{"url":"/dataset/ruslan","name":"RUSLAN","full_name":null,"description_markdown":"RUSLAN is a Russian spoken language corpus for text-to-speech task. RUSLAN contains 22,200 audio samples with text annotations – more than 31 hours of high-quality speech of one person – being one of the largest annotated Russian corpus in terms of speech duration for a single speaker. \r\n\r\nSource: [RUSLAN: Russian Spoken Language Corpus for Speech Synthesis](/paper/ruslan-russian-spoken-language-corpus-for)","description_withheld":null,"homepage":"https://ruslan-corpus.github.io/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/ruslan-russian-spoken-language-corpus-for","title":"RUSLAN: Russian Spoken Language Corpus for Speech Synthesis","first_author":"Lenar Gabdrakhmanov","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Synthesis","url":"/task/speech-synthesis","datasets_with_task":"/datasets/task/speech-synthesis"}],"languages":[{"name":"Russian","url":"/datasets/language/russian"}],"variants":["RUSLAN"],"data_loaders":[],"num_papers_in_archive":2,"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."}