New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Test on chinese videos #1

Open

QUTGXX opened this issue Dec 20, 2022 · 1 comment

QUTGXX commented Dec 20, 2022

I tried my own videos based on the Colab. The result seems not correct. Do you have any suggestions if I want to train it based on my own datasets?

Owner

v-iashin commented Dec 20, 2022

If you are trying to synchronise a talking head in Chinese, then it might not work due to the domain gap (a different language).

I guess you could try to make your dataset resemble the LRS3 (no face crop) structure and train/fine-tune the model.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment