Audio Classification
MLX
Safetensors
qwen3_asr
forced-alignment
speech
qwen3
audio
timestamps
4bit
quantized
Instructions to use aitytech/Qwen3-ForcedAligner-0.6B-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use aitytech/Qwen3-ForcedAligner-0.6B-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Qwen3-ForcedAligner-0.6B-4bit aitytech/Qwen3-ForcedAligner-0.6B-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
| { | |
| "quantization": { | |
| "group_size": 64, | |
| "bits": 4, | |
| "quantized_components": [ | |
| "text_decoder" | |
| ], | |
| "float_components": [ | |
| "audio_encoder", | |
| "classify_head", | |
| "norms" | |
| ] | |
| } | |
| } |