{"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/wavtokenizer-an-efficient-acoustic-discrete","title":"WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling","arxiv_id":"2408.16532","date":"2024-08-29","proceeding":null,"authors":["Shengpeng Ji","Ziyue Jiang","Wen Wang","Yifu Chen","Minghui Fang","Jialong Zuo","Qian Yang","Xize Cheng","Zehan Wang","RuiQi Li","Ziang Zhang","Xiaoda Yang","Rongjie Huang","Yidi Jiang","Qian Chen","Siqi Zheng","Zhou Zhao"],"abstract":"Language models have been effectively applied to modeling natural signals, such as images, video, speech, and audio. A crucial component of these models is the codec tokenizer, which compresses high-dimensional natural signals into lower-dimensional discrete tokens. In this paper, we introduce WavTokenizer, which offers several advantages over previous SOTA acoustic codec models in the audio domain: 1)extreme compression. By compressing the layers of quantizers and the temporal dimension of the discrete codec, one-second audio of 24kHz sampling rate requires only a single quantizer with 40 or 75 tokens. 2)improved subjective quality. Despite the reduced number of tokens, WavTokenizer achieves state-of-the-art reconstruction quality with outstanding UTMOS scores and inherently contains richer semantic information. Specifically, we achieve these results by designing a broader VQ space, extended contextual windows, and improved attention networks, as well as introducing a powerful multi-scale discriminator and an inverse Fourier transform structure. We conducted extensive reconstruction experiments in the domains of speech, audio, and music. WavTokenizer exhibited strong performance across various objective and subjective metrics compared to state-of-the-art models. We also tested semantic information, VQ utilization, and adaptability to generative models. Comprehensive ablation studies confirm the necessity of each module in WavTokenizer. The related code, demos, and pre-trained models are available at https://github.com/jishengpeng/WavTokenizer.","url_abs":"https://arxiv.org/abs/2408.16532v3","url_pdf":"https://arxiv.org/pdf/2408.16532v3.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":"wavtokenizer-an-efficient-acoustic-discrete","repo_url":"https://github.com/jishengpeng/wavtokenizer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2408.16532","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.16532"}},"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/jishengpeng/wavtokenizer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":2,"ran":3,"unverified":2},"by_repo_kind":{"official":{"samples":7,"ran":5,"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":"9fcdaa6e423e8aa7","entry":"Normalize","repo":"jishengpeng/wavtokenizer","repo_kind":"official","path":"decoder/models.py","file_url":"https://github.com/jishengpeng/wavtokenizer/blob/HEAD/decoder/models.py","link_basis":"harvester_set","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":"9fcdaa6e423e8aa7"}},{"code_sha256_prefix":"3137073275f8c21a","entry":"nonlinearity","repo":"jishengpeng/wavtokenizer","repo_kind":"official","path":"decoder/models.py","file_url":"https://github.com/jishengpeng/wavtokenizer/blob/HEAD/decoder/models.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3137073275f8c21a"}},{"code_sha256_prefix":"5923f41e711c0b69","entry":"safe_log","repo":"jishengpeng/wavtokenizer","repo_kind":"official","path":"decoder/modules.py","file_url":"https://github.com/jishengpeng/wavtokenizer/blob/HEAD/decoder/modules.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5923f41e711c0b69"}},{"code_sha256_prefix":"f1abe87534e9b4b5","entry":"symexp","repo":"jishengpeng/wavtokenizer","repo_kind":"official","path":"decoder/modules.py","file_url":"https://github.com/jishengpeng/wavtokenizer/blob/HEAD/decoder/modules.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1abe87534e9b4b5"}},{"code_sha256_prefix":"3acb919a94ac1a19","entry":"symlog","repo":"jishengpeng/wavtokenizer","repo_kind":"official","path":"decoder/modules.py","file_url":"https://github.com/jishengpeng/wavtokenizer/blob/HEAD/decoder/modules.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3acb919a94ac1a19"}},{"code_sha256_prefix":"705b857d58937815","entry":"instantiate_class","repo":"jishengpeng/WavTokenizer","repo_kind":"official","path":"decoder/pretrained.py","file_url":"https://github.com/jishengpeng/WavTokenizer/blob/HEAD/decoder/pretrained.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"705b857d58937815"}},{"code_sha256_prefix":"dba3d5f0d0d4a6f2","entry":"make_attn","repo":"jishengpeng/wavtokenizer","repo_kind":"official","path":"decoder/models.py","file_url":"https://github.com/jishengpeng/wavtokenizer/blob/HEAD/decoder/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dba3d5f0d0d4a6f2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}