{"url":"/dataset/naab","name":"naab","full_name":"naab","description_markdown":"# naab: A ready-to-use plug-and-play corpus for Farsi\r\nThe biggest cleaned and ready-to-use open-source textual corpus in Farsi. It contains about 130GB of data, 250 million paragraphs, and 15 billion words. The project name is derived from the Farsi word NAAB K which means pure and high grade. We also provide the raw version of the corpus called naab-raw and an easy-to-use preprocessor that can be employed by those who wanted to make a customized corpus.","description_withheld":null,"homepage":"https://huggingface.co/datasets/SLPL/naab","introduced_date":"2022-08-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/naab-a-ready-to-use-plug-and-play-corpus-for","title":"naab: A ready-to-use plug-and-play corpus for Farsi","first_author":"Sadra Sabouri","url":null},"license":null,"modalities":[],"tasks":[],"languages":[{"name":"Persian","url":"/datasets/language/persian"},{"name":"Iranian Persian","url":"/datasets/language/iranian-persian"}],"variants":["naab"],"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."}