{"url":"/dataset/psocr","name":"PsOCR","full_name":"Pashto OCR Dataset","description_markdown":"PsOCR is a large-scale synthetic dataset for Optical Character Recognition in low-resource Pashto language.","description_withheld":null,"homepage":"https://huggingface.co/datasets/zirak-ai/PashtoOCR","introduced_date":"2025-05-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/psocr-benchmarking-large-multimodal-models","title":"PsOCR: Benchmarking Large Multimodal Models for Optical Character Recognition in Low-resource Pashto Language","first_author":"Ijazul Haq","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"Optical Character Recognition (OCR)","url":"/task/optical-character-recognition","datasets_with_task":"/datasets/task/optical-character-recognition"},{"name":"Benchmarking","url":"/task/benchmarking","datasets_with_task":"/datasets/task/benchmarking"},{"name":"Image to text","url":"/task/image-to-text","datasets_with_task":"/datasets/task/image-to-text"}],"languages":[{"name":"Arabic","url":"/datasets/language/arabic"},{"name":"Persian","url":"/datasets/language/persian"},{"name":"Urdu","url":"/datasets/language/urdu"},{"name":"Southern Pashto","url":"/datasets/language/southern-pashto"},{"name":"Northern Pashto","url":"/datasets/language/northern-pashto"},{"name":"Central Pashto","url":"/datasets/language/central-pashto"}],"variants":["PsOCR"],"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."}