EncodecMAE

EncodecMAE is a self-supervised audio representation model developed by Meta, combining the EnCodec neural audio codec with a masked autoencoder (MAE) architecture for efficient music and speech understanding.

Two-hop subgraph: this entity, every entity it directly relates to, and every entity those neighbors relate to. Drag a node, scroll to zoom, click to inspect — or click any neighbor and re-center the atlas there.