word-sub / tests /expected /corner_cases.cpu /random.nocond_apollo11.mp3.words.json
RaeesRSB's picture
Upload 185 files
2cba4ca
{
"text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-VA GLEME GVA. All right. Okay, we like to say that they make it one or two on the helmet. We're going to have a B1 and you can put the other one on the mic helmet with those GVA blizzard frames. We were going to hack me on the ground with a cover. I tried it already. Okay, fine. We weren't sure of that. Just a suggestion. We thought we'd get you to check it out. I'm not sure if you've already turned that. So I guess we're going to come up with this. Let us know. Okay, no problem. Okay, no problem. No problem. No one at the end of the line.",
"segments": [
{
"id": 0,
"seek": 0,
"start": 0.64,
"end": 6.68,
"text": " Apollo 11, Houston we got a recommendation for you on your Soyuz-VA GLEME GVA.",
"tokens": [
25187,
2975,
11,
18717,
321,
658,
257,
11879,
337,
291,
322,
428,
24758,
3334,
12,
20914,
460,
2634,
15454,
460,
20914,
13
],
"temperature": 0.1,
"avg_logprob": -0.709779328937772,
"compression_ratio": 1.3631578947368421,
"no_speech_prob": 0.45045843720436096,
"confidence": 0.542,
"words": [
{
"text": "Apollo",
"start": 0.64,
"end": 0.98,
"confidence": 0.155
},
{
"text": "11,",
"start": 0.98,
"end": 1.54,
"confidence": 0.977
},
{
"text": "Houston",
"start": 1.54,
"end": 1.8,
"confidence": 0.986
},
{
"text": "we",
"start": 1.8,
"end": 1.98,
"confidence": 0.52
},
{
"text": "got",
"start": 1.98,
"end": 2.16,
"confidence": 0.824
},
{
"text": "a",
"start": 2.16,
"end": 2.38,
"confidence": 0.989
},
{
"text": "recommendation",
"start": 2.38,
"end": 3.1,
"confidence": 0.968
},
{
"text": "for",
"start": 3.1,
"end": 3.52,
"confidence": 0.947
},
{
"text": "you",
"start": 3.52,
"end": 3.9,
"confidence": 0.984
},
{
"text": "on",
"start": 3.9,
"end": 4.28,
"confidence": 0.909
},
{
"text": "your",
"start": 4.28,
"end": 4.32,
"confidence": 0.971
},
{
"text": "Soyuz-VA",
"start": 4.32,
"end": 5.38,
"confidence": 0.26
},
{
"text": "GLEME",
"start": 5.38,
"end": 6.04,
"confidence": 0.478
},
{
"text": "GVA.",
"start": 6.04,
"end": 6.68,
"confidence": 0.436
}
]
},
{
"id": 1,
"seek": 0,
"start": 7.5,
"end": 11.0,
"text": " All right.",
"tokens": [
1057,
558,
13
],
"temperature": 0.1,
"avg_logprob": -0.709779328937772,
"compression_ratio": 1.3631578947368421,
"no_speech_prob": 0.45045843720436096,
"confidence": 0.456,
"words": [
{
"text": "All",
"start": 7.5,
"end": 7.7,
"confidence": 0.212
},
{
"text": "right.",
"start": 7.7,
"end": 11.0,
"confidence": 0.982
}
]
},
{
"id": 2,
"seek": 0,
"start": 11.5,
"end": 17.19,
"text": " Okay, we like to say that they make it one or two on the helmet.",
"tokens": [
1033,
11,
321,
411,
281,
584,
300,
436,
652,
309,
472,
420,
732,
322,
264,
15922,
13
],
"temperature": 0.1,
"avg_logprob": -0.709779328937772,
"compression_ratio": 1.3631578947368421,
"no_speech_prob": 0.45045843720436096,
"confidence": 0.428,
"words": [
{
"text": "Okay,",
"start": 11.5,
"end": 12.82,
"confidence": 0.577
},
{
"text": "we",
"start": 12.82,
"end": 13.12,
"confidence": 0.541
},
{
"text": "like",
"start": 13.12,
"end": 13.44,
"confidence": 0.493
},
{
"text": "to",
"start": 13.44,
"end": 13.68,
"confidence": 0.307
},
{
"text": "say",
"start": 13.68,
"end": 14.96,
"confidence": 0.172
},
{
"text": "that",
"start": 14.96,
"end": 15.56,
"confidence": 0.203
},
{
"text": "they",
"start": 15.56,
"end": 15.6,
"confidence": 0.472
},
{
"text": "make",
"start": 15.6,
"end": 15.76,
"confidence": 0.378
},
{
"text": "it",
"start": 15.76,
"end": 15.96,
"confidence": 0.259
},
{
"text": "one",
"start": 15.96,
"end": 16.1,
"confidence": 0.481
},
{
"text": "or",
"start": 16.1,
"end": 16.34,
"confidence": 0.221
},
{
"text": "two",
"start": 16.34,
"end": 16.46,
"confidence": 0.938
},
{
"text": "on",
"start": 16.46,
"end": 16.7,
"confidence": 0.638
},
{
"text": "the",
"start": 16.7,
"end": 16.96,
"confidence": 0.885
},
{
"text": "helmet.",
"start": 16.96,
"end": 17.19,
"confidence": 0.695
}
]
},
{
"id": 3,
"seek": 0,
"start": 17.19,
"end": 24.74,
"text": " We're going to have a B1 and you can put the other one on the mic helmet with those GVA blizzard frames.",
"tokens": [
492,
434,
516,
281,
362,
257,
363,
16,
293,
291,
393,
829,
264,
661,
472,
322,
264,
3123,
15922,
365,
729,
460,
20914,
888,
31062,
12083,
13
],
"temperature": 0.1,
"avg_logprob": -0.709779328937772,
"compression_ratio": 1.3631578947368421,
"no_speech_prob": 0.45045843720436096,
"confidence": 0.515,
"words": [
{
"text": "We're",
"start": 17.19,
"end": 17.86,
"confidence": 0.63
},
{
"text": "going",
"start": 17.86,
"end": 18.06,
"confidence": 0.62
},
{
"text": "to",
"start": 18.06,
"end": 18.24,
"confidence": 0.993
},
{
"text": "have",
"start": 18.24,
"end": 18.3,
"confidence": 0.959
},
{
"text": "a",
"start": 18.3,
"end": 18.42,
"confidence": 0.32
},
{
"text": "B1",
"start": 18.42,
"end": 19.3,
"confidence": 0.799
},
{
"text": "and",
"start": 19.3,
"end": 20.18,
"confidence": 0.498
},
{
"text": "you",
"start": 20.18,
"end": 20.36,
"confidence": 0.87
},
{
"text": "can",
"start": 20.36,
"end": 20.54,
"confidence": 0.672
},
{
"text": "put",
"start": 20.54,
"end": 20.72,
"confidence": 0.967
},
{
"text": "the",
"start": 20.72,
"end": 20.88,
"confidence": 0.974
},
{
"text": "other",
"start": 20.88,
"end": 21.06,
"confidence": 0.995
},
{
"text": "one",
"start": 21.06,
"end": 21.26,
"confidence": 0.973
},
{
"text": "on",
"start": 21.26,
"end": 21.68,
"confidence": 0.973
},
{
"text": "the",
"start": 21.68,
"end": 21.96,
"confidence": 0.585
},
{
"text": "mic",
"start": 21.96,
"end": 22.6,
"confidence": 0.48
},
{
"text": "helmet",
"start": 22.6,
"end": 22.94,
"confidence": 0.949
},
{
"text": "with",
"start": 22.94,
"end": 23.2,
"confidence": 0.444
},
{
"text": "those",
"start": 23.2,
"end": 23.5,
"confidence": 0.351
},
{
"text": "GVA",
"start": 23.5,
"end": 23.86,
"confidence": 0.169
},
{
"text": "blizzard",
"start": 23.86,
"end": 24.32,
"confidence": 0.094
},
{
"text": "frames.",
"start": 24.32,
"end": 24.74,
"confidence": 0.245
}
]
},
{
"id": 4,
"seek": 5500,
"start": 56.0,
"end": 61.1,
"text": " We were going to hack me on the ground with a cover.",
"tokens": [
492,
645,
516,
281,
10339,
385,
322,
264,
2727,
365,
257,
2060,
13
],
"temperature": 0.1,
"avg_logprob": -0.46802620968576203,
"compression_ratio": 1.6418604651162791,
"no_speech_prob": 0.7498895525932312,
"confidence": 0.342,
"words": [
{
"text": "We",
"start": 56.0,
"end": 56.68,
"confidence": 0.071
},
{
"text": "were",
"start": 56.68,
"end": 56.98,
"confidence": 0.177
},
{
"text": "going",
"start": 56.98,
"end": 57.2,
"confidence": 0.148
},
{
"text": "to",
"start": 57.2,
"end": 57.46,
"confidence": 0.932
},
{
"text": "hack",
"start": 57.46,
"end": 57.5,
"confidence": 0.261
},
{
"text": "me",
"start": 57.5,
"end": 57.64,
"confidence": 0.544
},
{
"text": "on",
"start": 57.64,
"end": 59.2,
"confidence": 0.433
},
{
"text": "the",
"start": 59.2,
"end": 59.5,
"confidence": 0.309
},
{
"text": "ground",
"start": 59.5,
"end": 59.78,
"confidence": 0.356
},
{
"text": "with",
"start": 59.78,
"end": 60.62,
"confidence": 0.471
},
{
"text": "a",
"start": 60.62,
"end": 60.78,
"confidence": 0.538
},
{
"text": "cover.",
"start": 60.78,
"end": 61.1,
"confidence": 0.855
}
]
},
{
"id": 5,
"seek": 5500,
"start": 61.12,
"end": 61.88,
"text": " I tried it already.",
"tokens": [
286,
3031,
309,
1217,
13
],
"temperature": 0.1,
"avg_logprob": -0.46802620968576203,
"compression_ratio": 1.6418604651162791,
"no_speech_prob": 0.7498895525932312,
"confidence": 0.682,
"words": [
{
"text": "I",
"start": 61.12,
"end": 61.26,
"confidence": 0.407
},
{
"text": "tried",
"start": 61.26,
"end": 61.52,
"confidence": 0.889
},
{
"text": "it",
"start": 61.52,
"end": 61.7,
"confidence": 0.746
},
{
"text": "already.",
"start": 61.7,
"end": 61.88,
"confidence": 0.803
}
]
},
{
"id": 6,
"seek": 5500,
"start": 62.5,
"end": 63.12,
"text": " Okay, fine.",
"tokens": [
1033,
11,
2489,
13
],
"temperature": 0.1,
"avg_logprob": -0.46802620968576203,
"compression_ratio": 1.6418604651162791,
"no_speech_prob": 0.7498895525932312,
"confidence": 0.683,
"words": [
{
"text": "Okay,",
"start": 62.5,
"end": 63.04,
"confidence": 0.521
},
{
"text": "fine.",
"start": 63.04,
"end": 63.12,
"confidence": 0.895
}
]
},
{
"id": 7,
"seek": 5500,
"start": 63.12,
"end": 64.12,
"text": " We weren't sure of that.",
"tokens": [
492,
4999,
380,
988,
295,
300,
13
],
"temperature": 0.1,
"avg_logprob": -0.46802620968576203,
"compression_ratio": 1.6418604651162791,
"no_speech_prob": 0.7498895525932312,
"confidence": 0.895,
"words": [
{
"text": "We",
"start": 63.12,
"end": 63.34,
"confidence": 0.959
},
{
"text": "weren't",
"start": 63.34,
"end": 63.62,
"confidence": 0.988
},
{
"text": "sure",
"start": 63.62,
"end": 63.82,
"confidence": 0.903
},
{
"text": "of",
"start": 63.82,
"end": 64.08,
"confidence": 0.613
},
{
"text": "that.",
"start": 64.08,
"end": 64.12,
"confidence": 0.989
}
]
},
{
"id": 8,
"seek": 5500,
"start": 64.46,
"end": 65.2,
"text": " Just a suggestion.",
"tokens": [
1449,
257,
16541,
13
],
"temperature": 0.1,
"avg_logprob": -0.46802620968576203,
"compression_ratio": 1.6418604651162791,
"no_speech_prob": 0.7498895525932312,
"confidence": 0.755,
"words": [
{
"text": "Just",
"start": 64.46,
"end": 64.66,
"confidence": 0.545
},
{
"text": "a",
"start": 64.66,
"end": 64.76,
"confidence": 0.791
},
{
"text": "suggestion.",
"start": 64.76,
"end": 65.2,
"confidence": 0.997
}
]
},
{
"id": 9,
"seek": 5500,
"start": 65.34,
"end": 67.92,
"text": " We thought we'd get you to check it out.",
"tokens": [
492,
1194,
321,
1116,
483,
291,
281,
1520,
309,
484,
13
],
"temperature": 0.1,
"avg_logprob": -0.46802620968576203,
"compression_ratio": 1.6418604651162791,
"no_speech_prob": 0.7498895525932312,
"confidence": 0.692,
"words": [
{
"text": "We",
"start": 65.34,
"end": 65.44,
"confidence": 0.873
},
{
"text": "thought",
"start": 65.44,
"end": 65.62,
"confidence": 0.968
},
{
"text": "we'd",
"start": 65.62,
"end": 66.76,
"confidence": 0.686
},
{
"text": "get",
"start": 66.76,
"end": 67.06,
"confidence": 0.093
},
{
"text": "you",
"start": 67.06,
"end": 67.14,
"confidence": 0.823
},
{
"text": "to",
"start": 67.14,
"end": 67.32,
"confidence": 0.987
},
{
"text": "check",
"start": 67.32,
"end": 67.46,
"confidence": 0.845
},
{
"text": "it",
"start": 67.46,
"end": 67.68,
"confidence": 0.991
},
{
"text": "out.",
"start": 67.68,
"end": 67.92,
"confidence": 0.997
}
]
},
{
"id": 10,
"seek": 5500,
"start": 68.28,
"end": 69.34,
"text": " I'm not sure if you've already turned that.",
"tokens": [
286,
478,
406,
988,
498,
291,
600,
1217,
3574,
300,
13
],
"temperature": 0.1,
"avg_logprob": -0.46802620968576203,
"compression_ratio": 1.6418604651162791,
"no_speech_prob": 0.7498895525932312,
"confidence": 0.444,
"words": [
{
"text": "I'm",
"start": 68.28,
"end": 68.5,
"confidence": 0.314
},
{
"text": "not",
"start": 68.5,
"end": 68.56,
"confidence": 0.319
},
{
"text": "sure",
"start": 68.56,
"end": 68.74,
"confidence": 0.82
},
{
"text": "if",
"start": 68.74,
"end": 68.78,
"confidence": 0.334
},
{
"text": "you've",
"start": 68.78,
"end": 68.84,
"confidence": 0.389
},
{
"text": "already",
"start": 68.84,
"end": 68.94,
"confidence": 0.588
},
{
"text": "turned",
"start": 68.94,
"end": 69.12,
"confidence": 0.738
},
{
"text": "that.",
"start": 69.12,
"end": 69.34,
"confidence": 0.524
}
]
},
{
"id": 11,
"seek": 5500,
"start": 70.42,
"end": 71.98,
"text": " So I guess we're going to come up with this.",
"tokens": [
407,
286,
2041,
321,
434,
516,
281,
808,
493,
365,
341,
13
],
"temperature": 0.1,
"avg_logprob": -0.46802620968576203,
"compression_ratio": 1.6418604651162791,
"no_speech_prob": 0.7498895525932312,
"confidence": 0.709,
"words": [
{
"text": "So",
"start": 70.42,
"end": 70.5,
"confidence": 0.533
},
{
"text": "I",
"start": 70.5,
"end": 70.54,
"confidence": 0.454
},
{
"text": "guess",
"start": 70.54,
"end": 70.82,
"confidence": 0.991
},
{
"text": "we're",
"start": 70.82,
"end": 71.12,
"confidence": 0.654
},
{
"text": "going",
"start": 71.12,
"end": 71.28,
"confidence": 0.815
},
{
"text": "to",
"start": 71.28,
"end": 71.36,
"confidence": 0.992
},
{
"text": "come",
"start": 71.36,
"end": 71.48,
"confidence": 0.97
},
{
"text": "up",
"start": 71.48,
"end": 71.68,
"confidence": 0.958
},
{
"text": "with",
"start": 71.68,
"end": 71.92,
"confidence": 0.915
},
{
"text": "this.",
"start": 71.92,
"end": 71.98,
"confidence": 0.323
}
]
},
{
"id": 12,
"seek": 5500,
"start": 73.5,
"end": 73.62,
"text": " Let us know.",
"tokens": [
961,
505,
458,
13
],
"temperature": 0.1,
"avg_logprob": -0.46802620968576203,
"compression_ratio": 1.6418604651162791,
"no_speech_prob": 0.7498895525932312,
"confidence": 0.847,
"words": [
{
"text": "Let",
"start": 73.5,
"end": 73.54,
"confidence": 0.615
},
{
"text": "us",
"start": 73.54,
"end": 73.58,
"confidence": 0.99
},
{
"text": "know.",
"start": 73.58,
"end": 73.62,
"confidence": 0.998
}
]
},
{
"id": 13,
"seek": 5500,
"start": 74.22,
"end": 75.22,
"text": " Okay, no problem.",
"tokens": [
1033,
11,
572,
1154,
13
],
"temperature": 0.1,
"avg_logprob": -0.46802620968576203,
"compression_ratio": 1.6418604651162791,
"no_speech_prob": 0.7498895525932312,
"confidence": 0.851,
"words": [
{
"text": "Okay,",
"start": 74.22,
"end": 74.7,
"confidence": 0.687
},
{
"text": "no",
"start": 74.7,
"end": 74.86,
"confidence": 0.917
},
{
"text": "problem.",
"start": 74.86,
"end": 75.22,
"confidence": 0.976
}
]
},
{
"id": 14,
"seek": 5500,
"start": 75.28,
"end": 76.46,
"text": " Okay, no problem.",
"tokens": [
1033,
11,
572,
1154,
13
],
"temperature": 0.1,
"avg_logprob": -0.46802620968576203,
"compression_ratio": 1.6418604651162791,
"no_speech_prob": 0.7498895525932312,
"confidence": 0.623,
"words": [
{
"text": "Okay,",
"start": 75.28,
"end": 75.98,
"confidence": 0.258
},
{
"text": "no",
"start": 75.98,
"end": 76.2,
"confidence": 0.948
},
{
"text": "problem.",
"start": 76.2,
"end": 76.46,
"confidence": 0.993
}
]
},
{
"id": 15,
"seek": 7600,
"start": 76.46,
"end": 76.62,
"text": " No problem.",
"tokens": [
883,
1154,
13
],
"temperature": 0.1,
"avg_logprob": -0.7044810771942138,
"compression_ratio": 0.9344262295081968,
"no_speech_prob": 0.35927486419677734,
"confidence": 0.653,
"words": [
{
"text": "No",
"start": 76.46,
"end": 76.5,
"confidence": 0.463
},
{
"text": "problem.",
"start": 76.5,
"end": 76.62,
"confidence": 0.922
}
]
},
{
"id": 16,
"seek": 7700,
"start": 77.02,
"end": 78.32,
"text": " No one at the end of the line.",
"tokens": [
50364,
883,
472,
412,
264,
917,
295,
264,
1622,
13,
50464
],
"temperature": 0.1,
"avg_logprob": -0.676593542098999,
"compression_ratio": 0.8823529411764706,
"no_speech_prob": 0.2589211165904999,
"confidence": 0.558,
"words": [
{
"text": "No",
"start": 77.02,
"end": 77.22,
"confidence": 0.139
},
{
"text": "one",
"start": 77.22,
"end": 77.36,
"confidence": 0.335
},
{
"text": "at",
"start": 77.36,
"end": 77.44,
"confidence": 0.483
},
{
"text": "the",
"start": 77.44,
"end": 77.48,
"confidence": 0.996
},
{
"text": "end",
"start": 77.48,
"end": 77.92,
"confidence": 0.995
},
{
"text": "of",
"start": 77.92,
"end": 78.1,
"confidence": 0.968
},
{
"text": "the",
"start": 78.1,
"end": 78.2,
"confidence": 0.536
},
{
"text": "line.",
"start": 78.2,
"end": 78.32,
"confidence": 0.816
}
]
}
],
"language": "English"
}