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 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use JacobLinCool/TEA-ASR-1 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="JacobLinCool/TEA-ASR-1")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("JacobLinCool/TEA-ASR-1") model = AutoModelForMultimodalLM.from_pretrained("JacobLinCool/TEA-ASR-1", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
model card: fresh-eval numbers + protocol
Verified signature04ce27d -
model card: fresh-eval numbers + protocol
Verified signature961d21d -
model card: fresh-eval numbers + protocol
Verified signature7f12bb8 -
model card: fresh-eval numbers + protocol
Verified signature4f34285 -
figures: shorter labels
Verified signature8f811a1 -
figures: shorter labels
Verified signatureca23e97 -
card: + speed/VRAM table + figures
Verified signature7c49fda -
card: + speed/VRAM table + figures
Verified signature460590e -
card: + speed/VRAM table + figures
Verified signature82e7c3b -
card: + speed/VRAM table + figures
Verified signature0df59ee -
TEA-ASR clean leak-free release: merged weights + decorated tokenizer + fresh-eval card
Verified signature3a87a39 -
initial commit
Verified signaturedeeb57c