hnluo
hnluo
Please list your envs: Package Version：funasr version（pip list） Model： Command： Details： Error log：
you can get asr results from decoder_dir/1best_recog/tokens file
Please check whether torchaudio is installed successfully
I use aishell-1 data to finetune paraformer-large offline model with CTC, set dataset_type to small and large, the training log is as follows, you can refer to it 
I use [finetune.py](https://github.com/alibaba-damo-academy/FunASR/blob/main/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/finetune.py) recipe to finetune paraformer-large offline model, config.yaml you can refer to [config.yaml](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/file/view/master/config.yaml) and set ctc_weight to 0.3, and mvn file has not been modified
You can refer to my configuration and quickly verify it.
Please provide your inference recipe and recorded audio if possible.
Please check training data，format reference (https://alibaba-damo-academy.github.io/FunASR/en/egs_modelscope/asr/TEMPLATE/README.html#finetune-with-your-data)