# MULE
The Musicset Unsupervised Large Embedding (MULE) module is your
music-audio workhorse!
This module contains [SCOOCH](https://github.com/PandoraMedia/scooch) configurable code to run a simple
analysis pipeline to extract audio embeddings from audio files which
may then be used for downstream music understanding purposes.
This module requires FFMpeg to read audio files, which may be
downloaded [here](https://ffmpeg.org/download.html).
In order to create MULE embeddings, you will need a SCOOCH configuration
describing the pipeline, and the model weights. Both are licensed under
the [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode) license, and can be found in this [module's github repository](https://github.com/PandoraMedia/music-audio-representations).
To create embeddings for a single audio file, e.g., `test.wav` in the current
directory, you can use this module in conjunction with the provided configuration
and model weights:
```
pip install sxmp-mule
git clone https://github.com/PandoraMedia/music-audio-representations.git
cd ./music-audio-representations
mule analyze --config ./supporting_data/configs/mule_embedding.yml -i ../test.wav -o ./embedding.npy
```
For more information on this module, please check out the publication:
[*Supervised and Unsupervised Learning of Audio Representations for Music Understanding*](https://arxiv.org/abs/2210.03799), **M. C. McCallum**, F. Korzeniowski, S. Oramas, F. Gouyon, A. F. Ehmann.
Raw data
{
"_id": null,
"home_page": "https://github.com/PandoraMedia/music-audio-representations",
"name": "sxmp-mule",
"maintainer": null,
"docs_url": null,
"requires_python": ">=3.8",
"maintainer_email": null,
"keywords": "mule audio music embeddings machine learning",
"author": "Matt C. McCallum",
"author_email": "mmccallum@pandora.com",
"download_url": "https://files.pythonhosted.org/packages/d1/12/0fb5d43abbfa26bd781ae6402c2c7ef76769119d8c23b042b3a574e6d9d8/sxmp_mule-1.1.1.tar.gz",
"platform": null,
"description": "\n# MULE\n\nThe Musicset Unsupervised Large Embedding (MULE) module is your \nmusic-audio workhorse!\n\nThis module contains [SCOOCH](https://github.com/PandoraMedia/scooch) configurable code to run a simple \nanalysis pipeline to extract audio embeddings from audio files which\nmay then be used for downstream music understanding purposes.\n\nThis module requires FFMpeg to read audio files, which may be \ndownloaded [here](https://ffmpeg.org/download.html).\n\nIn order to create MULE embeddings, you will need a SCOOCH configuration\ndescribing the pipeline, and the model weights. Both are licensed under \nthe [CC BY-NC 4.0](https://creativecommons.org/licenses/by-nc/4.0/legalcode) license, and can be found in this [module's github repository](https://github.com/PandoraMedia/music-audio-representations).\n\nTo create embeddings for a single audio file, e.g., `test.wav` in the current\ndirectory, you can use this module in conjunction with the provided configuration\nand model weights:\n\n```\npip install sxmp-mule\ngit clone https://github.com/PandoraMedia/music-audio-representations.git\ncd ./music-audio-representations\nmule analyze --config ./supporting_data/configs/mule_embedding.yml -i ../test.wav -o ./embedding.npy\n```\n\nFor more information on this module, please check out the publication:\n\n[*Supervised and Unsupervised Learning of Audio Representations for Music Understanding*](https://arxiv.org/abs/2210.03799), **M. C. McCallum**, F. Korzeniowski, S. Oramas, F. Gouyon, A. F. Ehmann.\n\n",
"bugtrack_url": null,
"license": "GNU GPL 3.0",
"summary": null,
"version": "1.1.1",
"project_urls": {
"Bug Reports": "https://github.com/PandoraMedia/music-audio-representations/issues",
"Documentation": "https://github.com/PandoraMedia/music-audio-representations",
"Homepage": "https://github.com/PandoraMedia/music-audio-representations",
"Source": "https://github.com/PandoraMedia/music-audio-representations"
},
"split_keywords": [
"mule",
"audio",
"music",
"embeddings",
"machine",
"learning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "d1120fb5d43abbfa26bd781ae6402c2c7ef76769119d8c23b042b3a574e6d9d8",
"md5": "fb39c6b6545c770bc2e90a31b00b7a2c",
"sha256": "e6b2b4830e65670714bf9fd1b130ebb5246bbb9ab2fbb8e3a8145c86ad023608"
},
"downloads": -1,
"filename": "sxmp_mule-1.1.1.tar.gz",
"has_sig": false,
"md5_digest": "fb39c6b6545c770bc2e90a31b00b7a2c",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8",
"size": 45416,
"upload_time": "2024-05-01T23:27:54",
"upload_time_iso_8601": "2024-05-01T23:27:54.076234Z",
"url": "https://files.pythonhosted.org/packages/d1/12/0fb5d43abbfa26bd781ae6402c2c7ef76769119d8c23b042b3a574e6d9d8/sxmp_mule-1.1.1.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-05-01 23:27:54",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "PandoraMedia",
"github_project": "music-audio-representations",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "sxmp-mule"
}
JSON
