Symbolic Music Generation

Symbolic music generation taking inspiration from NLP Language Modeling, human composition process and music theory.

Contributor: Stefan/Yuzhao Heng, Carson/Jiachun Zhang, Xiaoyang Song. Mentored by Artem Abzaliev, supported by Prof. Rada Mihalcea at LIT.

Run the Scripts

Getting Started

Python version 3.10.8.

Modify the DIR_DSET variable in file project_paths.py as instructed.

Run

python musicnlp/util/config.py

A folder named as DIR_DSET should be kept at the same level as this repository, with dataset folder names specified as in config.json.

Add datasets to DIR_DSET, then see music_export.py for encoding Music MXL files.

Music Samples

See generated-samples.

Dataset

Datasets linked here. Dataset visualizations here.