metadata

license: apache-2.0
metrics:
  - cer

Welcome

If you find this model helpful, please like this model and star us on https://github.com/LianjiaTech/BELLE !

Belle-distilwhisper-large-v2-zh

Fine tune distilwhisper-large-v2 to improve Chinese speech recognition.

Same to distilwhisper-large-v2, Belle-distilwhisper-large-v2-zh is 5.8 times faster with 51% fewer parameters compare to whisper-large-v2.

Note that distilwhisper-large-v2 can not transcribe Chinese(only output English) on Chinese ASR benchmark(AISHELL1, AISHELL2, WENETSPEECH, HKUST).

Usage


from transformers import pipeline

transcriber = pipeline(
  "automatic-speech-recognition", 
  model="BELLE-2/Belle-distilwhisper-large-v2-zh"
)

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

transcription = transcriber("my_audio.wav")

Fine-tuning

Model	(Re)Sample Rate	Train Datasets	Fine-tuning (full or peft)
Belle-distilwhisper-large-v2-zh	16KHz	AISHELL-1 AISHELL-2 WenetSpeech HKUST	full fine-tuning

If you want to fine-thuning the model on your datasets, please reference to the github repo

CER(%)

Model	Parameters(M)	Language Tag	aishell_1_test	aishell_2_test	wenetspeech_net	wenetspeech_meeting	HKUST_dev
whisper-large-v2	1550	Chinese	8.818	6.183	12.343	26.413	31.917
distilwhisper-large-v2	756	Chinese	-	-	-	-	-
Belle-distilwhisper-large-v2-zh	756	Chinese	5.958	6.477	12.786	17.039	20.771

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}},
}