{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/voxpopuli-a-large-scale-multilingual-speech","title":"VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretation","arxiv_id":"2101.00390","date":"2021-01-02","proceeding":"ACL 2021 5","authors":["Changhan Wang","Morgane Rivière","Ann Lee","Anne Wu","Chaitanya Talnikar","Daniel Haziza","Mary Williamson","Juan Pino","Emmanuel Dupoux"],"abstract":"We introduce VoxPopuli, 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. We provide speech recognition baselines and validate the versatility of VoxPopuli unlabelled data in semi-supervised learning under challenging out-of-domain settings. We will release the corpus at https://github.com/facebookresearch/voxpopuli under an open license.","url_abs":"https://arxiv.org/abs/2101.00390v2","url_pdf":"https://arxiv.org/pdf/2101.00390v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"voxpopuli-a-large-scale-multilingual-speech","repo_url":"https://github.com/facebookresearch/voxpopuli","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[{"slug":"voxpopuli","name":"VoxPopuli","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-common-voice-french","task":"Speech Recognition","dataset":"Common Voice French","model":"VoxPopuli-50K (n-gram)","rank_in_archive_order":3,"of":8,"metrics":{"Test WER":"9.6%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-german","task":"Speech Recognition","dataset":"Common Voice German","model":"VoxPopuli (n-gram)","rank_in_archive_order":12,"of":14,"metrics":{"Test WER":"7.8%"},"uses_additional_data":true},{"leaderboard":"/sota/speech-recognition-on-common-voice-spanish","task":"Speech Recognition","dataset":"Common Voice Spanish","model":"VoxPopuli-50K (n-gram)","rank_in_archive_order":7,"of":8,"metrics":{"Test WER":"10.0%"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2101.00390","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2101.00390"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/facebookresearch/voxpopuli","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"0dc788392584bd1d","entry":"parse_src_id","repo":"facebookresearch/voxpopuli","repo_kind":"official","path":"voxpopuli/get_s2s_data.py","file_url":"https://github.com/facebookresearch/voxpopuli/blob/HEAD/voxpopuli/get_s2s_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"0dc788392584bd1d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}