ZacharyZhang-NY
2fa91abbc5
The report is regenerated after 10a39c5 so its stamp names the code it
describes. Speed is quoted as a range in the checklist because transcribe
seconds move with machine load (3.26s then 3.12s on this box) while WER,
denominators and word counts do not move at all.
Numbers: 258.18s of audio, WER 0.242 over 533 reference words, 80 audio atoms
and 563 word timestamps read back from the store, 0 out of order and 0 before
their own segment measured on the stored words.
118 lines
2.8 KiB
JSON
118 lines
2.8 KiB
JSON
{
|
|
"generated_utc": "2026-10-08T02:37:10+00:00",
|
|
"commit": "10a39c5125ebaf73e0ff7174b3af7af4c32bcf05",
|
|
"model": {
|
|
"id": "Systran/faster-whisper-tiny",
|
|
"sha256_model_bin": "dcb76c6586fc06cbdac6dd21f14cfd129cc4cdd9dce19bf4ffa62e59cbe6e6d1",
|
|
"compute": "cpu int8",
|
|
"cpu_threads": 4,
|
|
"decode_knobs": {
|
|
"word_timestamps": "True",
|
|
"beam_size": "1",
|
|
"temperature": "(0.0,)",
|
|
"condition_on_previous_text": "False",
|
|
"vad_filter": "False"
|
|
}
|
|
},
|
|
"reference": "Video-MME community subtitles: third-party captions, not verbatim transcripts",
|
|
"machine": {
|
|
"system": "Linux",
|
|
"release": "6.18.40.1-microsoft-standard-WSL2",
|
|
"cpus": 32,
|
|
"threads_per_query": 4,
|
|
"load_average_1_5_15": [
|
|
7.73,
|
|
2.66,
|
|
1.58
|
|
]
|
|
},
|
|
"passes": {
|
|
"count": 2,
|
|
"word_error_rate": [
|
|
0.242,
|
|
0.242
|
|
],
|
|
"identical_transcripts": true,
|
|
"per_video_wer": [
|
|
{
|
|
"video": "0IdYJGBmguM",
|
|
"first": 0.229,
|
|
"second": 0.229
|
|
},
|
|
{
|
|
"video": "1q-5IIyZL20",
|
|
"first": 0.253,
|
|
"second": 0.253
|
|
},
|
|
{
|
|
"video": "1tidNDIpKSY",
|
|
"first": 0.222,
|
|
"second": 0.222
|
|
}
|
|
]
|
|
},
|
|
"totals": {
|
|
"videos": 3,
|
|
"audio_seconds": 258.18,
|
|
"transcribe_seconds": 3.12,
|
|
"word_error_rate": 0.242,
|
|
"reference_words": 533,
|
|
"hypothesis_words": 563,
|
|
"words": 563,
|
|
"out_of_order": 0,
|
|
"before_their_segment": 0,
|
|
"atoms_all": 133,
|
|
"speech_atoms": 80,
|
|
"word_timestamps": 563,
|
|
"sources": 3,
|
|
"out_of_order_in_store": 0,
|
|
"before_their_segment_in_store": 0
|
|
},
|
|
"videos": [
|
|
{
|
|
"video": "0IdYJGBmguM",
|
|
"seconds": 88.93,
|
|
"transcribe_seconds": 1.3,
|
|
"real_time_factor": 68.4,
|
|
"segments": 38,
|
|
"reference_words": 201,
|
|
"hypothesis_words": 219,
|
|
"edits": 46,
|
|
"word_error_rate": 0.229,
|
|
"mean_word_confidence": 0.861,
|
|
"words": 219,
|
|
"out_of_order": 0,
|
|
"before_their_segment": 0
|
|
},
|
|
{
|
|
"video": "1q-5IIyZL20",
|
|
"seconds": 109.18,
|
|
"transcribe_seconds": 1.28,
|
|
"real_time_factor": 85.4,
|
|
"segments": 39,
|
|
"reference_words": 296,
|
|
"hypothesis_words": 313,
|
|
"edits": 75,
|
|
"word_error_rate": 0.253,
|
|
"mean_word_confidence": 0.821,
|
|
"words": 313,
|
|
"out_of_order": 0,
|
|
"before_their_segment": 0
|
|
},
|
|
{
|
|
"video": "1tidNDIpKSY",
|
|
"seconds": 60.07,
|
|
"transcribe_seconds": 0.54,
|
|
"real_time_factor": 111.2,
|
|
"segments": 3,
|
|
"reference_words": 36,
|
|
"hypothesis_words": 31,
|
|
"edits": 8,
|
|
"word_error_rate": 0.222,
|
|
"mean_word_confidence": 0.852,
|
|
"words": 31,
|
|
"out_of_order": 0,
|
|
"before_their_segment": 0
|
|
}
|
|
]
|
|
} |