# Nendo Plugin Musicgen
<br>
<p align="left">
<img src="https://okio.ai/docs/assets/nendo_core_logo.png" width="350" alt="nendo core">
</p>
<br>
---
![Documentation](https://img.shields.io/website/https/nendo.ai)
[![Twitter](https://img.shields.io/twitter/url/https/twitter.com/okio_ai.svg?style=social&label=Follow%20%40okio_ai)](https://twitter.com/okio_ai) [![](https://dcbadge.vercel.app/api/server/XpkUsjwXTp?compact=true&style=flat)](https://discord.gg/XpkUsjwXTp)
MusicGen: A state-of-the-art controllable text-to-music model (by [Meta Research](https://github.com/facebookresearch/audiocraft))
## Features
- Generate conditional and unconditional music
- Generate outpaintings from a prompt and a `NendoTrack`
- Use a `NendoTrack` as melody conditioning to generate music
- Use custom finetuned musicgen models
## Community Finetunes 🔥
For a list of community finetunes check out [`community_finetunes.json`](docs/community_finetunes.json).
If you want to contribute one to the list, open a PR
or contact us via [Twitter](https://twitter.com/okio_ai)
or [Discord](https://discord.gg/gaZMZKzScj)!
## Requirements
Since we depend on `audiocraft`, please make sure that you fulfill their requirements.
You need Pytorch 2.0.0 or higher, which can be installed via
`pip install "torch>=2.0"`
> Note: On Mac OSX, the instructions for installing pytorch differ. Please refer to the [pytorch installation instructions](https://pytorch.org/get-started/locally/). For all other problems please refer to the [audiocraft repository](https://github.com/facebookresearch/audiocraft/).
To run the plugin you also need to install `audiocraft` by Meta AI Research, run:
`pip install git+https://github.com/facebookresearch/audiocraft`
## Installation
1. [Install Nendo](https://github.com/okio-ai/nendo#installation)
2. `pip install nendo-plugin-musicgen`
## Usage
Take a look at a basic usage example below.
For more detailed information, please refer to the [documentation](https://okio.ai/docs/plugins).
For more advanced examples, check out the examples folder.
or try it in colab:
<a target="_blank" href="https://colab.research.google.com/drive/1krbzz1OqwCXcLWm5JUIa-otas4TeKZCt?usp=sharing">
<img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/>
</a>
```python
from nendo import Nendo, NendoConfig
nd = Nendo(config=NendoConfig(plugins=["nendo_plugin_musicgen"]))
# load track
track = nd.library.add_track(file_path='/path/to/track.mp3')
# run musicgen with custom model
generated_collection = nd.plugins.musicgen(
track=track,
n_samples=5,
prompt="janelle monae, rnb, funky, fast, futuristic",
bpm=116,
key="C",
scale="Major",
duration=30,
conditioning_length=10
)
generated_collection[0].play()
```
## Contributing
Visit our docs to learn all about how to contribute to Nendo: [Contributing](https://okio.ai/docs/contributing/)
## License
Nendo: MIT License
AudioCraft: MIT License
Pretrained models: The weights are released under the CC-BY-NC 4.0 license
Raw data
{
"_id": null,
"home_page": "https://okio.ai",
"name": "nendo_plugin_musicgen",
"maintainer": "",
"docs_url": null,
"requires_python": ">=3.8,<3.11",
"maintainer_email": "",
"keywords": "Nendo,Plugin,AI,Machine Learning,Audio,Generative,Music,Audio Production,Audio Generation",
"author": "Aaron Abebe",
"author_email": "aaron@okio.ai",
"download_url": "https://files.pythonhosted.org/packages/1f/21/720bdab34eb854c4ff145aa8df189c97dd9b453fb18c4f71a393c1c2f508/nendo_plugin_musicgen-0.1.3.tar.gz",
"platform": null,
"description": "# Nendo Plugin Musicgen \n\n<br>\n<p align=\"left\">\n <img src=\"https://okio.ai/docs/assets/nendo_core_logo.png\" width=\"350\" alt=\"nendo core\">\n</p>\n<br>\n\n---\n\n![Documentation](https://img.shields.io/website/https/nendo.ai)\n[![Twitter](https://img.shields.io/twitter/url/https/twitter.com/okio_ai.svg?style=social&label=Follow%20%40okio_ai)](https://twitter.com/okio_ai) [![](https://dcbadge.vercel.app/api/server/XpkUsjwXTp?compact=true&style=flat)](https://discord.gg/XpkUsjwXTp)\n\nMusicGen: A state-of-the-art controllable text-to-music model (by [Meta Research](https://github.com/facebookresearch/audiocraft))\n\n## Features\n\n- Generate conditional and unconditional music\n- Generate outpaintings from a prompt and a `NendoTrack`\n- Use a `NendoTrack` as melody conditioning to generate music\n- Use custom finetuned musicgen models\n\n## Community Finetunes \ud83d\udd25\n\nFor a list of community finetunes check out [`community_finetunes.json`](docs/community_finetunes.json).\nIf you want to contribute one to the list, open a PR \nor contact us via [Twitter](https://twitter.com/okio_ai) \nor [Discord](https://discord.gg/gaZMZKzScj)!\n\n## Requirements\n\nSince we depend on `audiocraft`, please make sure that you fulfill their requirements. \nYou need Pytorch 2.0.0 or higher, which can be installed via\n\n`pip install \"torch>=2.0\"`\n\n> Note: On Mac OSX, the instructions for installing pytorch differ. Please refer to the [pytorch installation instructions](https://pytorch.org/get-started/locally/). For all other problems please refer to the [audiocraft repository](https://github.com/facebookresearch/audiocraft/).\n\nTo run the plugin you also need to install `audiocraft` by Meta AI Research, run:\n\n`pip install git+https://github.com/facebookresearch/audiocraft`\n\n## Installation\n\n1. [Install Nendo](https://github.com/okio-ai/nendo#installation)\n2. `pip install nendo-plugin-musicgen`\n\n## Usage\n\nTake a look at a basic usage example below. \nFor more detailed information, please refer to the [documentation](https://okio.ai/docs/plugins).\n\nFor more advanced examples, check out the examples folder.\nor try it in colab:\n\n<a target=\"_blank\" href=\"https://colab.research.google.com/drive/1krbzz1OqwCXcLWm5JUIa-otas4TeKZCt?usp=sharing\">\n <img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/>\n</a>\n\n\n```python\nfrom nendo import Nendo, NendoConfig\n\nnd = Nendo(config=NendoConfig(plugins=[\"nendo_plugin_musicgen\"]))\n\n# load track\ntrack = nd.library.add_track(file_path='/path/to/track.mp3')\n\n# run musicgen with custom model\ngenerated_collection = nd.plugins.musicgen(\n track=track,\n n_samples=5,\n prompt=\"janelle monae, rnb, funky, fast, futuristic\",\n bpm=116,\n key=\"C\",\n scale=\"Major\",\n duration=30,\n conditioning_length=10\n)\ngenerated_collection[0].play()\n```\n\n## Contributing\n\nVisit our docs to learn all about how to contribute to Nendo: [Contributing](https://okio.ai/docs/contributing/)\n\n\n## License \n\nNendo: MIT License\n\nAudioCraft: MIT License\n\nPretrained models: The weights are released under the CC-BY-NC 4.0 license\n",
"bugtrack_url": null,
"license": "MIT",
"summary": "Nendo MusicGen plugin: A state-of-the-art controllable text-to-music model (by Meta Research)",
"version": "0.1.3",
"project_urls": {
"Homepage": "https://okio.ai",
"Repository": "https://github.com/okio-ai/nendo_plugin_musicgen"
},
"split_keywords": [
"nendo",
"plugin",
"ai",
"machine learning",
"audio",
"generative",
"music",
"audio production",
"audio generation"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "f64d801e2c1aa663d10bafc46f6f8c50aff683d3c55b1795d010502b1ac40347",
"md5": "b796b7bba5fa328954803aa3507a19ca",
"sha256": "5f43f2b0a1eb01ab29d440d6373b4719531abf6ee8a8a08121cab75d8cc25457"
},
"downloads": -1,
"filename": "nendo_plugin_musicgen-0.1.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "b796b7bba5fa328954803aa3507a19ca",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": ">=3.8,<3.11",
"size": 8667,
"upload_time": "2023-12-24T07:49:38",
"upload_time_iso_8601": "2023-12-24T07:49:38.777540Z",
"url": "https://files.pythonhosted.org/packages/f6/4d/801e2c1aa663d10bafc46f6f8c50aff683d3c55b1795d010502b1ac40347/nendo_plugin_musicgen-0.1.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "1f21720bdab34eb854c4ff145aa8df189c97dd9b453fb18c4f71a393c1c2f508",
"md5": "ff09131dfa8e3f0f69ec05d4bdbb4a2a",
"sha256": "525d8c1e4f4e274c6d0b430c8c1592d714e705e0c363bbbba840f9d557891c9a"
},
"downloads": -1,
"filename": "nendo_plugin_musicgen-0.1.3.tar.gz",
"has_sig": false,
"md5_digest": "ff09131dfa8e3f0f69ec05d4bdbb4a2a",
"packagetype": "sdist",
"python_version": "source",
"requires_python": ">=3.8,<3.11",
"size": 9406,
"upload_time": "2023-12-24T07:49:40",
"upload_time_iso_8601": "2023-12-24T07:49:40.649471Z",
"url": "https://files.pythonhosted.org/packages/1f/21/720bdab34eb854c4ff145aa8df189c97dd9b453fb18c4f71a393c1c2f508/nendo_plugin_musicgen-0.1.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2023-12-24 07:49:40",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "okio-ai",
"github_project": "nendo_plugin_musicgen",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"lcname": "nendo_plugin_musicgen"
}