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

Multivocoder Update: A substantial infrastructure upgrade proposed as a version improvement. #752

Draft
wants to merge 86 commits into
base: main
Choose a base branch
from

Conversation

blaisewf
Copy link
Member

We propose this update to modernize the code infrastructure. Currently, it will be a public experiment, gathering strong feedback from the community. If the results are deemed optimal, the version will be released only after completing the training phase of the base pre-trained models and the final optimization.

Objectives

  • Implement BigVGAN (V2)
  • Implement BigVSAN
  • Optional: Implement HiFiSAN
  • Optional: Implement Vocos
  • Idea: Optimize BigVGAN and BigVSAN activation to reduce high resource consumption by Snake
  • Train pre-trained models on all the vocoders (VCTK)

Updates

  • 08/06/2024: Start of development...
  • 30/07/2024: Experimental testing phase

@blaisewf blaisewf added the enhancement New feature or request label Oct 10, 2024
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

Successfully merging this pull request may close these issues.

2 participants