Automatic Speech Recognition
Transformers
Safetensors
Chinese
Yue Chinese
English
qwen3_asr
asr
speech-recognition
chinese
dialect
qwen3-asr
audio
Instructions to use ASLP-lab/CN-MultiDialect-ASR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ASLP-lab/CN-MultiDialect-ASR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ASLP-lab/CN-MultiDialect-ASR")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("ASLP-lab/CN-MultiDialect-ASR") model = AutoModelForMultimodalLM.from_pretrained("ASLP-lab/CN-MultiDialect-ASR", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download trainer_state.json from ASLP-lab/CN-MultiDialect-ASR: direct link, hf CLI and curl.
- Browser
- Download file 733 kB
-
https://huggingface.co/ASLP-lab/CN-MultiDialect-ASR/resolve/main/trainer_state.json
- Command line
-
hf download hf://ASLP-lab/CN-MultiDialect-ASR/trainer_state.json
-
curl -L -o trainer_state.json https://huggingface.co/ASLP-lab/CN-MultiDialect-ASR/resolve/main/trainer_state.json
733 kB
File too large to display, you can check the raw version instead.