Reimplementation in pytorch of the paper : Few-Shot Adversarial Learning of Realistic Neural Talking Head Models (https://arxiv.org/pdf/1905.08233.pdf).
The dataset is VoxCeleb2 you can get it here : http://www.robots.ox.ac.uk/~vgg/data/voxceleb/vox2.html
The weights Beluga : https://drive.google.com/drive/folders/1eXtX8H7v1mRJBJisN3Q16-bVq-Ayu7-4?usp=sharing Helios : https://drive.google.com/drive/folders/1FhQbFmaasnC7zL4E-L1SS3f47sE5to8c?usp=sharing Lab: https://drive.google.com/drive/folders/1vtFBWjeR7BBwfmunxt9toSB72lpeR8Oi?usp=sharing