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

End of the speech not detected at first call. #39

Open
gribouk opened this issue Nov 27, 2024 · 0 comments
Open

End of the speech not detected at first call. #39

gribouk opened this issue Nov 27, 2024 · 0 comments

Comments

@gribouk
Copy link

gribouk commented Nov 27, 2024

Hello!

I am using faster-whisped in a container. It serves for STT in HA assist. I use to talk to it via the companion app installed on my android phone. The problem is that when I open assist and start talking to it, my first addressing always ends with VAD timeout:, i.e. it does not detect the end of speech:

VAD end of speech detection timed out after 15.0 seconds

In the containers logs this appears:

DEBUG:wyoming_faster_whisper.handler:Language set to en
DEBUG:wyoming_faster_whisper.handler:Audio stopped. Transcribing with initial prompt=None
INFO:faster_whisper:Processing audio with duration 00:15.000
DEBUG:faster_whisper:Processing segment at 00:00.000
INFO:wyoming_faster_whisper.handler: Hello?
DEBUG:wyoming_faster_whisper.handler:Completed request

the consequent request are processed without significant delay, so it is the problem of conversation start only.
This container serves 3 of the assistans I have made for different languages if this info is usefull.

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

1 participant