Skip to content

EnCodec

Meta AIAudio generationOpen weights

The EnCodec model is an open-weights audio generation model from Meta AI.

About EnCodec

We introduce a state-of-the-art real-time, high-fidelity, audio codec leveraging neural networks. It consists in a streaming encoder-decoder architecture with quantized latent space trained in an end-to-end fashion. We simplify and speed-up the train

Details

Provider
Meta AI
Task
Audio generation
Released
2022-10-24
Open weights
Yes
View model source

Explore

FAQ