Mustango

by Deep Cognition and Language Research Lab

About the model:

Music generation model.

Model type:

Audio

Model performance class:

Full

Link to the model:

https://huggingface.co/declare-lab/mustango

Base models:

AudioLDM

End model:

Mustango

End model license:

Apache-2.0

About the organisation:

Deep Cognition and Language Research Lab, an AI research lab.

Link to the organisation:

https://declare-lab.github.io/

Model release date:

November 2023

Availability

Base Model Data

Datasets mentioned in base model paper.

https://arxiv.org/pdf/2301.12503

End User Model Data

Dataset published on HuggingFace.

https://huggingface.co/datasets/amaai-lab/MusicBench

Base Model Weights

Weights made available on HuggingFace.

https://huggingface.co/cvssp/audioldm

End User Model Weights

Weights made available on HuggingFace.

https://huggingface.co/declare-lab/mustango

Training Code

Training script mentioned in model card.

https://huggingface.co/declare-lab/mustango

Documentation

Code Documentation

Training code documented.

https://huggingface.co/declare-lab/mustango

Hardware Architecture

Hardware published in arXiv paper.

https://arxiv.org/pdf/2311.08355

Preprint

Preprint published through arXiv.

https://arxiv.org/pdf/2311.08355

Paper

Paper published through ACL.

https://aclanthology.org/2024.naacl-long.459/

Modelcard

Model card contains comprehensive and sufficient information.

https://huggingface.co/declare-lab/mustango

Datasheet

Data sourcing comprehensively documented in paper.

https://arxiv.org/pdf/2311.08355

Access

Licenses

Apache-2.0, an OSI-approved license.

https://huggingface.co/declare-lab/mustango

Is this information not up to date?

Contribute here ->

Supported by the Centre for Language Studies and the Dutch Research Council. Website design & development © 2024 by BSTN. This version of the index generated 09 April 2026, website content last updated 11 March 2026.