{"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/fairseq-s2t-fast-speech-to-text-modeling-with","title":"fairseq S2T: Fast Speech-to-Text Modeling with fairseq","arxiv_id":"2010.05171","date":"2020-10-11","proceeding":"Asian Chapter of the Association for Computational Linguistics 2020","authors":["Changhan Wang","Yun Tang","Xutai Ma","Anne Wu","Sravya Popuri","Dmytro Okhonko","Juan Pino"],"abstract":"We introduce fairseq S2T, a fairseq extension for speech-to-text (S2T) modeling tasks such as end-to-end speech recognition and speech-to-text translation. It follows fairseq's careful design for scalability and extensibility. We provide end-to-end workflows from data pre-processing, model training to offline (online) inference. We implement state-of-the-art RNN-based, Transformer-based as well as Conformer-based models and open-source detailed training recipes. Fairseq's machine translation models and language models can be seamlessly integrated into S2T workflows for multi-task learning or transfer learning. Fairseq S2T documentation and examples are available at https://github.com/pytorch/fairseq/tree/master/examples/speech_to_text.","url_abs":"https://arxiv.org/abs/2010.05171v2","url_pdf":"https://arxiv.org/pdf/2010.05171v2.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":"fairseq-s2t-fast-speech-to-text-modeling-with","repo_url":"https://github.com/pytorch/fairseq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"fairseq-s2t-fast-speech-to-text-modeling-with","repo_url":"https://github.com/pytorch/fairseq/tree/master/examples/speech_to_text","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"fairseq-s2t-fast-speech-to-text-modeling-with","repo_url":"https://github.com/huggingface/transformers","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"fairseq-s2t-fast-speech-to-text-modeling-with","repo_url":"https://github.com/pwc-1/Paper-10/tree/main/speech_to_text","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null},{"paper_slug":"fairseq-s2t-fast-speech-to-text-modeling-with","repo_url":"https://github.com/yangyucheng000/University/tree/main/model-3/speech_to_text","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-to-text","task_name":"Speech-to-Text"},{"task_slug":"speech-to-text-translation","task_name":"Speech-to-Text Translation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/speech-to-text-translation-on-must-c-en-de","task":"Speech-to-Text Translation","dataset":"MuST-C EN->DE","model":"Transformer + ASR Pretrain","rank_in_archive_order":8,"of":8,"metrics":{"Case-sensitive sacreBLEU":"22.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2010.05171","atlas_url":"https://app.syntology.ai/?focus=2010.05171","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}