Python package for generating audio with neural networks


Keywords
audio, music, sound, deep-learning, audio-files, generative-model, google-colab, jupyter-notebook, lightning, neptune, pypi-package, python, pytorch, torch
License
GPL-3.0
Install
pip install mimikit==0.3.2

Documentation

mimikit

The MusIc ModelIng toolKIT (mimikit) is a python package that does Machine Learning with audio data.

Currently, it focuses on training auto-regressive neural networks to generate audio.

but it does also contain an app to perform basic & experimental clustering of audio data in a notebook.

Installation

you can install with pip

pip install mimikit[torch]

or with

pip install --upgrade mimikit[torch]

if you are looking for the latest version

for an editable install, you'll need

pip install -e . --config-settings editable_mode=compat

Usage

Head straight to the notebooks for example usage of mimikit, or open them directly in Colab:

Open In Colab

Output Samples

You can explore the outputs of different trainings done with mimikit at this demo website:

https://ktonal.github.io/mimikit-demo-outputs

License

mimikit is distributed under the terms of the GNU General Public License v3.0