[ISSUE]: Model concurrency

shep920 commented 8 months ago

Voice Changer Version

branch f529331

Operational System

Windows 10

GPU

n/a

Read carefully and check the options

[ ] I've tried to Clear Settings
[ ] Sample/Default Models are working
[ ] I've tried to change the Chunk Size
[ ] GUI was successfully launched
[X] I've read the tutorial
[ ] I've tried to extract to another folder (or re-extract) the .zip file

Model Type

n/a

Issue Description

I am not sure if this is a bug or a feature request, but here is what I am wondering:

Currently, it is possible for the server to independently serve multiple requests for producing sound. However, only one model can be loaded at a time. In this screenshot, you can see I am intending to have two client instances to produce two separate sounds. While two sounds are successfully created, only one model is loaded and used at a time. Is it possible to have multiple models loaded at the same time?

Application Screenshot

Logs on console

n/a

w-okada commented 8 months ago

Currently, we are unable to run multiple models on a single server.

The feature request might be similar to the one found at the following link: https://github.com/w-okada/voice-changer/issues/837

So, close. If not the same, reopen.

shep920 commented 8 months ago

Understood. In the other issue, you mentioned that there would need to be large changes for this to work. What barriers do you currently see that need fixed in the way of making multiple connections work?

@w-okada

w-okada / voice-changer