LLM/WhisperLiveKit
1
0
Fork 0
mirror of https://github.com/QuentinFuxa/WhisperLiveKit.git synced 2026-03-07 22:33:36 +00:00
Code Issues Packages Projects Releases Wiki Activity

fixes https://github.com/QuentinFuxa/WhisperLiveKit/issues/269

Browse Source
This commit is contained in:
Quentin Fuxa
2025-11-09 20:08:18 +01:00
parent a732e0903e
commit 7108d2ddc5
3 changed files with 38 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
docs/models_compatible_formats.md
View File

@@ -3,12 +3,14 @@
The `--model-path` parameter accepts:
## File Path
- **`.pt` format only** (required for AlignAtt policy decoder)
- **`.pt` / `.bin` / `.safetensor` formats** Should be openable by pytorch/safetensor.
## Directory Path (recommended)
Must contain:
- **`.pt` file** (required for decoder)
- **`.pt` / `.bin` / `.safetensor` file** (required for decoder)
May optionally contain:
- **`.bin` file** - faster-whisper model for encoder (requires faster-whisper)
- **`weights.npz`** or **`weights.safetensors`** - for encoder (requires whisper-mlx)
- **`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.