{"url":"/dataset/samanantar","name":"Samanantar","full_name":null,"description_markdown":"Samanantar is the largest publicly available parallel corpora collection for Indic languages: Assamese, Bengali, Gujarati, Hindi, Kannada, Malayalam, Marathi, Oriya, Punjabi, Tamil, Telugu. The corpus has 49.6M sentence pairs between English to Indian Languages.","description_withheld":null,"homepage":"https://indicnlp.ai4bharat.org/samanantar/","introduced_date":"2021-04-12","introduced_date_note":null,"introduced_by":{"paper":"/paper/samanantar-the-largest-publicly-available","title":"Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languages","first_author":"Gowtham Ramesh","url":null},"license":{"name":"CC BY-NC 4.0","url":"https://creativecommons.org/licenses/by-nc/4.0/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"}],"languages":[{"name":"Bengali","url":"/datasets/language/bengali"},{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Marathi","url":"/datasets/language/marathi"},{"name":"Tamil","url":"/datasets/language/tamil"},{"name":"Telugu","url":"/datasets/language/telugu"},{"name":"Gujarati","url":"/datasets/language/gujarati"}],"variants":["Samanantar"],"data_loaders":[],"num_papers_in_archive":40,"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."}