PyLaia
Collection
The PyLaia collection contains models designed for Automatic Text Recognition (ATR) from line images.
•
14 items
•
Updated
•
1
This model performs Handwritten Text Recognition in Austrian German.
The model has been trained using the PyLaia library on the NewsEye / READ OCR training dataset from Austrian Newspapers (19th C.) dataset.
Training images were resized with a fixed height of 128 pixels, keeping the original aspect ratio.
split | N lines |
---|---|
train | 52,834 |
val | 4,667 |
An external 6-gram character language model can be used to improve recognition. The language model is trained on the text from the NewsEye training set.
The model achieves the following results:
set | Language model | CER (%) | WER (%) | N lines |
---|---|---|---|---|
val | no | 1.82 | 7.77 | 4,667 |
val | yes | 1.77 | 7.01 | 4,667 |
Please refer to the documentation.
@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"
}