{"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/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":{"atlas_url":"https://app.syntology.ai/?focus=2308.11596","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.11596"}},"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/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},"by_repo_kind":{"official":{"samples":2,"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":2,"samples":[{"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,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"9f6a6a6199e1dc32"}},{"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,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"6a4229d04ccaa9d4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}