Open Bebaam opened 12 months ago
I also encountered this problem. This is because the model parameters given by the author only include encoder-decoder. The complete model is too large. I saved 8.2G after training.
okay that is unfortunate, thank you for the insight.
Hello, may I ask how the signal features of your audio are extracted
When running inference, I only get an incomplete image with landmarks and mask. What do I need to do in order to get a clean image?![0000_0000](https://github.com/sstzal/DiffTalk/assets/44262699/b06dd6af-b85d-4012-ad9c-4a404eb49181)