ThePlasmak d02a385363 feat: precise word timestamps via wav2vec2 forced alignment (--precise) ...

- Add --precise flag for wav2vec2 forced alignment (~10ms word accuracy)
- Uses torchaudio MMS model (multilingual, 1000+ languages)
- Model cached across files for efficient batch processing
- Runs before diarization when both flags used (improves speaker assignment)
- Auto-enables word timestamps when --precise is set
- Graceful fallback: segments with unsupported chars keep original timestamps
- Install torchaudio alongside torch in setup.sh
- Update SKILL.md with --precise documentation and agent guidance

2026-02-17 18:46:23 +08:00

..

transcribe

Reorganize README: features, setup, usage, cross-platform

2026-01-28 21:10:14 +08:00

transcribe.cmd

Reorganize README: features, setup, usage, cross-platform

2026-01-28 21:10:14 +08:00

transcribe.ps1

Reorganize README: features, setup, usage, cross-platform

2026-01-28 21:10:14 +08:00

transcribe.py

feat: precise word timestamps via wav2vec2 forced alignment (--precise)

2026-02-17 18:46:23 +08:00