{"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/scaling-transformers-for-low-bitrate-high","title":"Scaling Transformers for Low-Bitrate High-Quality Speech Coding","arxiv_id":"2411.19842","date":"2024-11-29","proceeding":null,"authors":["Julian D Parker","Anton Smirnov","Jordi Pons","CJ Carr","Zack Zukowski","Zach Evans","Xubo Liu"],"abstract":"The tokenization of speech with neural audio codec models is a vital part of modern AI pipelines for the generation or understanding of speech, alone or in a multimodal context. Traditionally such tokenization models have concentrated on low parameter-count architectures using only components with strong inductive biases. In this work we show that by scaling a transformer architecture with large parameter count to this problem, and applying a flexible Finite Scalar Quantization (FSQ) based bottleneck, it is possible to reach state-of-the-art speech quality at extremely low bit-rates of $400$ or $700$ bits-per-second. The trained models strongly out-perform existing baselines in both objective and subjective tests.","url_abs":"https://arxiv.org/abs/2411.19842v1","url_pdf":"https://arxiv.org/pdf/2411.19842v1.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":"scaling-transformers-for-low-bitrate-high","repo_url":"https://github.com/Stability-AI/stable-codec","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"quantization","task_name":"Quantization"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2411.19842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2411.19842"}},"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/Stability-AI/stable-codec","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":5},"by_repo_kind":{"official":{"samples":5,"ran":0,"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":"4eed814b3580b4f4","entry":"build_target","repo":"Stability-AI/stable-codec","repo_kind":"official","path":"stable_codec/ctc_loss.py","file_url":"https://github.com/Stability-AI/stable-codec/blob/HEAD/stable_codec/ctc_loss.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":"4eed814b3580b4f4"}},{"code_sha256_prefix":"f93cc1014a6ed58c","entry":"edit_distance","repo":"Stability-AI/stable-codec","repo_kind":"official","path":"stable_codec/ctc_loss.py","file_url":"https://github.com/Stability-AI/stable-codec/blob/HEAD/stable_codec/ctc_loss.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":"f93cc1014a6ed58c"}},{"code_sha256_prefix":"3fafcf067dd71e69","entry":"leaky_hard_clip","repo":"Stability-AI/stable-codec","repo_kind":"official","path":"stable_codec/fsq.py","file_url":"https://github.com/Stability-AI/stable-codec/blob/HEAD/stable_codec/fsq.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":"3fafcf067dd71e69"}},{"code_sha256_prefix":"d939321c387018aa","entry":"round_ste","repo":"Stability-AI/stable-codec","repo_kind":"official","path":"stable_codec/fsq.py","file_url":"https://github.com/Stability-AI/stable-codec/blob/HEAD/stable_codec/fsq.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":"d939321c387018aa"}},{"code_sha256_prefix":"90de04f337c96e16","entry":"trim_to_shortest","repo":"Stability-AI/stable-codec","repo_kind":"official","path":"stable_codec/training_module.py","file_url":"https://github.com/Stability-AI/stable-codec/blob/HEAD/stable_codec/training_module.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":"90de04f337c96e16"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}