zhifu gao
zhifu gao
> > Maybe the diff is `am.mvn`, please check it. > > I replaced the am.mvn file used for training, and the result was still the same. There was no...
> > > > Maybe the diff is `am.mvn`, please check it. > > > > > > > > > I replaced the am.mvn file used for training, and...
Update the code and try it again.
Please check your training data as: https://alibaba-damo-academy.github.io/FunASR/en/egs_modelscope/asr/TEMPLATE/README_zh.html#id12
Strange! But I suggest you that you could first use only 1000-hour data to finetune model. And you could verify the data and hyper-parameter
KeyError: 'speaker-diarization-inference is not in the pipelines registry group speaker-diarization.
Please install: funasr==0.8.8 modelscope==1.10.0 https://github.com/alibaba-damo-academy/FunASR/tree/v0.8.8
git pull pip install -e ./
pip install torchaudio
delete all *model_revision, and try it again. All requirements would be installed automatically.
> Yes, thank you. But basically what I want to do is to build an image with installed packages ahead of running any scripts. I believe I should not figure...