Belle Whisper Large V3 Turbo Zh

🚀 Belle-whisper-large-v3-turbo-zh

Fine-tune the whisper-large-v3-turbo-zh model to enhance Chinese speech recognition capabilities, achieving a 24 - 64% relative performance improvement on Chinese ASR benchmarks.

🚀 Quick Start

If you find this model helpful, please like this model and star us on GitHub and GitHub.

✨ Features

• Fine tune whisper-large-v3-turbo-zh to enhance Chinese speech recognition capabilities.
• Demonstrate a 24 - 64% relative improvement in performance to whisper-large-v3-turbo on Chinese ASR benchmarks, including AISHELL1, AISHELL2, WENETSPEECH, and HKUST.
• Similar to Belle-whisper-large-v3-zh-punct, the punctuation marks come from the model punc_ct-transformer_cn-en-common-vocab471067-large and are added to the training datasets.

💻 Usage Examples

Basic Usage

from transformers import pipeline

transcriber = pipeline(
  "automatic-speech-recognition", 
  model="BELLE-2/Belle-whisper-large-v3-turbo-zh"
)

transcriber.model.config.forced_decoder_ids = (
  transcriber.tokenizer.get_decoder_prompt_ids(
    language="zh", 
    task="transcribe"
  )
)

transcription = transcriber("my_audio.wav") 

📚 Documentation

Fine-tuning

If you want to fine-tune the model on your datasets, please refer to the GitHub repo.

CER(%) ↓

It's worth noting that Belle-whisper-large-v3-turbo-zh shows significant improvements compared to whisper-large-v3 and whisper-large-v3-turbo.

📄 License

This project is licensed under the Apache-2.0 license.

📚 Citation

Please cite our paper and GitHub when using our code, data, or model.

@misc{BELLE,
  author = {BELLEGroup},
  title = {BELLE: Be Everyone's Large Language model Engine},
  year = {2023},
  publisher = {GitHub},
  journal = {GitHub repository},
  howpublished = {\url{https://github.com/LianjiaTech/BELLE}},
}