Automatic Speech Recognition
Safetensors
MLX
mlx-audio-plus
whisper
speech-recognition
speech-to-text
stt
Instructions to use mlx-community/whisper-large-v3-fp16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/whisper-large-v3-fp16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/whisper-large-v3-fp16 --local-dir whisper-large-v3-fp16
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download config.json from mlx-community/whisper-large-v3-fp16: direct link, hf CLI and curl.
- Browser
- Download file 269 Bytes
-
https://huggingface.co/mlx-community/whisper-large-v3-fp16/resolve/main/config.json
- Command line
-
hf download hf://mlx-community/whisper-large-v3-fp16/config.json
-
curl -L -o config.json https://huggingface.co/mlx-community/whisper-large-v3-fp16/resolve/main/config.json
269 Bytes
| { | |
| "n_mels": 128, | |
| "n_audio_ctx": 1500, | |
| "n_audio_state": 1280, | |
| "n_audio_head": 20, | |
| "n_audio_layer": 32, | |
| "n_vocab": 51866, | |
| "n_text_ctx": 448, | |
| "n_text_state": 1280, | |
| "n_text_head": 20, | |
| "n_text_layer": 32, | |
| "model_type": "whisper" | |
| } |