EdgeMusicTransformer: Source Code and Experimental Resources for Context-Aware Lightweight Symbolic Music Generation
This software package provides the implementation and experimental resources of EdgeMusicTransformer, a context-aware lightweight Transformer framework for symbolic music generation. It includes model architecture, REMI-based tokenization, dataset preprocessing, training and evaluation scripts, context-length analysis, host-CPU profiling, and ablation experiments. The package is intended to support reproducibility and further research on computationally efficient symbolic music generation.
Authors
- Yifan Zhang
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-09
- DOI
- https://doi.org/10.5281/zenodo.24093572
- Primary Topic
- Music Technology and Sound Studies
- Type
- article
- Field-Weighted Citation Impact
- 0.00