jisungk/deepjazz
Deep learning driven jazz generation using Keras & Theano!
Builds a two-layer LSTM neural network trained on MIDI files to generate original jazz compositions. The system learns melodic patterns and musical structure from input MIDI data, then synthesizes new sequences using Keras/Theano on CPU or GPU (NVIDIA CUDA). Integrates music21 for MIDI preprocessing and generation, requiring manual selection of melody tracks from source files.
2,896 stars. No commits in the last 6 months.
Stars
2,896
Forks
443
Language
Python
License
Apache-2.0
Category
Last pushed
May 14, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jisungk/deepjazz"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
Natooz/MidiTok
MIDI / symbolic music tokenizers for Deep Learning models 🎶
salu133445/muspy
A toolkit for symbolic music generation
mdeff/fma
FMA: A Dataset For Music Analysis
jacbz/Lofi
ML-supported lo-fi music generator
rbaltrusch/bach_generator
A Bach music generator using a neural network trained using a genetic algorithm.