{"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/wespeaker-a-research-and-production-oriented","title":"Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit","arxiv_id":"2210.17016","date":"2022-10-31","proceeding":null,"authors":["Hongji Wang","Chengdong Liang","Shuai Wang","Zhengyang Chen","Binbin Zhang","Xu Xiang","Yanlei Deng","Yanmin Qian"],"abstract":"Speaker modeling is essential for many related tasks, such as speaker recognition and speaker diarization. The dominant modeling approach is fixed-dimensional vector representation, i.e., speaker embedding. This paper introduces a research and production oriented speaker embedding learning toolkit, Wespeaker. Wespeaker contains the implementation of scalable data management, state-of-the-art speaker embedding models, loss functions, and scoring back-ends, with highly competitive results achieved by structured recipes which were adopted in the winning systems in several speaker verification challenges. The application to other downstream tasks such as speaker diarization is also exhibited in the related recipe. Moreover, CPU- and GPU-compatible deployment codes are integrated for production-oriented development. The toolkit is publicly available at https://github.com/wenet-e2e/wespeaker.","url_abs":"https://arxiv.org/abs/2210.17016v2","url_pdf":"https://arxiv.org/pdf/2210.17016v2.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"wespeaker-a-research-and-production-oriented","repo_url":"https://github.com/wenet-e2e/wespeaker","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"wespeaker-a-research-and-production-oriented","repo_url":"https://github.com/BUTSpeechFIT/wespeaker_ssl_public","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2210.17016","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.17016"}},"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/wenet-e2e/wespeaker","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/BUTSpeechFIT/wespeaker_ssl_public","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"ran_fixture":1,"unverified":8},"by_repo_kind":{"listed":{"samples":10,"ran":2,"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":"f30ebf4e48b7e2d7","entry":"gelu","repo":"BUTSpeechFIT/wespeaker_ssl_public","repo_kind":"listed","path":"wespeaker/models/ssl/modules.py","file_url":"https://github.com/BUTSpeechFIT/wespeaker_ssl_public/blob/HEAD/wespeaker/models/ssl/modules.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f30ebf4e48b7e2d7"}},{"code_sha256_prefix":"fabe0899316ffaa5","entry":"trunc_normal_","repo":"BUTSpeechFIT/wespeaker_ssl_public","repo_kind":"listed","path":"wespeaker/ssl/models/dino_wrapper.py","file_url":"https://github.com/BUTSpeechFIT/wespeaker_ssl_public/blob/HEAD/wespeaker/ssl/models/dino_wrapper.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fabe0899316ffaa5"}},{"code_sha256_prefix":"d22a5e7495dd7a3a","entry":"compute_mask_indices","repo":"BUTSpeechFIT/wespeaker_ssl_public","repo_kind":"listed","path":"wespeaker/models/ssl/WavLM.py","file_url":"https://github.com/BUTSpeechFIT/wespeaker_ssl_public/blob/HEAD/wespeaker/models/ssl/WavLM.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d22a5e7495dd7a3a"}},{"code_sha256_prefix":"73cecca9f3575f09","entry":"concat_all_gather","repo":"BUTSpeechFIT/wespeaker_ssl_public","repo_kind":"listed","path":"wespeaker/ssl/models/moco_wrapper.py","file_url":"https://github.com/BUTSpeechFIT/wespeaker_ssl_public/blob/HEAD/wespeaker/ssl/models/moco_wrapper.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"73cecca9f3575f09"}},{"code_sha256_prefix":"e7dc5569bb9b9f5d","entry":"contrastive_collate_fn","repo":"BUTSpeechFIT/wespeaker_ssl_public","repo_kind":"listed","path":"wespeaker/ssl/dataset/dataset.py","file_url":"https://github.com/BUTSpeechFIT/wespeaker_ssl_public/blob/HEAD/wespeaker/ssl/dataset/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e7dc5569bb9b9f5d"}},{"code_sha256_prefix":"0b7b70c22d6a66dd","entry":"dino_collate_fn","repo":"BUTSpeechFIT/wespeaker_ssl_public","repo_kind":"listed","path":"wespeaker/ssl/dataset/dataset.py","file_url":"https://github.com/BUTSpeechFIT/wespeaker_ssl_public/blob/HEAD/wespeaker/ssl/dataset/dataset.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0b7b70c22d6a66dd"}},{"code_sha256_prefix":"4aa7333ffd7e18c6","entry":"gelu_accurate","repo":"BUTSpeechFIT/wespeaker_ssl_public","repo_kind":"listed","path":"wespeaker/models/ssl/modules.py","file_url":"https://github.com/BUTSpeechFIT/wespeaker_ssl_public/blob/HEAD/wespeaker/models/ssl/modules.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4aa7333ffd7e18c6"}},{"code_sha256_prefix":"01233f4856456c5f","entry":"get_activation_fn","repo":"BUTSpeechFIT/wespeaker_ssl_public","repo_kind":"listed","path":"wespeaker/models/ssl/modules.py","file_url":"https://github.com/BUTSpeechFIT/wespeaker_ssl_public/blob/HEAD/wespeaker/models/ssl/modules.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"01233f4856456c5f"}},{"code_sha256_prefix":"bb3c357a90bdd28c","entry":"get_model_encoder_state_dict","repo":"BUTSpeechFIT/wespeaker_ssl_public","repo_kind":"listed","path":"wespeaker/ssl/bin/average_contrastive_model.py","file_url":"https://github.com/BUTSpeechFIT/wespeaker_ssl_public/blob/HEAD/wespeaker/ssl/bin/average_contrastive_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bb3c357a90bdd28c"}},{"code_sha256_prefix":"55d78222d8e61479","entry":"get_t_model_state_dict","repo":"BUTSpeechFIT/wespeaker_ssl_public","repo_kind":"listed","path":"wespeaker/ssl/bin/average_dino_model.py","file_url":"https://github.com/BUTSpeechFIT/wespeaker_ssl_public/blob/HEAD/wespeaker/ssl/bin/average_dino_model.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"55d78222d8e61479"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}