{"url":"/dataset/cvss","name":"CVSS","full_name":null,"description_markdown":"**CVSS** is a massively multilingual-to-English speech to speech translation (S2ST) corpus, covering sentence-level parallel S2ST pairs from 21 languages into English. CVSS is derived from the [Common Voice](common-voice)  speech corpus and the [CoVoST](covost) 2 speech-to-text translation (ST) corpus, by synthesizing the translation text from CoVoST 2 into speech using state-of-the-art TTS systems","description_withheld":null,"homepage":"https://github.com/google-research-datasets/cvss","introduced_date":"2022-01-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/cvss-corpus-and-massively-multilingual-speech","title":"CVSS Corpus and Massively Multilingual Speech-to-Speech Translation","first_author":"Ye Jia","url":null},"license":{"name":"CC BY 4.0","url":"https://github.com/google-research-datasets/cvss/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Text-To-Speech Synthesis","url":"/task/text-to-speech-synthesis","datasets_with_task":"/datasets/task/text-to-speech-synthesis"},{"name":"Translation","url":"/task/translation","datasets_with_task":"/datasets/task/translation"},{"name":"Speech-to-Speech Translation","url":"/task/speech-to-speech-translation","datasets_with_task":"/datasets/task/speech-to-speech-translation"},{"name":"fr-en","url":"/task/fr-en","datasets_with_task":"/datasets/task/fr-en"},{"name":"es-en","url":"/task/es-en","datasets_with_task":"/datasets/task/es-en"},{"name":"de-en","url":"/task/de-en","datasets_with_task":"/datasets/task/de-en"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"},{"name":"Italian","url":"/datasets/language/italian"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Japanese","url":"/datasets/language/japanese"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Portuguese","url":"/datasets/language/portuguese"},{"name":"Arabic","url":"/datasets/language/arabic"},{"name":"Catalan","url":"/datasets/language/catalan"},{"name":"Dutch","url":"/datasets/language/dutch"},{"name":"Estonian","url":"/datasets/language/estonian"},{"name":"Indonesian","url":"/datasets/language/indonesian"},{"name":"Latvian","url":"/datasets/language/latvian"},{"name":"Persian","url":"/datasets/language/persian"},{"name":"Slovenian","url":"/datasets/language/slovenian"},{"name":"Swedish","url":"/datasets/language/swedish"},{"name":"Tamil","url":"/datasets/language/tamil"},{"name":"Turkish","url":"/datasets/language/turkish"},{"name":"Welsh","url":"/datasets/language/welsh"},{"name":"Mongolian","url":"/datasets/language/mongolian"}],"variants":["CVSS"],"data_loaders":[],"num_papers_in_archive":26,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/speech-to-speech-translation-on-cvss","task":"Speech-to-Speech Translation","dataset_variant":"CVSS","rows":2,"metrics":["ASR-BLEU","Parameters"],"first_row_in_archive_order":{"model":"SeamlessM4T Large","paper":"/paper/seamlessm4t-massively-multilingual-multimodal","metrics":{"ASR-BLEU":"36.5","Parameters":"2.3B"},"code_links":[{"title":"facebookresearch/seamless_communication","url":"https://github.com/facebookresearch/seamless_communication"},{"title":"facebookresearch/sonar","url":"https://github.com/facebookresearch/sonar"},{"title":"yangyucheng000/University","url":"https://github.com/yangyucheng000/University/tree/main/model-3/seamless_m4t"},{"title":"pwc-1/Paper-10","url":"https://github.com/pwc-1/Paper-10/tree/main/seamless_m4t"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/seamlessm4t-massively-multilingual-multimodal","title":"SeamlessM4T: Massively Multilingual & Multimodal Machine Translation","date":"2023-08-22","rows_on_this_dataset":2,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":1,"samples_harvested":2,"samples_ran":2,"samples_unverified":0,"pointer_only_for_licence":2,"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."}