Hugging Face's logo

kullup
/
whisper-timestamped

Transformers
English
speech-recognition
ai-model
whisper
dynamic-time-warping
Eval Results
Model card Files
xet
Community
whisper-timestamped / tests /expected /corner_cases /issue24_empty.wav.words.json
kullup's picture
kullup
Upload 187 files
9480b39 verified
raw
history blame contribute delete
19.9 kB
 {
"text": " I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry. I'm sorry.",
"segments": [
{
"id": 0,
"seek": 0,
"start": 0.0,
"end": 0.96,
"text": " I'm sorry.",
"tokens": [
50363,
314,
1101,
7926,
13,
50413
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.102,
"words": [
{
"text": "I'm",
"start": 0.0,
"end": 0.94,
"confidence": 0.105
},
{
"text": "sorry",
"start": 0.94,
"end": 0.96,
"confidence": 0.097
}
]
},
{
"id": 1,
"seek": 0,
"start": 0.96,
"end": 2.38,
"text": " I'm sorry.",
"tokens": [
50413,
314,
1101,
7926,
13,
50463
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.406,
"words": [
{
"text": "I'm",
"start": 0.96,
"end": 2.26,
"confidence": 0.355
},
{
"text": "sorry",
"start": 2.26,
"end": 2.38,
"confidence": 0.534
}
]
},
{
"id": 2,
"seek": 0,
"start": 2.38,
"end": 2.42,
"text": " I'm sorry.",
"tokens": [
50463,
314,
1101,
7926,
13,
50513
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.612,
"words": [
{
"text": "I'm",
"start": 2.38,
"end": 2.4,
"confidence": 0.552
},
{
"text": "sorry",
"start": 2.4,
"end": 2.42,
"confidence": 0.753
}
]
},
{
"id": 3,
"seek": 0,
"start": 3.0,
"end": 3.24,
"text": " I'm sorry.",
"tokens": [
50513,
314,
1101,
7926,
13,
50563
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.765,
"words": [
{
"text": "I'm",
"start": 3.0,
"end": 3.22,
"confidence": 0.714
},
{
"text": "sorry",
"start": 3.22,
"end": 3.24,
"confidence": 0.877
}
]
},
{
"id": 4,
"seek": 0,
"start": 4.36,
"end": 4.48,
"text": " I'm sorry.",
"tokens": [
50563,
314,
1101,
7926,
13,
50613
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.849,
"words": [
{
"text": "I'm",
"start": 4.36,
"end": 4.42,
"confidence": 0.804
},
{
"text": "sorry",
"start": 4.42,
"end": 4.48,
"confidence": 0.947
}
]
},
{
"id": 5,
"seek": 0,
"start": 5.5,
"end": 5.78,
"text": " I'm sorry.",
"tokens": [
50613,
314,
1101,
7926,
13,
50663
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.89,
"words": [
{
"text": "I'm",
"start": 5.5,
"end": 5.54,
"confidence": 0.852
},
{
"text": "sorry",
"start": 5.54,
"end": 5.78,
"confidence": 0.972
}
]
},
{
"id": 6,
"seek": 0,
"start": 5.92,
"end": 6.8,
"text": " I'm sorry.",
"tokens": [
50663,
314,
1101,
7926,
13,
50713
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.918,
"words": [
{
"text": "I'm",
"start": 5.92,
"end": 6.14,
"confidence": 0.888
},
{
"text": "sorry",
"start": 6.14,
"end": 6.8,
"confidence": 0.983
}
]
},
{
"id": 7,
"seek": 0,
"start": 7.5,
"end": 8.5,
"text": " I'm sorry.",
"tokens": [
50713,
314,
1101,
7926,
13,
50763
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.941,
"words": [
{
"text": "I'm",
"start": 7.5,
"end": 8.48,
"confidence": 0.919
},
{
"text": "sorry",
"start": 8.48,
"end": 8.5,
"confidence": 0.988
}
]
},
{
"id": 8,
"seek": 0,
"start": 8.56,
"end": 9.48,
"text": " I'm sorry.",
"tokens": [
50763,
314,
1101,
7926,
13,
50813
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.95,
"words": [
{
"text": "I'm",
"start": 8.56,
"end": 9.0,
"confidence": 0.93
},
{
"text": "sorry",
"start": 9.0,
"end": 9.48,
"confidence": 0.991
}
]
},
{
"id": 9,
"seek": 0,
"start": 9.54,
"end": 10.38,
"text": " I'm sorry.",
"tokens": [
50813,
314,
1101,
7926,
13,
50863
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.963,
"words": [
{
"text": "I'm",
"start": 9.54,
"end": 9.56,
"confidence": 0.948
},
{
"text": "sorry",
"start": 9.56,
"end": 10.38,
"confidence": 0.993
}
]
},
{
"id": 10,
"seek": 0,
"start": 10.38,
"end": 11.36,
"text": " I'm sorry.",
"tokens": [
50863,
314,
1101,
7926,
13,
50913
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.968,
"words": [
{
"text": "I'm",
"start": 10.38,
"end": 11.34,
"confidence": 0.955
},
{
"text": "sorry",
"start": 11.34,
"end": 11.36,
"confidence": 0.994
}
]
},
{
"id": 11,
"seek": 0,
"start": 11.36,
"end": 12.48,
"text": " I'm sorry.",
"tokens": [
50913,
314,
1101,
7926,
13,
50963
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.977,
"words": [
{
"text": "I'm",
"start": 11.36,
"end": 12.06,
"confidence": 0.969
},
{
"text": "sorry",
"start": 12.06,
"end": 12.48,
"confidence": 0.996
}
]
},
{
"id": 12,
"seek": 0,
"start": 12.54,
"end": 12.93,
"text": " I'm sorry.",
"tokens": [
50963,
314,
1101,
7926,
13,
51013
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.979,
"words": [
{
"text": "I'm",
"start": 12.54,
"end": 12.56,
"confidence": 0.971
},
{
"text": "sorry",
"start": 12.56,
"end": 12.93,
"confidence": 0.996
}
]
},
{
"id": 13,
"seek": 0,
"start": 12.93,
"end": 14.5,
"text": " I'm sorry.",
"tokens": [
51013,
314,
1101,
7926,
13,
51063
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.979,
"words": [
{
"text": "I'm",
"start": 12.93,
"end": 14.48,
"confidence": 0.971
},
{
"text": "sorry",
"start": 14.48,
"end": 14.5,
"confidence": 0.996
}
]
},
{
"id": 14,
"seek": 0,
"start": 14.5,
"end": 15.46,
"text": " I'm sorry.",
"tokens": [
51063,
314,
1101,
7926,
13,
51113
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.982,
"words": [
{
"text": "I'm",
"start": 14.5,
"end": 15.42,
"confidence": 0.974
},
{
"text": "sorry",
"start": 15.42,
"end": 15.46,
"confidence": 0.996
}
]
},
{
"id": 15,
"seek": 0,
"start": 15.46,
"end": 16.48,
"text": " I'm sorry.",
"tokens": [
51113,
314,
1101,
7926,
13,
51163
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.983,
"words": [
{
"text": "I'm",
"start": 15.46,
"end": 16.38,
"confidence": 0.976
},
{
"text": "sorry",
"start": 16.38,
"end": 16.48,
"confidence": 0.997
}
]
},
{
"id": 16,
"seek": 0,
"start": 16.48,
"end": 17.5,
"text": " I'm sorry.",
"tokens": [
51163,
314,
1101,
7926,
13,
51213
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.982,
"words": [
{
"text": "I'm",
"start": 16.48,
"end": 17.48,
"confidence": 0.974
},
{
"text": "sorry",
"start": 17.48,
"end": 17.5,
"confidence": 0.997
}
]
},
{
"id": 17,
"seek": 0,
"start": 17.54,
"end": 18.5,
"text": " I'm sorry.",
"tokens": [
51213,
314,
1101,
7926,
13,
51263
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.984,
"words": [
{
"text": "I'm",
"start": 17.54,
"end": 18.48,
"confidence": 0.978
},
{
"text": "sorry",
"start": 18.48,
"end": 18.5,
"confidence": 0.997
}
]
},
{
"id": 18,
"seek": 0,
"start": 18.5,
"end": 19.48,
"text": " I'm sorry.",
"tokens": [
51263,
314,
1101,
7926,
13,
51313
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.984,
"words": [
{
"text": "I'm",
"start": 18.5,
"end": 19.34,
"confidence": 0.978
},
{
"text": "sorry",
"start": 19.34,
"end": 19.48,
"confidence": 0.997
}
]
},
{
"id": 19,
"seek": 0,
"start": 19.64,
"end": 20.32,
"text": " I'm sorry.",
"tokens": [
51313,
314,
1101,
7926,
13,
51363
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.986,
"words": [
{
"text": "I'm",
"start": 19.64,
"end": 19.68,
"confidence": 0.98
},
{
"text": "sorry",
"start": 19.68,
"end": 20.32,
"confidence": 0.997
}
]
},
{
"id": 20,
"seek": 0,
"start": 20.32,
"end": 20.36,
"text": " I'm sorry.",
"tokens": [
51363,
314,
1101,
7926,
13,
51413
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.986,
"words": [
{
"text": "I'm",
"start": 20.32,
"end": 20.34,
"confidence": 0.98
},
{
"text": "sorry",
"start": 20.34,
"end": 20.36,
"confidence": 0.997
}
]
},
{
"id": 21,
"seek": 0,
"start": 21.58,
"end": 22.5,
"text": " I'm sorry.",
"tokens": [
51413,
314,
1101,
7926,
13,
51463
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.988,
"words": [
{
"text": "I'm",
"start": 21.58,
"end": 22.48,
"confidence": 0.983
},
{
"text": "sorry",
"start": 22.48,
"end": 22.5,
"confidence": 0.997
}
]
},
{
"id": 22,
"seek": 0,
"start": 22.58,
"end": 23.46,
"text": " I'm sorry.",
"tokens": [
51463,
314,
1101,
7926,
13,
51513
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.987,
"words": [
{
"text": "I'm",
"start": 22.58,
"end": 22.6,
"confidence": 0.982
},
{
"text": "sorry",
"start": 22.6,
"end": 23.46,
"confidence": 0.997
}
]
},
{
"id": 23,
"seek": 0,
"start": 23.46,
"end": 23.7,
"text": " I'm sorry.",
"tokens": [
51513,
314,
1101,
7926,
13,
51563
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.988,
"words": [
{
"text": "I'm",
"start": 23.46,
"end": 23.48,
"confidence": 0.984
},
{
"text": "sorry",
"start": 23.48,
"end": 23.7,
"confidence": 0.997
}
]
},
{
"id": 24,
"seek": 0,
"start": 24.5,
"end": 24.54,
"text": " I'm sorry.",
"tokens": [
51563,
314,
1101,
7926,
13,
51613
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.988,
"words": [
{
"text": "I'm",
"start": 24.5,
"end": 24.52,
"confidence": 0.984
},
{
"text": "sorry",
"start": 24.52,
"end": 24.54,
"confidence": 0.998
}
]
},
{
"id": 25,
"seek": 0,
"start": 24.54,
"end": 26.48,
"text": " I'm sorry.",
"tokens": [
51613,
314,
1101,
7926,
13,
51663
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.986,
"words": [
{
"text": "I'm",
"start": 24.54,
"end": 26.26,
"confidence": 0.98
},
{
"text": "sorry",
"start": 26.26,
"end": 26.48,
"confidence": 0.998
}
]
},
{
"id": 26,
"seek": 0,
"start": 26.48,
"end": 27.5,
"text": " I'm sorry.",
"tokens": [
51663,
314,
1101,
7926,
13,
51713
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.982,
"words": [
{
"text": "I'm",
"start": 26.48,
"end": 27.48,
"confidence": 0.975
},
{
"text": "sorry",
"start": 27.48,
"end": 27.5,
"confidence": 0.998
}
]
},
{
"id": 27,
"seek": 0,
"start": 27.5,
"end": 28.46,
"text": " I'm sorry.",
"tokens": [
51713,
314,
1101,
7926,
13,
51763
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.975,
"words": [
{
"text": "I'm",
"start": 27.5,
"end": 28.44,
"confidence": 0.964
},
{
"text": "sorry",
"start": 28.44,
"end": 28.46,
"confidence": 0.998
}
]
},
{
"id": 28,
"seek": 0,
"start": 28.46,
"end": 29.32,
"text": " I'm sorry.",
"tokens": [
51763,
314,
1101,
7926,
13,
51813
],
"temperature": 0.0,
"avg_logprob": -0.12360930442810059,
"compression_ratio": 13.25,
"no_speech_prob": 0.7654247283935547,
"confidence": 0.954,
"words": [
{
"text": "I'm",
"start": 28.46,
"end": 29.3,
"confidence": 0.933
},
{
"text": "sorry",
"start": 29.3,
"end": 29.32,
"confidence": 0.998
}
]
}
],
"language": "en"
}