pyclef 1.0.3

Desktop OMR tool for turning sheet music into annotations, audio, MIDI, and synchronized video.

PyClef

PyClef is a desktop Optical Music Recognition workflow for turning sheet music into annotated pages, audio, MIDI, and synchronized video.

Usage

from pyclef import Pyclef

Pyclef()

Or from the terminal:

pyclef

Model file

The YOLO model is not included in the PyPI package because it is larger than the default file limits for GitHub and PyPI.

On first processing, PyClef looks for the model in this order:

1. PYCLEF_MODEL_PATH, if set.
2. The user cache at ~/.pyclef/models/best.pt.
3. Automatic download from PYCLEF_MODEL_URL.

By default, PYCLEF_MODEL_URL points to the PyClef GitHub Release asset:

https://github.com/viniciusfs14/PyClef/releases/download/model-v1.0.0/best.pt.zip

Create that release and attach best.pt.zip to make the download automatic for users.

On Windows, you can create the release asset with:

Compress-Archive -Path .\pyclef_app\model\best.pt -DestinationPath .\best.pt.zip -Force

For manual setup, place best.pt here:

~/.pyclef/models/best.pt

Or set PYCLEF_MODEL_PATH to the full path of the model file before starting PyClef.

PDF, MP3, MIDI, and video support

PyClef is prepared for pip install usage:

• PDF pages are rendered with pypdfium2, which is installed with PyClef.
• MP3/video generation uses FFmpeg through imageio-ffmpeg, which is installed with PyClef.
• MIDI generation is pure Python through mido.

If you prefer using a system Poppler installation for PDF rendering, set PYCLEF_POPPLER_PATH before starting PyClef. This is optional and only used as a fallback.