Wiki source code of Audiocraft AI
Version 1.1 by René Schmidt on 2025/03/28 12:21
Show last authors
| author | version | line-number | content |
|---|---|---|---|
| 1 | |((( | ||
| 2 | [[jan12 (>>url:https://github.com/facebookresearch/audiocraft/commit/e5fcc458a4dc1c6f7248cbceac9cfe471f2c92b8]][[#528>>url:https://github.com/facebookresearch/audiocraft/pull/528]][[)>>url:https://github.com/facebookresearch/audiocraft/commit/e5fcc458a4dc1c6f7248cbceac9cfe471f2c92b8]] | ||
| 3 | )))|Jan 15, 2025 | ||
| 4 | |(% colspan="1" %) | ||
| 5 | |||
| 6 | (% style="width:1363px" %) | ||
| 7 | |(% colspan="1" style="width:333px" %)((( | ||
| 8 | [[jasco_demo.ipynb>>url:https://github.com/facebookresearch/audiocraft/blob/main/jasco_demo.ipynb]] | ||
| 9 | )))|(% style="width:808px" %)((( | ||
| 10 | [[Jasco release jan12 (>>url:https://github.com/facebookresearch/audiocraft/commit/3c38b720398bfb587e0c42e8cd91f4c05293c82a]][[#527>>url:https://github.com/facebookresearch/audiocraft/pull/527]][[)>>url:https://github.com/facebookresearch/audiocraft/commit/3c38b720398bfb587e0c42e8cd91f4c05293c82a]] | ||
| 11 | )))|Jan 15, 2025 | ||
| 12 | |(% colspan="1" style="width:333px" %) | ||
| 13 | |||
| 14 | = AudioCraft = | ||
| 15 | |||
| 16 | |||
| 17 | [[~[~[image:https://github.com/facebookresearch/audiocraft/workflows/audiocraft_docs/badge.svg~|~|alt="docs badge"~]~]>>url:https://github.com/facebookresearch/audiocraft/workflows/audiocraft_docs/badge.svg]] [[~[~[image:https://github.com/facebookresearch/audiocraft/workflows/audiocraft_linter/badge.svg~|~|alt="linter badge"~]~]>>url:https://github.com/facebookresearch/audiocraft/workflows/audiocraft_linter/badge.svg]] [[~[~[image:https://github.com/facebookresearch/audiocraft/workflows/audiocraft_tests/badge.svg~|~|alt="tests badge"~]~]>>url:https://github.com/facebookresearch/audiocraft/workflows/audiocraft_tests/badge.svg]] | ||
| 18 | |||
| 19 | AudioCraft is a PyTorch library for deep learning research on audio generation. AudioCraft contains inference and training code for two state-of-the-art AI generative models producing high-quality audio: AudioGen and MusicGen. | ||
| 20 | |||
| 21 | == Installation == | ||
| 22 | |||
| 23 | |||
| 24 | AudioCraft requires Python 3.9, PyTorch 2.1.0. To install AudioCraft, you can run the following: | ||
| 25 | |||
| 26 | {{{# Best to make sure you have torch installed first, in particular before installing xformers. | ||
| 27 | # Don't run this if you already have PyTorch installed. | ||
| 28 | python -m pip install 'torch==2.1.0' | ||
| 29 | # You might need the following before trying to install the packages | ||
| 30 | python -m pip install setuptools wheel | ||
| 31 | # Then proceed to one of the following | ||
| 32 | python -m pip install -U audiocraft # stable release | ||
| 33 | python -m pip install -U git+https://git@github.com/facebookresearch/audiocraft#egg=audiocraft # bleeding edge | ||
| 34 | python -m pip install -e . # or if you cloned the repo locally (mandatory if you want to train). | ||
| 35 | python -m pip install -e '.[wm]' # if you want to train a watermarking model}}} | ||
| 36 | |||
| 37 | We also recommend having ffmpeg installed, either through your system or Anaconda: | ||
| 38 | |||
| 39 | {{{sudo apt-get install ffmpeg | ||
| 40 | # Or if you are using Anaconda or Miniconda | ||
| 41 | conda install "ffmpeg<5" -c conda-forge}}} | ||
| 42 | |||
| 43 | == Models == | ||
| 44 | |||
| 45 | |||
| 46 | At the moment, AudioCraft contains the training code and inference code for: |