Saved in:
Bibliographic Details
Main Authors: Sarawgi, Anjali, Arias, Esteban Garces, Zotter, Christof
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.17111
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917441569816576
author Sarawgi, Anjali
Arias, Esteban Garces
Zotter, Christof
author_facet Sarawgi, Anjali
Arias, Esteban Garces
Zotter, Christof
contents This paper presents the first end-to-end pipeline for Handwritten Text Recognition (HTR) for Old Nepali, a historically significant but low-resource language. We adopt a line-level transcription approach and systematically explore encoder-decoder architectures and data-centric techniques to improve recognition accuracy. Our best model achieves a Character Error Rate (CER) of 4.9\%. In addition, we implement and evaluate decoding strategies and analyze token-level confusions to better understand model behavior and error patterns. Although the evaluation dataset is confidential, we release our training code, model configurations, and evaluation scripts to support further research on HTR for low-resource historical scripts.
format Preprint
id arxiv_https___arxiv_org_abs_2512_17111
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Digitizing Nepal's Written Heritage: A Comprehensive HTR Pipeline for Old Nepali Manuscripts
Sarawgi, Anjali
Arias, Esteban Garces
Zotter, Christof
Machine Learning
This paper presents the first end-to-end pipeline for Handwritten Text Recognition (HTR) for Old Nepali, a historically significant but low-resource language. We adopt a line-level transcription approach and systematically explore encoder-decoder architectures and data-centric techniques to improve recognition accuracy. Our best model achieves a Character Error Rate (CER) of 4.9\%. In addition, we implement and evaluate decoding strategies and analyze token-level confusions to better understand model behavior and error patterns. Although the evaluation dataset is confidential, we release our training code, model configurations, and evaluation scripts to support further research on HTR for low-resource historical scripts.
title Digitizing Nepal's Written Heritage: A Comprehensive HTR Pipeline for Old Nepali Manuscripts
topic Machine Learning
url https://arxiv.org/abs/2512.17111