ZacharyZhang-NY
5289cb4b01
An audio file used to produce no memory at all: _ingest_file returned an empty batch for any suffix it did not know, with no log and no reason. It now raises UnsupportedFile when you name the file and records a SkippedFile when it was a directory walk, so a refusal is visible either way. Speech is measured, not promised. Over 210.5 seconds of real Video-MME audio, faster-whisper-tiny on CPU int8 transcribed at 51x realtime and reached word error rate 0.242 against community subtitles nobody here wrote (a caption track drops words a transcript keeps, so that is an upper bound). 66 speech atoms now carry 550 word-level timestamps, 0 words out of order and 0 starting before their own segment. The snapshot is 78.2 MB, under the 500 MB cap, and the report is bench/reports/ASR.md. Two library facts were measured rather than assumed. faster-whisper's own audio loader is broken against PyAV 19 (av.open got an unexpected keyword 'metadata_errors') and it declares av with no version bound, so asr.decode_audio decodes with PyAV directly and hands the model a float32 array instead of pinning an old av with no cp314 wheel. And av.Error does not exist on PyAV 19 - the real base is av.error.FFmpegError - so that is the only thing caught and my own ValueErrors keep their messages. Files over the 500-line rule were split rather than excused: ingestion.py (748) into ingestion_common / ingestion_media / ingestion_repository / ingestion, and cli.py (544) into cli_senses plus cli_common, following the cli_transactive register pattern. MediaIngest declares _source_record abstract, so a half-wired host fails at construction instead of returning None. Verification: 207 tests pass; ruff clean on the 13 touched files; mypy clean on them, and repo-wide mypy fell from 29 errors to 24 (5 fixed, none added); pyright reports 0 errors on the touched files.
80 lines
2.0 KiB
JSON
80 lines
2.0 KiB
JSON
{
|
|
"generated_utc": "2026-10-08T01:05:45+00:00",
|
|
"commit": "03ca35763fd63eb8d8f0d2c721d02c6c3ded90a7",
|
|
"model": {
|
|
"id": "Systran/faster-whisper-tiny",
|
|
"sha256_model_bin": "dcb76c6586fc06cbdac6dd21f14cfd129cc4cdd9dce19bf4ffa62e59cbe6e6d1",
|
|
"compute": "cpu int8"
|
|
},
|
|
"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": [
|
|
1.84,
|
|
1.85,
|
|
6.99
|
|
]
|
|
},
|
|
"totals": {
|
|
"videos": 3,
|
|
"audio_seconds": 210.5,
|
|
"word_error_rate": 0.242,
|
|
"speech_atoms": 66,
|
|
"words": 550,
|
|
"out_of_order": 0,
|
|
"before_their_segment": 0
|
|
},
|
|
"videos": [
|
|
{
|
|
"video": "0IdYJGBmguM",
|
|
"seconds": 88.9,
|
|
"transcribe_seconds": 1.73,
|
|
"real_time_factor": 51.3,
|
|
"segments": 31,
|
|
"speech_atoms": 31,
|
|
"modality": "audio",
|
|
"hypothesis_words": 218,
|
|
"reference_words": 201,
|
|
"word_error_rate": 0.179,
|
|
"mean_word_confidence": 0.879,
|
|
"words": 218,
|
|
"out_of_order": 0,
|
|
"before_their_segment": 0
|
|
},
|
|
{
|
|
"video": "1q-5IIyZL20",
|
|
"seconds": 99.9,
|
|
"transcribe_seconds": 1.94,
|
|
"real_time_factor": 51.6,
|
|
"segments": 32,
|
|
"speech_atoms": 32,
|
|
"modality": "audio",
|
|
"hypothesis_words": 300,
|
|
"reference_words": 296,
|
|
"word_error_rate": 0.28,
|
|
"mean_word_confidence": 0.83,
|
|
"words": 300,
|
|
"out_of_order": 0,
|
|
"before_their_segment": 0
|
|
},
|
|
{
|
|
"video": "1tidNDIpKSY",
|
|
"seconds": 21.7,
|
|
"transcribe_seconds": 1.34,
|
|
"real_time_factor": 16.1,
|
|
"segments": 3,
|
|
"speech_atoms": 3,
|
|
"modality": "audio",
|
|
"hypothesis_words": 32,
|
|
"reference_words": 36,
|
|
"word_error_rate": 0.278,
|
|
"mean_word_confidence": 0.852,
|
|
"words": 32,
|
|
"out_of_order": 0,
|
|
"before_their_segment": 0
|
|
}
|
|
]
|
|
} |