Teklia/pylaia-home-alcar

PyLaia - HOME-Alcar

This model performs Handwritten Text Recognition in Latin on medieval documents.

Model description

The model was trained using the PyLaia library on two medieval datasets:

• Himanis (French)
• HOME-Alcar (Latin)

For training, text-lines were resized with a fixed height of 128 pixels, keeping the original aspect ratio.

An external 6-gram character language model can be used to improve recognition. The language model is trained on the text from the HOME Alcar training set.

Evaluation results

On HOME-Alcar text lines, the model achieves the following results:

set	Language model	CER (%)	WER (%)	N lines
test	no	8.35	26.15	6,932
test	yes	7.85	23.20	6,932

How to use?

Please refer to the documentation.

Cite us!

@inproceedings{pylaia-lib,
    author = "Tarride, Solène and Schneider, Yoann and Generali, Marie and Boillet, Melodie and Abadie, Bastien and Kermorvant, Christopher",
    title = "Improving Automatic Text Recognition with Language Models in the PyLaia Open-Source Library",
    booktitle = "Submitted at ICDAR2024",
    year = "2024"
}