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

Adding Turn Detection Models: Improving VAD #154

Open
mahimairaja opened this issue Mar 8, 2025 · 3 comments
Open

Adding Turn Detection Models: Improving VAD #154

mahimairaja opened this issue Mar 8, 2025 · 3 comments

Comments

@mahimairaja
Copy link
Contributor

Pipecat released Smart Turn an innovative approach to replace VAD to decide on when the AI should talk

https://github.com/pipecat-ai/smart-turn?tab=readme-ov-file
@CuriousMonkey7
Copy link
Contributor

Really cool direction!
However, inference time would be a big blocker for FastRTC. They mentioned ~1500ms on CPU, while the current VAD model runs in real-time, plus the model size (~2GB).

@CuriousMonkey7
Copy link
Contributor

CuriousMonkey7 commented Mar 9, 2025 •
edited
Loading

This may be something FastRTC can use.

@mahimairaja
Copy link
Contributor Author

Yea @CuriousMonkey7 this is cool and in real time

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@CuriousMonkey7 @mahimairaja