Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/StefanHeng/Symbolic-Music-Generation
Symbolic music generation taking inspiration from NLP and human composition process
https://github.com/StefanHeng/Symbolic-Music-Generation
autoregressive-models melody-extraction melody-generation midi music-generation music-xml nlp reformer representation-learning transformer transformer-decoder transformer-xl transformers-models
Last synced: 3 months ago
JSON representation
Symbolic music generation taking inspiration from NLP and human composition process
- Host: GitHub
- URL: https://github.com/StefanHeng/Symbolic-Music-Generation
- Owner: StefanHeng
- License: mit
- Created: 2021-11-09T04:24:10.000Z (about 3 years ago)
- Default Branch: master
- Last Pushed: 2023-06-28T21:34:12.000Z (over 1 year ago)
- Last Synced: 2024-04-05T19:32:04.651Z (7 months ago)
- Topics: autoregressive-models, melody-extraction, melody-generation, midi, music-generation, music-xml, nlp, reformer, representation-learning, transformer, transformer-decoder, transformer-xl, transformers-models
- Language: Python
- Homepage:
- Size: 46.3 MB
- Stars: 16
- Watchers: 2
- Forks: 5
- Open Issues: 1
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Symbolic Music Generation
Symbolic music generation taking inspiration from NLP Language Modeling, human composition process and music theory.Contributor: [Stefan/Yuzhao Heng](https://stefanheng.github.io), [Carson/Jiachun Zhang](https://github.com/SonyaInSiberia), [Xiaoyang Song](https://github.com/Xiaoyang-Song).
Mentored by [Artem Abzaliev](http://artem.site44.com),
supported by [Prof. Rada Mihalcea](https://web.eecs.umich.edu/~mihalcea/) at [LIT](https://lit.eecs.umich.edu/people.html).## Run the Scripts
### Getting Started
Python version `3.10.8`.
Modify the `DIR_DSET` variable in file [`project_paths.py`](https://github.com/StefanHeng/Symbolic-Music-Generation/blob/master/musicnlp/util/project_paths.py)
as instructed.Run
```bash
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`](https://github.com/StefanHeng/Symbolic-Music-Generation/blob/master/musicnlp/util/config.json).Add datasets to `DIR_DSET`, then see [`music_export.py`](https://github.com/StefanHeng/Symbolic-Music-Generation/blob/master/musicnlp/preprocess/music_export.py) for encoding Music MXL files.
## Music Samples
See [`generated-samples`](https://github.com/StefanHeng/Symbolic-Music-Generation/tree/master/generated-samples).
## Dataset
Datasets linked [here](https://drive.google.com/drive/folders/1T4TDRjj4nwQWRoytBYNg5VlqHCivTjyP?usp=sharing). Dataset visualizations [here](https://github.com/StefanHeng/Symbolic-Music-Generation/blob/master/notebook/visualize/dataset_stats.ipynb).