metadata

library_name: PyLaia
license: mit
tags:
  - PyLaia
  - PyTorch
  - atr
  - htr
  - ocr
  - modern
  - handwritten
metrics:
  - CER
  - WER
language:
  - fr
datasets:
  - Teklia/rimes-2011-lines
pipeline_tag: image-to-text

PyLaia - RIMES

This model performs Handwritten Text Recognition in French.

Model description

The model has been trained using the PyLaia library on the RIMES dataset.

Training images were resized with a fixed height of 128 pixels, keeping the original aspect ratio.

split	N lines
train	10,188
val	1,138
test	778

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

Evaluation results

The model achieves the following results:

set	Language model	CER (%)	WER (%)	N lines
test	no	4.53	15.06	778
test	yes	3.47	10.20	778

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"
}