Jukebox: A Generative Model for Music

Preprint 2020 Prafulla DhariwalHeewoo JunChristine PayneJong Wook KimAlec RadfordIlya Sutskever

We introduce Jukebox, a model that generates music with singing in the raw audio domain. We tackle the long context of raw audio using a multi-scale VQ-VAE to compress it to discrete codes, and modeling those using autoregressive Transformers... (read more)

PDF Abstract Preprint 2020 PDF Preprint 2020 Abstract

Code


Tasks


Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper