, { "start": 4428.73, "end": 4428.83, "word": " and", "probability": 0.88916015625 }, { "start": 4428.83, "end": 4429.11, "word": " alert", "probability": 0.7568359375 }, { "start": 4429.11, "end": 4429.41, "word": " fatigue", "probability": 0.94775390625 }, { "start": 4429.41, "end": 4429.71, "word": " leads", "probability": 0.72216796875 }, { "start": 4429.71, "end": 4429.93, "word": " to", "probability": 0.90087890625 } ] }, { "id": 1261, "seek": 434376, "start": 4429.93, "end": 4431.87, "text": " just ignoring every single", "tokens": [ 50364, 445, 26258, 633, 2167, 50464 ], "temperature": 0.0, "avg_logprob": -0.21389181348456054, "compression_ratio": 1.7467811158798283, "no_speech_prob": 0.04083251953125, "words": [ { "start": 4429.93, "end": 4430.13, "word": " just", "probability": 0.2442626953125 }, { "start": 4430.13, "end": 4430.59, "word": " ignoring", "probability": 0.865234375 }, { "start": 4430.59, "end": 4430.87, "word": " every", "probability": 0.55078125 }, { "start": 4430.87, "end": 4431.87, "word": " single", "probability": 0.86767578125 } ] }, { "id": 1262, "seek": 434376, "start": 4431.87, "end": 4433.83, "text": " alert, and then all the false negatives get", "tokens": [ 50464, 9615, 11, 293, 550, 439, 264, 7908, 40019, 483, 50564 ], "temperature": 0.0, "avg_logprob": -0.21389181348456054, "compression_ratio": 1.7467811158798283, "no_speech_prob": 0.04083251953125, "words": [ { "start": 4431.87, "end": 4432.17, "word": " alert", "probability": 0.82421875 }, { "start": 4432.17, "end": 4432.39, "word": ",", "probability": 0.4453125 }, { "start": 4432.39, "end": 4432.53, "word": " and", "probability": 0.849609375 }, { "start": 4432.53, "end": 4432.67, "word": " then", "probability": 0.6845703125 }, { "start": 4432.67, "end": 4432.91, "word": " all", "probability": 0.88525390625 }, { "start": 4432.91, "end": 4433.05, "word": " the", "probability": 0.79150390625 }, { "start": 4433.05, "end": 4433.27, "word": " false", "probability": 0.82958984375 }, { "start": 4433.27, "end": 4433.57, "word": " negatives", "probability": 0.828125 }, { "start": 4433.57, "end": 4433.83, "word": " get", "probability": 0.8740234375 } ] }, { "id": 1263, "seek": 434376, "start": 4433.83, "end": 4435.93, "text": " through anyway. All the true negatives get through", "tokens": [ 50564, 807, 4033, 13, 1057, 264, 2074, 40019, 483, 807, 50664 ], "temperature": 0.0, "avg_logprob": -0.21389181348456054, "compression_ratio": 1.7467811158798283, "no_speech_prob": 0.04083251953125, "words": [ { "start": 4433.83, "end": 4434.05, "word": " through", "probability": 0.7919921875 }, { "start": 4434.05, "end": 4434.53, "word": " anyway", "probability": 0.806640625 }, { "start": 4434.53, "end": 4434.87, "word": ".", "probability": 0.65185546875 }, { "start": 4434.87, "end": 4434.97, "word": " All", "probability": 0.72802734375 }, { "start": 4434.97, "end": 4435.11, "word": " the", "probability": 0.814453125 }, { "start": 4435.11, "end": 4435.27, "word": " true", "probability": 0.9287109375 }, { "start": 4435.27, "end": 4435.57, "word": " negatives", "probability": 0.77587890625 }, { "start": 4435.57, "end": 4435.75, "word": " get", "probability": 0.8935546875 }, { "start": 4435.75, "end": 4435.93, "word": " through", "probability": 0.80859375 } ] }, { "id": 1264, "seek": 434376, "start": 4435.93, "end": 4436.77, "text": " anyway.", "tokens": [ 50664, 4033, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.21389181348456054, "compression_ratio": 1.7467811158798283, "no_speech_prob": 0.04083251953125, "words": [ { "start": 4435.93, "end": 4436.33, "word": " anyway", "probability": 0.8369140625 }, { "start": 4436.33, "end": 4436.77, "word": ".", "probability": 0.94970703125 } ] }, { "id": 1265, "seek": 434376, "start": 4437.91, "end": 4439.93, "text": " It is something...", "tokens": [ 50764, 467, 307, 746, 485, 50864 ], "temperature": 0.0, "avg_logprob": -0.21389181348456054, "compression_ratio": 1.7467811158798283, "no_speech_prob": 0.04083251953125, "words": [ { "start": 4437.91, "end": 4438.35, "word": " It", "probability": 0.110107421875 }, { "start": 4438.35, "end": 4438.79, "word": " is", "probability": 0.81591796875 }, { "start": 4438.79, "end": 4439.93, "word": " something...", "probability": 0.513427734375 } ] }, { "id": 1266, "seek": 434376, "start": 4440.75, "end": 4441.91, "text": " Yeah, and even that", "tokens": [ 50864, 865, 11, 293, 754, 300, 50964 ], "temperature": 0.0, "avg_logprob": -0.21389181348456054, "compression_ratio": 1.7467811158798283, "no_speech_prob": 0.04083251953125, "words": [ { "start": 4440.75, "end": 4440.89, "word": " Yeah", "probability": 0.319091796875 }, { "start": 4440.89, "end": 4441.05, "word": ",", "probability": 0.69482421875 }, { "start": 4441.05, "end": 4441.23, "word": " and", "probability": 0.74462890625 }, { "start": 4441.23, "end": 4441.69, "word": " even", "probability": 0.8134765625 }, { "start": 4441.69, "end": 4441.91, "word": " that", "probability": 0.88037109375 } ] }, { "id": 1267, "seek": 434376, "start": 4441.91, "end": 4444.03, "text": " model is a little clunky and hampers.", "tokens": [ 50964, 2316, 307, 257, 707, 596, 25837, 293, 324, 2455, 433, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.21389181348456054, "compression_ratio": 1.7467811158798283, "no_speech_prob": 0.04083251953125, "words": [ { "start": 4441.91, "end": 4442.19, "word": " model", "probability": 0.806640625 }, { "start": 4442.19, "end": 4442.57, "word": " is", "probability": 0.87158203125 }, { "start": 4442.73, "end": 4442.87, "word": " a little", "probability": 0.826171875 }, { "start": 4442.87, "end": 4443.19, "word": " clunky", "probability": 0.89306640625 }, { "start": 4443.19, "end": 4443.37, "word": " and", "probability": 0.4541015625 }, { "start": 4443.37, "end": 4443.71, "word": " hampers", "probability": 0.5763346354166666 }, { "start": 4443.71, "end": 4444.03, "word": ".", "probability": 0.27490234375 } ] }, { "id": 1268, "seek": 434376, "start": 4445.09, "end": 4445.75, "text": " Well, and", "tokens": [ 51064, 1042, 11, 293, 51164 ], "temperature": 0.0, "avg_logprob": -0.21389181348456054, "compression_ratio": 1.7467811158798283, "no_speech_prob": 0.04083251953125, "words": [ { "start": 4445.09, "end": 4445.53, "word": " Well", "probability": 0.2783203125 }, { "start": 4445.53, "end": 4445.69, "word": ",", "probability": 0.90087890625 }, { "start": 4445.69, "end": 4445.75, "word": " and", "probability": 0.48583984375 } ] }, { "id": 1269, "seek": 434376, "start": 4446.69, "end": 4448.05, "text": " it kind of leads to", "tokens": [ 51164, 309, 733, 295, 6689, 281, 51264 ], "temperature": 0.0, "avg_logprob": -0.21389181348456054, "compression_ratio": 1.7467811158798283, "no_speech_prob": 0.04083251953125, "words": [ { "start": 4446.69, "end": 4447.13, "word": " it", "probability": 0.6494140625 }, { "start": 4447.13, "end": 4447.29, "word": " kind", "probability": 0.61669921875 }, { "start": 4447.29, "end": 4447.37, "word": " of", "probability": 0.91015625 }, { "start": 4447.37, "end": 4447.65, "word": " leads", "probability": 0.7353515625 }, { "start": 4447.65, "end": 4448.05, "word": " to", "probability": 0.869140625 } ] }, { "id": 1270, "seek": 434376, "start": 4448.05, "end": 4449.91, "text": " with the alert fatigue, it kind of leads", "tokens": [ 51264, 365, 264, 9615, 20574, 11, 309, 733, 295, 6689, 51364 ], "temperature": 0.0, "avg_logprob": -0.21389181348456054, "compression_ratio": 1.7467811158798283, "no_speech_prob": 0.04083251953125, "words": [ { "start": 4448.05, "end": 4448.75, "word": " with", "probability": 0.062164306640625 }, { "start": 4448.75, "end": 4448.87, "word": " the", "probability": 0.80517578125 }, { "start": 4448.87, "end": 4449.03, "word": " alert", "probability": 0.72314453125 }, { "start": 4449.03, "end": 4449.35, "word": " fatigue", "probability": 0.94482421875 }, { "start": 4449.35, "end": 4449.43, "word": ",", "probability": 0.7109375 }, { "start": 4449.43, "end": 4449.51, "word": " it", "probability": 0.84228515625 }, { "start": 4449.51, "end": 4449.63, "word": " kind", "probability": 0.72119140625 }, { "start": 4449.63, "end": 4449.71, "word": " of", "probability": 0.91162109375 }, { "start": 4449.71, "end": 4449.91, "word": " leads", "probability": 0.7333984375 } ] }, { "id": 1271, "seek": 434376, "start": 4449.91, "end": 4451.69, "text": " to the common thing that we", "tokens": [ 51364, 281, 264, 2689, 551, 300, 321, 51464 ], "temperature": 0.0, "avg_logprob": -0.21389181348456054, "compression_ratio": 1.7467811158798283, "no_speech_prob": 0.04083251953125, "words": [ { "start": 4449.91, "end": 4450.17, "word": " to", "probability": 0.90380859375 }, { "start": 4450.17, "end": 4450.45, "word": " the", "probability": 0.80810546875 }, { "start": 4450.45, "end": 4451.01, "word": " common", "probability": 0.63427734375 }, { "start": 4451.01, "end": 4451.41, "word": " thing", "probability": 0.81591796875 }, { "start": 4451.41, "end": 4451.57, "word": " that", "probability": 0.87060546875 }, { "start": 4451.57, "end": 4451.69, "word": " we", "probability": 0.90673828125 } ] }, { "id": 1272, "seek": 434376, "start": 4452.57, "end": 4453.93, "text": " hear, especially in the technical", "tokens": [ 51464, 1568, 11, 2318, 294, 264, 6191, 51564 ], "temperature": 0.0, "avg_logprob": -0.21389181348456054, "compression_ratio": 1.7467811158798283, "no_speech_prob": 0.04083251953125, "words": [ { "start": 4452.57, "end": 4453.01, "word": " hear", "probability": 0.8515625 }, { "start": 4453.01, "end": 4453.23, "word": ",", "probability": 0.8134765625 }, { "start": 4453.23, "end": 4453.41, "word": " especially", "probability": 0.72021484375 }, { "start": 4453.41, "end": 4453.57, "word": " in", "probability": 0.900390625 }, { "start": 4453.57, "end": 4453.65, "word": " the", "probability": 0.81591796875 }, { "start": 4453.65, "end": 4453.93, "word": " technical", "probability": 0.8623046875 } ] }, { "id": 1273, "seek": 434376, "start": 4453.93, "end": 4455.99, "text": " community from non-technical people,", "tokens": [ 51564, 1768, 490, 2107, 12, 29113, 804, 561, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.21389181348456054, "compression_ratio": 1.7467811158798283, "no_speech_prob": 0.04083251953125, "words": [ { "start": 4453.93, "end": 4454.59, "word": " community", "probability": 0.81201171875 }, { "start": 4454.59, "end": 4454.95, "word": " from", "probability": 0.6328125 }, { "start": 4454.95, "end": 4455.25, "word": " non", "probability": 0.88427734375 }, { "start": 4455.25, "end": 4455.53, "word": "-technical", "probability": 0.8990885416666666 }, { "start": 4455.53, "end": 4455.85, "word": " people", "probability": 0.923828125 }, { "start": 4455.85, "end": 4455.99, "word": ",", "probability": 0.376220703125 } ] }, { "id": 1274, "seek": 434376, "start": 4455.99, "end": 4457.77, "text": " of why does my thing not work?", "tokens": [ 51664, 295, 983, 775, 452, 551, 406, 589, 30, 51764 ], "temperature": 0.0, "avg_logprob": -0.21389181348456054, "compression_ratio": 1.7467811158798283, "no_speech_prob": 0.04083251953125, "words": [ { "start": 4455.99, "end": 4456.05, "word": " of", "probability": 0.48486328125 }, { "start": 4456.05, "end": 4456.37, "word": " why", "probability": 0.31005859375 }, { "start": 4456.37, "end": 4456.55, "word": " does", "probability": 0.91552734375 }, { "start": 4456.55, "end": 4456.71, "word": " my", "probability": 0.90087890625 }, { "start": 4456.71, "end": 4456.89, "word": " thing", "probability": 0.82177734375 }, { "start": 4456.89, "end": 4457.07, "word": " not", "probability": 0.90087890625 }, { "start": 4457.07, "end": 4457.33, "word": " work", "probability": 0.8115234375 }, { "start": 4457.33, "end": 4457.77, "word": "?", "probability": 0.87451171875 } ] }, { "id": 1275, "seek": 437080, "start": 4458.61, "end": 4459.41, "text": " Okay.", "tokens": [ 50364, 1033, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.19124482781433863, "compression_ratio": 1.554263565891473, "no_speech_prob": 0.0002453327178955078, "words": [ { "start": 4458.61, "end": 4459.01, "word": " Okay", "probability": 0.436279296875 }, { "start": 4459.01, "end": 4459.41, "word": ".", "probability": 0.46923828125 } ] }, { "id": 1276, "seek": 437080, "start": 4460.27, "end": 4461.99, "text": " So that kind of helps address it.", "tokens": [ 50464, 407, 300, 733, 295, 3665, 2985, 309, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.19124482781433863, "compression_ratio": 1.554263565891473, "no_speech_prob": 0.0002453327178955078, "words": [ { "start": 4460.27, "end": 4460.67, "word": " So", "probability": 0.8349609375 }, { "start": 4460.67, "end": 4460.87, "word": " that", "probability": 0.79248046875 }, { "start": 4460.87, "end": 4461.03, "word": " kind", "probability": 0.6494140625 }, { "start": 4461.03, "end": 4461.09, "word": " of", "probability": 0.90673828125 }, { "start": 4461.09, "end": 4461.25, "word": " helps", "probability": 0.708984375 }, { "start": 4461.25, "end": 4461.51, "word": " address", "probability": 0.78857421875 }, { "start": 4461.51, "end": 4461.77, "word": " it", "probability": 0.9033203125 }, { "start": 4461.77, "end": 4461.99, "word": ".", "probability": 0.62158203125 } ] }, { "id": 1277, "seek": 437080, "start": 4461.99, "end": 4464.41, "text": " But yeah, these are all data science considerations.", "tokens": [ 50564, 583, 1338, 11, 613, 366, 439, 1412, 3497, 24070, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.19124482781433863, "compression_ratio": 1.554263565891473, "no_speech_prob": 0.0002453327178955078, "words": [ { "start": 4461.99, "end": 4462.11, "word": " But", "probability": 0.83349609375 }, { "start": 4462.11, "end": 4462.27, "word": " yeah", "probability": 0.8544921875 }, { "start": 4462.27, "end": 4462.31, "word": ",", "probability": 0.9072265625 }, { "start": 4462.31, "end": 4462.47, "word": " these", "probability": 0.70068359375 }, { "start": 4462.47, "end": 4462.57, "word": " are", "probability": 0.8896484375 }, { "start": 4462.57, "end": 4462.79, "word": " all", "probability": 0.89208984375 }, { "start": 4462.79, "end": 4463.15, "word": " data", "probability": 0.18994140625 }, { "start": 4463.15, "end": 4463.45, "word": " science", "probability": 0.85595703125 }, { "start": 4463.45, "end": 4464.01, "word": " considerations", "probability": 0.85009765625 }, { "start": 4464.01, "end": 4464.41, "word": ".", "probability": 0.9873046875 } ] }, { "id": 1278, "seek": 437080, "start": 4465.41, "end": 4465.93, "text": " So I'm", "tokens": [ 50664, 407, 286, 478, 50764 ], "temperature": 0.0, "avg_logprob": -0.19124482781433863, "compression_ratio": 1.554263565891473, "no_speech_prob": 0.0002453327178955078, "words": [ { "start": 4465.41, "end": 4465.81, "word": " So", "probability": 0.84619140625 }, { "start": 4465.81, "end": 4465.93, "word": " I'm", "probability": 0.977294921875 } ] }, { "id": 1279, "seek": 437080, "start": 4465.93, "end": 4467.15, "text": " going to go ahead and run this.", "tokens": [ 50764, 516, 281, 352, 2286, 293, 1190, 341, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.19124482781433863, "compression_ratio": 1.554263565891473, "no_speech_prob": 0.0002453327178955078, "words": [ { "start": 4465.93, "end": 4465.93, "word": " going", "probability": 0.322021484375 }, { "start": 4465.93, "end": 4465.97, "word": " to", "probability": 0.9052734375 }, { "start": 4465.97, "end": 4466.07, "word": " go", "probability": 0.89794921875 }, { "start": 4466.07, "end": 4466.21, "word": " ahead", "probability": 0.8447265625 }, { "start": 4466.21, "end": 4466.31, "word": " and", "probability": 0.89404296875 }, { "start": 4466.31, "end": 4466.45, "word": " run", "probability": 0.8935546875 }, { "start": 4466.45, "end": 4466.75, "word": " this", "probability": 0.88818359375 }, { "start": 4466.75, "end": 4467.15, "word": ".", "probability": 0.64697265625 } ] }, { "id": 1280, "seek": 437080, "start": 4467.43, "end": 4468.65, "text": " Shift-Enter.", "tokens": [ 50864, 28304, 12, 16257, 391, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.19124482781433863, "compression_ratio": 1.554263565891473, "no_speech_prob": 0.0002453327178955078, "words": [ { "start": 4467.43, "end": 4467.83, "word": " Shift", "probability": 0.7451171875 }, { "start": 4467.83, "end": 4468.25, "word": "-Enter", "probability": 0.5202229817708334 }, { "start": 4468.25, "end": 4468.65, "word": ".", "probability": 0.880859375 } ] }, { "id": 1281, "seek": 437080, "start": 4469.69, "end": 4472.07, "text": " And this is going to take a little bit longer than the multinomial", "tokens": [ 50964, 400, 341, 307, 516, 281, 747, 257, 707, 857, 2854, 813, 264, 45872, 47429, 51064 ], "temperature": 0.0, "avg_logprob": -0.19124482781433863, "compression_ratio": 1.554263565891473, "no_speech_prob": 0.0002453327178955078, "words": [ { "start": 4469.69, "end": 4470.03, "word": " And", "probability": 0.78369140625 }, { "start": 4470.03, "end": 4470.17, "word": " this", "probability": 0.88037109375 }, { "start": 4470.17, "end": 4470.27, "word": " is", "probability": 0.90380859375 }, { "start": 4470.27, "end": 4470.33, "word": " going", "probability": 0.81640625 }, { "start": 4470.33, "end": 4470.41, "word": " to", "probability": 0.90576171875 }, { "start": 4470.41, "end": 4470.55, "word": " take", "probability": 0.8115234375 }, { "start": 4470.73, "end": 4470.89, "word": " a little", "probability": 0.80859375 }, { "start": 4470.89, "end": 4471.03, "word": " bit", "probability": 0.8837890625 }, { "start": 4471.03, "end": 4471.25, "word": " longer", "probability": 0.833984375 }, { "start": 4471.25, "end": 4471.43, "word": " than", "probability": 0.87841796875 }, { "start": 4471.43, "end": 4471.57, "word": " the", "probability": 0.8046875 }, { "start": 4471.57, "end": 4472.07, "word": " multinomial", "probability": 0.867431640625 } ] }, { "id": 1282, "seek": 437080, "start": 4472.07, "end": 4473.63, "text": " Naive Bayesian, because logistic", "tokens": [ 51064, 6056, 488, 7840, 42434, 11, 570, 3565, 3142, 51164 ], "temperature": 0.0, "avg_logprob": -0.19124482781433863, "compression_ratio": 1.554263565891473, "no_speech_prob": 0.0002453327178955078, "words": [ { "start": 4472.07, "end": 4472.43, "word": " Naive", "probability": 0.5330810546875 }, { "start": 4472.43, "end": 4472.75, "word": " Bayesian", "probability": 0.887939453125 }, { "start": 4472.75, "end": 4472.91, "word": ",", "probability": 0.356689453125 }, { "start": 4472.91, "end": 4473.13, "word": " because", "probability": 0.8359375 }, { "start": 4473.13, "end": 4473.63, "word": " logistic", "probability": 0.908203125 } ] }, { "id": 1283, "seek": 437080, "start": 4473.63, "end": 4475.83, "text": " regression interprets", "tokens": [ 51164, 24590, 17489, 1373, 51264 ], "temperature": 0.0, "avg_logprob": -0.19124482781433863, "compression_ratio": 1.554263565891473, "no_speech_prob": 0.0002453327178955078, "words": [ { "start": 4473.63, "end": 4474.13, "word": " regression", "probability": 0.8818359375 }, { "start": 4474.13, "end": 4475.83, "word": " interprets", "probability": 0.84521484375 } ] }, { "id": 1284, "seek": 437080, "start": 4475.83, "end": 4477.75, "text": " the data a little differently, and so it needs to", "tokens": [ 51264, 264, 1412, 257, 707, 7614, 11, 293, 370, 309, 2203, 281, 51364 ], "temperature": 0.0, "avg_logprob": -0.19124482781433863, "compression_ratio": 1.554263565891473, "no_speech_prob": 0.0002453327178955078, "words": [ { "start": 4475.83, "end": 4476.01, "word": " the", "probability": 0.8154296875 }, { "start": 4476.01, "end": 4476.23, "word": " data", "probability": 0.80859375 }, { "start": 4476.43, "end": 4476.51, "word": " a little", "probability": 0.80810546875 }, { "start": 4476.51, "end": 4476.89, "word": " differently", "probability": 0.65087890625 }, { "start": 4476.89, "end": 4477.07, "word": ",", "probability": 0.61669921875 }, { "start": 4477.07, "end": 4477.15, "word": " and", "probability": 0.81103515625 }, { "start": 4477.15, "end": 4477.27, "word": " so", "probability": 0.90234375 }, { "start": 4477.27, "end": 4477.39, "word": " it", "probability": 0.900390625 }, { "start": 4477.39, "end": 4477.59, "word": " needs", "probability": 0.755859375 }, { "start": 4477.59, "end": 4477.75, "word": " to", "probability": 0.90673828125 } ] }, { "id": 1285, "seek": 437080, "start": 4477.75, "end": 4480.15, "text": " go through and kind of count things properly.", "tokens": [ 51364, 352, 807, 293, 733, 295, 1207, 721, 6108, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.19124482781433863, "compression_ratio": 1.554263565891473, "no_speech_prob": 0.0002453327178955078, "words": [ { "start": 4477.75, "end": 4477.91, "word": " go", "probability": 0.89697265625 }, { "start": 4477.91, "end": 4478.19, "word": " through", "probability": 0.80810546875 }, { "start": 4478.19, "end": 4478.45, "word": " and", "probability": 0.875 }, { "start": 4478.45, "end": 4478.63, "word": " kind", "probability": 0.57568359375 }, { "start": 4478.63, "end": 4478.73, "word": " of", "probability": 0.90625 }, { "start": 4478.73, "end": 4479.03, "word": " count", "probability": 0.81494140625 }, { "start": 4479.03, "end": 4479.33, "word": " things", "probability": 0.728515625 }, { "start": 4479.33, "end": 4479.75, "word": " properly", "probability": 0.830078125 }, { "start": 4479.75, "end": 4480.15, "word": ".", "probability": 0.99853515625 } ] }, { "id": 1286, "seek": 437080, "start": 4481.65, "end": 4482.05, "text": " This", "tokens": [ 51464, 639, 51564 ], "temperature": 0.0, "avg_logprob": -0.19124482781433863, "compression_ratio": 1.554263565891473, "no_speech_prob": 0.0002453327178955078, "words": [ { "start": 4481.65, "end": 4482.05, "word": " This", "probability": 0.814453125 } ] }, { "id": 1287, "seek": 437080, "start": 4482.05, "end": 4483.19, "text": " takes, I think, about", "tokens": [ 51564, 2516, 11, 286, 519, 11, 466, 51664 ], "temperature": 0.0, "avg_logprob": -0.19124482781433863, "compression_ratio": 1.554263565891473, "no_speech_prob": 0.0002453327178955078, "words": [ { "start": 4482.05, "end": 4482.41, "word": " takes", "probability": 0.73193359375 }, { "start": 4482.41, "end": 4482.73, "word": ",", "probability": 0.7548828125 }, { "start": 4482.73, "end": 4482.85, "word": " I", "probability": 0.998046875 }, { "start": 4482.85, "end": 4482.97, "word": " think", "probability": 0.8095703125 }, { "start": 4482.97, "end": 4483.01, "word": ",", "probability": 0.58740234375 }, { "start": 4483.01, "end": 4483.19, "word": " about", "probability": 0.8203125 } ] }, { "id": 1288, "seek": 437080, "start": 4483.65, "end": 4484.81, "text": " 30 seconds?", "tokens": [ 51664, 2217, 3949, 30, 51764 ], "temperature": 0.0, "avg_logprob": -0.19124482781433863, "compression_ratio": 1.554263565891473, "no_speech_prob": 0.0002453327178955078, "words": [ { "start": 4483.65, "end": 4484.05, "word": " 30", "probability": 0.86767578125 }, { "start": 4484.05, "end": 4484.41, "word": " seconds", "probability": 0.72021484375 }, { "start": 4484.41, "end": 4484.81, "word": "?", "probability": 0.3828125 } ] }, { "id": 1289, "seek": 439874, "start": 4486.31, "end": 4486.83, "text": " Yeah, it's", "tokens": [ 50364, 865, 11, 309, 311, 50464 ], "temperature": 0.0, "avg_logprob": -0.16710069541026046, "compression_ratio": 1.5, "no_speech_prob": 0.00036263465881347656, "words": [ { "start": 4486.31, "end": 4486.63, "word": " Yeah", "probability": 0.380859375 }, { "start": 4486.63, "end": 4486.69, "word": ",", "probability": 0.75146484375 }, { "start": 4486.69, "end": 4486.83, "word": " it's", "probability": 0.927001953125 } ] }, { "id": 1290, "seek": 439874, "start": 4487.67, "end": 4488.67, "text": " not too bad. It's", "tokens": [ 50464, 406, 886, 1578, 13, 467, 311, 50564 ], "temperature": 0.0, "avg_logprob": -0.16710069541026046, "compression_ratio": 1.5, "no_speech_prob": 0.00036263465881347656, "words": [ { "start": 4487.67, "end": 4487.99, "word": " not", "probability": 0.268310546875 }, { "start": 4487.99, "end": 4488.31, "word": " too", "probability": 0.79541015625 }, { "start": 4488.31, "end": 4488.49, "word": " bad", "probability": 0.8759765625 }, { "start": 4488.49, "end": 4488.61, "word": ".", "probability": 0.55810546875 }, { "start": 4488.61, "end": 4488.67, "word": " It's", "probability": 0.934814453125 } ] }, { "id": 1291, "seek": 439874, "start": 4488.67, "end": 4490.43, "text": " 30 to 60 seconds.", "tokens": [ 50564, 2217, 281, 4060, 3949, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.16710069541026046, "compression_ratio": 1.5, "no_speech_prob": 0.00036263465881347656, "words": [ { "start": 4488.67, "end": 4489.27, "word": " 30", "probability": 0.8896484375 }, { "start": 4489.27, "end": 4489.43, "word": " to", "probability": 0.66796875 }, { "start": 4489.43, "end": 4489.67, "word": " 60", "probability": 0.93505859375 }, { "start": 4489.67, "end": 4490.11, "word": " seconds", "probability": 0.73291015625 }, { "start": 4490.11, "end": 4490.43, "word": ".", "probability": 0.9384765625 } ] }, { "id": 1292, "seek": 439874, "start": 4491.43, "end": 4493.21, "text": " So I'm just going to go ahead and run this.", "tokens": [ 50664, 407, 286, 478, 445, 516, 281, 352, 2286, 293, 1190, 341, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.16710069541026046, "compression_ratio": 1.5, "no_speech_prob": 0.00036263465881347656, "words": [ { "start": 4491.43, "end": 4491.75, "word": " So", "probability": 0.83935546875 }, { "start": 4491.75, "end": 4491.83, "word": " I'm", "probability": 0.86767578125 }, { "start": 4491.83, "end": 4491.91, "word": " just", "probability": 0.880859375 }, { "start": 4491.91, "end": 4492.05, "word": " going", "probability": 0.39892578125 }, { "start": 4492.05, "end": 4492.09, "word": " to", "probability": 0.904296875 }, { "start": 4492.09, "end": 4492.19, "word": " go", "probability": 0.90087890625 }, { "start": 4492.19, "end": 4492.33, "word": " ahead", "probability": 0.8525390625 }, { "start": 4492.33, "end": 4492.43, "word": " and", "probability": 0.8955078125 }, { "start": 4492.43, "end": 4492.59, "word": " run", "probability": 0.90185546875 }, { "start": 4492.59, "end": 4492.89, "word": " this", "probability": 0.88427734375 }, { "start": 4492.89, "end": 4493.21, "word": ".", "probability": 0.93701171875 } ] }, { "id": 1293, "seek": 439874, "start": 4495.21, "end": 4496.79, "text": " And then for the logistic", "tokens": [ 50864, 400, 550, 337, 264, 3565, 3142, 50964 ], "temperature": 0.0, "avg_logprob": -0.16710069541026046, "compression_ratio": 1.5, "no_speech_prob": 0.00036263465881347656, "words": [ { "start": 4495.21, "end": 4495.49, "word": " And", "probability": 0.876953125 }, { "start": 4495.49, "end": 4495.61, "word": " then", "probability": 0.7236328125 }, { "start": 4495.61, "end": 4495.85, "word": " for", "probability": 0.8447265625 }, { "start": 4495.85, "end": 4496.21, "word": " the", "probability": 0.818359375 }, { "start": 4496.21, "end": 4496.79, "word": " logistic", "probability": 0.9287109375 } ] }, { "id": 1294, "seek": 439874, "start": 4496.79, "end": 4498.89, "text": " regression count, we're going to do the same thing we did", "tokens": [ 50964, 24590, 1207, 11, 321, 434, 516, 281, 360, 264, 912, 551, 321, 630, 51064 ], "temperature": 0.0, "avg_logprob": -0.16710069541026046, "compression_ratio": 1.5, "no_speech_prob": 0.00036263465881347656, "words": [ { "start": 4496.79, "end": 4497.17, "word": " regression", "probability": 0.86962890625 }, { "start": 4497.17, "end": 4497.71, "word": " count", "probability": 0.81005859375 }, { "start": 4497.71, "end": 4497.81, "word": ",", "probability": 0.91162109375 }, { "start": 4497.81, "end": 4497.95, "word": " we're", "probability": 0.92626953125 }, { "start": 4497.95, "end": 4498.03, "word": " going", "probability": 0.84130859375 }, { "start": 4498.03, "end": 4498.09, "word": " to", "probability": 0.9091796875 }, { "start": 4498.09, "end": 4498.17, "word": " do", "probability": 0.90478515625 }, { "start": 4498.17, "end": 4498.31, "word": " the", "probability": 0.8115234375 }, { "start": 4498.31, "end": 4498.45, "word": " same", "probability": 0.82470703125 }, { "start": 4498.45, "end": 4498.61, "word": " thing", "probability": 0.80712890625 }, { "start": 4498.61, "end": 4498.75, "word": " we", "probability": 0.8935546875 }, { "start": 4498.75, "end": 4498.89, "word": " did", "probability": 0.89697265625 } ] }, { "id": 1295, "seek": 439874, "start": 4498.89, "end": 4500.83, "text": " with the multinomial Naive Bayesian count", "tokens": [ 51064, 365, 264, 45872, 47429, 6056, 488, 7840, 42434, 1207, 51164 ], "temperature": 0.0, "avg_logprob": -0.16710069541026046, "compression_ratio": 1.5, "no_speech_prob": 0.00036263465881347656, "words": [ { "start": 4498.89, "end": 4499.03, "word": " with", "probability": 0.8076171875 }, { "start": 4499.03, "end": 4499.13, "word": " the", "probability": 0.8046875 }, { "start": 4499.13, "end": 4499.79, "word": " multinomial", "probability": 0.928466796875 }, { "start": 4499.79, "end": 4500.21, "word": " Naive", "probability": 0.43194580078125 }, { "start": 4500.21, "end": 4500.53, "word": " Bayesian", "probability": 0.92041015625 }, { "start": 4500.53, "end": 4500.83, "word": " count", "probability": 0.76806640625 } ] }, { "id": 1296, "seek": 439874, "start": 4500.83, "end": 4502.49, "text": " and just copy and change words", "tokens": [ 51164, 293, 445, 5055, 293, 1319, 2283, 51264 ], "temperature": 0.0, "avg_logprob": -0.16710069541026046, "compression_ratio": 1.5, "no_speech_prob": 0.00036263465881347656, "words": [ { "start": 4500.83, "end": 4500.95, "word": " and", "probability": 0.3974609375 }, { "start": 4500.95, "end": 4501.09, "word": " just", "probability": 0.88671875 }, { "start": 4501.09, "end": 4501.43, "word": " copy", "probability": 0.80078125 }, { "start": 4501.43, "end": 4501.63, "word": " and", "probability": 0.87451171875 }, { "start": 4501.63, "end": 4502.07, "word": " change", "probability": 0.828125 }, { "start": 4502.07, "end": 4502.49, "word": " words", "probability": 0.72412109375 } ] }, { "id": 1297, "seek": 439874, "start": 4503.83, "end": 4504.85, "text": " because I'm lazy.", "tokens": [ 51264, 570, 286, 478, 14847, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.16710069541026046, "compression_ratio": 1.5, "no_speech_prob": 0.00036263465881347656, "words": [ { "start": 4503.83, "end": 4504.15, "word": " because", "probability": 0.46337890625 }, { "start": 4504.15, "end": 4504.27, "word": " I'm", "probability": 0.998779296875 }, { "start": 4504.27, "end": 4504.53, "word": " lazy", "probability": 0.71923828125 }, { "start": 4504.53, "end": 4504.85, "word": ".", "probability": 0.9951171875 } ] }, { "id": 1298, "seek": 439874, "start": 4509.39, "end": 4510.87, "text": " But yeah, I'm really excited to see that", "tokens": [ 51564, 583, 1338, 11, 286, 478, 534, 2919, 281, 536, 300, 51664 ], "temperature": 0.0, "avg_logprob": -0.16710069541026046, "compression_ratio": 1.5, "no_speech_prob": 0.00036263465881347656, "words": [ { "start": 4509.39, "end": 4509.71, "word": " But", "probability": 0.39306640625 }, { "start": 4509.71, "end": 4509.83, "word": " yeah", "probability": 0.8056640625 }, { "start": 4509.83, "end": 4509.85, "word": ",", "probability": 0.95263671875 }, { "start": 4509.85, "end": 4509.97, "word": " I'm", "probability": 0.99951171875 }, { "start": 4509.97, "end": 4510.15, "word": " really", "probability": 0.78076171875 }, { "start": 4510.15, "end": 4510.41, "word": " excited", "probability": 0.8974609375 }, { "start": 4510.41, "end": 4510.57, "word": " to", "probability": 0.90966796875 }, { "start": 4510.57, "end": 4510.69, "word": " see", "probability": 0.8134765625 }, { "start": 4510.69, "end": 4510.87, "word": " that", "probability": 0.89599609375 } ] }, { "id": 1299, "seek": 439874, "start": 4510.87, "end": 4512.75, "text": " Twitch chat after I hop off to this", "tokens": [ 51664, 22222, 5081, 934, 286, 3818, 766, 281, 341, 51764 ], "temperature": 0.0, "avg_logprob": -0.16710069541026046, "compression_ratio": 1.5, "no_speech_prob": 0.00036263465881347656, "words": [ { "start": 4510.87, "end": 4511.13, "word": " Twitch", "probability": 0.8974609375 }, { "start": 4511.13, "end": 4511.51, "word": " chat", "probability": 0.82373046875 }, { "start": 4511.51, "end": 4512.03, "word": " after", "probability": 0.426025390625 }, { "start": 4512.03, "end": 4512.21, "word": " I", "probability": 0.99365234375 }, { "start": 4512.21, "end": 4512.37, "word": " hop", "probability": 0.88525390625 }, { "start": 4512.37, "end": 4512.51, "word": " off", "probability": 0.80615234375 }, { "start": 4512.51, "end": 4512.61, "word": " to", "probability": 0.362060546875 }, { "start": 4512.61, "end": 4512.75, "word": " this", "probability": 0.890625 } ] }, { "id": 1300, "seek": 442588, "start": 4512.75, "end": 4514.41, "text": " workshop and see just how", "tokens": [ 50364, 13541, 293, 536, 445, 577, 50464 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.5024630541871922, "no_speech_prob": 0.162353515625, "words": [ { "start": 4512.75, "end": 4513.17, "word": " workshop", "probability": 0.382568359375 }, { "start": 4513.17, "end": 4513.39, "word": " and", "probability": 0.83837890625 }, { "start": 4513.39, "end": 4513.55, "word": " see", "probability": 0.78955078125 }, { "start": 4513.55, "end": 4513.85, "word": " just", "probability": 0.70166015625 }, { "start": 4513.85, "end": 4514.41, "word": " how", "probability": 0.91357421875 } ] }, { "id": 1301, "seek": 442588, "start": 4516.99, "end": 4518.31, "text": " passionate people are", "tokens": [ 50564, 11410, 561, 366, 50664 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.5024630541871922, "no_speech_prob": 0.162353515625, "words": [ { "start": 4516.99, "end": 4517.43, "word": " passionate", "probability": 0.7529296875 }, { "start": 4517.43, "end": 4517.81, "word": " people", "probability": 0.92333984375 }, { "start": 4517.81, "end": 4518.31, "word": " are", "probability": 0.8955078125 } ] }, { "id": 1302, "seek": 442588, "start": 4518.31, "end": 4520.75, "text": " about the false positive,", "tokens": [ 50664, 466, 264, 7908, 3353, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.5024630541871922, "no_speech_prob": 0.162353515625, "words": [ { "start": 4518.31, "end": 4519.01, "word": " about", "probability": 0.7861328125 }, { "start": 4519.01, "end": 4519.35, "word": " the", "probability": 0.79296875 }, { "start": 4519.35, "end": 4520.23, "word": " false", "probability": 0.8037109375 }, { "start": 4520.23, "end": 4520.61, "word": " positive", "probability": 0.8056640625 }, { "start": 4520.61, "end": 4520.75, "word": ",", "probability": 0.95556640625 } ] }, { "id": 1303, "seek": 442588, "start": 4520.75, "end": 4522.71, "text": " true positive, and XYZ.", "tokens": [ 50764, 2074, 3353, 11, 293, 48826, 57, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.5024630541871922, "no_speech_prob": 0.162353515625, "words": [ { "start": 4520.75, "end": 4520.85, "word": " true", "probability": 0.875 }, { "start": 4520.85, "end": 4521.17, "word": " positive", "probability": 0.857421875 }, { "start": 4521.17, "end": 4521.47, "word": ",", "probability": 0.80419921875 }, { "start": 4521.47, "end": 4521.53, "word": " and", "probability": 0.8779296875 }, { "start": 4521.53, "end": 4522.27, "word": " XYZ", "probability": 0.6719970703125 }, { "start": 4522.27, "end": 4522.71, "word": ".", "probability": 0.974609375 } ] }, { "id": 1304, "seek": 442588, "start": 4523.29, "end": 4524.73, "text": " Oh, we're going to erase it before", "tokens": [ 50864, 876, 11, 321, 434, 516, 281, 23525, 309, 949, 50964 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.5024630541871922, "no_speech_prob": 0.162353515625, "words": [ { "start": 4523.29, "end": 4523.73, "word": " Oh", "probability": 0.355712890625 }, { "start": 4523.73, "end": 4523.77, "word": ",", "probability": 0.92626953125 }, { "start": 4523.77, "end": 4523.91, "word": " we're", "probability": 0.926025390625 }, { "start": 4523.91, "end": 4524.03, "word": " going", "probability": 0.81494140625 }, { "start": 4524.03, "end": 4524.13, "word": " to", "probability": 0.900390625 }, { "start": 4524.13, "end": 4524.41, "word": " erase", "probability": 0.822265625 }, { "start": 4524.41, "end": 4524.53, "word": " it", "probability": 0.8720703125 }, { "start": 4524.53, "end": 4524.73, "word": " before", "probability": 0.80126953125 } ] }, { "id": 1305, "seek": 442588, "start": 4524.73, "end": 4525.75, "text": " you get off.", "tokens": [ 50964, 291, 483, 766, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.5024630541871922, "no_speech_prob": 0.162353515625, "words": [ { "start": 4524.73, "end": 4524.91, "word": " you", "probability": 0.89404296875 }, { "start": 4524.91, "end": 4525.03, "word": " get", "probability": 0.89404296875 }, { "start": 4525.03, "end": 4525.31, "word": " off", "probability": 0.80078125 }, { "start": 4525.31, "end": 4525.75, "word": ".", "probability": 0.970703125 } ] }, { "id": 1306, "seek": 442588, "start": 4526.91, "end": 4528.25, "text": " Ruin my day.", "tokens": [ 51064, 497, 9445, 452, 786, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.5024630541871922, "no_speech_prob": 0.162353515625, "words": [ { "start": 4526.91, "end": 4527.35, "word": " Ruin", "probability": 0.5980224609375 }, { "start": 4527.35, "end": 4527.53, "word": " my", "probability": 0.75048828125 }, { "start": 4527.53, "end": 4527.81, "word": " day", "probability": 0.9013671875 }, { "start": 4527.81, "end": 4528.25, "word": ".", "probability": 0.92919921875 } ] }, { "id": 1307, "seek": 442588, "start": 4533.27, "end": 4535.63, "text": " Yeah, it's taking a little bit longer than I'm used to.", "tokens": [ 51264, 865, 11, 309, 311, 1940, 257, 707, 857, 2854, 813, 286, 478, 1143, 281, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.5024630541871922, "no_speech_prob": 0.162353515625, "words": [ { "start": 4533.27, "end": 4533.71, "word": " Yeah", "probability": 0.5048828125 }, { "start": 4533.71, "end": 4533.73, "word": ",", "probability": 0.93505859375 }, { "start": 4533.73, "end": 4533.81, "word": " it's", "probability": 0.929443359375 }, { "start": 4533.81, "end": 4534.03, "word": " taking", "probability": 0.6162109375 }, { "start": 4534.15, "end": 4534.23, "word": " a little", "probability": 0.80712890625 }, { "start": 4534.23, "end": 4534.35, "word": " bit", "probability": 0.88037109375 }, { "start": 4534.35, "end": 4534.55, "word": " longer", "probability": 0.80615234375 }, { "start": 4534.55, "end": 4534.69, "word": " than", "probability": 0.88916015625 }, { "start": 4534.69, "end": 4534.81, "word": " I'm", "probability": 0.96435546875 }, { "start": 4534.81, "end": 4534.95, "word": " used", "probability": 0.80322265625 }, { "start": 4534.95, "end": 4535.19, "word": " to", "probability": 0.90185546875 }, { "start": 4535.19, "end": 4535.63, "word": ".", "probability": 0.81396484375 } ] }, { "id": 1308, "seek": 442588, "start": 4537.31, "end": 4539.59, "text": " But that's okay. While this is going,", "tokens": [ 51464, 583, 300, 311, 1392, 13, 3987, 341, 307, 516, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.5024630541871922, "no_speech_prob": 0.162353515625, "words": [ { "start": 4537.31, "end": 4537.75, "word": " But", "probability": 0.74462890625 }, { "start": 4537.75, "end": 4538.19, "word": " that's", "probability": 0.933837890625 }, { "start": 4538.19, "end": 4538.51, "word": " okay", "probability": 0.00885009765625 }, { "start": 4538.51, "end": 4538.63, "word": ".", "probability": 0.9287109375 }, { "start": 4538.63, "end": 4538.79, "word": " While", "probability": 0.84033203125 }, { "start": 4538.79, "end": 4538.99, "word": " this", "probability": 0.8798828125 }, { "start": 4538.99, "end": 4539.13, "word": " is", "probability": 0.9033203125 }, { "start": 4539.13, "end": 4539.43, "word": " going", "probability": 0.86279296875 }, { "start": 4539.43, "end": 4539.59, "word": ",", "probability": 0.947265625 } ] }, { "id": 1309, "seek": 442588, "start": 4539.59, "end": 4541.19, "text": " I'm just going to go ahead", "tokens": [ 51564, 286, 478, 445, 516, 281, 352, 2286, 51664 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.5024630541871922, "no_speech_prob": 0.162353515625, "words": [ { "start": 4539.59, "end": 4539.73, "word": " I'm", "probability": 0.9990234375 }, { "start": 4539.73, "end": 4539.89, "word": " just", "probability": 0.88037109375 }, { "start": 4539.89, "end": 4540.03, "word": " going", "probability": 0.8408203125 }, { "start": 4540.03, "end": 4540.65, "word": " to", "probability": 0.904296875 }, { "start": 4540.65, "end": 4540.89, "word": " go", "probability": 0.90380859375 }, { "start": 4540.89, "end": 4541.19, "word": " ahead", "probability": 0.8447265625 } ] }, { "id": 1310, "seek": 442588, "start": 4541.19, "end": 4542.41, "text": " and hop into the next bit", "tokens": [ 51664, 293, 3818, 666, 264, 958, 857, 51764 ], "temperature": 0.0, "avg_logprob": -0.1704687447845936, "compression_ratio": 1.5024630541871922, "no_speech_prob": 0.162353515625, "words": [ { "start": 4541.19, "end": 4541.31, "word": " and", "probability": 0.07611083984375 }, { "start": 4541.31, "end": 4541.51, "word": " hop", "probability": 0.8984375 }, { "start": 4541.51, "end": 4541.71, "word": " into", "probability": 0.73291015625 }, { "start": 4541.71, "end": 4541.87, "word": " the", "probability": 0.8134765625 }, { "start": 4541.87, "end": 4542.09, "word": " next", "probability": 0.8623046875 }, { "start": 4542.09, "end": 4542.41, "word": " bit", "probability": 0.89599609375 } ] }, { "id": 1311, "seek": 445338, "start": 4545.31, "end": 4545.83, "text": " and", "tokens": [ 50364, 293, 50464 ], "temperature": 0.0, "avg_logprob": -0.19654605524581775, "compression_ratio": 1.7515527950310559, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4545.31, "end": 4545.83, "word": " and", "probability": 0.269775390625 } ] }, { "id": 1312, "seek": 445338, "start": 4545.83, "end": 4547.89, "text": " paste this. All we need to do", "tokens": [ 50464, 9163, 341, 13, 1057, 321, 643, 281, 360, 50564 ], "temperature": 0.0, "avg_logprob": -0.19654605524581775, "compression_ratio": 1.7515527950310559, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4545.83, "end": 4546.51, "word": " paste", "probability": 0.70458984375 }, { "start": 4546.51, "end": 4546.81, "word": " this", "probability": 0.88134765625 }, { "start": 4546.81, "end": 4546.97, "word": ".", "probability": 0.60546875 }, { "start": 4546.97, "end": 4547.19, "word": " All", "probability": 0.89501953125 }, { "start": 4547.19, "end": 4547.33, "word": " we", "probability": 0.90234375 }, { "start": 4547.33, "end": 4547.47, "word": " need", "probability": 0.8125 }, { "start": 4547.47, "end": 4547.57, "word": " to", "probability": 0.90576171875 }, { "start": 4547.57, "end": 4547.89, "word": " do", "probability": 0.9111328125 } ] }, { "id": 1313, "seek": 445338, "start": 4547.89, "end": 4549.19, "text": " is trade this", "tokens": [ 50564, 307, 4923, 341, 50664 ], "temperature": 0.0, "avg_logprob": -0.19654605524581775, "compression_ratio": 1.7515527950310559, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4547.89, "end": 4548.43, "word": " is", "probability": 0.89599609375 }, { "start": 4548.43, "end": 4548.93, "word": " trade", "probability": 0.7841796875 }, { "start": 4548.93, "end": 4549.19, "word": " this", "probability": 0.87548828125 } ] }, { "id": 1314, "seek": 445338, "start": 4549.19, "end": 4551.93, "text": " TF-IDF with COUNT.", "tokens": [ 50664, 40964, 12, 2777, 37, 365, 3002, 41872, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.19654605524581775, "compression_ratio": 1.7515527950310559, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4549.19, "end": 4549.83, "word": " TF", "probability": 0.5009765625 }, { "start": 4549.83, "end": 4550.29, "word": "-IDF", "probability": 0.7799479166666666 }, { "start": 4550.29, "end": 4550.67, "word": " with", "probability": 0.810546875 }, { "start": 4550.67, "end": 4551.41, "word": " COUNT", "probability": 0.4248046875 }, { "start": 4551.41, "end": 4551.93, "word": ".", "probability": 0.79150390625 } ] }, { "id": 1315, "seek": 445338, "start": 4553.03, "end": 4554.11, "text": " So I'm going to go ahead", "tokens": [ 50764, 407, 286, 478, 516, 281, 352, 2286, 50864 ], "temperature": 0.0, "avg_logprob": -0.19654605524581775, "compression_ratio": 1.7515527950310559, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4553.03, "end": 4553.55, "word": " So", "probability": 0.763671875 }, { "start": 4553.55, "end": 4553.79, "word": " I'm", "probability": 0.8583984375 }, { "start": 4553.79, "end": 4553.81, "word": " going", "probability": 0.277587890625 }, { "start": 4553.81, "end": 4553.81, "word": " to", "probability": 0.90087890625 }, { "start": 4553.81, "end": 4553.93, "word": " go", "probability": 0.87255859375 }, { "start": 4553.93, "end": 4554.11, "word": " ahead", "probability": 0.8251953125 } ] }, { "id": 1316, "seek": 445338, "start": 4554.11, "end": 4555.63, "text": " and copy that. We're going to use the same", "tokens": [ 50864, 293, 5055, 300, 13, 492, 434, 516, 281, 764, 264, 912, 50964 ], "temperature": 0.0, "avg_logprob": -0.19654605524581775, "compression_ratio": 1.7515527950310559, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4554.11, "end": 4554.21, "word": " and", "probability": 0.69775390625 }, { "start": 4554.21, "end": 4554.41, "word": " copy", "probability": 0.78564453125 }, { "start": 4554.41, "end": 4554.67, "word": " that", "probability": 0.88232421875 }, { "start": 4554.67, "end": 4554.75, "word": ".", "probability": 0.81494140625 }, { "start": 4554.75, "end": 4554.87, "word": " We're", "probability": 0.922119140625 }, { "start": 4554.87, "end": 4554.93, "word": " going", "probability": 0.7841796875 }, { "start": 4554.93, "end": 4554.95, "word": " to", "probability": 0.9072265625 }, { "start": 4554.95, "end": 4555.11, "word": " use", "probability": 0.818359375 }, { "start": 4555.11, "end": 4555.25, "word": " the", "probability": 0.81494140625 }, { "start": 4555.25, "end": 4555.63, "word": " same", "probability": 0.7978515625 } ] }, { "id": 1317, "seek": 445338, "start": 4555.63, "end": 4557.91, "text": " constructor and the same solver.", "tokens": [ 50964, 47479, 293, 264, 912, 1404, 331, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.19654605524581775, "compression_ratio": 1.7515527950310559, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4555.63, "end": 4556.23, "word": " constructor", "probability": 0.68310546875 }, { "start": 4556.23, "end": 4556.53, "word": " and", "probability": 0.82080078125 }, { "start": 4556.53, "end": 4556.67, "word": " the", "probability": 0.80126953125 }, { "start": 4556.67, "end": 4556.85, "word": " same", "probability": 0.80517578125 }, { "start": 4556.85, "end": 4557.39, "word": " solver", "probability": 0.8984375 }, { "start": 4557.39, "end": 4557.91, "word": ".", "probability": 0.94677734375 } ] }, { "id": 1318, "seek": 445338, "start": 4557.93, "end": 4559.73, "text": " We're going to use COUNTEX.", "tokens": [ 51064, 492, 434, 516, 281, 764, 3002, 3979, 13639, 55, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.19654605524581775, "compression_ratio": 1.7515527950310559, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4557.93, "end": 4558.43, "word": " We're", "probability": 0.927001953125 }, { "start": 4558.43, "end": 4558.53, "word": " going", "probability": 0.8017578125 }, { "start": 4558.53, "end": 4558.55, "word": " to", "probability": 0.904296875 }, { "start": 4558.55, "end": 4558.77, "word": " use", "probability": 0.80810546875 }, { "start": 4558.77, "end": 4559.57, "word": " COUNTEX", "probability": 0.69903564453125 }, { "start": 4559.57, "end": 4559.73, "word": ".", "probability": 0.488525390625 } ] }, { "id": 1319, "seek": 445338, "start": 4559.73, "end": 4562.05, "text": " We're going to use COUNTFIT.", "tokens": [ 51164, 492, 434, 516, 281, 764, 3002, 3979, 20527, 3927, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.19654605524581775, "compression_ratio": 1.7515527950310559, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4559.73, "end": 4559.85, "word": " We're", "probability": 0.930908203125 }, { "start": 4559.85, "end": 4559.93, "word": " going", "probability": 0.83935546875 }, { "start": 4559.93, "end": 4559.97, "word": " to", "probability": 0.904296875 }, { "start": 4559.97, "end": 4560.17, "word": " use", "probability": 0.7890625 }, { "start": 4560.17, "end": 4561.53, "word": " COUNTFIT", "probability": 0.8248291015625 }, { "start": 4561.53, "end": 4562.05, "word": ".", "probability": 0.81005859375 } ] }, { "id": 1320, "seek": 445338, "start": 4563.63, "end": 4564.15, "text": " COUNTCOUNT", "tokens": [ 51264, 3002, 3979, 18238, 46, 41872, 51364 ], "temperature": 0.0, "avg_logprob": -0.19654605524581775, "compression_ratio": 1.7515527950310559, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4563.63, "end": 4564.15, "word": " COUNTCOUNT", "probability": 0.67802734375 } ] }, { "id": 1321, "seek": 445338, "start": 4566.09, "end": 4566.61, "text": " COUNTCOUNT", "tokens": [ 51364, 3002, 3979, 18238, 46, 41872, 51464 ], "temperature": 0.0, "avg_logprob": -0.19654605524581775, "compression_ratio": 1.7515527950310559, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4566.09, "end": 4566.61, "word": " COUNTCOUNT", "probability": 0.7752197265625 } ] }, { "id": 1322, "seek": 445338, "start": 4567.33, "end": 4567.85, "text": " COUNTCOUNT", "tokens": [ 51464, 3002, 3979, 18238, 46, 41872, 51564 ], "temperature": 0.0, "avg_logprob": -0.19654605524581775, "compression_ratio": 1.7515527950310559, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4567.33, "end": 4567.85, "word": " COUNTCOUNT", "probability": 0.7247314453125 } ] }, { "id": 1323, "seek": 445338, "start": 4572.88, "end": 4574.86, "text": " Test labels is the same.", "tokens": [ 51664, 9279, 16949, 307, 264, 912, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.19654605524581775, "compression_ratio": 1.7515527950310559, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4572.88, "end": 4573.4, "word": " Test", "probability": 0.1463623046875 }, { "start": 4573.4, "end": 4573.68, "word": " labels", "probability": 0.44140625 }, { "start": 4573.68, "end": 4573.86, "word": " is", "probability": 0.54833984375 }, { "start": 4573.86, "end": 4574.02, "word": " the", "probability": 0.81103515625 }, { "start": 4574.02, "end": 4574.34, "word": " same", "probability": 0.8134765625 }, { "start": 4574.34, "end": 4574.86, "word": ".", "probability": 0.97265625 } ] }, { "id": 1324, "seek": 448186, "start": 4578.41, "end": 4579.05, "text": " These are", "tokens": [ 50364, 1981, 366, 50464 ], "temperature": 0.0, "avg_logprob": -0.17968750170742473, "compression_ratio": 1.446236559139785, "no_speech_prob": 0.0004878044128417969, "words": [ { "start": 4578.41, "end": 4578.85, "word": " These", "probability": 0.0740966796875 }, { "start": 4578.85, "end": 4579.05, "word": " are", "probability": 0.87451171875 } ] }, { "id": 1325, "seek": 448186, "start": 4579.05, "end": 4580.07, "text": " predictions.", "tokens": [ 50464, 21264, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.17968750170742473, "compression_ratio": 1.446236559139785, "no_speech_prob": 0.0004878044128417969, "words": [ { "start": 4579.05, "end": 4579.63, "word": " predictions", "probability": 0.3173828125 }, { "start": 4579.63, "end": 4580.07, "word": ".", "probability": 0.269287109375 } ] }, { "id": 1326, "seek": 448186, "start": 4581.01, "end": 4582.43, "text": " And just one", "tokens": [ 50564, 400, 445, 472, 50664 ], "temperature": 0.0, "avg_logprob": -0.17968750170742473, "compression_ratio": 1.446236559139785, "no_speech_prob": 0.0004878044128417969, "words": [ { "start": 4581.01, "end": 4581.25, "word": " And", "probability": 0.7060546875 }, { "start": 4581.25, "end": 4581.63, "word": " just", "probability": 0.8642578125 }, { "start": 4581.63, "end": 4582.43, "word": " one", "probability": 0.81982421875 } ] }, { "id": 1327, "seek": 448186, "start": 4583.19, "end": 4584.89, "text": " quick look over.", "tokens": [ 50664, 1702, 574, 670, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.17968750170742473, "compression_ratio": 1.446236559139785, "no_speech_prob": 0.0004878044128417969, "words": [ { "start": 4583.19, "end": 4583.63, "word": " quick", "probability": 0.90625 }, { "start": 4583.63, "end": 4583.99, "word": " look", "probability": 0.8984375 }, { "start": 4583.99, "end": 4584.45, "word": " over", "probability": 0.87109375 }, { "start": 4584.45, "end": 4584.89, "word": ".", "probability": 0.828125 } ] }, { "id": 1328, "seek": 448186, "start": 4587.01, "end": 4588.83, "text": " Yep, I have everything in.", "tokens": [ 50864, 7010, 11, 286, 362, 1203, 294, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.17968750170742473, "compression_ratio": 1.446236559139785, "no_speech_prob": 0.0004878044128417969, "words": [ { "start": 4587.01, "end": 4587.45, "word": " Yep", "probability": 0.6083984375 }, { "start": 4587.45, "end": 4587.63, "word": ",", "probability": 0.7607421875 }, { "start": 4587.63, "end": 4587.77, "word": " I", "probability": 0.994140625 }, { "start": 4587.77, "end": 4587.93, "word": " have", "probability": 0.876953125 }, { "start": 4587.93, "end": 4588.17, "word": " everything", "probability": 0.88671875 }, { "start": 4588.17, "end": 4588.39, "word": " in", "probability": 0.896484375 }, { "start": 4588.39, "end": 4588.83, "word": ".", "probability": 0.9404296875 } ] }, { "id": 1329, "seek": 448186, "start": 4589.43, "end": 4591.35, "text": " That's exactly how it's supposed to be.", "tokens": [ 50964, 663, 311, 2293, 577, 309, 311, 3442, 281, 312, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.17968750170742473, "compression_ratio": 1.446236559139785, "no_speech_prob": 0.0004878044128417969, "words": [ { "start": 4589.43, "end": 4589.81, "word": " That's", "probability": 0.7252197265625 }, { "start": 4589.81, "end": 4590.11, "word": " exactly", "probability": 0.74951171875 }, { "start": 4590.11, "end": 4590.27, "word": " how", "probability": 0.8994140625 }, { "start": 4590.27, "end": 4590.39, "word": " it's", "probability": 0.9453125 }, { "start": 4590.39, "end": 4590.53, "word": " supposed", "probability": 0.9033203125 }, { "start": 4590.53, "end": 4590.67, "word": " to", "probability": 0.9091796875 }, { "start": 4590.67, "end": 4590.91, "word": " be", "probability": 0.90673828125 }, { "start": 4590.91, "end": 4591.35, "word": ".", "probability": 0.97509765625 } ] }, { "id": 1330, "seek": 448186, "start": 4591.91, "end": 4593.23, "text": " Scroll up.", "tokens": [ 51064, 35395, 493, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.17968750170742473, "compression_ratio": 1.446236559139785, "no_speech_prob": 0.0004878044128417969, "words": [ { "start": 4591.91, "end": 4592.35, "word": " Scroll", "probability": 0.1483154296875 }, { "start": 4592.35, "end": 4592.79, "word": " up", "probability": 0.908203125 }, { "start": 4592.79, "end": 4593.23, "word": ".", "probability": 0.81982421875 } ] }, { "id": 1331, "seek": 448186, "start": 4593.87, "end": 4595.19, "text": " Oh, this is still going.", "tokens": [ 51164, 876, 11, 341, 307, 920, 516, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.17968750170742473, "compression_ratio": 1.446236559139785, "no_speech_prob": 0.0004878044128417969, "words": [ { "start": 4593.87, "end": 4594.09, "word": " Oh", "probability": 0.11138916015625 }, { "start": 4594.09, "end": 4594.09, "word": ",", "probability": 0.8203125 }, { "start": 4594.09, "end": 4594.19, "word": " this", "probability": 0.81494140625 }, { "start": 4594.19, "end": 4594.29, "word": " is", "probability": 0.90673828125 }, { "start": 4594.29, "end": 4594.47, "word": " still", "probability": 0.90380859375 }, { "start": 4594.47, "end": 4594.77, "word": " going", "probability": 0.796875 }, { "start": 4594.77, "end": 4595.19, "word": ".", "probability": 0.66748046875 } ] }, { "id": 1332, "seek": 448186, "start": 4595.19, "end": 4595.83, "text": " Look at that.", "tokens": [ 51264, 2053, 412, 300, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.17968750170742473, "compression_ratio": 1.446236559139785, "no_speech_prob": 0.0004878044128417969, "words": [ { "start": 4595.19, "end": 4595.19, "word": " Look", "probability": 0.4345703125 }, { "start": 4595.19, "end": 4595.19, "word": " at", "probability": 0.908203125 }, { "start": 4595.19, "end": 4595.39, "word": " that", "probability": 0.88720703125 }, { "start": 4595.39, "end": 4595.83, "word": ".", "probability": 0.9873046875 } ] }, { "id": 1333, "seek": 448186, "start": 4598.99, "end": 4599.87, "text": " Weird.", "tokens": [ 51464, 32033, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.17968750170742473, "compression_ratio": 1.446236559139785, "no_speech_prob": 0.0004878044128417969, "words": [ { "start": 4598.99, "end": 4599.43, "word": " Weird", "probability": 0.89599609375 }, { "start": 4599.43, "end": 4599.87, "word": ".", "probability": 0.93798828125 } ] }, { "id": 1334, "seek": 448186, "start": 4601.25, "end": 4602.89, "text": " I'm going to let that sit for a bit then.", "tokens": [ 51564, 286, 478, 516, 281, 718, 300, 1394, 337, 257, 857, 550, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.17968750170742473, "compression_ratio": 1.446236559139785, "no_speech_prob": 0.0004878044128417969, "words": [ { "start": 4601.25, "end": 4601.47, "word": " I'm", "probability": 0.703369140625 }, { "start": 4601.47, "end": 4601.51, "word": " going", "probability": 0.251708984375 }, { "start": 4601.51, "end": 4601.51, "word": " to", "probability": 0.896484375 }, { "start": 4601.51, "end": 4601.59, "word": " let", "probability": 0.88916015625 }, { "start": 4601.59, "end": 4601.77, "word": " that", "probability": 0.87353515625 }, { "start": 4601.77, "end": 4601.87, "word": " sit", "probability": 0.90087890625 }, { "start": 4601.87, "end": 4602.01, "word": " for", "probability": 0.896484375 }, { "start": 4602.13, "end": 4602.19, "word": " a bit", "probability": 0.90869140625 }, { "start": 4602.19, "end": 4602.45, "word": " then", "probability": 0.5712890625 }, { "start": 4602.45, "end": 4602.89, "word": ".", "probability": 0.99658203125 } ] }, { "id": 1335, "seek": 448186, "start": 4603.27, "end": 4605.09, "text": " So this one, I'm going to let you guys write down.", "tokens": [ 51664, 407, 341, 472, 11, 286, 478, 516, 281, 718, 291, 1074, 2464, 760, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.17968750170742473, "compression_ratio": 1.446236559139785, "no_speech_prob": 0.0004878044128417969, "words": [ { "start": 4603.27, "end": 4603.49, "word": " So", "probability": 0.86865234375 }, { "start": 4603.49, "end": 4603.65, "word": " this", "probability": 0.73486328125 }, { "start": 4603.65, "end": 4603.85, "word": " one", "probability": 0.814453125 }, { "start": 4603.85, "end": 4603.93, "word": ",", "probability": 0.5693359375 }, { "start": 4603.93, "end": 4604.05, "word": " I'm", "probability": 0.990478515625 }, { "start": 4604.05, "end": 4604.09, "word": " going", "probability": 0.81689453125 }, { "start": 4604.09, "end": 4604.09, "word": " to", "probability": 0.89990234375 }, { "start": 4604.09, "end": 4604.21, "word": " let", "probability": 0.9013671875 }, { "start": 4604.21, "end": 4604.31, "word": " you", "probability": 0.89599609375 }, { "start": 4604.31, "end": 4604.47, "word": " guys", "probability": 0.87353515625 }, { "start": 4604.47, "end": 4604.61, "word": " write", "probability": 0.79443359375 }, { "start": 4604.61, "end": 4604.93, "word": " down", "probability": 0.79736328125 }, { "start": 4604.93, "end": 4605.09, "word": ".", "probability": 0.74755859375 } ] }, { "id": 1336, "seek": 450996, "start": 4605.09, "end": 4607.59, "text": " This is task 6D.", "tokens": [ 50364, 639, 307, 5633, 1386, 35, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.1781528971291014, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 4605.09, "end": 4605.21, "word": " This", "probability": 0.57666015625 }, { "start": 4605.21, "end": 4605.37, "word": " is", "probability": 0.90478515625 }, { "start": 4605.37, "end": 4605.85, "word": " task", "probability": 0.73388671875 }, { "start": 4605.85, "end": 4607.15, "word": " 6D", "probability": 0.711669921875 }, { "start": 4607.15, "end": 4607.59, "word": ".", "probability": 0.6708984375 } ] }, { "id": 1337, "seek": 450996, "start": 4608.31, "end": 4609.03, "text": " So go ahead", "tokens": [ 50464, 407, 352, 2286, 50564 ], "temperature": 0.0, "avg_logprob": -0.1781528971291014, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 4608.31, "end": 4608.53, "word": " So", "probability": 0.77978515625 }, { "start": 4608.53, "end": 4608.79, "word": " go", "probability": 0.76806640625 }, { "start": 4608.79, "end": 4609.03, "word": " ahead", "probability": 0.8466796875 } ] }, { "id": 1338, "seek": 450996, "start": 4609.03, "end": 4611.03, "text": " and make sure that you have these written down", "tokens": [ 50564, 293, 652, 988, 300, 291, 362, 613, 3720, 760, 50664 ], "temperature": 0.0, "avg_logprob": -0.1781528971291014, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 4609.03, "end": 4609.15, "word": " and", "probability": 0.156494140625 }, { "start": 4609.15, "end": 4609.47, "word": " make", "probability": 0.8671875 }, { "start": 4609.47, "end": 4609.61, "word": " sure", "probability": 0.8076171875 }, { "start": 4609.61, "end": 4609.79, "word": " that", "probability": 0.76416015625 }, { "start": 4609.79, "end": 4609.89, "word": " you", "probability": 0.89453125 }, { "start": 4609.89, "end": 4610.13, "word": " have", "probability": 0.88671875 }, { "start": 4610.13, "end": 4610.35, "word": " these", "probability": 0.716796875 }, { "start": 4610.35, "end": 4610.57, "word": " written", "probability": 0.85400390625 }, { "start": 4610.57, "end": 4611.03, "word": " down", "probability": 0.81884765625 } ] }, { "id": 1339, "seek": 450996, "start": 4611.03, "end": 4613.13, "text": " while the other one is still going.", "tokens": [ 50664, 1339, 264, 661, 472, 307, 920, 516, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.1781528971291014, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 4611.03, "end": 4611.67, "word": " while", "probability": 0.76123046875 }, { "start": 4611.67, "end": 4611.85, "word": " the", "probability": 0.8076171875 }, { "start": 4611.85, "end": 4611.99, "word": " other", "probability": 0.78515625 }, { "start": 4611.99, "end": 4612.15, "word": " one", "probability": 0.81103515625 }, { "start": 4612.15, "end": 4612.27, "word": " is", "probability": 0.9052734375 }, { "start": 4612.27, "end": 4612.45, "word": " still", "probability": 0.9052734375 }, { "start": 4612.45, "end": 4612.85, "word": " going", "probability": 0.85595703125 }, { "start": 4612.85, "end": 4613.13, "word": ".", "probability": 0.6806640625 } ] }, { "id": 1340, "seek": 450996, "start": 4613.13, "end": 4615.09, "text": " I'm going to run this and then take a look at", "tokens": [ 50764, 286, 478, 516, 281, 1190, 341, 293, 550, 747, 257, 574, 412, 50864 ], "temperature": 0.0, "avg_logprob": -0.1781528971291014, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 4613.13, "end": 4613.29, "word": " I'm", "probability": 0.579345703125 }, { "start": 4613.29, "end": 4613.37, "word": " going", "probability": 0.382080078125 }, { "start": 4613.37, "end": 4613.45, "word": " to", "probability": 0.9072265625 }, { "start": 4613.45, "end": 4613.67, "word": " run", "probability": 0.89208984375 }, { "start": 4613.67, "end": 4613.97, "word": " this", "probability": 0.88330078125 }, { "start": 4613.97, "end": 4614.13, "word": " and", "probability": 0.787109375 }, { "start": 4614.13, "end": 4614.27, "word": " then", "probability": 0.6669921875 }, { "start": 4614.27, "end": 4614.47, "word": " take", "probability": 0.81787109375 }, { "start": 4614.59, "end": 4614.77, "word": " a look", "probability": 0.91162109375 }, { "start": 4614.77, "end": 4615.09, "word": " at", "probability": 0.890625 } ] }, { "id": 1341, "seek": 450996, "start": 4617.75, "end": 4618.15, "text": " a", "tokens": [ 50864, 257, 50964 ], "temperature": 0.0, "avg_logprob": -0.1781528971291014, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 4617.75, "end": 4618.15, "word": " a logistic", "probability": 0.91357421875 } ] }, { "id": 1342, "seek": 450996, "start": 4618.15, "end": 4619.53, "text": " logistic regression with the", "tokens": [ 50964, 3565, 3142, 24590, 365, 264, 51064 ], "temperature": 0.0, "avg_logprob": -0.1781528971291014, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 4618.15, "end": 4618.51, "word": " regression", "probability": 0.9140625 }, { "start": 4618.51, "end": 4618.69, "word": " with", "probability": 0.7724609375 }, { "start": 4618.69, "end": 4618.81, "word": " the", "probability": 0.7392578125 }, { "start": 4618.81, "end": 4619.05, "word": " TF", "probability": 0.666015625 }, { "start": 4619.05, "end": 4619.53, "word": "-IDF", "probability": 0.8616536458333334 } ] }, { "id": 1343, "seek": 450996, "start": 4619.53, "end": 4625.39, "text": " TF-IDF.", "tokens": [ 51064, 40964, 12, 2777, 37, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.1781528971291014, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 4619.53, "end": 4619.97, "word": ".", "probability": 0.98583984375 }, { "start": 4624.57, "end": 4625.01, "word": " We're", "probability": 0.883056640625 }, { "start": 4625.01, "end": 4625.17, "word": " actually", "probability": 0.77880859375 }, { "start": 4625.17, "end": 4625.39, "word": " doing", "probability": 0.91845703125 } ] }, { "id": 1344, "seek": 450996, "start": 4625.39, "end": 4626.93, "text": " We're actually doing really good", "tokens": [ 51164, 492, 434, 767, 884, 534, 665, 51264 ], "temperature": 0.0, "avg_logprob": -0.1781528971291014, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 4625.39, "end": 4625.75, "word": " really", "probability": 0.77197265625 }, { "start": 4625.75, "end": 4625.95, "word": " good", "probability": 0.87109375 }, { "start": 4625.95, "end": 4626.09, "word": " on", "probability": 0.90771484375 }, { "start": 4626.09, "end": 4626.39, "word": " time", "probability": 0.8046875 }, { "start": 4626.39, "end": 4626.79, "word": ".", "probability": 0.97802734375 }, { "start": 4626.79, "end": 4626.93, "word": " We", "probability": 0.896484375 } ] }, { "id": 1345, "seek": 450996, "start": 4626.93, "end": 4628.77, "text": " on time. We have one more task", "tokens": [ 51264, 322, 565, 13, 492, 362, 472, 544, 5633, 51364 ], "temperature": 0.0, "avg_logprob": -0.1781528971291014, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 4626.93, "end": 4627.05, "word": " have", "probability": 0.87890625 }, { "start": 4627.05, "end": 4627.27, "word": " one", "probability": 0.81494140625 }, { "start": 4627.27, "end": 4627.45, "word": " more", "probability": 0.8798828125 }, { "start": 4627.45, "end": 4627.77, "word": " task", "probability": 0.79541015625 }, { "start": 4627.77, "end": 4628.09, "word": " after", "probability": 0.72021484375 }, { "start": 4628.09, "end": 4628.41, "word": " this", "probability": 0.88330078125 }, { "start": 4628.41, "end": 4628.61, "word": ".", "probability": 0.8955078125 }, { "start": 4628.61, "end": 4628.77, "word": " It", "probability": 0.8935546875 } ] }, { "id": 1346, "seek": 450996, "start": 4628.77, "end": 4630.53, "text": " after this. It is", "tokens": [ 51364, 934, 341, 13, 467, 307, 51464 ], "temperature": 0.0, "avg_logprob": -0.1781528971291014, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 4628.77, "end": 4629.07, "word": " is", "probability": 0.880859375 }, { "start": 4629.07, "end": 4630.07, "word": " going", "probability": 0.8505859375 }, { "start": 4630.07, "end": 4630.25, "word": " to", "probability": 0.904296875 }, { "start": 4630.25, "end": 4630.37, "word": " be", "probability": 0.90673828125 }, { "start": 4630.37, "end": 4630.53, "word": " the", "probability": 0.81103515625 } ] }, { "id": 1347, "seek": 450996, "start": 4630.53, "end": 4633.73, "text": " going to be the most challenging task.", "tokens": [ 51464, 516, 281, 312, 264, 881, 7595, 5633, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.1781528971291014, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 4630.53, "end": 4630.75, "word": " most", "probability": 0.8017578125 }, { "start": 4630.75, "end": 4631.39, "word": " challenging", "probability": 0.79248046875 }, { "start": 4631.39, "end": 4631.91, "word": " task", "probability": 0.80078125 }, { "start": 4631.91, "end": 4632.35, "word": ".", "probability": 0.1434326171875 }, { "start": 4632.63, "end": 4633.07, "word": " But", "probability": 0.8779296875 }, { "start": 4633.07, "end": 4633.31, "word": " it", "probability": 0.8798828125 }, { "start": 4633.31, "end": 4633.47, "word": " is", "probability": 0.90283203125 }, { "start": 4633.47, "end": 4633.73, "word": " going", "probability": 0.857421875 } ] }, { "id": 1348, "seek": 450996, "start": 4633.73, "end": 4636.09, "text": " But it is going to", "tokens": [ 51564, 583, 309, 307, 516, 281, 51664 ], "temperature": 0.0, "avg_logprob": -0.1781528971291014, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.00394439697265625, "words": [ { "start": 4633.73, "end": 4634.41, "word": " to", "probability": 0.90380859375 }, { "start": 4634.41, "end": 4636.09, "word": " take", "probability": 0.80029296875 } ] }, { "id": 1349, "seek": 450996, "start": 4633.99, "end": 4635.99, "text": " take", "tokens": [ 51664, 747, 51764 ], "temperature": 0.0, "avg_logprob": -0.1781528971291014, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.00394439697265625, "words": [] }, { "id": 1350, "seek": 453752, "start": 4636.09, "end": 4637.75, "text": " everything from A to Z", "tokens": [ 50364, 1203, 490, 316, 281, 1176, 50464 ], "temperature": 0.0, "avg_logprob": -0.16441760669377717, "compression_ratio": 1.4484848484848485, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 4636.09, "end": 4636.51, "word": " everything", "probability": 0.77392578125 }, { "start": 4636.51, "end": 4637.07, "word": " from", "probability": 0.8203125 }, { "start": 4637.07, "end": 4637.35, "word": " A", "probability": 0.90478515625 }, { "start": 4637.35, "end": 4637.47, "word": " to", "probability": 0.85693359375 }, { "start": 4637.47, "end": 4637.75, "word": " Z", "probability": 0.99462890625 } ] }, { "id": 1351, "seek": 453752, "start": 4637.75, "end": 4640.17, "text": " and show us what we", "tokens": [ 50464, 293, 855, 505, 437, 321, 50564 ], "temperature": 0.0, "avg_logprob": -0.16441760669377717, "compression_ratio": 1.4484848484848485, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 4637.75, "end": 4638.73, "word": " and", "probability": 0.740234375 }, { "start": 4638.73, "end": 4639.83, "word": " show", "probability": 0.8681640625 }, { "start": 4639.83, "end": 4639.95, "word": " us", "probability": 0.89501953125 }, { "start": 4639.95, "end": 4640.07, "word": " what", "probability": 0.88720703125 }, { "start": 4640.07, "end": 4640.17, "word": " we", "probability": 0.90283203125 } ] }, { "id": 1352, "seek": 453752, "start": 4640.17, "end": 4640.99, "text": " learned.", "tokens": [ 50564, 3264, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.16441760669377717, "compression_ratio": 1.4484848484848485, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 4640.17, "end": 4640.43, "word": " learned", "probability": 0.71533203125 }, { "start": 4640.43, "end": 4640.99, "word": ".", "probability": 0.8994140625 } ] }, { "id": 1353, "seek": 453752, "start": 4643.94, "end": 4646.08, "text": " So I just want to check one last", "tokens": [ 50664, 407, 286, 445, 528, 281, 1520, 472, 1036, 50764 ], "temperature": 0.0, "avg_logprob": -0.16441760669377717, "compression_ratio": 1.4484848484848485, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 4643.94, "end": 4644.36, "word": " So", "probability": 0.411376953125 }, { "start": 4644.36, "end": 4644.6, "word": " I", "probability": 0.5615234375 }, { "start": 4644.6, "end": 4644.7, "word": " just", "probability": 0.541015625 }, { "start": 4644.7, "end": 4644.9, "word": " want", "probability": 0.6484375 }, { "start": 4644.9, "end": 4645.28, "word": " to", "probability": 0.90576171875 }, { "start": 4645.28, "end": 4645.62, "word": " check", "probability": 0.86279296875 }, { "start": 4645.62, "end": 4645.8, "word": " one", "probability": 0.82568359375 }, { "start": 4645.8, "end": 4646.08, "word": " last", "probability": 0.8154296875 } ] }, { "id": 1354, "seek": 453752, "start": 4646.08, "end": 4647.82, "text": " time. And that is", "tokens": [ 50764, 565, 13, 400, 300, 307, 50864 ], "temperature": 0.0, "avg_logprob": -0.16441760669377717, "compression_ratio": 1.4484848484848485, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 4646.08, "end": 4646.58, "word": " time", "probability": 0.81640625 }, { "start": 4646.58, "end": 4647.14, "word": ".", "probability": 0.45068359375 }, { "start": 4647.22, "end": 4647.54, "word": " And", "probability": 0.250244140625 }, { "start": 4647.54, "end": 4647.68, "word": " that", "probability": 0.74658203125 }, { "start": 4647.68, "end": 4647.82, "word": " is", "probability": 0.8740234375 } ] }, { "id": 1355, "seek": 453752, "start": 4647.82, "end": 4648.94, "text": " still going.", "tokens": [ 50864, 920, 516, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.16441760669377717, "compression_ratio": 1.4484848484848485, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 4647.82, "end": 4648.04, "word": " still", "probability": 0.90869140625 }, { "start": 4648.04, "end": 4648.38, "word": " going", "probability": 0.86083984375 }, { "start": 4648.38, "end": 4648.94, "word": ".", "probability": 0.83154296875 } ] }, { "id": 1356, "seek": 453752, "start": 4652.74, "end": 4654.44, "text": " So I'm going to go ahead and run", "tokens": [ 50964, 407, 286, 478, 516, 281, 352, 2286, 293, 1190, 51064 ], "temperature": 0.0, "avg_logprob": -0.16441760669377717, "compression_ratio": 1.4484848484848485, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 4652.74, "end": 4653.3, "word": " So", "probability": 0.80615234375 }, { "start": 4653.3, "end": 4653.58, "word": " I'm", "probability": 0.9658203125 }, { "start": 4653.58, "end": 4653.62, "word": " going", "probability": 0.5048828125 }, { "start": 4653.62, "end": 4653.64, "word": " to", "probability": 0.90087890625 }, { "start": 4653.64, "end": 4653.74, "word": " go", "probability": 0.90478515625 }, { "start": 4653.74, "end": 4653.9, "word": " ahead", "probability": 0.85986328125 }, { "start": 4653.9, "end": 4654.06, "word": " and", "probability": 0.89697265625 }, { "start": 4654.06, "end": 4654.44, "word": " run", "probability": 0.90185546875 } ] }, { "id": 1357, "seek": 453752, "start": 4654.44, "end": 4655.88, "text": " this.", "tokens": [ 51064, 341, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.16441760669377717, "compression_ratio": 1.4484848484848485, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 4654.44, "end": 4655.32, "word": " this", "probability": 0.88134765625 }, { "start": 4655.32, "end": 4655.88, "word": ".", "probability": 0.935546875 } ] }, { "id": 1358, "seek": 453752, "start": 4657.06, "end": 4658.52, "text": " This was 6D that I", "tokens": [ 51164, 639, 390, 1386, 35, 300, 286, 51264 ], "temperature": 0.0, "avg_logprob": -0.16441760669377717, "compression_ratio": 1.4484848484848485, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 4657.06, "end": 4657.62, "word": " This", "probability": 0.7685546875 }, { "start": 4657.62, "end": 4657.8, "word": " was", "probability": 0.8837890625 }, { "start": 4657.8, "end": 4658.24, "word": " 6D", "probability": 0.897216796875 }, { "start": 4658.24, "end": 4658.42, "word": " that", "probability": 0.8681640625 }, { "start": 4658.42, "end": 4658.52, "word": " I", "probability": 0.99560546875 } ] }, { "id": 1359, "seek": 453752, "start": 4658.52, "end": 4660.88, "text": " just clicked to run.", "tokens": [ 51264, 445, 23370, 281, 1190, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.16441760669377717, "compression_ratio": 1.4484848484848485, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 4658.52, "end": 4658.8, "word": " just", "probability": 0.884765625 }, { "start": 4658.8, "end": 4659.82, "word": " clicked", "probability": 0.78173828125 }, { "start": 4659.82, "end": 4660.04, "word": " to", "probability": 0.892578125 }, { "start": 4660.04, "end": 4660.32, "word": " run", "probability": 0.89794921875 }, { "start": 4660.32, "end": 4660.88, "word": ".", "probability": 0.96484375 } ] }, { "id": 1360, "seek": 453752, "start": 4664.42, "end": 4666.84, "text": " It says the kernel is idle.", "tokens": [ 51564, 467, 1619, 264, 28256, 307, 30650, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.16441760669377717, "compression_ratio": 1.4484848484848485, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 4664.42, "end": 4664.98, "word": " It", "probability": 0.0296478271484375 }, { "start": 4664.98, "end": 4665.54, "word": " says", "probability": 0.72021484375 }, { "start": 4665.54, "end": 4665.72, "word": " the", "probability": 0.7734375 }, { "start": 4665.72, "end": 4665.94, "word": " kernel", "probability": 0.671875 }, { "start": 4665.94, "end": 4666.1, "word": " is", "probability": 0.457763671875 }, { "start": 4666.1, "end": 4666.42, "word": " idle", "probability": 0.8779296875 }, { "start": 4666.42, "end": 4666.84, "word": ".", "probability": 0.86474609375 } ] }, { "id": 1361, "seek": 453752, "start": 4666.84, "end": 4668.02, "text": " That's not good.", "tokens": [ 51664, 663, 311, 406, 665, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.16441760669377717, "compression_ratio": 1.4484848484848485, "no_speech_prob": 0.0053863525390625, "words": [ { "start": 4666.84, "end": 4667.1, "word": " That's", "probability": 0.860595703125 }, { "start": 4667.1, "end": 4667.24, "word": " not", "probability": 0.861328125 }, { "start": 4667.24, "end": 4667.46, "word": " good", "probability": 0.8818359375 }, { "start": 4667.46, "end": 4668.02, "word": ".", "probability": 0.99755859375 } ] }, { "id": 1362, "seek": 456078, "start": 4672.78, "end": 4673.54, "text": " Let me see if I can", "tokens": [ 50364, 961, 385, 536, 498, 286, 393, 50464 ], "temperature": 0.0, "avg_logprob": -0.20827609431612623, "compression_ratio": 1.437125748502994, "no_speech_prob": 0.01971435546875, "words": [ { "start": 4672.78, "end": 4673.18, "word": " Let", "probability": 0.5361328125 }, { "start": 4673.18, "end": 4673.18, "word": " me", "probability": 0.65576171875 }, { "start": 4673.18, "end": 4673.3, "word": " see", "probability": 0.81982421875 }, { "start": 4673.3, "end": 4673.4, "word": " if", "probability": 0.89306640625 }, { "start": 4673.4, "end": 4673.44, "word": " I", "probability": 0.94189453125 }, { "start": 4673.44, "end": 4673.54, "word": " can", "probability": 0.90283203125 } ] }, { "id": 1363, "seek": 456078, "start": 4673.54, "end": 4674.98, "text": " pause this.", "tokens": [ 50464, 10465, 341, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.20827609431612623, "compression_ratio": 1.437125748502994, "no_speech_prob": 0.01971435546875, "words": [ { "start": 4673.54, "end": 4674.06, "word": " pause", "probability": 0.80224609375 }, { "start": 4674.06, "end": 4674.58, "word": " this", "probability": 0.88134765625 }, { "start": 4674.58, "end": 4674.98, "word": ".", "probability": 0.75390625 } ] }, { "id": 1364, "seek": 456078, "start": 4679.08, "end": 4680.72, "text": " Let me just interrupt it.", "tokens": [ 50564, 961, 385, 445, 12729, 309, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.20827609431612623, "compression_ratio": 1.437125748502994, "no_speech_prob": 0.01971435546875, "words": [ { "start": 4679.08, "end": 4679.48, "word": " Let", "probability": 0.293701171875 }, { "start": 4679.48, "end": 4679.48, "word": " me", "probability": 0.81494140625 }, { "start": 4679.48, "end": 4679.66, "word": " just", "probability": 0.896484375 }, { "start": 4679.66, "end": 4680.06, "word": " interrupt", "probability": 0.76953125 }, { "start": 4680.06, "end": 4680.32, "word": " it", "probability": 0.86328125 }, { "start": 4680.32, "end": 4680.72, "word": ".", "probability": 0.44775390625 } ] }, { "id": 1365, "seek": 456078, "start": 4680.98, "end": 4681.92, "text": " Interrupt the kernel.", "tokens": [ 50664, 5751, 5428, 264, 28256, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.20827609431612623, "compression_ratio": 1.437125748502994, "no_speech_prob": 0.01971435546875, "words": [ { "start": 4680.98, "end": 4681.08, "word": " Interrupt", "probability": 0.7392578125 }, { "start": 4681.08, "end": 4681.26, "word": " the", "probability": 0.7607421875 }, { "start": 4681.26, "end": 4681.52, "word": " kernel", "probability": 0.7255859375 }, { "start": 4681.52, "end": 4681.92, "word": ".", "probability": 0.798828125 } ] }, { "id": 1366, "seek": 456078, "start": 4685.54, "end": 4686.54, "text": " So I'm going to run this", "tokens": [ 50764, 407, 286, 478, 516, 281, 1190, 341, 50864 ], "temperature": 0.0, "avg_logprob": -0.20827609431612623, "compression_ratio": 1.437125748502994, "no_speech_prob": 0.01971435546875, "words": [ { "start": 4685.54, "end": 4685.92, "word": " So", "probability": 0.353515625 }, { "start": 4685.92, "end": 4686.08, "word": " I'm", "probability": 0.33941650390625 }, { "start": 4686.08, "end": 4686.14, "word": " going", "probability": 0.662109375 }, { "start": 4686.14, "end": 4686.14, "word": " to", "probability": 0.90478515625 }, { "start": 4686.14, "end": 4686.34, "word": " run", "probability": 0.87939453125 }, { "start": 4686.34, "end": 4686.54, "word": " this", "probability": 0.87451171875 } ] }, { "id": 1367, "seek": 456078, "start": 4686.54, "end": 4687.78, "text": " because that took a second.", "tokens": [ 50864, 570, 300, 1890, 257, 1150, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.20827609431612623, "compression_ratio": 1.437125748502994, "no_speech_prob": 0.01971435546875, "words": [ { "start": 4686.54, "end": 4686.68, "word": " because", "probability": 0.57421875 }, { "start": 4686.68, "end": 4686.82, "word": " that", "probability": 0.8505859375 }, { "start": 4686.82, "end": 4686.98, "word": " took", "probability": 0.87158203125 }, { "start": 4687.14, "end": 4687.38, "word": " a second", "probability": 0.8017578125 }, { "start": 4687.38, "end": 4687.78, "word": ".", "probability": 0.9970703125 } ] }, { "id": 1368, "seek": 456078, "start": 4691.47, "end": 4692.33, "text": " Uh oh, I hope I didn't", "tokens": [ 50964, 4019, 1954, 11, 286, 1454, 286, 994, 380, 51064 ], "temperature": 0.0, "avg_logprob": -0.20827609431612623, "compression_ratio": 1.437125748502994, "no_speech_prob": 0.01971435546875, "words": [ { "start": 4691.47, "end": 4691.77, "word": " Uh", "probability": 0.6826171875 }, { "start": 4691.77, "end": 4691.85, "word": " oh", "probability": 0.310546875 }, { "start": 4691.85, "end": 4691.89, "word": ",", "probability": 0.705078125 }, { "start": 4691.89, "end": 4691.99, "word": " I", "probability": 0.998046875 }, { "start": 4691.99, "end": 4692.11, "word": " hope", "probability": 0.83154296875 }, { "start": 4692.11, "end": 4692.21, "word": " I", "probability": 0.98828125 }, { "start": 4692.21, "end": 4692.33, "word": " didn't", "probability": 0.7120361328125 } ] }, { "id": 1369, "seek": 456078, "start": 4692.33, "end": 4693.33, "text": " time out.", "tokens": [ 51064, 565, 484, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.20827609431612623, "compression_ratio": 1.437125748502994, "no_speech_prob": 0.01971435546875, "words": [ { "start": 4692.33, "end": 4692.61, "word": " time", "probability": 0.84326171875 }, { "start": 4692.61, "end": 4692.93, "word": " out", "probability": 0.68212890625 }, { "start": 4692.93, "end": 4693.33, "word": ".", "probability": 0.94921875 } ] }, { "id": 1370, "seek": 456078, "start": 4694.19, "end": 4695.65, "text": " That would be very bad.", "tokens": [ 51164, 663, 576, 312, 588, 1578, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.20827609431612623, "compression_ratio": 1.437125748502994, "no_speech_prob": 0.01971435546875, "words": [ { "start": 4694.19, "end": 4694.59, "word": " That", "probability": 0.64404296875 }, { "start": 4694.59, "end": 4694.61, "word": " would", "probability": 0.59033203125 }, { "start": 4694.61, "end": 4694.69, "word": " be", "probability": 0.90234375 }, { "start": 4694.69, "end": 4694.91, "word": " very", "probability": 0.73583984375 }, { "start": 4694.91, "end": 4695.25, "word": " bad", "probability": 0.8876953125 }, { "start": 4695.25, "end": 4695.65, "word": ".", "probability": 0.99609375 } ] }, { "id": 1371, "seek": 456078, "start": 4710.95, "end": 4712.37, "text": " Let's try and run it again.", "tokens": [ 51264, 961, 311, 853, 293, 1190, 309, 797, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.20827609431612623, "compression_ratio": 1.437125748502994, "no_speech_prob": 0.01971435546875, "words": [ { "start": 4710.95, "end": 4711.19, "word": " Let's", "probability": 0.759033203125 }, { "start": 4711.19, "end": 4711.31, "word": " try", "probability": 0.82958984375 }, { "start": 4711.31, "end": 4711.41, "word": " and", "probability": 0.404541015625 }, { "start": 4711.41, "end": 4711.53, "word": " run", "probability": 0.90234375 }, { "start": 4711.53, "end": 4711.63, "word": " it", "probability": 0.90283203125 }, { "start": 4711.63, "end": 4711.97, "word": " again", "probability": 0.91943359375 }, { "start": 4711.97, "end": 4712.37, "word": ".", "probability": 0.99560546875 } ] }, { "id": 1372, "seek": 456078, "start": 4714.23, "end": 4714.67, "text": " Yeah,", "tokens": [ 51364, 865, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.20827609431612623, "compression_ratio": 1.437125748502994, "no_speech_prob": 0.01971435546875, "words": [ { "start": 4714.23, "end": 4714.63, "word": " Yeah", "probability": 0.89111328125 }, { "start": 4714.63, "end": 4714.67, "word": ",", "probability": 0.9287109375 } ] }, { "id": 1373, "seek": 456078, "start": 4714.67, "end": 4715.69, "text": " that's not good.", "tokens": [ 51464, 300, 311, 406, 665, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.20827609431612623, "compression_ratio": 1.437125748502994, "no_speech_prob": 0.01971435546875, "words": [ { "start": 4714.67, "end": 4714.89, "word": " that's", "probability": 0.940673828125 }, { "start": 4714.89, "end": 4715.07, "word": " not", "probability": 0.89453125 }, { "start": 4715.07, "end": 4715.29, "word": " good", "probability": 0.88232421875 }, { "start": 4715.29, "end": 4715.69, "word": ".", "probability": 0.99853515625 } ] }, { "id": 1374, "seek": 458858, "start": 4722.27, "end": 4724.15, "text": " Restart and clear output.", "tokens": [ 50364, 13094, 446, 293, 1850, 5598, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.2380617990922392, "compression_ratio": 1.465, "no_speech_prob": 0.006389617919921875, "words": [ { "start": 4722.27, "end": 4722.71, "word": " Restart", "probability": 0.59564208984375 }, { "start": 4722.71, "end": 4723.05, "word": " and", "probability": 0.650390625 }, { "start": 4723.05, "end": 4723.35, "word": " clear", "probability": 0.6689453125 }, { "start": 4723.35, "end": 4723.71, "word": " output", "probability": 0.830078125 }, { "start": 4723.71, "end": 4724.15, "word": ".", "probability": 0.85986328125 } ] }, { "id": 1375, "seek": 458858, "start": 4727.18, "end": 4729.62, "text": " So this is going to go all the way to the beginning.", "tokens": [ 50864, 407, 341, 307, 516, 281, 352, 439, 264, 636, 281, 264, 2863, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.2380617990922392, "compression_ratio": 1.465, "no_speech_prob": 0.006389617919921875, "words": [ { "start": 4727.18, "end": 4727.62, "word": " So", "probability": 0.40380859375 }, { "start": 4727.62, "end": 4727.72, "word": " this", "probability": 0.72021484375 }, { "start": 4727.72, "end": 4727.8, "word": " is", "probability": 0.90087890625 }, { "start": 4727.8, "end": 4727.92, "word": " going", "probability": 0.5615234375 }, { "start": 4727.92, "end": 4727.96, "word": " to", "probability": 0.90087890625 }, { "start": 4727.96, "end": 4728.1, "word": " go", "probability": 0.89501953125 }, { "start": 4728.1, "end": 4728.46, "word": " all", "probability": 0.89404296875 }, { "start": 4728.46, "end": 4728.6, "word": " the", "probability": 0.81494140625 }, { "start": 4728.6, "end": 4728.7, "word": " way", "probability": 0.89208984375 }, { "start": 4728.7, "end": 4728.8, "word": " to", "probability": 0.90234375 }, { "start": 4728.8, "end": 4728.9, "word": " the", "probability": 0.8173828125 }, { "start": 4728.9, "end": 4729.18, "word": " beginning", "probability": 0.80126953125 }, { "start": 4729.18, "end": 4729.62, "word": ".", "probability": 0.94970703125 } ] }, { "id": 1376, "seek": 458858, "start": 4731.14, "end": 4732.68, "text": " Let's see if I can get this to run.", "tokens": [ 51064, 961, 311, 536, 498, 286, 393, 483, 341, 281, 1190, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.2380617990922392, "compression_ratio": 1.465, "no_speech_prob": 0.006389617919921875, "words": [ { "start": 4731.14, "end": 4731.58, "word": " Let's", "probability": 0.705322265625 }, { "start": 4731.58, "end": 4731.68, "word": " see", "probability": 0.79150390625 }, { "start": 4731.68, "end": 4731.72, "word": " if", "probability": 0.89306640625 }, { "start": 4731.72, "end": 4731.78, "word": " I", "probability": 0.4453125 }, { "start": 4731.78, "end": 4731.82, "word": " can", "probability": 0.88134765625 }, { "start": 4731.82, "end": 4731.96, "word": " get", "probability": 0.87744140625 }, { "start": 4731.96, "end": 4732.12, "word": " this", "probability": 0.8818359375 }, { "start": 4732.12, "end": 4732.26, "word": " to", "probability": 0.89892578125 }, { "start": 4732.26, "end": 4732.48, "word": " run", "probability": 0.8935546875 }, { "start": 4732.48, "end": 4732.68, "word": ".", "probability": 0.935546875 } ] }, { "id": 1377, "seek": 458858, "start": 4732.68, "end": 4734.12, "text": " Okay, so that runs now.", "tokens": [ 51164, 1033, 11, 370, 300, 6676, 586, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.2380617990922392, "compression_ratio": 1.465, "no_speech_prob": 0.006389617919921875, "words": [ { "start": 4732.68, "end": 4732.9, "word": " Okay", "probability": 0.359619140625 }, { "start": 4732.9, "end": 4732.96, "word": ",", "probability": 0.8046875 }, { "start": 4732.96, "end": 4733.06, "word": " so", "probability": 0.89404296875 }, { "start": 4733.06, "end": 4733.22, "word": " that", "probability": 0.884765625 }, { "start": 4733.22, "end": 4733.46, "word": " runs", "probability": 0.8271484375 }, { "start": 4733.46, "end": 4733.68, "word": " now", "probability": 0.87548828125 }, { "start": 4733.68, "end": 4734.12, "word": ".", "probability": 0.99755859375 } ] }, { "id": 1378, "seek": 458858, "start": 4735.18, "end": 4737.52, "text": " So I ran into a bit of a technical difficulty.", "tokens": [ 51264, 407, 286, 5872, 666, 257, 857, 295, 257, 6191, 10360, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.2380617990922392, "compression_ratio": 1.465, "no_speech_prob": 0.006389617919921875, "words": [ { "start": 4735.18, "end": 4735.62, "word": " So", "probability": 0.85302734375 }, { "start": 4735.62, "end": 4735.66, "word": " I", "probability": 0.86328125 }, { "start": 4735.66, "end": 4735.78, "word": " ran", "probability": 0.89404296875 }, { "start": 4735.78, "end": 4735.9, "word": " into", "probability": 0.74462890625 }, { "start": 4736.02, "end": 4736.1, "word": " a bit", "probability": 0.89111328125 }, { "start": 4736.1, "end": 4736.18, "word": " of", "probability": 0.90625 }, { "start": 4736.26, "end": 4736.54, "word": " a technical", "probability": 0.84814453125 }, { "start": 4736.54, "end": 4737.08, "word": " difficulty", "probability": 0.62646484375 }, { "start": 4737.08, "end": 4737.52, "word": ".", "probability": 0.8857421875 } ] }, { "id": 1379, "seek": 458858, "start": 4737.64, "end": 4739.1, "text": " Instead of going through", "tokens": [ 51364, 7156, 295, 516, 807, 51464 ], "temperature": 0.0, "avg_logprob": -0.2380617990922392, "compression_ratio": 1.465, "no_speech_prob": 0.006389617919921875, "words": [ { "start": 4737.64, "end": 4738.08, "word": " Instead", "probability": 0.91259765625 }, { "start": 4738.08, "end": 4738.38, "word": " of", "probability": 0.90673828125 }, { "start": 4738.38, "end": 4738.7, "word": " going", "probability": 0.8681640625 }, { "start": 4738.7, "end": 4739.1, "word": " through", "probability": 0.80078125 } ] }, { "id": 1380, "seek": 458858, "start": 4739.1, "end": 4740.88, "text": " and filling", "tokens": [ 51464, 293, 10623, 51564 ], "temperature": 0.0, "avg_logprob": -0.2380617990922392, "compression_ratio": 1.465, "no_speech_prob": 0.006389617919921875, "words": [ { "start": 4739.1, "end": 4739.86, "word": " and", "probability": 0.8935546875 }, { "start": 4739.86, "end": 4740.88, "word": " filling", "probability": 0.69921875 } ] }, { "id": 1381, "seek": 458858, "start": 4740.88, "end": 4742.86, "text": " everything out, I'm just going to quickly", "tokens": [ 51564, 1203, 484, 11, 286, 478, 445, 516, 281, 2661, 51664 ], "temperature": 0.0, "avg_logprob": -0.2380617990922392, "compression_ratio": 1.465, "no_speech_prob": 0.006389617919921875, "words": [ { "start": 4740.88, "end": 4741.5, "word": " everything", "probability": 0.8681640625 }, { "start": 4741.5, "end": 4741.84, "word": " out", "probability": 0.82421875 }, { "start": 4741.84, "end": 4741.94, "word": ",", "probability": 0.91650390625 }, { "start": 4741.94, "end": 4742.04, "word": " I'm", "probability": 0.995849609375 }, { "start": 4742.04, "end": 4742.16, "word": " just", "probability": 0.876953125 }, { "start": 4742.16, "end": 4742.3, "word": " going", "probability": 0.681640625 }, { "start": 4742.3, "end": 4742.52, "word": " to", "probability": 0.90576171875 }, { "start": 4742.52, "end": 4742.86, "word": " quickly", "probability": 0.88671875 } ] }, { "id": 1382, "seek": 458858, "start": 4742.86, "end": 4744.86, "text": " grab the completed workbook.", "tokens": [ 51664, 4444, 264, 7365, 589, 2939, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.2380617990922392, "compression_ratio": 1.465, "no_speech_prob": 0.006389617919921875, "words": [ { "start": 4742.86, "end": 4743.34, "word": " grab", "probability": 0.79150390625 }, { "start": 4743.34, "end": 4743.62, "word": " the", "probability": 0.81591796875 }, { "start": 4743.62, "end": 4744.14, "word": " completed", "probability": 0.60009765625 }, { "start": 4744.14, "end": 4744.7, "word": " workbook", "probability": 0.883544921875 }, { "start": 4744.7, "end": 4744.86, "word": ".", "probability": 0.83203125 } ] }, { "id": 1383, "seek": 461858, "start": 4746.26, "end": 4749.7, "text": " And I'm", "tokens": [ 50364, 400, 286, 478, 50464 ], "temperature": 0.0, "avg_logprob": -0.2052801782372354, "compression_ratio": 1.6774193548387097, "no_speech_prob": 0.0011873245239257812, "words": [ { "start": 4746.26, "end": 4746.94, "word": " And", "probability": 0.484619140625 }, { "start": 4749.36, "end": 4749.7, "word": " I'm", "probability": 0.73876953125 } ] }, { "id": 1384, "seek": 461858, "start": 4749.7, "end": 4750.76, "text": " going to", "tokens": [ 50464, 516, 281, 50564 ], "temperature": 0.0, "avg_logprob": -0.2052801782372354, "compression_ratio": 1.6774193548387097, "no_speech_prob": 0.0011873245239257812, "words": [ { "start": 4749.7, "end": 4749.96, "word": " going", "probability": 0.85888671875 }, { "start": 4749.96, "end": 4750.76, "word": " to", "probability": 0.90869140625 } ] }, { "id": 1385, "seek": 461858, "start": 4752.38, "end": 4753.06, "text": " just", "tokens": [ 50564, 445, 50664 ], "temperature": 0.0, "avg_logprob": -0.2052801782372354, "compression_ratio": 1.6774193548387097, "no_speech_prob": 0.0011873245239257812, "words": [ { "start": 4752.38, "end": 4753.06, "word": " just", "probability": 0.79443359375 } ] }, { "id": 1386, "seek": 461858, "start": 4753.06, "end": 4755.48, "text": " go ahead, run all.", "tokens": [ 50664, 352, 2286, 11, 1190, 439, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.2052801782372354, "compression_ratio": 1.6774193548387097, "no_speech_prob": 0.0011873245239257812, "words": [ { "start": 4753.06, "end": 4753.9, "word": " go", "probability": 0.89697265625 }, { "start": 4753.9, "end": 4754.16, "word": " ahead", "probability": 0.8671875 }, { "start": 4754.16, "end": 4754.4, "word": ",", "probability": 0.448486328125 }, { "start": 4754.4, "end": 4754.64, "word": " run", "probability": 0.7724609375 }, { "start": 4754.64, "end": 4755.14, "word": " all", "probability": 0.86767578125 }, { "start": 4755.14, "end": 4755.48, "word": ".", "probability": 0.90771484375 } ] }, { "id": 1387, "seek": 461858, "start": 4757.18, "end": 4759.08, "text": " This is going to run", "tokens": [ 50864, 639, 307, 516, 281, 1190, 50964 ], "temperature": 0.0, "avg_logprob": -0.2052801782372354, "compression_ratio": 1.6774193548387097, "no_speech_prob": 0.0011873245239257812, "words": [ { "start": 4757.18, "end": 4757.86, "word": " This", "probability": 0.802734375 }, { "start": 4757.86, "end": 4758.0, "word": " is", "probability": 0.904296875 }, { "start": 4758.0, "end": 4758.18, "word": " going", "probability": 0.8662109375 }, { "start": 4758.18, "end": 4758.56, "word": " to", "probability": 0.90576171875 }, { "start": 4758.56, "end": 4759.08, "word": " run", "probability": 0.90771484375 } ] }, { "id": 1388, "seek": 461858, "start": 4759.08, "end": 4761.12, "text": " everything for me.", "tokens": [ 50964, 1203, 337, 385, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.2052801782372354, "compression_ratio": 1.6774193548387097, "no_speech_prob": 0.0011873245239257812, "words": [ { "start": 4759.08, "end": 4759.6, "word": " everything", "probability": 0.89013671875 }, { "start": 4759.6, "end": 4760.12, "word": " for", "probability": 0.90478515625 }, { "start": 4760.12, "end": 4760.44, "word": " me", "probability": 0.904296875 }, { "start": 4760.44, "end": 4761.12, "word": ".", "probability": 0.83349609375 } ] }, { "id": 1389, "seek": 461858, "start": 4762.86, "end": 4763.54, "text": " So", "tokens": [ 51064, 407, 51164 ], "temperature": 0.0, "avg_logprob": -0.2052801782372354, "compression_ratio": 1.6774193548387097, "no_speech_prob": 0.0011873245239257812, "words": [ { "start": 4762.86, "end": 4763.54, "word": " So", "probability": 0.90234375 } ] }, { "id": 1390, "seek": 461858, "start": 4763.54, "end": 4765.38, "text": " while I'm waiting for some of", "tokens": [ 51164, 1339, 286, 478, 3806, 337, 512, 295, 51264 ], "temperature": 0.0, "avg_logprob": -0.2052801782372354, "compression_ratio": 1.6774193548387097, "no_speech_prob": 0.0011873245239257812, "words": [ { "start": 4763.54, "end": 4764.04, "word": " while", "probability": 0.69140625 }, { "start": 4764.04, "end": 4764.18, "word": " I'm", "probability": 0.996826171875 }, { "start": 4764.18, "end": 4764.46, "word": " waiting", "probability": 0.8232421875 }, { "start": 4764.46, "end": 4764.76, "word": " for", "probability": 0.90185546875 }, { "start": 4764.76, "end": 4765.3, "word": " some", "probability": 0.81298828125 }, { "start": 4765.3, "end": 4765.38, "word": " of", "probability": 0.90771484375 } ] }, { "id": 1391, "seek": 461858, "start": 4765.38, "end": 4767.62, "text": " this stuff to run,", "tokens": [ 51264, 341, 1507, 281, 1190, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.2052801782372354, "compression_ratio": 1.6774193548387097, "no_speech_prob": 0.0011873245239257812, "words": [ { "start": 4765.38, "end": 4765.52, "word": " this", "probability": 0.8115234375 }, { "start": 4765.52, "end": 4765.76, "word": " stuff", "probability": 0.79150390625 }, { "start": 4765.76, "end": 4766.04, "word": " to", "probability": 0.9052734375 }, { "start": 4766.04, "end": 4766.4, "word": " run", "probability": 0.9013671875 }, { "start": 4766.4, "end": 4767.62, "word": ",", "probability": 0.7978515625 } ] }, { "id": 1392, "seek": 461858, "start": 4767.62, "end": 4769.1, "text": " let's see that packages are", "tokens": [ 51364, 718, 311, 536, 300, 17401, 366, 51464 ], "temperature": 0.0, "avg_logprob": -0.2052801782372354, "compression_ratio": 1.6774193548387097, "no_speech_prob": 0.0011873245239257812, "words": [ { "start": 4767.62, "end": 4767.84, "word": " let's", "probability": 0.65625 }, { "start": 4767.84, "end": 4768.0, "word": " see", "probability": 0.802734375 }, { "start": 4768.0, "end": 4768.4, "word": " that", "probability": 0.615234375 }, { "start": 4768.4, "end": 4768.8, "word": " packages", "probability": 0.80322265625 }, { "start": 4768.8, "end": 4769.1, "word": " are", "probability": 0.88232421875 } ] }, { "id": 1393, "seek": 461858, "start": 4769.1, "end": 4772.92, "text": " being downloaded, tokenization is defined,", "tokens": [ 51464, 885, 21748, 11, 14862, 2144, 307, 7642, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.2052801782372354, "compression_ratio": 1.6774193548387097, "no_speech_prob": 0.0011873245239257812, "words": [ { "start": 4769.1, "end": 4769.56, "word": " being", "probability": 0.85400390625 }, { "start": 4769.56, "end": 4770.0, "word": " downloaded", "probability": 0.83642578125 }, { "start": 4770.0, "end": 4770.38, "word": ",", "probability": 0.80029296875 }, { "start": 4770.38, "end": 4770.84, "word": " tokenization", "probability": 0.85986328125 }, { "start": 4770.84, "end": 4771.1, "word": " is", "probability": 0.71337890625 }, { "start": 4771.1, "end": 4771.54, "word": " defined", "probability": 0.72900390625 }, { "start": 4771.54, "end": 4772.92, "word": ",", "probability": 0.379150390625 } ] }, { "id": 1394, "seek": 461858, "start": 4772.92, "end": 4773.58, "text": " everything's good,", "tokens": [ 51564, 1203, 311, 665, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.2052801782372354, "compression_ratio": 1.6774193548387097, "no_speech_prob": 0.0011873245239257812, "words": [ { "start": 4772.92, "end": 4773.34, "word": " everything's", "probability": 0.856201171875 }, { "start": 4773.34, "end": 4773.52, "word": " good", "probability": 0.87255859375 }, { "start": 4773.52, "end": 4773.58, "word": ",", "probability": 0.90576171875 } ] }, { "id": 1395, "seek": 461858, "start": 4773.58, "end": 4774.98, "text": " everything's good, everything's good.", "tokens": [ 51664, 1203, 311, 665, 11, 1203, 311, 665, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.2052801782372354, "compression_ratio": 1.6774193548387097, "no_speech_prob": 0.0011873245239257812, "words": [ { "start": 4773.58, "end": 4773.88, "word": " everything's", "probability": 0.9326171875 }, { "start": 4773.88, "end": 4774.02, "word": " good", "probability": 0.87548828125 }, { "start": 4774.02, "end": 4774.06, "word": ",", "probability": 0.97509765625 }, { "start": 4774.06, "end": 4774.4, "word": " everything's", "probability": 0.94287109375 }, { "start": 4774.4, "end": 4774.72, "word": " good", "probability": 0.87451171875 }, { "start": 4774.72, "end": 4774.98, "word": ".", "probability": 0.9541015625 } ] }, { "id": 1396, "seek": 464704, "start": 4782.49, "end": 4784.01, "text": " Where is it stuck now?", "tokens": [ 50364, 2305, 307, 309, 5541, 586, 30, 50464 ], "temperature": 0.0, "avg_logprob": -0.1899271786791607, "compression_ratio": 1.6195121951219513, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4782.49, "end": 4782.87, "word": " Where", "probability": 0.326171875 }, { "start": 4782.87, "end": 4782.97, "word": " is", "probability": 0.59033203125 }, { "start": 4782.97, "end": 4783.09, "word": " it", "probability": 0.88330078125 }, { "start": 4783.09, "end": 4783.33, "word": " stuck", "probability": 0.75390625 }, { "start": 4783.33, "end": 4783.69, "word": " now", "probability": 0.8603515625 }, { "start": 4783.69, "end": 4784.01, "word": "?", "probability": 0.9189453125 } ] }, { "id": 1397, "seek": 464704, "start": 4784.01, "end": 4786.79, "text": " It is stuck...", "tokens": [ 50464, 467, 307, 5541, 485, 50564 ], "temperature": 0.0, "avg_logprob": -0.1899271786791607, "compression_ratio": 1.6195121951219513, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4784.01, "end": 4784.17, "word": " It", "probability": 0.890625 }, { "start": 4784.17, "end": 4784.47, "word": " is", "probability": 0.88818359375 }, { "start": 4784.47, "end": 4786.79, "word": " stuck...", "probability": 0.45074462890625 } ] }, { "id": 1398, "seek": 464704, "start": 4790.54, "end": 4792.52, "text": " Looks like it's stuck reading the data.", "tokens": [ 50664, 10027, 411, 309, 311, 5541, 3760, 264, 1412, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.1899271786791607, "compression_ratio": 1.6195121951219513, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4790.54, "end": 4790.98, "word": " Looks", "probability": 0.36572265625 }, { "start": 4790.98, "end": 4791.08, "word": " like", "probability": 0.87646484375 }, { "start": 4791.08, "end": 4791.22, "word": " it's", "probability": 0.928466796875 }, { "start": 4791.22, "end": 4791.42, "word": " stuck", "probability": 0.78466796875 }, { "start": 4791.42, "end": 4791.64, "word": " reading", "probability": 0.8173828125 }, { "start": 4791.64, "end": 4791.8, "word": " the", "probability": 0.814453125 }, { "start": 4791.8, "end": 4792.08, "word": " data", "probability": 0.81298828125 }, { "start": 4792.08, "end": 4792.52, "word": ".", "probability": 0.849609375 } ] }, { "id": 1399, "seek": 464704, "start": 4793.72, "end": 4795.4, "text": " Training spam, training ham.", "tokens": [ 50764, 20620, 24028, 11, 3097, 7852, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.1899271786791607, "compression_ratio": 1.6195121951219513, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4793.72, "end": 4793.94, "word": " Training", "probability": 0.59765625 }, { "start": 4793.94, "end": 4794.26, "word": " spam", "probability": 0.56982421875 }, { "start": 4794.26, "end": 4794.38, "word": ",", "probability": 0.796875 }, { "start": 4794.38, "end": 4794.56, "word": " training", "probability": 0.78125 }, { "start": 4794.56, "end": 4794.96, "word": " ham", "probability": 0.859375 }, { "start": 4794.96, "end": 4795.4, "word": ".", "probability": 0.82568359375 } ] }, { "id": 1400, "seek": 464704, "start": 4803.01, "end": 4805.27, "text": " That one's done, done.", "tokens": [ 50964, 663, 472, 311, 1096, 11, 1096, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.1899271786791607, "compression_ratio": 1.6195121951219513, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4803.01, "end": 4803.45, "word": " That", "probability": 0.74267578125 }, { "start": 4803.45, "end": 4803.67, "word": " one's", "probability": 0.875 }, { "start": 4803.67, "end": 4804.01, "word": " done", "probability": 0.806640625 }, { "start": 4804.01, "end": 4804.25, "word": ",", "probability": 0.41748046875 }, { "start": 4804.25, "end": 4804.83, "word": " done", "probability": 0.8154296875 }, { "start": 4804.83, "end": 4805.27, "word": ".", "probability": 0.89404296875 } ] }, { "id": 1401, "seek": 464704, "start": 4808.37, "end": 4809.21, "text": " Yeah, when you see", "tokens": [ 51164, 865, 11, 562, 291, 536, 51264 ], "temperature": 0.0, "avg_logprob": -0.1899271786791607, "compression_ratio": 1.6195121951219513, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4808.37, "end": 4808.81, "word": " Yeah", "probability": 0.8466796875 }, { "start": 4808.81, "end": 4808.85, "word": ",", "probability": 0.89013671875 }, { "start": 4808.85, "end": 4808.97, "word": " when", "probability": 0.8671875 }, { "start": 4808.97, "end": 4809.07, "word": " you", "probability": 0.89892578125 }, { "start": 4809.07, "end": 4809.21, "word": " see", "probability": 0.8193359375 } ] }, { "id": 1402, "seek": 464704, "start": 4809.21, "end": 4811.25, "text": " numbers here, that means that that was the order", "tokens": [ 51264, 3547, 510, 11, 300, 1355, 300, 300, 390, 264, 1668, 51364 ], "temperature": 0.0, "avg_logprob": -0.1899271786791607, "compression_ratio": 1.6195121951219513, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4809.21, "end": 4809.63, "word": " numbers", "probability": 0.85546875 }, { "start": 4809.63, "end": 4809.95, "word": " here", "probability": 0.8095703125 }, { "start": 4809.95, "end": 4810.05, "word": ",", "probability": 0.82373046875 }, { "start": 4810.05, "end": 4810.15, "word": " that", "probability": 0.8828125 }, { "start": 4810.15, "end": 4810.39, "word": " means", "probability": 0.8916015625 }, { "start": 4810.39, "end": 4810.59, "word": " that", "probability": 0.8779296875 }, { "start": 4810.59, "end": 4810.73, "word": " that", "probability": 0.7412109375 }, { "start": 4810.73, "end": 4810.87, "word": " was", "probability": 0.89208984375 }, { "start": 4810.87, "end": 4811.03, "word": " the", "probability": 0.82421875 }, { "start": 4811.03, "end": 4811.25, "word": " order", "probability": 0.8310546875 } ] }, { "id": 1403, "seek": 464704, "start": 4811.25, "end": 4813.13, "text": " it was ran in. When you see a star,", "tokens": [ 51364, 309, 390, 5872, 294, 13, 1133, 291, 536, 257, 3543, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.1899271786791607, "compression_ratio": 1.6195121951219513, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4811.25, "end": 4811.39, "word": " it", "probability": 0.8955078125 }, { "start": 4811.39, "end": 4811.51, "word": " was", "probability": 0.83642578125 }, { "start": 4811.51, "end": 4811.75, "word": " ran", "probability": 0.87109375 }, { "start": 4811.75, "end": 4811.91, "word": " in", "probability": 0.8955078125 }, { "start": 4811.91, "end": 4811.97, "word": ".", "probability": 0.8662109375 }, { "start": 4811.97, "end": 4812.07, "word": " When", "probability": 0.814453125 }, { "start": 4812.07, "end": 4812.21, "word": " you", "probability": 0.8994140625 }, { "start": 4812.21, "end": 4812.35, "word": " see", "probability": 0.8154296875 }, { "start": 4812.53, "end": 4813.01, "word": " a star", "probability": 0.86376953125 }, { "start": 4813.01, "end": 4813.13, "word": ",", "probability": 0.91650390625 } ] }, { "id": 1404, "seek": 464704, "start": 4813.13, "end": 4814.89, "text": " that means that it's still running.", "tokens": [ 51464, 300, 1355, 300, 309, 311, 920, 2614, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.1899271786791607, "compression_ratio": 1.6195121951219513, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4813.13, "end": 4813.25, "word": " that", "probability": 0.88134765625 }, { "start": 4813.25, "end": 4813.45, "word": " means", "probability": 0.88232421875 }, { "start": 4813.45, "end": 4813.61, "word": " that", "probability": 0.87255859375 }, { "start": 4813.61, "end": 4813.81, "word": " it's", "probability": 0.949951171875 }, { "start": 4813.81, "end": 4814.01, "word": " still", "probability": 0.90625 }, { "start": 4814.01, "end": 4814.45, "word": " running", "probability": 0.8857421875 }, { "start": 4814.45, "end": 4814.89, "word": ".", "probability": 0.82177734375 } ] }, { "id": 1405, "seek": 464704, "start": 4815.17, "end": 4817.09, "text": " I'm not sure why the logistic regression", "tokens": [ 51564, 286, 478, 406, 988, 983, 264, 3565, 3142, 24590, 51664 ], "temperature": 0.0, "avg_logprob": -0.1899271786791607, "compression_ratio": 1.6195121951219513, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4815.17, "end": 4815.37, "word": " I'm", "probability": 0.766845703125 }, { "start": 4815.37, "end": 4815.55, "word": " not", "probability": 0.89599609375 }, { "start": 4815.55, "end": 4815.77, "word": " sure", "probability": 0.81201171875 }, { "start": 4815.77, "end": 4815.95, "word": " why", "probability": 0.8271484375 }, { "start": 4815.95, "end": 4816.25, "word": " the", "probability": 0.81494140625 }, { "start": 4816.25, "end": 4816.71, "word": " logistic", "probability": 0.913818359375 }, { "start": 4816.71, "end": 4817.09, "word": " regression", "probability": 0.88818359375 } ] }, { "id": 1406, "seek": 464704, "start": 4817.09, "end": 4819.73, "text": " was causing problems,", "tokens": [ 51664, 390, 9853, 2740, 11, 51764 ], "temperature": 0.0, "avg_logprob": -0.1899271786791607, "compression_ratio": 1.6195121951219513, "no_speech_prob": 0.0009398460388183594, "words": [ { "start": 4817.09, "end": 4817.43, "word": " was", "probability": 0.89306640625 }, { "start": 4817.43, "end": 4818.59, "word": " causing", "probability": 0.796875 }, { "start": 4818.59, "end": 4819.19, "word": " problems", "probability": 0.69140625 }, { "start": 4819.19, "end": 4819.73, "word": ",", "probability": 0.74609375 } ] }, { "id": 1407, "seek": 467482, "start": 4819.73, "end": 4821.79, "text": " but let's take", "tokens": [ 50364, 457, 718, 311, 747, 50464 ], "temperature": 0.0, "avg_logprob": -0.17563657996095258, "compression_ratio": 1.375, "no_speech_prob": 0.0021820068359375, "words": [ { "start": 4819.73, "end": 4819.95, "word": " but", "probability": 0.293212890625 }, { "start": 4819.95, "end": 4821.59, "word": " let's", "probability": 0.86962890625 }, { "start": 4821.59, "end": 4821.79, "word": " take", "probability": 0.81494140625 } ] }, { "id": 1408, "seek": 467482, "start": 4821.95, "end": 4823.73, "text": " a quick look at...", "tokens": [ 50464, 257, 1702, 574, 412, 485, 50564 ], "temperature": 0.0, "avg_logprob": -0.17563657996095258, "compression_ratio": 1.375, "no_speech_prob": 0.0021820068359375, "words": [ { "start": 4821.95, "end": 4822.29, "word": " a quick", "probability": 0.88916015625 }, { "start": 4822.29, "end": 4822.73, "word": " look", "probability": 0.91162109375 }, { "start": 4822.73, "end": 4823.73, "word": " at...", "probability": 0.566650390625 } ] }, { "id": 1409, "seek": 467482, "start": 4828.19, "end": 4829.43, "text": " Oh.", "tokens": [ 50664, 876, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.17563657996095258, "compression_ratio": 1.375, "no_speech_prob": 0.0021820068359375, "words": [ { "start": 4828.19, "end": 4828.87, "word": " Oh", "probability": 0.322265625 }, { "start": 4828.87, "end": 4829.43, "word": ".", "probability": 0.1771240234375 } ] }, { "id": 1410, "seek": 467482, "start": 4830.31, "end": 4832.45, "text": " Looks like there's some stuff missing.", "tokens": [ 50764, 10027, 411, 456, 311, 512, 1507, 5361, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.17563657996095258, "compression_ratio": 1.375, "no_speech_prob": 0.0021820068359375, "words": [ { "start": 4830.31, "end": 4830.99, "word": " Looks", "probability": 0.6806640625 }, { "start": 4830.99, "end": 4831.13, "word": " like", "probability": 0.88037109375 }, { "start": 4831.13, "end": 4831.29, "word": " there's", "probability": 0.9189453125 }, { "start": 4831.29, "end": 4831.47, "word": " some", "probability": 0.81005859375 }, { "start": 4831.47, "end": 4831.73, "word": " stuff", "probability": 0.79638671875 }, { "start": 4831.73, "end": 4832.11, "word": " missing", "probability": 0.8564453125 }, { "start": 4832.11, "end": 4832.45, "word": ".", "probability": 0.96142578125 } ] }, { "id": 1411, "seek": 467482, "start": 4837.16, "end": 4838.82, "text": " Well, that's unfortunate.", "tokens": [ 50964, 1042, 11, 300, 311, 17843, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.17563657996095258, "compression_ratio": 1.375, "no_speech_prob": 0.0021820068359375, "words": [ { "start": 4837.16, "end": 4837.5, "word": " Well", "probability": 0.5751953125 }, { "start": 4837.5, "end": 4837.5, "word": ",", "probability": 0.63671875 }, { "start": 4837.5, "end": 4837.68, "word": " that's", "probability": 0.941162109375 }, { "start": 4837.68, "end": 4838.14, "word": " unfortunate", "probability": 0.77734375 }, { "start": 4838.14, "end": 4838.82, "word": ".", "probability": 0.97021484375 } ] }, { "id": 1412, "seek": 467482, "start": 4843.0, "end": 4844.22, "text": " So I'm just going to go", "tokens": [ 51064, 407, 286, 478, 445, 516, 281, 352, 51164 ], "temperature": 0.0, "avg_logprob": -0.17563657996095258, "compression_ratio": 1.375, "no_speech_prob": 0.0021820068359375, "words": [ { "start": 4843.0, "end": 4843.68, "word": " So", "probability": 0.8134765625 }, { "start": 4843.68, "end": 4843.76, "word": " I'm", "probability": 0.903564453125 }, { "start": 4843.76, "end": 4843.92, "word": " just", "probability": 0.880859375 }, { "start": 4843.92, "end": 4844.04, "word": " going", "probability": 0.380126953125 }, { "start": 4844.04, "end": 4844.08, "word": " to", "probability": 0.90380859375 }, { "start": 4844.08, "end": 4844.22, "word": " go", "probability": 0.89404296875 } ] }, { "id": 1413, "seek": 467482, "start": 4844.22, "end": 4846.12, "text": " ahead and create new code", "tokens": [ 51164, 2286, 293, 1884, 777, 3089, 51264 ], "temperature": 0.0, "avg_logprob": -0.17563657996095258, "compression_ratio": 1.375, "no_speech_prob": 0.0021820068359375, "words": [ { "start": 4844.22, "end": 4844.48, "word": " ahead", "probability": 0.85107421875 }, { "start": 4844.48, "end": 4844.9, "word": " and", "probability": 0.8916015625 }, { "start": 4844.9, "end": 4845.28, "word": " create", "probability": 0.83740234375 }, { "start": 4845.28, "end": 4845.92, "word": " new", "probability": 0.8046875 }, { "start": 4845.92, "end": 4846.12, "word": " code", "probability": 0.8076171875 } ] }, { "id": 1414, "seek": 467482, "start": 4846.12, "end": 4848.22, "text": " blocks. I'm just going", "tokens": [ 51264, 8474, 13, 286, 478, 445, 516, 51364 ], "temperature": 0.0, "avg_logprob": -0.17563657996095258, "compression_ratio": 1.375, "no_speech_prob": 0.0021820068359375, "words": [ { "start": 4846.12, "end": 4846.5, "word": " blocks", "probability": 0.76708984375 }, { "start": 4846.5, "end": 4847.18, "word": ".", "probability": 0.83203125 }, { "start": 4847.7, "end": 4847.96, "word": " I'm", "probability": 0.906982421875 }, { "start": 4847.96, "end": 4848.08, "word": " just", "probability": 0.87158203125 }, { "start": 4848.08, "end": 4848.22, "word": " going", "probability": 0.80224609375 } ] }, { "id": 1415, "seek": 467482, "start": 4848.22, "end": 4849.82, "text": " to copy the code we had", "tokens": [ 51364, 281, 5055, 264, 3089, 321, 632, 51464 ], "temperature": 0.0, "avg_logprob": -0.17563657996095258, "compression_ratio": 1.375, "no_speech_prob": 0.0021820068359375, "words": [ { "start": 4848.22, "end": 4848.4, "word": " to", "probability": 0.91064453125 }, { "start": 4848.4, "end": 4848.74, "word": " copy", "probability": 0.8134765625 }, { "start": 4848.74, "end": 4848.94, "word": " the", "probability": 0.80859375 }, { "start": 4848.94, "end": 4849.18, "word": " code", "probability": 0.82177734375 }, { "start": 4849.18, "end": 4849.36, "word": " we", "probability": 0.8955078125 }, { "start": 4849.36, "end": 4849.82, "word": " had", "probability": 0.81201171875 } ] }, { "id": 1416, "seek": 467482, "start": 4851.82, "end": 4854.2, "text": " from task 6D", "tokens": [ 51564, 490, 5633, 1386, 35, 51664 ], "temperature": 0.0, "avg_logprob": -0.17563657996095258, "compression_ratio": 1.375, "no_speech_prob": 0.0021820068359375, "words": [ { "start": 4851.82, "end": 4852.5, "word": " from", "probability": 0.7529296875 }, { "start": 4852.5, "end": 4853.18, "word": " task", "probability": 0.486572265625 }, { "start": 4853.18, "end": 4854.2, "word": " 6D", "probability": 0.73486328125 } ] }, { "id": 1417, "seek": 467482, "start": 4854.2, "end": 4855.94, "text": " and 6C.", "tokens": [ 51664, 293, 1386, 34, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.17563657996095258, "compression_ratio": 1.375, "no_speech_prob": 0.0021820068359375, "words": [ { "start": 4854.2, "end": 4854.52, "word": " and", "probability": 0.89208984375 }, { "start": 4854.52, "end": 4855.26, "word": " 6C", "probability": 0.990966796875 }, { "start": 4855.26, "end": 4855.94, "word": ".", "probability": 0.94677734375 } ] }, { "id": 1418, "seek": 470480, "start": 4857.08, "end": 4858.76, "text": " I apologize for scrolling", "tokens": [ 50414, 286, 12328, 337, 29053, 50514 ], "temperature": 0.0, "avg_logprob": -0.15794836567795795, "compression_ratio": 1.4180790960451977, "no_speech_prob": 0.00400543212890625, "words": [ { "start": 4857.08, "end": 4857.72, "word": " I", "probability": 0.197021484375 }, { "start": 4857.72, "end": 4858.1, "word": " apologize", "probability": 0.71533203125 }, { "start": 4858.1, "end": 4858.42, "word": " for", "probability": 0.89404296875 }, { "start": 4858.42, "end": 4858.76, "word": " scrolling", "probability": 0.81884765625 } ] }, { "id": 1419, "seek": 470480, "start": 4858.76, "end": 4860.22, "text": " so fast.", "tokens": [ 50514, 370, 2370, 13, 50614 ], "temperature": 0.0, "avg_logprob": -0.15794836567795795, "compression_ratio": 1.4180790960451977, "no_speech_prob": 0.00400543212890625, "words": [ { "start": 4858.76, "end": 4859.06, "word": " so", "probability": 0.892578125 }, { "start": 4859.06, "end": 4859.58, "word": " fast", "probability": 0.8037109375 }, { "start": 4859.58, "end": 4860.22, "word": ".", "probability": 0.7275390625 } ] }, { "id": 1420, "seek": 470480, "start": 4861.3, "end": 4862.86, "text": " So let's go ahead", "tokens": [ 50614, 407, 718, 311, 352, 2286, 50714 ], "temperature": 0.0, "avg_logprob": -0.15794836567795795, "compression_ratio": 1.4180790960451977, "no_speech_prob": 0.00400543212890625, "words": [ { "start": 4861.3, "end": 4861.94, "word": " So", "probability": 0.64208984375 }, { "start": 4861.94, "end": 4862.24, "word": " let's", "probability": 0.8154296875 }, { "start": 4862.24, "end": 4862.4, "word": " go", "probability": 0.90771484375 }, { "start": 4862.4, "end": 4862.86, "word": " ahead", "probability": 0.8173828125 } ] }, { "id": 1421, "seek": 470480, "start": 4862.86, "end": 4864.9, "text": " and grab all of that,", "tokens": [ 50714, 293, 4444, 439, 295, 300, 11, 50814 ], "temperature": 0.0, "avg_logprob": -0.15794836567795795, "compression_ratio": 1.4180790960451977, "no_speech_prob": 0.00400543212890625, "words": [ { "start": 4862.86, "end": 4863.26, "word": " and", "probability": 0.265869140625 }, { "start": 4863.26, "end": 4863.62, "word": " grab", "probability": 0.71044921875 }, { "start": 4863.62, "end": 4863.94, "word": " all", "probability": 0.888671875 }, { "start": 4863.94, "end": 4864.12, "word": " of", "probability": 0.87646484375 }, { "start": 4864.12, "end": 4864.46, "word": " that", "probability": 0.8828125 }, { "start": 4864.46, "end": 4864.9, "word": ",", "probability": 0.4990234375 } ] }, { "id": 1422, "seek": 470480, "start": 4864.9, "end": 4867.04, "text": " paste it in, run it.", "tokens": [ 50814, 9163, 309, 294, 11, 1190, 309, 13, 50914 ], "temperature": 0.0, "avg_logprob": -0.15794836567795795, "compression_ratio": 1.4180790960451977, "no_speech_prob": 0.00400543212890625, "words": [ { "start": 4864.9, "end": 4865.32, "word": " paste", "probability": 0.60791015625 }, { "start": 4865.32, "end": 4865.48, "word": " it", "probability": 0.89892578125 }, { "start": 4865.48, "end": 4865.7, "word": " in", "probability": 0.900390625 }, { "start": 4865.7, "end": 4865.94, "word": ",", "probability": 0.828125 }, { "start": 4865.94, "end": 4866.18, "word": " run", "probability": 0.71044921875 }, { "start": 4866.18, "end": 4866.4, "word": " it", "probability": 0.90185546875 }, { "start": 4866.4, "end": 4867.04, "word": ".", "probability": 0.8134765625 } ] }, { "id": 1423, "seek": 470480, "start": 4867.94, "end": 4868.9, "text": " Logistic regression", "tokens": [ 50914, 10824, 3142, 24590, 51014 ], "temperature": 0.0, "avg_logprob": -0.15794836567795795, "compression_ratio": 1.4180790960451977, "no_speech_prob": 0.00400543212890625, "words": [ { "start": 4867.94, "end": 4868.44, "word": " Logistic", "probability": 0.78466796875 }, { "start": 4868.44, "end": 4868.9, "word": " regression", "probability": 0.82666015625 } ] }, { "id": 1424, "seek": 470480, "start": 4868.9, "end": 4870.46, "text": " is not defined.", "tokens": [ 51014, 307, 406, 7642, 13, 51114 ], "temperature": 0.0, "avg_logprob": -0.15794836567795795, "compression_ratio": 1.4180790960451977, "no_speech_prob": 0.00400543212890625, "words": [ { "start": 4868.9, "end": 4869.12, "word": " is", "probability": 0.8759765625 }, { "start": 4869.12, "end": 4869.3, "word": " not", "probability": 0.912109375 }, { "start": 4869.3, "end": 4869.82, "word": " defined", "probability": 0.7490234375 }, { "start": 4869.82, "end": 4870.46, "word": ".", "probability": 0.87744140625 } ] }, { "id": 1425, "seek": 470480, "start": 4872.0, "end": 4873.18, "text": " That's weird.", "tokens": [ 51114, 663, 311, 3657, 13, 51214 ], "temperature": 0.0, "avg_logprob": -0.15794836567795795, "compression_ratio": 1.4180790960451977, "no_speech_prob": 0.00400543212890625, "words": [ { "start": 4872.0, "end": 4872.54, "word": " That's", "probability": 0.866943359375 }, { "start": 4872.54, "end": 4872.86, "word": " weird", "probability": 0.87060546875 }, { "start": 4872.86, "end": 4873.18, "word": ".", "probability": 0.97802734375 } ] }, { "id": 1426, "seek": 470480, "start": 4877.24, "end": 4878.86, "text": " Oh, it's not even in here.", "tokens": [ 51414, 876, 11, 309, 311, 406, 754, 294, 510, 13, 51514 ], "temperature": 0.0, "avg_logprob": -0.15794836567795795, "compression_ratio": 1.4180790960451977, "no_speech_prob": 0.00400543212890625, "words": [ { "start": 4877.24, "end": 4877.88, "word": " Oh", "probability": 0.8193359375 }, { "start": 4877.88, "end": 4877.92, "word": ",", "probability": 0.8232421875 }, { "start": 4877.92, "end": 4878.04, "word": " it's", "probability": 0.941162109375 }, { "start": 4878.04, "end": 4878.18, "word": " not", "probability": 0.88720703125 }, { "start": 4878.18, "end": 4878.38, "word": " even", "probability": 0.822265625 }, { "start": 4878.38, "end": 4878.52, "word": " in", "probability": 0.83447265625 }, { "start": 4878.52, "end": 4878.7, "word": " here", "probability": 0.81005859375 }, { "start": 4878.7, "end": 4878.86, "word": ".", "probability": 0.91064453125 } ] }, { "id": 1427, "seek": 470480, "start": 4878.86, "end": 4881.44, "text": " That is something I'm going to have to fix.", "tokens": [ 51514, 663, 307, 746, 286, 478, 516, 281, 362, 281, 3191, 13, 51614 ], "temperature": 0.0, "avg_logprob": -0.15794836567795795, "compression_ratio": 1.4180790960451977, "no_speech_prob": 0.00400543212890625, "words": [ { "start": 4878.86, "end": 4879.04, "word": " That", "probability": 0.7705078125 }, { "start": 4879.04, "end": 4879.78, "word": " is", "probability": 0.87158203125 }, { "start": 4879.78, "end": 4880.0, "word": " something", "probability": 0.74853515625 }, { "start": 4880.0, "end": 4880.22, "word": " I'm", "probability": 0.9697265625 }, { "start": 4880.22, "end": 4880.22, "word": " going", "probability": 0.53076171875 }, { "start": 4880.22, "end": 4880.28, "word": " to", "probability": 0.900390625 }, { "start": 4880.28, "end": 4880.42, "word": " have", "probability": 0.87939453125 }, { "start": 4880.42, "end": 4880.54, "word": " to", "probability": 0.90234375 }, { "start": 4880.54, "end": 4880.86, "word": " fix", "probability": 0.9091796875 }, { "start": 4880.86, "end": 4881.44, "word": ".", "probability": 0.900390625 } ] }, { "id": 1428, "seek": 470480, "start": 4881.44, "end": 4883.4, "text": " I'm not sure... Oh.", "tokens": [ 51614, 286, 478, 406, 988, 485, 876, 13, 51714 ], "temperature": 0.0, "avg_logprob": -0.15794836567795795, "compression_ratio": 1.4180790960451977, "no_speech_prob": 0.00400543212890625, "words": [ { "start": 4881.44, "end": 4881.56, "word": " I'm", "probability": 0.96435546875 }, { "start": 4881.56, "end": 4881.78, "word": " not", "probability": 0.892578125 }, { "start": 4881.78, "end": 4882.5, "word": " sure...", "probability": 0.46893310546875 }, { "start": 4882.5, "end": 4882.76, "word": " Oh", "probability": 0.552734375 }, { "start": 4882.76, "end": 4883.4, "word": ".", "probability": 0.314697265625 } ] }, { "id": 1429, "seek": 470480, "start": 4884.64, "end": 4885.92, "text": " Because that's", "tokens": [ 51714, 1436, 300, 311, 51814 ], "temperature": 0.0, "avg_logprob": -0.15794836567795795, "compression_ratio": 1.4180790960451977, "no_speech_prob": 0.00400543212890625, "words": [ { "start": 4884.64, "end": 4885.28, "word": " Because", "probability": 0.59033203125 }, { "start": 4885.28, "end": 4885.92, "word": " that's", "probability": 0.9345703125 } ] }, { "id": 1430, "seek": 473304, "start": 4885.92, "end": 4887.22, "text": " a whole different workbook.", "tokens": [ 50364, 257, 1379, 819, 589, 2939, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.19883241954740588, "compression_ratio": 1.4406779661016949, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4885.92, "end": 4886.1, "word": " a whole", "probability": 0.64306640625 }, { "start": 4886.1, "end": 4886.38, "word": " different", "probability": 0.677734375 }, { "start": 4886.38, "end": 4886.88, "word": " workbook", "probability": 0.90380859375 }, { "start": 4886.88, "end": 4887.22, "word": ".", "probability": 0.77587890625 } ] }, { "id": 1431, "seek": 473304, "start": 4887.22, "end": 4889.54, "text": " I need complete spam filter", "tokens": [ 50464, 286, 643, 3566, 24028, 6608, 50564 ], "temperature": 0.0, "avg_logprob": -0.19883241954740588, "compression_ratio": 1.4406779661016949, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4887.22, "end": 4887.32, "word": " I", "probability": 0.90283203125 }, { "start": 4887.32, "end": 4887.66, "word": " need", "probability": 0.76953125 }, { "start": 4887.66, "end": 4888.8, "word": " complete", "probability": 0.37353515625 }, { "start": 4888.8, "end": 4889.16, "word": " spam", "probability": 0.546875 }, { "start": 4889.16, "end": 4889.54, "word": " filter", "probability": 0.80810546875 } ] }, { "id": 1432, "seek": 473304, "start": 4889.54, "end": 4892.64, "text": " sklearn. That's the one that I need.", "tokens": [ 50564, 1110, 306, 1083, 13, 663, 311, 264, 472, 300, 286, 643, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.19883241954740588, "compression_ratio": 1.4406779661016949, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4889.54, "end": 4890.36, "word": " sklearn", "probability": 0.7352701822916666 }, { "start": 4890.36, "end": 4890.96, "word": ".", "probability": 0.6318359375 }, { "start": 4890.96, "end": 4891.3, "word": " That's", "probability": 0.89599609375 }, { "start": 4891.3, "end": 4891.4, "word": " the", "probability": 0.814453125 }, { "start": 4891.4, "end": 4891.54, "word": " one", "probability": 0.82958984375 }, { "start": 4891.54, "end": 4891.64, "word": " that", "probability": 0.849609375 }, { "start": 4891.64, "end": 4891.76, "word": " I", "probability": 0.9970703125 }, { "start": 4891.76, "end": 4891.98, "word": " need", "probability": 0.802734375 }, { "start": 4891.98, "end": 4892.64, "word": ".", "probability": 0.9453125 } ] }, { "id": 1433, "seek": 473304, "start": 4893.84, "end": 4895.56, "text": " My mistake.", "tokens": [ 50764, 1222, 6146, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.19883241954740588, "compression_ratio": 1.4406779661016949, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4893.84, "end": 4894.5, "word": " My", "probability": 0.7822265625 }, { "start": 4894.5, "end": 4894.9, "word": " mistake", "probability": 0.92626953125 }, { "start": 4894.9, "end": 4895.56, "word": ".", "probability": 0.8642578125 } ] }, { "id": 1434, "seek": 473304, "start": 4896.1, "end": 4897.8, "text": " So kernel, restart,", "tokens": [ 50864, 407, 28256, 11, 21022, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.19883241954740588, "compression_ratio": 1.4406779661016949, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4896.1, "end": 4896.66, "word": " So", "probability": 0.80712890625 }, { "start": 4896.66, "end": 4896.94, "word": " kernel", "probability": 0.61328125 }, { "start": 4896.94, "end": 4897.22, "word": ",", "probability": 0.323486328125 }, { "start": 4897.22, "end": 4897.66, "word": " restart", "probability": 0.826171875 }, { "start": 4897.66, "end": 4897.8, "word": ",", "probability": 0.56982421875 } ] }, { "id": 1435, "seek": 473304, "start": 4897.8, "end": 4898.92, "text": " run all.", "tokens": [ 50964, 1190, 439, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.19883241954740588, "compression_ratio": 1.4406779661016949, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4897.8, "end": 4897.94, "word": " run", "probability": 0.8828125 }, { "start": 4897.94, "end": 4898.26, "word": " all", "probability": 0.8720703125 }, { "start": 4898.26, "end": 4898.92, "word": ".", "probability": 0.9150390625 } ] }, { "id": 1436, "seek": 473304, "start": 4901.88, "end": 4903.4, "text": " So this is going to run", "tokens": [ 51164, 407, 341, 307, 516, 281, 1190, 51264 ], "temperature": 0.0, "avg_logprob": -0.19883241954740588, "compression_ratio": 1.4406779661016949, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4901.88, "end": 4902.54, "word": " So", "probability": 0.316650390625 }, { "start": 4902.54, "end": 4902.68, "word": " this", "probability": 0.8662109375 }, { "start": 4902.68, "end": 4902.8, "word": " is", "probability": 0.90087890625 }, { "start": 4902.8, "end": 4902.96, "word": " going", "probability": 0.86181640625 }, { "start": 4902.96, "end": 4903.14, "word": " to", "probability": 0.904296875 }, { "start": 4903.14, "end": 4903.4, "word": " run", "probability": 0.89111328125 } ] }, { "id": 1437, "seek": 473304, "start": 4903.4, "end": 4904.8, "text": " all of them.", "tokens": [ 51264, 439, 295, 552, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.19883241954740588, "compression_ratio": 1.4406779661016949, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4903.4, "end": 4903.72, "word": " all", "probability": 0.8896484375 }, { "start": 4903.72, "end": 4903.88, "word": " of", "probability": 0.9013671875 }, { "start": 4903.88, "end": 4904.14, "word": " them", "probability": 0.7431640625 }, { "start": 4904.14, "end": 4904.8, "word": ".", "probability": 0.962890625 } ] }, { "id": 1438, "seek": 473304, "start": 4906.0, "end": 4907.58, "text": " Let's see where it", "tokens": [ 51364, 961, 311, 536, 689, 309, 51464 ], "temperature": 0.0, "avg_logprob": -0.19883241954740588, "compression_ratio": 1.4406779661016949, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4906.0, "end": 4906.66, "word": " Let's", "probability": 0.939697265625 }, { "start": 4906.66, "end": 4906.94, "word": " see", "probability": 0.82275390625 }, { "start": 4906.94, "end": 4907.3, "word": " where", "probability": 0.904296875 }, { "start": 4907.3, "end": 4907.58, "word": " it", "probability": 0.90478515625 } ] }, { "id": 1439, "seek": 473304, "start": 4907.58, "end": 4909.1, "text": " gets stuck.", "tokens": [ 51464, 2170, 5541, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.19883241954740588, "compression_ratio": 1.4406779661016949, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4907.58, "end": 4907.98, "word": " gets", "probability": 0.78076171875 }, { "start": 4907.98, "end": 4908.44, "word": " stuck", "probability": 0.7998046875 }, { "start": 4908.44, "end": 4909.1, "word": ".", "probability": 0.8916015625 } ] }, { "id": 1440, "seek": 473304, "start": 4909.76, "end": 4911.48, "text": " Prints out the emails.", "tokens": [ 51564, 2114, 8654, 484, 264, 12524, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.19883241954740588, "compression_ratio": 1.4406779661016949, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4909.76, "end": 4910.1, "word": " Prints", "probability": 0.6937255859375 }, { "start": 4910.1, "end": 4910.26, "word": " out", "probability": 0.75732421875 }, { "start": 4910.26, "end": 4910.4, "word": " the", "probability": 0.76220703125 }, { "start": 4910.4, "end": 4910.82, "word": " emails", "probability": 0.7607421875 }, { "start": 4910.82, "end": 4911.48, "word": ".", "probability": 0.8056640625 } ] }, { "id": 1441, "seek": 473304, "start": 4912.34, "end": 4914.16, "text": " It's training the vectorizers.", "tokens": [ 51664, 467, 311, 3097, 264, 8062, 22525, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.19883241954740588, "compression_ratio": 1.4406779661016949, "no_speech_prob": 0.1602783203125, "words": [ { "start": 4912.34, "end": 4913.0, "word": " It's", "probability": 0.91650390625 }, { "start": 4913.0, "end": 4913.24, "word": " training", "probability": 0.77392578125 }, { "start": 4913.24, "end": 4913.4, "word": " the", "probability": 0.791015625 }, { "start": 4913.4, "end": 4913.96, "word": " vectorizers", "probability": 0.93359375 }, { "start": 4913.96, "end": 4914.16, "word": ".", "probability": 0.751953125 } ] }, { "id": 1442, "seek": 476074, "start": 4914.16, "end": 4916.78, "text": " I remember that took about a minute or so.", "tokens": [ 50364, 286, 1604, 300, 1890, 466, 257, 3456, 420, 370, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.1743574716220392, "compression_ratio": 1.537313432835821, "no_speech_prob": 0.06561279296875, "words": [ { "start": 4914.16, "end": 4914.34, "word": " I", "probability": 0.0504150390625 }, { "start": 4914.34, "end": 4914.36, "word": " remember", "probability": 0.460693359375 }, { "start": 4914.36, "end": 4914.6, "word": " that", "probability": 0.87744140625 }, { "start": 4914.6, "end": 4914.88, "word": " took", "probability": 0.84912109375 }, { "start": 4914.88, "end": 4915.48, "word": " about", "probability": 0.7529296875 }, { "start": 4915.6, "end": 4915.78, "word": " a minute", "probability": 0.8779296875 }, { "start": 4915.78, "end": 4915.96, "word": " or", "probability": 0.90283203125 }, { "start": 4915.96, "end": 4916.26, "word": " so", "probability": 0.90966796875 }, { "start": 4916.26, "end": 4916.78, "word": ".", "probability": 0.806640625 } ] }, { "id": 1443, "seek": 476074, "start": 4919.0, "end": 4920.14, "text": " But what we want", "tokens": [ 50564, 583, 437, 321, 528, 50664 ], "temperature": 0.0, "avg_logprob": -0.1743574716220392, "compression_ratio": 1.537313432835821, "no_speech_prob": 0.06561279296875, "words": [ { "start": 4919.0, "end": 4919.52, "word": " But", "probability": 0.8623046875 }, { "start": 4919.52, "end": 4919.74, "word": " what", "probability": 0.8310546875 }, { "start": 4919.74, "end": 4919.9, "word": " we", "probability": 0.90869140625 }, { "start": 4919.9, "end": 4920.14, "word": " want", "probability": 0.8095703125 } ] }, { "id": 1444, "seek": 476074, "start": 4920.14, "end": 4920.82, "text": " to see", "tokens": [ 50664, 281, 536, 50764 ], "temperature": 0.0, "avg_logprob": -0.1743574716220392, "compression_ratio": 1.537313432835821, "no_speech_prob": 0.06561279296875, "words": [ { "start": 4920.14, "end": 4920.32, "word": " to", "probability": 0.90966796875 }, { "start": 4920.32, "end": 4920.82, "word": " see", "probability": 0.82275390625 } ] }, { "id": 1445, "seek": 476074, "start": 4922.66, "end": 4924.78, "text": " after task 6D,", "tokens": [ 50764, 934, 5633, 1386, 35, 11, 50864 ], "temperature": 0.0, "avg_logprob": -0.1743574716220392, "compression_ratio": 1.537313432835821, "no_speech_prob": 0.06561279296875, "words": [ { "start": 4922.66, "end": 4923.18, "word": " after", "probability": 0.6279296875 }, { "start": 4923.18, "end": 4923.62, "word": " task", "probability": 0.6259765625 }, { "start": 4923.62, "end": 4924.32, "word": " 6D", "probability": 0.751708984375 }, { "start": 4924.32, "end": 4924.78, "word": ",", "probability": 0.7353515625 } ] }, { "id": 1446, "seek": 476074, "start": 4924.78, "end": 4926.92, "text": " we'll look at 6C and 6D,", "tokens": [ 50864, 321, 603, 574, 412, 1386, 34, 293, 1386, 35, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.1743574716220392, "compression_ratio": 1.537313432835821, "no_speech_prob": 0.06561279296875, "words": [ { "start": 4924.78, "end": 4925.04, "word": " we'll", "probability": 0.580078125 }, { "start": 4925.04, "end": 4925.16, "word": " look", "probability": 0.9150390625 }, { "start": 4925.16, "end": 4925.28, "word": " at", "probability": 0.9052734375 }, { "start": 4925.28, "end": 4925.64, "word": " 6C", "probability": 0.690673828125 }, { "start": 4925.64, "end": 4925.76, "word": " and", "probability": 0.8779296875 }, { "start": 4925.76, "end": 4926.22, "word": " 6D", "probability": 0.99560546875 }, { "start": 4926.22, "end": 4926.92, "word": ",", "probability": 0.56005859375 } ] }, { "id": 1447, "seek": 476074, "start": 4926.92, "end": 4928.24, "text": " is at the end", "tokens": [ 50964, 307, 412, 264, 917, 51064 ], "temperature": 0.0, "avg_logprob": -0.1743574716220392, "compression_ratio": 1.537313432835821, "no_speech_prob": 0.06561279296875, "words": [ { "start": 4926.92, "end": 4927.72, "word": " is", "probability": 0.88037109375 }, { "start": 4927.72, "end": 4927.98, "word": " at", "probability": 0.83349609375 }, { "start": 4927.98, "end": 4928.12, "word": " the", "probability": 0.81591796875 }, { "start": 4928.12, "end": 4928.24, "word": " end", "probability": 0.80908203125 } ] }, { "id": 1448, "seek": 476074, "start": 4928.24, "end": 4929.88, "text": " of this, what we're going to do is", "tokens": [ 51064, 295, 341, 11, 437, 321, 434, 516, 281, 360, 307, 51164 ], "temperature": 0.0, "avg_logprob": -0.1743574716220392, "compression_ratio": 1.537313432835821, "no_speech_prob": 0.06561279296875, "words": [ { "start": 4928.24, "end": 4928.36, "word": " of", "probability": 0.904296875 }, { "start": 4928.36, "end": 4928.56, "word": " this", "probability": 0.87890625 }, { "start": 4928.56, "end": 4928.64, "word": ",", "probability": 0.5791015625 }, { "start": 4928.64, "end": 4928.72, "word": " what", "probability": 0.884765625 }, { "start": 4928.72, "end": 4928.88, "word": " we're", "probability": 0.92626953125 }, { "start": 4928.88, "end": 4928.96, "word": " going", "probability": 0.3349609375 }, { "start": 4928.96, "end": 4929.06, "word": " to", "probability": 0.90576171875 }, { "start": 4929.06, "end": 4929.34, "word": " do", "probability": 0.90283203125 }, { "start": 4929.34, "end": 4929.88, "word": " is", "probability": 0.89794921875 } ] }, { "id": 1449, "seek": 476074, "start": 4929.88, "end": 4932.1, "text": " grab a spam", "tokens": [ 51164, 4444, 257, 24028, 51264 ], "temperature": 0.0, "avg_logprob": -0.1743574716220392, "compression_ratio": 1.537313432835821, "no_speech_prob": 0.06561279296875, "words": [ { "start": 4929.88, "end": 4930.54, "word": " grab", "probability": 0.814453125 }, { "start": 4931.24, "end": 4932.1, "word": " a spam", "probability": 0.91845703125 } ] }, { "id": 1450, "seek": 476074, "start": 4932.1, "end": 4934.18, "text": " email. This one is actually one that I grabbed", "tokens": [ 51264, 3796, 13, 639, 472, 307, 767, 472, 300, 286, 18607, 51364 ], "temperature": 0.0, "avg_logprob": -0.1743574716220392, "compression_ratio": 1.537313432835821, "no_speech_prob": 0.06561279296875, "words": [ { "start": 4932.1, "end": 4932.38, "word": " email", "probability": 0.87744140625 }, { "start": 4932.38, "end": 4932.56, "word": ".", "probability": 0.9375 }, { "start": 4932.56, "end": 4932.7, "word": " This", "probability": 0.80908203125 }, { "start": 4932.7, "end": 4932.88, "word": " one", "probability": 0.80322265625 }, { "start": 4932.88, "end": 4933.0, "word": " is", "probability": 0.90380859375 }, { "start": 4933.0, "end": 4933.24, "word": " actually", "probability": 0.79248046875 }, { "start": 4933.24, "end": 4933.46, "word": " one", "probability": 0.80615234375 }, { "start": 4933.46, "end": 4933.7, "word": " that", "probability": 0.87646484375 }, { "start": 4933.7, "end": 4933.88, "word": " I", "probability": 0.9970703125 }, { "start": 4933.88, "end": 4934.18, "word": " grabbed", "probability": 0.81787109375 } ] }, { "id": 1451, "seek": 476074, "start": 4934.18, "end": 4935.72, "text": " directly from my spam box", "tokens": [ 51364, 3838, 490, 452, 24028, 2424, 51464 ], "temperature": 0.0, "avg_logprob": -0.1743574716220392, "compression_ratio": 1.537313432835821, "no_speech_prob": 0.06561279296875, "words": [ { "start": 4934.18, "end": 4934.58, "word": " directly", "probability": 0.75146484375 }, { "start": 4934.58, "end": 4934.82, "word": " from", "probability": 0.8232421875 }, { "start": 4934.82, "end": 4935.04, "word": " my", "probability": 0.8876953125 }, { "start": 4935.04, "end": 4935.3, "word": " spam", "probability": 0.83349609375 }, { "start": 4935.3, "end": 4935.72, "word": " box", "probability": 0.81884765625 } ] }, { "id": 1452, "seek": 476074, "start": 4936.38, "end": 4937.68, "text": " last year.", "tokens": [ 51464, 1036, 1064, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.1743574716220392, "compression_ratio": 1.537313432835821, "no_speech_prob": 0.06561279296875, "words": [ { "start": 4936.38, "end": 4936.9, "word": " last", "probability": 0.783203125 }, { "start": 4936.9, "end": 4937.16, "word": " year", "probability": 0.88330078125 }, { "start": 4937.16, "end": 4937.68, "word": ".", "probability": 0.794921875 } ] }, { "id": 1453, "seek": 476074, "start": 4938.02, "end": 4940.06, "text": " And I like it because we can use", "tokens": [ 51564, 400, 286, 411, 309, 570, 321, 393, 764, 51664 ], "temperature": 0.0, "avg_logprob": -0.1743574716220392, "compression_ratio": 1.537313432835821, "no_speech_prob": 0.06561279296875, "words": [ { "start": 4938.02, "end": 4938.54, "word": " And", "probability": 0.857421875 }, { "start": 4938.54, "end": 4938.62, "word": " I", "probability": 0.99755859375 }, { "start": 4938.62, "end": 4938.8, "word": " like", "probability": 0.875 }, { "start": 4938.8, "end": 4938.92, "word": " it", "probability": 0.90380859375 }, { "start": 4938.92, "end": 4939.2, "word": " because", "probability": 0.7841796875 }, { "start": 4939.2, "end": 4939.6, "word": " we", "probability": 0.90283203125 }, { "start": 4939.6, "end": 4939.74, "word": " can", "probability": 0.89111328125 }, { "start": 4939.74, "end": 4940.06, "word": " use", "probability": 0.83740234375 } ] }, { "id": 1454, "seek": 476074, "start": 4940.06, "end": 4941.86, "text": " our spam email predictor", "tokens": [ 51664, 527, 24028, 3796, 6069, 284, 51764 ], "temperature": 0.0, "avg_logprob": -0.1743574716220392, "compression_ratio": 1.537313432835821, "no_speech_prob": 0.06561279296875, "words": [ { "start": 4940.06, "end": 4940.5, "word": " our", "probability": 0.82763671875 }, { "start": 4940.5, "end": 4940.94, "word": " spam", "probability": 0.89013671875 }, { "start": 4940.94, "end": 4941.22, "word": " email", "probability": 0.91015625 }, { "start": 4941.22, "end": 4941.86, "word": " predictor", "probability": 0.850341796875 } ] }, { "id": 1455, "seek": 478852, "start": 4941.86, "end": 4943.68, "text": " to identify whether or not", "tokens": [ 50364, 281, 5876, 1968, 420, 406, 50464 ], "temperature": 0.0, "avg_logprob": -0.19638761850672032, "compression_ratio": 1.5919282511210762, "no_speech_prob": 0.00757598876953125, "words": [ { "start": 4941.86, "end": 4942.58, "word": " to", "probability": 0.5078125 }, { "start": 4942.58, "end": 4943.16, "word": " identify", "probability": 0.84912109375 }, { "start": 4943.16, "end": 4943.42, "word": " whether", "probability": 0.83447265625 }, { "start": 4943.42, "end": 4943.56, "word": " or", "probability": 0.89013671875 }, { "start": 4943.56, "end": 4943.68, "word": " not", "probability": 0.89404296875 } ] }, { "id": 1456, "seek": 478852, "start": 4943.68, "end": 4945.5, "text": " it's spam. And then we can look and", "tokens": [ 50464, 309, 311, 24028, 13, 400, 550, 321, 393, 574, 293, 50564 ], "temperature": 0.0, "avg_logprob": -0.19638761850672032, "compression_ratio": 1.5919282511210762, "no_speech_prob": 0.00757598876953125, "words": [ { "start": 4943.68, "end": 4943.86, "word": " it's", "probability": 0.9208984375 }, { "start": 4943.86, "end": 4944.18, "word": " spam", "probability": 0.931640625 }, { "start": 4944.18, "end": 4944.34, "word": ".", "probability": 0.318359375 }, { "start": 4944.34, "end": 4944.38, "word": " And", "probability": 0.7607421875 }, { "start": 4944.38, "end": 4944.5, "word": " then", "probability": 0.72119140625 }, { "start": 4944.5, "end": 4944.6, "word": " we", "probability": 0.8818359375 }, { "start": 4944.6, "end": 4944.78, "word": " can", "probability": 0.89013671875 }, { "start": 4944.78, "end": 4945.04, "word": " look", "probability": 0.9111328125 }, { "start": 4945.04, "end": 4945.5, "word": " and", "probability": 0.86962890625 } ] }, { "id": 1457, "seek": 478852, "start": 4945.5, "end": 4946.46, "text": " utilize", "tokens": [ 50564, 16117, 50664 ], "temperature": 0.0, "avg_logprob": -0.19638761850672032, "compression_ratio": 1.5919282511210762, "no_speech_prob": 0.00757598876953125, "words": [ { "start": 4945.5, "end": 4946.46, "word": " utilize", "probability": 0.7177734375 } ] }, { "id": 1458, "seek": 478852, "start": 4947.94, "end": 4949.1, "text": " any of the models", "tokens": [ 50664, 604, 295, 264, 5245, 50764 ], "temperature": 0.0, "avg_logprob": -0.19638761850672032, "compression_ratio": 1.5919282511210762, "no_speech_prob": 0.00757598876953125, "words": [ { "start": 4947.94, "end": 4948.46, "word": " any", "probability": 0.775390625 }, { "start": 4948.46, "end": 4948.6, "word": " of", "probability": 0.90625 }, { "start": 4948.6, "end": 4948.72, "word": " the", "probability": 0.8134765625 }, { "start": 4948.72, "end": 4949.1, "word": " models", "probability": 0.80615234375 } ] }, { "id": 1459, "seek": 478852, "start": 4949.1, "end": 4951.3, "text": " to really identify that.", "tokens": [ 50764, 281, 534, 5876, 300, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.19638761850672032, "compression_ratio": 1.5919282511210762, "no_speech_prob": 0.00757598876953125, "words": [ { "start": 4949.1, "end": 4949.8, "word": " to", "probability": 0.892578125 }, { "start": 4949.8, "end": 4950.0, "word": " really", "probability": 0.79052734375 }, { "start": 4950.0, "end": 4950.42, "word": " identify", "probability": 0.88916015625 }, { "start": 4950.42, "end": 4950.78, "word": " that", "probability": 0.88623046875 }, { "start": 4950.78, "end": 4951.3, "word": ".", "probability": 0.9951171875 } ] }, { "id": 1460, "seek": 478852, "start": 4953.82, "end": 4956.06, "text": " So this was supposed to be", "tokens": [ 50964, 407, 341, 390, 3442, 281, 312, 51064 ], "temperature": 0.0, "avg_logprob": -0.19638761850672032, "compression_ratio": 1.5919282511210762, "no_speech_prob": 0.00757598876953125, "words": [ { "start": 4953.82, "end": 4954.26, "word": " So", "probability": 0.83056640625 }, { "start": 4954.26, "end": 4954.56, "word": " this", "probability": 0.75732421875 }, { "start": 4954.56, "end": 4954.76, "word": " was", "probability": 0.89453125 }, { "start": 4954.76, "end": 4955.34, "word": " supposed", "probability": 0.89794921875 }, { "start": 4955.34, "end": 4955.6, "word": " to", "probability": 0.90380859375 }, { "start": 4955.6, "end": 4956.06, "word": " be", "probability": 0.8974609375 } ] }, { "id": 1461, "seek": 478852, "start": 4957.4, "end": 4958.32, "text": " a fill-in-the-blank", "tokens": [ 51064, 257, 2836, 12, 259, 12, 3322, 12, 5199, 657, 51164 ], "temperature": 0.0, "avg_logprob": -0.19638761850672032, "compression_ratio": 1.5919282511210762, "no_speech_prob": 0.00757598876953125, "words": [ { "start": 4957.4, "end": 4957.82, "word": " a fill", "probability": 0.75634765625 }, { "start": 4957.82, "end": 4957.92, "word": "-in", "probability": 0.6514892578125 }, { "start": 4957.92, "end": 4958.02, "word": "-the", "probability": 0.93798828125 }, { "start": 4958.02, "end": 4958.32, "word": "-blank", "probability": 0.9425455729166666 } ] }, { "id": 1462, "seek": 478852, "start": 4958.32, "end": 4959.8, "text": " kind of thing like we've been", "tokens": [ 51164, 733, 295, 551, 411, 321, 600, 668, 51264 ], "temperature": 0.0, "avg_logprob": -0.19638761850672032, "compression_ratio": 1.5919282511210762, "no_speech_prob": 0.00757598876953125, "words": [ { "start": 4958.32, "end": 4959.0, "word": " kind", "probability": 0.7978515625 }, { "start": 4959.0, "end": 4959.1, "word": " of", "probability": 0.90625 }, { "start": 4959.1, "end": 4959.3, "word": " thing", "probability": 0.80859375 }, { "start": 4959.3, "end": 4959.48, "word": " like", "probability": 0.599609375 }, { "start": 4959.48, "end": 4959.7, "word": " we've", "probability": 0.92138671875 }, { "start": 4959.7, "end": 4959.8, "word": " been", "probability": 0.80615234375 } ] }, { "id": 1463, "seek": 478852, "start": 4959.8, "end": 4960.98, "text": " going through.", "tokens": [ 51264, 516, 807, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.19638761850672032, "compression_ratio": 1.5919282511210762, "no_speech_prob": 0.00757598876953125, "words": [ { "start": 4959.8, "end": 4960.02, "word": " going", "probability": 0.859375 }, { "start": 4960.02, "end": 4960.46, "word": " through", "probability": 0.79150390625 }, { "start": 4960.46, "end": 4960.98, "word": ".", "probability": 0.59619140625 } ] }, { "id": 1464, "seek": 478852, "start": 4961.46, "end": 4963.16, "text": " But this last task, it just asks us", "tokens": [ 51364, 583, 341, 1036, 5633, 11, 309, 445, 8962, 505, 51464 ], "temperature": 0.0, "avg_logprob": -0.19638761850672032, "compression_ratio": 1.5919282511210762, "no_speech_prob": 0.00757598876953125, "words": [ { "start": 4961.46, "end": 4961.66, "word": " But", "probability": 0.87158203125 }, { "start": 4961.66, "end": 4961.82, "word": " this", "probability": 0.8740234375 }, { "start": 4961.82, "end": 4962.06, "word": " last", "probability": 0.8134765625 }, { "start": 4962.06, "end": 4962.36, "word": " task", "probability": 0.828125 }, { "start": 4962.36, "end": 4962.42, "word": ",", "probability": 0.70751953125 }, { "start": 4962.42, "end": 4962.48, "word": " it", "probability": 0.89599609375 }, { "start": 4962.48, "end": 4962.66, "word": " just", "probability": 0.8818359375 }, { "start": 4962.66, "end": 4962.92, "word": " asks", "probability": 0.50634765625 }, { "start": 4962.92, "end": 4963.16, "word": " us", "probability": 0.86669921875 } ] }, { "id": 1465, "seek": 478852, "start": 4963.16, "end": 4965.46, "text": " use the vectorizers and the models created to perform", "tokens": [ 51464, 764, 264, 8062, 22525, 293, 264, 5245, 2942, 281, 2042, 51564 ], "temperature": 0.0, "avg_logprob": -0.19638761850672032, "compression_ratio": 1.5919282511210762, "no_speech_prob": 0.00757598876953125, "words": [ { "start": 4963.16, "end": 4963.72, "word": " use", "probability": 0.1287841796875 }, { "start": 4963.72, "end": 4963.82, "word": " the", "probability": 0.76611328125 }, { "start": 4963.82, "end": 4964.24, "word": " vectorizers", "probability": 0.9189453125 }, { "start": 4964.24, "end": 4964.4, "word": " and", "probability": 0.467529296875 }, { "start": 4964.4, "end": 4964.5, "word": " the", "probability": 0.81396484375 }, { "start": 4964.5, "end": 4964.7, "word": " models", "probability": 0.7998046875 }, { "start": 4964.7, "end": 4965.04, "word": " created", "probability": 0.72021484375 }, { "start": 4965.04, "end": 4965.2, "word": " to", "probability": 0.88916015625 }, { "start": 4965.2, "end": 4965.46, "word": " perform", "probability": 0.7548828125 } ] }, { "id": 1466, "seek": 478852, "start": 4965.46, "end": 4967.32, "text": " predictions on the test email", "tokens": [ 51564, 21264, 322, 264, 1500, 3796, 51664 ], "temperature": 0.0, "avg_logprob": -0.19638761850672032, "compression_ratio": 1.5919282511210762, "no_speech_prob": 0.00757598876953125, "words": [ { "start": 4965.46, "end": 4965.86, "word": " predictions", "probability": 0.69873046875 }, { "start": 4965.86, "end": 4966.3, "word": " on", "probability": 0.90771484375 }, { "start": 4966.3, "end": 4966.58, "word": " the", "probability": 0.8115234375 }, { "start": 4966.58, "end": 4967.0, "word": " test", "probability": 0.80517578125 }, { "start": 4967.0, "end": 4967.32, "word": " email", "probability": 0.8662109375 } ] }, { "id": 1467, "seek": 478852, "start": 4967.84, "end": 4969.64, "text": " that we created up at the top", "tokens": [ 51664, 300, 321, 2942, 493, 412, 264, 1192, 51764 ], "temperature": 0.0, "avg_logprob": -0.19638761850672032, "compression_ratio": 1.5919282511210762, "no_speech_prob": 0.00757598876953125, "words": [ { "start": 4967.84, "end": 4968.1, "word": " that", "probability": 0.86767578125 }, { "start": 4968.1, "end": 4968.22, "word": " we", "probability": 0.9013671875 }, { "start": 4968.22, "end": 4968.54, "word": " created", "probability": 0.734375 }, { "start": 4968.54, "end": 4968.84, "word": " up", "probability": 0.9052734375 }, { "start": 4968.84, "end": 4969.18, "word": " at", "probability": 0.83984375 }, { "start": 4969.18, "end": 4969.32, "word": " the", "probability": 0.8134765625 }, { "start": 4969.32, "end": 4969.64, "word": " top", "probability": 0.81689453125 } ] }, { "id": 1468, "seek": 481606, "start": 4969.64, "end": 4971.24, "text": " and the test spam email", "tokens": [ 50364, 293, 264, 1500, 24028, 3796, 50464 ], "temperature": 0.0, "avg_logprob": -0.1610937537252903, "compression_ratio": 1.6628571428571428, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 4969.64, "end": 4970.0, "word": " and", "probability": 0.6328125 }, { "start": 4970.0, "end": 4970.2, "word": " the", "probability": 0.8095703125 }, { "start": 4970.2, "end": 4970.48, "word": " test", "probability": 0.63671875 }, { "start": 4970.48, "end": 4970.84, "word": " spam", "probability": 0.64599609375 }, { "start": 4970.84, "end": 4971.24, "word": " email", "probability": 0.888671875 } ] }, { "id": 1469, "seek": 481606, "start": 4972.4, "end": 4973.64, "text": " which is the real", "tokens": [ 50464, 597, 307, 264, 957, 50564 ], "temperature": 0.0, "avg_logprob": -0.1610937537252903, "compression_ratio": 1.6628571428571428, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 4972.4, "end": 4973.02, "word": " which", "probability": 0.342529296875 }, { "start": 4973.02, "end": 4973.18, "word": " is", "probability": 0.89990234375 }, { "start": 4973.18, "end": 4973.38, "word": " the", "probability": 0.8134765625 }, { "start": 4973.38, "end": 4973.64, "word": " real", "probability": 0.87353515625 } ] }, { "id": 1470, "seek": 481606, "start": 4973.64, "end": 4975.58, "text": " world email that I pulled from a spam", "tokens": [ 50564, 1002, 3796, 300, 286, 7373, 490, 257, 24028, 50664 ], "temperature": 0.0, "avg_logprob": -0.1610937537252903, "compression_ratio": 1.6628571428571428, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 4973.64, "end": 4973.88, "word": " world", "probability": 0.5703125 }, { "start": 4973.88, "end": 4974.18, "word": " email", "probability": 0.8955078125 }, { "start": 4974.18, "end": 4974.38, "word": " that", "probability": 0.83984375 }, { "start": 4974.38, "end": 4974.48, "word": " I", "probability": 0.953125 }, { "start": 4974.48, "end": 4974.72, "word": " pulled", "probability": 0.837890625 }, { "start": 4974.72, "end": 4975.02, "word": " from", "probability": 0.8291015625 }, { "start": 4975.32, "end": 4975.58, "word": " a spam", "probability": 0.884765625 } ] }, { "id": 1471, "seek": 481606, "start": 4975.58, "end": 4976.74, "text": " inbox.", "tokens": [ 50664, 35067, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.1610937537252903, "compression_ratio": 1.6628571428571428, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 4975.58, "end": 4976.12, "word": " inbox", "probability": 0.7587890625 }, { "start": 4976.12, "end": 4976.74, "word": ".", "probability": 0.7841796875 } ] }, { "id": 1472, "seek": 481606, "start": 4977.62, "end": 4979.6, "text": " And so what we want to do", "tokens": [ 50764, 400, 370, 437, 321, 528, 281, 360, 50864 ], "temperature": 0.0, "avg_logprob": -0.1610937537252903, "compression_ratio": 1.6628571428571428, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 4977.62, "end": 4977.66, "word": " And", "probability": 0.6982421875 }, { "start": 4977.66, "end": 4977.96, "word": " so", "probability": 0.8994140625 }, { "start": 4977.96, "end": 4978.86, "word": " what", "probability": 0.705078125 }, { "start": 4978.86, "end": 4979.06, "word": " we", "probability": 0.90625 }, { "start": 4979.06, "end": 4979.22, "word": " want", "probability": 0.6298828125 }, { "start": 4979.22, "end": 4979.32, "word": " to", "probability": 0.90673828125 }, { "start": 4979.32, "end": 4979.6, "word": " do", "probability": 0.904296875 } ] }, { "id": 1473, "seek": 481606, "start": 4979.6, "end": 4981.64, "text": " is grab that as", "tokens": [ 50864, 307, 4444, 300, 382, 50964 ], "temperature": 0.0, "avg_logprob": -0.1610937537252903, "compression_ratio": 1.6628571428571428, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 4979.6, "end": 4980.06, "word": " is", "probability": 0.90673828125 }, { "start": 4980.06, "end": 4980.96, "word": " grab", "probability": 0.826171875 }, { "start": 4980.96, "end": 4981.26, "word": " that", "probability": 0.8837890625 }, { "start": 4981.26, "end": 4981.64, "word": " as", "probability": 0.900390625 } ] }, { "id": 1474, "seek": 481606, "start": 4982.06, "end": 4983.34, "text": " a working email.", "tokens": [ 50964, 257, 1364, 3796, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.1610937537252903, "compression_ratio": 1.6628571428571428, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 4982.06, "end": 4982.46, "word": " a working", "probability": 0.71923828125 }, { "start": 4982.46, "end": 4982.86, "word": " email", "probability": 0.9169921875 }, { "start": 4982.86, "end": 4983.34, "word": ".", "probability": 0.1444091796875 } ] }, { "id": 1475, "seek": 481606, "start": 4983.34, "end": 4985.64, "text": " And this will let us change this to", "tokens": [ 51064, 400, 341, 486, 718, 505, 1319, 341, 281, 51164 ], "temperature": 0.0, "avg_logprob": -0.1610937537252903, "compression_ratio": 1.6628571428571428, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 4983.34, "end": 4983.56, "word": " And", "probability": 0.796875 }, { "start": 4983.56, "end": 4983.7, "word": " this", "probability": 0.87939453125 }, { "start": 4983.7, "end": 4983.84, "word": " will", "probability": 0.81201171875 }, { "start": 4983.84, "end": 4984.04, "word": " let", "probability": 0.904296875 }, { "start": 4984.04, "end": 4984.4, "word": " us", "probability": 0.9091796875 }, { "start": 4984.4, "end": 4985.12, "word": " change", "probability": 0.8349609375 }, { "start": 4985.12, "end": 4985.42, "word": " this", "probability": 0.88427734375 }, { "start": 4985.42, "end": 4985.64, "word": " to", "probability": 0.90478515625 } ] }, { "id": 1476, "seek": 481606, "start": 4985.64, "end": 4987.66, "text": " test email and test spam", "tokens": [ 51164, 1500, 3796, 293, 1500, 24028, 51264 ], "temperature": 0.0, "avg_logprob": -0.1610937537252903, "compression_ratio": 1.6628571428571428, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 4985.64, "end": 4986.0, "word": " test", "probability": 0.77099609375 }, { "start": 4986.0, "end": 4986.38, "word": " email", "probability": 0.8466796875 }, { "start": 4986.38, "end": 4986.62, "word": " and", "probability": 0.748046875 }, { "start": 4986.62, "end": 4987.34, "word": " test", "probability": 0.62890625 }, { "start": 4987.34, "end": 4987.66, "word": " spam", "probability": 0.90234375 } ] }, { "id": 1477, "seek": 481606, "start": 4987.66, "end": 4988.66, "text": " email.", "tokens": [ 51264, 3796, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.1610937537252903, "compression_ratio": 1.6628571428571428, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 4987.66, "end": 4988.04, "word": " email", "probability": 0.908203125 }, { "start": 4988.04, "end": 4988.66, "word": ".", "probability": 0.99072265625 } ] }, { "id": 1478, "seek": 481606, "start": 4990.2, "end": 4991.64, "text": " Remember, we want to", "tokens": [ 51364, 5459, 11, 321, 528, 281, 51464 ], "temperature": 0.0, "avg_logprob": -0.1610937537252903, "compression_ratio": 1.6628571428571428, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 4990.2, "end": 4990.82, "word": " Remember", "probability": 0.91064453125 }, { "start": 4990.82, "end": 4991.04, "word": ",", "probability": 0.427001953125 }, { "start": 4991.04, "end": 4991.26, "word": " we", "probability": 0.90673828125 }, { "start": 4991.26, "end": 4991.46, "word": " want", "probability": 0.80712890625 }, { "start": 4991.46, "end": 4991.64, "word": " to", "probability": 0.90673828125 } ] }, { "id": 1479, "seek": 481606, "start": 4991.64, "end": 4993.6, "text": " use the tf.idf", "tokens": [ 51464, 764, 264, 256, 69, 13, 327, 69, 51564 ], "temperature": 0.0, "avg_logprob": -0.1610937537252903, "compression_ratio": 1.6628571428571428, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 4991.64, "end": 4992.04, "word": " use", "probability": 0.82666015625 }, { "start": 4992.04, "end": 4992.62, "word": " the", "probability": 0.79833984375 }, { "start": 4992.62, "end": 4993.12, "word": " tf", "probability": 0.682373046875 }, { "start": 4993.12, "end": 4993.6, "word": ".idf", "probability": 0.7254231770833334 } ] }, { "id": 1480, "seek": 481606, "start": 4993.6, "end": 4995.46, "text": " and the count vectorizers", "tokens": [ 51564, 293, 264, 1207, 8062, 22525, 51664 ], "temperature": 0.0, "avg_logprob": -0.1610937537252903, "compression_ratio": 1.6628571428571428, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 4993.6, "end": 4993.92, "word": " and", "probability": 0.87939453125 }, { "start": 4993.92, "end": 4994.2, "word": " the", "probability": 0.8076171875 }, { "start": 4994.2, "end": 4994.68, "word": " count", "probability": 0.69091796875 }, { "start": 4994.68, "end": 4995.46, "word": " vectorizers", "probability": 0.912353515625 } ] }, { "id": 1481, "seek": 481606, "start": 4995.46, "end": 4997.18, "text": " in order to use", "tokens": [ 51664, 294, 1668, 281, 764, 51764 ], "temperature": 0.0, "avg_logprob": -0.1610937537252903, "compression_ratio": 1.6628571428571428, "no_speech_prob": 0.00327301025390625, "words": [ { "start": 4995.46, "end": 4996.18, "word": " in", "probability": 0.880859375 }, { "start": 4996.18, "end": 4996.32, "word": " order", "probability": 0.826171875 }, { "start": 4996.32, "end": 4996.7, "word": " to", "probability": 0.904296875 }, { "start": 4996.7, "end": 4997.18, "word": " use", "probability": 0.82421875 } ] }, { "id": 1482, "seek": 484452, "start": 4998.02, "end": 4999.6, "text": " the working email.", "tokens": [ 50364, 264, 1364, 3796, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.15057964130274712, "compression_ratio": 1.658008658008658, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 4998.02, "end": 4998.58, "word": " the", "probability": 0.0640869140625 }, { "start": 4998.58, "end": 4998.88, "word": " working", "probability": 0.6826171875 }, { "start": 4998.88, "end": 4999.26, "word": " email", "probability": 0.8857421875 }, { "start": 4999.26, "end": 4999.6, "word": ".", "probability": 0.33203125 } ] }, { "id": 1483, "seek": 484452, "start": 4999.6, "end": 5001.32, "text": " We need to use that to preprocess", "tokens": [ 50464, 492, 643, 281, 764, 300, 281, 2666, 340, 780, 50564 ], "temperature": 0.0, "avg_logprob": -0.15057964130274712, "compression_ratio": 1.658008658008658, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 4999.6, "end": 5000.0, "word": " We", "probability": 0.73583984375 }, { "start": 5000.0, "end": 5000.22, "word": " need", "probability": 0.626953125 }, { "start": 5000.22, "end": 5000.44, "word": " to", "probability": 0.908203125 }, { "start": 5000.44, "end": 5000.72, "word": " use", "probability": 0.81494140625 }, { "start": 5000.72, "end": 5000.88, "word": " that", "probability": 0.87939453125 }, { "start": 5000.88, "end": 5001.04, "word": " to", "probability": 0.8974609375 }, { "start": 5001.04, "end": 5001.32, "word": " preprocess", "probability": 0.7805989583333334 } ] }, { "id": 1484, "seek": 484452, "start": 5002.1, "end": 5003.52, "text": " and because it's", "tokens": [ 50564, 293, 570, 309, 311, 50664 ], "temperature": 0.0, "avg_logprob": -0.15057964130274712, "compression_ratio": 1.658008658008658, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 5002.1, "end": 5002.66, "word": " and", "probability": 0.38916015625 }, { "start": 5002.66, "end": 5002.92, "word": " because", "probability": 0.8232421875 }, { "start": 5002.92, "end": 5003.52, "word": " it's", "probability": 0.934814453125 } ] }, { "id": 1485, "seek": 484452, "start": 5003.96, "end": 5005.54, "text": " a string, we just wrap it in these", "tokens": [ 50664, 257, 6798, 11, 321, 445, 7019, 309, 294, 613, 50764 ], "temperature": 0.0, "avg_logprob": -0.15057964130274712, "compression_ratio": 1.658008658008658, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 5003.96, "end": 5004.28, "word": " a string", "probability": 0.7607421875 }, { "start": 5004.28, "end": 5004.6, "word": ",", "probability": 0.46923828125 }, { "start": 5004.6, "end": 5004.76, "word": " we", "probability": 0.81787109375 }, { "start": 5004.76, "end": 5004.88, "word": " just", "probability": 0.8740234375 }, { "start": 5004.88, "end": 5005.14, "word": " wrap", "probability": 0.77587890625 }, { "start": 5005.14, "end": 5005.22, "word": " it", "probability": 0.8857421875 }, { "start": 5005.22, "end": 5005.32, "word": " in", "probability": 0.90576171875 }, { "start": 5005.32, "end": 5005.54, "word": " these", "probability": 0.58544921875 } ] }, { "id": 1486, "seek": 484452, "start": 5005.54, "end": 5007.64, "text": " square brackets in order to classify", "tokens": [ 50764, 3732, 26179, 294, 1668, 281, 33872, 50864 ], "temperature": 0.0, "avg_logprob": -0.15057964130274712, "compression_ratio": 1.658008658008658, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 5005.54, "end": 5005.94, "word": " square", "probability": 0.9189453125 }, { "start": 5005.94, "end": 5006.32, "word": " brackets", "probability": 0.78662109375 }, { "start": 5006.32, "end": 5006.64, "word": " in", "probability": 0.861328125 }, { "start": 5006.64, "end": 5006.8, "word": " order", "probability": 0.82421875 }, { "start": 5006.8, "end": 5007.3, "word": " to", "probability": 0.892578125 }, { "start": 5007.3, "end": 5007.64, "word": " classify", "probability": 0.9423828125 } ] }, { "id": 1487, "seek": 484452, "start": 5007.64, "end": 5009.68, "text": " it as a list because the transform function", "tokens": [ 50864, 309, 382, 257, 1329, 570, 264, 4088, 2445, 50964 ], "temperature": 0.0, "avg_logprob": -0.15057964130274712, "compression_ratio": 1.658008658008658, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 5007.64, "end": 5007.84, "word": " it", "probability": 0.8955078125 }, { "start": 5007.84, "end": 5007.94, "word": " as", "probability": 0.91015625 }, { "start": 5008.1, "end": 5008.3, "word": " a list", "probability": 0.89306640625 }, { "start": 5008.3, "end": 5008.62, "word": " because", "probability": 0.6298828125 }, { "start": 5008.62, "end": 5008.88, "word": " the", "probability": 0.82177734375 }, { "start": 5008.88, "end": 5009.22, "word": " transform", "probability": 0.80859375 }, { "start": 5009.22, "end": 5009.68, "word": " function", "probability": 0.90087890625 } ] }, { "id": 1488, "seek": 484452, "start": 5009.68, "end": 5011.14, "text": " expects a list.", "tokens": [ 50964, 33280, 257, 1329, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.15057964130274712, "compression_ratio": 1.658008658008658, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 5009.68, "end": 5010.16, "word": " expects", "probability": 0.80615234375 }, { "start": 5010.36, "end": 5010.58, "word": " a list", "probability": 0.8828125 }, { "start": 5010.58, "end": 5011.14, "word": ".", "probability": 0.95703125 } ] }, { "id": 1489, "seek": 484452, "start": 5011.8, "end": 5013.86, "text": " We have that as test email,", "tokens": [ 51064, 492, 362, 300, 382, 1500, 3796, 11, 51164 ], "temperature": 0.0, "avg_logprob": -0.15057964130274712, "compression_ratio": 1.658008658008658, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 5011.8, "end": 5012.36, "word": " We", "probability": 0.89111328125 }, { "start": 5012.36, "end": 5012.54, "word": " have", "probability": 0.87890625 }, { "start": 5012.54, "end": 5012.74, "word": " that", "probability": 0.8876953125 }, { "start": 5012.74, "end": 5012.98, "word": " as", "probability": 0.90478515625 }, { "start": 5012.98, "end": 5013.26, "word": " test", "probability": 0.74853515625 }, { "start": 5013.26, "end": 5013.64, "word": " email", "probability": 0.501953125 }, { "start": 5013.64, "end": 5013.86, "word": ",", "probability": 0.638671875 } ] }, { "id": 1490, "seek": 484452, "start": 5013.86, "end": 5015.58, "text": " tf.idf, and test email", "tokens": [ 51164, 256, 69, 13, 327, 69, 11, 293, 1500, 3796, 51264 ], "temperature": 0.0, "avg_logprob": -0.15057964130274712, "compression_ratio": 1.658008658008658, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 5013.86, "end": 5014.14, "word": " tf", "probability": 0.7105712890625 }, { "start": 5014.14, "end": 5014.62, "word": ".idf", "probability": 0.7142333984375 }, { "start": 5014.62, "end": 5014.68, "word": ",", "probability": 0.55029296875 }, { "start": 5014.68, "end": 5014.9, "word": " and", "probability": 0.87841796875 }, { "start": 5014.9, "end": 5015.22, "word": " test", "probability": 0.80908203125 }, { "start": 5015.22, "end": 5015.58, "word": " email", "probability": 0.86083984375 } ] }, { "id": 1491, "seek": 484452, "start": 5015.58, "end": 5016.52, "text": " count.", "tokens": [ 51264, 1207, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.15057964130274712, "compression_ratio": 1.658008658008658, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 5015.58, "end": 5015.96, "word": " count", "probability": 0.68408203125 }, { "start": 5015.96, "end": 5016.52, "word": ".", "probability": 0.849609375 } ] }, { "id": 1492, "seek": 484452, "start": 5017.94, "end": 5019.62, "text": " And then we use each of our models", "tokens": [ 51364, 400, 550, 321, 764, 1184, 295, 527, 5245, 51464 ], "temperature": 0.0, "avg_logprob": -0.15057964130274712, "compression_ratio": 1.658008658008658, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 5017.94, "end": 5018.5, "word": " And", "probability": 0.75634765625 }, { "start": 5018.5, "end": 5018.58, "word": " then", "probability": 0.72119140625 }, { "start": 5018.58, "end": 5018.66, "word": " we", "probability": 0.88623046875 }, { "start": 5018.66, "end": 5018.84, "word": " use", "probability": 0.818359375 }, { "start": 5018.84, "end": 5019.02, "word": " each", "probability": 0.87109375 }, { "start": 5019.02, "end": 5019.12, "word": " of", "probability": 0.900390625 }, { "start": 5019.12, "end": 5019.26, "word": " our", "probability": 0.822265625 }, { "start": 5019.26, "end": 5019.62, "word": " models", "probability": 0.80224609375 } ] }, { "id": 1493, "seek": 484452, "start": 5019.62, "end": 5021.54, "text": " to form a prediction. So we have", "tokens": [ 51464, 281, 1254, 257, 17630, 13, 407, 321, 362, 51564 ], "temperature": 0.0, "avg_logprob": -0.15057964130274712, "compression_ratio": 1.658008658008658, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 5019.62, "end": 5020.08, "word": " to", "probability": 0.90576171875 }, { "start": 5020.08, "end": 5020.44, "word": " form", "probability": 0.8125 }, { "start": 5020.56, "end": 5020.82, "word": " a prediction", "probability": 0.8798828125 }, { "start": 5020.82, "end": 5021.1, "word": ".", "probability": 0.77294921875 }, { "start": 5021.1, "end": 5021.18, "word": " So", "probability": 0.85693359375 }, { "start": 5021.18, "end": 5021.3, "word": " we", "probability": 0.8466796875 }, { "start": 5021.3, "end": 5021.54, "word": " have", "probability": 0.87744140625 } ] }, { "id": 1494, "seek": 484452, "start": 5021.54, "end": 5022.5, "text": " the multinomial", "tokens": [ 51564, 264, 45872, 47429, 51664 ], "temperature": 0.0, "avg_logprob": -0.15057964130274712, "compression_ratio": 1.658008658008658, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 5021.54, "end": 5021.78, "word": " the", "probability": 0.80322265625 }, { "start": 5021.78, "end": 5022.5, "word": " multinomial", "probability": 0.9267578125 } ] }, { "id": 1495, "seek": 484452, "start": 5023.16, "end": 5025.64, "text": " Naive Bayesian with tf.idf, multinomial", "tokens": [ 51664, 6056, 488, 7840, 42434, 365, 256, 69, 13, 327, 69, 11, 45872, 47429, 51764 ], "temperature": 0.0, "avg_logprob": -0.15057964130274712, "compression_ratio": 1.658008658008658, "no_speech_prob": 0.0033245086669921875, "words": [ { "start": 5023.16, "end": 5023.72, "word": " Naive", "probability": 0.5137939453125 }, { "start": 5023.72, "end": 5024.06, "word": " Bayesian", "probability": 0.891357421875 }, { "start": 5024.06, "end": 5024.26, "word": " with", "probability": 0.78857421875 }, { "start": 5024.26, "end": 5024.56, "word": " tf", "probability": 0.9521484375 }, { "start": 5024.56, "end": 5024.94, "word": ".idf", "probability": 0.9812825520833334 }, { "start": 5024.94, "end": 5025.04, "word": ",", "probability": 0.822265625 }, { "start": 5025.04, "end": 5025.64, "word": " multinomial", "probability": 0.9111328125 } ] }, { "id": 1496, "seek": 487264, "start": 5025.64, "end": 5027.48, "text": " with count, logistic regression", "tokens": [ 50364, 365, 1207, 11, 3565, 3142, 24590, 50464 ], "temperature": 0.0, "avg_logprob": -0.13716813526322355, "compression_ratio": 1.9329608938547487, "no_speech_prob": 0.051849365234375, "words": [ { "start": 5025.64, "end": 5026.02, "word": " with", "probability": 0.07537841796875 }, { "start": 5026.02, "end": 5026.44, "word": " count", "probability": 0.58154296875 }, { "start": 5026.44, "end": 5026.6, "word": ",", "probability": 0.73193359375 }, { "start": 5026.6, "end": 5026.96, "word": " logistic", "probability": 0.928955078125 }, { "start": 5026.96, "end": 5027.48, "word": " regression", "probability": 0.89453125 } ] }, { "id": 1497, "seek": 487264, "start": 5027.48, "end": 5029.74, "text": " tf.idf, and logistic regression", "tokens": [ 50464, 256, 69, 13, 327, 69, 11, 293, 3565, 3142, 24590, 50564 ], "temperature": 0.0, "avg_logprob": -0.13716813526322355, "compression_ratio": 1.9329608938547487, "no_speech_prob": 0.051849365234375, "words": [ { "start": 5027.48, "end": 5028.0, "word": " tf", "probability": 0.498046875 }, { "start": 5028.0, "end": 5028.42, "word": ".idf", "probability": 0.7149251302083334 }, { "start": 5028.42, "end": 5028.5, "word": ",", "probability": 0.7177734375 }, { "start": 5028.5, "end": 5028.8, "word": " and", "probability": 0.88623046875 }, { "start": 5028.8, "end": 5029.28, "word": " logistic", "probability": 0.927734375 }, { "start": 5029.28, "end": 5029.74, "word": " regression", "probability": 0.8818359375 } ] }, { "id": 1498, "seek": 487264, "start": 5029.74, "end": 5031.72, "text": " with count. They all use", "tokens": [ 50564, 365, 1207, 13, 814, 439, 764, 50664 ], "temperature": 0.0, "avg_logprob": -0.13716813526322355, "compression_ratio": 1.9329608938547487, "no_speech_prob": 0.051849365234375, "words": [ { "start": 5029.74, "end": 5030.18, "word": " with", "probability": 0.8017578125 }, { "start": 5030.18, "end": 5030.5, "word": " count", "probability": 0.775390625 }, { "start": 5030.5, "end": 5030.86, "word": ".", "probability": 0.90478515625 }, { "start": 5030.86, "end": 5031.32, "word": " They", "probability": 0.69482421875 }, { "start": 5031.32, "end": 5031.48, "word": " all", "probability": 0.892578125 }, { "start": 5031.48, "end": 5031.72, "word": " use", "probability": 0.79833984375 } ] }, { "id": 1499, "seek": 487264, "start": 5031.72, "end": 5033.88, "text": " the same predict function. They're all using", "tokens": [ 50664, 264, 912, 6069, 2445, 13, 814, 434, 439, 1228, 50764 ], "temperature": 0.0, "avg_logprob": -0.13716813526322355, "compression_ratio": 1.9329608938547487, "no_speech_prob": 0.051849365234375, "words": [ { "start": 5031.72, "end": 5031.9, "word": " the", "probability": 0.81494140625 }, { "start": 5031.9, "end": 5032.1, "word": " same", "probability": 0.81005859375 }, { "start": 5032.1, "end": 5032.34, "word": " predict", "probability": 0.80419921875 }, { "start": 5032.34, "end": 5032.8, "word": " function", "probability": 0.8759765625 }, { "start": 5032.8, "end": 5033.0, "word": ".", "probability": 0.5107421875 }, { "start": 5033.0, "end": 5033.12, "word": " They're", "probability": 0.806396484375 }, { "start": 5033.12, "end": 5033.34, "word": " all", "probability": 0.8828125 }, { "start": 5033.34, "end": 5033.88, "word": " using", "probability": 0.8310546875 } ] }, { "id": 1500, "seek": 487264, "start": 5033.88, "end": 5036.5, "text": " either the tf.idf", "tokens": [ 50764, 2139, 264, 256, 69, 13, 327, 69, 50864 ], "temperature": 0.0, "avg_logprob": -0.13716813526322355, "compression_ratio": 1.9329608938547487, "no_speech_prob": 0.051849365234375, "words": [ { "start": 5033.88, "end": 5035.02, "word": " either", "probability": 0.66064453125 }, { "start": 5035.02, "end": 5035.4, "word": " the", "probability": 0.78369140625 }, { "start": 5035.4, "end": 5036.0, "word": " tf", "probability": 0.9580078125 }, { "start": 5036.0, "end": 5036.5, "word": ".idf", "probability": 0.9801432291666666 } ] }, { "id": 1501, "seek": 487264, "start": 5036.5, "end": 5037.64, "text": " vectorized version", "tokens": [ 50864, 8062, 1602, 3037, 50964 ], "temperature": 0.0, "avg_logprob": -0.13716813526322355, "compression_ratio": 1.9329608938547487, "no_speech_prob": 0.051849365234375, "words": [ { "start": 5036.5, "end": 5037.24, "word": " vectorized", "probability": 0.9091796875 }, { "start": 5037.24, "end": 5037.64, "word": " version", "probability": 0.703125 } ] }, { "id": 1502, "seek": 487264, "start": 5037.64, "end": 5039.26, "text": " of the email or the count", "tokens": [ 50964, 295, 264, 3796, 420, 264, 1207, 51064 ], "temperature": 0.0, "avg_logprob": -0.13716813526322355, "compression_ratio": 1.9329608938547487, "no_speech_prob": 0.051849365234375, "words": [ { "start": 5037.64, "end": 5037.8, "word": " of", "probability": 0.90478515625 }, { "start": 5037.8, "end": 5037.92, "word": " the", "probability": 0.8095703125 }, { "start": 5037.92, "end": 5038.16, "word": " email", "probability": 0.89013671875 }, { "start": 5038.16, "end": 5038.6, "word": " or", "probability": 0.65185546875 }, { "start": 5038.6, "end": 5038.86, "word": " the", "probability": 0.8056640625 }, { "start": 5038.86, "end": 5039.26, "word": " count", "probability": 0.75927734375 } ] }, { "id": 1503, "seek": 487264, "start": 5039.26, "end": 5041.54, "text": " vectorized version of the email", "tokens": [ 51064, 8062, 1602, 3037, 295, 264, 3796, 51164 ], "temperature": 0.0, "avg_logprob": -0.13716813526322355, "compression_ratio": 1.9329608938547487, "no_speech_prob": 0.051849365234375, "words": [ { "start": 5039.26, "end": 5040.22, "word": " vectorized", "probability": 0.919677734375 }, { "start": 5040.22, "end": 5040.82, "word": " version", "probability": 0.72412109375 }, { "start": 5040.82, "end": 5041.08, "word": " of", "probability": 0.9052734375 }, { "start": 5041.08, "end": 5041.22, "word": " the", "probability": 0.8154296875 }, { "start": 5041.22, "end": 5041.54, "word": " email", "probability": 0.91650390625 } ] }, { "id": 1504, "seek": 487264, "start": 5043.14, "end": 5044.06, "text": " based on", "tokens": [ 51164, 2361, 322, 51264 ], "temperature": 0.0, "avg_logprob": -0.13716813526322355, "compression_ratio": 1.9329608938547487, "no_speech_prob": 0.051849365234375, "words": [ { "start": 5043.14, "end": 5043.76, "word": " based", "probability": 0.54931640625 }, { "start": 5043.76, "end": 5044.06, "word": " on", "probability": 0.90380859375 } ] }, { "id": 1505, "seek": 487264, "start": 5044.06, "end": 5045.56, "text": " whether or not it's the tf.idf", "tokens": [ 51264, 1968, 420, 406, 309, 311, 264, 256, 69, 13, 327, 69, 51364 ], "temperature": 0.0, "avg_logprob": -0.13716813526322355, "compression_ratio": 1.9329608938547487, "no_speech_prob": 0.051849365234375, "words": [ { "start": 5044.06, "end": 5044.32, "word": " whether", "probability": 0.8369140625 }, { "start": 5044.32, "end": 5044.44, "word": " or", "probability": 0.88427734375 }, { "start": 5044.44, "end": 5044.54, "word": " not", "probability": 0.89599609375 }, { "start": 5044.54, "end": 5044.76, "word": " it's", "probability": 0.947998046875 }, { "start": 5044.76, "end": 5044.88, "word": " the", "probability": 0.7802734375 }, { "start": 5044.88, "end": 5045.12, "word": " tf", "probability": 0.975341796875 }, { "start": 5045.12, "end": 5045.56, "word": ".idf", "probability": 0.9847005208333334 } ] }, { "id": 1506, "seek": 487264, "start": 5045.56, "end": 5047.58, "text": " or the count version of the model.", "tokens": [ 51364, 420, 264, 1207, 3037, 295, 264, 2316, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.13716813526322355, "compression_ratio": 1.9329608938547487, "no_speech_prob": 0.051849365234375, "words": [ { "start": 5045.56, "end": 5045.82, "word": " or", "probability": 0.86962890625 }, { "start": 5045.82, "end": 5045.98, "word": " the", "probability": 0.80615234375 }, { "start": 5045.98, "end": 5046.18, "word": " count", "probability": 0.73974609375 }, { "start": 5046.18, "end": 5046.46, "word": " version", "probability": 0.73193359375 }, { "start": 5046.46, "end": 5046.6, "word": " of", "probability": 0.90380859375 }, { "start": 5046.6, "end": 5046.72, "word": " the", "probability": 0.81591796875 }, { "start": 5046.72, "end": 5046.96, "word": " model", "probability": 0.80419921875 }, { "start": 5046.96, "end": 5047.58, "word": ".", "probability": 0.8583984375 } ] }, { "id": 1507, "seek": 487264, "start": 5048.82, "end": 5049.7, "text": " And then", "tokens": [ 51464, 400, 550, 51564 ], "temperature": 0.0, "avg_logprob": -0.13716813526322355, "compression_ratio": 1.9329608938547487, "no_speech_prob": 0.051849365234375, "words": [ { "start": 5048.82, "end": 5049.42, "word": " And", "probability": 0.685546875 }, { "start": 5049.42, "end": 5049.7, "word": " then", "probability": 0.72119140625 } ] }, { "id": 1508, "seek": 487264, "start": 5049.7, "end": 5053.2, "text": " we make our predictions,", "tokens": [ 51564, 321, 652, 527, 21264, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.13716813526322355, "compression_ratio": 1.9329608938547487, "no_speech_prob": 0.051849365234375, "words": [ { "start": 5049.7, "end": 5050.88, "word": " we", "probability": 0.82763671875 }, { "start": 5050.88, "end": 5051.36, "word": " make", "probability": 0.873046875 }, { "start": 5051.36, "end": 5051.5, "word": " our", "probability": 0.81005859375 }, { "start": 5051.5, "end": 5051.84, "word": " predictions", "probability": 0.70751953125 }, { "start": 5051.84, "end": 5053.2, "word": ",", "probability": 0.415283203125 } ] }, { "id": 1509, "seek": 487264, "start": 5053.2, "end": 5053.76, "text": " we print", "tokens": [ 51664, 321, 4482, 51764 ], "temperature": 0.0, "avg_logprob": -0.13716813526322355, "compression_ratio": 1.9329608938547487, "no_speech_prob": 0.051849365234375, "words": [ { "start": 5053.2, "end": 5053.44, "word": " we", "probability": 0.89111328125 }, { "start": 5053.44, "end": 5053.76, "word": " print", "probability": 0.84521484375 } ] }, { "id": 1510, "seek": 490046, "start": 5053.76, "end": 5055.56, "text": " the email itself, and then we can", "tokens": [ 50364, 264, 3796, 2564, 11, 293, 550, 321, 393, 50464 ], "temperature": 0.0, "avg_logprob": -0.14039964501101238, "compression_ratio": 1.5609756097560976, "no_speech_prob": 0.01363372802734375, "words": [ { "start": 5053.76, "end": 5054.08, "word": " the", "probability": 0.60986328125 }, { "start": 5054.08, "end": 5054.52, "word": " email", "probability": 0.875 }, { "start": 5054.52, "end": 5055.0, "word": " itself", "probability": 0.7568359375 }, { "start": 5055.0, "end": 5055.18, "word": ",", "probability": 0.338134765625 }, { "start": 5055.18, "end": 5055.2, "word": " and", "probability": 0.884765625 }, { "start": 5055.2, "end": 5055.3, "word": " then", "probability": 0.7373046875 }, { "start": 5055.3, "end": 5055.38, "word": " we", "probability": 0.8994140625 }, { "start": 5055.38, "end": 5055.56, "word": " can", "probability": 0.89404296875 } ] }, { "id": 1511, "seek": 490046, "start": 5055.56, "end": 5057.48, "text": " print what", "tokens": [ 50464, 4482, 437, 50564 ], "temperature": 0.0, "avg_logprob": -0.14039964501101238, "compression_ratio": 1.5609756097560976, "no_speech_prob": 0.01363372802734375, "words": [ { "start": 5055.56, "end": 5056.0, "word": " print", "probability": 0.87158203125 }, { "start": 5056.0, "end": 5057.48, "word": " what", "probability": 0.841796875 } ] }, { "id": 1512, "seek": 490046, "start": 5057.48, "end": 5059.56, "text": " each model thinks", "tokens": [ 50564, 1184, 2316, 7309, 50664 ], "temperature": 0.0, "avg_logprob": -0.14039964501101238, "compression_ratio": 1.5609756097560976, "no_speech_prob": 0.01363372802734375, "words": [ { "start": 5057.48, "end": 5058.16, "word": " each", "probability": 0.87109375 }, { "start": 5058.16, "end": 5058.7, "word": " model", "probability": 0.82080078125 }, { "start": 5058.7, "end": 5059.56, "word": " thinks", "probability": 0.73779296875 } ] }, { "id": 1513, "seek": 490046, "start": 5059.56, "end": 5060.8, "text": " it is.", "tokens": [ 50664, 309, 307, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.14039964501101238, "compression_ratio": 1.5609756097560976, "no_speech_prob": 0.01363372802734375, "words": [ { "start": 5059.56, "end": 5059.82, "word": " it", "probability": 0.90087890625 }, { "start": 5059.82, "end": 5060.2, "word": " is", "probability": 0.90283203125 }, { "start": 5060.2, "end": 5060.8, "word": ".", "probability": 0.974609375 } ] }, { "id": 1514, "seek": 490046, "start": 5062.66, "end": 5063.64, "text": " So if you're", "tokens": [ 50764, 407, 498, 291, 434, 50864 ], "temperature": 0.0, "avg_logprob": -0.14039964501101238, "compression_ratio": 1.5609756097560976, "no_speech_prob": 0.01363372802734375, "words": [ { "start": 5062.66, "end": 5063.26, "word": " So", "probability": 0.74267578125 }, { "start": 5063.26, "end": 5063.48, "word": " if", "probability": 0.74365234375 }, { "start": 5063.48, "end": 5063.64, "word": " you're", "probability": 0.92431640625 } ] }, { "id": 1515, "seek": 490046, "start": 5063.64, "end": 5065.72, "text": " still on the fill in the blank bit,", "tokens": [ 50864, 920, 322, 264, 2836, 294, 264, 8247, 857, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.14039964501101238, "compression_ratio": 1.5609756097560976, "no_speech_prob": 0.01363372802734375, "words": [ { "start": 5063.64, "end": 5063.94, "word": " still", "probability": 0.9052734375 }, { "start": 5063.94, "end": 5064.18, "word": " on", "probability": 0.83935546875 }, { "start": 5064.18, "end": 5064.38, "word": " the", "probability": 0.80908203125 }, { "start": 5064.38, "end": 5064.6, "word": " fill", "probability": 0.6875 }, { "start": 5064.6, "end": 5064.7, "word": " in", "probability": 0.58740234375 }, { "start": 5064.7, "end": 5064.78, "word": " the", "probability": 0.8076171875 }, { "start": 5064.78, "end": 5064.98, "word": " blank", "probability": 0.83837890625 }, { "start": 5064.98, "end": 5065.26, "word": " bit", "probability": 0.85986328125 }, { "start": 5065.26, "end": 5065.72, "word": ",", "probability": 0.82080078125 } ] }, { "id": 1516, "seek": 490046, "start": 5065.72, "end": 5067.88, "text": " I encourage you to", "tokens": [ 50964, 286, 5373, 291, 281, 51064 ], "temperature": 0.0, "avg_logprob": -0.14039964501101238, "compression_ratio": 1.5609756097560976, "no_speech_prob": 0.01363372802734375, "words": [ { "start": 5065.72, "end": 5066.44, "word": " I", "probability": 0.9755859375 }, { "start": 5066.44, "end": 5066.78, "word": " encourage", "probability": 0.61767578125 }, { "start": 5066.78, "end": 5067.14, "word": " you", "probability": 0.8935546875 }, { "start": 5067.14, "end": 5067.88, "word": " to", "probability": 0.90673828125 } ] }, { "id": 1517, "seek": 490046, "start": 5067.88, "end": 5069.94, "text": " fill this out.", "tokens": [ 51064, 2836, 341, 484, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.14039964501101238, "compression_ratio": 1.5609756097560976, "no_speech_prob": 0.01363372802734375, "words": [ { "start": 5067.88, "end": 5068.9, "word": " fill", "probability": 0.8232421875 }, { "start": 5068.9, "end": 5069.12, "word": " this", "probability": 0.873046875 }, { "start": 5069.12, "end": 5069.34, "word": " out", "probability": 0.828125 }, { "start": 5069.34, "end": 5069.94, "word": ".", "probability": 0.84716796875 } ] }, { "id": 1518, "seek": 490046, "start": 5070.36, "end": 5071.58, "text": " If you are using", "tokens": [ 51164, 759, 291, 366, 1228, 51264 ], "temperature": 0.0, "avg_logprob": -0.14039964501101238, "compression_ratio": 1.5609756097560976, "no_speech_prob": 0.01363372802734375, "words": [ { "start": 5070.36, "end": 5070.96, "word": " If", "probability": 0.8857421875 }, { "start": 5070.96, "end": 5071.06, "word": " you", "probability": 0.896484375 }, { "start": 5071.06, "end": 5071.18, "word": " are", "probability": 0.8916015625 }, { "start": 5071.18, "end": 5071.58, "word": " using", "probability": 0.8271484375 } ] }, { "id": 1519, "seek": 490046, "start": 5071.58, "end": 5073.66, "text": " the completed workbook, like", "tokens": [ 51264, 264, 7365, 589, 2939, 11, 411, 51364 ], "temperature": 0.0, "avg_logprob": -0.14039964501101238, "compression_ratio": 1.5609756097560976, "no_speech_prob": 0.01363372802734375, "words": [ { "start": 5071.58, "end": 5072.04, "word": " the", "probability": 0.81787109375 }, { "start": 5072.04, "end": 5072.46, "word": " completed", "probability": 0.6083984375 }, { "start": 5072.46, "end": 5073.02, "word": " workbook", "probability": 0.898681640625 }, { "start": 5073.02, "end": 5073.2, "word": ",", "probability": 0.2210693359375 }, { "start": 5073.2, "end": 5073.66, "word": " like", "probability": 0.87890625 } ] }, { "id": 1520, "seek": 490046, "start": 5073.66, "end": 5075.62, "text": " I am, it's already filled out", "tokens": [ 51364, 286, 669, 11, 309, 311, 1217, 6412, 484, 51464 ], "temperature": 0.0, "avg_logprob": -0.14039964501101238, "compression_ratio": 1.5609756097560976, "no_speech_prob": 0.01363372802734375, "words": [ { "start": 5073.66, "end": 5073.8, "word": " I", "probability": 0.9404296875 }, { "start": 5073.8, "end": 5074.1, "word": " am", "probability": 0.89794921875 }, { "start": 5074.1, "end": 5074.4, "word": ",", "probability": 0.9638671875 }, { "start": 5074.4, "end": 5074.9, "word": " it's", "probability": 0.94970703125 }, { "start": 5074.9, "end": 5075.08, "word": " already", "probability": 0.82958984375 }, { "start": 5075.08, "end": 5075.32, "word": " filled", "probability": 0.8056640625 }, { "start": 5075.32, "end": 5075.62, "word": " out", "probability": 0.82421875 } ] }, { "id": 1521, "seek": 490046, "start": 5075.62, "end": 5077.52, "text": " and we're just going to go ahead and", "tokens": [ 51464, 293, 321, 434, 445, 516, 281, 352, 2286, 293, 51564 ], "temperature": 0.0, "avg_logprob": -0.14039964501101238, "compression_ratio": 1.5609756097560976, "no_speech_prob": 0.01363372802734375, "words": [ { "start": 5075.62, "end": 5076.12, "word": " and", "probability": 0.420166015625 }, { "start": 5076.12, "end": 5076.32, "word": " we're", "probability": 0.93115234375 }, { "start": 5076.32, "end": 5076.5, "word": " just", "probability": 0.88232421875 }, { "start": 5076.5, "end": 5076.62, "word": " going", "probability": 0.69970703125 }, { "start": 5076.62, "end": 5076.7, "word": " to", "probability": 0.9091796875 }, { "start": 5076.7, "end": 5076.84, "word": " go", "probability": 0.9013671875 }, { "start": 5076.84, "end": 5077.12, "word": " ahead", "probability": 0.8544921875 }, { "start": 5077.12, "end": 5077.52, "word": " and", "probability": 0.890625 } ] }, { "id": 1522, "seek": 490046, "start": 5077.52, "end": 5079.36, "text": " let everything else", "tokens": [ 51564, 718, 1203, 1646, 51664 ], "temperature": 0.0, "avg_logprob": -0.14039964501101238, "compression_ratio": 1.5609756097560976, "no_speech_prob": 0.01363372802734375, "words": [ { "start": 5077.52, "end": 5078.38, "word": " let", "probability": 0.89892578125 }, { "start": 5078.38, "end": 5078.88, "word": " everything", "probability": 0.880859375 }, { "start": 5078.88, "end": 5079.36, "word": " else", "probability": 0.83935546875 } ] }, { "id": 1523, "seek": 490046, "start": 5079.36, "end": 5081.58, "text": " run in the background until we get", "tokens": [ 51664, 1190, 294, 264, 3678, 1826, 321, 483, 51764 ], "temperature": 0.0, "avg_logprob": -0.14039964501101238, "compression_ratio": 1.5609756097560976, "no_speech_prob": 0.01363372802734375, "words": [ { "start": 5079.36, "end": 5079.96, "word": " run", "probability": 0.9013671875 }, { "start": 5079.96, "end": 5080.14, "word": " in", "probability": 0.90625 }, { "start": 5080.14, "end": 5080.26, "word": " the", "probability": 0.81201171875 }, { "start": 5080.26, "end": 5080.66, "word": " background", "probability": 0.75732421875 }, { "start": 5080.66, "end": 5081.3, "word": " until", "probability": 0.77001953125 }, { "start": 5081.3, "end": 5081.46, "word": " we", "probability": 0.9013671875 }, { "start": 5081.46, "end": 5081.58, "word": " get", "probability": 0.89892578125 } ] }, { "id": 1524, "seek": 492876, "start": 5081.58, "end": 5082.94, "text": " to this point.", "tokens": [ 50364, 281, 341, 935, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.19908708400940628, "compression_ratio": 1.3867403314917126, "no_speech_prob": 0.1441650390625, "words": [ { "start": 5081.58, "end": 5081.7, "word": " to", "probability": 0.3076171875 }, { "start": 5081.7, "end": 5081.9, "word": " this", "probability": 0.72705078125 }, { "start": 5081.9, "end": 5082.22, "word": " point", "probability": 0.85302734375 }, { "start": 5082.22, "end": 5082.94, "word": ".", "probability": 0.83935546875 } ] }, { "id": 1525, "seek": 492876, "start": 5085.84, "end": 5087.8, "text": " So, sorry about that.", "tokens": [ 50564, 407, 11, 2597, 466, 300, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.19908708400940628, "compression_ratio": 1.3867403314917126, "no_speech_prob": 0.1441650390625, "words": [ { "start": 5085.84, "end": 5086.22, "word": " So", "probability": 0.43798828125 }, { "start": 5086.22, "end": 5086.52, "word": ",", "probability": 0.525390625 }, { "start": 5086.52, "end": 5086.92, "word": " sorry", "probability": 0.74755859375 }, { "start": 5086.92, "end": 5087.12, "word": " about", "probability": 0.8212890625 }, { "start": 5087.12, "end": 5087.44, "word": " that", "probability": 0.88623046875 }, { "start": 5087.44, "end": 5087.8, "word": ".", "probability": 0.9560546875 } ] }, { "id": 1526, "seek": 492876, "start": 5089.36, "end": 5091.52, "text": " In the meantime, are there any", "tokens": [ 50764, 682, 264, 14991, 11, 366, 456, 604, 50864 ], "temperature": 0.0, "avg_logprob": -0.19908708400940628, "compression_ratio": 1.3867403314917126, "no_speech_prob": 0.1441650390625, "words": [ { "start": 5089.36, "end": 5090.08, "word": " In", "probability": 0.85205078125 }, { "start": 5090.08, "end": 5090.18, "word": " the", "probability": 0.80859375 }, { "start": 5090.18, "end": 5090.46, "word": " meantime", "probability": 0.83984375 }, { "start": 5090.46, "end": 5090.82, "word": ",", "probability": 0.880859375 }, { "start": 5090.82, "end": 5090.94, "word": " are", "probability": 0.87353515625 }, { "start": 5090.94, "end": 5091.18, "word": " there", "probability": 0.85986328125 }, { "start": 5091.18, "end": 5091.52, "word": " any", "probability": 0.828125 } ] }, { "id": 1527, "seek": 492876, "start": 5091.52, "end": 5094.06, "text": " questions, any thoughts,", "tokens": [ 50864, 1651, 11, 604, 4598, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.19908708400940628, "compression_ratio": 1.3867403314917126, "no_speech_prob": 0.1441650390625, "words": [ { "start": 5091.52, "end": 5092.06, "word": " questions", "probability": 0.908203125 }, { "start": 5092.06, "end": 5093.04, "word": ",", "probability": 0.58203125 }, { "start": 5093.04, "end": 5093.28, "word": " any", "probability": 0.77197265625 }, { "start": 5093.28, "end": 5093.7, "word": " thoughts", "probability": 0.75341796875 }, { "start": 5093.7, "end": 5094.06, "word": ",", "probability": 0.97314453125 } ] }, { "id": 1528, "seek": 492876, "start": 5094.06, "end": 5095.9, "text": " concerns, ideas?", "tokens": [ 50964, 7389, 11, 3487, 30, 51064 ], "temperature": 0.0, "avg_logprob": -0.19908708400940628, "compression_ratio": 1.3867403314917126, "no_speech_prob": 0.1441650390625, "words": [ { "start": 5094.06, "end": 5094.6, "word": " concerns", "probability": 0.8291015625 }, { "start": 5094.6, "end": 5094.8, "word": ",", "probability": 0.98095703125 }, { "start": 5094.8, "end": 5095.22, "word": " ideas", "probability": 0.79833984375 }, { "start": 5095.22, "end": 5095.9, "word": "?", "probability": 0.83544921875 } ] }, { "id": 1529, "seek": 492876, "start": 5095.9, "end": 5097.64, "text": " I'd love to hear from you.", "tokens": [ 51064, 286, 1116, 959, 281, 1568, 490, 291, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.19908708400940628, "compression_ratio": 1.3867403314917126, "no_speech_prob": 0.1441650390625, "words": [ { "start": 5095.9, "end": 5096.3, "word": " I'd", "probability": 0.6798095703125 }, { "start": 5096.3, "end": 5096.4, "word": " love", "probability": 0.8916015625 }, { "start": 5096.4, "end": 5096.48, "word": " to", "probability": 0.90380859375 }, { "start": 5096.48, "end": 5096.6, "word": " hear", "probability": 0.8798828125 }, { "start": 5096.6, "end": 5096.78, "word": " from", "probability": 0.81201171875 }, { "start": 5096.78, "end": 5096.92, "word": " you", "probability": 0.89794921875 }, { "start": 5096.92, "end": 5097.64, "word": ".", "probability": 0.98388671875 } ] }, { "id": 1530, "seek": 492876, "start": 5115.77, "end": 5117.21, "text": " All right.", "tokens": [ 51164, 1057, 558, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.19908708400940628, "compression_ratio": 1.3867403314917126, "no_speech_prob": 0.1441650390625, "words": [ { "start": 5115.77, "end": 5116.23, "word": " All", "probability": 0.32421875 }, { "start": 5116.23, "end": 5116.49, "word": " right", "probability": 0.884765625 }, { "start": 5116.49, "end": 5117.21, "word": ".", "probability": 0.5654296875 } ] }, { "id": 1531, "seek": 492876, "start": 5117.63, "end": 5118.35, "text": " Psychdude", "tokens": [ 51264, 17303, 67, 2303, 51364 ], "temperature": 0.0, "avg_logprob": -0.19908708400940628, "compression_ratio": 1.3867403314917126, "no_speech_prob": 0.1441650390625, "words": [ { "start": 5117.63, "end": 5118.35, "word": " Psychdude", "probability": 0.5638020833333334 } ] }, { "id": 1532, "seek": 492876, "start": 5118.35, "end": 5120.19, "text": " says, on the completed workbook", "tokens": [ 51364, 1619, 11, 322, 264, 7365, 589, 2939, 51464 ], "temperature": 0.0, "avg_logprob": -0.19908708400940628, "compression_ratio": 1.3867403314917126, "no_speech_prob": 0.1441650390625, "words": [ { "start": 5118.35, "end": 5118.81, "word": " says", "probability": 0.33642578125 }, { "start": 5118.81, "end": 5118.95, "word": ",", "probability": 0.544921875 }, { "start": 5118.95, "end": 5119.05, "word": " on", "probability": 0.257568359375 }, { "start": 5119.05, "end": 5119.19, "word": " the", "probability": 0.80908203125 }, { "start": 5119.19, "end": 5119.55, "word": " completed", "probability": 0.6416015625 }, { "start": 5119.55, "end": 5120.19, "word": " workbook", "probability": 0.79150390625 } ] }, { "id": 1533, "seek": 492876, "start": 5120.19, "end": 5122.23, "text": " 6a, show the", "tokens": [ 51464, 1386, 64, 11, 855, 264, 51564 ], "temperature": 0.0, "avg_logprob": -0.19908708400940628, "compression_ratio": 1.3867403314917126, "no_speech_prob": 0.1441650390625, "words": [ { "start": 5120.19, "end": 5120.87, "word": " 6a", "probability": 0.71923828125 }, { "start": 5120.87, "end": 5121.63, "word": ",", "probability": 0.8359375 }, { "start": 5121.63, "end": 5122.03, "word": " show", "probability": 0.87109375 }, { "start": 5122.03, "end": 5122.23, "word": " the", "probability": 0.78857421875 } ] }, { "id": 1534, "seek": 492876, "start": 5122.23, "end": 5124.35, "text": " top right and bottom left", "tokens": [ 51564, 1192, 558, 293, 2767, 1411, 51664 ], "temperature": 0.0, "avg_logprob": -0.19908708400940628, "compression_ratio": 1.3867403314917126, "no_speech_prob": 0.1441650390625, "words": [ { "start": 5122.23, "end": 5122.51, "word": " top", "probability": 0.833984375 }, { "start": 5122.51, "end": 5123.47, "word": " right", "probability": 0.68603515625 }, { "start": 5123.47, "end": 5123.77, "word": " and", "probability": 0.8916015625 }, { "start": 5123.77, "end": 5124.09, "word": " bottom", "probability": 0.76904296875 }, { "start": 5124.09, "end": 5124.35, "word": " left", "probability": 0.84814453125 } ] }, { "id": 1535, "seek": 492876, "start": 5124.35, "end": 5126.51, "text": " numbers swapped in 6a.", "tokens": [ 51664, 3547, 50011, 294, 1386, 64, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.19908708400940628, "compression_ratio": 1.3867403314917126, "no_speech_prob": 0.1441650390625, "words": [ { "start": 5124.35, "end": 5124.75, "word": " numbers", "probability": 0.498291015625 }, { "start": 5124.75, "end": 5125.19, "word": " swapped", "probability": 0.7548828125 }, { "start": 5125.19, "end": 5125.53, "word": " in", "probability": 0.8994140625 }, { "start": 5125.53, "end": 5126.15, "word": " 6a", "probability": 0.989013671875 }, { "start": 5126.15, "end": 5126.51, "word": ".", "probability": 0.86279296875 } ] }, { "id": 1536, "seek": 495660, "start": 5126.51, "end": 5127.79, "text": " Wait a second.", "tokens": [ 50364, 3802, 257, 1150, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.19833097132769498, "compression_ratio": 1.440217391304348, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5126.51, "end": 5126.69, "word": " Wait", "probability": 0.4228515625 }, { "start": 5126.85, "end": 5127.03, "word": " a second", "probability": 0.58740234375 }, { "start": 5127.03, "end": 5127.79, "word": ".", "probability": 0.77197265625 } ] }, { "id": 1537, "seek": 495660, "start": 5127.81, "end": 5130.59, "text": " But the one", "tokens": [ 50464, 583, 264, 472, 50564 ], "temperature": 0.0, "avg_logprob": -0.19833097132769498, "compression_ratio": 1.440217391304348, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5127.81, "end": 5128.37, "word": " But", "probability": 0.09613037109375 }, { "start": 5128.37, "end": 5130.45, "word": " the", "probability": 0.80908203125 }, { "start": 5130.45, "end": 5130.59, "word": " one", "probability": 0.81982421875 } ] }, { "id": 1538, "seek": 495660, "start": 5130.59, "end": 5132.35, "text": " you were working on earlier", "tokens": [ 50564, 291, 645, 1364, 322, 3071, 50664 ], "temperature": 0.0, "avg_logprob": -0.19833097132769498, "compression_ratio": 1.440217391304348, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5130.59, "end": 5130.71, "word": " you", "probability": 0.89599609375 }, { "start": 5130.71, "end": 5130.83, "word": " were", "probability": 0.84130859375 }, { "start": 5130.83, "end": 5131.13, "word": " working", "probability": 0.73095703125 }, { "start": 5131.13, "end": 5131.57, "word": " on", "probability": 0.908203125 }, { "start": 5131.57, "end": 5132.35, "word": " earlier", "probability": 0.8857421875 } ] }, { "id": 1539, "seek": 495660, "start": 5132.35, "end": 5133.53, "text": " had those flipped.", "tokens": [ 50664, 632, 729, 26273, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.19833097132769498, "compression_ratio": 1.440217391304348, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5132.35, "end": 5132.61, "word": " had", "probability": 0.75634765625 }, { "start": 5132.61, "end": 5132.77, "word": " those", "probability": 0.53076171875 }, { "start": 5132.77, "end": 5132.99, "word": " flipped", "probability": 0.06884765625 }, { "start": 5132.99, "end": 5133.53, "word": ".", "probability": 0.78515625 } ] }, { "id": 1540, "seek": 495660, "start": 5133.53, "end": 5136.37, "text": " The fill in the blank and", "tokens": [ 50764, 440, 2836, 294, 264, 8247, 293, 50864 ], "temperature": 0.0, "avg_logprob": -0.19833097132769498, "compression_ratio": 1.440217391304348, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5133.53, "end": 5134.09, "word": " The", "probability": 0.07708740234375 }, { "start": 5134.09, "end": 5135.35, "word": " fill", "probability": 0.728515625 }, { "start": 5135.35, "end": 5135.45, "word": " in", "probability": 0.73193359375 }, { "start": 5135.45, "end": 5135.55, "word": " the", "probability": 0.80224609375 }, { "start": 5135.55, "end": 5135.85, "word": " blank", "probability": 0.82177734375 }, { "start": 5135.85, "end": 5136.37, "word": " and", "probability": 0.86181640625 } ] }, { "id": 1541, "seek": 495660, "start": 5136.37, "end": 5138.51, "text": " the completed, were", "tokens": [ 50864, 264, 7365, 11, 645, 50964 ], "temperature": 0.0, "avg_logprob": -0.19833097132769498, "compression_ratio": 1.440217391304348, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5136.37, "end": 5136.81, "word": " the", "probability": 0.81005859375 }, { "start": 5136.81, "end": 5137.49, "word": " completed", "probability": 0.66064453125 }, { "start": 5137.49, "end": 5138.13, "word": ",", "probability": 0.75341796875 }, { "start": 5138.13, "end": 5138.51, "word": " were", "probability": 0.86279296875 } ] }, { "id": 1542, "seek": 495660, "start": 5138.51, "end": 5140.43, "text": " they different somehow?", "tokens": [ 50964, 436, 819, 6063, 30, 51064 ], "temperature": 0.0, "avg_logprob": -0.19833097132769498, "compression_ratio": 1.440217391304348, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5138.51, "end": 5138.95, "word": " they", "probability": 0.73828125 }, { "start": 5138.95, "end": 5139.71, "word": " different", "probability": 0.69970703125 }, { "start": 5139.71, "end": 5139.99, "word": " somehow", "probability": 0.806640625 }, { "start": 5139.99, "end": 5140.43, "word": "?", "probability": 0.98974609375 } ] }, { "id": 1543, "seek": 495660, "start": 5140.43, "end": 5142.37, "text": " Yeah, so I'm", "tokens": [ 51064, 865, 11, 370, 286, 478, 51164 ], "temperature": 0.0, "avg_logprob": -0.19833097132769498, "compression_ratio": 1.440217391304348, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5140.43, "end": 5140.61, "word": " Yeah", "probability": 0.5029296875 }, { "start": 5140.61, "end": 5140.83, "word": ",", "probability": 0.398681640625 }, { "start": 5140.83, "end": 5141.17, "word": " so", "probability": 0.78173828125 }, { "start": 5141.17, "end": 5142.37, "word": " I'm", "probability": 0.937744140625 } ] }, { "id": 1544, "seek": 495660, "start": 5142.37, "end": 5144.33, "text": " thinking the reason why they're swapped", "tokens": [ 51164, 1953, 264, 1778, 983, 436, 434, 50011, 51264 ], "temperature": 0.0, "avg_logprob": -0.19833097132769498, "compression_ratio": 1.440217391304348, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5142.37, "end": 5142.71, "word": " thinking", "probability": 0.7314453125 }, { "start": 5142.71, "end": 5142.97, "word": " the", "probability": 0.8115234375 }, { "start": 5142.97, "end": 5143.23, "word": " reason", "probability": 0.91015625 }, { "start": 5143.23, "end": 5143.61, "word": " why", "probability": 0.8271484375 }, { "start": 5143.61, "end": 5143.85, "word": " they're", "probability": 0.835205078125 }, { "start": 5143.85, "end": 5144.33, "word": " swapped", "probability": 0.79931640625 } ] }, { "id": 1545, "seek": 495660, "start": 5144.33, "end": 5145.49, "text": " is because", "tokens": [ 51264, 307, 570, 51364 ], "temperature": 0.0, "avg_logprob": -0.19833097132769498, "compression_ratio": 1.440217391304348, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5144.33, "end": 5145.03, "word": " is", "probability": 0.873046875 }, { "start": 5145.03, "end": 5145.49, "word": " because", "probability": 0.83154296875 } ] }, { "id": 1546, "seek": 495660, "start": 5146.51, "end": 5147.23, "text": " there was", "tokens": [ 51364, 456, 390, 51464 ], "temperature": 0.0, "avg_logprob": -0.19833097132769498, "compression_ratio": 1.440217391304348, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5146.51, "end": 5146.91, "word": " there", "probability": 0.8271484375 }, { "start": 5146.91, "end": 5147.23, "word": " was", "probability": 0.89599609375 } ] }, { "id": 1547, "seek": 495660, "start": 5149.45, "end": 5150.97, "text": " a way that", "tokens": [ 51464, 257, 636, 300, 51564 ], "temperature": 0.0, "avg_logprob": -0.19833097132769498, "compression_ratio": 1.440217391304348, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5149.45, "end": 5150.21, "word": " a way", "probability": 0.86328125 }, { "start": 5150.21, "end": 5150.97, "word": " that", "probability": 0.8798828125 } ] }, { "id": 1548, "seek": 495660, "start": 5150.97, "end": 5152.57, "text": " Scikit-learn", "tokens": [ 51564, 16942, 22681, 12, 306, 1083, 51664 ], "temperature": 0.0, "avg_logprob": -0.19833097132769498, "compression_ratio": 1.440217391304348, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5150.97, "end": 5152.27, "word": " Scikit", "probability": 0.678466796875 }, { "start": 5152.27, "end": 5152.57, "word": "-learn", "probability": 0.8785807291666666 } ] }, { "id": 1549, "seek": 495660, "start": 5152.57, "end": 5154.35, "text": " documented how they did", "tokens": [ 51664, 23007, 577, 436, 630, 51764 ], "temperature": 0.0, "avg_logprob": -0.19833097132769498, "compression_ratio": 1.440217391304348, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5152.57, "end": 5153.33, "word": " documented", "probability": 0.75341796875 }, { "start": 5153.33, "end": 5153.95, "word": " how", "probability": 0.8935546875 }, { "start": 5153.95, "end": 5154.15, "word": " they", "probability": 0.7470703125 }, { "start": 5154.15, "end": 5154.35, "word": " did", "probability": 0.904296875 } ] }, { "id": 1550, "seek": 498420, "start": 5154.35, "end": 5156.09, "text": " their confusion matrix versus how they", "tokens": [ 50364, 641, 15075, 8141, 5717, 577, 436, 50464 ], "temperature": 0.0, "avg_logprob": -0.17175572974081257, "compression_ratio": 1.7401574803149606, "no_speech_prob": 0.030670166015625, "words": [ { "start": 5154.35, "end": 5154.51, "word": " their", "probability": 0.53173828125 }, { "start": 5154.51, "end": 5154.93, "word": " confusion", "probability": 0.8857421875 }, { "start": 5154.93, "end": 5155.37, "word": " matrix", "probability": 0.8427734375 }, { "start": 5155.37, "end": 5155.71, "word": " versus", "probability": 0.65380859375 }, { "start": 5155.71, "end": 5155.95, "word": " how", "probability": 0.9013671875 }, { "start": 5155.95, "end": 5156.09, "word": " they", "probability": 0.736328125 } ] }, { "id": 1551, "seek": 498420, "start": 5156.09, "end": 5157.99, "text": " actually did their confusion matrix,", "tokens": [ 50464, 767, 630, 641, 15075, 8141, 11, 50564 ], "temperature": 0.0, "avg_logprob": -0.17175572974081257, "compression_ratio": 1.7401574803149606, "no_speech_prob": 0.030670166015625, "words": [ { "start": 5156.09, "end": 5156.49, "word": " actually", "probability": 0.7958984375 }, { "start": 5156.49, "end": 5156.71, "word": " did", "probability": 0.89697265625 }, { "start": 5156.71, "end": 5156.83, "word": " their", "probability": 0.8896484375 }, { "start": 5156.83, "end": 5157.25, "word": " confusion", "probability": 0.9111328125 }, { "start": 5157.25, "end": 5157.75, "word": " matrix", "probability": 0.83935546875 }, { "start": 5157.75, "end": 5157.99, "word": ",", "probability": 0.340087890625 } ] }, { "id": 1552, "seek": 498420, "start": 5157.99, "end": 5160.95, "text": " and it was swapped from what you would normally see.", "tokens": [ 50564, 293, 309, 390, 50011, 490, 437, 291, 576, 5646, 536, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.17175572974081257, "compression_ratio": 1.7401574803149606, "no_speech_prob": 0.030670166015625, "words": [ { "start": 5157.99, "end": 5158.27, "word": " and", "probability": 0.8837890625 }, { "start": 5158.27, "end": 5158.37, "word": " it", "probability": 0.89208984375 }, { "start": 5158.37, "end": 5158.55, "word": " was", "probability": 0.90478515625 }, { "start": 5158.55, "end": 5159.01, "word": " swapped", "probability": 0.75830078125 }, { "start": 5159.01, "end": 5159.33, "word": " from", "probability": 0.818359375 }, { "start": 5159.33, "end": 5159.49, "word": " what", "probability": 0.88525390625 }, { "start": 5159.49, "end": 5159.59, "word": " you", "probability": 0.89013671875 }, { "start": 5159.59, "end": 5159.71, "word": " would", "probability": 0.83642578125 }, { "start": 5159.71, "end": 5160.07, "word": " normally", "probability": 0.8564453125 }, { "start": 5160.07, "end": 5160.47, "word": " see", "probability": 0.81591796875 }, { "start": 5160.47, "end": 5160.95, "word": ".", "probability": 0.83642578125 } ] }, { "id": 1553, "seek": 498420, "start": 5161.37, "end": 5162.23, "text": " And so, following", "tokens": [ 50664, 400, 370, 11, 3480, 50764 ], "temperature": 0.0, "avg_logprob": -0.17175572974081257, "compression_ratio": 1.7401574803149606, "no_speech_prob": 0.030670166015625, "words": [ { "start": 5161.37, "end": 5161.39, "word": " And", "probability": 0.80029296875 }, { "start": 5161.39, "end": 5161.73, "word": " so", "probability": 0.88720703125 }, { "start": 5161.73, "end": 5161.81, "word": ",", "probability": 0.26953125 }, { "start": 5161.81, "end": 5162.23, "word": " following", "probability": 0.828125 } ] }, { "id": 1554, "seek": 498420, "start": 5162.23, "end": 5164.59, "text": " what you would normally see is what I did,", "tokens": [ 50764, 437, 291, 576, 5646, 536, 307, 437, 286, 630, 11, 50864 ], "temperature": 0.0, "avg_logprob": -0.17175572974081257, "compression_ratio": 1.7401574803149606, "no_speech_prob": 0.030670166015625, "words": [ { "start": 5162.23, "end": 5162.63, "word": " what", "probability": 0.88427734375 }, { "start": 5162.63, "end": 5162.75, "word": " you", "probability": 0.892578125 }, { "start": 5162.75, "end": 5162.91, "word": " would", "probability": 0.841796875 }, { "start": 5162.91, "end": 5163.23, "word": " normally", "probability": 0.8515625 }, { "start": 5163.23, "end": 5163.65, "word": " see", "probability": 0.81298828125 }, { "start": 5163.65, "end": 5163.89, "word": " is", "probability": 0.8388671875 }, { "start": 5163.89, "end": 5164.05, "word": " what", "probability": 0.88671875 }, { "start": 5164.05, "end": 5164.21, "word": " I", "probability": 0.998046875 }, { "start": 5164.21, "end": 5164.47, "word": " did", "probability": 0.8994140625 }, { "start": 5164.47, "end": 5164.59, "word": ",", "probability": 0.71484375 } ] }, { "id": 1555, "seek": 498420, "start": 5164.59, "end": 5166.61, "text": " and that's where the mistake came in.", "tokens": [ 50864, 293, 300, 311, 689, 264, 6146, 1361, 294, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.17175572974081257, "compression_ratio": 1.7401574803149606, "no_speech_prob": 0.030670166015625, "words": [ { "start": 5164.59, "end": 5164.81, "word": " and", "probability": 0.89453125 }, { "start": 5164.81, "end": 5165.05, "word": " that's", "probability": 0.937255859375 }, { "start": 5165.05, "end": 5165.21, "word": " where", "probability": 0.908203125 }, { "start": 5165.21, "end": 5165.37, "word": " the", "probability": 0.8173828125 }, { "start": 5165.37, "end": 5165.67, "word": " mistake", "probability": 0.88916015625 }, { "start": 5165.67, "end": 5165.93, "word": " came", "probability": 0.810546875 }, { "start": 5165.93, "end": 5166.17, "word": " in", "probability": 0.90576171875 }, { "start": 5166.17, "end": 5166.61, "word": ".", "probability": 0.7578125 } ] }, { "id": 1556, "seek": 498420, "start": 5166.61, "end": 5168.65, "text": " And I can actually show you that.", "tokens": [ 50964, 400, 286, 393, 767, 855, 291, 300, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.17175572974081257, "compression_ratio": 1.7401574803149606, "no_speech_prob": 0.030670166015625, "words": [ { "start": 5166.61, "end": 5166.83, "word": " And", "probability": 0.744140625 }, { "start": 5166.83, "end": 5166.89, "word": " I", "probability": 0.98291015625 }, { "start": 5166.89, "end": 5166.99, "word": " can", "probability": 0.890625 }, { "start": 5166.99, "end": 5167.29, "word": " actually", "probability": 0.78466796875 }, { "start": 5167.29, "end": 5167.67, "word": " show", "probability": 0.8857421875 }, { "start": 5167.67, "end": 5167.85, "word": " you", "probability": 0.8955078125 }, { "start": 5167.85, "end": 5168.17, "word": " that", "probability": 0.88037109375 }, { "start": 5168.17, "end": 5168.65, "word": ".", "probability": 0.9052734375 } ] }, { "id": 1557, "seek": 498420, "start": 5168.95, "end": 5170.41, "text": " I was hoping nobody noticed, but", "tokens": [ 51064, 286, 390, 7159, 5079, 5694, 11, 457, 51164 ], "temperature": 0.0, "avg_logprob": -0.17175572974081257, "compression_ratio": 1.7401574803149606, "no_speech_prob": 0.030670166015625, "words": [ { "start": 5168.95, "end": 5169.05, "word": " I", "probability": 0.875 }, { "start": 5169.05, "end": 5169.11, "word": " was", "probability": 0.8984375 }, { "start": 5169.11, "end": 5169.27, "word": " hoping", "probability": 0.833984375 }, { "start": 5169.27, "end": 5169.53, "word": " nobody", "probability": 0.81396484375 }, { "start": 5169.53, "end": 5169.97, "word": " noticed", "probability": 0.85498046875 }, { "start": 5169.97, "end": 5170.17, "word": ",", "probability": 0.8505859375 }, { "start": 5170.17, "end": 5170.41, "word": " but", "probability": 0.90185546875 } ] }, { "id": 1558, "seek": 498420, "start": 5170.41, "end": 5171.41, "text": " good eye.", "tokens": [ 51164, 665, 3313, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.17175572974081257, "compression_ratio": 1.7401574803149606, "no_speech_prob": 0.030670166015625, "words": [ { "start": 5170.41, "end": 5170.71, "word": " good", "probability": 0.66845703125 }, { "start": 5170.71, "end": 5170.93, "word": " eye", "probability": 0.873046875 }, { "start": 5170.93, "end": 5171.41, "word": ".", "probability": 0.98046875 } ] }, { "id": 1559, "seek": 498420, "start": 5172.93, "end": 5174.21, "text": " So if you look at 6,", "tokens": [ 51264, 407, 498, 291, 574, 412, 1386, 11, 51364 ], "temperature": 0.0, "avg_logprob": -0.17175572974081257, "compression_ratio": 1.7401574803149606, "no_speech_prob": 0.030670166015625, "words": [ { "start": 5172.93, "end": 5173.21, "word": " So", "probability": 0.8037109375 }, { "start": 5173.21, "end": 5173.31, "word": " if", "probability": 0.5947265625 }, { "start": 5173.31, "end": 5173.39, "word": " you", "probability": 0.89501953125 }, { "start": 5173.39, "end": 5173.51, "word": " look", "probability": 0.912109375 }, { "start": 5173.51, "end": 5173.65, "word": " at", "probability": 0.9033203125 }, { "start": 5173.65, "end": 5174.07, "word": " 6", "probability": 0.282470703125 }, { "start": 5174.07, "end": 5174.21, "word": ",", "probability": 0.51416015625 } ] }, { "id": 1560, "seek": 498420, "start": 5174.21, "end": 5176.31, "text": " actually before we go there, let's take a look", "tokens": [ 51364, 767, 949, 321, 352, 456, 11, 718, 311, 747, 257, 574, 51464 ], "temperature": 0.0, "avg_logprob": -0.17175572974081257, "compression_ratio": 1.7401574803149606, "no_speech_prob": 0.030670166015625, "words": [ { "start": 5174.21, "end": 5174.47, "word": " actually", "probability": 0.7529296875 }, { "start": 5174.47, "end": 5174.69, "word": " before", "probability": 0.58740234375 }, { "start": 5174.69, "end": 5174.85, "word": " we", "probability": 0.9013671875 }, { "start": 5174.85, "end": 5174.97, "word": " go", "probability": 0.9052734375 }, { "start": 5174.97, "end": 5175.27, "word": " there", "probability": 0.86083984375 }, { "start": 5175.27, "end": 5175.61, "word": ",", "probability": 0.89306640625 }, { "start": 5175.61, "end": 5175.81, "word": " let's", "probability": 0.9384765625 }, { "start": 5175.81, "end": 5175.97, "word": " take", "probability": 0.814453125 }, { "start": 5176.11, "end": 5176.31, "word": " a look", "probability": 0.91015625 } ] }, { "id": 1561, "seek": 498420, "start": 5176.31, "end": 5178.09, "text": " and see the count.", "tokens": [ 51464, 293, 536, 264, 1207, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.17175572974081257, "compression_ratio": 1.7401574803149606, "no_speech_prob": 0.030670166015625, "words": [ { "start": 5176.31, "end": 5176.75, "word": " and", "probability": 0.85009765625 }, { "start": 5176.75, "end": 5177.49, "word": " see", "probability": 0.791015625 }, { "start": 5177.49, "end": 5177.65, "word": " the", "probability": 0.81689453125 }, { "start": 5177.65, "end": 5177.99, "word": " count", "probability": 0.5048828125 }, { "start": 5177.99, "end": 5178.09, "word": ".", "probability": 0.951171875 } ] }, { "id": 1562, "seek": 498420, "start": 5178.09, "end": 5180.19, "text": " So we have 590 ham emails in our", "tokens": [ 51564, 407, 321, 362, 1025, 7771, 7852, 12524, 294, 527, 51664 ], "temperature": 0.0, "avg_logprob": -0.17175572974081257, "compression_ratio": 1.7401574803149606, "no_speech_prob": 0.030670166015625, "words": [ { "start": 5178.09, "end": 5178.17, "word": " So", "probability": 0.89013671875 }, { "start": 5178.17, "end": 5178.23, "word": " we", "probability": 0.84033203125 }, { "start": 5178.23, "end": 5178.33, "word": " have", "probability": 0.81787109375 }, { "start": 5178.33, "end": 5178.99, "word": " 590", "probability": 0.939697265625 }, { "start": 5178.99, "end": 5179.37, "word": " ham", "probability": 0.693359375 }, { "start": 5179.37, "end": 5179.75, "word": " emails", "probability": 0.740234375 }, { "start": 5179.75, "end": 5180.05, "word": " in", "probability": 0.890625 }, { "start": 5180.05, "end": 5180.19, "word": " our", "probability": 0.81689453125 } ] }, { "id": 1563, "seek": 498420, "start": 5180.19, "end": 5181.95, "text": " test dataset, 276", "tokens": [ 51664, 1500, 28872, 11, 7634, 21, 51764 ], "temperature": 0.0, "avg_logprob": -0.17175572974081257, "compression_ratio": 1.7401574803149606, "no_speech_prob": 0.030670166015625, "words": [ { "start": 5180.19, "end": 5180.41, "word": " test", "probability": 0.82861328125 }, { "start": 5180.41, "end": 5180.75, "word": " dataset", "probability": 0.33154296875 }, { "start": 5180.75, "end": 5181.03, "word": ",", "probability": 0.76220703125 }, { "start": 5181.03, "end": 5181.95, "word": " 276", "probability": 0.89892578125 } ] }, { "id": 1564, "seek": 501192, "start": 5181.95, "end": 5183.59, "text": " spam emails in our", "tokens": [ 50364, 24028, 12524, 294, 527, 50464 ], "temperature": 0.0, "avg_logprob": -0.1777712213543226, "compression_ratio": 1.5297297297297296, "no_speech_prob": 0.0311431884765625, "words": [ { "start": 5181.95, "end": 5182.31, "word": " spam", "probability": 0.54052734375 }, { "start": 5182.31, "end": 5182.77, "word": " emails", "probability": 0.74755859375 }, { "start": 5182.77, "end": 5183.47, "word": " in", "probability": 0.880859375 }, { "start": 5183.47, "end": 5183.59, "word": " our", "probability": 0.8212890625 } ] }, { "id": 1565, "seek": 501192, "start": 5183.59, "end": 5185.79, "text": " test dataset. And so if we", "tokens": [ 50464, 1500, 28872, 13, 400, 370, 498, 321, 50564 ], "temperature": 0.0, "avg_logprob": -0.1777712213543226, "compression_ratio": 1.5297297297297296, "no_speech_prob": 0.0311431884765625, "words": [ { "start": 5183.59, "end": 5183.93, "word": " test", "probability": 0.81494140625 }, { "start": 5183.93, "end": 5184.41, "word": " dataset", "probability": 0.342529296875 }, { "start": 5184.41, "end": 5185.09, "word": ".", "probability": 0.8701171875 }, { "start": 5185.29, "end": 5185.39, "word": " And", "probability": 0.8076171875 }, { "start": 5185.39, "end": 5185.55, "word": " so", "probability": 0.8935546875 }, { "start": 5185.55, "end": 5185.67, "word": " if", "probability": 0.771484375 }, { "start": 5185.67, "end": 5185.79, "word": " we", "probability": 0.900390625 } ] }, { "id": 1566, "seek": 501192, "start": 5185.79, "end": 5188.31, "text": " look at 6A,", "tokens": [ 50564, 574, 412, 1386, 32, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.1777712213543226, "compression_ratio": 1.5297297297297296, "no_speech_prob": 0.0311431884765625, "words": [ { "start": 5185.79, "end": 5186.11, "word": " look", "probability": 0.9140625 }, { "start": 5186.11, "end": 5186.45, "word": " at", "probability": 0.9052734375 }, { "start": 5186.45, "end": 5187.27, "word": " 6A", "probability": 0.735107421875 }, { "start": 5187.27, "end": 5188.31, "word": ",", "probability": 0.8271484375 } ] }, { "id": 1567, "seek": 501192, "start": 5188.31, "end": 5189.75, "text": " we see 590 ham", "tokens": [ 50664, 321, 536, 1025, 7771, 7852, 50764 ], "temperature": 0.0, "avg_logprob": -0.1777712213543226, "compression_ratio": 1.5297297297297296, "no_speech_prob": 0.0311431884765625, "words": [ { "start": 5188.31, "end": 5188.67, "word": " we", "probability": 0.853515625 }, { "start": 5188.67, "end": 5188.79, "word": " see", "probability": 0.79296875 }, { "start": 5188.79, "end": 5189.45, "word": " 590", "probability": 0.938720703125 }, { "start": 5189.45, "end": 5189.75, "word": " ham", "probability": 0.54833984375 } ] }, { "id": 1568, "seek": 501192, "start": 5189.75, "end": 5191.63, "text": " emails, but", "tokens": [ 50764, 12524, 11, 457, 50864 ], "temperature": 0.0, "avg_logprob": -0.1777712213543226, "compression_ratio": 1.5297297297297296, "no_speech_prob": 0.0311431884765625, "words": [ { "start": 5189.75, "end": 5190.29, "word": " emails", "probability": 0.74609375 }, { "start": 5190.29, "end": 5190.99, "word": ",", "probability": 0.482177734375 }, { "start": 5190.99, "end": 5191.63, "word": " but", "probability": 0.8984375 } ] }, { "id": 1569, "seek": 501192, "start": 5191.63, "end": 5193.77, "text": " as far as actual label, we", "tokens": [ 50864, 382, 1400, 382, 3539, 7645, 11, 321, 50964 ], "temperature": 0.0, "avg_logprob": -0.1777712213543226, "compression_ratio": 1.5297297297297296, "no_speech_prob": 0.0311431884765625, "words": [ { "start": 5191.63, "end": 5192.45, "word": " as", "probability": 0.8369140625 }, { "start": 5192.45, "end": 5192.61, "word": " far", "probability": 0.900390625 }, { "start": 5192.61, "end": 5192.73, "word": " as", "probability": 0.90625 }, { "start": 5192.73, "end": 5193.13, "word": " actual", "probability": 0.794921875 }, { "start": 5193.13, "end": 5193.51, "word": " label", "probability": 0.79638671875 }, { "start": 5193.51, "end": 5193.67, "word": ",", "probability": 0.890625 }, { "start": 5193.67, "end": 5193.77, "word": " we", "probability": 0.8984375 } ] }, { "id": 1570, "seek": 501192, "start": 5193.77, "end": 5195.65, "text": " should see in the column for spam", "tokens": [ 50964, 820, 536, 294, 264, 7738, 337, 24028, 51064 ], "temperature": 0.0, "avg_logprob": -0.1777712213543226, "compression_ratio": 1.5297297297297296, "no_speech_prob": 0.0311431884765625, "words": [ { "start": 5193.77, "end": 5193.93, "word": " should", "probability": 0.91943359375 }, { "start": 5193.93, "end": 5194.25, "word": " see", "probability": 0.81591796875 }, { "start": 5194.25, "end": 5194.49, "word": " in", "probability": 0.88818359375 }, { "start": 5194.49, "end": 5194.65, "word": " the", "probability": 0.822265625 }, { "start": 5194.65, "end": 5194.99, "word": " column", "probability": 0.81982421875 }, { "start": 5194.99, "end": 5195.27, "word": " for", "probability": 0.529296875 }, { "start": 5195.27, "end": 5195.65, "word": " spam", "probability": 0.89208984375 } ] }, { "id": 1571, "seek": 501192, "start": 5195.97, "end": 5197.33, "text": " a total of the", "tokens": [ 51064, 257, 3217, 295, 264, 51164 ], "temperature": 0.0, "avg_logprob": -0.1777712213543226, "compression_ratio": 1.5297297297297296, "no_speech_prob": 0.0311431884765625, "words": [ { "start": 5195.97, "end": 5196.31, "word": " a total", "probability": 0.794921875 }, { "start": 5196.31, "end": 5197.03, "word": " of", "probability": 0.90087890625 }, { "start": 5197.03, "end": 5197.33, "word": " the", "probability": 0.75439453125 } ] }, { "id": 1572, "seek": 501192, "start": 5197.95, "end": 5199.89, "text": " 276. We don't see", "tokens": [ 51164, 7634, 21, 13, 492, 500, 380, 536, 51264 ], "temperature": 0.0, "avg_logprob": -0.1777712213543226, "compression_ratio": 1.5297297297297296, "no_speech_prob": 0.0311431884765625, "words": [ { "start": 5197.95, "end": 5198.49, "word": " 276", "probability": 0.895751953125 }, { "start": 5198.49, "end": 5198.83, "word": ".", "probability": 0.72265625 }, { "start": 5198.83, "end": 5199.21, "word": " We", "probability": 0.90087890625 }, { "start": 5199.21, "end": 5199.59, "word": " don't", "probability": 0.947021484375 }, { "start": 5199.59, "end": 5199.89, "word": " see", "probability": 0.81396484375 } ] }, { "id": 1573, "seek": 501192, "start": 5199.89, "end": 5201.65, "text": " that. And the reason why", "tokens": [ 51264, 300, 13, 400, 264, 1778, 983, 51364 ], "temperature": 0.0, "avg_logprob": -0.1777712213543226, "compression_ratio": 1.5297297297297296, "no_speech_prob": 0.0311431884765625, "words": [ { "start": 5199.89, "end": 5200.19, "word": " that", "probability": 0.88232421875 }, { "start": 5200.19, "end": 5200.87, "word": ".", "probability": 0.8955078125 }, { "start": 5200.95, "end": 5201.03, "word": " And", "probability": 0.73681640625 }, { "start": 5201.03, "end": 5201.13, "word": " the", "probability": 0.81982421875 }, { "start": 5201.13, "end": 5201.29, "word": " reason", "probability": 0.9111328125 }, { "start": 5201.29, "end": 5201.65, "word": " why", "probability": 0.81591796875 } ] }, { "id": 1574, "seek": 501192, "start": 5201.65, "end": 5203.67, "text": " is because this is supposed to be", "tokens": [ 51364, 307, 570, 341, 307, 3442, 281, 312, 51464 ], "temperature": 0.0, "avg_logprob": -0.1777712213543226, "compression_ratio": 1.5297297297297296, "no_speech_prob": 0.0311431884765625, "words": [ { "start": 5201.65, "end": 5201.89, "word": " is", "probability": 0.861328125 }, { "start": 5201.89, "end": 5202.27, "word": " because", "probability": 0.83349609375 }, { "start": 5202.27, "end": 5202.81, "word": " this", "probability": 0.86962890625 }, { "start": 5202.81, "end": 5203.07, "word": " is", "probability": 0.90380859375 }, { "start": 5203.07, "end": 5203.29, "word": " supposed", "probability": 0.9072265625 }, { "start": 5203.29, "end": 5203.57, "word": " to", "probability": 0.90673828125 }, { "start": 5203.57, "end": 5203.67, "word": " be", "probability": 0.90966796875 } ] }, { "id": 1575, "seek": 501192, "start": 5203.67, "end": 5205.35, "text": " the actual, see", "tokens": [ 51464, 264, 3539, 11, 536, 51564 ], "temperature": 0.0, "avg_logprob": -0.1777712213543226, "compression_ratio": 1.5297297297297296, "no_speech_prob": 0.0311431884765625, "words": [ { "start": 5203.67, "end": 5203.89, "word": " the", "probability": 0.818359375 }, { "start": 5203.89, "end": 5204.33, "word": " actual", "probability": 0.79833984375 }, { "start": 5204.33, "end": 5205.13, "word": ",", "probability": 0.64208984375 }, { "start": 5205.13, "end": 5205.35, "word": " see", "probability": 0.2005615234375 } ] }, { "id": 1576, "seek": 501192, "start": 5205.35, "end": 5208.79, "text": " 108 plus 168 is 276,", "tokens": [ 51564, 41342, 1804, 3165, 23, 307, 7634, 21, 11, 51664 ], "temperature": 0.0, "avg_logprob": -0.1777712213543226, "compression_ratio": 1.5297297297297296, "no_speech_prob": 0.0311431884765625, "words": [ { "start": 5205.35, "end": 5205.69, "word": " 108", "probability": 0.65673828125 }, { "start": 5205.69, "end": 5206.07, "word": " plus", "probability": 0.79736328125 }, { "start": 5206.07, "end": 5206.83, "word": " 168", "probability": 0.8876953125 }, { "start": 5206.83, "end": 5207.03, "word": " is", "probability": 0.89306640625 }, { "start": 5207.03, "end": 5208.15, "word": " 276", "probability": 0.886962890625 }, { "start": 5208.15, "end": 5208.79, "word": ",", "probability": 0.26171875 } ] }, { "id": 1577, "seek": 501192, "start": 5208.79, "end": 5209.67, "text": " and then", "tokens": [ 51664, 293, 550, 51764 ], "temperature": 0.0, "avg_logprob": -0.1777712213543226, "compression_ratio": 1.5297297297297296, "no_speech_prob": 0.0311431884765625, "words": [ { "start": 5208.79, "end": 5209.55, "word": " and", "probability": 0.884765625 }, { "start": 5209.55, "end": 5209.67, "word": " then", "probability": 0.724609375 } ] }, { "id": 1578, "seek": 503960, "start": 5209.67, "end": 5211.75, "text": " this was supposed to be the predicted.", "tokens": [ 50364, 341, 390, 3442, 281, 312, 264, 19147, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.16488094670431955, "compression_ratio": 1.5586854460093897, "no_speech_prob": 0.02032470703125, "words": [ { "start": 5209.67, "end": 5209.91, "word": " this", "probability": 0.182861328125 }, { "start": 5209.91, "end": 5210.07, "word": " was", "probability": 0.86474609375 }, { "start": 5210.07, "end": 5210.33, "word": " supposed", "probability": 0.90283203125 }, { "start": 5210.33, "end": 5210.53, "word": " to", "probability": 0.90625 }, { "start": 5210.53, "end": 5210.61, "word": " be", "probability": 0.9033203125 }, { "start": 5210.61, "end": 5210.77, "word": " the", "probability": 0.80126953125 }, { "start": 5210.77, "end": 5211.15, "word": " predicted", "probability": 0.712890625 }, { "start": 5211.15, "end": 5211.75, "word": ".", "probability": 0.90185546875 } ] }, { "id": 1579, "seek": 503960, "start": 5211.79, "end": 5213.03, "text": " The problem is", "tokens": [ 50464, 440, 1154, 307, 50564 ], "temperature": 0.0, "avg_logprob": -0.16488094670431955, "compression_ratio": 1.5586854460093897, "no_speech_prob": 0.02032470703125, "words": [ { "start": 5211.79, "end": 5212.11, "word": " The", "probability": 0.77880859375 }, { "start": 5212.11, "end": 5212.51, "word": " problem", "probability": 0.740234375 }, { "start": 5212.51, "end": 5213.03, "word": " is", "probability": 0.9052734375 } ] }, { "id": 1580, "seek": 503960, "start": 5213.41, "end": 5214.73, "text": " the way that scikit-learn", "tokens": [ 50564, 264, 636, 300, 2180, 22681, 12, 306, 1083, 50664 ], "temperature": 0.0, "avg_logprob": -0.16488094670431955, "compression_ratio": 1.5586854460093897, "no_speech_prob": 0.02032470703125, "words": [ { "start": 5213.41, "end": 5213.71, "word": " the", "probability": 0.67236328125 }, { "start": 5213.71, "end": 5213.89, "word": " way", "probability": 0.90283203125 }, { "start": 5213.89, "end": 5214.11, "word": " that", "probability": 0.8447265625 }, { "start": 5214.11, "end": 5214.39, "word": " scikit", "probability": 0.7232666015625 }, { "start": 5214.39, "end": 5214.73, "word": "-learn", "probability": 0.9471028645833334 } ] }, { "id": 1581, "seek": 503960, "start": 5215.63, "end": 5217.73, "text": " swapped them,", "tokens": [ 50664, 50011, 552, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.16488094670431955, "compression_ratio": 1.5586854460093897, "no_speech_prob": 0.02032470703125, "words": [ { "start": 5215.63, "end": 5216.23, "word": " swapped", "probability": 0.6689453125 }, { "start": 5216.23, "end": 5216.47, "word": " them", "probability": 0.74560546875 }, { "start": 5216.47, "end": 5217.73, "word": ",", "probability": 0.433349609375 } ] }, { "id": 1582, "seek": 503960, "start": 5217.73, "end": 5219.65, "text": " and I guess I did not swap", "tokens": [ 50764, 293, 286, 2041, 286, 630, 406, 18135, 50864 ], "temperature": 0.0, "avg_logprob": -0.16488094670431955, "compression_ratio": 1.5586854460093897, "no_speech_prob": 0.02032470703125, "words": [ { "start": 5217.73, "end": 5218.09, "word": " and", "probability": 0.833984375 }, { "start": 5218.09, "end": 5218.27, "word": " I", "probability": 0.98046875 }, { "start": 5218.27, "end": 5218.69, "word": " guess", "probability": 0.8203125 }, { "start": 5218.69, "end": 5218.81, "word": " I", "probability": 0.95361328125 }, { "start": 5218.81, "end": 5218.95, "word": " did", "probability": 0.87939453125 }, { "start": 5218.95, "end": 5219.21, "word": " not", "probability": 0.89892578125 }, { "start": 5219.21, "end": 5219.65, "word": " swap", "probability": 0.93359375 } ] }, { "id": 1583, "seek": 503960, "start": 5219.65, "end": 5220.75, "text": " them back.", "tokens": [ 50864, 552, 646, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.16488094670431955, "compression_ratio": 1.5586854460093897, "no_speech_prob": 0.02032470703125, "words": [ { "start": 5219.65, "end": 5219.81, "word": " them", "probability": 0.7265625 }, { "start": 5219.81, "end": 5220.15, "word": " back", "probability": 0.822265625 }, { "start": 5220.15, "end": 5220.75, "word": ".", "probability": 0.57421875 } ] }, { "id": 1584, "seek": 503960, "start": 5222.29, "end": 5223.63, "text": " To get the", "tokens": [ 50964, 1407, 483, 264, 51064 ], "temperature": 0.0, "avg_logprob": -0.16488094670431955, "compression_ratio": 1.5586854460093897, "no_speech_prob": 0.02032470703125, "words": [ { "start": 5222.29, "end": 5222.89, "word": " To", "probability": 0.8896484375 }, { "start": 5222.89, "end": 5223.37, "word": " get", "probability": 0.89208984375 }, { "start": 5223.37, "end": 5223.63, "word": " the", "probability": 0.81103515625 } ] }, { "id": 1585, "seek": 503960, "start": 5223.63, "end": 5225.53, "text": " correct result, you just need to switch the", "tokens": [ 51064, 3006, 1874, 11, 291, 445, 643, 281, 3679, 264, 51164 ], "temperature": 0.0, "avg_logprob": -0.16488094670431955, "compression_ratio": 1.5586854460093897, "no_speech_prob": 0.02032470703125, "words": [ { "start": 5223.63, "end": 5223.91, "word": " correct", "probability": 0.87646484375 }, { "start": 5223.91, "end": 5224.23, "word": " result", "probability": 0.7763671875 }, { "start": 5224.23, "end": 5224.31, "word": ",", "probability": 0.65185546875 }, { "start": 5224.31, "end": 5224.39, "word": " you", "probability": 0.89208984375 }, { "start": 5224.39, "end": 5224.55, "word": " just", "probability": 0.87841796875 }, { "start": 5224.55, "end": 5224.67, "word": " need", "probability": 0.79296875 }, { "start": 5224.67, "end": 5224.83, "word": " to", "probability": 0.90234375 }, { "start": 5224.83, "end": 5225.25, "word": " switch", "probability": 0.93408203125 }, { "start": 5225.25, "end": 5225.53, "word": " the", "probability": 0.81640625 } ] }, { "id": 1586, "seek": 503960, "start": 5225.53, "end": 5227.75, "text": " test labels and the predictions", "tokens": [ 51164, 1500, 16949, 293, 264, 21264, 51264 ], "temperature": 0.0, "avg_logprob": -0.16488094670431955, "compression_ratio": 1.5586854460093897, "no_speech_prob": 0.02032470703125, "words": [ { "start": 5225.53, "end": 5225.81, "word": " test", "probability": 0.82763671875 }, { "start": 5225.81, "end": 5226.19, "word": " labels", "probability": 0.86865234375 }, { "start": 5226.19, "end": 5226.95, "word": " and", "probability": 0.84423828125 }, { "start": 5226.95, "end": 5227.25, "word": " the", "probability": 0.814453125 }, { "start": 5227.25, "end": 5227.75, "word": " predictions", "probability": 0.72509765625 } ] }, { "id": 1587, "seek": 503960, "start": 5227.75, "end": 5229.93, "text": " MNB on both sides", "tokens": [ 51264, 376, 45, 33, 322, 1293, 4881, 51364 ], "temperature": 0.0, "avg_logprob": -0.16488094670431955, "compression_ratio": 1.5586854460093897, "no_speech_prob": 0.02032470703125, "words": [ { "start": 5227.75, "end": 5228.33, "word": " MNB", "probability": 0.6161702473958334 }, { "start": 5228.33, "end": 5228.97, "word": " on", "probability": 0.90087890625 }, { "start": 5228.97, "end": 5229.39, "word": " both", "probability": 0.80810546875 }, { "start": 5229.39, "end": 5229.93, "word": " sides", "probability": 0.79296875 } ] }, { "id": 1588, "seek": 503960, "start": 5229.93, "end": 5231.77, "text": " for the confusion matrix", "tokens": [ 51364, 337, 264, 15075, 8141, 51464 ], "temperature": 0.0, "avg_logprob": -0.16488094670431955, "compression_ratio": 1.5586854460093897, "no_speech_prob": 0.02032470703125, "words": [ { "start": 5229.93, "end": 5231.01, "word": " for", "probability": 0.78466796875 }, { "start": 5231.01, "end": 5231.15, "word": " the", "probability": 0.8134765625 }, { "start": 5231.15, "end": 5231.45, "word": " confusion", "probability": 0.86669921875 }, { "start": 5231.45, "end": 5231.77, "word": " matrix", "probability": 0.85986328125 } ] }, { "id": 1589, "seek": 503960, "start": 5231.77, "end": 5233.63, "text": " and the classification report.", "tokens": [ 51464, 293, 264, 21538, 2275, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.16488094670431955, "compression_ratio": 1.5586854460093897, "no_speech_prob": 0.02032470703125, "words": [ { "start": 5231.77, "end": 5232.05, "word": " and", "probability": 0.857421875 }, { "start": 5232.05, "end": 5232.15, "word": " the", "probability": 0.80859375 }, { "start": 5232.15, "end": 5232.59, "word": " classification", "probability": 0.9404296875 }, { "start": 5232.59, "end": 5233.03, "word": " report", "probability": 0.7685546875 }, { "start": 5233.03, "end": 5233.63, "word": ".", "probability": 0.9814453125 } ] }, { "id": 1590, "seek": 503960, "start": 5234.63, "end": 5235.49, "text": " So, yeah.", "tokens": [ 51564, 407, 11, 1338, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.16488094670431955, "compression_ratio": 1.5586854460093897, "no_speech_prob": 0.02032470703125, "words": [ { "start": 5234.63, "end": 5234.65, "word": " So", "probability": 0.634765625 }, { "start": 5234.65, "end": 5235.17, "word": ",", "probability": 0.30859375 }, { "start": 5235.17, "end": 5235.39, "word": " yeah", "probability": 0.8564453125 }, { "start": 5235.39, "end": 5235.49, "word": ".", "probability": 0.17724609375 } ] }, { "id": 1591, "seek": 503960, "start": 5235.49, "end": 5237.35, "text": " That's why they seem swapped.", "tokens": [ 51664, 663, 311, 983, 436, 1643, 50011, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.16488094670431955, "compression_ratio": 1.5586854460093897, "no_speech_prob": 0.02032470703125, "words": [ { "start": 5235.49, "end": 5235.75, "word": " That's", "probability": 0.90380859375 }, { "start": 5235.75, "end": 5235.91, "word": " why", "probability": 0.80859375 }, { "start": 5235.91, "end": 5236.15, "word": " they", "probability": 0.73876953125 }, { "start": 5236.15, "end": 5236.53, "word": " seem", "probability": 0.70458984375 }, { "start": 5236.53, "end": 5236.97, "word": " swapped", "probability": 0.76171875 }, { "start": 5236.97, "end": 5237.35, "word": ".", "probability": 0.93896484375 } ] }, { "id": 1592, "seek": 506760, "start": 5237.35, "end": 5239.21, "text": " The one on the completed workbook", "tokens": [ 50364, 440, 472, 322, 264, 7365, 589, 2939, 50464 ], "temperature": 0.0, "avg_logprob": -0.178246354593814, "compression_ratio": 1.5213270142180095, "no_speech_prob": 0.0275726318359375, "words": [ { "start": 5237.35, "end": 5237.51, "word": " The", "probability": 0.439453125 }, { "start": 5237.51, "end": 5237.99, "word": " one", "probability": 0.8125 }, { "start": 5237.99, "end": 5238.27, "word": " on", "probability": 0.91259765625 }, { "start": 5238.27, "end": 5238.45, "word": " the", "probability": 0.806640625 }, { "start": 5238.45, "end": 5238.79, "word": " completed", "probability": 0.62744140625 }, { "start": 5238.79, "end": 5239.21, "word": " workbook", "probability": 0.906005859375 } ] }, { "id": 1593, "seek": 506760, "start": 5239.21, "end": 5241.23, "text": " is correct, because I believe", "tokens": [ 50464, 307, 3006, 11, 570, 286, 1697, 50564 ], "temperature": 0.0, "avg_logprob": -0.178246354593814, "compression_ratio": 1.5213270142180095, "no_speech_prob": 0.0275726318359375, "words": [ { "start": 5239.21, "end": 5239.47, "word": " is", "probability": 0.89892578125 }, { "start": 5239.47, "end": 5239.95, "word": " correct", "probability": 0.8759765625 }, { "start": 5239.95, "end": 5240.39, "word": ",", "probability": 0.36767578125 }, { "start": 5240.39, "end": 5240.81, "word": " because", "probability": 0.8271484375 }, { "start": 5240.81, "end": 5241.05, "word": " I", "probability": 0.97900390625 }, { "start": 5241.05, "end": 5241.23, "word": " believe", "probability": 0.73974609375 } ] }, { "id": 1594, "seek": 506760, "start": 5241.23, "end": 5242.49, "text": " the completed workbook", "tokens": [ 50564, 264, 7365, 589, 2939, 50664 ], "temperature": 0.0, "avg_logprob": -0.178246354593814, "compression_ratio": 1.5213270142180095, "no_speech_prob": 0.0275726318359375, "words": [ { "start": 5241.23, "end": 5241.41, "word": " the", "probability": 0.7958984375 }, { "start": 5241.41, "end": 5241.79, "word": " completed", "probability": 0.638671875 }, { "start": 5241.79, "end": 5242.49, "word": " workbook", "probability": 0.903564453125 } ] }, { "id": 1595, "seek": 506760, "start": 5243.59, "end": 5245.09, "text": " shows in the actual label", "tokens": [ 50664, 3110, 294, 264, 3539, 7645, 50764 ], "temperature": 0.0, "avg_logprob": -0.178246354593814, "compression_ratio": 1.5213270142180095, "no_speech_prob": 0.0275726318359375, "words": [ { "start": 5243.59, "end": 5244.11, "word": " shows", "probability": 0.78955078125 }, { "start": 5244.11, "end": 5244.39, "word": " in", "probability": 0.79248046875 }, { "start": 5244.39, "end": 5244.51, "word": " the", "probability": 0.8154296875 }, { "start": 5244.51, "end": 5244.79, "word": " actual", "probability": 0.80859375 }, { "start": 5244.79, "end": 5245.09, "word": " label", "probability": 0.80615234375 } ] }, { "id": 1596, "seek": 506760, "start": 5245.09, "end": 5247.21, "text": " column the spam emails, and if you total", "tokens": [ 50764, 7738, 264, 24028, 12524, 11, 293, 498, 291, 3217, 50864 ], "temperature": 0.0, "avg_logprob": -0.178246354593814, "compression_ratio": 1.5213270142180095, "no_speech_prob": 0.0275726318359375, "words": [ { "start": 5245.09, "end": 5245.63, "word": " column", "probability": 0.8076171875 }, { "start": 5245.63, "end": 5245.87, "word": " the", "probability": 0.51904296875 }, { "start": 5245.87, "end": 5246.13, "word": " spam", "probability": 0.93359375 }, { "start": 5246.13, "end": 5246.51, "word": " emails", "probability": 0.7548828125 }, { "start": 5246.51, "end": 5246.65, "word": ",", "probability": 0.45849609375 }, { "start": 5246.65, "end": 5246.71, "word": " and", "probability": 0.89208984375 }, { "start": 5246.71, "end": 5246.83, "word": " if", "probability": 0.90771484375 }, { "start": 5246.83, "end": 5246.95, "word": " you", "probability": 0.8896484375 }, { "start": 5246.95, "end": 5247.21, "word": " total", "probability": 0.8486328125 } ] }, { "id": 1597, "seek": 506760, "start": 5247.21, "end": 5249.65, "text": " the two numbers, you get 276.", "tokens": [ 50864, 264, 732, 3547, 11, 291, 483, 7634, 21, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.178246354593814, "compression_ratio": 1.5213270142180095, "no_speech_prob": 0.0275726318359375, "words": [ { "start": 5247.21, "end": 5247.39, "word": " the", "probability": 0.80224609375 }, { "start": 5247.39, "end": 5247.55, "word": " two", "probability": 0.81640625 }, { "start": 5247.55, "end": 5247.89, "word": " numbers", "probability": 0.85986328125 }, { "start": 5247.89, "end": 5247.99, "word": ",", "probability": 0.66162109375 }, { "start": 5247.99, "end": 5248.05, "word": " you", "probability": 0.89501953125 }, { "start": 5248.05, "end": 5248.17, "word": " get", "probability": 0.900390625 }, { "start": 5248.17, "end": 5249.13, "word": " 276", "probability": 0.886474609375 }, { "start": 5249.13, "end": 5249.65, "word": ".", "probability": 0.88916015625 } ] }, { "id": 1598, "seek": 506760, "start": 5249.67, "end": 5251.51, "text": " So, good eye on that.", "tokens": [ 50964, 407, 11, 665, 3313, 322, 300, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.178246354593814, "compression_ratio": 1.5213270142180095, "no_speech_prob": 0.0275726318359375, "words": [ { "start": 5249.67, "end": 5249.95, "word": " So", "probability": 0.84765625 }, { "start": 5249.95, "end": 5250.09, "word": ",", "probability": 0.4130859375 }, { "start": 5250.09, "end": 5250.23, "word": " good", "probability": 0.87841796875 }, { "start": 5250.23, "end": 5250.49, "word": " eye", "probability": 0.9130859375 }, { "start": 5250.49, "end": 5250.75, "word": " on", "probability": 0.89111328125 }, { "start": 5250.75, "end": 5250.99, "word": " that", "probability": 0.8828125 }, { "start": 5250.99, "end": 5251.51, "word": ".", "probability": 0.966796875 } ] }, { "id": 1599, "seek": 506760, "start": 5254.98, "end": 5256.74, "text": " Go ahead and check this.", "tokens": [ 51164, 1037, 2286, 293, 1520, 341, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.178246354593814, "compression_ratio": 1.5213270142180095, "no_speech_prob": 0.0275726318359375, "words": [ { "start": 5254.98, "end": 5255.26, "word": " Go", "probability": 0.607421875 }, { "start": 5255.26, "end": 5255.48, "word": " ahead", "probability": 0.83544921875 }, { "start": 5255.48, "end": 5255.6, "word": " and", "probability": 0.87548828125 }, { "start": 5255.6, "end": 5255.8, "word": " check", "probability": 0.82470703125 }, { "start": 5255.8, "end": 5256.22, "word": " this", "probability": 0.88232421875 }, { "start": 5256.22, "end": 5256.74, "word": ".", "probability": 0.6923828125 } ] }, { "id": 1600, "seek": 506760, "start": 5256.98, "end": 5257.76, "text": " Perfect.", "tokens": [ 51264, 10246, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.178246354593814, "compression_ratio": 1.5213270142180095, "no_speech_prob": 0.0275726318359375, "words": [ { "start": 5256.98, "end": 5257.24, "word": " Perfect", "probability": 0.79736328125 }, { "start": 5257.24, "end": 5257.76, "word": ".", "probability": 0.9892578125 } ] }, { "id": 1601, "seek": 506760, "start": 5261.22, "end": 5263.2, "text": " Before we ran into the problems,", "tokens": [ 51464, 4546, 321, 5872, 666, 264, 2740, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.178246354593814, "compression_ratio": 1.5213270142180095, "no_speech_prob": 0.0275726318359375, "words": [ { "start": 5261.22, "end": 5261.74, "word": " Before", "probability": 0.11822509765625 }, { "start": 5261.74, "end": 5262.26, "word": " we", "probability": 0.90869140625 }, { "start": 5262.26, "end": 5262.46, "word": " ran", "probability": 0.73046875 }, { "start": 5262.46, "end": 5262.58, "word": " into", "probability": 0.73046875 }, { "start": 5262.58, "end": 5262.74, "word": " the", "probability": 0.80908203125 }, { "start": 5262.74, "end": 5263.1, "word": " problems", "probability": 0.70556640625 }, { "start": 5263.1, "end": 5263.2, "word": ",", "probability": 0.9697265625 } ] }, { "id": 1602, "seek": 506760, "start": 5263.2, "end": 5264.14, "text": " we're going to look at", "tokens": [ 51564, 321, 434, 516, 281, 574, 412, 51664 ], "temperature": 0.0, "avg_logprob": -0.178246354593814, "compression_ratio": 1.5213270142180095, "no_speech_prob": 0.0275726318359375, "words": [ { "start": 5263.2, "end": 5263.4, "word": " we're", "probability": 0.91943359375 }, { "start": 5263.4, "end": 5263.44, "word": " going", "probability": 0.23974609375 }, { "start": 5263.44, "end": 5263.48, "word": " to", "probability": 0.90185546875 }, { "start": 5263.48, "end": 5263.62, "word": " look", "probability": 0.91650390625 }, { "start": 5263.62, "end": 5264.14, "word": " at", "probability": 0.9052734375 } ] }, { "id": 1603, "seek": 506760, "start": 5264.74, "end": 5267.0, "text": " 6C and 6D with a logistic", "tokens": [ 51664, 1386, 34, 293, 1386, 35, 365, 257, 3565, 3142, 51764 ], "temperature": 0.0, "avg_logprob": -0.178246354593814, "compression_ratio": 1.5213270142180095, "no_speech_prob": 0.0275726318359375, "words": [ { "start": 5264.74, "end": 5265.26, "word": " 6C", "probability": 0.80810546875 }, { "start": 5265.26, "end": 5265.56, "word": " and", "probability": 0.89111328125 }, { "start": 5265.56, "end": 5266.12, "word": " 6D", "probability": 0.998291015625 }, { "start": 5266.12, "end": 5266.6, "word": " with", "probability": 0.619140625 }, { "start": 5266.72, "end": 5267.0, "word": " a logistic", "probability": 0.9287109375 } ] }, { "id": 1604, "seek": 509554, "start": 5267.0, "end": 5268.1, "text": " regression.", "tokens": [ 50364, 24590, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.16771788498677245, "compression_ratio": 1.5401069518716577, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 5267.0, "end": 5267.42, "word": " regression", "probability": 0.301513671875 }, { "start": 5267.42, "end": 5268.1, "word": ".", "probability": 0.6025390625 } ] }, { "id": 1605, "seek": 509554, "start": 5268.72, "end": 5271.02, "text": " Remember, we had 0.85", "tokens": [ 50464, 5459, 11, 321, 632, 1958, 13, 19287, 50564 ], "temperature": 0.0, "avg_logprob": -0.16771788498677245, "compression_ratio": 1.5401069518716577, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 5268.72, "end": 5269.4, "word": " Remember", "probability": 0.8671875 }, { "start": 5269.4, "end": 5269.7, "word": ",", "probability": 0.289794921875 }, { "start": 5269.7, "end": 5269.82, "word": " we", "probability": 0.89892578125 }, { "start": 5269.82, "end": 5270.22, "word": " had", "probability": 0.8154296875 }, { "start": 5270.22, "end": 5270.68, "word": " 0", "probability": 0.505859375 }, { "start": 5270.68, "end": 5271.02, "word": ".85", "probability": 0.9580078125 } ] }, { "id": 1606, "seek": 509554, "start": 5272.0, "end": 5273.32, "text": " or 0.87", "tokens": [ 50564, 420, 1958, 13, 23853, 50664 ], "temperature": 0.0, "avg_logprob": -0.16771788498677245, "compression_ratio": 1.5401069518716577, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 5272.0, "end": 5272.68, "word": " or", "probability": 0.7275390625 }, { "start": 5272.68, "end": 5272.9, "word": " 0", "probability": 0.94580078125 }, { "start": 5272.9, "end": 5273.32, "word": ".87", "probability": 0.984619140625 } ] }, { "id": 1607, "seek": 509554, "start": 5273.32, "end": 5275.26, "text": " 0.5% accuracy", "tokens": [ 50664, 1958, 13, 20, 4, 14170, 50764 ], "temperature": 0.0, "avg_logprob": -0.16771788498677245, "compression_ratio": 1.5401069518716577, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 5273.32, "end": 5273.56, "word": " 0", "probability": 0.04254150390625 }, { "start": 5273.56, "end": 5273.92, "word": ".5", "probability": 0.974609375 }, { "start": 5273.92, "end": 5274.22, "word": "%", "probability": 0.452880859375 }, { "start": 5274.22, "end": 5275.26, "word": " accuracy", "probability": 0.7763671875 } ] }, { "id": 1608, "seek": 509554, "start": 5275.26, "end": 5276.66, "text": " for the TF-IDF", "tokens": [ 50764, 337, 264, 40964, 12, 2777, 37, 50864 ], "temperature": 0.0, "avg_logprob": -0.16771788498677245, "compression_ratio": 1.5401069518716577, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 5275.26, "end": 5275.78, "word": " for", "probability": 0.8876953125 }, { "start": 5275.78, "end": 5276.02, "word": " the", "probability": 0.80322265625 }, { "start": 5276.02, "end": 5276.24, "word": " TF", "probability": 0.83642578125 }, { "start": 5276.24, "end": 5276.66, "word": "-IDF", "probability": 0.8406575520833334 } ] }, { "id": 1609, "seek": 509554, "start": 5276.66, "end": 5278.44, "text": " multinomial Naive Bayesian.", "tokens": [ 50864, 45872, 47429, 6056, 488, 7840, 42434, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.16771788498677245, "compression_ratio": 1.5401069518716577, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 5276.66, "end": 5277.28, "word": " multinomial", "probability": 0.8427734375 }, { "start": 5277.28, "end": 5277.62, "word": " Naive", "probability": 0.5338134765625 }, { "start": 5277.62, "end": 5277.94, "word": " Bayesian", "probability": 0.898193359375 }, { "start": 5277.94, "end": 5278.44, "word": ".", "probability": 0.6484375 } ] }, { "id": 1610, "seek": 509554, "start": 5278.44, "end": 5280.9, "text": " For the count multinomial Naive Bayesian,", "tokens": [ 50964, 1171, 264, 1207, 45872, 47429, 6056, 488, 7840, 42434, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.16771788498677245, "compression_ratio": 1.5401069518716577, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 5278.44, "end": 5278.68, "word": " For", "probability": 0.8876953125 }, { "start": 5278.68, "end": 5279.06, "word": " the", "probability": 0.80859375 }, { "start": 5279.06, "end": 5279.48, "word": " count", "probability": 0.306396484375 }, { "start": 5279.48, "end": 5280.18, "word": " multinomial", "probability": 0.904541015625 }, { "start": 5280.18, "end": 5280.48, "word": " Naive", "probability": 0.910888671875 }, { "start": 5280.48, "end": 5280.8, "word": " Bayesian", "probability": 0.931396484375 }, { "start": 5280.8, "end": 5280.9, "word": ",", "probability": 0.560546875 } ] }, { "id": 1611, "seek": 509554, "start": 5280.9, "end": 5282.58, "text": " we have 0.94.", "tokens": [ 51064, 321, 362, 1958, 13, 27032, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.16771788498677245, "compression_ratio": 1.5401069518716577, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 5280.9, "end": 5280.98, "word": " we", "probability": 0.89013671875 }, { "start": 5280.98, "end": 5281.14, "word": " have", "probability": 0.86962890625 }, { "start": 5281.14, "end": 5281.4, "word": " 0", "probability": 0.96826171875 }, { "start": 5281.4, "end": 5281.9, "word": ".94", "probability": 0.99462890625 }, { "start": 5281.9, "end": 5282.58, "word": ".", "probability": 0.9013671875 } ] }, { "id": 1612, "seek": 509554, "start": 5283.48, "end": 5285.18, "text": " For the logistic regression,", "tokens": [ 51164, 1171, 264, 3565, 3142, 24590, 11, 51264 ], "temperature": 0.0, "avg_logprob": -0.16771788498677245, "compression_ratio": 1.5401069518716577, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 5283.48, "end": 5284.16, "word": " For", "probability": 0.876953125 }, { "start": 5284.16, "end": 5284.38, "word": " the", "probability": 0.81298828125 }, { "start": 5284.38, "end": 5284.68, "word": " logistic", "probability": 0.926025390625 }, { "start": 5284.68, "end": 5285.1, "word": " regression", "probability": 0.9111328125 }, { "start": 5285.1, "end": 5285.18, "word": ",", "probability": 0.8173828125 } ] }, { "id": 1613, "seek": 509554, "start": 5285.18, "end": 5286.32, "text": " we get a little bit better.", "tokens": [ 51264, 321, 483, 257, 707, 857, 1101, 13, 51364 ], "temperature": 0.0, "avg_logprob": -0.16771788498677245, "compression_ratio": 1.5401069518716577, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 5285.18, "end": 5285.3, "word": " we", "probability": 0.89501953125 }, { "start": 5285.3, "end": 5285.38, "word": " get", "probability": 0.8505859375 }, { "start": 5285.56, "end": 5285.72, "word": " a little", "probability": 0.802734375 }, { "start": 5285.72, "end": 5285.9, "word": " bit", "probability": 0.89892578125 }, { "start": 5285.9, "end": 5286.16, "word": " better", "probability": 0.81689453125 }, { "start": 5286.16, "end": 5286.32, "word": ".", "probability": 0.7822265625 } ] }, { "id": 1614, "seek": 509554, "start": 5286.32, "end": 5288.24, "text": " We're at 0.959", "tokens": [ 51364, 492, 434, 412, 1958, 13, 15718, 24, 51464 ], "temperature": 0.0, "avg_logprob": -0.16771788498677245, "compression_ratio": 1.5401069518716577, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 5286.32, "end": 5286.44, "word": " We're", "probability": 0.91162109375 }, { "start": 5286.44, "end": 5286.56, "word": " at", "probability": 0.90185546875 }, { "start": 5286.56, "end": 5286.9, "word": " 0", "probability": 0.978515625 }, { "start": 5286.9, "end": 5288.24, "word": ".959", "probability": 0.9757486979166666 } ] }, { "id": 1615, "seek": 509554, "start": 5288.7, "end": 5290.3, "text": " as our accuracy.", "tokens": [ 51464, 382, 527, 14170, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.16771788498677245, "compression_ratio": 1.5401069518716577, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 5288.7, "end": 5289.04, "word": " as", "probability": 0.76220703125 }, { "start": 5289.04, "end": 5289.18, "word": " our", "probability": 0.802734375 }, { "start": 5289.18, "end": 5289.62, "word": " accuracy", "probability": 0.7509765625 }, { "start": 5289.62, "end": 5290.3, "word": ".", "probability": 0.9453125 } ] }, { "id": 1616, "seek": 509554, "start": 5290.58, "end": 5292.68, "text": " We have fewer", "tokens": [ 51564, 492, 362, 13366, 51664 ], "temperature": 0.0, "avg_logprob": -0.16771788498677245, "compression_ratio": 1.5401069518716577, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 5290.58, "end": 5291.08, "word": " We", "probability": 0.8974609375 }, { "start": 5291.08, "end": 5291.58, "word": " have", "probability": 0.876953125 }, { "start": 5291.58, "end": 5292.68, "word": " fewer", "probability": 0.720703125 } ] }, { "id": 1617, "seek": 509554, "start": 5292.68, "end": 5294.94, "text": " ham emails being classified as", "tokens": [ 51664, 7852, 12524, 885, 20627, 382, 51764 ], "temperature": 0.0, "avg_logprob": -0.16771788498677245, "compression_ratio": 1.5401069518716577, "no_speech_prob": 0.0284271240234375, "words": [ { "start": 5292.68, "end": 5293.5, "word": " ham", "probability": 0.560546875 }, { "start": 5293.5, "end": 5293.92, "word": " emails", "probability": 0.75244140625 }, { "start": 5293.92, "end": 5294.2, "word": " being", "probability": 0.880859375 }, { "start": 5294.2, "end": 5294.62, "word": " classified", "probability": 0.93994140625 }, { "start": 5294.62, "end": 5294.94, "word": " as", "probability": 0.908203125 } ] }, { "id": 1618, "seek": 512302, "start": 5294.94, "end": 5296.56, "text": " spam and fewer", "tokens": [ 50364, 24028, 293, 13366, 50464 ], "temperature": 0.0, "avg_logprob": -0.15320723746952258, "compression_ratio": 1.7102272727272727, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5294.94, "end": 5295.26, "word": " spam", "probability": 0.1412353515625 }, { "start": 5295.26, "end": 5296.06, "word": " and", "probability": 0.423828125 }, { "start": 5296.06, "end": 5296.56, "word": " fewer", "probability": 0.75439453125 } ] }, { "id": 1619, "seek": 512302, "start": 5296.56, "end": 5299.26, "text": " spam emails being classified as ham.", "tokens": [ 50464, 24028, 12524, 885, 20627, 382, 7852, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.15320723746952258, "compression_ratio": 1.7102272727272727, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5296.56, "end": 5297.48, "word": " spam", "probability": 0.94775390625 }, { "start": 5297.48, "end": 5297.78, "word": " emails", "probability": 0.7685546875 }, { "start": 5297.78, "end": 5298.02, "word": " being", "probability": 0.857421875 }, { "start": 5298.02, "end": 5298.36, "word": " classified", "probability": 0.93359375 }, { "start": 5298.36, "end": 5298.64, "word": " as", "probability": 0.90625 }, { "start": 5298.64, "end": 5298.86, "word": " ham", "probability": 0.68701171875 }, { "start": 5298.86, "end": 5299.26, "word": ".", "probability": 0.7919921875 } ] }, { "id": 1620, "seek": 512302, "start": 5299.26, "end": 5301.04, "text": " We're getting better.", "tokens": [ 50564, 492, 434, 1242, 1101, 13, 50664 ], "temperature": 0.0, "avg_logprob": -0.15320723746952258, "compression_ratio": 1.7102272727272727, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5299.26, "end": 5299.54, "word": " We're", "probability": 0.478271484375 }, { "start": 5299.54, "end": 5299.74, "word": " getting", "probability": 0.9072265625 }, { "start": 5299.74, "end": 5300.4, "word": " better", "probability": 0.8251953125 }, { "start": 5300.4, "end": 5301.04, "word": ".", "probability": 0.74560546875 } ] }, { "id": 1621, "seek": 512302, "start": 5303.06, "end": 5304.34, "text": " With the", "tokens": [ 50764, 2022, 264, 50864 ], "temperature": 0.0, "avg_logprob": -0.15320723746952258, "compression_ratio": 1.7102272727272727, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5303.06, "end": 5303.7, "word": " With", "probability": 0.1502685546875 }, { "start": 5303.7, "end": 5304.34, "word": " the", "probability": 0.78662109375 } ] }, { "id": 1622, "seek": 512302, "start": 5304.94, "end": 5306.82, "text": " task 6D, this is logistic", "tokens": [ 50864, 5633, 1386, 35, 11, 341, 307, 3565, 3142, 50964 ], "temperature": 0.0, "avg_logprob": -0.15320723746952258, "compression_ratio": 1.7102272727272727, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5304.94, "end": 5305.36, "word": " task", "probability": 0.403564453125 }, { "start": 5305.36, "end": 5305.96, "word": " 6D", "probability": 0.581298828125 }, { "start": 5305.96, "end": 5306.12, "word": ",", "probability": 0.748046875 }, { "start": 5306.12, "end": 5306.22, "word": " this", "probability": 0.8447265625 }, { "start": 5306.22, "end": 5306.36, "word": " is", "probability": 0.904296875 }, { "start": 5306.36, "end": 5306.82, "word": " logistic", "probability": 0.881103515625 } ] }, { "id": 1623, "seek": 512302, "start": 5306.82, "end": 5309.32, "text": " regression with count vectorizer.", "tokens": [ 50964, 24590, 365, 1207, 8062, 6545, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.15320723746952258, "compression_ratio": 1.7102272727272727, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5306.82, "end": 5307.24, "word": " regression", "probability": 0.82177734375 }, { "start": 5307.24, "end": 5307.66, "word": " with", "probability": 0.7998046875 }, { "start": 5307.66, "end": 5308.12, "word": " count", "probability": 0.67041015625 }, { "start": 5308.12, "end": 5308.76, "word": " vectorizer", "probability": 0.9326171875 }, { "start": 5308.76, "end": 5309.32, "word": ".", "probability": 0.89013671875 } ] }, { "id": 1624, "seek": 512302, "start": 5309.52, "end": 5310.78, "text": " This is going to be our", "tokens": [ 51064, 639, 307, 516, 281, 312, 527, 51164 ], "temperature": 0.0, "avg_logprob": -0.15320723746952258, "compression_ratio": 1.7102272727272727, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5309.52, "end": 5310.16, "word": " This", "probability": 0.8095703125 }, { "start": 5310.16, "end": 5310.3, "word": " is", "probability": 0.904296875 }, { "start": 5310.3, "end": 5310.42, "word": " going", "probability": 0.861328125 }, { "start": 5310.42, "end": 5310.54, "word": " to", "probability": 0.90380859375 }, { "start": 5310.54, "end": 5310.64, "word": " be", "probability": 0.90673828125 }, { "start": 5310.64, "end": 5310.78, "word": " our", "probability": 0.8232421875 } ] }, { "id": 1625, "seek": 512302, "start": 5310.78, "end": 5314.04, "text": " best model at 0.976.", "tokens": [ 51164, 1151, 2316, 412, 1958, 13, 23247, 21, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.15320723746952258, "compression_ratio": 1.7102272727272727, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5310.78, "end": 5311.18, "word": " best", "probability": 0.82080078125 }, { "start": 5311.18, "end": 5311.56, "word": " model", "probability": 0.8017578125 }, { "start": 5311.56, "end": 5311.9, "word": " at", "probability": 0.8818359375 }, { "start": 5311.9, "end": 5312.16, "word": " 0", "probability": 0.8017578125 }, { "start": 5312.16, "end": 5313.4, "word": ".976", "probability": 0.9275716145833334 }, { "start": 5313.4, "end": 5314.04, "word": ".", "probability": 0.81787109375 } ] }, { "id": 1626, "seek": 512302, "start": 5314.8, "end": 5317.02, "text": " Here we only have 8 of the", "tokens": [ 51364, 1692, 321, 787, 362, 1649, 295, 264, 51464 ], "temperature": 0.0, "avg_logprob": -0.15320723746952258, "compression_ratio": 1.7102272727272727, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5314.8, "end": 5315.06, "word": " Here", "probability": 0.7607421875 }, { "start": 5315.06, "end": 5315.18, "word": " we", "probability": 0.67431640625 }, { "start": 5315.18, "end": 5315.34, "word": " only", "probability": 0.85693359375 }, { "start": 5315.34, "end": 5315.62, "word": " have", "probability": 0.875 }, { "start": 5315.62, "end": 5316.08, "word": " 8", "probability": 0.373291015625 }, { "start": 5316.08, "end": 5316.7, "word": " of", "probability": 0.8984375 }, { "start": 5316.7, "end": 5317.02, "word": " the", "probability": 0.81103515625 } ] }, { "id": 1627, "seek": 512302, "start": 5317.02, "end": 5318.74, "text": " ham emails being classified as spam", "tokens": [ 51464, 7852, 12524, 885, 20627, 382, 24028, 51564 ], "temperature": 0.0, "avg_logprob": -0.15320723746952258, "compression_ratio": 1.7102272727272727, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5317.02, "end": 5317.32, "word": " ham", "probability": 0.81640625 }, { "start": 5317.32, "end": 5317.6, "word": " emails", "probability": 0.767578125 }, { "start": 5317.6, "end": 5317.86, "word": " being", "probability": 0.88134765625 }, { "start": 5317.86, "end": 5318.18, "word": " classified", "probability": 0.9384765625 }, { "start": 5318.18, "end": 5318.46, "word": " as", "probability": 0.904296875 }, { "start": 5318.46, "end": 5318.74, "word": " spam", "probability": 0.9326171875 } ] }, { "id": 1628, "seek": 512302, "start": 5318.74, "end": 5320.9, "text": " and 12 of the spam emails being", "tokens": [ 51564, 293, 2272, 295, 264, 24028, 12524, 885, 51664 ], "temperature": 0.0, "avg_logprob": -0.15320723746952258, "compression_ratio": 1.7102272727272727, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5318.74, "end": 5319.1, "word": " and", "probability": 0.72998046875 }, { "start": 5319.1, "end": 5319.5, "word": " 12", "probability": 0.892578125 }, { "start": 5319.5, "end": 5319.78, "word": " of", "probability": 0.90673828125 }, { "start": 5319.78, "end": 5319.94, "word": " the", "probability": 0.80810546875 }, { "start": 5319.94, "end": 5320.18, "word": " spam", "probability": 0.9228515625 }, { "start": 5320.18, "end": 5320.5, "word": " emails", "probability": 0.80859375 }, { "start": 5320.5, "end": 5320.9, "word": " being", "probability": 0.87158203125 } ] }, { "id": 1629, "seek": 512302, "start": 5320.9, "end": 5322.42, "text": " classified as ham.", "tokens": [ 51664, 20627, 382, 7852, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.15320723746952258, "compression_ratio": 1.7102272727272727, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5320.9, "end": 5321.24, "word": " classified", "probability": 0.947265625 }, { "start": 5321.24, "end": 5321.54, "word": " as", "probability": 0.9130859375 }, { "start": 5321.54, "end": 5321.78, "word": " ham", "probability": 0.87841796875 }, { "start": 5321.78, "end": 5322.42, "word": ".", "probability": 0.994140625 } ] }, { "id": 1630, "seek": 514622, "start": 5322.42, "end": 5324.32, "text": " Of the four models that we", "tokens": [ 50364, 2720, 264, 1451, 5245, 300, 321, 50464 ], "temperature": 0.0, "avg_logprob": -0.19515624582767488, "compression_ratio": 1.7438423645320198, "no_speech_prob": 0.0003859996795654297, "words": [ { "start": 5322.42, "end": 5323.08, "word": " Of", "probability": 0.052337646484375 }, { "start": 5323.08, "end": 5323.5, "word": " the", "probability": 0.80712890625 }, { "start": 5323.5, "end": 5323.76, "word": " four", "probability": 0.8193359375 }, { "start": 5323.76, "end": 5324.0, "word": " models", "probability": 0.81396484375 }, { "start": 5324.0, "end": 5324.2, "word": " that", "probability": 0.75927734375 }, { "start": 5324.2, "end": 5324.32, "word": " we", "probability": 0.8984375 } ] }, { "id": 1631, "seek": 514622, "start": 5324.32, "end": 5326.56, "text": " trained, this", "tokens": [ 50464, 8895, 11, 341, 50564 ], "temperature": 0.0, "avg_logprob": -0.19515624582767488, "compression_ratio": 1.7438423645320198, "no_speech_prob": 0.0003859996795654297, "words": [ { "start": 5324.32, "end": 5324.9, "word": " trained", "probability": 0.79833984375 }, { "start": 5324.9, "end": 5325.72, "word": ",", "probability": 0.78515625 }, { "start": 5325.72, "end": 5326.56, "word": " this", "probability": 0.85400390625 } ] }, { "id": 1632, "seek": 514622, "start": 5326.56, "end": 5327.48, "text": " is the better one", "tokens": [ 50564, 307, 264, 1101, 472, 50664 ], "temperature": 0.0, "avg_logprob": -0.19515624582767488, "compression_ratio": 1.7438423645320198, "no_speech_prob": 0.0003859996795654297, "words": [ { "start": 5326.56, "end": 5326.72, "word": " is", "probability": 0.90771484375 }, { "start": 5326.72, "end": 5326.9, "word": " the", "probability": 0.8115234375 }, { "start": 5326.9, "end": 5327.12, "word": " better", "probability": 0.81640625 }, { "start": 5327.12, "end": 5327.48, "word": " one", "probability": 0.81201171875 } ] }, { "id": 1633, "seek": 514622, "start": 5328.64, "end": 5330.34, "text": " in terms of accuracy.", "tokens": [ 50664, 294, 2115, 295, 14170, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.19515624582767488, "compression_ratio": 1.7438423645320198, "no_speech_prob": 0.0003859996795654297, "words": [ { "start": 5328.64, "end": 5329.1, "word": " in", "probability": 0.66748046875 }, { "start": 5329.1, "end": 5329.32, "word": " terms", "probability": 0.74658203125 }, { "start": 5329.32, "end": 5329.44, "word": " of", "probability": 0.90087890625 }, { "start": 5329.44, "end": 5329.88, "word": " accuracy", "probability": 0.70654296875 }, { "start": 5329.88, "end": 5330.34, "word": ".", "probability": 0.8134765625 } ] }, { "id": 1634, "seek": 514622, "start": 5331.32, "end": 5332.78, "text": " This is why we want to try", "tokens": [ 50764, 639, 307, 983, 321, 528, 281, 853, 50864 ], "temperature": 0.0, "avg_logprob": -0.19515624582767488, "compression_ratio": 1.7438423645320198, "no_speech_prob": 0.0003859996795654297, "words": [ { "start": 5331.32, "end": 5331.6, "word": " This", "probability": 0.421875 }, { "start": 5331.6, "end": 5331.76, "word": " is", "probability": 0.9072265625 }, { "start": 5331.76, "end": 5331.94, "word": " why", "probability": 0.8154296875 }, { "start": 5331.94, "end": 5332.1, "word": " we", "probability": 0.90185546875 }, { "start": 5332.1, "end": 5332.26, "word": " want", "probability": 0.69873046875 }, { "start": 5332.26, "end": 5332.38, "word": " to", "probability": 0.908203125 }, { "start": 5332.38, "end": 5332.78, "word": " try", "probability": 0.80908203125 } ] }, { "id": 1635, "seek": 514622, "start": 5332.78, "end": 5334.56, "text": " different algorithms, different machine", "tokens": [ 50864, 819, 14642, 11, 819, 3479, 50964 ], "temperature": 0.0, "avg_logprob": -0.19515624582767488, "compression_ratio": 1.7438423645320198, "no_speech_prob": 0.0003859996795654297, "words": [ { "start": 5332.78, "end": 5333.48, "word": " different", "probability": 0.71044921875 }, { "start": 5333.48, "end": 5334.0, "word": " algorithms", "probability": 0.701171875 }, { "start": 5334.0, "end": 5334.12, "word": ",", "probability": 0.888671875 }, { "start": 5334.12, "end": 5334.28, "word": " different", "probability": 0.68115234375 }, { "start": 5334.28, "end": 5334.56, "word": " machine", "probability": 0.71435546875 } ] }, { "id": 1636, "seek": 514622, "start": 5334.56, "end": 5336.4, "text": " learning algorithms, as well as different ways", "tokens": [ 50964, 2539, 14642, 11, 382, 731, 382, 819, 2098, 51064 ], "temperature": 0.0, "avg_logprob": -0.19515624582767488, "compression_ratio": 1.7438423645320198, "no_speech_prob": 0.0003859996795654297, "words": [ { "start": 5334.56, "end": 5334.82, "word": " learning", "probability": 0.79736328125 }, { "start": 5334.82, "end": 5335.26, "word": " algorithms", "probability": 0.88525390625 }, { "start": 5335.26, "end": 5335.44, "word": ",", "probability": 0.62451171875 }, { "start": 5335.44, "end": 5335.56, "word": " as", "probability": 0.90283203125 }, { "start": 5335.56, "end": 5335.7, "word": " well", "probability": 0.87109375 }, { "start": 5335.7, "end": 5335.86, "word": " as", "probability": 0.9091796875 }, { "start": 5335.86, "end": 5336.12, "word": " different", "probability": 0.66845703125 }, { "start": 5336.12, "end": 5336.4, "word": " ways", "probability": 0.80322265625 } ] }, { "id": 1637, "seek": 514622, "start": 5336.4, "end": 5338.94, "text": " that we preprocess or vectorize our data.", "tokens": [ 51064, 300, 321, 2666, 340, 780, 420, 8062, 1125, 527, 1412, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.19515624582767488, "compression_ratio": 1.7438423645320198, "no_speech_prob": 0.0003859996795654297, "words": [ { "start": 5336.4, "end": 5336.54, "word": " that", "probability": 0.8642578125 }, { "start": 5336.54, "end": 5336.66, "word": " we", "probability": 0.90869140625 }, { "start": 5336.66, "end": 5337.34, "word": " preprocess", "probability": 0.76416015625 }, { "start": 5337.34, "end": 5337.54, "word": " or", "probability": 0.853515625 }, { "start": 5337.54, "end": 5338.02, "word": " vectorize", "probability": 0.879638671875 }, { "start": 5338.02, "end": 5338.18, "word": " our", "probability": 0.8115234375 }, { "start": 5338.18, "end": 5338.48, "word": " data", "probability": 0.81201171875 }, { "start": 5338.48, "end": 5338.94, "word": ".", "probability": 0.9384765625 } ] }, { "id": 1638, "seek": 514622, "start": 5339.52, "end": 5340.66, "text": " That way we can create", "tokens": [ 51164, 663, 636, 321, 393, 1884, 51264 ], "temperature": 0.0, "avg_logprob": -0.19515624582767488, "compression_ratio": 1.7438423645320198, "no_speech_prob": 0.0003859996795654297, "words": [ { "start": 5339.52, "end": 5339.98, "word": " That", "probability": 0.80615234375 }, { "start": 5339.98, "end": 5340.08, "word": " way", "probability": 0.89453125 }, { "start": 5340.08, "end": 5340.2, "word": " we", "probability": 0.69677734375 }, { "start": 5340.2, "end": 5340.36, "word": " can", "probability": 0.896484375 }, { "start": 5340.36, "end": 5340.66, "word": " create", "probability": 0.8232421875 } ] }, { "id": 1639, "seek": 514622, "start": 5340.66, "end": 5342.38, "text": " different models, see which ones perform", "tokens": [ 51264, 819, 5245, 11, 536, 597, 2306, 2042, 51364 ], "temperature": 0.0, "avg_logprob": -0.19515624582767488, "compression_ratio": 1.7438423645320198, "no_speech_prob": 0.0003859996795654297, "words": [ { "start": 5340.66, "end": 5341.06, "word": " different", "probability": 0.70361328125 }, { "start": 5341.06, "end": 5341.44, "word": " models", "probability": 0.80419921875 }, { "start": 5341.44, "end": 5341.62, "word": ",", "probability": 0.92529296875 }, { "start": 5341.62, "end": 5341.72, "word": " see", "probability": 0.794921875 }, { "start": 5341.72, "end": 5341.86, "word": " which", "probability": 0.9208984375 }, { "start": 5341.86, "end": 5342.04, "word": " ones", "probability": 0.76708984375 }, { "start": 5342.04, "end": 5342.38, "word": " perform", "probability": 0.7275390625 } ] }, { "id": 1640, "seek": 514622, "start": 5342.38, "end": 5344.38, "text": " the best, and then we can gravitate", "tokens": [ 51364, 264, 1151, 11, 293, 550, 321, 393, 7427, 8086, 51464 ], "temperature": 0.0, "avg_logprob": -0.19515624582767488, "compression_ratio": 1.7438423645320198, "no_speech_prob": 0.0003859996795654297, "words": [ { "start": 5342.38, "end": 5342.54, "word": " the", "probability": 0.80322265625 }, { "start": 5342.54, "end": 5342.84, "word": " best", "probability": 0.79736328125 }, { "start": 5342.84, "end": 5342.96, "word": ",", "probability": 0.72509765625 }, { "start": 5342.96, "end": 5343.02, "word": " and", "probability": 0.87109375 }, { "start": 5343.02, "end": 5343.18, "word": " then", "probability": 0.68408203125 }, { "start": 5343.18, "end": 5343.56, "word": " we", "probability": 0.87646484375 }, { "start": 5343.56, "end": 5343.7, "word": " can", "probability": 0.89208984375 }, { "start": 5343.7, "end": 5344.38, "word": " gravitate", "probability": 0.793212890625 } ] }, { "id": 1641, "seek": 514622, "start": 5344.38, "end": 5345.62, "text": " towards that one.", "tokens": [ 51464, 3030, 300, 472, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.19515624582767488, "compression_ratio": 1.7438423645320198, "no_speech_prob": 0.0003859996795654297, "words": [ { "start": 5344.38, "end": 5344.7, "word": " towards", "probability": 0.60888671875 }, { "start": 5344.7, "end": 5344.94, "word": " that", "probability": 0.88427734375 }, { "start": 5344.94, "end": 5345.16, "word": " one", "probability": 0.81640625 }, { "start": 5345.16, "end": 5345.62, "word": ".", "probability": 0.998046875 } ] }, { "id": 1642, "seek": 517504, "start": 5349.8, "end": 5350.48, "text": " As far", "tokens": [ 50364, 1018, 1400, 50464 ], "temperature": 0.0, "avg_logprob": -0.21264881633576893, "compression_ratio": 1.6435643564356435, "no_speech_prob": 0.00818634033203125, "words": [ { "start": 5349.8, "end": 5350.28, "word": " As", "probability": 0.31005859375 }, { "start": 5350.28, "end": 5350.48, "word": " far", "probability": 0.8671875 } ] }, { "id": 1643, "seek": 517504, "start": 5350.48, "end": 5351.02, "text": " as the", "tokens": [ 50464, 382, 264, 50564 ], "temperature": 0.0, "avg_logprob": -0.21264881633576893, "compression_ratio": 1.6435643564356435, "no_speech_prob": 0.00818634033203125, "words": [ { "start": 5350.48, "end": 5350.68, "word": " as", "probability": 0.900390625 }, { "start": 5350.68, "end": 5351.02, "word": " the", "probability": 0.78515625 } ] }, { "id": 1644, "seek": 517504, "start": 5351.02, "end": 5353.0, "text": " test spam email,", "tokens": [ 50564, 1500, 24028, 3796, 11, 50664 ], "temperature": 0.0, "avg_logprob": -0.21264881633576893, "compression_ratio": 1.6435643564356435, "no_speech_prob": 0.00818634033203125, "words": [ { "start": 5351.02, "end": 5351.92, "word": " test", "probability": 0.67919921875 }, { "start": 5351.92, "end": 5352.42, "word": " spam", "probability": 0.79345703125 }, { "start": 5352.42, "end": 5352.7, "word": " email", "probability": 0.75634765625 }, { "start": 5352.7, "end": 5353.0, "word": ",", "probability": 0.66162109375 } ] }, { "id": 1645, "seek": 517504, "start": 5353.0, "end": 5355.3, "text": " this is a brand new email.", "tokens": [ 50664, 341, 307, 257, 3360, 777, 3796, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.21264881633576893, "compression_ratio": 1.6435643564356435, "no_speech_prob": 0.00818634033203125, "words": [ { "start": 5353.0, "end": 5353.22, "word": " this", "probability": 0.333740234375 }, { "start": 5353.22, "end": 5353.44, "word": " is", "probability": 0.9072265625 }, { "start": 5353.72, "end": 5354.18, "word": " a brand", "probability": 0.7099609375 }, { "start": 5354.18, "end": 5354.4, "word": " new", "probability": 0.71484375 }, { "start": 5354.4, "end": 5354.82, "word": " email", "probability": 0.92236328125 }, { "start": 5354.82, "end": 5355.3, "word": ".", "probability": 0.31591796875 } ] }, { "id": 1646, "seek": 517504, "start": 5355.4, "end": 5357.06, "text": " It comes in on our email server.", "tokens": [ 50764, 467, 1487, 294, 322, 527, 3796, 7154, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.21264881633576893, "compression_ratio": 1.6435643564356435, "no_speech_prob": 0.00818634033203125, "words": [ { "start": 5355.4, "end": 5355.6, "word": " It", "probability": 0.5400390625 }, { "start": 5355.6, "end": 5355.86, "word": " comes", "probability": 0.7939453125 }, { "start": 5355.86, "end": 5356.02, "word": " in", "probability": 0.87353515625 }, { "start": 5356.02, "end": 5356.14, "word": " on", "probability": 0.7490234375 }, { "start": 5356.14, "end": 5356.26, "word": " our", "probability": 0.77880859375 }, { "start": 5356.26, "end": 5356.54, "word": " email", "probability": 0.88623046875 }, { "start": 5356.54, "end": 5356.92, "word": " server", "probability": 0.826171875 }, { "start": 5356.92, "end": 5357.06, "word": ".", "probability": 0.418212890625 } ] }, { "id": 1647, "seek": 517504, "start": 5357.06, "end": 5358.8, "text": " We want to use our models to", "tokens": [ 50864, 492, 528, 281, 764, 527, 5245, 281, 50964 ], "temperature": 0.0, "avg_logprob": -0.21264881633576893, "compression_ratio": 1.6435643564356435, "no_speech_prob": 0.00818634033203125, "words": [ { "start": 5357.06, "end": 5357.12, "word": " We", "probability": 0.86279296875 }, { "start": 5357.12, "end": 5357.26, "word": " want", "probability": 0.7607421875 }, { "start": 5357.26, "end": 5357.34, "word": " to", "probability": 0.9052734375 }, { "start": 5357.34, "end": 5357.48, "word": " use", "probability": 0.8388671875 }, { "start": 5357.48, "end": 5357.64, "word": " our", "probability": 0.83154296875 }, { "start": 5357.64, "end": 5358.04, "word": " models", "probability": 0.7822265625 }, { "start": 5358.04, "end": 5358.8, "word": " to", "probability": 0.89599609375 } ] }, { "id": 1648, "seek": 517504, "start": 5358.8, "end": 5360.38, "text": " classify it.", "tokens": [ 50964, 33872, 309, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.21264881633576893, "compression_ratio": 1.6435643564356435, "no_speech_prob": 0.00818634033203125, "words": [ { "start": 5358.8, "end": 5359.5, "word": " classify", "probability": 0.91650390625 }, { "start": 5359.5, "end": 5359.9, "word": " it", "probability": 0.8916015625 }, { "start": 5359.9, "end": 5360.38, "word": ".", "probability": 0.97021484375 } ] }, { "id": 1649, "seek": 517504, "start": 5362.48, "end": 5365.14, "text": " Let's go ahead and make a prediction.", "tokens": [ 51164, 961, 311, 352, 2286, 293, 652, 257, 17630, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.21264881633576893, "compression_ratio": 1.6435643564356435, "no_speech_prob": 0.00818634033203125, "words": [ { "start": 5362.48, "end": 5362.96, "word": " Let's", "probability": 0.92431640625 }, { "start": 5362.96, "end": 5363.14, "word": " go", "probability": 0.8505859375 }, { "start": 5363.14, "end": 5363.58, "word": " ahead", "probability": 0.84912109375 }, { "start": 5363.58, "end": 5363.96, "word": " and", "probability": 0.89306640625 }, { "start": 5363.96, "end": 5364.24, "word": " make", "probability": 0.873046875 }, { "start": 5364.36, "end": 5364.66, "word": " a prediction", "probability": 0.8671875 }, { "start": 5364.66, "end": 5365.14, "word": ".", "probability": 0.95654296875 } ] }, { "id": 1650, "seek": 517504, "start": 5366.14, "end": 5368.38, "text": " As I went over earlier, we're going to have", "tokens": [ 51364, 1018, 286, 1437, 670, 3071, 11, 321, 434, 516, 281, 362, 51464 ], "temperature": 0.0, "avg_logprob": -0.21264881633576893, "compression_ratio": 1.6435643564356435, "no_speech_prob": 0.00818634033203125, "words": [ { "start": 5366.14, "end": 5366.62, "word": " As", "probability": 0.611328125 }, { "start": 5366.62, "end": 5366.72, "word": " I", "probability": 0.98291015625 }, { "start": 5366.72, "end": 5366.82, "word": " went", "probability": 0.822265625 }, { "start": 5366.82, "end": 5367.0, "word": " over", "probability": 0.88037109375 }, { "start": 5367.0, "end": 5367.44, "word": " earlier", "probability": 0.8916015625 }, { "start": 5367.44, "end": 5367.8, "word": ",", "probability": 0.8564453125 }, { "start": 5367.8, "end": 5367.94, "word": " we're", "probability": 0.87744140625 }, { "start": 5367.94, "end": 5368.1, "word": " going", "probability": 0.8359375 }, { "start": 5368.1, "end": 5368.2, "word": " to", "probability": 0.9033203125 }, { "start": 5368.2, "end": 5368.38, "word": " have", "probability": 0.87646484375 } ] }, { "id": 1651, "seek": 517504, "start": 5368.38, "end": 5370.54, "text": " our test spam email, which is called working email,", "tokens": [ 51464, 527, 1500, 24028, 3796, 11, 597, 307, 1219, 1364, 3796, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.21264881633576893, "compression_ratio": 1.6435643564356435, "no_speech_prob": 0.00818634033203125, "words": [ { "start": 5368.38, "end": 5368.56, "word": " our", "probability": 0.81005859375 }, { "start": 5368.56, "end": 5368.82, "word": " test", "probability": 0.80712890625 }, { "start": 5368.82, "end": 5369.06, "word": " spam", "probability": 0.89697265625 }, { "start": 5369.06, "end": 5369.42, "word": " email", "probability": 0.91943359375 }, { "start": 5369.42, "end": 5369.54, "word": ",", "probability": 0.53173828125 }, { "start": 5369.54, "end": 5369.66, "word": " which", "probability": 0.54443359375 }, { "start": 5369.66, "end": 5369.74, "word": " is", "probability": 0.8310546875 }, { "start": 5369.74, "end": 5369.88, "word": " called", "probability": 0.5615234375 }, { "start": 5369.88, "end": 5370.18, "word": " working", "probability": 0.38037109375 }, { "start": 5370.18, "end": 5370.42, "word": " email", "probability": 0.8984375 }, { "start": 5370.42, "end": 5370.54, "word": ",", "probability": 0.4443359375 } ] }, { "id": 1652, "seek": 517504, "start": 5370.54, "end": 5372.44, "text": " so we can swap this out pretty", "tokens": [ 51564, 370, 321, 393, 18135, 341, 484, 1238, 51664 ], "temperature": 0.0, "avg_logprob": -0.21264881633576893, "compression_ratio": 1.6435643564356435, "no_speech_prob": 0.00818634033203125, "words": [ { "start": 5370.54, "end": 5370.6, "word": " so", "probability": 0.8837890625 }, { "start": 5370.6, "end": 5370.74, "word": " we", "probability": 0.72900390625 }, { "start": 5370.74, "end": 5370.88, "word": " can", "probability": 0.8896484375 }, { "start": 5370.88, "end": 5371.14, "word": " swap", "probability": 0.94140625 }, { "start": 5371.14, "end": 5371.38, "word": " this", "probability": 0.49609375 }, { "start": 5371.38, "end": 5371.66, "word": " out", "probability": 0.82177734375 }, { "start": 5371.66, "end": 5372.44, "word": " pretty", "probability": 0.86328125 } ] }, { "id": 1653, "seek": 517504, "start": 5372.44, "end": 5374.44, "text": " seamlessly. We're going to use our", "tokens": [ 51664, 38083, 13, 492, 434, 516, 281, 764, 527, 51764 ], "temperature": 0.0, "avg_logprob": -0.21264881633576893, "compression_ratio": 1.6435643564356435, "no_speech_prob": 0.00818634033203125, "words": [ { "start": 5372.44, "end": 5372.86, "word": " seamlessly", "probability": 0.76025390625 }, { "start": 5372.86, "end": 5373.34, "word": ".", "probability": 0.9736328125 }, { "start": 5373.58, "end": 5374.06, "word": " We're", "probability": 0.85302734375 }, { "start": 5374.06, "end": 5374.06, "word": " going", "probability": 0.78564453125 }, { "start": 5374.06, "end": 5374.06, "word": " to", "probability": 0.90673828125 }, { "start": 5374.06, "end": 5374.22, "word": " use", "probability": 0.8408203125 }, { "start": 5374.22, "end": 5374.44, "word": " our", "probability": 0.81201171875 } ] }, { "id": 1654, "seek": 520302, "start": 5374.44, "end": 5376.14, "text": " vectorizers that we already defined", "tokens": [ 50364, 8062, 22525, 300, 321, 1217, 7642, 50464 ], "temperature": 0.0, "avg_logprob": -0.19345237385658992, "compression_ratio": 1.7038461538461538, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 5374.44, "end": 5375.08, "word": " vectorizers", "probability": 0.6683349609375 }, { "start": 5375.08, "end": 5375.34, "word": " that", "probability": 0.787109375 }, { "start": 5375.34, "end": 5375.44, "word": " we", "probability": 0.90576171875 }, { "start": 5375.44, "end": 5375.64, "word": " already", "probability": 0.79833984375 }, { "start": 5375.64, "end": 5376.14, "word": " defined", "probability": 0.70654296875 } ] }, { "id": 1655, "seek": 520302, "start": 5376.14, "end": 5378.46, "text": " to transform our working", "tokens": [ 50464, 281, 4088, 527, 1364, 50564 ], "temperature": 0.0, "avg_logprob": -0.19345237385658992, "compression_ratio": 1.7038461538461538, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 5376.14, "end": 5376.62, "word": " to", "probability": 0.87109375 }, { "start": 5376.62, "end": 5377.6, "word": " transform", "probability": 0.85546875 }, { "start": 5377.6, "end": 5378.16, "word": " our", "probability": 0.80419921875 }, { "start": 5378.16, "end": 5378.46, "word": " working", "probability": 0.6630859375 } ] }, { "id": 1656, "seek": 520302, "start": 5378.46, "end": 5380.74, "text": " email. And then of course, being a", "tokens": [ 50564, 3796, 13, 400, 550, 295, 1164, 11, 885, 257, 50664 ], "temperature": 0.0, "avg_logprob": -0.19345237385658992, "compression_ratio": 1.7038461538461538, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 5378.46, "end": 5378.76, "word": " email", "probability": 0.91845703125 }, { "start": 5378.76, "end": 5379.2, "word": ".", "probability": 0.4794921875 }, { "start": 5379.5, "end": 5379.54, "word": " And", "probability": 0.61669921875 }, { "start": 5379.54, "end": 5379.66, "word": " then", "probability": 0.70361328125 }, { "start": 5379.66, "end": 5379.78, "word": " of", "probability": 0.72998046875 }, { "start": 5379.78, "end": 5380.0, "word": " course", "probability": 0.86328125 }, { "start": 5380.0, "end": 5380.16, "word": ",", "probability": 0.454833984375 }, { "start": 5380.16, "end": 5380.36, "word": " being", "probability": 0.84521484375 }, { "start": 5380.52, "end": 5380.74, "word": " a string", "probability": 0.76220703125 } ] }, { "id": 1657, "seek": 520302, "start": 5380.74, "end": 5382.42, "text": " string, we need to put it in a list.", "tokens": [ 50664, 6798, 11, 321, 643, 281, 829, 309, 294, 257, 1329, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.19345237385658992, "compression_ratio": 1.7038461538461538, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 5380.74, "end": 5380.82, "word": ",", "probability": 0.7138671875 }, { "start": 5380.82, "end": 5380.92, "word": " we", "probability": 0.904296875 }, { "start": 5380.92, "end": 5381.04, "word": " need", "probability": 0.81005859375 }, { "start": 5381.04, "end": 5381.14, "word": " to", "probability": 0.90380859375 }, { "start": 5381.14, "end": 5381.28, "word": " put", "probability": 0.88916015625 }, { "start": 5381.28, "end": 5381.4, "word": " it", "probability": 0.89111328125 }, { "start": 5381.4, "end": 5381.54, "word": " in", "probability": 0.9072265625 }, { "start": 5381.68, "end": 5381.96, "word": " a list", "probability": 0.8740234375 }, { "start": 5381.96, "end": 5382.3, "word": ".", "probability": 0.666015625 }, { "start": 5382.3, "end": 5382.42, "word": " That's", "probability": 0.900390625 } ] }, { "id": 1658, "seek": 520302, "start": 5382.42, "end": 5384.74, "text": " That's what the square brackets are for.", "tokens": [ 50764, 663, 311, 437, 264, 3732, 26179, 366, 337, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.19345237385658992, "compression_ratio": 1.7038461538461538, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 5382.42, "end": 5382.52, "word": " what", "probability": 0.884765625 }, { "start": 5382.52, "end": 5382.66, "word": " the", "probability": 0.8076171875 }, { "start": 5382.66, "end": 5382.82, "word": " square", "probability": 0.875 }, { "start": 5382.82, "end": 5383.14, "word": " brackets", "probability": 0.81103515625 }, { "start": 5383.14, "end": 5383.3, "word": " are", "probability": 0.89208984375 }, { "start": 5383.3, "end": 5383.66, "word": " for", "probability": 0.8984375 }, { "start": 5383.66, "end": 5384.1, "word": ".", "probability": 0.9296875 }, { "start": 5384.46, "end": 5384.64, "word": " Then", "probability": 0.701171875 }, { "start": 5384.64, "end": 5384.74, "word": " we", "probability": 0.87646484375 } ] }, { "id": 1659, "seek": 520302, "start": 5384.74, "end": 5387.38, "text": " Then we use all four of our models,", "tokens": [ 50864, 1396, 321, 764, 439, 1451, 295, 527, 5245, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.19345237385658992, "compression_ratio": 1.7038461538461538, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 5384.74, "end": 5384.96, "word": " use", "probability": 0.8193359375 }, { "start": 5384.96, "end": 5385.22, "word": " all", "probability": 0.90185546875 }, { "start": 5385.22, "end": 5385.72, "word": " four", "probability": 0.875 }, { "start": 5385.72, "end": 5385.96, "word": " of", "probability": 0.90625 }, { "start": 5385.96, "end": 5386.12, "word": " our", "probability": 0.826171875 }, { "start": 5386.12, "end": 5386.48, "word": " models", "probability": 0.80126953125 }, { "start": 5386.48, "end": 5386.58, "word": ",", "probability": 0.607421875 }, { "start": 5386.58, "end": 5386.68, "word": " the", "probability": 0.81494140625 }, { "start": 5386.68, "end": 5387.38, "word": " multinomial", "probability": 0.904541015625 } ] }, { "id": 1660, "seek": 520302, "start": 5387.38, "end": 5389.3, "text": " the multinomial and the logistic", "tokens": [ 50964, 264, 45872, 47429, 293, 264, 3565, 3142, 51064 ], "temperature": 0.0, "avg_logprob": -0.19345237385658992, "compression_ratio": 1.7038461538461538, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 5387.38, "end": 5388.02, "word": " and", "probability": 0.68994140625 }, { "start": 5388.02, "end": 5388.16, "word": " the", "probability": 0.8115234375 }, { "start": 5388.16, "end": 5388.48, "word": " logistic", "probability": 0.9482421875 }, { "start": 5388.48, "end": 5388.9, "word": " regression", "probability": 0.86181640625 }, { "start": 5388.9, "end": 5389.18, "word": " with", "probability": 0.73095703125 }, { "start": 5389.18, "end": 5389.3, "word": " the", "probability": 0.67138671875 } ] }, { "id": 1661, "seek": 520302, "start": 5389.3, "end": 5391.26, "text": " regression with the tf and the count", "tokens": [ 51064, 24590, 365, 264, 256, 69, 293, 264, 1207, 51164 ], "temperature": 0.0, "avg_logprob": -0.19345237385658992, "compression_ratio": 1.7038461538461538, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 5389.3, "end": 5389.68, "word": " tf", "probability": 0.7181396484375 }, { "start": 5389.68, "end": 5389.9, "word": " and", "probability": 0.84814453125 }, { "start": 5389.9, "end": 5390.02, "word": " the", "probability": 0.81201171875 }, { "start": 5390.02, "end": 5390.24, "word": " count", "probability": 0.791015625 }, { "start": 5390.24, "end": 5390.9, "word": " vectorizers", "probability": 0.95068359375 }, { "start": 5390.9, "end": 5391.26, "word": ".", "probability": 0.90283203125 } ] }, { "id": 1662, "seek": 520302, "start": 5391.26, "end": 5394.9, "text": " vectorizers. We use the predict function", "tokens": [ 51164, 8062, 22525, 13, 492, 764, 264, 6069, 2445, 51264 ], "temperature": 0.0, "avg_logprob": -0.19345237385658992, "compression_ratio": 1.7038461538461538, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 5391.26, "end": 5391.58, "word": " We", "probability": 0.85595703125 }, { "start": 5391.58, "end": 5391.72, "word": " use", "probability": 0.80078125 }, { "start": 5391.72, "end": 5391.84, "word": " the", "probability": 0.80322265625 }, { "start": 5391.84, "end": 5392.04, "word": " predict", "probability": 0.8193359375 }, { "start": 5392.04, "end": 5392.54, "word": " function", "probability": 0.88134765625 }, { "start": 5392.54, "end": 5393.48, "word": " on", "probability": 0.90087890625 }, { "start": 5393.48, "end": 5393.94, "word": " the", "probability": 0.81591796875 }, { "start": 5393.94, "end": 5394.9, "word": " vectorized", "probability": 0.9326171875 } ] }, { "id": 1663, "seek": 520302, "start": 5394.9, "end": 5398.08, "text": " on the vectorized", "tokens": [ 51264, 322, 264, 8062, 1602, 51364 ], "temperature": 0.0, "avg_logprob": -0.19345237385658992, "compression_ratio": 1.7038461538461538, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 5394.9, "end": 5395.42, "word": " emails", "probability": 0.7880859375 }, { "start": 5395.42, "end": 5395.86, "word": ".", "probability": 0.65380859375 }, { "start": 5397.54, "end": 5397.98, "word": " And", "probability": 0.8056640625 }, { "start": 5397.98, "end": 5398.08, "word": " then", "probability": 0.72119140625 } ] }, { "id": 1664, "seek": 520302, "start": 5398.08, "end": 5398.28, "text": " emails.", "tokens": [ 51364, 12524, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.19345237385658992, "compression_ratio": 1.7038461538461538, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 5398.08, "end": 5398.16, "word": " we", "probability": 0.896484375 }, { "start": 5398.16, "end": 5398.28, "word": " just", "probability": 0.88037109375 } ] }, { "id": 1665, "seek": 520302, "start": 5398.28, "end": 5399.26, "text": " And then we just go", "tokens": [ 51464, 400, 550, 321, 445, 352, 51564 ], "temperature": 0.0, "avg_logprob": -0.19345237385658992, "compression_ratio": 1.7038461538461538, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 5398.28, "end": 5398.4, "word": " go", "probability": 0.919921875 }, { "start": 5398.4, "end": 5398.7, "word": " ahead", "probability": 0.861328125 }, { "start": 5398.7, "end": 5398.96, "word": " and", "probability": 0.196533203125 }, { "start": 5398.96, "end": 5399.12, "word": " print", "probability": 0.92919921875 }, { "start": 5399.12, "end": 5399.26, "word": " out", "probability": 0.8095703125 } ] }, { "id": 1666, "seek": 520302, "start": 5399.26, "end": 5402.12, "text": " ahead and print out the working email itself.", "tokens": [ 51564, 2286, 293, 4482, 484, 264, 1364, 3796, 2564, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.19345237385658992, "compression_ratio": 1.7038461538461538, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 5399.26, "end": 5399.42, "word": " the", "probability": 0.81005859375 }, { "start": 5399.42, "end": 5399.68, "word": " working", "probability": 0.6826171875 }, { "start": 5399.68, "end": 5399.96, "word": " email", "probability": 0.9228515625 }, { "start": 5399.96, "end": 5400.5, "word": " itself", "probability": 0.76318359375 }, { "start": 5400.5, "end": 5400.94, "word": ".", "probability": 0.7978515625 }, { "start": 5401.12, "end": 5401.56, "word": " Your", "probability": 0.0384521484375 }, { "start": 5401.56, "end": 5401.8, "word": " latest", "probability": 0.79248046875 }, { "start": 5401.8, "end": 5402.02, "word": " issue", "probability": 0.64111328125 }, { "start": 5402.02, "end": 5402.12, "word": " is", "probability": 0.7998046875 } ] }, { "id": 1667, "seek": 520302, "start": 5402.12, "end": 5402.42, "text": " Your latest issue is available", "tokens": [ 51664, 2260, 6792, 2734, 307, 2435, 51764 ], "temperature": 0.0, "avg_logprob": -0.19345237385658992, "compression_ratio": 1.7038461538461538, "no_speech_prob": 0.0111541748046875, "words": [ { "start": 5402.12, "end": 5402.42, "word": " available", "probability": 0.71630859375 } ] }, { "id": 1668, "seek": 523106, "start": 5402.42, "end": 5404.54, "text": " now. If you don't want issue notifications,", "tokens": [ 50364, 586, 13, 759, 291, 500, 380, 528, 2734, 13426, 11, 50464 ], "temperature": 0.0, "avg_logprob": -0.16610360763094448, "compression_ratio": 1.6008064516129032, "no_speech_prob": 0.00669097900390625, "words": [ { "start": 5402.42, "end": 5402.74, "word": " now", "probability": 0.388427734375 }, { "start": 5402.74, "end": 5402.96, "word": ".", "probability": 0.560546875 }, { "start": 5402.96, "end": 5403.06, "word": " If", "probability": 0.87353515625 }, { "start": 5403.06, "end": 5403.14, "word": " you", "probability": 0.896484375 }, { "start": 5403.14, "end": 5403.26, "word": " don't", "probability": 0.943603515625 }, { "start": 5403.26, "end": 5403.5, "word": " want", "probability": 0.810546875 }, { "start": 5403.5, "end": 5403.8, "word": " issue", "probability": 0.458251953125 }, { "start": 5403.8, "end": 5404.34, "word": " notifications", "probability": 0.79248046875 }, { "start": 5404.34, "end": 5404.54, "word": ",", "probability": 0.52490234375 } ] }, { "id": 1669, "seek": 523106, "start": 5404.54, "end": 5405.92, "text": " click here to unsubscribe.", "tokens": [ 50464, 2052, 510, 281, 2693, 9493, 13, 50564 ], "temperature": 0.0, "avg_logprob": -0.16610360763094448, "compression_ratio": 1.6008064516129032, "no_speech_prob": 0.00669097900390625, "words": [ { "start": 5404.54, "end": 5404.7, "word": " click", "probability": 0.84130859375 }, { "start": 5404.7, "end": 5404.84, "word": " here", "probability": 0.80908203125 }, { "start": 5404.84, "end": 5404.94, "word": " to", "probability": 0.90576171875 }, { "start": 5404.94, "end": 5405.44, "word": " unsubscribe", "probability": 0.807373046875 }, { "start": 5405.44, "end": 5405.92, "word": ".", "probability": 0.7333984375 } ] }, { "id": 1670, "seek": 523106, "start": 5407.44, "end": 5408.24, "text": " And then", "tokens": [ 50564, 400, 550, 50664 ], "temperature": 0.0, "avg_logprob": -0.16610360763094448, "compression_ratio": 1.6008064516129032, "no_speech_prob": 0.00669097900390625, "words": [ { "start": 5407.44, "end": 5407.92, "word": " And", "probability": 0.76953125 }, { "start": 5407.92, "end": 5408.24, "word": " then", "probability": 0.728515625 } ] }, { "id": 1671, "seek": 523106, "start": 5408.24, "end": 5410.58, "text": " we print out the values", "tokens": [ 50664, 321, 4482, 484, 264, 4190, 50764 ], "temperature": 0.0, "avg_logprob": -0.16610360763094448, "compression_ratio": 1.6008064516129032, "no_speech_prob": 0.00669097900390625, "words": [ { "start": 5408.24, "end": 5409.08, "word": " we", "probability": 0.8271484375 }, { "start": 5409.08, "end": 5409.58, "word": " print", "probability": 0.88818359375 }, { "start": 5409.58, "end": 5409.82, "word": " out", "probability": 0.80810546875 }, { "start": 5409.82, "end": 5410.12, "word": " the", "probability": 0.810546875 }, { "start": 5410.12, "end": 5410.58, "word": " values", "probability": 0.916015625 } ] }, { "id": 1672, "seek": 523106, "start": 5411.18, "end": 5412.16, "text": " that are predicted", "tokens": [ 50764, 300, 366, 19147, 50864 ], "temperature": 0.0, "avg_logprob": -0.16610360763094448, "compression_ratio": 1.6008064516129032, "no_speech_prob": 0.00669097900390625, "words": [ { "start": 5411.18, "end": 5411.66, "word": " that", "probability": 0.66357421875 }, { "start": 5411.66, "end": 5411.78, "word": " are", "probability": 0.89208984375 }, { "start": 5411.78, "end": 5412.16, "word": " predicted", "probability": 0.7275390625 } ] }, { "id": 1673, "seek": 523106, "start": 5412.16, "end": 5413.8, "text": " from each of our models.", "tokens": [ 50864, 490, 1184, 295, 527, 5245, 13, 50964 ], "temperature": 0.0, "avg_logprob": -0.16610360763094448, "compression_ratio": 1.6008064516129032, "no_speech_prob": 0.00669097900390625, "words": [ { "start": 5412.16, "end": 5412.56, "word": " from", "probability": 0.810546875 }, { "start": 5412.56, "end": 5412.74, "word": " each", "probability": 0.8681640625 }, { "start": 5412.74, "end": 5412.84, "word": " of", "probability": 0.90380859375 }, { "start": 5412.84, "end": 5412.98, "word": " our", "probability": 0.82470703125 }, { "start": 5412.98, "end": 5413.32, "word": " models", "probability": 0.7958984375 }, { "start": 5413.32, "end": 5413.8, "word": ".", "probability": 0.86376953125 } ] }, { "id": 1674, "seek": 523106, "start": 5414.14, "end": 5416.48, "text": " If we look at it, we're going to see something interesting.", "tokens": [ 50964, 759, 321, 574, 412, 309, 11, 321, 434, 516, 281, 536, 746, 1880, 13, 51064 ], "temperature": 0.0, "avg_logprob": -0.16610360763094448, "compression_ratio": 1.6008064516129032, "no_speech_prob": 0.00669097900390625, "words": [ { "start": 5414.14, "end": 5414.62, "word": " If", "probability": 0.32666015625 }, { "start": 5414.62, "end": 5414.7, "word": " we", "probability": 0.89892578125 }, { "start": 5414.7, "end": 5414.84, "word": " look", "probability": 0.9150390625 }, { "start": 5414.84, "end": 5414.94, "word": " at", "probability": 0.908203125 }, { "start": 5414.94, "end": 5415.0, "word": " it", "probability": 0.892578125 }, { "start": 5415.0, "end": 5415.02, "word": ",", "probability": 0.79736328125 }, { "start": 5415.02, "end": 5415.1, "word": " we're", "probability": 0.918212890625 }, { "start": 5415.1, "end": 5415.18, "word": " going", "probability": 0.69189453125 }, { "start": 5415.18, "end": 5415.24, "word": " to", "probability": 0.90625 }, { "start": 5415.24, "end": 5415.36, "word": " see", "probability": 0.818359375 }, { "start": 5415.36, "end": 5415.58, "word": " something", "probability": 0.7333984375 }, { "start": 5415.58, "end": 5416.0, "word": " interesting", "probability": 0.6318359375 }, { "start": 5416.0, "end": 5416.48, "word": ".", "probability": 0.9873046875 } ] }, { "id": 1675, "seek": 523106, "start": 5420.02, "end": 5420.98, "text": " Our best", "tokens": [ 51164, 2621, 1151, 51264 ], "temperature": 0.0, "avg_logprob": -0.16610360763094448, "compression_ratio": 1.6008064516129032, "no_speech_prob": 0.00669097900390625, "words": [ { "start": 5420.02, "end": 5420.5, "word": " Our", "probability": 0.0924072265625 }, { "start": 5420.5, "end": 5420.98, "word": " best", "probability": 0.607421875 } ] }, { "id": 1676, "seek": 523106, "start": 5420.98, "end": 5422.4, "text": " performing model, which is the", "tokens": [ 51264, 10205, 2316, 11, 597, 307, 264, 51364 ], "temperature": 0.0, "avg_logprob": -0.16610360763094448, "compression_ratio": 1.6008064516129032, "no_speech_prob": 0.00669097900390625, "words": [ { "start": 5420.98, "end": 5421.48, "word": " performing", "probability": 0.56591796875 }, { "start": 5421.48, "end": 5421.82, "word": " model", "probability": 0.81982421875 }, { "start": 5421.82, "end": 5422.0, "word": ",", "probability": 0.884765625 }, { "start": 5422.0, "end": 5422.06, "word": " which", "probability": 0.880859375 }, { "start": 5422.06, "end": 5422.2, "word": " is", "probability": 0.9052734375 }, { "start": 5422.2, "end": 5422.4, "word": " the", "probability": 0.81396484375 } ] }, { "id": 1677, "seek": 523106, "start": 5422.4, "end": 5425.08, "text": " logistic regression with the count vectorizer,", "tokens": [ 51364, 3565, 3142, 24590, 365, 264, 1207, 8062, 6545, 11, 51464 ], "temperature": 0.0, "avg_logprob": -0.16610360763094448, "compression_ratio": 1.6008064516129032, "no_speech_prob": 0.00669097900390625, "words": [ { "start": 5422.4, "end": 5422.82, "word": " logistic", "probability": 0.921142578125 }, { "start": 5422.82, "end": 5423.24, "word": " regression", "probability": 0.8408203125 }, { "start": 5423.24, "end": 5423.48, "word": " with", "probability": 0.78759765625 }, { "start": 5423.48, "end": 5423.6, "word": " the", "probability": 0.468994140625 }, { "start": 5423.6, "end": 5423.8, "word": " count", "probability": 0.70703125 }, { "start": 5423.8, "end": 5424.46, "word": " vectorizer", "probability": 0.942626953125 }, { "start": 5424.46, "end": 5425.08, "word": ",", "probability": 0.85302734375 } ] }, { "id": 1678, "seek": 523106, "start": 5425.08, "end": 5426.76, "text": " correctly classified this as a", "tokens": [ 51464, 8944, 20627, 341, 382, 257, 51564 ], "temperature": 0.0, "avg_logprob": -0.16610360763094448, "compression_ratio": 1.6008064516129032, "no_speech_prob": 0.00669097900390625, "words": [ { "start": 5425.08, "end": 5425.42, "word": " correctly", "probability": 0.87646484375 }, { "start": 5425.42, "end": 5425.92, "word": " classified", "probability": 0.875 }, { "start": 5425.92, "end": 5426.24, "word": " this", "probability": 0.87451171875 }, { "start": 5426.24, "end": 5426.38, "word": " as", "probability": 0.9091796875 }, { "start": 5426.5, "end": 5426.76, "word": " a spam", "probability": 0.9462890625 } ] }, { "id": 1679, "seek": 523106, "start": 5426.76, "end": 5428.9, "text": " spam email. But our worst", "tokens": [ 51564, 24028, 3796, 13, 583, 527, 5855, 51664 ], "temperature": 0.0, "avg_logprob": -0.16610360763094448, "compression_ratio": 1.6008064516129032, "no_speech_prob": 0.00669097900390625, "words": [ { "start": 5426.76, "end": 5427.08, "word": " email", "probability": 0.8984375 }, { "start": 5427.08, "end": 5427.56, "word": ".", "probability": 0.755859375 }, { "start": 5427.64, "end": 5427.96, "word": " But", "probability": 0.8671875 }, { "start": 5427.96, "end": 5428.08, "word": " our", "probability": 0.7978515625 }, { "start": 5428.08, "end": 5428.46, "word": " worst", "probability": 0.9189453125 }, { "start": 5428.46, "end": 5428.9, "word": " performing", "probability": 0.70849609375 } ] }, { "id": 1680, "seek": 523106, "start": 5428.9, "end": 5430.46, "text": " performing model, even though it still had an", "tokens": [ 51664, 10205, 2316, 11, 754, 1673, 309, 920, 632, 364, 51764 ], "temperature": 0.0, "avg_logprob": -0.16610360763094448, "compression_ratio": 1.6008064516129032, "no_speech_prob": 0.00669097900390625, "words": [ { "start": 5428.9, "end": 5429.24, "word": " model", "probability": 0.8251953125 }, { "start": 5429.24, "end": 5429.32, "word": ",", "probability": 0.9375 }, { "start": 5429.32, "end": 5429.48, "word": " even", "probability": 0.810546875 }, { "start": 5429.48, "end": 5429.62, "word": " though", "probability": 0.7685546875 }, { "start": 5429.62, "end": 5429.74, "word": " it", "probability": 0.90771484375 }, { "start": 5429.74, "end": 5429.94, "word": " still", "probability": 0.8935546875 }, { "start": 5429.94, "end": 5430.3, "word": " had", "probability": 0.81201171875 }, { "start": 5430.3, "end": 5430.46, "word": " an", "probability": 0.896484375 } ] }, { "id": 1681, "seek": 525906, "start": 5430.46, "end": 5432.48, "text": " 87.5% accuracy,", "tokens": [ 50364, 27990, 13, 20, 4, 14170, 11, 50464 ], "temperature": 0.0, "avg_logprob": -0.17542614110491492, "compression_ratio": 1.4833333333333334, "no_speech_prob": 0.001956939697265625, "words": [ { "start": 5430.46, "end": 5430.82, "word": " 87", "probability": 0.244384765625 }, { "start": 5430.82, "end": 5431.44, "word": ".5", "probability": 0.992919921875 }, { "start": 5431.44, "end": 5431.72, "word": "%", "probability": 0.74169921875 }, { "start": 5431.72, "end": 5432.24, "word": " accuracy", "probability": 0.71533203125 }, { "start": 5432.24, "end": 5432.48, "word": ",", "probability": 0.56103515625 } ] }, { "id": 1682, "seek": 525906, "start": 5433.04, "end": 5434.3, "text": " our multinomial Naive Bayesian", "tokens": [ 50464, 527, 45872, 47429, 6056, 488, 7840, 42434, 50564 ], "temperature": 0.0, "avg_logprob": -0.17542614110491492, "compression_ratio": 1.4833333333333334, "no_speech_prob": 0.001956939697265625, "words": [ { "start": 5433.04, "end": 5433.14, "word": " our", "probability": 0.755859375 }, { "start": 5433.14, "end": 5433.66, "word": " multinomial", "probability": 0.892822265625 }, { "start": 5433.66, "end": 5433.98, "word": " Naive", "probability": 0.547119140625 }, { "start": 5433.98, "end": 5434.3, "word": " Bayesian", "probability": 0.9267578125 } ] }, { "id": 1683, "seek": 525906, "start": 5434.3, "end": 5436.54, "text": " with tf.idf incorrectly classified", "tokens": [ 50564, 365, 256, 69, 13, 327, 69, 42892, 20627, 50664 ], "temperature": 0.0, "avg_logprob": -0.17542614110491492, "compression_ratio": 1.4833333333333334, "no_speech_prob": 0.001956939697265625, "words": [ { "start": 5434.3, "end": 5434.48, "word": " with", "probability": 0.73974609375 }, { "start": 5434.48, "end": 5434.74, "word": " tf", "probability": 0.504302978515625 }, { "start": 5434.74, "end": 5435.18, "word": ".idf", "probability": 0.6612141927083334 }, { "start": 5435.18, "end": 5436.02, "word": " incorrectly", "probability": 0.74755859375 }, { "start": 5436.02, "end": 5436.54, "word": " classified", "probability": 0.9248046875 } ] }, { "id": 1684, "seek": 525906, "start": 5436.54, "end": 5438.66, "text": " this as a ham email.", "tokens": [ 50664, 341, 382, 257, 7852, 3796, 13, 50764 ], "temperature": 0.0, "avg_logprob": -0.17542614110491492, "compression_ratio": 1.4833333333333334, "no_speech_prob": 0.001956939697265625, "words": [ { "start": 5436.54, "end": 5436.96, "word": " this", "probability": 0.87060546875 }, { "start": 5436.96, "end": 5437.44, "word": " as", "probability": 0.896484375 }, { "start": 5437.56, "end": 5437.82, "word": " a ham", "probability": 0.53271484375 }, { "start": 5437.82, "end": 5438.18, "word": " email", "probability": 0.84716796875 }, { "start": 5438.18, "end": 5438.66, "word": ".", "probability": 0.81396484375 } ] }, { "id": 1685, "seek": 525906, "start": 5439.62, "end": 5440.44, "text": " And so this is also", "tokens": [ 50764, 400, 370, 341, 307, 611, 50864 ], "temperature": 0.0, "avg_logprob": -0.17542614110491492, "compression_ratio": 1.4833333333333334, "no_speech_prob": 0.001956939697265625, "words": [ { "start": 5439.62, "end": 5439.72, "word": " And", "probability": 0.53759765625 }, { "start": 5439.72, "end": 5439.84, "word": " so", "probability": 0.8955078125 }, { "start": 5439.84, "end": 5440.06, "word": " this", "probability": 0.759765625 }, { "start": 5440.06, "end": 5440.2, "word": " is", "probability": 0.9072265625 }, { "start": 5440.2, "end": 5440.44, "word": " also", "probability": 0.8173828125 } ] }, { "id": 1686, "seek": 525906, "start": 5440.44, "end": 5441.38, "text": " why we want to", "tokens": [ 50864, 983, 321, 528, 281, 50964 ], "temperature": 0.0, "avg_logprob": -0.17542614110491492, "compression_ratio": 1.4833333333333334, "no_speech_prob": 0.001956939697265625, "words": [ { "start": 5440.44, "end": 5440.64, "word": " why", "probability": 0.822265625 }, { "start": 5440.64, "end": 5440.78, "word": " we", "probability": 0.9033203125 }, { "start": 5440.78, "end": 5440.96, "word": " want", "probability": 0.75830078125 }, { "start": 5440.96, "end": 5441.38, "word": " to", "probability": 0.90478515625 } ] }, { "id": 1687, "seek": 525906, "start": 5442.02, "end": 5444.28, "text": " try building different models and get things that", "tokens": [ 50964, 853, 2390, 819, 5245, 293, 483, 721, 300, 51064 ], "temperature": 0.0, "avg_logprob": -0.17542614110491492, "compression_ratio": 1.4833333333333334, "no_speech_prob": 0.001956939697265625, "words": [ { "start": 5442.02, "end": 5442.5, "word": " try", "probability": 0.7548828125 }, { "start": 5442.5, "end": 5442.76, "word": " building", "probability": 0.77783203125 }, { "start": 5442.76, "end": 5443.04, "word": " different", "probability": 0.697265625 }, { "start": 5443.04, "end": 5443.38, "word": " models", "probability": 0.7998046875 }, { "start": 5443.38, "end": 5443.6, "word": " and", "probability": 0.8623046875 }, { "start": 5443.6, "end": 5443.78, "word": " get", "probability": 0.89111328125 }, { "start": 5443.78, "end": 5444.08, "word": " things", "probability": 0.72412109375 }, { "start": 5444.08, "end": 5444.28, "word": " that", "probability": 0.8798828125 } ] }, { "id": 1688, "seek": 525906, "start": 5444.28, "end": 5445.76, "text": " predict much better.", "tokens": [ 51064, 6069, 709, 1101, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.17542614110491492, "compression_ratio": 1.4833333333333334, "no_speech_prob": 0.001956939697265625, "words": [ { "start": 5444.28, "end": 5444.66, "word": " predict", "probability": 0.76953125 }, { "start": 5444.66, "end": 5444.96, "word": " much", "probability": 0.7470703125 }, { "start": 5444.96, "end": 5445.28, "word": " better", "probability": 0.81396484375 }, { "start": 5445.28, "end": 5445.76, "word": ".", "probability": 0.9384765625 } ] }, { "id": 1689, "seek": 525906, "start": 5451.02, "end": 5452.44, "text": " Let me know if there's any", "tokens": [ 51364, 961, 385, 458, 498, 456, 311, 604, 51464 ], "temperature": 0.0, "avg_logprob": -0.17542614110491492, "compression_ratio": 1.4833333333333334, "no_speech_prob": 0.001956939697265625, "words": [ { "start": 5451.02, "end": 5451.5, "word": " Let", "probability": 0.07891845703125 }, { "start": 5451.5, "end": 5451.98, "word": " me", "probability": 0.904296875 }, { "start": 5451.98, "end": 5452.08, "word": " know", "probability": 0.81201171875 }, { "start": 5452.08, "end": 5452.18, "word": " if", "probability": 0.908203125 }, { "start": 5452.18, "end": 5452.32, "word": " there's", "probability": 0.893310546875 }, { "start": 5452.32, "end": 5452.44, "word": " any", "probability": 0.818359375 } ] }, { "id": 1690, "seek": 525906, "start": 5452.44, "end": 5453.7, "text": " questions on that.", "tokens": [ 51464, 1651, 322, 300, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.17542614110491492, "compression_ratio": 1.4833333333333334, "no_speech_prob": 0.001956939697265625, "words": [ { "start": 5452.44, "end": 5452.78, "word": " questions", "probability": 0.9052734375 }, { "start": 5452.78, "end": 5453.02, "word": " on", "probability": 0.8857421875 }, { "start": 5453.02, "end": 5453.22, "word": " that", "probability": 0.8798828125 }, { "start": 5453.22, "end": 5453.7, "word": ".", "probability": 0.8564453125 } ] }, { "id": 1691, "seek": 525906, "start": 5454.22, "end": 5456.38, "text": " We are short on time. We're actually running", "tokens": [ 51564, 492, 366, 2099, 322, 565, 13, 492, 434, 767, 2614, 51664 ], "temperature": 0.0, "avg_logprob": -0.17542614110491492, "compression_ratio": 1.4833333333333334, "no_speech_prob": 0.001956939697265625, "words": [ { "start": 5454.22, "end": 5454.7, "word": " We", "probability": 0.89599609375 }, { "start": 5454.7, "end": 5454.88, "word": " are", "probability": 0.88232421875 }, { "start": 5454.88, "end": 5455.36, "word": " short", "probability": 0.89697265625 }, { "start": 5455.36, "end": 5455.52, "word": " on", "probability": 0.900390625 }, { "start": 5455.52, "end": 5455.8, "word": " time", "probability": 0.8017578125 }, { "start": 5455.8, "end": 5455.92, "word": ".", "probability": 0.51806640625 }, { "start": 5455.92, "end": 5455.98, "word": " We're", "probability": 0.911376953125 }, { "start": 5455.98, "end": 5456.16, "word": " actually", "probability": 0.78955078125 }, { "start": 5456.16, "end": 5456.38, "word": " running", "probability": 0.875 } ] }, { "id": 1692, "seek": 525906, "start": 5456.5, "end": 5458.46, "text": " a little over, but before I let you go, there's one more", "tokens": [ 51664, 257, 707, 670, 11, 457, 949, 286, 718, 291, 352, 11, 456, 311, 472, 544, 51764 ], "temperature": 0.0, "avg_logprob": -0.17542614110491492, "compression_ratio": 1.4833333333333334, "no_speech_prob": 0.001956939697265625, "words": [ { "start": 5456.5, "end": 5456.6, "word": " a little", "probability": 0.8125 }, { "start": 5456.6, "end": 5456.9, "word": " over", "probability": 0.87890625 }, { "start": 5456.9, "end": 5457.08, "word": ",", "probability": 0.485107421875 }, { "start": 5457.08, "end": 5457.2, "word": " but", "probability": 0.89404296875 }, { "start": 5457.2, "end": 5457.52, "word": " before", "probability": 0.79736328125 }, { "start": 5457.52, "end": 5457.62, "word": " I", "probability": 0.9833984375 }, { "start": 5457.62, "end": 5457.7, "word": " let", "probability": 0.890625 }, { "start": 5457.7, "end": 5457.8, "word": " you", "probability": 0.896484375 }, { "start": 5457.8, "end": 5457.94, "word": " go", "probability": 0.908203125 }, { "start": 5457.94, "end": 5458.0, "word": ",", "probability": 0.6357421875 }, { "start": 5458.0, "end": 5458.12, "word": " there's", "probability": 0.927734375 }, { "start": 5458.12, "end": 5458.32, "word": " one", "probability": 0.8203125 }, { "start": 5458.32, "end": 5458.46, "word": " more", "probability": 0.8828125 } ] }, { "id": 1693, "seek": 528654, "start": 5458.46, "end": 5460.74, "text": " thing I want to show you. And that is", "tokens": [ 50364, 551, 286, 528, 281, 855, 291, 13, 400, 300, 307, 50464 ], "temperature": 0.0, "avg_logprob": -0.16581357424629145, "compression_ratio": 1.5247524752475248, "no_speech_prob": 0.025177001953125, "words": [ { "start": 5458.46, "end": 5458.64, "word": " thing", "probability": 0.372314453125 }, { "start": 5458.64, "end": 5458.74, "word": " I", "probability": 0.93798828125 }, { "start": 5458.74, "end": 5458.84, "word": " want", "probability": 0.76025390625 }, { "start": 5458.84, "end": 5458.92, "word": " to", "probability": 0.90673828125 }, { "start": 5458.92, "end": 5459.1, "word": " show", "probability": 0.87646484375 }, { "start": 5459.1, "end": 5459.32, "word": " you", "probability": 0.89501953125 }, { "start": 5459.32, "end": 5459.84, "word": ".", "probability": 0.1455078125 }, { "start": 5460.04, "end": 5460.08, "word": " And", "probability": 0.7099609375 }, { "start": 5460.08, "end": 5460.26, "word": " that", "probability": 0.8740234375 }, { "start": 5460.26, "end": 5460.74, "word": " is", "probability": 0.90283203125 } ] }, { "id": 1694, "seek": 528654, "start": 5460.74, "end": 5462.46, "text": " the hyperparameter", "tokens": [ 50464, 264, 9848, 2181, 335, 2398, 50564 ], "temperature": 0.0, "avg_logprob": -0.16581357424629145, "compression_ratio": 1.5247524752475248, "no_speech_prob": 0.025177001953125, "words": [ { "start": 5460.74, "end": 5461.22, "word": " the", "probability": 0.7861328125 }, { "start": 5461.22, "end": 5462.46, "word": " hyperparameter", "probability": 0.833984375 } ] }, { "id": 1695, "seek": 528654, "start": 5462.46, "end": 5464.42, "text": " tuning. So if we", "tokens": [ 50564, 15164, 13, 407, 498, 321, 50664 ], "temperature": 0.0, "avg_logprob": -0.16581357424629145, "compression_ratio": 1.5247524752475248, "no_speech_prob": 0.025177001953125, "words": [ { "start": 5462.46, "end": 5462.9, "word": " tuning", "probability": 0.81591796875 }, { "start": 5462.9, "end": 5463.42, "word": ".", "probability": 0.97998046875 }, { "start": 5463.66, "end": 5464.02, "word": " So", "probability": 0.86962890625 }, { "start": 5464.02, "end": 5464.26, "word": " if", "probability": 0.765625 }, { "start": 5464.26, "end": 5464.42, "word": " we", "probability": 0.912109375 } ] }, { "id": 1696, "seek": 528654, "start": 5464.42, "end": 5466.62, "text": " jump up to that worst performing model,", "tokens": [ 50664, 3012, 493, 281, 300, 5855, 10205, 2316, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.16581357424629145, "compression_ratio": 1.5247524752475248, "no_speech_prob": 0.025177001953125, "words": [ { "start": 5464.42, "end": 5464.68, "word": " jump", "probability": 0.80517578125 }, { "start": 5464.68, "end": 5464.86, "word": " up", "probability": 0.90625 }, { "start": 5464.86, "end": 5465.0, "word": " to", "probability": 0.90576171875 }, { "start": 5465.0, "end": 5465.18, "word": " that", "probability": 0.87353515625 }, { "start": 5465.18, "end": 5465.6, "word": " worst", "probability": 0.9150390625 }, { "start": 5465.6, "end": 5466.1, "word": " performing", "probability": 0.62744140625 }, { "start": 5466.1, "end": 5466.5, "word": " model", "probability": 0.806640625 }, { "start": 5466.5, "end": 5466.62, "word": ",", "probability": 0.6337890625 } ] }, { "id": 1697, "seek": 528654, "start": 5466.62, "end": 5468.1, "text": " that 0.85%,", "tokens": [ 50764, 300, 1958, 13, 19287, 8923, 50864 ], "temperature": 0.0, "avg_logprob": -0.16581357424629145, "compression_ratio": 1.5247524752475248, "no_speech_prob": 0.025177001953125, "words": [ { "start": 5466.62, "end": 5466.76, "word": " that", "probability": 0.876953125 }, { "start": 5466.76, "end": 5467.08, "word": " 0", "probability": 0.61376953125 }, { "start": 5467.08, "end": 5468.1, "word": ".85%,", "probability": 0.7802734375 } ] }, { "id": 1698, "seek": 528654, "start": 5468.1, "end": 5470.66, "text": " the multinomial with tf.idf,", "tokens": [ 50864, 264, 45872, 47429, 365, 256, 69, 13, 327, 69, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.16581357424629145, "compression_ratio": 1.5247524752475248, "no_speech_prob": 0.025177001953125, "words": [ { "start": 5468.1, "end": 5468.5, "word": " the", "probability": 0.8076171875 }, { "start": 5468.5, "end": 5469.18, "word": " multinomial", "probability": 0.90087890625 }, { "start": 5469.18, "end": 5469.42, "word": " with", "probability": 0.77392578125 }, { "start": 5469.42, "end": 5469.76, "word": " tf", "probability": 0.5274658203125 }, { "start": 5469.76, "end": 5470.4, "word": ".idf", "probability": 0.6932779947916666 }, { "start": 5470.4, "end": 5470.66, "word": ",", "probability": 0.54736328125 } ] }, { "id": 1699, "seek": 528654, "start": 5471.58, "end": 5472.18, "text": " sorry,", "tokens": [ 50964, 2597, 11, 51064 ], "temperature": 0.0, "avg_logprob": -0.16581357424629145, "compression_ratio": 1.5247524752475248, "no_speech_prob": 0.025177001953125, "words": [ { "start": 5471.58, "end": 5472.04, "word": " sorry", "probability": 0.60205078125 }, { "start": 5472.04, "end": 5472.18, "word": ",", "probability": 0.67138671875 } ] }, { "id": 1700, "seek": 528654, "start": 5472.18, "end": 5473.94, "text": " 0.875%.", "tokens": [ 51064, 1958, 13, 23, 11901, 6856, 51164 ], "temperature": 0.0, "avg_logprob": -0.16581357424629145, "compression_ratio": 1.5247524752475248, "no_speech_prob": 0.025177001953125, "words": [ { "start": 5472.18, "end": 5472.3, "word": " 0", "probability": 0.9697265625 }, { "start": 5472.3, "end": 5473.94, "word": ".875%.", "probability": 0.8663330078125 } ] }, { "id": 1701, "seek": 528654, "start": 5475.16, "end": 5476.4, "text": " And we use that", "tokens": [ 51164, 400, 321, 764, 300, 51264 ], "temperature": 0.0, "avg_logprob": -0.16581357424629145, "compression_ratio": 1.5247524752475248, "no_speech_prob": 0.025177001953125, "words": [ { "start": 5475.16, "end": 5475.68, "word": " And", "probability": 0.89501953125 }, { "start": 5475.68, "end": 5475.82, "word": " we", "probability": 0.90625 }, { "start": 5475.82, "end": 5476.1, "word": " use", "probability": 0.7412109375 }, { "start": 5476.1, "end": 5476.4, "word": " that", "probability": 0.86572265625 } ] }, { "id": 1702, "seek": 528654, "start": 5476.4, "end": 5478.6, "text": " alpha that we saw in our", "tokens": [ 51264, 8961, 300, 321, 1866, 294, 527, 51364 ], "temperature": 0.0, "avg_logprob": -0.16581357424629145, "compression_ratio": 1.5247524752475248, "no_speech_prob": 0.025177001953125, "words": [ { "start": 5476.4, "end": 5476.82, "word": " alpha", "probability": 0.76220703125 }, { "start": 5476.82, "end": 5477.26, "word": " that", "probability": 0.85986328125 }, { "start": 5477.26, "end": 5477.4, "word": " we", "probability": 0.904296875 }, { "start": 5477.4, "end": 5477.76, "word": " saw", "probability": 0.82470703125 }, { "start": 5477.76, "end": 5478.14, "word": " in", "probability": 0.9033203125 }, { "start": 5478.14, "end": 5478.6, "word": " our", "probability": 0.822265625 } ] }, { "id": 1703, "seek": 528654, "start": 5478.6, "end": 5480.5, "text": " formulas on the slides.", "tokens": [ 51364, 30546, 322, 264, 9788, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.16581357424629145, "compression_ratio": 1.5247524752475248, "no_speech_prob": 0.025177001953125, "words": [ { "start": 5478.6, "end": 5479.08, "word": " formulas", "probability": 0.900390625 }, { "start": 5479.08, "end": 5479.34, "word": " on", "probability": 0.90380859375 }, { "start": 5479.34, "end": 5479.48, "word": " the", "probability": 0.81396484375 }, { "start": 5479.48, "end": 5479.98, "word": " slides", "probability": 0.90771484375 }, { "start": 5479.98, "end": 5480.5, "word": ".", "probability": 0.55029296875 } ] }, { "id": 1704, "seek": 528654, "start": 5481.32, "end": 5483.04, "text": " Alpha is set to 1.", "tokens": [ 51464, 20588, 307, 992, 281, 502, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.16581357424629145, "compression_ratio": 1.5247524752475248, "no_speech_prob": 0.025177001953125, "words": [ { "start": 5481.32, "end": 5481.84, "word": " Alpha", "probability": 0.8857421875 }, { "start": 5481.84, "end": 5482.02, "word": " is", "probability": 0.52880859375 }, { "start": 5482.02, "end": 5482.14, "word": " set", "probability": 0.87890625 }, { "start": 5482.14, "end": 5482.3, "word": " to", "probability": 0.90087890625 }, { "start": 5482.3, "end": 5482.58, "word": " 1", "probability": 0.1790771484375 }, { "start": 5482.58, "end": 5483.04, "word": ".", "probability": 0.5693359375 } ] }, { "id": 1705, "seek": 528654, "start": 5483.04, "end": 5484.98, "text": " We can go ahead and run that.", "tokens": [ 51564, 492, 393, 352, 2286, 293, 1190, 300, 13, 51664 ], "temperature": 0.0, "avg_logprob": -0.16581357424629145, "compression_ratio": 1.5247524752475248, "no_speech_prob": 0.025177001953125, "words": [ { "start": 5483.04, "end": 5483.4, "word": " We", "probability": 0.728515625 }, { "start": 5483.4, "end": 5483.52, "word": " can", "probability": 0.8984375 }, { "start": 5483.52, "end": 5483.66, "word": " go", "probability": 0.904296875 }, { "start": 5483.66, "end": 5483.86, "word": " ahead", "probability": 0.8525390625 }, { "start": 5483.86, "end": 5484.04, "word": " and", "probability": 0.896484375 }, { "start": 5484.04, "end": 5484.2, "word": " run", "probability": 0.8994140625 }, { "start": 5484.2, "end": 5484.46, "word": " that", "probability": 0.87841796875 }, { "start": 5484.46, "end": 5484.98, "word": ".", "probability": 0.7119140625 } ] }, { "id": 1706, "seek": 528654, "start": 5485.06, "end": 5485.94, "text": " And we see that we're at", "tokens": [ 51664, 400, 321, 536, 300, 321, 434, 412, 51764 ], "temperature": 0.0, "avg_logprob": -0.16581357424629145, "compression_ratio": 1.5247524752475248, "no_speech_prob": 0.025177001953125, "words": [ { "start": 5485.06, "end": 5485.24, "word": " And", "probability": 0.705078125 }, { "start": 5485.24, "end": 5485.32, "word": " we", "probability": 0.89697265625 }, { "start": 5485.32, "end": 5485.46, "word": " see", "probability": 0.8115234375 }, { "start": 5485.46, "end": 5485.6, "word": " that", "probability": 0.888671875 }, { "start": 5485.6, "end": 5485.76, "word": " we're", "probability": 0.925048828125 }, { "start": 5485.76, "end": 5485.94, "word": " at", "probability": 0.90771484375 } ] }, { "id": 1707, "seek": 531470, "start": 5485.94, "end": 5487.56, "text": " 0.875.", "tokens": [ 50364, 1958, 13, 23, 11901, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.14062499799648254, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5485.94, "end": 5486.4, "word": " 0", "probability": 0.35302734375 }, { "start": 5486.4, "end": 5487.04, "word": ".875", "probability": 0.9388020833333334 }, { "start": 5487.04, "end": 5487.56, "word": ".", "probability": 0.53271484375 } ] }, { "id": 1708, "seek": 531470, "start": 5488.06, "end": 5489.96, "text": " But what if we shrink that alpha", "tokens": [ 50464, 583, 437, 498, 321, 23060, 300, 8961, 50564 ], "temperature": 0.0, "avg_logprob": -0.14062499799648254, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5488.06, "end": 5488.58, "word": " But", "probability": 0.841796875 }, { "start": 5488.58, "end": 5488.72, "word": " what", "probability": 0.85205078125 }, { "start": 5488.72, "end": 5488.84, "word": " if", "probability": 0.90625 }, { "start": 5488.84, "end": 5489.08, "word": " we", "probability": 0.9033203125 }, { "start": 5489.08, "end": 5489.48, "word": " shrink", "probability": 0.8916015625 }, { "start": 5489.48, "end": 5489.7, "word": " that", "probability": 0.87353515625 }, { "start": 5489.7, "end": 5489.96, "word": " alpha", "probability": 0.767578125 } ] }, { "id": 1709, "seek": 531470, "start": 5489.96, "end": 5491.74, "text": " to 0.1?", "tokens": [ 50564, 281, 1958, 13, 16, 30, 50664 ], "temperature": 0.0, "avg_logprob": -0.14062499799648254, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5489.96, "end": 5490.38, "word": " to", "probability": 0.8916015625 }, { "start": 5490.38, "end": 5490.92, "word": " 0", "probability": 0.92529296875 }, { "start": 5490.92, "end": 5491.28, "word": ".1", "probability": 0.99267578125 }, { "start": 5491.28, "end": 5491.74, "word": "?", "probability": 0.65185546875 } ] }, { "id": 1710, "seek": 531470, "start": 5491.74, "end": 5494.12, "text": " This is hyperparameter tuning. We can change", "tokens": [ 50664, 639, 307, 9848, 2181, 335, 2398, 15164, 13, 492, 393, 1319, 50764 ], "temperature": 0.0, "avg_logprob": -0.14062499799648254, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5491.74, "end": 5492.0, "word": " This", "probability": 0.78955078125 }, { "start": 5492.0, "end": 5492.24, "word": " is", "probability": 0.9033203125 }, { "start": 5492.24, "end": 5493.18, "word": " hyperparameter", "probability": 0.86181640625 }, { "start": 5493.18, "end": 5493.46, "word": " tuning", "probability": 0.79150390625 }, { "start": 5493.46, "end": 5493.56, "word": ".", "probability": 0.55859375 }, { "start": 5493.56, "end": 5493.66, "word": " We", "probability": 0.796875 }, { "start": 5493.66, "end": 5493.78, "word": " can", "probability": 0.77392578125 }, { "start": 5493.78, "end": 5494.12, "word": " change", "probability": 0.83740234375 } ] }, { "id": 1711, "seek": 531470, "start": 5494.12, "end": 5494.84, "text": " it.", "tokens": [ 50764, 309, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.14062499799648254, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5494.12, "end": 5494.32, "word": " it", "probability": 0.9033203125 }, { "start": 5494.32, "end": 5494.84, "word": ".", "probability": 0.810546875 } ] }, { "id": 1712, "seek": 531470, "start": 5495.78, "end": 5497.92, "text": " Now our accuracy changed from", "tokens": [ 50864, 823, 527, 14170, 3105, 490, 50964 ], "temperature": 0.0, "avg_logprob": -0.14062499799648254, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5495.78, "end": 5496.16, "word": " Now", "probability": 0.431640625 }, { "start": 5496.16, "end": 5496.36, "word": " our", "probability": 0.72998046875 }, { "start": 5496.36, "end": 5496.74, "word": " accuracy", "probability": 0.7607421875 }, { "start": 5496.74, "end": 5497.44, "word": " changed", "probability": 0.5849609375 }, { "start": 5497.44, "end": 5497.92, "word": " from", "probability": 0.8076171875 } ] }, { "id": 1713, "seek": 531470, "start": 5497.92, "end": 5499.68, "text": " one of the worst models that we have", "tokens": [ 50964, 472, 295, 264, 5855, 5245, 300, 321, 362, 51064 ], "temperature": 0.0, "avg_logprob": -0.14062499799648254, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5497.92, "end": 5498.1, "word": " one", "probability": 0.82666015625 }, { "start": 5498.1, "end": 5498.2, "word": " of", "probability": 0.90087890625 }, { "start": 5498.2, "end": 5498.42, "word": " the", "probability": 0.8115234375 }, { "start": 5498.42, "end": 5498.68, "word": " worst", "probability": 0.9091796875 }, { "start": 5498.68, "end": 5498.98, "word": " models", "probability": 0.7978515625 }, { "start": 5498.98, "end": 5499.14, "word": " that", "probability": 0.8798828125 }, { "start": 5499.14, "end": 5499.28, "word": " we", "probability": 0.904296875 }, { "start": 5499.28, "end": 5499.68, "word": " have", "probability": 0.869140625 } ] }, { "id": 1714, "seek": 531470, "start": 5499.68, "end": 5502.32, "text": " to one of the better models that we have.", "tokens": [ 51064, 281, 472, 295, 264, 1101, 5245, 300, 321, 362, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.14062499799648254, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5499.68, "end": 5500.32, "word": " to", "probability": 0.728515625 }, { "start": 5500.32, "end": 5500.46, "word": " one", "probability": 0.8271484375 }, { "start": 5500.46, "end": 5500.54, "word": " of", "probability": 0.904296875 }, { "start": 5500.54, "end": 5500.64, "word": " the", "probability": 0.8115234375 }, { "start": 5500.64, "end": 5500.84, "word": " better", "probability": 0.81982421875 }, { "start": 5500.84, "end": 5501.16, "word": " models", "probability": 0.8056640625 }, { "start": 5501.16, "end": 5501.32, "word": " that", "probability": 0.8828125 }, { "start": 5501.32, "end": 5501.46, "word": " we", "probability": 0.90673828125 }, { "start": 5501.46, "end": 5501.8, "word": " have", "probability": 0.87646484375 }, { "start": 5501.8, "end": 5502.32, "word": ".", "probability": 0.96630859375 } ] }, { "id": 1715, "seek": 531470, "start": 5502.64, "end": 5504.48, "text": " In fact, this is second place.", "tokens": [ 51164, 682, 1186, 11, 341, 307, 1150, 1081, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.14062499799648254, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5502.64, "end": 5502.82, "word": " In", "probability": 0.9072265625 }, { "start": 5502.82, "end": 5502.96, "word": " fact", "probability": 0.8125 }, { "start": 5502.96, "end": 5502.98, "word": ",", "probability": 0.705078125 }, { "start": 5502.98, "end": 5503.14, "word": " this", "probability": 0.88134765625 }, { "start": 5503.14, "end": 5503.26, "word": " is", "probability": 0.900390625 }, { "start": 5503.26, "end": 5503.5, "word": " second", "probability": 0.78369140625 }, { "start": 5503.5, "end": 5503.96, "word": " place", "probability": 0.8154296875 }, { "start": 5503.96, "end": 5504.48, "word": ".", "probability": 0.476318359375 } ] }, { "id": 1716, "seek": 531470, "start": 5504.66, "end": 5506.9, "text": " So we have 0.965%", "tokens": [ 51264, 407, 321, 362, 1958, 13, 24, 16824, 4, 51364 ], "temperature": 0.0, "avg_logprob": -0.14062499799648254, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5504.66, "end": 5504.92, "word": " So", "probability": 0.63916015625 }, { "start": 5504.92, "end": 5505.02, "word": " we", "probability": 0.8076171875 }, { "start": 5505.02, "end": 5505.12, "word": " have", "probability": 0.88037109375 }, { "start": 5505.12, "end": 5505.4, "word": " 0", "probability": 0.9638671875 }, { "start": 5505.4, "end": 5506.12, "word": ".965", "probability": 0.9659830729166666 }, { "start": 5506.12, "end": 5506.9, "word": "%", "probability": 0.5859375 } ] }, { "id": 1717, "seek": 531470, "start": 5506.9, "end": 5508.06, "text": " accuracy.", "tokens": [ 51364, 14170, 13, 51464 ], "temperature": 0.0, "avg_logprob": -0.14062499799648254, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5506.9, "end": 5507.54, "word": " accuracy", "probability": 0.7490234375 }, { "start": 5507.54, "end": 5508.06, "word": ".", "probability": 0.9658203125 } ] }, { "id": 1718, "seek": 531470, "start": 5509.48, "end": 5510.0, "text": " And so you can", "tokens": [ 51464, 400, 370, 291, 393, 51564 ], "temperature": 0.0, "avg_logprob": -0.14062499799648254, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5509.48, "end": 5509.66, "word": " And", "probability": 0.77783203125 }, { "start": 5509.66, "end": 5509.76, "word": " so", "probability": 0.90234375 }, { "start": 5509.76, "end": 5509.88, "word": " you", "probability": 0.8505859375 }, { "start": 5509.88, "end": 5510.0, "word": " can", "probability": 0.896484375 } ] }, { "id": 1719, "seek": 531470, "start": 5510.0, "end": 5511.86, "text": " see how hyperparameter tuning can", "tokens": [ 51564, 536, 577, 9848, 2181, 335, 2398, 15164, 393, 51664 ], "temperature": 0.0, "avg_logprob": -0.14062499799648254, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5510.0, "end": 5510.22, "word": " see", "probability": 0.8134765625 }, { "start": 5510.22, "end": 5510.52, "word": " how", "probability": 0.8896484375 }, { "start": 5510.52, "end": 5511.26, "word": " hyperparameter", "probability": 0.9652099609375 }, { "start": 5511.26, "end": 5511.6, "word": " tuning", "probability": 0.841796875 }, { "start": 5511.6, "end": 5511.86, "word": " can", "probability": 0.8994140625 } ] }, { "id": 1720, "seek": 531470, "start": 5511.86, "end": 5514.1, "text": " really help out in tweaking", "tokens": [ 51664, 534, 854, 484, 294, 6986, 2456, 51764 ], "temperature": 0.0, "avg_logprob": -0.14062499799648254, "compression_ratio": 1.5934579439252337, "no_speech_prob": 0.003482818603515625, "words": [ { "start": 5511.86, "end": 5512.12, "word": " really", "probability": 0.7802734375 }, { "start": 5512.12, "end": 5512.44, "word": " help", "probability": 0.81787109375 }, { "start": 5512.44, "end": 5512.78, "word": " out", "probability": 0.82373046875 }, { "start": 5512.78, "end": 5513.5, "word": " in", "probability": 0.8974609375 }, { "start": 5513.5, "end": 5514.1, "word": " tweaking", "probability": 0.934326171875 } ] }, { "id": 1721, "seek": 534262, "start": 5514.1, "end": 5515.96, "text": " the way that our models operate.", "tokens": [ 50364, 264, 636, 300, 527, 5245, 9651, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.2253951156276396, "compression_ratio": 1.5212765957446808, "no_speech_prob": 0.046722412109375, "words": [ { "start": 5514.1, "end": 5514.28, "word": " the", "probability": 0.55029296875 }, { "start": 5514.28, "end": 5514.44, "word": " way", "probability": 0.8916015625 }, { "start": 5514.44, "end": 5514.58, "word": " that", "probability": 0.68603515625 }, { "start": 5514.58, "end": 5514.72, "word": " our", "probability": 0.82958984375 }, { "start": 5514.72, "end": 5514.94, "word": " models", "probability": 0.80322265625 }, { "start": 5514.94, "end": 5515.44, "word": " operate", "probability": 0.73974609375 }, { "start": 5515.44, "end": 5515.96, "word": ".", "probability": 0.9619140625 } ] }, { "id": 1722, "seek": 534262, "start": 5523.13, "end": 5524.87, "text": " Before I let you go,", "tokens": [ 50664, 4546, 286, 718, 291, 352, 11, 50764 ], "temperature": 0.0, "avg_logprob": -0.2253951156276396, "compression_ratio": 1.5212765957446808, "no_speech_prob": 0.046722412109375, "words": [ { "start": 5523.13, "end": 5523.65, "word": " Before", "probability": 0.1766357421875 }, { "start": 5523.65, "end": 5524.17, "word": " I", "probability": 0.97509765625 }, { "start": 5524.17, "end": 5524.23, "word": " let", "probability": 0.90478515625 }, { "start": 5524.23, "end": 5524.33, "word": " you", "probability": 0.8994140625 }, { "start": 5524.33, "end": 5524.57, "word": " go", "probability": 0.90869140625 }, { "start": 5524.57, "end": 5524.87, "word": ",", "probability": 0.70263671875 } ] }, { "id": 1723, "seek": 534262, "start": 5528.83, "end": 5529.83, "text": " here's some references", "tokens": [ 50964, 510, 311, 512, 15400, 51064 ], "temperature": 0.0, "avg_logprob": -0.2253951156276396, "compression_ratio": 1.5212765957446808, "no_speech_prob": 0.046722412109375, "words": [ { "start": 5528.83, "end": 5529.35, "word": " here's", "probability": 0.62353515625 }, { "start": 5529.35, "end": 5529.49, "word": " some", "probability": 0.81640625 }, { "start": 5529.49, "end": 5529.83, "word": " references", "probability": 0.80078125 } ] }, { "id": 1724, "seek": 534262, "start": 5530.29, "end": 5532.55, "text": " for more information.", "tokens": [ 51064, 337, 544, 1589, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.2253951156276396, "compression_ratio": 1.5212765957446808, "no_speech_prob": 0.046722412109375, "words": [ { "start": 5530.29, "end": 5530.55, "word": " for", "probability": 0.8505859375 }, { "start": 5530.55, "end": 5531.57, "word": " more", "probability": 0.865234375 }, { "start": 5531.57, "end": 5532.03, "word": " information", "probability": 0.7353515625 }, { "start": 5532.03, "end": 5532.55, "word": ".", "probability": 0.5888671875 } ] }, { "id": 1725, "seek": 534262, "start": 5532.77, "end": 5534.05, "text": " And if you want the slides to this", "tokens": [ 51164, 400, 498, 291, 528, 264, 9788, 281, 341, 51264 ], "temperature": 0.0, "avg_logprob": -0.2253951156276396, "compression_ratio": 1.5212765957446808, "no_speech_prob": 0.046722412109375, "words": [ { "start": 5532.77, "end": 5532.79, "word": " And", "probability": 0.257568359375 }, { "start": 5532.79, "end": 5532.95, "word": " if", "probability": 0.890625 }, { "start": 5532.95, "end": 5533.03, "word": " you", "probability": 0.8935546875 }, { "start": 5533.03, "end": 5533.19, "word": " want", "probability": 0.81591796875 }, { "start": 5533.19, "end": 5533.33, "word": " the", "probability": 0.78271484375 }, { "start": 5533.33, "end": 5533.57, "word": " slides", "probability": 0.91943359375 }, { "start": 5533.57, "end": 5533.75, "word": " to", "probability": 0.85791015625 }, { "start": 5533.75, "end": 5534.05, "word": " this", "probability": 0.87548828125 } ] }, { "id": 1726, "seek": 534262, "start": 5534.05, "end": 5536.29, "text": " and more information from me", "tokens": [ 51264, 293, 544, 1589, 490, 385, 51364 ], "temperature": 0.0, "avg_logprob": -0.2253951156276396, "compression_ratio": 1.5212765957446808, "no_speech_prob": 0.046722412109375, "words": [ { "start": 5534.05, "end": 5534.59, "word": " and", "probability": 0.58251953125 }, { "start": 5534.59, "end": 5534.89, "word": " more", "probability": 0.86767578125 }, { "start": 5534.89, "end": 5535.41, "word": " information", "probability": 0.73828125 }, { "start": 5535.41, "end": 5535.87, "word": " from", "probability": 0.80712890625 }, { "start": 5535.87, "end": 5536.29, "word": " me", "probability": 0.9033203125 } ] }, { "id": 1727, "seek": 534262, "start": 5536.29, "end": 5538.53, "text": " and the GitHub", "tokens": [ 51364, 293, 264, 23331, 51464 ], "temperature": 0.0, "avg_logprob": -0.2253951156276396, "compression_ratio": 1.5212765957446808, "no_speech_prob": 0.046722412109375, "words": [ { "start": 5536.29, "end": 5536.91, "word": " and", "probability": 0.76171875 }, { "start": 5536.91, "end": 5537.91, "word": " the", "probability": 0.79541015625 }, { "start": 5537.91, "end": 5538.53, "word": " GitHub", "probability": 0.76708984375 } ] }, { "id": 1728, "seek": 534262, "start": 5538.53, "end": 5540.45, "text": " project that this is all part of,", "tokens": [ 51464, 1716, 300, 341, 307, 439, 644, 295, 11, 51564 ], "temperature": 0.0, "avg_logprob": -0.2253951156276396, "compression_ratio": 1.5212765957446808, "no_speech_prob": 0.046722412109375, "words": [ { "start": 5538.53, "end": 5538.95, "word": " project", "probability": 0.806640625 }, { "start": 5538.95, "end": 5539.13, "word": " that", "probability": 0.76708984375 }, { "start": 5539.13, "end": 5539.27, "word": " this", "probability": 0.833984375 }, { "start": 5539.27, "end": 5539.41, "word": " is", "probability": 0.89013671875 }, { "start": 5539.41, "end": 5539.57, "word": " all", "probability": 0.8857421875 }, { "start": 5539.57, "end": 5539.83, "word": " part", "probability": 0.76416015625 }, { "start": 5539.83, "end": 5540.13, "word": " of", "probability": 0.90771484375 }, { "start": 5540.13, "end": 5540.45, "word": ",", "probability": 0.896484375 } ] }, { "id": 1729, "seek": 534262, "start": 5540.45, "end": 5542.43, "text": " check out github.com.netsec", "tokens": [ 51564, 1520, 484, 290, 355, 836, 13, 1112, 13, 7129, 8159, 51664 ], "temperature": 0.0, "avg_logprob": -0.2253951156276396, "compression_ratio": 1.5212765957446808, "no_speech_prob": 0.046722412109375, "words": [ { "start": 5540.45, "end": 5540.73, "word": " check", "probability": 0.806640625 }, { "start": 5540.73, "end": 5540.91, "word": " out", "probability": 0.77294921875 }, { "start": 5540.91, "end": 5541.25, "word": " github", "probability": 0.861328125 }, { "start": 5541.25, "end": 5541.75, "word": ".com", "probability": 0.94580078125 }, { "start": 5541.75, "end": 5542.43, "word": ".netsec", "probability": 0.1360448201497396 } ] }, { "id": 1730, "seek": 534262, "start": 5542.43, "end": 5544.45, "text": " explain and you can shoot me an email with any", "tokens": [ 51664, 2903, 293, 291, 393, 3076, 385, 364, 3796, 365, 604, 51764 ], "temperature": 0.0, "avg_logprob": -0.2253951156276396, "compression_ratio": 1.5212765957446808, "no_speech_prob": 0.046722412109375, "words": [ { "start": 5542.43, "end": 5542.75, "word": " explain", "probability": 0.006801605224609375 }, { "start": 5542.75, "end": 5543.21, "word": " and", "probability": 0.422119140625 }, { "start": 5543.21, "end": 5543.31, "word": " you", "probability": 0.83544921875 }, { "start": 5543.31, "end": 5543.45, "word": " can", "probability": 0.8896484375 }, { "start": 5543.45, "end": 5543.61, "word": " shoot", "probability": 0.763671875 }, { "start": 5543.61, "end": 5543.75, "word": " me", "probability": 0.900390625 }, { "start": 5543.75, "end": 5543.87, "word": " an", "probability": 0.88232421875 }, { "start": 5543.87, "end": 5544.13, "word": " email", "probability": 0.87060546875 }, { "start": 5544.13, "end": 5544.31, "word": " with", "probability": 0.80712890625 }, { "start": 5544.31, "end": 5544.45, "word": " any", "probability": 0.79052734375 } ] }, { "id": 1731, "seek": 536718, "start": 5544.45, "end": 5546.71, "text": " questions, thoughts, comments", "tokens": [ 50364, 1651, 11, 4598, 11, 3053, 50464 ], "temperature": 0.0, "avg_logprob": -0.17316366470966144, "compression_ratio": 1.5502645502645502, "no_speech_prob": 0.2364501953125, "words": [ { "start": 5544.45, "end": 5544.95, "word": " questions", "probability": 0.47705078125 }, { "start": 5544.95, "end": 5545.21, "word": ",", "probability": 0.74072265625 }, { "start": 5545.21, "end": 5545.71, "word": " thoughts", "probability": 0.82861328125 }, { "start": 5545.71, "end": 5546.25, "word": ",", "probability": 0.94873046875 }, { "start": 5546.25, "end": 5546.71, "word": " comments", "probability": 0.7314453125 } ] }, { "id": 1732, "seek": 536718, "start": 5546.71, "end": 5548.37, "text": " at gtklondike", "tokens": [ 50464, 412, 290, 83, 7837, 684, 1123, 50564 ], "temperature": 0.0, "avg_logprob": -0.17316366470966144, "compression_ratio": 1.5502645502645502, "no_speech_prob": 0.2364501953125, "words": [ { "start": 5546.71, "end": 5547.61, "word": " at", "probability": 0.60986328125 }, { "start": 5547.61, "end": 5548.37, "word": " gtklondike", "probability": 0.84033203125 } ] }, { "id": 1733, "seek": 536718, "start": 5548.37, "end": 5549.93, "text": " at gmail.com", "tokens": [ 50564, 412, 290, 11799, 13, 1112, 50664 ], "temperature": 0.0, "avg_logprob": -0.17316366470966144, "compression_ratio": 1.5502645502645502, "no_speech_prob": 0.2364501953125, "words": [ { "start": 5548.37, "end": 5548.65, "word": " at", "probability": 0.016021728515625 }, { "start": 5548.65, "end": 5549.11, "word": " gmail", "probability": 0.870849609375 }, { "start": 5549.11, "end": 5549.93, "word": ".com", "probability": 0.865234375 } ] }, { "id": 1734, "seek": 536718, "start": 5552.31, "end": 5554.21, "text": " So that's all I have for you guys.", "tokens": [ 50764, 407, 300, 311, 439, 286, 362, 337, 291, 1074, 13, 50864 ], "temperature": 0.0, "avg_logprob": -0.17316366470966144, "compression_ratio": 1.5502645502645502, "no_speech_prob": 0.2364501953125, "words": [ { "start": 5552.31, "end": 5552.87, "word": " So", "probability": 0.11224365234375 }, { "start": 5552.87, "end": 5553.25, "word": " that's", "probability": 0.859130859375 }, { "start": 5553.25, "end": 5553.35, "word": " all", "probability": 0.90673828125 }, { "start": 5553.35, "end": 5553.43, "word": " I", "probability": 0.9482421875 }, { "start": 5553.43, "end": 5553.59, "word": " have", "probability": 0.876953125 }, { "start": 5553.59, "end": 5553.69, "word": " for", "probability": 0.896484375 }, { "start": 5553.69, "end": 5553.81, "word": " you", "probability": 0.89599609375 }, { "start": 5553.81, "end": 5554.07, "word": " guys", "probability": 0.88623046875 }, { "start": 5554.07, "end": 5554.21, "word": ".", "probability": 0.59423828125 } ] }, { "id": 1735, "seek": 536718, "start": 5554.21, "end": 5556.31, "text": " If there's any discussion,", "tokens": [ 50864, 759, 456, 311, 604, 5017, 11, 50964 ], "temperature": 0.0, "avg_logprob": -0.17316366470966144, "compression_ratio": 1.5502645502645502, "no_speech_prob": 0.2364501953125, "words": [ { "start": 5554.21, "end": 5554.41, "word": " If", "probability": 0.88671875 }, { "start": 5554.41, "end": 5554.73, "word": " there's", "probability": 0.9150390625 }, { "start": 5554.73, "end": 5555.03, "word": " any", "probability": 0.79833984375 }, { "start": 5555.03, "end": 5555.65, "word": " discussion", "probability": 0.76171875 }, { "start": 5555.65, "end": 5556.31, "word": ",", "probability": 0.61962890625 } ] }, { "id": 1736, "seek": 536718, "start": 5556.31, "end": 5558.27, "text": " TAs, do we have a separate room for the workshops", "tokens": [ 50964, 314, 10884, 11, 360, 321, 362, 257, 4994, 1808, 337, 264, 19162, 51064 ], "temperature": 0.0, "avg_logprob": -0.17316366470966144, "compression_ratio": 1.5502645502645502, "no_speech_prob": 0.2364501953125, "words": [ { "start": 5556.31, "end": 5556.63, "word": " TAs", "probability": 0.571533203125 }, { "start": 5556.63, "end": 5556.69, "word": ",", "probability": 0.666015625 }, { "start": 5556.69, "end": 5556.79, "word": " do", "probability": 0.890625 }, { "start": 5556.79, "end": 5556.91, "word": " we", "probability": 0.90576171875 }, { "start": 5556.91, "end": 5557.07, "word": " have", "probability": 0.8798828125 }, { "start": 5557.21, "end": 5557.47, "word": " a separate", "probability": 0.8671875 }, { "start": 5557.47, "end": 5557.71, "word": " room", "probability": 0.8330078125 }, { "start": 5557.71, "end": 5557.87, "word": " for", "probability": 0.8974609375 }, { "start": 5557.87, "end": 5557.99, "word": " the", "probability": 0.8115234375 }, { "start": 5557.99, "end": 5558.27, "word": " workshops", "probability": 0.6259765625 } ] }, { "id": 1737, "seek": 536718, "start": 5558.27, "end": 5560.37, "text": " or are we just going to use this", "tokens": [ 51064, 420, 366, 321, 445, 516, 281, 764, 341, 51164 ], "temperature": 0.0, "avg_logprob": -0.17316366470966144, "compression_ratio": 1.5502645502645502, "no_speech_prob": 0.2364501953125, "words": [ { "start": 5558.27, "end": 5558.91, "word": " or", "probability": 0.55908203125 }, { "start": 5558.91, "end": 5559.21, "word": " are", "probability": 0.88232421875 }, { "start": 5559.21, "end": 5559.31, "word": " we", "probability": 0.90283203125 }, { "start": 5559.31, "end": 5559.43, "word": " just", "probability": 0.884765625 }, { "start": 5559.43, "end": 5559.63, "word": " going", "probability": 0.8583984375 }, { "start": 5559.63, "end": 5559.83, "word": " to", "probability": 0.90869140625 }, { "start": 5559.83, "end": 5560.09, "word": " use", "probability": 0.82666015625 }, { "start": 5560.09, "end": 5560.37, "word": " this", "probability": 0.86474609375 } ] }, { "id": 1738, "seek": 536718, "start": 5560.37, "end": 5560.75, "text": " Discord?", "tokens": [ 51164, 32623, 30, 51264 ], "temperature": 0.0, "avg_logprob": -0.17316366470966144, "compression_ratio": 1.5502645502645502, "no_speech_prob": 0.2364501953125, "words": [ { "start": 5560.37, "end": 5560.71, "word": " Discord", "probability": 0.28173828125 }, { "start": 5560.71, "end": 5560.75, "word": "?", "probability": 0.77294921875 } ] }, { "id": 1739, "seek": 536718, "start": 5561.57, "end": 5564.31, "text": " Nope, there is a separate room for", "tokens": [ 51264, 12172, 11, 456, 307, 257, 4994, 1808, 337, 51364 ], "temperature": 0.0, "avg_logprob": -0.17316366470966144, "compression_ratio": 1.5502645502645502, "no_speech_prob": 0.2364501953125, "words": [ { "start": 5561.57, "end": 5562.13, "word": " Nope", "probability": 0.515625 }, { "start": 5562.13, "end": 5562.25, "word": ",", "probability": 0.6318359375 }, { "start": 5562.25, "end": 5562.43, "word": " there", "probability": 0.85009765625 }, { "start": 5562.43, "end": 5562.71, "word": " is", "probability": 0.89892578125 }, { "start": 5562.97, "end": 5563.51, "word": " a separate", "probability": 0.8603515625 }, { "start": 5563.51, "end": 5563.97, "word": " room", "probability": 0.83154296875 }, { "start": 5563.97, "end": 5564.31, "word": " for", "probability": 0.8955078125 } ] }, { "id": 1740, "seek": 536718, "start": 5564.31, "end": 5565.59, "text": " the workshops here. Let me", "tokens": [ 51364, 264, 19162, 510, 13, 961, 385, 51464 ], "temperature": 0.0, "avg_logprob": -0.17316366470966144, "compression_ratio": 1.5502645502645502, "no_speech_prob": 0.2364501953125, "words": [ { "start": 5564.31, "end": 5564.55, "word": " the", "probability": 0.8154296875 }, { "start": 5564.55, "end": 5564.95, "word": " workshops", "probability": 0.599609375 }, { "start": 5564.95, "end": 5565.23, "word": " here", "probability": 0.763671875 }, { "start": 5565.23, "end": 5565.31, "word": ".", "probability": 0.80810546875 }, { "start": 5565.31, "end": 5565.41, "word": " Let", "probability": 0.87548828125 }, { "start": 5565.41, "end": 5565.59, "word": " me", "probability": 0.9013671875 } ] }, { "id": 1741, "seek": 536718, "start": 5566.23, "end": 5569.01, "text": " post that in Twitch.", "tokens": [ 51464, 2183, 300, 294, 22222, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.17316366470966144, "compression_ratio": 1.5502645502645502, "no_speech_prob": 0.2364501953125, "words": [ { "start": 5566.23, "end": 5566.79, "word": " post", "probability": 0.79541015625 }, { "start": 5566.79, "end": 5567.11, "word": " that", "probability": 0.8857421875 }, { "start": 5567.11, "end": 5567.61, "word": " in", "probability": 0.876953125 }, { "start": 5567.61, "end": 5568.45, "word": " Twitch", "probability": 0.86962890625 }, { "start": 5568.45, "end": 5569.01, "word": ".", "probability": 0.9208984375 } ] }, { "id": 1742, "seek": 539554, "start": 5571.43, "end": 5571.91, "text": " Um...", "tokens": [ 50364, 3301, 485, 50464 ], "temperature": 0.0, "avg_logprob": -0.1968149058520794, "compression_ratio": 1.5227272727272727, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5571.43, "end": 5571.91, "word": " Um...", "probability": 0.09027099609375 } ] }, { "id": 1743, "seek": 539554, "start": 5573.19, "end": 5575.09, "text": " There you go, folks. If you have any", "tokens": [ 50564, 821, 291, 352, 11, 4024, 13, 759, 291, 362, 604, 50664 ], "temperature": 0.0, "avg_logprob": -0.1968149058520794, "compression_ratio": 1.5227272727272727, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5573.19, "end": 5573.67, "word": " There", "probability": 0.619140625 }, { "start": 5573.67, "end": 5573.77, "word": " you", "probability": 0.89208984375 }, { "start": 5573.77, "end": 5573.95, "word": " go", "probability": 0.9033203125 }, { "start": 5573.95, "end": 5573.99, "word": ",", "probability": 0.634765625 }, { "start": 5573.99, "end": 5574.21, "word": " folks", "probability": 0.8564453125 }, { "start": 5574.21, "end": 5574.35, "word": ".", "probability": 0.85693359375 }, { "start": 5574.35, "end": 5574.53, "word": " If", "probability": 0.89599609375 }, { "start": 5574.53, "end": 5574.69, "word": " you", "probability": 0.8984375 }, { "start": 5574.69, "end": 5574.87, "word": " have", "probability": 0.87890625 }, { "start": 5574.87, "end": 5575.09, "word": " any", "probability": 0.81201171875 } ] }, { "id": 1744, "seek": 539554, "start": 5575.09, "end": 5577.11, "text": " other questions or want to continue talking", "tokens": [ 50664, 661, 1651, 420, 528, 281, 2354, 1417, 50764 ], "temperature": 0.0, "avg_logprob": -0.1968149058520794, "compression_ratio": 1.5227272727272727, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5575.09, "end": 5575.33, "word": " other", "probability": 0.79150390625 }, { "start": 5575.33, "end": 5575.85, "word": " questions", "probability": 0.90869140625 }, { "start": 5575.85, "end": 5576.11, "word": " or", "probability": 0.7841796875 }, { "start": 5576.11, "end": 5576.31, "word": " want", "probability": 0.6259765625 }, { "start": 5576.31, "end": 5576.41, "word": " to", "probability": 0.90625 }, { "start": 5576.41, "end": 5576.75, "word": " continue", "probability": 0.818359375 }, { "start": 5576.75, "end": 5577.11, "word": " talking", "probability": 0.787109375 } ] }, { "id": 1745, "seek": 539554, "start": 5577.11, "end": 5578.99, "text": " about this workshop, you can find us", "tokens": [ 50764, 466, 341, 13541, 11, 291, 393, 915, 505, 50864 ], "temperature": 0.0, "avg_logprob": -0.1968149058520794, "compression_ratio": 1.5227272727272727, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5577.11, "end": 5577.37, "word": " about", "probability": 0.81494140625 }, { "start": 5577.37, "end": 5577.61, "word": " this", "probability": 0.88720703125 }, { "start": 5577.61, "end": 5578.05, "word": " workshop", "probability": 0.67626953125 }, { "start": 5578.05, "end": 5578.15, "word": ",", "probability": 0.90234375 }, { "start": 5578.15, "end": 5578.25, "word": " you", "probability": 0.8857421875 }, { "start": 5578.25, "end": 5578.41, "word": " can", "probability": 0.9013671875 }, { "start": 5578.41, "end": 5578.69, "word": " find", "probability": 0.8271484375 }, { "start": 5578.69, "end": 5578.99, "word": " us", "probability": 0.90478515625 } ] }, { "id": 1746, "seek": 539554, "start": 5578.99, "end": 5581.13, "text": " at that channel", "tokens": [ 50864, 412, 300, 2269, 50964 ], "temperature": 0.0, "avg_logprob": -0.1968149058520794, "compression_ratio": 1.5227272727272727, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5578.99, "end": 5579.35, "word": " at", "probability": 0.900390625 }, { "start": 5579.35, "end": 5580.05, "word": " that", "probability": 0.767578125 }, { "start": 5580.05, "end": 5581.13, "word": " channel", "probability": 0.71337890625 } ] }, { "id": 1747, "seek": 539554, "start": 5581.13, "end": 5582.99, "text": " in the AI Village", "tokens": [ 50964, 294, 264, 7318, 22651, 51064 ], "temperature": 0.0, "avg_logprob": -0.1968149058520794, "compression_ratio": 1.5227272727272727, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5581.13, "end": 5582.03, "word": " in", "probability": 0.1748046875 }, { "start": 5582.03, "end": 5582.27, "word": " the", "probability": 0.7861328125 }, { "start": 5582.27, "end": 5582.57, "word": " AI", "probability": 0.7890625 }, { "start": 5582.57, "end": 5582.99, "word": " Village", "probability": 0.455078125 } ] }, { "id": 1748, "seek": 539554, "start": 5582.99, "end": 5585.17, "text": " in the DC Discord.", "tokens": [ 51064, 294, 264, 9114, 32623, 13, 51164 ], "temperature": 0.0, "avg_logprob": -0.1968149058520794, "compression_ratio": 1.5227272727272727, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5582.99, "end": 5583.49, "word": " in", "probability": 0.7685546875 }, { "start": 5583.49, "end": 5583.69, "word": " the", "probability": 0.81201171875 }, { "start": 5583.69, "end": 5584.15, "word": " DC", "probability": 0.88623046875 }, { "start": 5584.15, "end": 5584.69, "word": " Discord", "probability": 0.72314453125 }, { "start": 5584.69, "end": 5585.17, "word": ".", "probability": 0.9921875 } ] }, { "id": 1749, "seek": 539554, "start": 5586.07, "end": 5587.03, "text": " Perfect.", "tokens": [ 51164, 10246, 13, 51264 ], "temperature": 0.0, "avg_logprob": -0.1968149058520794, "compression_ratio": 1.5227272727272727, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5586.07, "end": 5586.55, "word": " Perfect", "probability": 0.4638671875 }, { "start": 5586.55, "end": 5587.03, "word": ".", "probability": 0.8935546875 } ] }, { "id": 1750, "seek": 539554, "start": 5587.67, "end": 5588.89, "text": " And then I'm going to go ahead", "tokens": [ 51264, 400, 550, 286, 478, 516, 281, 352, 2286, 51364 ], "temperature": 0.0, "avg_logprob": -0.1968149058520794, "compression_ratio": 1.5227272727272727, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5587.67, "end": 5587.93, "word": " And", "probability": 0.630859375 }, { "start": 5587.93, "end": 5588.09, "word": " then", "probability": 0.595703125 }, { "start": 5588.09, "end": 5588.29, "word": " I'm", "probability": 0.963134765625 }, { "start": 5588.29, "end": 5588.35, "word": " going", "probability": 0.48681640625 }, { "start": 5588.35, "end": 5588.37, "word": " to", "probability": 0.90478515625 }, { "start": 5588.37, "end": 5588.49, "word": " go", "probability": 0.8994140625 }, { "start": 5588.49, "end": 5588.89, "word": " ahead", "probability": 0.83984375 } ] }, { "id": 1751, "seek": 539554, "start": 5588.89, "end": 5591.01, "text": " and end the stream. I'm going to hop into", "tokens": [ 51364, 293, 917, 264, 4309, 13, 286, 478, 516, 281, 3818, 666, 51464 ], "temperature": 0.0, "avg_logprob": -0.1968149058520794, "compression_ratio": 1.5227272727272727, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5588.89, "end": 5589.37, "word": " and", "probability": 0.89111328125 }, { "start": 5589.37, "end": 5589.71, "word": " end", "probability": 0.83056640625 }, { "start": 5589.71, "end": 5589.93, "word": " the", "probability": 0.55859375 }, { "start": 5589.93, "end": 5590.23, "word": " stream", "probability": 0.87646484375 }, { "start": 5590.23, "end": 5590.37, "word": ".", "probability": 0.921875 }, { "start": 5590.37, "end": 5590.51, "word": " I'm", "probability": 0.995849609375 }, { "start": 5590.51, "end": 5590.55, "word": " going", "probability": 0.7998046875 }, { "start": 5590.55, "end": 5590.65, "word": " to", "probability": 0.9111328125 }, { "start": 5590.65, "end": 5590.85, "word": " hop", "probability": 0.89404296875 }, { "start": 5590.85, "end": 5591.01, "word": " into", "probability": 0.74072265625 } ] }, { "id": 1752, "seek": 539554, "start": 5591.01, "end": 5593.69, "text": " that channel and I will see you guys there.", "tokens": [ 51464, 300, 2269, 293, 286, 486, 536, 291, 1074, 456, 13, 51564 ], "temperature": 0.0, "avg_logprob": -0.1968149058520794, "compression_ratio": 1.5227272727272727, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5591.01, "end": 5591.25, "word": " that", "probability": 0.88232421875 }, { "start": 5591.25, "end": 5591.59, "word": " channel", "probability": 0.79248046875 }, { "start": 5591.59, "end": 5592.07, "word": " and", "probability": 0.40966796875 }, { "start": 5592.07, "end": 5592.29, "word": " I", "probability": 0.99609375 }, { "start": 5592.29, "end": 5592.43, "word": " will", "probability": 0.80908203125 }, { "start": 5592.43, "end": 5592.61, "word": " see", "probability": 0.818359375 }, { "start": 5592.61, "end": 5592.73, "word": " you", "probability": 0.896484375 }, { "start": 5592.73, "end": 5592.91, "word": " guys", "probability": 0.8828125 }, { "start": 5592.91, "end": 5593.21, "word": " there", "probability": 0.853515625 }, { "start": 5593.21, "end": 5593.69, "word": ".", "probability": 0.99267578125 } ] }, { "id": 1753, "seek": 539554, "start": 5595.11, "end": 5597.37, "text": " Thanks a lot, Gavin. Absolutely.", "tokens": [ 51664, 2561, 257, 688, 11, 24020, 13, 7021, 13, 51764 ], "temperature": 0.0, "avg_logprob": -0.1968149058520794, "compression_ratio": 1.5227272727272727, "no_speech_prob": 0.07806396484375, "words": [ { "start": 5595.11, "end": 5595.59, "word": " Thanks", "probability": 0.53857421875 }, { "start": 5595.71, "end": 5595.77, "word": " a lot", "probability": 0.90234375 }, { "start": 5595.77, "end": 5595.81, "word": ",", "probability": 0.9794921875 }, { "start": 5595.81, "end": 5595.97, "word": " Gavin", "probability": 0.7333984375 }, { "start": 5595.97, "end": 5596.31, "word": ".", "probability": 0.98291015625 }, { "start": 5596.49, "end": 5596.97, "word": " Absolutely", "probability": 0.74755859375 }, { "start": 5596.97, "end": 5597.37, "word": ".", "probability": 0.7890625 } ] }, { "id": 1754, "seek": 539918, "start": 5597.37, "end": 5598.23, "text": " Thank you.", "tokens": [ 50364, 1044, 291, 13, 50464 ], "temperature": 0.0, "avg_logprob": -0.062215166787306465, "compression_ratio": 0.5555555555555556, "no_speech_prob": 0.0196075439453125, "words": [ { "start": 5597.37, "end": 5597.65, "word": " Thank", "probability": 0.83740234375 }, { "start": 5597.65, "end": 5597.79, "word": " you", "probability": 0.89501953125 }, { "start": 5597.79, "end": 5598.23, "word": ".", "probability": 0.94287109375 } ] } ], "text": " Are we ready to go? We are. Perfect. Hello and welcome to Machine Learning for Security Analysts. This is our first workshop here at the AI village, DEF CON Safe Mode. So the goal here is to kind of take machine learning out of the buzzword and into the mainstream. So buzzwords like machine learning and AI have been in the industry for a couple of years now, but for most people, it's not really well understood what these actually mean. So my goal is to kind of introduce you to machine learning, and we're going to do this by kind of going over what machine learning is, how it fits in the broader concept of AI, and why it's important for security analysts and hackers to understand machine learning, as well as what the machine learning process looks like. And then we're going to take all of that and put that into building our first machine learning model, which will be something very familiar. So let's go ahead and get started. So who am I? My name is Gavin. I go by the pseudonym GT Klondike. I'm an independent security researcher and a security consultant. I have a passion for network security, both attack and defense. And so through that passion, I run a project called NetSec Explained, which is a blog and a YouTube channel where I use intermediate and advanced-level concepts and try to explain them in a very easy-to-understand way. So it's usually at this point where, in person, I would kind of ask the audience, when you hear the word machine learning, what comes to mind? Some of the common answers that I get are, oh, you need to have a PhD in multivariable calculus and linear algebra, or Skynet's going to take over the world, or pattern matching. So these are all pretty interesting answers, but what we're going to walk through in this workshop is kind of show you that not all of that is necessary. You don't need a PhD in multivariable calculus or linear algebra, especially with some of the abstraction libraries like Scikit-learn, Keras, TensorFlow, and things like that. And then as far as machines taking over the world, not quite. So machine learning and how it fits in the broader idea of artificial intelligence. So artificial intelligence is this big umbrella term that kind of is a catch-all for different types of ways that machines operate. So back in the past, when they first invented digital calculators, they thought that was machine intelligence or artificial intelligence. And then it came to video game AI. Today we also see things like rules-based artificial intelligence, or classic image recognition. So there's a bunch of different artificial intelligence technologies that aren't necessarily machine learning. Machine learning itself is more about applied statistics, and a merge between what used to be considered business intelligence, and statisticians would do this job, and computer science. With the improvement of computing resources such as memory and CPU, a lot more power can be put behind some of these algorithms. And then deep learning is specifically talking about deep neural networks. Neural networks are a type of machine learning algorithm, and then deep learning allows us to stack layers on top of these. So deep learning, usually these are referred to for convolutional neural networks, which are used for image recognition, primarily. And then recurrent neural networks, which are used for cyclical pattern recognition, such as heartbeat monitors. But if we were to find all of this, I would say machine learning is a set of statistical techniques that enables the process of information mining, pattern discovery, and drawing inferences from data. The idea is that machines learn from the data, instead of us having to program signatures, or heuristics, or invent new algorithms for different problems. For example, deep learning, we have convolutional neural networks where deciding between whether something is a bike or a bus is the exact same algorithm and exact same problem as deciding whether or not something is a tiger or a cheetah. So a couple examples, especially in the security space, we have the ability to classify domain generation algorithms. These are primarily used by botnets as a way for the bot herder to stay in contact with their networks. Web application firewalls, these we will usually see with being able to perform some anomaly detection and see, okay, this is what normal user traffic looks like compared to abnormal user traffic. So in this case, the machine learning algorithm identified a potential SQL injection in the parameter because it's very abnormal from what it's used to seeing. And then, of course, network anomaly detection. This is one of the big ones, especially in the security side, the defender side of things, where we can predict what we think the network traffic will look like over a period of time and then compare that to what the actual is. Once it's beyond a certain delta, then that's something that we should pass off to a human to kind of dig in a little deeper and kind of figure out what's going on. So why is this important? Well, today we have over a quarter of security products that are used for detection that use some form of machine learning. And we see machine learning being applied to more and more things every day. We see facial recognition, we see advanced spam filtering, data heuristics and persona collection. And so in order for security analysts to properly deploy and manage these machine learning products, they need to have a better understanding of how they operate so that they can ensure that they work efficiently. So the machine learning process, it follows seven steps. This is not a step one, step two, step three, but this is really a cycle. So you start at step one, you go all the way down to step seven, and then you hop back up to step one. So you start off with gathering the data. So first you want to identify if I'm going to build a network anomaly detection system, if I'm going to build some sort of hacking tool. I need to gather data that applies to that, and then I need to prepare the data. So I can't just take raw information, I need to look at things like metadata and pre-process that. This step is also known as pre-processing. We need to choose the model, and the model is going to depend... There are some heuristics. Some models work better for different problem sets, but generally we're going to try a couple different models and see what works best. We're going to train the model, we're going to evaluate the model, and then if we think that the model can perform a little bit better than it's actually performing right now, we can do what's called hyperparameter tuning. And so this lets us make little tweaks here and there. And then of course we deploy it. And as I said earlier, this is a bit of a cyclical process, because machine learning algorithms stop learning as soon as you stop training them. And so you want to continue to gather new data and train new models and build them into newer and better generations. So before we get started, what we're going to do is hop in and learn how to build a basic spam filter. Spam filters are fantastic first examples, especially for a lot of the newbies, because we already know how spam filters work. If it says something that looks spammy, like buy Viagra now, then that's going to be automatically thrown away into our spam filter. If we have something that seems legitimate, then that's going to be passed on to the user. So before we get into that, are there any questions on any of the stuff that I've gone over so far? Okay. One more thing. I totally forgot this, but this is a bit of a story that really... Yes. Okay. This is a story that really made things click for me. So a friend of mine, this was a few years ago, was approached by a non-profit organization. And what this non-profit does is they have cameras set up all over Africa and they take pictures to see if there's a cheetah. And they're tracking cheetah population. So they'll take pictures, it'll get sent off to a human analyst, and the human will look at it and say, okay, is there a cheetah in the picture or not? And so they approached my friend and they said, hey, is there a way that we can improve this process? What's something that we can do here? And so he said, okay, let me try a couple things. So what he did was use a very common image library and said, okay, let's train a machine learning algorithm to identify images, if there's a cheetah in the picture or not. If it reached above a 5% confidence, says, okay, I'm 5% confident or 6% confident that there's a cheetah in this image, it got sent over to an analyst. If it was less than 5% confident, it would just throw it away. Now, 5%, that doesn't really sound like a lot, and it's not. But the ROI of what this model was able to do is pretty astounding. So what normally would have taken them a year of labor to perform, they were able to do in one month. That is a 1,200% increase in productivity. So that's pretty powerful. And that's just a very simple model. So as we can develop more and more advanced things, these are ways that we can really improve our processes to move at machine speed and scale. GT? Yeah. We have a question, and it's, any links to information pertaining to creating your own models rather than training existing ones? Creating your own models rather than training existing ones? Yeah. I think that you're going to be showing them how to create their own model. We are going to create our own model. So there are existing models that you can use, what's called transfer learning. So you take a problem, for example, ImageNet, which is a challenge. It can recognize hundreds of different categories of images, and you can take that idea, train your own model so that it can recognize whether or not there's a cheetah in an image. But what we're going to do is actually build a model from scratch. There's no previously trained information, and I'm going to walk you through how to do that, and we're going to see a workbook in a little bit. Thank you. Hopefully that helps answer the question. Okay. So before we get started, machine learning, it uses statistics, and so what we need to do is grab information and turn them into numbers. But if we wanted to have the idea of a spam email versus a regular email or a ham email, we need to kind of understand how we're going to interpret words into numbers. So here's a couple sentences that refer to sports and not sports, or realistically, elections. So we see a great game, and that talks about sports. And then we see the election was over, and that talks about not sports. So the idea is how do we take a sentence that we haven't seen before, because that's what machine learning is supposed to do. We were trained on certain information, but we want to predict on information that we haven't seen before. How do we take a new sentence and then try and make a decision whether or not it's talking about sports or not sports? So to do that, we're going to use what's called Bayes' theorem. Bayes' theorem is a very common probability theorem that basically says, okay, so if we have a sentence that we already know, and given the probability that this sentence is talking about sports, versus here's a new sentence, what is the probability that it's talking about sports given that new sentence? So the probability of A given B equals probability of B given A, blah, blah, blah. We don't need to know too much about this, but it's important to get a good foundation of this understanding. So the idea is, what is the probability that the sentence, a very close game, is talking about sports? We don't know the answer to that. We've never come across the sentence of a very close game, but we would need to fill it into this algorithm here. So instead, what we can do is actually break up a very close game into their individual words, a, very, close, and game. And then we can turn that probability into, what's the probability that A is talking about sports? What's the probability that very is talking about sports? What's the probability of close talking about sports, and game talking about sports? So this winds up becoming a bit of a counting game. How many times do we see A, and it's talking about sports? Twice. And of course we need to do the same thing for not sports, because we need to find the probability of A happening, the probability of B happening, and we take whichever is higher. So the probability that A is talking about sports, we see it twice in two of our sentences, or twice across all of our sports sentences. Got to be precise. We don't see A in not sports at all, so that's going to be zero across all of our not sports sentences. Very shows up in sports once, does not show up in not sports. Close shows up in not sports once, does not show up in sports, and then game shows up in sports twice, and it doesn't show up in not sports. So we take those numbers and we plug them in. We saw for sports, A showed up twice, Very showed up once, Close didn't show up at all, and Game showed up twice. And then if we count the number of words that we have across all of the sports sentences, we have a total of 11. So it just becomes a simple 2 divided by 11, 1 divided by 11, and so on. But we can't use straight, naive Bayesian. And the reason why is because we have these zeros. Now, close is a word that we've never seen in sports, so we get zero, and that winds up being zero divided by 11, which is zero. Zero times everything is zero, and so unfortunately the probability of this sentence being about sports, if we just use straight Bayesian, is zero. So that doesn't really work for us. So instead, what we're going to use is called multinomial naive Bayesian. It's a very similar formula, but we have what's called a smoothing filter, and that's this alpha. We can set this alpha to whatever we want. Usually we just set it to 1. But we can modify that, and this will be a hyperparameter that we'll take a look at later in our workbook. So with the smoothing filter, we do the exact same word counting. We see A showed up twice in sports. Very showed up once in sports. Close, zero. Game showed up twice in sports. And then we do the same thing for not sports. But you see here where it says close for sports? That smoothing filter makes it so that that number never becomes zero. It's always greater than zero. So our probabilities will always fit. And then this is just simple addition and then division. And if we took out a calculator, did all our math, we can see that AVeryCloseGame has a probability of .0000461 that it's talking about sports. And then AVeryCloseGame has a probability of 0000143 that it's talking about not sports. So we take whichever is higher, in this case sports, and so our classifier has decided that AVeryCloseGame is talking about sports. So I know that was a lot of information. Let me know if there's any questions. I'm going to kind of hop forward a little bit, but TAs, feel free to chime in if there's any questions on this. I know this bit's a little confusing sometimes, but it's not something we need to harp on too much. It's just an underlying foundation that's good to know. So the five things that we need to keep track of in order to do our pen and pencil math that we did earlier, is we need to keep track of the total number of unique words, the total number of words in spam, the total number of words in ham, and these two were what we've put in the denominator. The count of each word in spam and the count of each word in ham. So this is where we had to count the word A, count the word very, count close, count game. And so these are the five things that we need to pay attention to. Are there any questions so far? It looks like we're clear on questions right now. Awesome. Okay, so how do we take this idea and expand it to a full email? Well, here's a spam email. Yeah, no, this is not a spam email. This is a regular email. And we're going to use this as a common example throughout the rest of our workbook. So in this example email, we have re, re, East Asian fonts in Lenny. Thanks for your support. Installing Unifonts did it well for me. Now, we could take this entire email and look at it, but there are some things that we want to probably remove, things that don't really make a lot of sense, especially in the English language. So punctuation, punctuation doesn't really make sense. It doesn't add any context to a sentence. Small words, which are called stop words, such as in, of, on, for, the, they also don't add any context. So we can just go ahead and remove that, and that'll reduce the amount of words that we're looking at in this email, because we want to look at keywords. Things like unsubscribe and unsubscribed, or thanks, or thank you. They mean the same thing. A really good example, especially in English, is congrats and congratulations. They mean the same thing. And if we want to narrow this down to keywords, we should do what's called stemming. And so what stemming does is it shortens the word down so that you have I thanked somebody today, as in past tense, thank-ed, thanks, thank with an S, and thank you, where it's just plain thank. We want to count those all as the same word. And then, of course, we want to set everything to lowercase, because capital words such as unsubscribe, all caps, is the exact same as unsubscribe, lowercase. So this is our preprocessing step. And what we did was we removed all the stop words. We removed re, in, for, your, did, it, for. And then we're going to stem the words. I didn't show the stemming in here, and we'll see in the workbook as we go along what the stemming actually looks like. But we can see that we kind of shrunk the email a little bit, and this is going to be a little easier for us to compare emails to each other. So I think this is the point where we can go ahead and open up our workbook. So I'm going to escape out of there, open this up. So for our workshops, we're going to do this for this workshop and for the other workshops. We're going to use a system called MyBender. MyBender is fantastic. It uses Jupyter notebooks in a Docker container. So I'm going to go ahead and copy this and send it off into Discord somehow. Actually, is there a way... I'm going to kind of hide my screen for a second. Yeah, just post it to me, and I'll put it in all the places for you. Yeah, absolutely. Okay. All right, perfect. Got it. Display capture. I'm still getting used to OBS and Twitch streaming. I haven't done this before, but I'm really excited. So MyBender, once you get the link, you can just grab that link, paste it in here, or you can click launch, and you can do this with any GitHub repository. So this is going to launch some Jupyter notebooks. It takes about a minute or two to spin up. So I'm going to let you guys get that link from the TA, from the workshops channel, and then I'll let this spin up for me. I'll wait a little bit longer so that it spins up for you, and then we can get moving. While this is happening, are there any questions? Feel free to just write them in the channel, and the TAs will relay them. And once yours spins up the way that I have this laid out, go into the workbooks directory. If you would like to follow along in the live coding session, we're going to use the workbook spam filter sklearn document. If you are not that familiar with Python, and you just want to follow along, you can go ahead and use the completed workbook. I would give it just another couple of minutes to make sure theirs are spun up. Yes, absolutely. Absolutely. So I just want to check something real quick on my other screen. And these workbooks outside of this workshop, you can play with them on your own. I have a couple others if you want to take a look. But yeah, for the purpose of this workshop, we're going to be using the spam filter sklearn, or the completed spam filter sklearn. Okay. So I'm going to go ahead and start. The first couple things that I'm going to go over are just next, next, next run. If you're still waiting for your instance to spin up, don't feel bad. You'll be able to catch up very quickly. So I'm going to go ahead and open up my spam filter sklearn. And in this one, we are going to use scikit-learn, which is a wonderful abstraction library. Great for beginners. So we're going to go ahead and install a couple tools. So for these blocks, in order to run them, you can click on them and press shift enter, or you can press run button up here. You can see that it's running all the Python code. In this one, I'm just installing the libraries and I am configuring the data directory where all of our spam and our ham emails will be located. So that's going to take a little bit while that is going. Just kind of a quick overview of this first block. We have our imports. So in this case, we're going to use matplotlib. Matplotlib is going to let us print some nice graphs. NumPy and Pandas is going to let us grab some of the information that we need. We're going to use a couple of the others as some support libraries. For example, OS, we're going to use that later to kind of grab all of the files. We want to use NLTK. NLTK stands for Natural Language Toolkit. And so this will allow us to identify our stop words and perform our stemming functions. From scikit-learn, we're going to use a train-test split. The way that you typically want to train a machine learning model is you have a bunch of clean labeled data and you're going to take probably about 80 or 70% of that and use it to train the model. But then you want to see how well the model is doing. So you're going to use the other 20 or 30% as your testing and you're going to use this as evaluation. It's kind of the same way we teach students in elementary school. Here's the bulk of the information and now we're going to test you to see how well you understand it. And then our TF-IDF and count vectorizers, we will get into that in a bit. These are going to be used for transforming our words into numbers that we can work with. And then the two models that we're actually going to build out are going to be the multinomial Naive Bayesian, which we went over in the slides, and then one that is completely unfamiliar, logistic regression. And this is to show how incredible machine learning can be where you can just swap out algorithms. So we can use SVM, random forest, neural networks, things of that nature without massively changing the way that our data is represented. And then to kind of represent how our models are doing, we're going to use Seaborn as a graphic representation, and we're going to use a confusion matrix and a classification report to identify exactly where our model is doing well, where it's not doing well, and how mild changes are going to affect it. So I'm going to go ahead, shift-enter, run that. And that's just going to do the import, and we'll see libraries imported. And then here's our test email from the slides. This is the East Asian fonts in Lenny. We're going to see every step of the way how this email is manipulated and transformed into workable data for our machine learning models. So I'm going to hit shift-enter and run that. TAs, are there any questions so far? Is everybody able to get their stuff set up? No questions so far. Looks like everything is going well. Perfect. So the tokenizer, this is the first step where we want to define a function that will pre-process our information. So, as we saw in the slides, we want to make everything lowercase, we want to remove the stop words, and we want to stem the words. So this function is already defined for you, but we can see that we grab all the punctuation, we grab all the stop words using nl2k, and then we define the porter stemmer, which is going to stem our words. And then we're going to create a list of tokens by taking all of our words, setting them to lowercase, and using the word tokenizer, which will just take a sentence, split it up by its individual words, we're going to strip out the punctuations, and then we are going to merge everything together. So we're going to go ahead and run that. It's going to define our function, and we're going to hop into our first task. So our first task is really easy. It's just print the full test email, and then we're going to print the tokenized version of the test email. So in Python we can just do print test email, and then we can do print tokenizer test email. And then shift-enter, going to go ahead and run that. So we see the original email, East Asian fonts in Leni. Then we can see the stop words have been removed. So we're looking at East Asian font Leni. Thanks has been turned into thank. Support install. Install is missing an L because we see installing. You have I installed something, or I am going to install something. And so we're going to stem that so that all of those words are counted the same. We see unsubscribe. Unsubscribe shows up twice. And then we see list.debian.org, which also shows up twice. So this is the way that our tokenizer modifies the email as we're going through. And again, just for those that are trying to catch up, all we did was print the test email and then print the tokenizer version of the test email. There's a question from Twitch chat. So why are we assuming the punctuation is not relevant? In our case, we're looking at spam emails. And so the punctuation, you'll look at commas, hyphens, question marks. And so in the context, if we're looking at keywords, the punctuation doesn't really matter. So if you see buy a Viagra now, period, it doesn't make any difference between buy Viagra now, exclamation point, or buy Viagra now with a question mark at the end. So in the context of the sentence, that one sentence would likely be classified as spam because it's talking about Viagra and it's very unlikely. That's a very common spam word we'll see in a lot of spam messages. So punctuation is just not relevant because it doesn't add any context to the message. And so that's something that we can remove. If you would like, you can follow through on this workbook and then try it without removing the punctuation and see if you notice any differences. But I don't think there would be any differences just because of that context. There are better things to weigh than periods, question marks, commas, things of that nature. And then as you see, emails or websites, such as lists.debian.org, they still have their punctuation because that's not the word lists, debian, and org. That is a URL, lists.debian.org. And so that's kind of the difference there. If we had hyphenated words, we would see them included in here as well. So we're going to go on and load the training data. This one is just going to give us the counts that we need. This is just done for you. Remember, one of those five things that we needed to keep track was all of the word counts in the ham emails, all the word counts in the spam emails. But what this is going to do is count the number of emails that we have in ham, count the number of emails that we have in spam, and then count the total number of emails that we have in our testing set. So for here, our testing and training split is already defined. It's 80-20, and so we'll see that in a moment. And we go ahead and hop into our second task, which is to load the training data. So task two, it asks us to create two lists, and we're going to have corpus. And it's important to get these words identical because of how we use them later on. So we're going to have a list called corpus. We're going to have a list called labels. And then the next bit is we want to load each of the email bodies from the data directory slash ham and data directory slash spam into the corpus array. So what we're going to do is for each in os.listdir, data.dir, this was defined above, slash ham. And then we're going to say with each open file, ham slash plus each, because that's what we defined in our for loop. We're going to read them as a file named f, corpus.append, f.read, and then labels.append the word ham. And the reason why is because this third task is load the labels for each email into the labels array. So in this first code block, we're going to read every single ham email in the ham directory. We're going to add the bodies to the corpus array, and then we're going to add the label ham into the labels array. Then we can go ahead and do the exact same thing for spam. We're just going to have to change each thing to spam, spam, and the labels to spam. And this will go through and read all of the emails. So I'm going to leave this up for a moment, let you guys copy that down. And then I'm going to press shift enter and run it. So this was really quick, just read all the ham emails, all the spam emails, and now it's loaded into our arrays. If we want to get an idea of what our class count looks like, we have a total of 2,359 ham emails, 1,100 spam emails, and then just as a graph we can see here. And I think it's important to graph these counts because sometimes you will have what are considered unbalanced data sets, and so you need to perform other changes here and there just to make sure that the data sets are balanced. Especially for things like credit card fraud, where that happens less than a percent of the time. You can build a model that's 99% accurate by just saying everything is a legitimate transaction, but unfortunately that doesn't really help when you're trying to stop credit card fraud. So when you have imbalanced data sets, there's additional things that you do. In this case, it looks a little unbalanced, but we'll be able to work with it no problems. So we are on task 2A. In this one we want to see the full text body of a random email in our corpus array, and then we want to see the tokenized result of that same email. So this is going to be very similar to what we did for task 1, which was printing out the test email, and then printing out the tokenized version of the test email. So we'll just go ahead and grab a random email. So email equals corpus. Actually, let me go ahead and do this. Let's have email ID equals just the number 5. Why not? And then we're going to grab email ID. So this is going to be our random email. We're going to... probably going to print a... No, I already have a divider in there. Cool. So let's just print that email. And then, same thing, we're going to do print tokenizer, and then that same email. So this line and this line is exactly the same that we did in task 1. This is the only thing that changes so that we grab a random email. And then you don't have to put 5, you can put any number, but I'm just picking 5. So go ahead, Shift-Enter. And this one's pretty nice. So we see the body of the email, product review, virttools, dev, URL, product review, virttool, dev, 2.0 URL. We see the full path for the URL here. Let's see if there's anything interesting. Maybe features, feature is shortened to feature, because you can say featured in a motion picture with an ed at the end, features as they have here, or we will feature with just an e at the end. So this is the way that our tokenizer operates, but we still need to turn these words into numbers, and this is where our vectorizers come in. So our vectorizers, we're going to use two kinds of vectorizer. We're going to use the count vectorizer, which just takes the straight word count. It's exactly what we did in the slides. Then we're going to use a TF-IDF vectorizer that applies a mathematical weight to each of the words. And they work slightly different, but let's go ahead and define them, and we'll show you what the difference looks like. So we're going to name this CVEC as our count vectorizer. Count vectorizer, and the capitalizations are important. Then we're going to use our tokenizer function above as our tokenizer function here. So we're going to have tokenizer equals tokenizer. Awesome. And then we want to vectorize our words, so this is going to be saved as countX. So we're going to have count underscore capital X equals... Oops, did not mean to open that. CVEC, our vectorizer, and then we're going to use fit transform. Fit is Scikit-learn's way of saying train. So in this instance, we're going to train our vectorizer. So fit transform, and then our purpose, which is just our list of words. And then we're going to do the same thing for our TF-IDF vectorizer. So we're going to take TVEC equals TF-IDF. Vectorizer and capitalization is important. Tokenizer equals tokenizer. And then our TF-IDF X capital X equals TVEC dot fit transform corpus. Cool. So I'm going to let that sit there for a second while you guys are typing in. And then I'm going to go ahead and run it. So this takes about a minute because what it's doing is it is counting all of the words across all of the emails, the ham emails and the spam emails. And so as it's counting each of these words, it's applying a word count for the count vectorizer, and then it applies a weight for the TF-IDF vectorizer. And the weight takes all the words into account. So it becomes a whole process. But this takes about 60 to 120 seconds. So we'll go ahead and let that run. While that's running, we're just going to get started on task 3A, which is just to print each token from the test email. Now this one can be a little tricky. So there's a bit of a trick to identify the unique words and the counts. So what we're going to do is create a list of dictionary keys. So what that's going to look like is for i in list dict from keys. Tokenized email was defined above, and what that is is the tokenized version of our test email. So we're going to go ahead and print. I'm just using the Python format. Tokenized email dot count of each word, and then the word in the tokenized email. So I'm going to verify vectorizing is complete. And I'm going to let you guys run your vectorizers, let that sit for a little bit. And then we're going to run this, because we need... Oh, I don't believe we do need the previous one to run this. So if your vectorizer is still going, your code here will not run right away, but it will run as soon as the vectorizer completes. So I'm going to go ahead and run mine. So shift-enter, and tokenizer email is not correct. I think it's tokenized email, that makes a little bit more sense. I'm going to run that. Tokenized email is not defined. Okay, give me a second. I'm going to scroll up to our tokenizer. I guess I don't have that defined. Where is that? Ah, I was supposed to save it up above. That's okay. So we'll go ahead and create it here. Tokenized email equals tokenizer test email. So we're going to go ahead and save that. And here we have the word counts of our test email. We see the familiar East Asian font, Lenny. We know unsubscribe showed up twice, and we know list.debian.org showed up twice. Everything else in here only showed up once. I know I went very quickly, but this was the line that I needed to add. Tokenized email equals tokenizer test email. And then we grab the list of the dictionary from that list of the tokenized email, and we print out the word counts. So going on to 3b, what we want to see is, okay, we know what the word count looks like if we just did a straight word count. How does the count vectorizer and the tf.idf vectorizer transform our test email as we're going through? So we're going to go ahead and use our example CVEC. And the reason why we're using a separate example version is because we want to redefine a count vectorizer. Don't forget our tokenizer equals tokenizer. And then we're going to have our exampleX using our exampleCVEC.fitTransform. And then it expects a list. Our test email is a simple string, so we're going to have to wrap it in these brackets so that it becomes a list. And then we're going to have our test email. Cool. And then we're going to go ahead and print our example email. Oops. ExampleX. And then here, we're going to do the same thing. We're going to have exampleTVEC equals tf.idf vectorizer. Capitals are important. Tokenizer equals tokenizer. And then our example, tf.idf. I'll just call it exampleX because it doesn't matter. Once we print out our original exampleX, we don't need it anymore. ExampleTVEC.fitTransform. And then the brackets, test email. And then we can print our exampleX. So I'm going to let that sit for a moment. Let you guys copy that down. I'm going to just look ahead real quick. We are doing great. Okay. So I'm going to go ahead and run this now. I pressed Shift-Enter. And if we look at our count vectorizer of test email, we see these different numbers. And what these numbers represent are tokens. So, for example, a very nice game. A would be token 1. Very would be token 2. Nice would be token 3. Game would be token 4. So in this case, Scikit-Learn actually knows the best way that it wants to tokenize things. So the letters, for example, 0, this does not necessarily represent East. And so, basically, Scikit-Learn knows how these tokens are used. We don't know how these tokens are used. But something that we can point out is we see token 16 shows up twice and token 9 shows up twice. So based on what we saw up above, we can guarantee that either token 16 or token 9 is unsubscribe. And then the other one is list.debian.org. And so these show up twice. So this is exactly the same as if we had done the word count ourselves. The TF-IDF vectorizer, however, uses a bit of a weight algorithm. And so everything that was set as 1 has this 0.204 weight. The 2, which is token 9 and token 16, have this 0.408 weight. And this doesn't necessarily happen in every instance. But in this instance, you can see the 0.408 shows up twice as much as the 0.204 exactly. And so this is the way that count vectorizer operates and TF-IDF vectorizer operates. The underlying, what happens underneath the hood, we don't really need to worry about. We just need to know how these work and the differences between the two. So moving on, we're going to load the testing data. This is already written for us. So we're just going to grab the first 10 files in the testing directory and print those out. So we see we just have all these test emails. And at the end of the file name, we have the label that it's supposed to belong to. So we have ham, ham, spam, spam, spam, ham. And so what we're going to do is read each of these emails. And then we're going to pull off the last little bit of the file name and use that as our label. And we want to have the testing separate from the training so that we can evaluate how well our model is doing. So we're going to load the testing data. And this one's a little complicated, so we have a couple tasks to run through. So we're going to create two list arrays, kind of like we did earlier. We're going to have test corpus, and we're going to set that as an empty list. And we're going to have test labels, which is also going to be an empty list. And then we are going to load all of the emails from the test directory. So we're going to say, for filename in os.listdir, our data directory, plus test, which is where it's located, with each file that is open. And we need to tell it which file test plus filename are. For read, as filenamed f, we are going to do test corpus.append, f.read. And then we are going to do something a little weird here, so bear with me. I'm just going to use re.split, just to split this up. I'm looking for txt. And then we're just going to grab the last bit in that split. So this is going to split the file trainemail.txt. So it's going to split it to this section, and then to this section. So this would be considered index 0, and this last little bit would be considered index 1, which is why we have this 1 here at the end. And then we're going to append the labels. So test.labels.appendLabel And so I'm going to give you guys a little bit to go ahead and get this all written up. Be careful, there is a backslash before this period, because this is a regular expression. And everything should be good. So I'm just going to let that sit for a little bit, let you guys do your thing. In the meantime, I'm just going to look ahead real quick. The rest of this gets so much easier. It's pretty crazy how easy it gets. In the meantime, TAs, are there any questions in the chat? We appear to be good so far. Awesome. So I'm going to go ahead and move on. I'm going to press Shift-Enter. It's going to load all of those emails. So this is just reading all of the test emails into our corpus array and grabbing those labels and putting them into the end of our test labels array. And then just like last time, what this is going to do is print out the number of test emails. We have 590 ham emails, 276 spam emails. And here's just a nice pretty graph representing what that looks like. And as I said earlier, this information or this data has already been split up in an 80-20 split. So 80% of it is being used for our training and then 20% of it is being used for our testing. And then this one, it might sound complicated, but this is actually really easy. We have already trained our CVEC and our TVEC. And now all we need to do is collect our testing values. We need to tokenize our testing values using these already trained vectorizers. So this is super easy. testCountX equals CVEC.transformTestCorpus. And that's it. That's all we've got to do for that. We can just copy and paste here. Say our testTFIDFX is our TVEC.transformTestCorpus. The reason this works is if you remember in the slides how we had the sentences that we already knew about, and then we had to perform a counting game for a very close game. We had to count how many times a showed up in the sentences that we were already aware of, how many times very showed up, how many times close showed up, how many times game showed up. So this transform allows us to do just that. So what this will do is grab each email and it will say, okay, here's the tokenized words of the email that I have. How many times does it show up in the count vectorizer? And then what is the weight that it shows up in the TFIDF vectorizer? So I'm going to go ahead, Shift-Enter, run that. And just like last time, this is going to take a little bit. It's counting all the words and associating them with the different tokens. This is going to be significantly faster than training it. See, it's almost done already. And so we're going to go ahead and move on. So this bit, we're going to get ready to test and evaluate our models. So this is just a helper function that's going to show us a bunch of really neat statistics. The details of this helper function you can look into on your own. But for now, what we need to use as an input is our confusion matrix, our score, and our classification report. So we're just going to go ahead, Shift-Enter, run that. Definition defined. And then here's where we get into tasks 6a, 6b, 6c, and 6d, which is going to be us training and evaluating our different models. So we're going to start with multinomial Naive Bayesian with a TF-IDF vectorizer, with a count vectorizer, and then we're going to do the same for logistic regression with TF-IDF and logistic regression with a count vectorizer. So we're going to start out just one thing at a time. We're going to define our constructor. So this is going to be MNB TF-IDF equals multinomial NB. Watch your capitalization. We're going to define that, and then we're going to train it. MNB TF-IDF dot fit, which is train in scikit-learn world. And we're going to use our TF-IDF X, which is our preprocessed information, and then we're going to compare it to our labels. So that's going to train our model. Now we're going to grab a couple really neat statistics. So the first one we're going to get is our score, and this wants us to call it score. Score MNB TF-IDF predictions using our predict function. We're going to develop a confusion matrix called C matrix, MNB TF-IDF, and then classification report, C report, MNB TF-IDF. So we're going to start with our score. Score MNB TF-IDF equals MNB TF-IDF dot score. And then we're going to use our test values, because we've trained it on our training data, and we want to test it with our testing. So we're going to do test TF-IDF X, because that's the way that our system was vectorizing these. So we don't want to use count vectorizer with a TF-IDF train, because that's not going to work. And then we're going to use test labels. That's going to give us our score. So we're going to get our predictions. Predictions MNB TF-IDF equals MNB TF-IDF dot predict. And this is going to give us our raw predictions. This is going to tell us what it thinks each email is, whereas our score is going to see how accurate it is. And then this is going to be C matrix. MNB TF-IDF equals confusion matrix. We're going to use our test labels and our predictions. MNB TF-IDF. So this is going to tell us what it thinks the value is, if it's a spam or ham email, and then what it actually is. So it's going to give us our true positives, our false positives, our true negatives, and our false negatives. And then the C report. We're not going to do too much with this, but what a classification report will do is show us some more metrics, such as the recall and the precision, which we don't need to worry about too much. We're just going to focus on the accuracy for now. But for data science, it's important to know what the recall and the precision are as we go through things. Report, test labels, and then we're going to use our predictions again. And this is just like our C matrix MNB TF-IDF, in the order that we put things. We have test labels, test labels, predictions, predictions. And that is it. And then we're going to use our helper function generate report. So I know that's a lot of typing. I'm going to go ahead and sit here as you guys kind of follow through. So we have our MNB TF-IDF constructor. We are going to train it using the fit function. We're going to train it on our testing data, which is stored as TF-IDFX, and our testing labels, which is just stored as labels. We are going to use score, MNB TF-IDF.score, to evaluate our accuracy. We're going to use our predictions to get the raw predictions. And then with the raw predictions, we are going to develop a confusion matrix and a classification report, which will tell us how well our model is doing visually. So I'm going to let that sit for one more minute. TA, are there any questions? No, I think... well, hang on, let me go back one here. Nope, still got it. So I think we're good. Awesome. Awesome. Fantastic. So I am going to go ahead and move on. I'm going to press Shift-Enter. It's going to run. And now we have our... up here at the top is our classification report. And so what this is going to do is show us our precision and our recall. We don't need to worry too much about this one. Instead, I want you to focus on the lower chart. So here we have an accuracy of 87.5%. We can see that all of the actual ham emails were predicted as ham. So these are our true positives. A little more than half of our spam emails were correctly predicted as spam. So these are our true negatives. And then, unfortunately, it misclassified... Oh, my mistake. I have that backwards. So it says 108 of our ham emails it thinks are spam emails, whereas all of the spam emails, so the actual spam emails, were correctly classified as spam. And then all of our ham emails, what it thought were ham emails, were ham. So we're going to go ahead and do the same thing for 6b, 6c, and 6d. One of the beautiful things, and I'm going to show you this just as a super quick and easy way of going about and doing things, is I'm just going to copy the code that I'd already written. This is why machine learning is awesome, and very different from programming normal algorithms, is all we need to do is just change these tf.ids to count, and then everything else is the same. So we use mnbcount to define our multinomial Naive Bayesian, as we have been asked of us here in 6b. mnbcount.fit, and we're going to use our countX because that's how it's been vectorized. We're going to change our score mnbcount using mnbcount.score. We're going to change our tf.idsx to testCountX, and then likewise kind of all throughout here. TestLabels is going to stay the same, predictions is going to change because it is no longer predictions.tf.ids, it is predictionsCount, and then we have our confusion matrix and our classification report. So just to go over it one more time, we define our multinomial Naive Bayesian constructor, we train it using the fit function and the count vectorizer, our testing data, our training data. We develop our score off of our testCount data using our testLabels, and then we have our predictions, we have our confusion matrix, and our classification report. So I'm going to let this sit for just a little bit as you guys go through and copy that down. What's really cool is in the GitHub repository, there are other workbooks. So for example, we use the exact same methodology to build a malicious URL predictor, so things that look like it's possibly part of a botnet. All of this code is exactly the same. Once we vectorize our information, we just copy and paste this code in, and it does the exact same thing. And so that's the benefit of machine learning, is it learns from the data itself instead of us having to manually program, okay, this solves problem A, but now we have to rewrite this to solve problem B. It just all does the same thing. So I am going to go ahead and move on. I'm going to press Shift-Enter. And we see that we got a little bit better, right? We are at a 94% accuracy. It thinks that some of our ham emails are still spam, but significantly less. We went from 108 down to 23, but now it thinks that some of our spam emails are actually ham. And so that's a problem. So we have a few more emails going through our filter than we would like, but we have significantly fewer of our ham emails from being blocked. GT, we've got a question from Twitch chat. Absolutely. So Chris... I'm not going to try and pronounce the name. Did you intentionally avoid having spam emails classified as ham when you created the model, or is it simply a try and error kind of thing when training the model? Intentionally avoid having spam emails classified as ham? Is that what they said? Yeah. Yeah, we wouldn't want spam emails to be classified as ham. We want to draw a line and separate so that you stop getting emails about Viagra and you start getting the regular emails from your school or your work. And so this is just kind of the way that spam filters operate. So we could build a model that would classify more spam emails as being part of ham or regular emails, or we can build a model that says, okay, we want absolutely zero spam emails. If we wind up losing regular emails and classifying those as spam as a mistake, we're okay with that. A really good example, actually I'm glad you brought this up, is antivirus. So the way that antivirus companies work is they can err on the side of, oh, I think this is a virus, therefore it must be a virus, or this could be benign, or I kind of think this is a virus, but instead of blocking it, I'm just going to let it go through. And so you think about the way that malware works. You have malware that will make calls out to the internet, it'll probably take over your webcam, it'll try and write files, it'll probably take over your microphone. What else does that? Chrome, IE, Firefox, browsers. And so the idea is instead of blocking what could be legitimate applications, and so that would really interrupt the user experience, they kind of err on the side of, we don't want to block the user experience because then you'll uninstall the antivirus. So they are more willing to let viruses go through than blocking legitimate applications. And so in this case, these are trade-offs that we have to make as data scientists of if we are okay with letting a few spam emails through versus blocking all of our regular emails. So he's specifically asking about task 6A. So if you scroll up a little bit. Task 6A? Yeah, I think the answer is a bit of that and a bit of the question of when you build these models, the training process literally punishes the model for getting it wrong every single time. And in this case... Yeah, so Chris, you're asking about a false negative. A false negative is when you've got something that's malicious, that's misclassified as benign, which is what the point of the model is, but what GT brought up is probably more important is when you have something that's benign that you classify as malicious, that is much more common because you get more benign things on users' devices, as GT brought up. So in this case, I don't think this was intentional. No, this wasn't intentional. This is just the way that the model learned. And then as we go through the other models, you'll see how these shift. Yeah, but this is honestly the way it looks like. You've got the ham stuff that are classified as spam is very low so that all the user experience isn't impacted that badly. And the spam stuff that's classified as ham is relatively high, but you've got a trade-off between the false positives and the false negatives. Yeah, exactly. And I hope that answered your question, Christopher. I think going through the other models will kind of help answer it a little bit more too. So accuracy, 87%. 87.5%. 94.3%. In this one, we're going to use a model that we haven't used before, logistic regression. And so with Scikit-learn, it's very easy. It's the exact same thing. The difference is we need to use a LBFGS solver. So what that's going to look like is LGSTFIDF equals logistic regression. Then we're going to set our solver LBFGS. And this is just a thing with logistic regression specifically. We saw in the slides that multinomial naivetation has a variable called alpha. We can tweak that. That's one of our hyperparameters. This is considered a hyperparameter. It's the way that logistic regression interprets the information. But for this case, we're just going to use LBFGS. We're going to do the same thing. We're going to fit LGSTFIDF dot fit TFIDFX and then it enables. Let me just hop down here. We're going to do score equals LG S TFIDF equals LGSTFIDF dot score testTFIDFX Pay attention to your capitals. Test labels. Then we're going to do predictions shuns LGSTFIDF equals LGSTFIDF dot predict and then our test data Typing TFIDF so much it's very confusing for my hands. T matrix we're going to use our confusion matrix test labels and predictions LGSTFIDF and then our C report LGSTFIDF equals location report test labels predictions TFIDF That should be good. Just checking for errors. That looks right. So, go ahead copy this down. I will sit and wait for a bit, but you'll notice a lot of similarities to the multinomial Naive Bayesian. In fact, we could have just copied and pasted and just changed it from LGS to MNB or from MNB to LGS and then change our constructor to be a logistic regression with the LBFGS solver. We have our logistic regression constructor. We train it using the fit function using our TFIDF vectorized data and our labels. We use our test data and our test labels to generate a score and to generate predictions. And then, off of those predictions, we generate a confusion matrix and a classification report. And then, of course, our nice little helper function at the bottom that's going to print us out some helpful stats. So, I'm just going to let this sit for a little bit longer. Kometh, did Chris ask any more questions, follow-up, or did we take care of them? A bunch of people piled on and I helped answer the question because of what he asked. Honestly, one of the most important things is the false positive versus false negative trade-off. Yeah. Yeah, a lot of people have strong opinions about that because it's a lot of... It's important. It's definitely important, especially in data science. This, I'm... That might have been a good talk. So, here's the interesting thing, is when I first started out, this I thought was amazing. Now, as I've learned more over time, I kind of feel like, oh, no, this is a little clunky and a little ham-fisted. I'm ignoring this, I'm ignoring this, I'm ignoring this, I'm ignoring this. But this is a great way for beginners to understand machine learning. And then from there, you can kind of hop into a little bit more of the data science considerations, like imbalanced data sets, true positives, false positives, and some of those trade-offs, as well as more hyperparameter tuning. If you want to look at a malware, you keep bringing it up, you can look at the Google Endgame Ember. I'll drop a link in the Twitch chat in a sec. But there's a malware model that you can look into, like the open-source code, and the final thing at the end of that is it sets the false-positive rate to 0.05% or 0.5% at the end, because that's what you should do in production, because customers care more about false positives, because false positives lead to alert fatigue, and alert fatigue leads to just ignoring every single alert, and then all the false negatives get through anyway. All the true negatives get through anyway. It is something... Yeah, and even that model is a little clunky and hampers. Well, and it kind of leads to with the alert fatigue, it kind of leads to the common thing that we hear, especially in the technical community from non-technical people, of why does my thing not work? Okay. So that kind of helps address it. But yeah, these are all data science considerations. So I'm going to go ahead and run this. Shift-Enter. And this is going to take a little bit longer than the multinomial Naive Bayesian, because logistic regression interprets the data a little differently, and so it needs to go through and kind of count things properly. This takes, I think, about 30 seconds? Yeah, it's not too bad. It's 30 to 60 seconds. So I'm just going to go ahead and run this. And then for the logistic regression count, we're going to do the same thing we did with the multinomial Naive Bayesian count and just copy and change words because I'm lazy. But yeah, I'm really excited to see that Twitch chat after I hop off to this workshop and see just how passionate people are about the false positive, true positive, and XYZ. Oh, we're going to erase it before you get off. Ruin my day. Yeah, it's taking a little bit longer than I'm used to. But that's okay. While this is going, I'm just going to go ahead and hop into the next bit and paste this. All we need to do is trade this TF-IDF with COUNT. So I'm going to go ahead and copy that. We're going to use the same constructor and the same solver. We're going to use COUNTEX. We're going to use COUNTFIT. COUNTCOUNT COUNTCOUNT COUNTCOUNT Test labels is the same. These are predictions. And just one quick look over. Yep, I have everything in. That's exactly how it's supposed to be. Scroll up. Oh, this is still going. Look at that. Weird. I'm going to let that sit for a bit then. So this one, I'm going to let you guys write down. This is task 6D. So go ahead and make sure that you have these written down while the other one is still going. I'm going to run this and then take a look at a logistic regression with the TF-IDF. We're actually doing really good on time. We have one more task after this. It is going to be the most challenging task. But it is going to take everything from A to Z and show us what we learned. So I just want to check one last time. And that is still going. So I'm going to go ahead and run this. This was 6D that I just clicked to run. It says the kernel is idle. That's not good. Let me see if I can pause this. Let me just interrupt it. Interrupt the kernel. So I'm going to run this because that took a second. Uh oh, I hope I didn't time out. That would be very bad. Let's try and run it again. Yeah, that's not good. Restart and clear output. So this is going to go all the way to the beginning. Let's see if I can get this to run. Okay, so that runs now. So I ran into a bit of a technical difficulty. Instead of going through and filling everything out, I'm just going to quickly grab the completed workbook. And I'm going to just go ahead, run all. This is going to run everything for me. So while I'm waiting for some of this stuff to run, let's see that packages are being downloaded, tokenization is defined, everything's good, everything's good, everything's good. Where is it stuck now? It is stuck... Looks like it's stuck reading the data. Training spam, training ham. That one's done, done. Yeah, when you see numbers here, that means that that was the order it was ran in. When you see a star, that means that it's still running. I'm not sure why the logistic regression was causing problems, but let's take a quick look at... Oh. Looks like there's some stuff missing. Well, that's unfortunate. So I'm just going to go ahead and create new code blocks. I'm just going to copy the code we had from task 6D and 6C. I apologize for scrolling so fast. So let's go ahead and grab all of that, paste it in, run it. Logistic regression is not defined. That's weird. Oh, it's not even in here. That is something I'm going to have to fix. I'm not sure... Oh. Because that's a whole different workbook. I need complete spam filter sklearn. That's the one that I need. My mistake. So kernel, restart, run all. So this is going to run all of them. Let's see where it gets stuck. Prints out the emails. It's training the vectorizers. I remember that took about a minute or so. But what we want to see after task 6D, we'll look at 6C and 6D, is at the end of this, what we're going to do is grab a spam email. This one is actually one that I grabbed directly from my spam box last year. And I like it because we can use our spam email predictor to identify whether or not it's spam. And then we can look and utilize any of the models to really identify that. So this was supposed to be a fill-in-the-blank kind of thing like we've been going through. But this last task, it just asks us use the vectorizers and the models created to perform predictions on the test email that we created up at the top and the test spam email which is the real world email that I pulled from a spam inbox. And so what we want to do is grab that as a working email. And this will let us change this to test email and test spam email. Remember, we want to use the tf.idf and the count vectorizers in order to use the working email. We need to use that to preprocess and because it's a string, we just wrap it in these square brackets in order to classify it as a list because the transform function expects a list. We have that as test email, tf.idf, and test email count. And then we use each of our models to form a prediction. So we have the multinomial Naive Bayesian with tf.idf, multinomial with count, logistic regression tf.idf, and logistic regression with count. They all use the same predict function. They're all using either the tf.idf vectorized version of the email or the count vectorized version of the email based on whether or not it's the tf.idf or the count version of the model. And then we make our predictions, we print the email itself, and then we can print what each model thinks it is. So if you're still on the fill in the blank bit, I encourage you to fill this out. If you are using the completed workbook, like I am, it's already filled out and we're just going to go ahead and let everything else run in the background until we get to this point. So, sorry about that. In the meantime, are there any questions, any thoughts, concerns, ideas? I'd love to hear from you. All right. Psychdude says, on the completed workbook 6a, show the top right and bottom left numbers swapped in 6a. Wait a second. But the one you were working on earlier had those flipped. The fill in the blank and the completed, were they different somehow? Yeah, so I'm thinking the reason why they're swapped is because there was a way that Scikit-learn documented how they did their confusion matrix versus how they actually did their confusion matrix, and it was swapped from what you would normally see. And so, following what you would normally see is what I did, and that's where the mistake came in. And I can actually show you that. I was hoping nobody noticed, but good eye. So if you look at 6, actually before we go there, let's take a look and see the count. So we have 590 ham emails in our test dataset, 276 spam emails in our test dataset. And so if we look at 6A, we see 590 ham emails, but as far as actual label, we should see in the column for spam a total of the 276. We don't see that. And the reason why is because this is supposed to be the actual, see 108 plus 168 is 276, and then this was supposed to be the predicted. The problem is the way that scikit-learn swapped them, and I guess I did not swap them back. To get the correct result, you just need to switch the test labels and the predictions MNB on both sides for the confusion matrix and the classification report. So, yeah. That's why they seem swapped. The one on the completed workbook is correct, because I believe the completed workbook shows in the actual label column the spam emails, and if you total the two numbers, you get 276. So, good eye on that. Go ahead and check this. Perfect. Before we ran into the problems, we're going to look at 6C and 6D with a logistic regression. Remember, we had 0.85 or 0.87 0.5% accuracy for the TF-IDF multinomial Naive Bayesian. For the count multinomial Naive Bayesian, we have 0.94. For the logistic regression, we get a little bit better. We're at 0.959 as our accuracy. We have fewer ham emails being classified as spam and fewer spam emails being classified as ham. We're getting better. With the task 6D, this is logistic regression with count vectorizer. This is going to be our best model at 0.976. Here we only have 8 of the ham emails being classified as spam and 12 of the spam emails being classified as ham. Of the four models that we trained, this is the better one in terms of accuracy. This is why we want to try different algorithms, different machine learning algorithms, as well as different ways that we preprocess or vectorize our data. That way we can create different models, see which ones perform the best, and then we can gravitate towards that one. As far as the test spam email, this is a brand new email. It comes in on our email server. We want to use our models to classify it. Let's go ahead and make a prediction. As I went over earlier, we're going to have our test spam email, which is called working email, so we can swap this out pretty seamlessly. We're going to use our vectorizers that we already defined to transform our working email. And then of course, being a string, we need to put it in a list. That's what the square brackets are for. Then we use all four of our models, the multinomial and the logistic regression with the tf and the count vectorizers. We use the predict function on the vectorized emails. And then we just go ahead and print out the working email itself. Your latest issue is available now. If you don't want issue notifications, click here to unsubscribe. And then we print out the values that are predicted from each of our models. If we look at it, we're going to see something interesting. Our best performing model, which is the logistic regression with the count vectorizer, correctly classified this as a spam email. But our worst performing model, even though it still had an 87.5% accuracy, our multinomial Naive Bayesian with tf.idf incorrectly classified this as a ham email. And so this is also why we want to try building different models and get things that predict much better. Let me know if there's any questions on that. We are short on time. We're actually running a little over, but before I let you go, there's one more thing I want to show you. And that is the hyperparameter tuning. So if we jump up to that worst performing model, that 0.85%, the multinomial with tf.idf, sorry, 0.875%. And we use that alpha that we saw in our formulas on the slides. Alpha is set to 1. We can go ahead and run that. And we see that we're at 0.875. But what if we shrink that alpha to 0.1? This is hyperparameter tuning. We can change it. Now our accuracy changed from one of the worst models that we have to one of the better models that we have. In fact, this is second place. So we have 0.965% accuracy. And so you can see how hyperparameter tuning can really help out in tweaking the way that our models operate. Before I let you go, here's some references for more information. And if you want the slides to this and more information from me and the GitHub project that this is all part of, check out github.com.netsec explain and you can shoot me an email with any questions, thoughts, comments at gtklondike at gmail.com So that's all I have for you guys. If there's any discussion, TAs, do we have a separate room for the workshops or are we just going to use this Discord? Nope, there is a separate room for the workshops here. Let me post that in Twitch. Um... There you go, folks. If you have any other questions or want to continue talking about this workshop, you can find us at that channel in the AI Village in the DC Discord. Perfect. And then I'm going to go ahead and end the stream. I'm going to hop into that channel and I will see you guys there. Thanks a lot, Gavin. Absolutely. Thank you." }