{"url":"/dataset/gumar-corpus","name":"Gumar Corpus","full_name":null,"description_markdown":"A large-scale corpus of Gulf Arabic consisting of 110 million words from 1,200 forum novels.\r\n\r\nSource: [A Large Scale Corpus of Gulf Arabic](/paper/a-large-scale-corpus-of-gulf-arabic)","description_withheld":null,"homepage":"https://nyuad.nyu.edu/en/research/faculty-labs-and-projects/computational-approaches-to-modeling-language-lab/research/gumar-corpus.html","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/a-large-scale-corpus-of-gulf-arabic","title":"A Large Scale Corpus of Gulf Arabic","first_author":"Salam Khalifa","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Speech Synthesis","url":"/task/speech-synthesis","datasets_with_task":"/datasets/task/speech-synthesis"},{"name":"Text-To-Speech Synthesis","url":"/task/text-to-speech-synthesis","datasets_with_task":"/datasets/task/text-to-speech-synthesis"}],"languages":[{"name":"Arabic","url":"/datasets/language/arabic"}],"variants":["Gumar Corpus"],"data_loaders":[],"num_papers_in_archive":7,"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."}