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-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JacobLinCool/TEA-ASR-1.1-mini 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-mini")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("JacobLinCool/TEA-ASR-1.1-mini") model = AutoModelForMultimodalLM.from_pretrained("JacobLinCool/TEA-ASR-1.1-mini") - Notebooks
- Google Colab
- Kaggle
TEA-ASR-1.1-mini refresh to v27: code-switch upgrade (ASCEND 11.20, CSZS 12.51, CV19 5.12) + format-tag support; recipe-consistent with TEA-ASR-1.1
d172201 verified | { | |
| "base": "Qwen/Qwen3-ASR-0.6B", | |
| "adapter": "outputs/tea11_v27_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 | |
| } | |
| } | |