{"url":"/dataset/french-dialect-samples","name":"French Dialect Samples","full_name":null,"description_markdown":"We collated subcorpora each between 50,000 and 70,000 words, containing samples of national dialects of French across different countries: Algeria, Democratic Republic of Congo, France, Ivory Coast, Morocco and Senegal.","description_withheld":null,"homepage":"https://github.com/omariosc/Data-Collection-and-Analysis-of-French-Dialects/tree/main/txt","introduced_date":"2022-08-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/data-collection-and-analysis-of-french","title":"Data Collection and Analysis of French Dialects","first_author":"Omar Shaur Choudhry","url":null},"license":null,"modalities":[],"tasks":[],"languages":[{"name":"French","url":"/datasets/language/french"}],"variants":["French Dialect Samples"],"data_loaders":[{"repo":"https://github.com/omariosc/Data-Collection-and-Analysis-of-French-Dialects","url":"https://github.com/omariosc/Data-Collection-and-Analysis-of-French-Dialects","frameworks":[]}],"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."}