You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
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)
The text was updated successfully, but these errors were encountered:
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)
The text was updated successfully, but these errors were encountered: