Skip to content
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.

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

How to train sv2p? #1

Open
Zoe0123 opened this issue Feb 22, 2022 · 1 comment
Open

How to train sv2p? #1

Zoe0123 opened this issue Feb 22, 2022 · 1 comment

Comments

@Zoe0123
Copy link

Zoe0123 commented Feb 22, 2022

Hi, thank you so much for your hard work providing this open-source! Could you tell me more about how I can follow the three steps as in sv2p paper (3.2 section) to train? Have they all included in the CNDATrainer, or should I change the multiplier of KL-loss by myself from step 1 to step 3, and where should I change?

In addition, could you tell me how to initialize the hyper-parameters krireg and mfreg? They are not in the myrun.ini.

Thank you very much in advance for your kind help!

@kkew3
Copy link
Owner

kkew3 commented Feb 23, 2022

Sorry I haven't been maintaining this project for a while and am afraid I couldn't answer your questions at the time.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants