{"url":"/dataset/adima","name":"ADIMA","full_name":null,"description_markdown":"**ADIMA** is a novel, linguistically diverse, ethically sourced, expert annotated and well-balanced multilingual profanity detection audio dataset comprising of 11,775 audio samples in 10 Indic languages spanning 65 hours and spoken by 6,446 unique users.","description_withheld":null,"homepage":"https://github.com/ShareChatAI/Adima","introduced_date":"2022-02-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/adima-abuse-detection-in-multilingual-audio","title":"ADIMA: Abuse Detection In Multilingual Audio","first_author":"Vikram Gupta","url":null},"license":null,"modalities":[{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"}],"languages":[{"name":"Hindi","url":"/datasets/language/hindi"}],"variants":["ADIMA"],"data_loaders":[],"num_papers_in_archive":8,"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."}