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 tokenizer.json from mlx-community/Confucius4-R2T2-8bit: direct link, hf CLI and curl.
- Browser
- Download file 11.4 MB
-
https://huggingface.co/mlx-community/Confucius4-R2T2-8bit/resolve/main/tokenizer.json
- Command line
-
hf download hf://mlx-community/Confucius4-R2T2-8bit/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/mlx-community/Confucius4-R2T2-8bit/resolve/main/tokenizer.json
11.4 MB
- Xet hash:
- 19b7109665b15805068c57b005ab01638ae2321dc9ac6ed3fc4356134a4d1c1c
- Size of remote file:
- 11.4 MB
- SHA256:
- 0499602714160467f2d68b910651d6216020689f1e016be87a2d0019ee3baeab
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.