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.

MusicLM

Google Research and IRCAM · 2023

Generative music model that can be conditioned across various genres and styles based on text prompts.

Application types: Text-to-music

Architecture:Autoregressive transformer

Essential categories

Category	Status	Notes
Source code	✘ Closed	Source code not available.
Training data	~ Partial	Training data is not available nor properly described.
Model weights	✘ Closed	Not provided.
Code documentation	✘ Closed	Not available.
Training procedure	~ Partial	Training procedure is partially documented, missing the hardware requirements.
Evaluation procedure	~ Partial	Evaluation data is provided and metrics are described, but exact implementations are not referenced.
Research paper	~ Partial	Peer-reviewed paper not found.
Licensing	✘ Closed	Not available.

Desirable categories

Category	Status	Notes
Model card	∅ Not included	Not available.
Datasheet	∅ Not included	Not available.
Package	∅ Not included	Not available.
User-oriented application	∅ Not included
Supplementary material page	⭐ Included	Complementary page is available with sound examples and demonstration of the model's capabilities.

Raw YAML file with complete evaluation.