Meta (formerly Facebook) has released its AI-powered music generator called ‘MusicGen’, which will turn text description and melody into audio.
The company also released the code and models for open research, reproducibility, and the music community.
“We present MusicGen: A simple and controllable music generation model. MusicGen can be prompted by both text and melody. We release code (MIT) and models (CC-BY NC) for open research, reproducibility, and for the music community,” tweeted Felix Kreuk, Research Engineer at Meta AI research.
“MusicGen is built on top of the EnCodec audio tokenizer. Unlike prior work, MusicGen is a single-stage transformerLM which uses an efficient token interleaving patterns, hence eliminates the need for cascading several models (e.g., hierarchically or upsampling),” he added.
