{"url":"/dataset/europarl-st","name":"Europarl-ST","full_name":null,"description_markdown":"Europarl-ST is a multilingual Spoken Language Translation corpus containing paired audio-text samples for SLT from and into 9 European languages, for a total of 72 different translation directions. This corpus has been compiled using the debates held in the European Parliament in the period between 2008 and 2012. \r\n\r\nSource: [Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debates](/paper/europarl-st-a-multilingual-corpus-for-speech)","description_withheld":null,"homepage":"https://www.mllp.upv.es/europarl-st/","introduced_date":"2019-11-08","introduced_date_note":null,"introduced_by":{"paper":"/paper/europarl-st-a-multilingual-corpus-for-speech","title":"Europarl-ST: A Multilingual Corpus For Speech Translation Of Parliamentary Debates","first_author":"Javier Iranzo-Sánchez","url":null},"license":{"name":"Custom","url":"https://www.mllp.upv.es/europarl-st/README.md"},"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"},{"name":"Data Augmentation","url":"/task/data-augmentation","datasets_with_task":"/datasets/task/data-augmentation"}],"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":"Portuguese","url":"/datasets/language/portuguese"},{"name":"Dutch","url":"/datasets/language/dutch"},{"name":"Polish","url":"/datasets/language/polish"},{"name":"Romanian","url":"/datasets/language/romanian"}],"variants":["Europarl-ST"],"data_loaders":[],"num_papers_in_archive":57,"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."}