# Cross-Temporal Sinhala OCR: Page-Level Adaptation and Diachronic Analysis

arXiv: https://arxiv.org/abs/2606.29378 · HTML: https://mlsanity.com/paper/2606.29378/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 29 references that are in the map.
- First posted on arXiv 28 Jun 2026.

## Builds on (most cited first, 21 of 21)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognition](https://mlsanity.com/paper/1507.05717/) (2015)
- [TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models](https://mlsanity.com/paper/2109.10282/) (2021)
- [Character Region Awareness for Text Detection](https://mlsanity.com/paper/1904.01941/) (2019)
- [EAST: An Efficient and Accurate Scene Text Detector](https://mlsanity.com/paper/1704.03155/) (2017)
- [DeepSeek-OCR: Contexts Optical Compression](https://mlsanity.com/paper/2510.18234/) (2025)
- [Robust Scene Text Recognition with Automatic Rectification](https://mlsanity.com/paper/1603.03915/) (2016)
- [KOSMOS-2.5: A Multimodal Literate Model](https://mlsanity.com/paper/2309.11419/) (2023)
- [DeepSeek-OCR 2: Visual Causal Flow](https://mlsanity.com/paper/2601.20552/) (2026)
- [What If We Only Use Real Datasets for Scene Text Recognition? Toward Scene Text Recognition With Fewer Labels](https://mlsanity.com/paper/2103.04400/) (2021)
- [LightOnOCR: A 1B End-to-End Multilingual Vision-Language Model for State-of-the-Art OCR](https://mlsanity.com/paper/2601.14251/) (2026)
- [Benchmarking Vision-Language Models on Chinese Ancient Documents: From OCR to Knowledge Reasoning](https://mlsanity.com/paper/2509.09731/) (2025)
- [Zero-shot OCR Accuracy of Low-Resourced Languages: A Comparative Analysis on Sinhala and Tamil](https://mlsanity.com/paper/2507.18264/) (2025)
- [OCR of historical printings with an application to building diachronic corpora: A case study using the RIDGES herbal corpus](https://mlsanity.com/paper/1608.02153/) (2016)
- [Sri Lanka Document Datasets: A Large-Scale, Multilingual Resource for Law, News, and Policy](https://mlsanity.com/paper/2510.04124/) (2025)
- [Adapting the Tesseract Open-Source OCR Engine for Tamil and Sinhala Legacy Fonts and Creating a Parallel Corpus for Tamil-Sinhala-English](https://mlsanity.com/paper/2109.05952/) (2021)
- [Chronicling Germany: An Annotated Historical Newspaper Dataset](https://mlsanity.com/paper/2401.16845/) (2024)
- [Why Stop at Words? Unveiling the Bigger Picture through Line-Level OCR](https://mlsanity.com/paper/2508.21693/) (2025)

## Abstract (arXiv)

Sinhala is a morphologically rich abugida spoken by roughly 16 million people in Sri Lanka, and to date, there are no publicly available real-world datasets for page-level Sinhala OCR. All previous studies for assessing Sinhala OCR models have used artificially generated data. To bridge the gap, we introduce sinhala-ocr-lk-acts-1010, an annotated dataset of 1,010 page-level images and their transcriptions collected from Sri Lankan Legislative Acts published between 1981-1989 and 2000-2019, split into 707 training examples, 101 validation examples, and 202 testing examples. Three models based on deep learning-based visual language processing, namely DeepSeek-OCR V1, DeepSeek-OCR V2, and LightOnOCR-2-1B, are fine-tuned using QLoRA in 8 experiments conducted on consumer and cloud GPUs. LightOnOCR-2-1B is the top performer, achieving a CER of 1.05% across all test examples, outperforming state-of-the-art open-source OCR models such as Surya-OCR (8.84%) and Tesseract v5 (10.69%), as well as commercially available OCR models such as Google Document AI (2.06%). Our results suggest that LightOnOCR-2-1B outperforms other baselines on real-world OCR tasks and maintains consistent performance across all print periods, even when documents are severely degraded.