smashcima 0.2.0

Training data synthesizer for OMR

A library and a framework for synthesizing images containing handwritten music, intended for the creation of training data for OMR models.

Try out the demo on 🤗 Huggingface Spaces right now!
Example output with MUSCIMA++ writer no. 28 style:

Install from pypi with:

pip install smashcima

Getting started

To quickly learn how to start using Smashcima for your project, start with the tutorials:

1. Producing music notation images
2. Changing background texture
3. Using custom glyphs

How it works

Smashcima is primarily a framework and a set of crafted interfaces for building custom visual-data related synthesizers.

• Introduction
• Models and service orchestration
• Scene
  • Scene objects
  • Affine spaces and rendering
  • Semantic music scene objects
  • Visual music scene objects
• Synthesis
  • Synthesizer interfaces
  • Glyphs
  • Style control
• Asset bundles
• ...

If you feel like improving the library, take a look at the TODO List.

After cloning

Create a virtual environment and install dependencies:

python3 -m venv .venv
.venv/bin/pip3 install -e .

# to run jupyter notebooks:
.venv/bin/pip3 install -e .[jupyter]

# to run the gradio demo:
.venv/bin/pip3 install -e .[gradio]

Checklists

• Before commit
• Publishing to PyPI
• Deploying Gradio Demo

Acknowledgement

There's a publication being written. Until then, you can cite the original Mashcima paper:

Jiří Mayer and Pavel Pecina. Synthesizing Training Data for Handwritten Music Recognition. 16th International Conference on Document Analysis and Recognition, ICDAR 2021. Lausanne, September 8-10, pp. 626-641, 2021.

Contact

Developed and maintained by Jiří Mayer ([e-mail]) as part of the Prague Music Computing Group lead by Jan Hajič jr. ([e-mail]).