GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
BELLE-2
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
BELLE-2
Model Tree
openai/whisper-large-v3
Input Modalities
Output Modalities
Supported Functionality
If you find this model helpful, please like this model and star us on https://github.com/LianjiaTech/BELLE and https://github.com/shuaijiang/Whisper-Finetune
Fine tune whisper-large-v3 to enhance Chinese speech recognition capabilities, Belle-whisper-large-v3-zh demonstrates a 24-65% relative improvement in performance on Chinese ASR benchmarks, including AISHELL1, AISHELL2, WENETSPEECH, and HKUST.
python
from transformers import pipeline transcriber = pipeline( "automatic-speech-recognition", model="BELLE-2/Belle-whisper-large-v3-zh") transcriber.model.config.forced_decoder_ids = ( transcriber.tokenizer.get_decoder_prompt_ids( language="zh", task="transcribe" )) transcription = transcriber("my_audio.wav") | Model | (Re)Sample Rate | Train Datasets | Fine-tuning (full or peft) |
|---|---|---|---|
| Belle-whisper-large-v3-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
| Model | Language Tag | aishell_1_test(↓) | aishell_2_test(↓) | wenetspeech_net(↓) | wenetspeech_meeting(↓) | HKUST_dev(↓) |
|---|---|---|---|---|---|---|
| whisper-large-v3 | Chinese | 8.085 | 5.475 | 11.72 | 20.15 | 28.597 |
| Belle-whisper-large-v2-zh | Chinese | 2.549 | 3.746 | 8.503 | 14.598 | 16.289 |
| Belle-whisper-large-v3-zh | Chinese | 2.781 | 3.786 | 8.865 | 11.246 | 16.440 |
It is worth mentioning that compared to Belle-whisper-large-v2-zh, Belle-whisper-large-v3-zh has a significant improvement in complex acoustic scenes(such as wenetspeech_meeting).
Please cite our paper and github when using our code, data or model.
text
@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}},}from transformers import pipeline transcriber = pipeline( "automatic-speech-recognition", model="BELLE-2/Belle-whisper-large-v3-zh") transcriber.model.config.forced_decoder_ids = ( transcriber.tokenizer.get_decoder_prompt_ids( language="zh", task="transcribe" )) transcription = transcriber("my_audio.wav") @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}},}