{"url":"/dataset/libris2s","name":"LibriS2S","full_name":null,"description_markdown":"LibriS2S is a Speech to Speech Translation (S2ST) dataset build further upon existing resources. The dataset provides English-German speech and text quadruplets ranging just over 50 hours for both languages.","description_withheld":null,"homepage":"","introduced_date":"2022-04-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/libris2s-a-german-english-speech-to-speech","title":"LibriS2S: A German-English Speech-to-Speech Translation Corpus","first_author":"Pedro Jeuris","url":null},"license":{"name":"CC BY-NC-SA 4.0","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech-to-Speech Translation","url":"/task/speech-to-speech-translation","datasets_with_task":"/datasets/task/speech-to-speech-translation"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"German","url":"/datasets/language/german"}],"variants":["LibriS2S"],"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":"2026-09-24T18:15:14+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."}