Audiocraft

Audiocraft is a PyTorch library for deep learning research on audio generation. At the moment, it contains the code for MusicGen, a state-of-the-art controllable text-to-music model.

MusicGen

Audiocraft provides the code and models for MusicGen, a simple and controllable model for music generation. MusicGen is a single stage auto-regressive Transformer model trained over a 32kHz EnCodec tokenizer with 4 codebooks sampled at 50 Hz. Unlike existing methods like MusicLM, MusicGen doesn't not require a self-supervised semantic representation, and it generates all 4 codebooks in one pass. By introducing a small delay between the codebooks, we show we can predict them in parallel, thus having only 50 auto-regressive steps per second of audio. Check out our sample page or test the available demo!

Installation

Audiocraft requires Python 3.9, PyTorch 2.0.0, and a GPU with at least 16 GB of memory (for the medium-sized model). To install Audiocraft, you can run the following:

# Best to make sure you have torch installed first, in particular before installing xformers.
# Don't run this if you already have PyTorch installed.
pip install 'torch>=2.0'
# Then proceed to one of the following
pip install -U audiocraft  # stable release
pip install -U git+https://git@github.com/facebookresearch/audiocraft#egg=audiocraft  # bleeding edge
pip install -e .  # or if you cloned the repo locally

Usage

You can play with MusicGen by running the jupyter notebook at demo.ipynb locally, or use the provided colab notebook. Finally, a demo is also available on the facebook/MusiGen HugginFace Space (huge thanks to all the HF team for their support).

API

We provide a simple API and 4 pre-trained models. The pre trained models are:

small: 300M model, text to music only,
medium: 1.5B model, text to music only,
melody: 1.5B model, text to music and text+melody to music,
large: 3.3B model, text to music only.

We observe the best trade-off between quality and compute with the medium or melody model. In order to use MusicGen locally you must have a GPU. We recommend 16GB of memory, but smaller GPUs will be able to generate short sequences, or longer sequences with the small model.

See after a quick example for using the API.

import torchaudio
from audiocraft.models import MusicGen
from audiocraft.data.audio import audio_write

model = MusicGen.get_pretrained('melody')
model.set_generation_params(duration=8)  # generate 8 seconds.
wav = model.generate_unconditional(4)    # generates 4 unconditional audio samples
descriptions = ['happy rock', 'energetic EDM', 'sad jazz']
wav = model.generate(descriptions)  # generates 3 samples.

melody, sr = torchaudio.load('./assets/bach.mp3')
# generates using the melody from the given audio and the provided descriptions.
wav = model.generate_with_chroma(descriptions, melody[None].expand(3, -1, -1), sr)

for idx, one_wav in enumerate(wav):
    # Will save under {idx}.wav, with loudness normalization at -14 db LUFS.
    audio_write(f'{idx}', one_wav, model.sample_rate, strategy="loudness")

Model Card

See the model card page.

FAQ

Will the training code be released?

Yes. We will soon release the training code for MusicGen and EnCodec.

Citation

@article{copet2023simple,
      title={Simple and Controllable Music Generation},
      author={Jade Copet and Felix Kreuk and Itai Gat and Tal Remez and David Kant and Gabriel Synnaeve and Yossi Adi and Alexandre Défossez},
      year={2023},
      journal={arXiv preprint arXiv:2306.05284},
}

License

The code in this repository is released under the MIT license as found in the LICENSE file.
The weights in this repository are released under the CC-BY-NC 4.0 license as found in the LICENSE_weights file.