{"url":"/dataset/zazagoranicorpus","name":"ZazaGoraniCorpus","full_name":"A corpus of Zazaki and Gorani corpus","description_markdown":"A corpus for two endangered languages of the Zaza-Gorani language family: Zazaki and Gorani.","description_withheld":null,"homepage":"https://github.com/sinaahmadi/ZazaGoraniCorpus","introduced_date":"2020-12-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/building-a-corpus-for-the-zaza-gorani","title":"Building a Corpus for the Zaza–Gorani Language Family","first_author":"Sina Ahmadi","url":null},"license":null,"modalities":[],"tasks":[],"languages":[{"name":"Kurdish","url":"/datasets/language/kurdish"},{"name":"Zaza","url":"/datasets/language/zaza"}],"variants":["ZazaGoraniCorpus"],"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":"2026-09-25T09:33:49+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."}