{"url":"/dataset/dakshina","name":"Dakshina","full_name":"Dakshina","description_markdown":"The Dakshina dataset is a collection of text in both Latin and native scripts for 12 South Asian languages. For each language, the dataset includes a large collection of native script Wikipedia text, a romanization lexicon which consists of words in the native script with attested romanizations, and some full sentence parallel data in both a native script of the language and the basic Latin alphabet.\r\n\r\nSource: [Google Research](https://github.com/google-research-datasets/dakshina)","description_withheld":null,"homepage":"https://github.com/google-research-datasets/dakshina","introduced_date":"2020-07-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/processing-south-asian-languages-written-in-1","title":"Processing South Asian Languages Written in the Latin Script: the Dakshina Dataset","first_author":"Brian Roark","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"},{"name":"Language Identification","url":"/task/language-identification","datasets_with_task":"/datasets/task/language-identification"},{"name":"Transliteration","url":"/task/transliteration","datasets_with_task":"/datasets/task/transliteration"}],"languages":[{"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":"Urdu","url":"/datasets/language/urdu"},{"name":"Gujarati","url":"/datasets/language/gujarati"},{"name":"Kannada","url":"/datasets/language/kannada"},{"name":"Malayalam","url":"/datasets/language/malayalam"},{"name":"Punjabi","url":"/datasets/language/punjabi"},{"name":"Sinhala","url":"/datasets/language/sinhala"},{"name":"Sindhi","url":"/datasets/language/sindhi"}],"variants":["Dakshina"],"data_loaders":[{"repo":"https://github.com/google-research-datasets/dakshina","url":"https://github.com/google-research-datasets/dakshina","frameworks":[]}],"num_papers_in_archive":14,"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."}