FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control

by Dimitri von Rütte, Luca Biggio, Yannic Kilcher, Thomas Hofmann

• FIGARO: Generating Symbolic Music with Fine-Grained Artistic Control
  • Getting started
    • Setup
    • Preparing the Data
    • Download Pre-Trained Models
  • Training
  • Generation
  • Evaluation
  • Parameters
    • Training (train.py)
    • Generation (generate.py)
    • Evaluation (evaluate.py)

Getting started

Prerequisites:

• Python 3.9
• Conda

Setup

1. Clone this repository to your disk
2. Install required packages (see requirements.txt). With Conda:

conda create --name figaro python=3.9
conda activate figaro
pip install -r requirements.txt

Preparing the Data

To train models and to generate new samples, we use the Lakh MIDI dataset (altough any collection of MIDI files can be used).

1. Download (size: 1.6GB) and extract the archive file:

wget http://hog.ee.columbia.edu/craffel/lmd/lmd_full.tar.gz
tar -xzf lmd_full.tar.gz

2. You may wish to remove the archive file now: rm lmd_full.tar.gz

Download Pre-Trained Models

If you don't wish to train your own models, you can download our pre-trained models.

1. Download (size: 2.3GB) and extract the archive file:

wget -O checkpoints.zip https://polybox.ethz.ch/index.php/s/a0HUHzKuPPefWkW/download
unzip checkpoints.zip

2. You may wish to remove the archive file now: rm checkpoints.zip

Training

Training arguments such as model type, batch size, model params are passed to the training scripts via environment variables.

Available model types are:

• vq-vae: VQ-VAE model used for the learned desription
• figaro: FIGARO with both the expert and learned description
• figaro-expert: FIGARO with only the expert description
• figaro-learned: FIGARO with only the learned description
• figaro-no-inst: FIGARO (expert) without instruments
• figaro-no-chord: FIGARO (expert) without chords
• figaro-no-meta: FIGARO (expert) without style (meta) information
• baseline: Unconditional decoder-only baseline following Huang et al. (2018)

Example invocation of the training script is given by the following command:

MODEL=figaro-expert python src/train.py

For models using the learned description (figaro and figaro-learned), a pre-trained VQ-VAE checkpoint needs to be provided as well:

MODEL=figaro VAE_CHECKPOINT=./checkpoints/vq-vae.ckpt python src/train.py

Generation

To generate samples, make sure you have a trained checkpoint prepared (either download one or train it yourself). For this script, make sure that the dataset is prepared according to Preparing the Data. This is needed to extract descriptions, based on which new samples can be generated.

An example invocation of the generation script is given by the following command:

MODEL=figaro-expert CHECKPOINT=./checkpoints/figaro-expert.ckpt python src/generate.py

For models using the learned description (figaro and figaro-learned), a pre-trained VQ-VAE checkpoint needs to be provided as well:

MODEL=figaro CHECKPOINT=./checkpoints/figaro.ckpt VAE_CHECKPOINT=./checkpoints/vq-vae.ckpt python src/generate.py

Evaluation

We provide the evaluation scripts used to calculate the desription metrics on some set of generated samples. Refer to the previous section for how to generate samples yourself.

Example usage:

SAMPLE_DIR=./samples/figaro-expert python src/evaluate.py

Parameters

The following environment variables are available for controlling hyperparameters beyond their default value.

Training (train.py)

Model

Optimization

Others

Generation (generate.py)

Evaluation (evaluate.py)