@article{tamizhinetocrcreatingaqualitylarge, title = {Adapting the Tesseract Open-Source OCR Engine for Tamil and Sinhala Legacy Fonts and Creating a Parallel Corpus for Tamil-Sinhala-English}, author = {Charangan Vasantharajan and Laksika Tharmalingam and Uthayasanker Thayasivam}, year = {2021}, eprint = {2109.05952}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2109.05952v3}, }