JASCO

by Meta

About the model:

Conditional audio generation based on audio samples or text.

Model type:

Audio

Model performance class:

Limited

Link to the model:

https://huggingface.co/facebook/jasco-chords-drums-melody-1B

Base models:

(undefined)

End model:

JASCO-Chords-Drums-Melody-1B

End model license:

CC-BY-NC-4.0

About the organisation:

Meta, a major technology company.

Link to the organisation:

https://ai.meta.com/

Model release date:

January 2025

Availability

Base Model Data

End User Model Data

Base Model Weights

https://huggingface.co/facebook/jasco-chords-drums-melody-1B

End User Model Weights

https://huggingface.co/facebook/jasco-chords-drums-melody-1B

Training Code

Training code provided through GitHub.

https://github.com/facebookresearch/audiocraft

Documentation

Code Documentation

Repository thoroughly documented.

https://github.com/facebookresearch/audiocraft

Hardware Architecture

Preprint

https://arxiv.org/abs/2406.10970

Paper

Modelcard

https://huggingface.co/papers/2406.10970

Datasheet

Access

Package

API and Meta Prompts

Licenses

weights as CC-BY-NC-4.0

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 10 March 2026, website content last updated 11 March 2026.