Automatic Speech Recognition
MLX
Safetensors
voxtral_realtime
voxtral
audio
speech
speech-recognition
realtime
streaming
asr
rotorquant
quantization
8-bit precision
Instructions to use majentik/Voxtral-Mini-4B-Realtime-2602-RotorQuant-MLX-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use majentik/Voxtral-Mini-4B-Realtime-2602-RotorQuant-MLX-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Voxtral-Mini-4B-Realtime-2602-RotorQuant-MLX-8bit majentik/Voxtral-Mini-4B-Realtime-2602-RotorQuant-MLX-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio