word-sub / tests /expected /corner_cases /large_apollo11.mp3.words.json
RaeesRSB's picture
Upload 185 files
2cba4ca
{
"text": " Apollo 11, Houston. We got a recommendation for you on your DOJ's E-A limb, E-G-E-A's, over. Go ahead. Okay, we'd like to have, say, a selected one or two on the helmet. We're going to have an B1. And you could put the other one on Mike's helmet, we're still seeing the bleepers. Over. with a cover I tried it already. Okay fine, we weren't sure that this was a suggestion. We thought we'd uh... you could check it out. How much you've already done that. So uh... I guess whatever you can come up with, just let us know and... Okay there's no problem. Okay, there's no problem. We'll let you know where they end up. Nice.",
"segments": [
{
"id": 0,
"seek": 0,
"start": 0.36,
"end": 6.96,
"text": " Apollo 11, Houston. We got a recommendation for you on your DOJ's E-A limb, E-G-E-A's, over.",
"tokens": [
50364,
25187,
2975,
11,
18717,
13,
492,
658,
257,
11879,
337,
291,
322,
428,
10699,
41,
311,
462,
12,
32,
30390,
11,
462,
12,
38,
12,
36,
12,
32,
311,
11,
670,
13,
50714
],
"temperature": 0.4,
"avg_logprob": -0.6033297837382615,
"compression_ratio": 1.425,
"no_speech_prob": 0.3341304659843445,
"confidence": 0.595,
"words": [
{
"text": "Apollo",
"start": 0.36,
"end": 0.92,
"confidence": 0.79
},
{
"text": "11,",
"start": 0.92,
"end": 1.32,
"confidence": 0.877
},
{
"text": "Houston.",
"start": 1.5,
"end": 1.74,
"confidence": 0.827
},
{
"text": "We",
"start": 1.9,
"end": 1.94,
"confidence": 0.836
},
{
"text": "got",
"start": 1.94,
"end": 2.1,
"confidence": 0.639
},
{
"text": "a",
"start": 2.1,
"end": 2.3,
"confidence": 0.995
},
{
"text": "recommendation",
"start": 2.3,
"end": 3.08,
"confidence": 0.709
},
{
"text": "for",
"start": 3.08,
"end": 3.46,
"confidence": 0.856
},
{
"text": "you",
"start": 3.46,
"end": 3.62,
"confidence": 0.859
},
{
"text": "on",
"start": 3.62,
"end": 3.76,
"confidence": 0.87
},
{
"text": "your",
"start": 3.76,
"end": 4.06,
"confidence": 0.767
},
{
"text": "DOJ's",
"start": 4.06,
"end": 4.88,
"confidence": 0.163
},
{
"text": "E-A",
"start": 4.88,
"end": 5.3,
"confidence": 0.408
},
{
"text": "limb,",
"start": 5.3,
"end": 5.62,
"confidence": 0.264
},
{
"text": "E-G-E-A's,",
"start": 5.76,
"end": 6.8,
"confidence": 0.768
},
{
"text": "over.",
"start": 6.82,
"end": 6.96,
"confidence": 0.817
}
]
},
{
"id": 1,
"seek": 0,
"start": 10.74,
"end": 11.14,
"text": " Go ahead.",
"tokens": [
50864,
1037,
2286,
13,
50914
],
"temperature": 0.4,
"avg_logprob": -0.6033297837382615,
"compression_ratio": 1.425,
"no_speech_prob": 0.3341304659843445,
"confidence": 0.85,
"words": [
{
"text": "Go",
"start": 10.74,
"end": 10.98,
"confidence": 0.842
},
{
"text": "ahead.",
"start": 10.98,
"end": 11.14,
"confidence": 0.858
}
]
},
{
"id": 2,
"seek": 0,
"start": 11.88,
"end": 17.3,
"text": " Okay, we'd like to have, say, a selected one or two on the helmet.",
"tokens": [
50914,
1033,
11,
321,
1116,
411,
281,
362,
11,
584,
11,
257,
8209,
472,
420,
732,
322,
264,
15922,
13,
51214
],
"temperature": 0.4,
"avg_logprob": -0.6033297837382615,
"compression_ratio": 1.425,
"no_speech_prob": 0.3341304659843445,
"confidence": 0.428,
"words": [
{
"text": "Okay,",
"start": 11.88,
"end": 12.28,
"confidence": 0.507
},
{
"text": "we'd",
"start": 12.5,
"end": 13.16,
"confidence": 0.623
},
{
"text": "like",
"start": 13.16,
"end": 13.32,
"confidence": 0.876
},
{
"text": "to",
"start": 13.32,
"end": 13.56,
"confidence": 0.737
},
{
"text": "have,",
"start": 13.56,
"end": 14.24,
"confidence": 0.124
},
{
"text": "say,",
"start": 14.74,
"end": 15.0,
"confidence": 0.153
},
{
"text": "a",
"start": 15.1,
"end": 15.16,
"confidence": 0.061
},
{
"text": "selected",
"start": 15.16,
"end": 15.76,
"confidence": 0.143
},
{
"text": "one",
"start": 15.76,
"end": 16.08,
"confidence": 0.754
},
{
"text": "or",
"start": 16.08,
"end": 16.22,
"confidence": 0.67
},
{
"text": "two",
"start": 16.22,
"end": 16.36,
"confidence": 0.6
},
{
"text": "on",
"start": 16.36,
"end": 16.6,
"confidence": 0.875
},
{
"text": "the",
"start": 16.6,
"end": 16.82,
"confidence": 0.809
},
{
"text": "helmet.",
"start": 16.82,
"end": 17.3,
"confidence": 0.651
}
]
},
{
"id": 3,
"seek": 0,
"start": 17.32,
"end": 19.12,
"text": " We're going to have an B1.",
"tokens": [
51214,
492,
434,
516,
281,
362,
364,
363,
16,
13,
51314
],
"temperature": 0.4,
"avg_logprob": -0.6033297837382615,
"compression_ratio": 1.425,
"no_speech_prob": 0.3341304659843445,
"confidence": 0.545,
"words": [
{
"text": "We're",
"start": 17.32,
"end": 17.78,
"confidence": 0.7
},
{
"text": "going",
"start": 17.78,
"end": 17.94,
"confidence": 0.505
},
{
"text": "to",
"start": 17.94,
"end": 18.06,
"confidence": 0.899
},
{
"text": "have",
"start": 18.06,
"end": 18.22,
"confidence": 0.848
},
{
"text": "an",
"start": 18.22,
"end": 18.4,
"confidence": 0.264
},
{
"text": "B1.",
"start": 18.4,
"end": 19.12,
"confidence": 0.395
}
]
},
{
"id": 4,
"seek": 0,
"start": 20.08,
"end": 24.32,
"text": " And you could put the other one on Mike's helmet, we're still seeing the bleepers.",
"tokens": [
51314,
400,
291,
727,
829,
264,
661,
472,
322,
6602,
311,
15922,
11,
321,
434,
920,
2577,
264,
5408,
595,
433,
13,
51564
],
"temperature": 0.4,
"avg_logprob": -0.6033297837382615,
"compression_ratio": 1.425,
"no_speech_prob": 0.3341304659843445,
"confidence": 0.528,
"words": [
{
"text": "And",
"start": 20.08,
"end": 20.22,
"confidence": 0.796
},
{
"text": "you",
"start": 20.22,
"end": 20.34,
"confidence": 0.885
},
{
"text": "could",
"start": 20.34,
"end": 20.48,
"confidence": 0.415
},
{
"text": "put",
"start": 20.48,
"end": 20.66,
"confidence": 0.894
},
{
"text": "the",
"start": 20.66,
"end": 20.84,
"confidence": 0.813
},
{
"text": "other",
"start": 20.84,
"end": 21.02,
"confidence": 0.774
},
{
"text": "one",
"start": 21.02,
"end": 21.22,
"confidence": 0.779
},
{
"text": "on",
"start": 21.22,
"end": 21.46,
"confidence": 0.906
},
{
"text": "Mike's",
"start": 21.46,
"end": 22.72,
"confidence": 0.831
},
{
"text": "helmet,",
"start": 22.72,
"end": 22.86,
"confidence": 0.791
},
{
"text": "we're",
"start": 23.06,
"end": 23.14,
"confidence": 0.354
},
{
"text": "still",
"start": 23.14,
"end": 23.34,
"confidence": 0.792
},
{
"text": "seeing",
"start": 23.34,
"end": 23.64,
"confidence": 0.728
},
{
"text": "the",
"start": 23.64,
"end": 23.88,
"confidence": 0.099
},
{
"text": "bleepers.",
"start": 23.88,
"end": 24.32,
"confidence": 0.228
}
]
},
{
"id": 5,
"seek": 0,
"start": 24.86,
"end": 25.1,
"text": " Over.",
"tokens": [
51564,
4886,
13,
51614
],
"temperature": 0.4,
"avg_logprob": -0.6033297837382615,
"compression_ratio": 1.425,
"no_speech_prob": 0.3341304659843445,
"confidence": 0.616,
"words": [
{
"text": "Over.",
"start": 24.86,
"end": 25.1,
"confidence": 0.616
}
]
},
{
"id": 6,
"seek": 6000,
"start": 60.0,
"end": 61.9,
"text": " with a cover I tried it already.",
"tokens": [
50364,
365,
257,
2060,
286,
3031,
309,
1217,
13,
50474
],
"temperature": 0.4,
"avg_logprob": -0.6061306174741973,
"compression_ratio": 1.5876777251184835,
"no_speech_prob": 0.0662694051861763,
"confidence": 0.442,
"words": [
{
"text": "with",
"start": 60.0,
"end": 60.2,
"confidence": 0.119
},
{
"text": "a",
"start": 60.2,
"end": 60.38,
"confidence": 0.457
},
{
"text": "cover",
"start": 60.38,
"end": 61.04,
"confidence": 0.558
},
{
"text": "I",
"start": 61.04,
"end": 61.22,
"confidence": 0.278
},
{
"text": "tried",
"start": 61.22,
"end": 61.48,
"confidence": 0.625
},
{
"text": "it",
"start": 61.48,
"end": 61.64,
"confidence": 0.802
},
{
"text": "already.",
"start": 61.64,
"end": 61.9,
"confidence": 0.772
}
]
},
{
"id": 7,
"seek": 6000,
"start": 62.42,
"end": 65.18,
"text": " Okay fine, we weren't sure that this was a suggestion.",
"tokens": [
50474,
1033,
2489,
11,
321,
4999,
380,
988,
300,
341,
390,
257,
16541,
13,
50629
],
"temperature": 0.4,
"avg_logprob": -0.6061306174741973,
"compression_ratio": 1.5876777251184835,
"no_speech_prob": 0.0662694051861763,
"confidence": 0.666,
"words": [
{
"text": "Okay",
"start": 62.42,
"end": 62.82,
"confidence": 0.414
},
{
"text": "fine,",
"start": 62.82,
"end": 63.1,
"confidence": 0.467
},
{
"text": "we",
"start": 63.22,
"end": 63.3,
"confidence": 0.846
},
{
"text": "weren't",
"start": 63.3,
"end": 63.56,
"confidence": 0.886
},
{
"text": "sure",
"start": 63.56,
"end": 63.74,
"confidence": 0.809
},
{
"text": "that",
"start": 63.74,
"end": 64.1,
"confidence": 0.513
},
{
"text": "this",
"start": 64.1,
"end": 64.58,
"confidence": 0.59
},
{
"text": "was",
"start": 64.58,
"end": 64.76,
"confidence": 0.787
},
{
"text": "a",
"start": 64.76,
"end": 64.88,
"confidence": 0.769
},
{
"text": "suggestion.",
"start": 64.88,
"end": 65.18,
"confidence": 0.605
}
]
},
{
"id": 8,
"seek": 6000,
"start": 65.22,
"end": 66.76,
"text": " We thought we'd uh...",
"tokens": [
50629,
492,
1194,
321,
1116,
2232,
485,
50699
],
"temperature": 0.4,
"avg_logprob": -0.6061306174741973,
"compression_ratio": 1.5876777251184835,
"no_speech_prob": 0.0662694051861763,
"confidence": 0.604,
"words": [
{
"text": "We",
"start": 65.22,
"end": 65.4,
"confidence": 0.876
},
{
"text": "thought",
"start": 65.4,
"end": 65.56,
"confidence": 0.816
},
{
"text": "we'd",
"start": 65.56,
"end": 65.88,
"confidence": 0.561
},
{
"text": "uh...",
"start": 65.88,
"end": 66.76,
"confidence": 0.356
}
]
},
{
"id": 9,
"seek": 6000,
"start": 66.76,
"end": 67.82,
"text": " you could check it out.",
"tokens": [
50699,
291,
727,
1520,
309,
484,
13,
50769
],
"temperature": 0.4,
"avg_logprob": -0.6061306174741973,
"compression_ratio": 1.5876777251184835,
"no_speech_prob": 0.0662694051861763,
"confidence": 0.599,
"words": [
{
"text": "you",
"start": 66.76,
"end": 67.04,
"confidence": 0.191
},
{
"text": "could",
"start": 67.04,
"end": 67.22,
"confidence": 0.698
},
{
"text": "check",
"start": 67.22,
"end": 67.44,
"confidence": 0.792
},
{
"text": "it",
"start": 67.44,
"end": 67.58,
"confidence": 0.901
},
{
"text": "out.",
"start": 67.58,
"end": 67.82,
"confidence": 0.811
}
]
},
{
"id": 10,
"seek": 6000,
"start": 68.18,
"end": 69.3,
"text": " How much you've already done that.",
"tokens": [
50769,
1012,
709,
291,
600,
1217,
1096,
300,
13,
50834
],
"temperature": 0.4,
"avg_logprob": -0.6061306174741973,
"compression_ratio": 1.5876777251184835,
"no_speech_prob": 0.0662694051861763,
"confidence": 0.617,
"words": [
{
"text": "How",
"start": 68.18,
"end": 68.42,
"confidence": 0.234
},
{
"text": "much",
"start": 68.42,
"end": 68.6,
"confidence": 0.806
},
{
"text": "you've",
"start": 68.6,
"end": 68.76,
"confidence": 0.575
},
{
"text": "already",
"start": 68.76,
"end": 68.88,
"confidence": 0.814
},
{
"text": "done",
"start": 68.88,
"end": 69.1,
"confidence": 0.779
},
{
"text": "that.",
"start": 69.1,
"end": 69.3,
"confidence": 0.861
}
]
},
{
"id": 11,
"seek": 6000,
"start": 69.36,
"end": 70.26,
"text": " So uh...",
"tokens": [
50834,
407,
2232,
485,
50879
],
"temperature": 0.4,
"avg_logprob": -0.6061306174741973,
"compression_ratio": 1.5876777251184835,
"no_speech_prob": 0.0662694051861763,
"confidence": 0.644,
"words": [
{
"text": "So",
"start": 69.36,
"end": 69.66,
"confidence": 0.883
},
{
"text": "uh...",
"start": 69.66,
"end": 70.26,
"confidence": 0.469
}
]
},
{
"id": 12,
"seek": 6000,
"start": 70.32,
"end": 71.8,
"text": " I guess whatever you can come up with,",
"tokens": [
50879,
286,
2041,
2035,
291,
393,
808,
493,
365,
11,
50954
],
"temperature": 0.4,
"avg_logprob": -0.6061306174741973,
"compression_ratio": 1.5876777251184835,
"no_speech_prob": 0.0662694051861763,
"confidence": 0.632,
"words": [
{
"text": "I",
"start": 70.32,
"end": 70.5,
"confidence": 0.992
},
{
"text": "guess",
"start": 70.5,
"end": 70.7,
"confidence": 0.905
},
{
"text": "whatever",
"start": 70.7,
"end": 71.12,
"confidence": 0.201
},
{
"text": "you",
"start": 71.12,
"end": 71.26,
"confidence": 0.884
},
{
"text": "can",
"start": 71.26,
"end": 71.32,
"confidence": 0.281
},
{
"text": "come",
"start": 71.32,
"end": 71.46,
"confidence": 0.777
},
{
"text": "up",
"start": 71.46,
"end": 71.62,
"confidence": 0.898
},
{
"text": "with,",
"start": 71.62,
"end": 71.8,
"confidence": 0.817
}
]
},
{
"id": 13,
"seek": 6000,
"start": 71.8,
"end": 72.76,
"text": " just let us know and...",
"tokens": [
50954,
445,
718,
505,
458,
293,
485,
51004
],
"temperature": 0.4,
"avg_logprob": -0.6061306174741973,
"compression_ratio": 1.5876777251184835,
"no_speech_prob": 0.0662694051861763,
"confidence": 0.721,
"words": [
{
"text": "just",
"start": 71.8,
"end": 71.98,
"confidence": 0.866
},
{
"text": "let",
"start": 71.98,
"end": 72.12,
"confidence": 0.905
},
{
"text": "us",
"start": 72.12,
"end": 72.26,
"confidence": 0.904
},
{
"text": "know",
"start": 72.26,
"end": 72.42,
"confidence": 0.798
},
{
"text": "and...",
"start": 72.42,
"end": 72.76,
"confidence": 0.346
}
]
},
{
"id": 14,
"seek": 6000,
"start": 74.16,
"end": 75.24,
"text": " Okay there's no problem.",
"tokens": [
51004,
1033,
456,
311,
572,
1154,
13,
51129
],
"temperature": 0.4,
"avg_logprob": -0.6061306174741973,
"compression_ratio": 1.5876777251184835,
"no_speech_prob": 0.0662694051861763,
"confidence": 0.558,
"words": [
{
"text": "Okay",
"start": 74.16,
"end": 74.44,
"confidence": 0.335
},
{
"text": "there's",
"start": 74.44,
"end": 74.74,
"confidence": 0.486
},
{
"text": "no",
"start": 74.74,
"end": 74.88,
"confidence": 0.888
},
{
"text": "problem.",
"start": 74.88,
"end": 75.24,
"confidence": 0.771
}
]
},
{
"id": 15,
"seek": 6000,
"start": 75.32,
"end": 76.56,
"text": " Okay, there's no problem.",
"tokens": [
51129,
1033,
11,
456,
311,
572,
1154,
13,
51194
],
"temperature": 0.4,
"avg_logprob": -0.6061306174741973,
"compression_ratio": 1.5876777251184835,
"no_speech_prob": 0.0662694051861763,
"confidence": 0.777,
"words": [
{
"text": "Okay,",
"start": 75.32,
"end": 75.84,
"confidence": 0.784
},
{
"text": "there's",
"start": 76.0,
"end": 76.08,
"confidence": 0.712
},
{
"text": "no",
"start": 76.08,
"end": 76.22,
"confidence": 0.898
},
{
"text": "problem.",
"start": 76.22,
"end": 76.56,
"confidence": 0.793
}
]
},
{
"id": 16,
"seek": 6000,
"start": 76.6,
"end": 77.8,
"text": " We'll let you know where they end up.",
"tokens": [
51194,
492,
603,
718,
291,
458,
689,
436,
917,
493,
13,
51259
],
"temperature": 0.4,
"avg_logprob": -0.6061306174741973,
"compression_ratio": 1.5876777251184835,
"no_speech_prob": 0.0662694051861763,
"confidence": 0.723,
"words": [
{
"text": "We'll",
"start": 76.6,
"end": 76.82,
"confidence": 0.834
},
{
"text": "let",
"start": 76.82,
"end": 76.96,
"confidence": 0.885
},
{
"text": "you",
"start": 76.96,
"end": 77.04,
"confidence": 0.764
},
{
"text": "know",
"start": 77.04,
"end": 77.2,
"confidence": 0.815
},
{
"text": "where",
"start": 77.2,
"end": 77.32,
"confidence": 0.6
},
{
"text": "they",
"start": 77.32,
"end": 77.42,
"confidence": 0.33
},
{
"text": "end",
"start": 77.42,
"end": 77.54,
"confidence": 0.787
},
{
"text": "up.",
"start": 77.54,
"end": 77.8,
"confidence": 0.905
}
]
},
{
"id": 17,
"seek": 6000,
"start": 77.94,
"end": 78.32,
"text": " Nice.",
"tokens": [
51259,
5490,
13,
51299
],
"temperature": 0.4,
"avg_logprob": -0.6061306174741973,
"compression_ratio": 1.5876777251184835,
"no_speech_prob": 0.0662694051861763,
"confidence": 0.495,
"words": [
{
"text": "Nice.",
"start": 77.94,
"end": 78.32,
"confidence": 0.495
}
]
}
],
"language": "en"
}