LSTM to generate drum tracks based on Metallica's midi drum tracks
Latest commit 4e65597 Jan 24, 2017 @keunwoochoi committed on GitHub Update


A LSTM network that learns from the drum tracks of Metallica and generates new tracks.


  • keras, a deeplearning framework
  • python-midi, to get midi file
  • numpy, probably you already have it.


  • Clone the repo
  • $ python to get generated drum track in text file
  • text->midi: $ python - this is when you need python-midi
  • Use this text file, an aggregated-and-encoded text file for Metallica's drum tracks, to do something more
  • This folder contains the original drum midi tracks.

External links


Text-based LSTM networks for Automatic Music Composition, Keunwoo Choi, George Fazekas, Mark Sandler, 1st Conference on Computer Simulation of Musical Creativity, Huddersfield, UK, 2016, arXiv, pdf, bib