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

翻译：我们着手解决条件音乐生成任务。我们引入了MusicGen，这是一种单一的语言模型（LM），能够处理多流压缩离散音乐表示（即令牌）。与先前的工作不同，MusicGen由单阶段变换器LM与高效的令牌交错模式组成，从而无需级联多个模型（例如，基于层次结构或上采样）。通过这种方法，我们展示了MusicGen如何生成高质量的单声道和立体声样本，同时以文本描述或旋律特征为条件，从而更好地控制生成输出。我们进行了广泛的实证评估，包括自动评估和人工研究，结果表明所提出的方法在标准文本到音乐基准测试中优于评估的基线方法。通过消融研究，我们阐明了组成MusicGen的每个组件的重要性。音乐样本、代码和模型可在https://github.com/facebookresearch/audiocraft 获取。