{"url":"/dataset/dataset-for-post-ocr-text-correction-in","name":"Dataset for Post-OCR text correction in Sanskrit","full_name":null,"description_markdown":"This dataset contains around 218K sentences, with 1.5 million words, from 30 different books designed for Post-OCR text correction.\r\n\r\nSource: [A Benchmark and Dataset for Post-OCR text correction in Sanskrit](https://arxiv.org/pdf/2211.07980v1.pdf)\r\n\r\nImage Source: [https://arxiv.org/pdf/2211.07980v1.pdf](https://arxiv.org/pdf/2211.07980v1.pdf)","description_withheld":null,"homepage":"https://github.com/ayushbits/pe-ocr-sanskrit","introduced_date":"2022-11-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-benchmark-and-dataset-for-post-ocr-text","title":"A Benchmark and Dataset for Post-OCR text correction in Sanskrit","first_author":"Ayush Maheshwari","url":null},"license":{"name":"https://github.com/ayushbits/pe-ocr-sanskrit","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Visual Text Correction","url":"/task/visual-text-correction","datasets_with_task":"/datasets/task/visual-text-correction"}],"languages":[{"name":"Sanskrit","url":"/datasets/language/sanskrit"}],"variants":["Dataset for Post-OCR text correction in Sanskrit"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}