{"url":"/dataset/m-ailabs-speech-dataset","name":"M-AILabs speech dataset","full_name":null,"description_markdown":"The M-AILABS Speech Dataset is the first large dataset that we are providing free-of-charge, freely usable as training data for speech recognition and speech synthesis.\r\nMost of the data is based on LibriVox and Project Gutenberg. The training data consist of nearly thousand hours of audio and the text-files in prepared format.\r\nA transcription is provided for each clip. Clips vary in length from 1 to 20 seconds and have a total length of approximately shown in the list (and in the respective info.txt-files) below.\r\nThe texts were published between 1884 and 1964, and are in the public domain. The audio was recorded by the LibriVox project and is also in the public domain","description_withheld":null,"homepage":"https://www.caito.de/2019/01/03/the-m-ailabs-speech-dataset/","introduced_date":"2019-01-03","introduced_date_note":null,"introduced_by":null,"license":{"name":"permissive","url":"https://www.caito.de/2019/01/03/the-m-ailabs-speech-dataset"},"modalities":[{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Automatic Speech Recognition (ASR)","url":"/task/automatic-speech-recognition","datasets_with_task":"/datasets/task/automatic-speech-recognition"}],"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":"Russian","url":"/datasets/language/russian"},{"name":"Polish","url":"/datasets/language/polish"},{"name":"Ukrainian","url":"/datasets/language/ukrainian"}],"variants":["M-AILabs speech dataset"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/automatic-speech-recognition-on-m-ailabs","task":"Automatic Speech Recognition (ASR)","dataset_variant":"M-AILabs speech dataset","rows":1,"metrics":["WER (%)"],"first_row_in_archive_order":{"model":"Conformer Transducer","paper":"/paper/automatic-speech-recognition-in-german-a","metrics":{"WER (%)":"4.28%"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/automatic-speech-recognition-in-german-a","title":"Automatic Speech Recognition in German: A Detailed Error Analysis","date":"2022-08-03","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"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."}