{"url":"/dataset/css10","name":"CSS10","full_name":null,"description_markdown":"A collection of single speaker speech datasets for ten languages. It is composed of short audio clips from LibriVox audiobooks and their aligned texts.\r\n\r\nSource: [CSS10: A Collection of Single Speaker Speech Datasets for 10 Languages](/paper/css10-a-collection-of-single-speaker-speech)","description_withheld":null,"homepage":"https://github.com/Kyubyong/css10","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/css10-a-collection-of-single-speaker-speech","title":"CSS10: A Collection of Single Speaker Speech Datasets for 10 Languages","first_author":"Kyubyong Park","url":null},"license":null,"modalities":[],"tasks":[{"name":"AutoML","url":"/task/automl","datasets_with_task":"/datasets/task/automl"},{"name":"Speech Synthesis","url":"/task/speech-synthesis","datasets_with_task":"/datasets/task/speech-synthesis"}],"languages":[],"variants":["CSS10"],"data_loaders":[{"repo":"https://github.com/Kyubyong/css10","url":"https://github.com/Kyubyong/css10","frameworks":["tf"]}],"num_papers_in_archive":22,"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."}