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

Stream generated audio to browser in real-time #33

Open
wants to merge 2 commits into
base: main
Choose a base branch
from

Conversation

MattJeanes
Copy link

I have changed the audio to be generated in a stream and adds a new audio box in the gradio UI that streams said audio to the browser in real-time (if your PC is fast enough anyway) so allow for much faster feedback. The full file is still available after generation has been completed to download / stored in the temp folder as before.

I have noticed this warning comes up using the XTTS.inference_stream instead of XTTS.inference but I believe this issue an issue in the library code and shouldn't be an issue.

@daswer123
Copy link
Owner

Hi, thanks a lot for your contribution, now I'm preparing to add the ability to tune DVAE, after that I'll check your PR

@MattJeanes
Copy link
Author

Thank you, no rush! I was just working on it myself to see if I could get it to stream in real-time and figured I might as well contribute it back if you like it!

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.

2 participants