susanqq / talking_face_generation Goto Github PK

Thanks for sharing the code and the trained models.
Can you also share the test files. It will save lot time when testing.

Thank you for sharing your code. But I still have two problems with data processing.
1.In your data processing code, I didn't understand how you specifically process the dataset. I also don't understand which part of the code is to process video into image sequences and audio frames. Can you tell me how to process the LRW dataset?
2. In "LRW_training_list_npy_128.txt" , What do the last numbers mean in each line？ （43，69，83，109，0）

Thanks for sharing the code.
Can you also share the trained model files. It will save lot time when testing.

Hi, Greate Job!
It is inital commit, how about the training performance?
and the test results?
could you commit sample data and pretrained model？

In the test, can I input non-human character into the network to generate non-human character talking face, such as animal image as follow: