Automatic Speech Recognition
Safetensors
MLX
mlx-audio
qwen3_asr
apple-silicon
quantized
mixed-precision
axquant
axq
development
qwen3-asr
4bit
4-bit precision
v2
audio
speech-to-text
Instructions to use AutomatosX/AX-Qwen3-ASR-1.7B-MLX-AXQ-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AutomatosX/AX-Qwen3-ASR-1.7B-MLX-AXQ-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir AX-Qwen3-ASR-1.7B-MLX-AXQ-4bit AutomatosX/AX-Qwen3-ASR-1.7B-MLX-AXQ-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
| { | |
| "chunk_length": 30, | |
| "dither": 0.0, | |
| "feature_extractor_type": "WhisperFeatureExtractor", | |
| "feature_size": 128, | |
| "hop_length": 160, | |
| "n_fft": 400, | |
| "n_samples": 480000, | |
| "nb_max_frames": 3000, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "processor_class": "Qwen3ASRProcessor", | |
| "return_attention_mask": true | |
| } |