Simple and Controllable Music Generation

Code

• github.com/facebookresearch/audiocraft
  In paperpytorch★ 23,110
• github.com/whisperspeech/whisperspeech
  pytorch★ 4,576
• github.com/collabora/whisperspeech
  pytorch★ 4,576
• github.com/theodorblackbird/lina-speech
  pytorch★ 179
• github.com/atharva20038/music4all
  jax★ 4
• github.com/pwc-1/Paper-5/tree/main/musicgen_melody
  mindspore★ 0
• github.com/pwc-1/Paper-9/tree/main/4/text-to-music
  mindspore★ 0
• github.com/pwc-1/Paper-5/tree/main/musicgen
  mindspore★ 0

Abstract

We tackle the task of conditional music generation. We introduce MusicGen, a single Language Model (LM) that operates over several streams of compressed discrete music representation, i.e., tokens. Unlike prior work, MusicGen is comprised of a single-stage transformer LM together with efficient token interleaving patterns, which eliminates the need for cascading several models, e.g., hierarchically or upsampling. Following this approach, we demonstrate how MusicGen can generate high-quality samples, both mono and stereo, while being conditioned on textual description or melodic features, allowing better controls over the generated output. We conduct extensive empirical evaluation, considering both automatic and human studies, showing the proposed approach is superior to the evaluated baselines on a standard text-to-music benchmark. Through ablation studies, we shed light over the importance of each of the components comprising MusicGen. Music samples, code, and models are available at https://github.com/facebookresearch/audiocraft

Tasks

Benchmark Results

Reproductions