{"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/wav2vec-unsupervised-pre-training-for-speech","title":"wav2vec: Unsupervised Pre-training for Speech Recognition","arxiv_id":"1904.05862","date":"2019-04-11","proceeding":null,"authors":["Steffen Schneider","Alexei Baevski","Ronan Collobert","Michael Auli"],"abstract":"We explore unsupervised pre-training for speech recognition by learning representations of raw audio. wav2vec is trained on large amounts of unlabeled audio data and the resulting representations are then used to improve acoustic model training. We pre-train a simple multi-layer convolutional neural network optimized via a noise contrastive binary classification task. Our experiments on WSJ reduce WER of a strong character-based log-mel filterbank baseline by up to 36% when only a few hours of transcribed data is available. Our approach achieves 2.43% WER on the nov92 test set. This outperforms Deep Speech 2, the best reported character-based system in the literature while using two orders of magnitude less labeled training data.","url_abs":"https://arxiv.org/abs/1904.05862v4","url_pdf":"https://arxiv.org/pdf/1904.05862v4.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":"wav2vec-unsupervised-pre-training-for-speech","repo_url":"https://github.com/pytorch/fairseq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"wav2vec-unsupervised-pre-training-for-speech","repo_url":"https://github.com/eastonYi/wav2vec","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"wav2vec-unsupervised-pre-training-for-speech","repo_url":"https://github.com/mailong25/vietnamese-speech-recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"wav2vec-unsupervised-pre-training-for-speech","repo_url":"https://github.com/shangeth/wavencoder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"wav2vec-unsupervised-pre-training-for-speech","repo_url":"https://github.com/MS-P3/code7/tree/main/wav2vec2_with_lm","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"wav2vec-unsupervised-pre-training-for-speech","repo_url":"https://github.com/pwc-1/Paper-9/tree/main/1/wav2vec2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"wav2vec-unsupervised-pre-training-for-speech","repo_url":"https://github.com/pytorch/fairseq/blob/master/fairseq/models/wav2vec.py","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"binary-classification","task_name":"Binary Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"unsupervised-pre-training","task_name":"Unsupervised Pre-training"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-recognition-on-timit","task":"Speech Recognition","dataset":"TIMIT","model":"wav2vec","rank_in_archive_order":5,"of":22,"metrics":{"Percentage error":"14.7"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1904.05862","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.05862"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pytorch/fairseq","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/eastonYi/wav2vec","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pytorch/fairseq/blob/master/fairseq/models/wav2vec.py","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mailong25/vietnamese-speech-recognition","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shangeth/wavencoder","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MS-P3/code7/tree/main/wav2vec2_with_lm","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pwc-1/Paper-9/tree/main/1/wav2vec2","reach":null}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"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":0,"samples":[{"code_sha256_prefix":"5d07a9bbfd8a4ae6","entry":"norm_block","repo":"shangeth/wavencoder","repo_kind":"listed","path":"wavencoder/models/wav2vec.py","file_url":"https://github.com/shangeth/wavencoder/blob/HEAD/wavencoder/models/wav2vec.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5d07a9bbfd8a4ae6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}