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.

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

Teacher forcing vs knowledge distillation #5781

Open
Curiosci opened this issue May 9, 2024 · 0 comments
Open

Teacher forcing vs knowledge distillation #5781

Curiosci opened this issue May 9, 2024 · 0 comments
Assignees
@kan-bayashi
Labels
Question Question TTS Text-to-speech

Comments

@Curiosci
Copy link

Curiosci commented May 9, 2024

How would you explain the difference between teacher forcing and knowledge distillation ? i noticed that fastspeech2 in your implementationuses knowledge ditillation by predicting durations from AR model, however in their paper, they state that they no longer use it in fastspeech2.
@Curiosci Curiosci added the Question Question label May 9, 2024
@sw005320 sw005320 added the TTS Text-to-speech label May 9, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@kan-bayashi kan-bayashi

Labels
Question Question TTS Text-to-speech
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@sw005320 @kan-bayashi @Curiosci