{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/seamlessm4t-massively-multilingual-multimodal","title":"SeamlessM4T: Massively Multilingual & Multimodal Machine Translation","arxiv_id":"2308.11596","date":"2023-08-22","proceeding":null,"authors":["Seamless Communication","Loïc Barrault","Yu-An Chung","Mariano Cora Meglioli","David Dale","Ning Dong","Paul-Ambroise Duquenne","Hady Elsahar","Hongyu Gong","Kevin Heffernan","John Hoffman","Christopher Klaiber","Pengwei Li","Daniel Licht","Jean Maillard","Alice Rakotoarison","Kaushik Ram Sadagopan","Guillaume Wenzek","Ethan Ye","Bapi Akula","Peng-Jen Chen","Naji El Hachem","Brian Ellis","Gabriel Mejia Gonzalez","Justin Haaheim","Prangthip Hansanti","Russ Howes","Bernie Huang","Min-Jae Hwang","Hirofumi Inaguma","Somya Jain","Elahe Kalbassi","Amanda Kallet","Ilia Kulikov","Janice Lam","Daniel Li","Xutai Ma","Ruslan Mavlyutov","Benjamin Peloquin","Mohamed Ramadan","Abinesh Ramakrishnan","Anna Sun","Kevin Tran","Tuan Tran","Igor Tufanov","Vish Vogeti","Carleigh Wood","Yilin Yang","Bokai Yu","Pierre Andrews","Can Balioglu","Marta R. Costa-jussà","Onur Celebi","Maha Elbayad","Cynthia Gao","Francisco Guzmán","Justine Kao","Ann Lee","Alexandre Mourachko","Juan Pino","Sravya Popuri","Christophe Ropers","Safiyyah Saleem","Holger Schwenk","Paden Tomasello","Changhan Wang","Jeff Wang","Skyler Wang"],"abstract":"What does it take to create the Babel Fish, a tool that can help individuals translate speech between any two languages? While recent breakthroughs in text-based models have pushed machine translation coverage beyond 200 languages, unified speech-to-speech translation models have yet to achieve similar strides. More specifically, conventional speech-to-speech translation systems rely on cascaded systems that perform translation progressively, putting high-performing unified systems out of reach. To address these gaps, we introduce SeamlessM4T, a single model that supports speech-to-speech translation, speech-to-text translation, text-to-speech translation, text-to-text translation, and automatic speech recognition for up to 100 languages. To build this, we used 1 million hours of open speech audio data to learn self-supervised speech representations with w2v-BERT 2.0. Subsequently, we created a multimodal corpus of automatically aligned speech translations. Filtered and combined with human-labeled and pseudo-labeled data, we developed the first multilingual system capable of translating from and into English for both speech and text. On FLEURS, SeamlessM4T sets a new standard for translations into multiple target languages, achieving an improvement of 20% BLEU over the previous SOTA in direct speech-to-text translation. Compared to strong cascaded models, SeamlessM4T improves the quality of into-English translation by 1.3 BLEU points in speech-to-text and by 2.6 ASR-BLEU points in speech-to-speech. Tested for robustness, our system performs better against background noises and speaker variations in speech-to-text tasks compared to the current SOTA model. Critically, we evaluated SeamlessM4T on gender bias and added toxicity to assess translation safety. Finally, all contributions in this work are open-sourced and accessible at https://github.com/facebookresearch/seamless_communication","url_abs":"https://arxiv.org/abs/2308.11596v3","url_pdf":"https://arxiv.org/pdf/2308.11596v3.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":"seamlessm4t-massively-multilingual-multimodal","repo_url":"https://github.com/facebookresearch/seamless_communication","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"seamlessm4t-massively-multilingual-multimodal","repo_url":"https://github.com/facebookresearch/sonar","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"seamlessm4t-massively-multilingual-multimodal","repo_url":"https://github.com/pwc-1/Paper-10/tree/main/seamless_m4t","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"seamlessm4t-massively-multilingual-multimodal","repo_url":"https://github.com/yangyucheng000/University/tree/main/model-3/seamless_m4t","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"speech-to-speech-translation","task_name":"Speech-to-Speech Translation"},{"task_slug":"speech-to-text","task_name":"Speech-to-Text"},{"task_slug":"speech-to-text-translation","task_name":"Speech-to-Text Translation"},{"task_slug":"text-to-speech","task_name":"Text to Speech"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"text-to-speech-1","task_name":"text-to-speech"},{"task_slug":"text-to-speech-translation","task_name":"text-to-speech translation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/machine-translation-on-flores-200","task":"Machine Translation","dataset":"FLoRes-200","model":"SeamlessM4T-Large-V1","rank_in_archive_order":3,"of":5,"metrics":{"BLEU":"37.5"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-flores95-devtest-x-eng","task":"Machine Translation","dataset":"flores95-devtest X-eng","model":"SeamlessM4T Large","rank_in_archive_order":1,"of":3,"metrics":{"ChrF++":"60.8"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-flores95-devtest-x-eng","task":"Machine Translation","dataset":"flores95-devtest X-eng","model":"SeamlessM4T-NLLB-1.3B","rank_in_archive_order":2,"of":3,"metrics":{"ChrF++":"60.7"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-flores95-devtest-x-eng","task":"Machine Translation","dataset":"flores95-devtest X-eng","model":"SeamlessM4T Medium","rank_in_archive_order":3,"of":3,"metrics":{"ChrF++":"55.4"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-flores95-devtest-eng-x","task":"Machine Translation","dataset":"flores95-devtest eng-X","model":"SeamlessM4T Large","rank_in_archive_order":1,"of":3,"metrics":{"ChrF++":"50.9"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-flores95-devtest-eng-x","task":"Machine Translation","dataset":"flores95-devtest eng-X","model":"SeamlessM4T-NLLB-1.3B","rank_in_archive_order":2,"of":3,"metrics":{"ChrF++":"49.6"},"uses_additional_data":false},{"leaderboard":"/sota/machine-translation-on-flores95-devtest-eng-x","task":"Machine Translation","dataset":"flores95-devtest eng-X","model":"SeamlessM4T Medium","rank_in_archive_order":3,"of":3,"metrics":{"ChrF++":"48.4"},"uses_additional_data":false},{"leaderboard":"/sota/speech-to-speech-translation-on-cvss","task":"Speech-to-Speech Translation","dataset":"CVSS","model":"SeamlessM4T Large","rank_in_archive_order":1,"of":2,"metrics":{"ASR-BLEU":"36.5","Parameters":"2.3B"},"uses_additional_data":true},{"leaderboard":"/sota/speech-to-speech-translation-on-cvss","task":"Speech-to-Speech Translation","dataset":"CVSS","model":"SeamlessM4T Medium","rank_in_archive_order":2,"of":2,"metrics":{"ASR-BLEU":"28.1","Parameters":"1.2B"},"uses_additional_data":false},{"leaderboard":"/sota/speech-to-speech-translation-on-fleurs-x-eng","task":"Speech-to-Speech Translation","dataset":"FLEURS X-eng","model":"SeamlessM4T LargeV2","rank_in_archive_order":3,"of":7,"metrics":{"ASR-BLEU":"29.4"},"uses_additional_data":false},{"leaderboard":"/sota/speech-to-speech-translation-on-fleurs-x-eng","task":"Speech-to-Speech Translation","dataset":"FLEURS X-eng","model":"SeamlessM4T Large","rank_in_archive_order":4,"of":7,"metrics":{"ASR-BLEU":"25.8"},"uses_additional_data":false},{"leaderboard":"/sota/speech-to-speech-translation-on-fleurs-x-eng","task":"Speech-to-Speech Translation","dataset":"FLEURS X-eng","model":"SeamlessM4T Medium","rank_in_archive_order":7,"of":7,"metrics":{"ASR-BLEU":"20.4"},"uses_additional_data":false},{"leaderboard":"/sota/speech-to-text-translation-on-covost-2-x-eng","task":"Speech-to-Text Translation","dataset":"CoVoST 2 X-eng","model":"SeamlessM4T Large","rank_in_archive_order":1,"of":2,"metrics":{"BLEU":"34.1"},"uses_additional_data":false},{"leaderboard":"/sota/speech-to-text-translation-on-covost-2-x-eng","task":"Speech-to-Text Translation","dataset":"CoVoST 2 X-eng","model":"SeamlessM4T Medium","rank_in_archive_order":2,"of":2,"metrics":{"BLEU":"29.8"},"uses_additional_data":false},{"leaderboard":"/sota/speech-to-text-translation-on-covost-2-eng-x","task":"Speech-to-Text Translation","dataset":"CoVoST 2 eng-X","model":"SeamlessM4T Large","rank_in_archive_order":1,"of":2,"metrics":{"BLEU":"30.6"},"uses_additional_data":false},{"leaderboard":"/sota/speech-to-text-translation-on-covost-2-eng-x","task":"Speech-to-Text Translation","dataset":"CoVoST 2 eng-X","model":"SeamlessM4T Medium","rank_in_archive_order":2,"of":2,"metrics":{"BLEU":"26.6"},"uses_additional_data":false},{"leaderboard":"/sota/speech-to-text-translation-on-fleurs-x-eng","task":"Speech-to-Text Translation","dataset":"FLEURS X-eng","model":"SeamlessM4T Large","rank_in_archive_order":1,"of":2,"metrics":{"BLEU":"24.0"},"uses_additional_data":false},{"leaderboard":"/sota/speech-to-text-translation-on-fleurs-x-eng","task":"Speech-to-Text Translation","dataset":"FLEURS X-eng","model":"SeamlessM4T Medium","rank_in_archive_order":2,"of":2,"metrics":{"BLEU":"20.9"},"uses_additional_data":false},{"leaderboard":"/sota/speech-to-text-translation-on-fleurs-eng-x","task":"Speech-to-Text Translation","dataset":"FLEURS eng-X","model":"SeamlessM4T Large","rank_in_archive_order":1,"of":2,"metrics":{"BLEU":"21.5"},"uses_additional_data":false},{"leaderboard":"/sota/speech-to-text-translation-on-fleurs-eng-x","task":"Speech-to-Text Translation","dataset":"FLEURS eng-X","model":"SeamlessM4T Medium","rank_in_archive_order":2,"of":2,"metrics":{"BLEU":"19.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.11596","atlas_url":"https://app.syntology.ai/?focus=2308.11596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11596"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2308.11596"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2308.11596"},"call":"get_harvested_code_for_paper(arxiv_id=\"2308.11596\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2308.11596"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2308.11596\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2308.11596"},"call":"get_concepts_for_paper(arxiv_id=\"2308.11596\")"}],"by_repo":[{"repo":"facebookresearch/seamless_communication","kind":"official","samples":2,"ran":2,"instrument":2,"unverified":0},{"repo":"facebookresearch/sonar","kind":"named_in_paper","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"pwc-1/Paper-10","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2403.07714"],"harvested_for_calls":[{"arxiv_id":"2403.07714","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2403.07714"},"call":"get_harvested_code_for_paper(arxiv_id=\"2403.07714\")"}]},{"repo":"yangyucheng000/University","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2409.12191"],"harvested_for_calls":[{"arxiv_id":"2409.12191","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2409.12191"},"call":"get_harvested_code_for_paper(arxiv_id=\"2409.12191\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2308.11596.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2308.11596.svg"},"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/pwc-1/Paper-10/tree/main/seamless_m4t","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangyucheng000/University/tree/main/model-3/seamless_m4t","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/sonar","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/seamless_communication","reach":null}],"summary":{"ran_draft_wrong":2},"n_samples":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":true,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":2,"ran":2,"n_ran_checked":0,"n_instrument":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":2,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":2,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-22","last":"2026-09-22","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"samples":[{"code_sha256":"9f6a6a6199e1dc32","code_sha256_prefix":"9f6a6a6199e1dc32","entry":"add_inference_arguments","repo":"facebookresearch/seamless_communication","repo_kind":"official","path":"src/seamless_communication/cli/m4t/predict/predict.py","file_url":"https://github.com/facebookresearch/seamless_communication/blob/HEAD/src/seamless_communication/cli/m4t/predict/predict.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,"signature":"parser:ArgumentParser/0/?","fixture_out_type":"ArgumentParser","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, facebookresearch/seamless_communication (NOASSERTION)","mcp_get_code":{"code_sha256":"9f6a6a6199e1dc32"}},{"code_sha256":"6a4229d04ccaa9d4","code_sha256_prefix":"6a4229d04ccaa9d4","entry":"remove_prosody_tokens_from_text","repo":"facebookresearch/seamless_communication","repo_kind":"official","path":"src/seamless_communication/cli/expressivity/predict/predict.py","file_url":"https://github.com/facebookresearch/seamless_communication/blob/HEAD/src/seamless_communication/cli/expressivity/predict/predict.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"signature":"text:str/0/str","fixture_out_type":"str","level_recorded_at":"2026-09-22T14:31:46.068493+00:00","retrieve_with":{"tool":"get_code","code_sha256":"6a4229d04ccaa9d4"},"code_page":null,"census":null,"licence":"NOASSERTION","inline_ok":false,"inline_ok_link":false,"withheld_clause":"GitHub could not classify the licence of this paper's repository, facebookresearch/seamless_communication (NOASSERTION)","mcp_get_code":{"code_sha256":"6a4229d04ccaa9d4"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"aea8261e67943728737bff1f7d166deed589873bdb3956b4f766703f9b7fbc58","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}