Skip to content

Commit

Permalink
Update README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
dorienh authored Jun 4, 2024
1 parent 3df566c commit a9b79bd
Showing 1 changed file with 16 additions and 4 deletions.
20 changes: 16 additions & 4 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -5,9 +5,11 @@
<a href="https://huggingface.co/datasets/amaai-lab/MidiCaps">Dataset</a>
</div>

In this repository, we provide the pipeline to extract a comprehensive set of music-specific features extracted from MIDI files. These features succinctly characterize the musical content, encompassing tempo, chord progression, time signature, instrument presence, genre, and mood. Consecutively we provide the script to generate captions from unseen MIDI files.
In this repository, we provide the pipeline to extract a comprehensive set of music-specific features extracted from MIDI files. These features succinctly characterize the musical content, encompassing tempo, chord progression, time signature, instrument presence, genre, and mood. Consecutively we provide the script to generate captions from your own collection of MIDI files.

To access the MidiCaps dataset, please visit our huggingface dataset page: [<img src="imgs/hf-logo.png" alt="dataset" width= "5%" class="center" >](https://huggingface.co/datasets/amaai-lab/MidiCaps)
To directly download the MidiCaps dataset, please visit our huggingface dataset page: [<img src="imgs/hf-logo.png" alt="dataset" width= "5%" class="center" >](https://huggingface.co/datasets/amaai-lab/MidiCaps).

The below code will help you extract captions from your own collection of MIDI files. If you use this model or dataset, please cite our paper (see below).

## Installation Guide
```bash
Expand All @@ -20,12 +22,22 @@ pip install -r requirements.txt
```bash
python pipeline.py --config config.cfg
```
Output of this will be `all_files_output.json`. We generate `test.json` from this to do in-context learning for [claude 3](https://www.anthropic.com/news/claude-3-family). we provide a sample `test.json` and a basic script to run claude 3. Users have to add claude 3 key as environment variable ANTHROPIC_API_KEY.
Output of this will be `all_files_output.json`. We generate `test.json` from this to do in-context learning for [claude 3](https://www.anthropic.com/news/claude-3-family). We provide a sample `test.json` and a basic script to run claude 3. Users have to add claude 3 key as environment variable `ANTHROPIC_API_KEY`.
```bash
export ANTHROPIC_API_KEY=<your claude 3 key>
python captions_claude.py
```
Please change line 59 in caption_claude.py for your preferred location.

## Citation
If you find our work useful, please consider citing our work
If you find our work useful, please cite our paper:

'''
@article{Melechovsky2024,
author = {Jan Melechovsky and Abhinaba Roy and Dorien Herremans},
title = {MidiCaps - A Large-scale MIDI Dataset with Text Captions},
year = {2024},
}
'''

APA: Jan Melechovsky, Abhinaba Roy, Dorien Herremans, 2024, MidiCaps - A large-scale MIDI dataset with text captions.

0 comments on commit a9b79bd

Please sign in to comment.