YinonDouchanClarity

No weights and no inference code provided

3

Hi, it seems that there is no way to use the code right now since there are no weights provided and no explanation on how to use the code. Is...

Poor performance of pretrained SyncNet (lipsync_expert.pth) on AVSpeech videos

4

I tried using the pre-trained syncnet model on a subset of the AVSpeech dataset. The videos that I chose from AVSpeech were 25FPS videos. In color_syncnet_train.py, I tried turning off...