OpenTalker / SadTalker

[CVPR 2023] SadTalker:Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation
https://sadtalker.github.io/
Other
11.73k stars 2.19k forks source link

MacOS ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor' #924

Open mlvps opened 3 months ago

mlvps commented 3 months ago

I get the following error when trying to run the app_sadtalker.py:

ModuleNotFoundError: No module named 'torchvision.transforms.functional_tensor'

Any ideas? torch, torchvision and torchaudio got installed successfuly but the error still occurs.

kamilgregorczyk commented 3 months ago

also happening with colab, I think the project's dead though, no commit in last 9 months?