{"url":"/dataset/imasc","name":"IMaSC","full_name":"ICFOSS Malayalam Speech Corpus","description_markdown":"IMaSC is a Malayalam text and speech corpus made available by ICFOSS for the purpose of developing speech technology for Malayalam, particularly text-to-speech. The corpus contains 34,473 text-audio pairs of Malayalam sentences spoken by 8 speakers, totalling in approximately 50 hours of audio.","description_withheld":null,"homepage":"","introduced_date":"2022-11-23","introduced_date_note":null,"introduced_by":{"paper":"/paper/imasc-icfoss-malayalam-speech-corpus","title":"IMaSC -- ICFOSS Malayalam Speech Corpus","first_author":"Deepa P Gopinath","url":null},"license":{"name":"CC BY-SA 4.0","url":"https://creativecommons.org/licenses/by-sa/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Automatic Speech Recognition (ASR)","url":"/task/automatic-speech-recognition","datasets_with_task":"/datasets/task/automatic-speech-recognition"},{"name":"Text-To-Speech Synthesis","url":"/task/text-to-speech-synthesis","datasets_with_task":"/datasets/task/text-to-speech-synthesis"}],"languages":[{"name":"Malayalam","url":"/datasets/language/malayalam"}],"variants":["IMaSC"],"data_loaders":[],"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":"2026-09-25T09:33:49+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."}