{"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/nemo-inverse-text-normalization-from","title":"NeMo Inverse Text Normalization: From Development To Production","arxiv_id":"2104.05055","date":"2021-04-11","proceeding":null,"authors":["Yang Zhang","Evelina Bakhturina","Kyle Gorman","Boris Ginsburg"],"abstract":"Inverse text normalization (ITN) converts spoken-domain automatic speech recognition (ASR) output into written-domain text to improve the readability of the ASR output. Many state-of-the-art ITN systems use hand-written weighted finite-state transducer(WFST) grammars since this task has extremely low tolerance to unrecoverable errors. We introduce an open-source Python WFST-based library for ITN which enables a seamless path from development to production. We describe the specification of ITN grammar rules for English, but the library can be adapted for other languages. It can also be used for written-to-spoken text normalization. We evaluate the NeMo ITN library using a modified version of the Google Text normalization dataset.","url_abs":"https://arxiv.org/abs/2104.05055v2","url_pdf":"https://arxiv.org/pdf/2104.05055v2.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":"nemo-inverse-text-normalization-from","repo_url":"https://github.com/NVIDIA/NeMo/tree/main/nemo_text_processing/inverse_text_normalization","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","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":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"text-normalization","task_name":"Text Normalization"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"wfst","method_name":"WFST"}],"datasets_introduced":[],"methods_introduced":[{"slug":"wfst","name":"WFST","full_name":"weighted finite state transducer"}],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.05055","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}