Skip to content

A Deep Learning Audio Plugin that Classifies Beatboxes in Real Time.

License

Notifications You must be signed in to change notification settings

eupston/Deepbox

Repository files navigation

Deepbox

A Deep Learning Audio Plugin that Classifies Beatboxes and converts to midi in Real Time.

Welcome to the Deepbox repository!

Deepbox is an audio plugin that uses a convolutional neural network to classify and predict beatboxes in realtime. You can then create a midi file from the plugin with the corresponding beats. It works at any tempo and uses the DAW as it's master tempo. You can view a demo of Deepbox here.

Supported Platforms Builds:

AU/VST3

Model Training:

All the code for creating a CNN model is in ModelCreation

  1. To Build Your Own Keras Model:

You can run this python file and change the global test and training data variables.

python CNNAudioClassifer.py

  1. Convert Keras Model into an fdeep json model:

python ConvertModel.py <input .h5 filename here> <output .json filename here>

The model used for this plugin was trained with audio sample sizes of 512 samples.

Dependencies:

  • Frugally Deep: Used for inferencing Keras models in C++
  • Essentia: Used to extract audio features for training and inference.
  • Juce: Used as the core audio plugin framework

About

A Deep Learning Audio Plugin that Classifies Beatboxes in Real Time.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published