---
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](https://fki.tic.heia-fr.ch/databases/iam-handwriting-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](https://atr.pages.teklia.com/pylaia/).

## Cite us!

```bibtex
@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"
}
```