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This model performs Handwritten Text Recognition in French on historical documents.
The model was trained using the PyLaia library on the Belfort dataset.
For training, text-lines were resized with a fixed height of 128 pixels, keeping the original aspect ratio. Vertical lines are discarded.
split | N lines |
---|---|
train | 25,800 |
val | 3,102 |
test | 3,819 |
An external 6-gram character language model can be used to improve recognition. The language model is trained on the text from the Belfort training set.
The model achieves the following results:
set | Language model | CER (%) | WER (%) | N lines |
---|---|---|---|---|
test | no | 10.54 | 28.12 | 3,819 |
test | yes | 9.52 | 23.73 | 3,819 |
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"
}
@inproceedings{belfort-2023,
author = {Tarride, Solène and Faine, Tristan and Boillet, Mélodie and Mouchère, Harold and Kermorvant, Christopher},
title = {Handwritten Text Recognition from Crowdsourced Annotations},
year = {2023},
isbn = {9798400708411},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3604951.3605517},
doi = {10.1145/3604951.3605517},
booktitle = {Proceedings of the 7th International Workshop on Historical Document Imaging and Processing},
pages = {1–6},
numpages = {6},
keywords = {Crowdsourcing, Handwritten Text Recognition, Historical Documents, Neural Networks, Text Aggregation},
series = {HIP '23}
}