Jukebox: A Generative Model for Music
openai/jukebox
“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. We show that the combined model at scale can generate high-fidelity and diverse songs with coherence up to multiple minutes…”
Source: github.com/openai/jukebox/
August 24, 2020
Subscribe
Login
Please login to comment
0 Comments