Wav2Lip icon indicating copy to clipboard operation
Wav2Lip copied to clipboard

This repository contains the codes of "A Lip Sync Expert Is All You Need for Speech to Lip Generation In the Wild", published at ACM Multimedia 2020.

Results 152 Wav2Lip issues
Sort by recently updated
recently updated
newest added

Across 2 out of 3 machines I've worked on, I've run into this CUDA-related error, a failure of 'THCCudaCheck' starting at the preprocessing step which seems to lead to failure-causing...

Why__ getitem__ Loading the dataset is slow. How can I solve it? Who can help me

大佬们,请问一下,为什么我按照官方教程步骤训练,我用的CMRL数据集,训练syncnet模型、训练wav2lip模型,最后生成的模型唇形一点都对不上

python inference.py --checkpoint_path checkpoints/disc_checkpoint_step000000001.pth --face sample_data/foto.png --audio sample_data/audio.wav Traceback (most recent call last): File "/kaggle/working/wav2lip/inference.py", line 280, in main() File "/kaggle/working/wav2lip/inference.py", line 252, in main model = load_model(args.checkpoint_path) File "/kaggle/working/wav2lip/inference.py",...

![image](https://github.com/Rudrabha/Wav2Lip/assets/646709/7312cf69-4de6-49c3-8b3b-18f192ca4228) wav2lip高清模型训练288x288,400K,以后已经收敛到0.28一下,不知道还需要多久。大家一起交流一下。

我使用了 CMLR 数据集训练 color_syncnet,训练到了 80000 step了,但是 loss 却一直卡在 0.69+,请问是什么原因?

目前能够完美去边框,重新训练了一个中文的数据集,但是解决不了高清的问题(不想通过gfpgan的方式,太慢)请问有朋友解决的吗,付费学习一下。[email protected],谢谢!