Thai Whisper - Elderly Healthcare ASR
Fine-tuned Thonburian Whisper model for Thai elderly speech recognition in healthcare domains.
Performance
| Metric | Value |
|---|---|
| WER | 6.73% |
| CER | 1.01% |
Usage
from transformers import pipeline
pipe = pipeline("automatic-speech-recognition", model="xb2g/thai-whisper-elderly-healthcare")
result = pipe("audio.mp3", generate_kwargs={"language": "<|th|>"})
print(result["text"])