Swa-bhasha Resource Hub: Romanized Sinhala to Sinhala Transliteration Systems and Data Resources

TL;DR

The paper introduces the Swa-bhasha Resource Hub, a comprehensive collection of data and tools for Romanized Sinhala to Sinhala transliteration, supporting NLP research and applications.

Contribution

It provides publicly accessible datasets and algorithms for Sinhala transliteration, along with a comparative analysis of existing transliteration applications.

Findings

Resources significantly aid Sinhala NLP research.

Open datasets and tools are publicly available.

Comparative analysis of transliteration applications included.

Abstract

The Swa-bhasha Resource Hub provides a comprehensive collection of data resources and algorithms developed for Romanized Sinhala to Sinhala transliteration between 2020 and 2025. These resources have played a significant role in advancing research in Sinhala Natural Language Processing (NLP), particularly in training transliteration models and developing applications involving Romanized Sinhala. The current openly accessible data sets and corresponding tools are made publicly available through this hub. This paper presents a detailed overview of the resources contributed by the authors and includes a comparative analysis of existing transliteration applications in the domain.