Automatic Speech Recognition
Safetensors
MLX
mlx-audio
qwen3_asr
speech-to-text
speech
transcription
asr
stt
Instructions to use runfuture/Mega-ASR-MLX-FP16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use runfuture/Mega-ASR-MLX-FP16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Mega-ASR-MLX-FP16 runfuture/Mega-ASR-MLX-FP16
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
Mega-ASR MLX FP16
This is a private MLX conversion of zhifeixie/Mega-ASR.
The checkpoint was produced by merging the mega-asr-merged LoRA adapter from
zhifeixie/Mega-ASR into the bundled Qwen3-ASR-1.7B base checkpoint, then
converting the merged weights to the mlx-audio Qwen3-ASR layout.
Conversion
- Base/source repo:
zhifeixie/Mega-ASR - Adapter:
mega-asr-merged - Format: MLX /
mlx-audio - Precision: FP16
Use With mlx-audio
pip install -U mlx-audio
python -m mlx_audio.stt.generate --model runfuture/Mega-ASR-MLX-FP16 --audio audio.wav
- Downloads last month
- 2
Model size
2B params
Tensor type
F16
·
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for runfuture/Mega-ASR-MLX-FP16
Base model
zhifeixie/Mega-ASR