{"url":"/dataset/voxpopuli","name":"VoxPopuli","full_name":null,"description_markdown":"VoxPopuli is a large-scale multilingual corpus providing 100K hours of unlabelled speech data in 23 languages. It is the largest open data to date for unsupervised representation learning as well as semi-supervised learning. VoxPopuli also contains 1.8K hours of transcribed speeches in 16 languages and their aligned oral interpretations into 5 other languages totaling 5.1K hours.\r\n\r\nSource: [VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation](/paper/voxpopuli-a-large-scale-multilingual-speech)","description_withheld":null,"homepage":"https://github.com/facebookresearch/voxpopuli","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/voxpopuli-a-large-scale-multilingual-speech","title":"VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation","first_author":"Changhan Wang","url":null},"license":null,"modalities":[{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Speech Recognition","url":"/task/speech-recognition","datasets_with_task":"/datasets/task/speech-recognition"},{"name":"Automatic Speech Recognition","url":"/task/automatic-speech-recognition-2","datasets_with_task":"/datasets/task/automatic-speech-recognition-2"},{"name":"Automatic Speech Recognition (ASR)","url":"/task/automatic-speech-recognition","datasets_with_task":"/datasets/task/automatic-speech-recognition"},{"name":"speech-recognition","url":"/task/speech-recognition-1","datasets_with_task":"/datasets/task/speech-recognition-1"}],"languages":[{"name":"Multilingual","url":"/datasets/language/multilingual"}],"variants":["VoxPopuli","Voxpopuli (German)","facebook/voxpopuli","facebook/voxpopuli fr"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Edmon02/hyvoxpopuli","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/voxpopuli","url":"https://github.com/facebookresearch/voxpopuli","frameworks":["pytorch"]}],"num_papers_in_archive":113,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/automatic-speech-recognition-on-voxpopuli","task":"Automatic Speech Recognition (ASR)","dataset_variant":"VoxPopuli","rows":1,"metrics":["WER (%)"],"first_row_in_archive_order":{"model":"Conformer Transducer (German)","paper":"/paper/automatic-speech-recognition-in-german-a","metrics":{"WER (%)":"8.98%"},"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."}