{"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/mixed-precision-training-for-nlp-and-speech","title":"Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq","arxiv_id":"1805.10387","date":"2018-05-25","proceeding":null,"authors":["Oleksii Kuchaiev","Boris Ginsburg","Igor Gitman","Vitaly Lavrukhin","Jason Li","Huyen Nguyen","Carl Case","Paulius Micikevicius"],"abstract":"We present OpenSeq2Seq - a TensorFlow-based toolkit for training\nsequence-to-sequence models that features distributed and mixed-precision\ntraining. Benchmarks on machine translation and speech recognition tasks show\nthat models built using OpenSeq2Seq give state-of-the-art performance at 1.5-3x\nless training time. OpenSeq2Seq currently provides building blocks for models\nthat solve a wide range of tasks including neural machine translation,\nautomatic speech recognition, and speech synthesis.","url_abs":"http://arxiv.org/abs/1805.10387v2","url_pdf":"http://arxiv.org/pdf/1805.10387v2.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":"mixed-precision-training-for-nlp-and-speech","repo_url":"https://github.com/NVIDIA/OpenSeq2Seq","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"mixed-precision-training-for-nlp-and-speech","repo_url":"https://github.com/FazedAI/OpenSeq2Seq","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"mixed-precision-training-for-nlp-and-speech","repo_url":"https://github.com/rickyHong/OpenSeq2Seq-repl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"automatic-speech-recognition-2","task_name":"Automatic Speech Recognition"},{"task_slug":"automatic-speech-recognition","task_name":"Automatic Speech Recognition (ASR)"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-synthesis","task_name":"Speech Synthesis"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1805.10387","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}