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

Add speed control for inference #3214

Merged
merged 3 commits into from
Nov 14, 2023
Merged

Add speed control for inference #3214

merged 3 commits into from
Nov 14, 2023

Conversation

WeberJulian
Copy link
Contributor

No description provided.

@erogol erogol merged commit 04901fb into dev Nov 14, 2023
53 checks passed
@erogol erogol deleted the add-speed-control branch November 14, 2023 15:07
@platform-kit
Copy link

@WeberJulian @erogol how do you pass the speed param with xtts?

@WeberJulian
Copy link
Contributor Author

@platform-kit
Copy link

platform-kit commented Dec 11, 2023

@WeberJulian is there a trick to it I am missing? As I said in another thread, one would expect that passing a value of double or triple the default would produce double or triple the talking speed, and same in the inverse direction, but this is not the case with XTTS.

What value do I need to pass, if not 0.5 (ie does it ned to be a negative? this isnt specified anywhere), to get half-speed talking? Or can the model not go that slow?

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

Successfully merging this pull request may close these issues.

3 participants