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

Whisper speech to text timeout #1361

Closed
Ahmed-farag36 opened this issue May 8, 2023 · 2 comments
Closed

Whisper speech to text timeout #1361

Ahmed-farag36 opened this issue May 8, 2023 · 2 comments

Comments

@Ahmed-farag36
Copy link
Contributor

My setup
Virtual box running HA OS latest version 10.1 with dedicated resources: 4 cores CPU i7 100% cap and 8 GB of RAM and on SSD drive.
config for whisper is language: en, model: tiny-int8, beam-size: 1.
my pipeline is the default English with Whisper as SST and Google translate as TTS

The problem
sometimes I got my voice transcribed but in more than 25 seconds, but in many tries I get timeout error.

and this is my debug result
conversation.zip

any suggestions please

@edurenye
Copy link
Contributor

I was having the same problem, so I tried to set the whisper docker image in base machine using docker in hopes to get better performance using the GPU (Virtual box does not have GPU passthrough, docker does support it). But the images do not have support for GPU, so I created this issue there: rhasspy/wyoming-addons#3
If that is addressed we could use GPU and speed up Whisper.

Onother solution would be to increse the timeout, but I don't think it makes sence to have a timeout greater that 25 seconds, what we really need is a faster whisper server. IMHO.

@edurenye
Copy link
Contributor

Anyway I don't think this is an issue related to the intents.

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

3 participants