新数据集让僧伽罗语OCR有了真实评测基准，LightOnOCR-2-1B 只用1.05%错误率碾压商业和开源方案，适合做古籍或法律文档自动识别。
研究者发布 sinhala-ocr-lk-acts-1010 数据集，包含1,010页来自斯里兰卡立法法案（1981-1989与2000-2019年）的页面级图像与转录文本，划分为707训练、101验证和202测试样本。使用QLoRA在8次实验中微调 DeepSeek-OCR V1、DeepSeek-OCR V2 和 LightOnOCR-2-1B 三个模型。LightOnOCR-2-1B 取得最佳性能，在全部测试样本上字符错误率(CER)为1.05%，优于 Surya-OCR（8.84%）、Tesseract v5（10.69%）和 Google Document AI（2.06%）。该模型在不同印刷年份的文档上表现一致，即使文档严重退化仍保持性能。
Cross-Temporal Sinhala OCR: Page-Level Adaptation and Diachronic Analysis
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.