Automatic Speech Recognition
MLX
Safetensors
Chinese
English
qwen3_asr
mlx-audio
asr
streaming
confucius4
r2t2
8-bit precision
Instructions to use mlx-community/Confucius4-R2T2-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Confucius4-R2T2-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Confucius4-R2T2-8bit mlx-community/Confucius4-R2T2-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download generation_config.json from mlx-community/Confucius4-R2T2-8bit: direct link, hf CLI and curl.
- Browser
- Download file 142 Bytes
-
https://huggingface.co/mlx-community/Confucius4-R2T2-8bit/resolve/main/generation_config.json
- Command line
-
hf download hf://mlx-community/Confucius4-R2T2-8bit/generation_config.json
-
curl -L -o generation_config.json https://huggingface.co/mlx-community/Confucius4-R2T2-8bit/resolve/main/generation_config.json
142 Bytes
| { | |
| "_from_model_config": true, | |
| "eos_token_id": [151643,151645], | |
| "pad_token_id": 151643, | |
| "do_sample": false, | |
| "temperature": 0.000001 | |
| } |