Automatic Speech Recognition
Transformers
Safetensors
Chinese
English
qwen3_asr
taiwan-mandarin
traditional-chinese
code-switching
qwen3-asr
speech
Instructions to use JacobLinCool/TEA-ASR-1.1-fmt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JacobLinCool/TEA-ASR-1.1-fmt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="JacobLinCool/TEA-ASR-1.1-fmt", device_map="auto")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("JacobLinCool/TEA-ASR-1.1-fmt") model = AutoModelForMultimodalLM.from_pretrained("JacobLinCool/TEA-ASR-1.1-fmt", device_map="auto") - Notebooks
- Google Colab
- Kaggle
TEA-ASR-1.1-fmt release: format-controllable variant (fused drop-in, dial verified on this artifact)
99fcb48 verified | { | |
| "base": "Qwen/Qwen3-ASR-1.7B", | |
| "adapter": "outputs/tea11_17b_v7_a070_r_s0", | |
| "selected_row_delta": null, | |
| "selected_row_summary": null, | |
| "decode_config": "s2tw", | |
| "tokenizer_stats": { | |
| "clean": 150482, | |
| "marked": 1161, | |
| "merges": [ | |
| 151387, | |
| 138969 | |
| ] | |
| }, | |
| "verification": { | |
| "checked_sequences": 152643, | |
| "decode_mismatches": 0, | |
| "sentinel_leaks": 0, | |
| "examples": [], | |
| "is_fast": true | |
| } | |
| } | |