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

Transcription continues even when source is muted #34

Closed
KayOhtie opened this issue Oct 5, 2023 · 4 comments
Closed

Transcription continues even when source is muted #34

KayOhtie opened this issue Oct 5, 2023 · 4 comments
Labels
enhancement New feature or request
Milestone

Comments

@KayOhtie
Copy link

KayOhtie commented Oct 5, 2023

Problem: LocalVocal transcribes audio it hears even when the audio source is muted.

Expectation: LocalVocal ceases transcription when source is muted.

Steps to reproduce: Mute the microphone and keep talking anyway.

I know above is a bit silly, but it's a very unexpected issue, which sucks because I really like this project so far.

@royshil royshil added this to the 0.0.4 milestone Oct 7, 2023
@royshil
Copy link
Collaborator

royshil commented Oct 7, 2023

implemented in #36

@royshil
Copy link
Collaborator

royshil commented Oct 7, 2023

@Ceralor please test the artifacts in https://github.com/obs-ai/obs-localvocal/actions/runs/6442663172 it should be implemented

@royshil royshil added the enhancement New feature or request label Oct 9, 2023
@KayOhtie
Copy link
Author

Worked properly! However, now it always outputs [blank_audio] with VAD off or [skip] with it on (and sometimes vice versa) when I'm not saying anything.

As an aside, are the configuration options documented anywhere? It'd be very cool to have a better understanding of the terms involved.

@royshil
Copy link
Collaborator

royshil commented Oct 12, 2023

if there's no VAD then it your audio to Whisper even if there's no speaking, and Whisper returns [blank_audio] as an output
really VAD should be on, to conserve computation resources.

the config options for Whisper are probably best documented on the whisper repos e.g . https://github.com/ggerganov/whisper.cpp and https://github.com/openai/whisper/

@royshil royshil closed this as completed Oct 13, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

2 participants