MusGO Framework: Assessing Openness in Music-Generative AI

This website builds on the paper MusGO: A Community-Driven Framework for Assessing Openness in Music-Generative AI, authored by Roser Batlle-Roca, Laura Ibáñez-Martínez, Xavier Serra, Emilia Gómez, and Martín Rocamora, and published in the Proceedings of the 26th International Society for Music Information Retrieval Conference (ISMIR 2025). It serves not only as a companion to the publication, but also as a living resource, which is continuously updated and shaped by contributions from the community.

GANsynth

Google Magenta · 2019

Algorithm for synthesizing audio with generative adversarial networks.

Application types: Audio synthesisMIDI-to-audio

Architecture:GAN

Essential categories

Category	Status	Notes
Source code	✔︎ Open	Source code is available.
Training data	~ Partial	Dataset is available, but the reduced version that they use and the newly created test/train splits are not provided.
Model weights	✔︎ Open	Two pretrained checkpoints are provided.
Code documentation	✔︎ Open	Codebase is documented, including high-level instructions and configuration files.
Training procedure	✔︎ Open	Training procedure is fully documented, including hardware requirements and model configuration.
Evaluation procedure	~ Partial	Evaluation metrics are described but exact implementations are not referenced.
Research paper	✔︎ Open	Accepted at ICLR 2019.
Licensing	✔︎ Open	System is covered by Apache License.

Desirable categories

Category	Status	Notes
Model card	∅ Not included	Very few details are given of the pretrained checkpoints.
Datasheet	∅ Not included	Not available.
Package	⭐ Included	Available within the magenta pip package.
User-oriented application	∅ Not included	Not available.
Supplementary material page	⭐ Included	Demo page is available, including sound examples of the model's capabilities.

Raw YAML file with complete evaluation.