| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| faster-whisper 1.0.3 source code.tar.gz | 2024-07-01 | 17.1 MB | |
| faster-whisper 1.0.3 source code.zip | 2024-07-01 | 17.2 MB | |
| README.md | 2024-07-01 | 719 Bytes | |
| Totals: 3 Items | 34.3 MB | 0 | |
Upgrade Silero-Vad model to latest V5 version (https://github.com/SYSTRAN/faster-whisper/pull/884)
Silero-vad V5 release: https://github.com/snakers4/silero-vad/releases/tag/v5.0
- window_size_samples parameter is fixed at 512.
- Change to use the state variable instead of the existing h and c variables.
- Slightly changed internal logic, now some context (part of previous chunk) is passed along with the current chunk.
- Change the dimensions of the state variable from 64 to 128.
- Replace ONNX file with V5 version
Other changes
- Improve language detection when using clip_timestamps (#867)
- Docker file improvements (#848)
- Fix [#839] incorrect clip_timestamps being used in model (#842)