word-sub / tests /expected /corner_cases /accurate.tiny_apollo11.mp3.words.json
RaeesRSB's picture
Upload 185 files
2cba4ca
{
"text": " I'm all around my business and we got a recommendation for you on your door to the VA We have 18A's Okay, okay, I think I'll just get him or if they like just want to go on the Yeah, now what you want is on having a B1 And you just get the other one on my Now when we're here, we're going to go on the Yeah Okay, we want to hear that This is it, we know we just You can hit that That's how much you've ordered in that So I guess I'm working on my position but it's not Oh my god Okay, no problem No idea No idea Okay Okay",
"segments": [
{
"id": 0,
"seek": 0,
"start": 0.6,
"end": 5.36,
"text": " I'm all around my business and we got a recommendation for you on your door to the VA",
"tokens": [
50364,
286,
478,
439,
926,
452,
1606,
293,
321,
658,
257,
11879,
337,
291,
322,
428,
2853,
281,
264,
18527,
50628
],
"temperature": 0.0,
"avg_logprob": -1.1827944879946501,
"compression_ratio": 1.52020202020202,
"no_speech_prob": 0.35403239727020264,
"confidence": 0.324,
"words": [
{
"text": "I'm",
"start": 0.6,
"end": 0.82,
"confidence": 0.168
},
{
"text": "all",
"start": 0.82,
"end": 1.06,
"confidence": 0.082
},
{
"text": "around",
"start": 1.06,
"end": 1.28,
"confidence": 0.104
},
{
"text": "my",
"start": 1.28,
"end": 1.46,
"confidence": 0.128
},
{
"text": "business",
"start": 1.46,
"end": 1.72,
"confidence": 0.342
},
{
"text": "and",
"start": 1.72,
"end": 1.92,
"confidence": 0.613
},
{
"text": "we",
"start": 1.92,
"end": 1.98,
"confidence": 0.937
},
{
"text": "got",
"start": 1.98,
"end": 2.18,
"confidence": 0.4
},
{
"text": "a",
"start": 2.18,
"end": 2.4,
"confidence": 0.639
},
{
"text": "recommendation",
"start": 2.4,
"end": 3.06,
"confidence": 0.599
},
{
"text": "for",
"start": 3.06,
"end": 3.5,
"confidence": 0.371
},
{
"text": "you",
"start": 3.5,
"end": 3.68,
"confidence": 0.974
},
{
"text": "on",
"start": 3.68,
"end": 3.88,
"confidence": 0.805
},
{
"text": "your",
"start": 3.88,
"end": 4.24,
"confidence": 0.562
},
{
"text": "door",
"start": 4.24,
"end": 4.68,
"confidence": 0.145
},
{
"text": "to",
"start": 4.68,
"end": 4.88,
"confidence": 0.182
},
{
"text": "the",
"start": 4.88,
"end": 5.08,
"confidence": 0.501
},
{
"text": "VA",
"start": 5.08,
"end": 5.36,
"confidence": 0.249
}
]
},
{
"id": 1,
"seek": 0,
"start": 5.36,
"end": 6.94,
"text": " We have 18A's",
"tokens": [
50628,
492,
362,
2443,
32,
311,
50714
],
"temperature": 0.0,
"avg_logprob": -1.1827944879946501,
"compression_ratio": 1.52020202020202,
"no_speech_prob": 0.35403239727020264,
"confidence": 0.175,
"words": [
{
"text": "We",
"start": 5.36,
"end": 5.74,
"confidence": 0.042
},
{
"text": "have",
"start": 5.74,
"end": 5.76,
"confidence": 0.652
},
{
"text": "18A's",
"start": 5.76,
"end": 6.94,
"confidence": 0.182
}
]
},
{
"id": 2,
"seek": 0,
"start": 12.0,
"end": 16.79,
"text": " Okay, okay, I think I'll just get him or if they like just want to go on the",
"tokens": [
50914,
1033,
11,
1392,
11,
286,
519,
286,
603,
445,
483,
796,
420,
498,
436,
411,
445,
528,
281,
352,
322,
264,
51197
],
"temperature": 0.0,
"avg_logprob": -1.1827944879946501,
"compression_ratio": 1.52020202020202,
"no_speech_prob": 0.35403239727020264,
"confidence": 0.327,
"words": [
{
"text": "Okay,",
"start": 12.0,
"end": 12.38,
"confidence": 0.662
},
{
"text": "okay,",
"start": 12.88,
"end": 13.12,
"confidence": 0.291
},
{
"text": "I",
"start": 13.12,
"end": 13.3,
"confidence": 0.209
},
{
"text": "think",
"start": 13.3,
"end": 13.58,
"confidence": 0.263
},
{
"text": "I'll",
"start": 13.58,
"end": 13.9,
"confidence": 0.2
},
{
"text": "just",
"start": 13.9,
"end": 14.1,
"confidence": 0.17
},
{
"text": "get",
"start": 14.1,
"end": 14.28,
"confidence": 0.248
},
{
"text": "him",
"start": 14.28,
"end": 14.52,
"confidence": 0.153
},
{
"text": "or",
"start": 14.52,
"end": 14.74,
"confidence": 0.199
},
{
"text": "if",
"start": 14.74,
"end": 14.94,
"confidence": 0.088
},
{
"text": "they",
"start": 14.94,
"end": 15.44,
"confidence": 0.607
},
{
"text": "like",
"start": 15.44,
"end": 15.74,
"confidence": 0.2
},
{
"text": "just",
"start": 15.74,
"end": 15.96,
"confidence": 0.462
},
{
"text": "want",
"start": 15.96,
"end": 16.18,
"confidence": 0.765
},
{
"text": "to",
"start": 16.18,
"end": 16.36,
"confidence": 0.91
},
{
"text": "go",
"start": 16.36,
"end": 16.56,
"confidence": 0.948
},
{
"text": "on",
"start": 16.56,
"end": 16.7,
"confidence": 0.566
},
{
"text": "the",
"start": 16.7,
"end": 16.79,
"confidence": 0.585
}
]
},
{
"id": 3,
"seek": 0,
"start": 16.79,
"end": 19.0,
"text": " Yeah, now what you want is on having a B1",
"tokens": [
51197,
865,
11,
586,
437,
291,
528,
307,
322,
1419,
257,
363,
16,
51322
],
"temperature": 0.0,
"avg_logprob": -1.1827944879946501,
"compression_ratio": 1.52020202020202,
"no_speech_prob": 0.35403239727020264,
"confidence": 0.471,
"words": [
{
"text": "Yeah,",
"start": 16.79,
"end": 17.1,
"confidence": 0.28
},
{
"text": "now",
"start": 17.18,
"end": 17.3,
"confidence": 0.365
},
{
"text": "what",
"start": 17.3,
"end": 17.48,
"confidence": 0.743
},
{
"text": "you",
"start": 17.48,
"end": 17.62,
"confidence": 0.932
},
{
"text": "want",
"start": 17.62,
"end": 17.84,
"confidence": 0.743
},
{
"text": "is",
"start": 17.84,
"end": 17.96,
"confidence": 0.674
},
{
"text": "on",
"start": 17.96,
"end": 18.16,
"confidence": 0.327
},
{
"text": "having",
"start": 18.16,
"end": 18.44,
"confidence": 0.563
},
{
"text": "a",
"start": 18.44,
"end": 18.76,
"confidence": 0.287
},
{
"text": "B1",
"start": 18.76,
"end": 19.0,
"confidence": 0.37
}
]
},
{
"id": 4,
"seek": 0,
"start": 19.0,
"end": 21.88,
"text": " And you just get the other one on my",
"tokens": [
51322,
400,
291,
445,
483,
264,
661,
472,
322,
452,
51462
],
"temperature": 0.0,
"avg_logprob": -1.1827944879946501,
"compression_ratio": 1.52020202020202,
"no_speech_prob": 0.35403239727020264,
"confidence": 0.516,
"words": [
{
"text": "And",
"start": 19.0,
"end": 20.26,
"confidence": 0.272
},
{
"text": "you",
"start": 20.26,
"end": 20.4,
"confidence": 0.846
},
{
"text": "just",
"start": 20.4,
"end": 20.64,
"confidence": 0.694
},
{
"text": "get",
"start": 20.64,
"end": 20.8,
"confidence": 0.134
},
{
"text": "the",
"start": 20.8,
"end": 20.9,
"confidence": 0.65
},
{
"text": "other",
"start": 20.9,
"end": 21.08,
"confidence": 0.937
},
{
"text": "one",
"start": 21.08,
"end": 21.26,
"confidence": 0.976
},
{
"text": "on",
"start": 21.26,
"end": 21.66,
"confidence": 0.872
},
{
"text": "my",
"start": 21.66,
"end": 21.88,
"confidence": 0.232
}
]
},
{
"id": 5,
"seek": 0,
"start": 22.12,
"end": 25.36,
"text": " Now when we're here, we're going to go on the",
"tokens": [
51462,
823,
562,
321,
434,
510,
11,
321,
434,
516,
281,
352,
322,
264,
51616
],
"temperature": 0.0,
"avg_logprob": -1.1827944879946501,
"compression_ratio": 1.52020202020202,
"no_speech_prob": 0.35403239727020264,
"confidence": 0.336,
"words": [
{
"text": "Now",
"start": 22.12,
"end": 22.8,
"confidence": 0.168
},
{
"text": "when",
"start": 22.8,
"end": 23.04,
"confidence": 0.35
},
{
"text": "we're",
"start": 23.04,
"end": 23.24,
"confidence": 0.745
},
{
"text": "here,",
"start": 23.24,
"end": 23.44,
"confidence": 0.492
},
{
"text": "we're",
"start": 23.66,
"end": 23.88,
"confidence": 0.293
},
{
"text": "going",
"start": 23.88,
"end": 23.94,
"confidence": 0.291
},
{
"text": "to",
"start": 23.94,
"end": 24.38,
"confidence": 0.88
},
{
"text": "go",
"start": 24.38,
"end": 24.72,
"confidence": 0.119
},
{
"text": "on",
"start": 24.72,
"end": 25.34,
"confidence": 0.133
},
{
"text": "the",
"start": 25.34,
"end": 25.36,
"confidence": 0.364
}
]
},
{
"id": 6,
"seek": 3000,
"start": 31.36,
"end": 31.56,
"text": " Yeah",
"tokens": [
50364,
865,
50464
],
"temperature": 0.0,
"avg_logprob": -1.6116297245025635,
"compression_ratio": 0.3333333333333333,
"no_speech_prob": 0.29405874013900757,
"confidence": 0.057,
"words": [
{
"text": "Yeah",
"start": 31.36,
"end": 31.56,
"confidence": 0.057
}
]
},
{
"id": 7,
"seek": 6000,
"start": 62.7,
"end": 64.14,
"text": " Okay, we want to hear that",
"tokens": [
50364,
1033,
11,
321,
528,
281,
1568,
300,
50564
],
"temperature": 0.0,
"avg_logprob": -0.9387273416890727,
"compression_ratio": 1.4172185430463575,
"no_speech_prob": 0.10345567017793655,
"confidence": 0.355,
"words": [
{
"text": "Okay,",
"start": 62.7,
"end": 62.72,
"confidence": 0.125
},
{
"text": "we",
"start": 63.1,
"end": 63.32,
"confidence": 0.238
},
{
"text": "want",
"start": 63.32,
"end": 63.62,
"confidence": 0.529
},
{
"text": "to",
"start": 63.62,
"end": 63.72,
"confidence": 0.571
},
{
"text": "hear",
"start": 63.72,
"end": 63.84,
"confidence": 0.245
},
{
"text": "that",
"start": 63.84,
"end": 64.14,
"confidence": 0.92
}
]
},
{
"id": 8,
"seek": 6000,
"start": 64.46,
"end": 66.82,
"text": " This is it, we know we just",
"tokens": [
50564,
639,
307,
309,
11,
321,
458,
321,
445,
50714
],
"temperature": 0.0,
"avg_logprob": -0.9387273416890727,
"compression_ratio": 1.4172185430463575,
"no_speech_prob": 0.10345567017793655,
"confidence": 0.459,
"words": [
{
"text": "This",
"start": 64.46,
"end": 64.72,
"confidence": 0.243
},
{
"text": "is",
"start": 64.72,
"end": 64.94,
"confidence": 0.663
},
{
"text": "it,",
"start": 64.94,
"end": 65.12,
"confidence": 0.243
},
{
"text": "we",
"start": 65.22,
"end": 65.42,
"confidence": 0.475
},
{
"text": "know",
"start": 65.42,
"end": 65.62,
"confidence": 0.696
},
{
"text": "we",
"start": 65.62,
"end": 65.88,
"confidence": 0.823
},
{
"text": "just",
"start": 65.88,
"end": 66.82,
"confidence": 0.405
}
]
},
{
"id": 9,
"seek": 6000,
"start": 66.86,
"end": 68.3,
"text": " You can hit that",
"tokens": [
50714,
509,
393,
2045,
300,
50764
],
"temperature": 0.0,
"avg_logprob": -0.9387273416890727,
"compression_ratio": 1.4172185430463575,
"no_speech_prob": 0.10345567017793655,
"confidence": 0.329,
"words": [
{
"text": "You",
"start": 66.86,
"end": 67.14,
"confidence": 0.246
},
{
"text": "can",
"start": 67.14,
"end": 67.32,
"confidence": 0.577
},
{
"text": "hit",
"start": 67.32,
"end": 67.52,
"confidence": 0.126
},
{
"text": "that",
"start": 67.52,
"end": 68.3,
"confidence": 0.656
}
]
},
{
"id": 10,
"seek": 6000,
"start": 68.32,
"end": 69.46,
"text": " That's how much you've ordered in that",
"tokens": [
50764,
663,
311,
577,
709,
291,
600,
8866,
294,
300,
50864
],
"temperature": 0.0,
"avg_logprob": -0.9387273416890727,
"compression_ratio": 1.4172185430463575,
"no_speech_prob": 0.10345567017793655,
"confidence": 0.3,
"words": [
{
"text": "That's",
"start": 68.32,
"end": 68.58,
"confidence": 0.262
},
{
"text": "how",
"start": 68.58,
"end": 68.6,
"confidence": 0.237
},
{
"text": "much",
"start": 68.6,
"end": 68.68,
"confidence": 0.974
},
{
"text": "you've",
"start": 68.68,
"end": 68.84,
"confidence": 0.416
},
{
"text": "ordered",
"start": 68.84,
"end": 69.02,
"confidence": 0.145
},
{
"text": "in",
"start": 69.02,
"end": 69.22,
"confidence": 0.204
},
{
"text": "that",
"start": 69.22,
"end": 69.46,
"confidence": 0.246
}
]
},
{
"id": 11,
"seek": 6000,
"start": 70.4,
"end": 72.52,
"text": " So I guess I'm working on my position but it's not",
"tokens": [
50864,
407,
286,
2041,
286,
478,
1364,
322,
452,
2535,
457,
309,
311,
406,
51014
],
"temperature": 0.0,
"avg_logprob": -0.9387273416890727,
"compression_ratio": 1.4172185430463575,
"no_speech_prob": 0.10345567017793655,
"confidence": 0.458,
"words": [
{
"text": "So",
"start": 70.4,
"end": 70.42,
"confidence": 0.914
},
{
"text": "I",
"start": 70.42,
"end": 70.54,
"confidence": 0.727
},
{
"text": "guess",
"start": 70.54,
"end": 70.8,
"confidence": 0.767
},
{
"text": "I'm",
"start": 70.8,
"end": 71.3,
"confidence": 0.363
},
{
"text": "working",
"start": 71.3,
"end": 71.32,
"confidence": 0.653
},
{
"text": "on",
"start": 71.32,
"end": 71.58,
"confidence": 0.396
},
{
"text": "my",
"start": 71.58,
"end": 71.74,
"confidence": 0.261
},
{
"text": "position",
"start": 71.74,
"end": 71.98,
"confidence": 0.081
},
{
"text": "but",
"start": 71.98,
"end": 72.18,
"confidence": 0.291
},
{
"text": "it's",
"start": 72.18,
"end": 72.38,
"confidence": 0.792
},
{
"text": "not",
"start": 72.38,
"end": 72.52,
"confidence": 0.585
}
]
},
{
"id": 12,
"seek": 6000,
"start": 74.72,
"end": 75.22,
"text": " Oh my god",
"tokens": [
51014,
876,
452,
3044,
51114
],
"temperature": 0.0,
"avg_logprob": -0.9387273416890727,
"compression_ratio": 1.4172185430463575,
"no_speech_prob": 0.10345567017793655,
"confidence": 0.199,
"words": [
{
"text": "Oh",
"start": 74.72,
"end": 74.74,
"confidence": 0.145
},
{
"text": "my",
"start": 74.74,
"end": 75.08,
"confidence": 0.273
},
{
"text": "god",
"start": 75.08,
"end": 75.22,
"confidence": 0.2
}
]
},
{
"id": 13,
"seek": 6000,
"start": 75.22,
"end": 76.64,
"text": " Okay, no problem",
"tokens": [
51114,
1033,
11,
572,
1154,
51214
],
"temperature": 0.0,
"avg_logprob": -0.9387273416890727,
"compression_ratio": 1.4172185430463575,
"no_speech_prob": 0.10345567017793655,
"confidence": 0.623,
"words": [
{
"text": "Okay,",
"start": 75.22,
"end": 75.9,
"confidence": 0.682
},
{
"text": "no",
"start": 76.26,
"end": 76.32,
"confidence": 0.365
},
{
"text": "problem",
"start": 76.32,
"end": 76.64,
"confidence": 0.97
}
]
},
{
"id": 14,
"seek": 6000,
"start": 76.64,
"end": 77.5,
"text": " No idea",
"tokens": [
51214,
883,
1558,
51264
],
"temperature": 0.0,
"avg_logprob": -0.9387273416890727,
"compression_ratio": 1.4172185430463575,
"no_speech_prob": 0.10345567017793655,
"confidence": 0.223,
"words": [
{
"text": "No",
"start": 76.64,
"end": 77.28,
"confidence": 0.223
},
{
"text": "idea",
"start": 77.28,
"end": 77.5,
"confidence": 0.224
}
]
},
{
"id": 15,
"seek": 6000,
"start": 78.06,
"end": 78.6,
"text": " No idea",
"tokens": [
51264,
883,
1558,
51314
],
"temperature": 0.0,
"avg_logprob": -0.9387273416890727,
"compression_ratio": 1.4172185430463575,
"no_speech_prob": 0.10345567017793655,
"confidence": 0.282,
"words": [
{
"text": "No",
"start": 78.06,
"end": 78.38,
"confidence": 0.105
},
{
"text": "idea",
"start": 78.38,
"end": 78.6,
"confidence": 0.76
}
]
},
{
"id": 16,
"seek": 6000,
"start": 85.28,
"end": 85.58,
"text": " Okay",
"tokens": [
51614,
1033,
51664
],
"temperature": 0.0,
"avg_logprob": -0.9387273416890727,
"compression_ratio": 1.4172185430463575,
"no_speech_prob": 0.10345567017793655,
"confidence": 0.101,
"words": [
{
"text": "Okay",
"start": 85.28,
"end": 85.58,
"confidence": 0.101
}
]
},
{
"id": 17,
"seek": 6000,
"start": 86.6,
"end": 86.86,
"text": " Okay",
"tokens": [
51664,
1033,
51714
],
"temperature": 0.0,
"avg_logprob": -0.9387273416890727,
"compression_ratio": 1.4172185430463575,
"no_speech_prob": 0.10345567017793655,
"confidence": 0.159,
"words": [
{
"text": "Okay",
"start": 86.6,
"end": 86.86,
"confidence": 0.159
}
]
}
],
"language": "en",
"language_probs": {
"en": 0.90898597240448,
"zh": 0.0063686794601380825,
"de": 0.0015729529550299048,
"es": 0.0061727361753582954,
"ru": 0.0024746020790189505,
"ko": 0.004695970099419355,
"fr": 0.0016613693442195654,
"ja": 0.003055725945159793,
"pt": 0.002100167563185096,
"tr": 0.0005608535720966756,
"pl": 0.00023197913833428174,
"ca": 5.729480835725553e-05,
"nl": 0.0019272222416475415,
"ar": 0.0010980981169268489,
"sv": 0.0010980981169268489,
"it": 0.0002393429313087836,
"id": 0.0011873272014781833,
"hi": 0.00014977698447182775,
"fi": 0.0010076714679598808,
"vi": 0.005533204879611731,
"he": 0.00017239226144738495,
"uk": 0.0002932491188403219,
"el": 0.0003401749418117106,
"ms": 0.0010076714679598808,
"cs": 4.4621239794651046e-05,
"ro": 0.0002079447585856542,
"da": 0.0010980981169268489,
"hu": 0.0001657880056882277,
"ta": 0.00026492850156500936,
"no": 8.873992919689044e-05,
"th": 0.0017685183556750417,
"ur": 0.0001606872392585501,
"hr": 3.6135381378699094e-05,
"bg": 3.8767600926803425e-05,
"lt": 1.964646617125254e-05,
"la": 0.002067607594653964,
"mi": 0.001782389241270721,
"ml": 0.001432189834304154,
"cy": 0.002436236944049597,
"sk": 8.650221388961654e-06,
"te": 9.084433986572549e-05,
"fa": 7.186378206824884e-05,
"lv": 2.4260149075416848e-05,
"bn": 8.01698406576179e-05,
"sr": 1.1869727131852414e-05,
"az": 8.416896889684722e-06,
"sl": 3.18893653457053e-05,
"kn": 5.105106083647115e-06,
"et": 1.059847363649169e-05,
"mk": 5.2466243687376846e-06,
"br": 0.0005696857697330415,
"eu": 1.7203019524458796e-05,
"is": 3.7282443372532725e-05,
"hy": 1.7203019524458796e-05,
"ne": 4.567940050037578e-05,
"mn": 0.00018640047346707433,
"bs": 2.7923257221118547e-05,
"kk": 4.5405749915516935e-06,
"sq": 2.5030247343238443e-05,
"sw": 9.670329018263146e-05,
"gl": 0.00016971956938505173,
"mr": 1.874678855529055e-05,
"pa": 6.182035122037632e-06,
"si": 0.00013425922952592373,
"km": 0.0008033857448026538,
"sn": 0.00027548204525373876,
"yo": 0.00018494989490136504,
"so": 4.215781245875405e-06,
"af": 8.01698406576179e-05,
"oc": 3.18893653457053e-05,
"ka": 8.221919415518641e-06,
"be": 1.7203019524458796e-05,
"tg": 1.2656181525017018e-07,
"sd": 3.0908227927284315e-05,
"gu": 3.4950057852256577e-06,
"am": 1.1685703611874487e-05,
"yi": 0.00014977698447182775,
"lo": 2.8809638024540618e-05,
"uz": 1.9721213551093797e-09,
"fo": 0.00045419312664307654,
"ht": 0.00015574341523461044,
"ps": 9.316655450675171e-06,
"tk": 1.7671988317147225e-08,
"nn": 0.015158776193857193,
"mt": 1.2439366400940344e-05,
"sa": 9.446316107641906e-05,
"lb": 1.3684594080132229e-07,
"my": 0.00024311205197591335,
"bo": 0.00028422678587958217,
"tl": 0.0014776524621993303,
"mg": 3.611920007529079e-08,
"as": 1.2635258826776408e-05,
"tt": 1.3765013306965557e-07,
"haw": 0.010665531270205975,
"ln": 9.956344001693651e-06,
"ha": 1.6636236921385716e-07,
"ba": 1.7880301683703692e-08,
"jw": 0.004480925854295492,
"su": 1.108212259737229e-07
}
}