deepharmony

Deep Harmony is a machine learning project for creating harmonies based on a given melody.

Using LSTM neural networks to produce accompaniments for melodies. Developed for a music practicum class at WPI.

Currently, Deep Harmony is learning to mimic the behavior of Bach Chorales created by David Cope.

Deep Harmony is written in Python 3.5 and uses the Keras machine learning library.

Dependencies:

Jupyter Notebook, an interactive programming environment and editor (necessary for using the .ipynb files)
Python 3.5, and the following libraries:
numpy and matplotlib, for numerical computation and graphical plotting.
- music21, for processing music data
- tqdm, for nice progress bars
- Keras, a deep learning library. We recommend installing it with the Theano backend, but the code should work with the TensorFlow backend as well.
musescore 2+, for allowing music21 to render music as pictures

Jupyter Notebook, Python, Numpy, and Matplotlib are all packaged together in Anaconda, and we recommend installing them that way.

Name		Name	Last commit message	Last commit date
Latest commit History 39 Commits
data		data
README.md		README.md
dependencies		dependencies
keras-model-1.ipynb		keras-model-1.ipynb
keras-model-2-holds-with-pitches.ipynb		keras-model-2-holds-with-pitches.ipynb
keras-model-2-nopreprocess.ipynb		keras-model-2-nopreprocess.ipynb
keras-model-2.ipynb		keras-model-2.ipynb
keras-model-multidimensional-output.ipynb		keras-model-multidimensional-output.ipynb
music21-tests-voice-separation.ipynb		music21-tests-voice-separation.ipynb
music21-tests.ipynb		music21-tests.ipynb
preprocess.py		preprocess.py
util.py		util.py