Fine-tuned large-v3 model does not transcribe non-English such as Chinese, Malay

[toanhuynhnguyen]

Based on this guide https://huggingface.co/blog/fine-tune-whisper, I tried to fine-tune "small" and "large-v3" models.

• The fine-tuned "small" model works normally.
• But the fine-tuned "large-v3" model works poorly on non-English audio files such as Chinese audio files, it auto-translates Chinese to English though I specified transcribing in Chinese, not translating.
  Have you faced this issue, and can you give me advice? Thank you so much.