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

Feature request: WaveNetVA implementation #361

Open
38github opened this issue Dec 21, 2022 · 2 comments
Open

Feature request: WaveNetVA implementation #361

38github opened this issue Dec 21, 2022 · 2 comments

Comments

@38github
Copy link

I would really like this option since an other plugin supporting this is buggy and you might even manage to get the CPU down like you did with Proteus/GuitarML AND it will be available as CLAP. I will donate to the project and hopefully others will do the same.

@jatinchowdhury18
Copy link
Contributor

Yeah, having a generic and performance WaveNetVA implementation would be pretty nice! However, I think that sort of thing would fit better in the RTNeural library. If it's okay with you, I can move the issue over there?

@38github
Copy link
Author

Of course, it is alright. You are the developer and knows better than me so go on. WaveNet recreates profiles/models so much better than any LSTM implementation I have heard but it uses a lot more CPU. I have made models with GuitarML's Colab scripts which I can't distinguish from the original. The problem with SmartPedal though is that the Linux version crashes all the time on all my systems. The upside if you implement it, besides probably less CPU usage, is that we will have a CLAP version and a plugin that is stable.

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

2 participants