{"url":"/dataset/nepalinewscorpus","name":"NepaliNewsCorpus","full_name":null,"description_markdown":"# Nepali News Corpus\r\n## Raw nepali text scrapped from several online websites.\r\n### Total file size of concatenated text file -> 4.6 GB. \r\n\r\n## This raw text   corpus can be used for tasks such as casual language modelling and masked language modelling.","description_withheld":null,"homepage":"","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[],"languages":[{"name":"Nepali (macrolanguage)","url":"/datasets/language/nepali-macrolanguage"}],"variants":["NepaliNewsCorpus"],"data_loaders":[{"repo":"https://github.com/pudasainishushant/NepaliLanguageModelPretraining","url":"https://github.com/pudasainishushant/NepaliLanguageModelPretraining","frameworks":["tf","pytorch"]}],"num_papers_in_archive":0,"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."}