Automatic Speech Recognition
MLX
whisper
mlx-whisper
taiwanese-hokkien
taigi
zh
nan
4-bit precision
quantized
Instructions to use doggy8088/Breeze-ASR-26-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use doggy8088/Breeze-ASR-26-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download doggy8088/Breeze-ASR-26-MLX-4bit --local-dir Breeze-ASR-26-MLX-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download preprocessor_config.json from doggy8088/Breeze-ASR-26-MLX-4bit: direct link, hf CLI and curl.
- Browser
- Download file 339 Bytes
-
https://huggingface.co/doggy8088/Breeze-ASR-26-MLX-4bit/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://doggy8088/Breeze-ASR-26-MLX-4bit/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/doggy8088/Breeze-ASR-26-MLX-4bit/resolve/main/preprocessor_config.json
339 Bytes
| { | |
| "chunk_length": 30, | |
| "feature_extractor_type": "WhisperFeatureExtractor", | |
| "feature_size": 80, | |
| "hop_length": 160, | |
| "n_fft": 400, | |
| "n_samples": 480000, | |
| "nb_max_frames": 3000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "processor_class": "WhisperProcessor", | |
| "return_attention_mask": false, | |
| "sampling_rate": 16000 | |
| } | |