LLM/WhisperLiveKit
1
0
Fork 0
mirror of https://github.com/QuentinFuxa/WhisperLiveKit.git synced 2026-03-07 14:23:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

hf compatibility

Browse Source
This commit is contained in:
Quentin Fuxa
2025-11-15 18:34:19 +01:00
parent 8d9be88fe6
commit d310f7e25f
5 changed files with 188 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
docs/models_compatible_formats.md
View File

@@ -13,4 +13,7 @@ May optionally contain:
- **`.bin` file** - faster-whisper model for encoder (requires faster-whisper)
- **`weights.npz`** or **`weights.safetensors`** - for encoder (requires whisper-mlx)
To improve speed/reduce allucinations, you may want to use `scripts/determine_alignment_heads.py` to determine the alignment heads to use for your model, and use the `--custom-alignment-heads` to pass them to WLK. If not, alignement heads are set to be all the heads of the last half layer of decoder.
## Hugging Face Repo ID
- Provide the repo ID (e.g. `openai/whisper-large-v3`) and WhisperLiveKit will download and cache the snapshot automatically. For gated repos, authenticate via `huggingface-cli login` first.
To improve speed/reduce allucinations, you may want to use `scripts/determine_alignment_heads.py` to determine the alignment heads to use for your model, and use the `--custom-alignment-heads` to pass them to WLK. If not, alignement heads are set to be all the heads of the last half layer of decoder.