Automatic Speech Recognition
MLX
Safetensors
Chinese
English
qwen3_asr
asr
code-switching
thundertalk
Instructions to use Oulasong/ThunderTalk-ASR-0.6B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Oulasong/ThunderTalk-ASR-0.6B with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download Oulasong/ThunderTalk-ASR-0.6B --local-dir ThunderTalk-ASR-0.6B
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download preprocessor_config.json from Oulasong/ThunderTalk-ASR-0.6B: direct link, hf CLI and curl.
- Browser
- Download file 330 Bytes
-
https://huggingface.co/Oulasong/ThunderTalk-ASR-0.6B/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://Oulasong/ThunderTalk-ASR-0.6B/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/Oulasong/ThunderTalk-ASR-0.6B/resolve/main/preprocessor_config.json
330 Bytes
| { | |
| "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 | |
| } |