Automatic Speech Recognition
Safetensors
MLX
mlx-audio
whisper
speech-to-text
taigi
taiwanese-hokkien
min-nan-chinese
4-bit precision
Instructions to use RayyTien/Breeze-ASR-26-mlx-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use RayyTien/Breeze-ASR-26-mlx-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Breeze-ASR-26-mlx-4bit RayyTien/Breeze-ASR-26-mlx-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
| { | |
| "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 | |
| } | |