Automatic Speech Recognition
MLX
Safetensors
voxtral_realtime
mlx-audio
speech-to-text
streaming
realtime
voxtral
4-bit precision
Instructions to use iris-sfg/Voxtral-Mini-4B-Realtime-2602-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use iris-sfg/Voxtral-Mini-4B-Realtime-2602-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Voxtral-Mini-4B-Realtime-2602-4bit iris-sfg/Voxtral-Mini-4B-Realtime-2602-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "feature_extractor": { | |
| "feature_extractor_type": "VoxtralRealtimeFeatureExtractor", | |
| "feature_size": 128, | |
| "global_log_mel_max": 1.5, | |
| "hop_length": 160, | |
| "n_fft": 400, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000, | |
| "win_length": 400 | |
| }, | |
| "processor_class": "VoxtralRealtimeProcessor" | |
| } | |