taste-music-dataset

A multimodal dataset shaped to fine tune MusicGEN

https://github.com/matteospanio/taste-music-dataset

Science Score: 67.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
    Found CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
    Found .zenodo.json file
  • DOI references
    Found 2 DOI reference(s) in README
  • Academic publication links
    Links to: arxiv.org, zenodo.org
  • Committers with academic emails
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (9.2%) to scientific vocabulary
Last synced: 7 months ago · JSON representation ·

Repository

A multimodal dataset shaped to fine tune MusicGEN

Basic Info
  • Host: GitHub
  • Owner: matteospanio
  • License: cc-by-4.0
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 46.9 KB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 1
Created almost 2 years ago · Last pushed about 1 year ago
Metadata Files
Readme License Code of conduct Citation

README.md

taste-music-dataset

License: CC BY 4.0 DOI arXiv

This is the repository to make a fine-tuning dataset for MusicGEN, a model for music generation by Facebook Research.

This dataset has been released under the project A Multimodal Symphony: Integrating Taste and Sound through Generative AI, and is an attachment to the paper A Multimodal Symphony: Integrating Taste and Sound through Generative AI by Matteo Spanio, Massimiliano Zampini, Antonio Rodà and Franco Pierucci.

How to use

  1. Clone this repository
  2. Run make data to download the dataset and generate the fine-tuning dataset

At the end of the process you should have a folder named data with the following structure: data ├── dataset ├── eval ├── metadata_1.xlsx ├── metadata_2.xlsx └── train

Move to your MusicGEN folder and copy the dataset to make some finetuning, if you cloned the audiocraft repo you can run the following commands from the audiocraft folder:

bash mv /path/to/taste-music-dataset/data/dataset ./dataset/finetune mv /path/to/taste-music-dataset/data/train ./egs/train mv /path/to/taste-music-dataset/data/eval ./egs/eval

Citation

If you use this code or the data in your research, please cite the following article:

@misc{spanio2025multimodalsymphonyintegratingtaste, title={A Multimodal Symphony: Integrating Taste and Sound through Generative AI}, author={Matteo Spanio and Massimiliano Zampini and Antonio Rodà and Franco Pierucci}, year={2025}, eprint={2503.02823}, archivePrefix={arXiv}, primaryClass={cs.SD}, url={https://arxiv.org/abs/2503.02823}, }

Acknowledgements

We thank the authors of the Taste & Affect Music Database[^1], a set of 100 musical stimuli suitable for crossmodal and affective research, on which this dataset is based.

License

This dataset is distributed under the CC BY 4.0 license.

[^1]: Guedes, D., Prada, M., Garrido, M. V., & Lamy, E. (2022, November 24). The Taste & Affect Music Database. Retrieved from osf.io/2cqa5

Owner

  • Name: Matteo
  • Login: matteospanio
  • Kind: user
  • Location: Padua, Italy
  • Company: CSC @ Unipd

Ph.D. student @CSCPadova. I'm a linux and python lover. I also have a conservatory degree in clarinet.

Citation (CITATION.cff)

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: Taste music dataset
message: >-
  If you use this dataset, please cite it using the metadata
  from this file.
type: dataset
authors:
  - given-names: Matteo
    name-particle: M
    family-names: Spanio
    email: spanio@dei.unipd.it
    affiliation: University of Padova
    orcid: 'https://orcid.org/0000-0002-2436-7208'
repository-code: 'https://github.com/matteospanio/taste-music-dataset'
url: 'https://osf.io/2cqa5/'
keywords:
  - dataset
  - Crossmodal correspondences
  - multimodality
  - music
  - taste
  - Synesthesia
license: CC-BY-4.0
identifiers:
  - type: doi
    value: 10.5281/zenodo.14879129

GitHub Events

Total
  • Release event: 1
  • Push event: 5
  • Create event: 1
Last Year
  • Release event: 1
  • Push event: 5
  • Create event: 1

Committers

Last synced: 9 months ago

All Time
  • Total Commits: 18
  • Total Committers: 1
  • Avg Commits per committer: 18.0
  • Development Distribution Score (DDS): 0.0
Past Year
  • Commits: 14
  • Committers: 1
  • Avg Commits per committer: 14.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Matteo s****0@g****m 18

Issues and Pull Requests

Last synced: 9 months ago

All Time
  • Total issues: 0
  • Total pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Total issue authors: 0
  • Total pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
Top Authors
Issue Authors
Pull Request Authors
Top Labels
Issue Labels
Pull Request Labels

Dependencies

requirements.txt pypi
  • audioread ==3.0.1
  • certifi ==2024.7.4
  • cffi ==1.16.0
  • charset-normalizer ==3.3.2
  • decorator ==5.1.1
  • et-xmlfile ==1.1.0
  • idna ==3.7
  • joblib ==1.4.2
  • lazy_loader ==0.4
  • librosa ==0.10.2.post1
  • llvmlite ==0.43.0
  • msgpack ==1.0.8
  • mutagen ==1.47.0
  • numba ==0.60.0
  • numpy ==1.26.4
  • openpyxl ==3.1.5
  • packaging ==24.1
  • pandas ==2.2.1
  • platformdirs ==4.2.2
  • pooch ==1.8.2
  • pycparser ==2.22
  • python-dateutil ==2.9.0.post0
  • pytz ==2024.1
  • requests ==2.32.3
  • scikit-learn ==1.5.1
  • scipy ==1.14.0
  • six ==1.16.0
  • soundfile ==0.12.1
  • soxr ==0.3.7
  • threadpoolctl ==3.5.0
  • typing_extensions ==4.12.2
  • tzdata ==2024.1
  • urllib3 ==2.2.2