@inproceedings{nakarmi-etal-2026-nepal,
title = "{N}epal Script Text Recognition from Ancient Artifacts: Challenges and Opportunities",
author = "Nakarmi, Swornim and
Sthapit, Sarin and
Tuladhar, Sahil Ratna and
Shakya, Arya and
Bal, Bal Krishna and
Chulyadyo, Rajani",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.248/",
doi = "10.63317/427yvm8biop7",
pages = "3161--3170",
abstract = "Nepal Script, a script of significant linguistic, historical, and cultural importance, can be found in ancient artifacts in Nepal. As this script has faced a decline in use, it is considered among endangered scripts at present. For its revival and preservation, it is important to digitize ancient artifacts written in Nepal Script and create an accessible digital dataset. Among such artifacts are stone inscriptions, and manuscripts, from which we attempt to recognize texts using Artificial Intelligence techniques. This paper presents our approach of preparing a dataset through an extensive data acquisition method, and developing a system that recognizes Nepal Script texts from images. Our system combines the YOLOv8 algorithm with Convolutional Recurrent Neural Network architecture and Connectionist Temporal Classification loss. Our dataset consists of 5,219 text line images from ancient stone inscriptions, manuscripts, and modern handwritten and typed documents. Utilizing an augmented dataset of 41,752 samples, our system achieved 12.61{\%} Character Error Rate. Despite the small training dataset, our model successfully predicted texts in not only new stone inscriptions and manuscripts but also wooden and copper plate inscriptions. We expect our contributions will encourage further research on Nepal Script and other Nepalese scripts."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nakarmi-etal-2026-nepal">
<titleInfo>
<title>Nepal Script Text Recognition from Ancient Artifacts: Challenges and Opportunities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Swornim</namePart>
<namePart type="family">Nakarmi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarin</namePart>
<namePart type="family">Sthapit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sahil</namePart>
<namePart type="given">Ratna</namePart>
<namePart type="family">Tuladhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arya</namePart>
<namePart type="family">Shakya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bal</namePart>
<namePart type="given">Krishna</namePart>
<namePart type="family">Bal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajani</namePart>
<namePart type="family">Chulyadyo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Nepal Script, a script of significant linguistic, historical, and cultural importance, can be found in ancient artifacts in Nepal. As this script has faced a decline in use, it is considered among endangered scripts at present. For its revival and preservation, it is important to digitize ancient artifacts written in Nepal Script and create an accessible digital dataset. Among such artifacts are stone inscriptions, and manuscripts, from which we attempt to recognize texts using Artificial Intelligence techniques. This paper presents our approach of preparing a dataset through an extensive data acquisition method, and developing a system that recognizes Nepal Script texts from images. Our system combines the YOLOv8 algorithm with Convolutional Recurrent Neural Network architecture and Connectionist Temporal Classification loss. Our dataset consists of 5,219 text line images from ancient stone inscriptions, manuscripts, and modern handwritten and typed documents. Utilizing an augmented dataset of 41,752 samples, our system achieved 12.61% Character Error Rate. Despite the small training dataset, our model successfully predicted texts in not only new stone inscriptions and manuscripts but also wooden and copper plate inscriptions. We expect our contributions will encourage further research on Nepal Script and other Nepalese scripts.</abstract>
<identifier type="citekey">nakarmi-etal-2026-nepal</identifier>
<identifier type="doi">10.63317/427yvm8biop7</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.248/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>3161</start>
<end>3170</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Nepal Script Text Recognition from Ancient Artifacts: Challenges and Opportunities
%A Nakarmi, Swornim
%A Sthapit, Sarin
%A Tuladhar, Sahil Ratna
%A Shakya, Arya
%A Bal, Bal Krishna
%A Chulyadyo, Rajani
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F nakarmi-etal-2026-nepal
%X Nepal Script, a script of significant linguistic, historical, and cultural importance, can be found in ancient artifacts in Nepal. As this script has faced a decline in use, it is considered among endangered scripts at present. For its revival and preservation, it is important to digitize ancient artifacts written in Nepal Script and create an accessible digital dataset. Among such artifacts are stone inscriptions, and manuscripts, from which we attempt to recognize texts using Artificial Intelligence techniques. This paper presents our approach of preparing a dataset through an extensive data acquisition method, and developing a system that recognizes Nepal Script texts from images. Our system combines the YOLOv8 algorithm with Convolutional Recurrent Neural Network architecture and Connectionist Temporal Classification loss. Our dataset consists of 5,219 text line images from ancient stone inscriptions, manuscripts, and modern handwritten and typed documents. Utilizing an augmented dataset of 41,752 samples, our system achieved 12.61% Character Error Rate. Despite the small training dataset, our model successfully predicted texts in not only new stone inscriptions and manuscripts but also wooden and copper plate inscriptions. We expect our contributions will encourage further research on Nepal Script and other Nepalese scripts.
%R 10.63317/427yvm8biop7
%U https://aclanthology.org/2026.lrec-1.248/
%U https://doi.org/10.63317/427yvm8biop7
%P 3161-3170
Markdown (Informal)
[Nepal Script Text Recognition from Ancient Artifacts: Challenges and Opportunities](https://aclanthology.org/2026.lrec-1.248/) (Nakarmi et al., LREC 2026)
ACL