Nendo Plugin Vampnet
Nendo Plugin for VampNet: Music Generation via Masked Acoustic Token Modeling (by Hugo Flores Garcia).
Features
- Generate unconditional variations
- Use custom finetuned vampnet models
- Generate in- and outpaintings from a
NendoTrack
Requirements
Due to madmom versions < 0.17 errors with python 3.10, we require the latest version of the package from git, where this is fixed. See also this related issue.
Run:
pip install git+https://github.com/CPJKU/madmom.git@0551aa8
This plugin also requires the manual installation of vampnet via its git repository:
pip install git+https://github.com/hugofloresgarcia/vampnet.git@0c0c6bc
For further information, please refer to the original vampnet repository.
Installation
- Install Nendo
pip install nendo-plugin-vampnet
Usage
Take a look at a basic usage example below. For more detailed information, please refer to the documentation.
For more advanced examples, check out the examples folder. or try it in colab:
from nendo import Nendo, NendoConfig
nd = Nendo(config=NendoConfig(plugins=["nendo_plugin_vampnet"]))
track = nd.library.add_track(file_path='/path/to/track.mp3')
vamp = nd.plugins.vampnet(track=track, prefix_secs=2, suffix_secs=0)
vamp.play()Contributing
Visit our docs to learn all about how to contribute to Nendo: Contributing
License
Nendo: MIT License
Vampnet: MIT License
Pretrained Models: The weights for the models are licensed CC BY-NC-SA 4.0. Likewise, any VampNet models fine-tuned on the pretrained models are also licensed CC BY-NC-SA 4.0.
