README.md

metadata

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

PyLaia - IAM

This model performs Handwritten Text Recognition in English on modern documents.

Model description

The model was trained using the PyLaia library on the RWTH split of the IAM database.

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

split	N lines
train	6,482
val	976
test	2,915

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

Evaluation results

The model achieves the following results:

set	Language model	CER (%)	WER (%)	N lines
test	no	8.44	24.51	2,915
test	yes	7.50	20.98	2,915

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"
}