Skip to content
#

joint-embedding-predictive-architecture

Here are 10 public repositories matching this topic...

a controlled comparison study of SSL masked-modeling objectives where masked spectrograms reconstruction MAE, masked latent prediction M2D, and joint-embedding prediction Audio-JEPA are pretrained on 52h corpus of Indic speech across 12 languages, all sharing an identical ViT-S/16 encoder and evaluated on the LID & SID tasks of IndicSUPERB

  • Updated Aug 16, 2026
  • Jupyter Notebook

Add this topic to your repo

To associate your repository with the joint-embedding-predictive-architecture topic, visit your repo's landing page and select "manage topics."

Learn more