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

Add ECOGEN embedding and generative #5

Open
sammlapp opened this issue Jan 22, 2024 · 0 comments
Open

Add ECOGEN embedding and generative #5

sammlapp opened this issue Jan 22, 2024 · 0 comments

Comments

@sammlapp
Copy link
Contributor

ECOGEN is a self-supervised (VQ-VAE architecture) encoder-decoder trained on xeno canto. It was created for generation of new samples by perturbing the feature space (called the code book), but could also serve as an effective embedding model using only the encoder half. The model and code are open-source, though I haven't successfully installed the repo in a python package yet (see ixobert/birds-generation#7)

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

1 participant