Automatic Speech Recognition
MLX
Safetensors
voxtral_realtime
voxtral
audio
speech
speech-recognition
realtime
streaming
asr
turboquant
quantization
8-bit precision
Instructions to use majentik/Voxtral-Mini-4B-Realtime-2602-TurboQuant-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-TurboQuant-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-TurboQuant-MLX-8bit majentik/Voxtral-Mini-4B-Realtime-2602-TurboQuant-MLX-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
File size: 135 Bytes
afee1dc | 1 2 3 4 | version https://git-lfs.github.com/spec/v1
oid sha256:a446bcafe1d3ea39414702f39bf8f25704e3d026c999ea4e7cd3b89b8761af04
size 4713828284
|