yl4579 / StarGANv2-VC

StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion
MIT License
466 stars 110 forks source link

What was the pytorch version this model used for training? #79

Closed yurong58 closed 1 year ago

yurong58 commented 1 year ago

Hi! thank you for providing all these works! I really appreciate it. I am a beginner and had done training the model, however, I encounter a problem when doing the interference. Screenshot from 2023-03-02 18-19-33 According to the internet, it said that the pytorch version used for training the model isn't the same one I am using right now. I have looked through the information you have provided but still cant find anything about it. Do I miss anything? Thank you so much!!!

daozhi0921 commented 1 year ago

按照如下环境安装, 测试可用, 你可以试试: librosa==0.7.2 SoundFile munch pydub pyyaml click tensorboard==2.12.0 numba==0.48.0 pip install setuptools==56.1.0 pip3 install torch==1.9.1+cu111 torchvision==0.10.1+cu111 torchaudio==0.9.1 -f https://download.pytorch.org/whl/torch_stable.html