{"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/vietnamese-automatic-speech-recognition-using","title":"Vietnamese Automatic Speech Recognition using Wav2vec 2.0","arxiv_id":null,"date":"2022-05-08","proceeding":"https://huggingface.co/khanhld/wav2vec2-base-vietnamese-160h 2022 5","authors":["Le Duy Khanh"],"abstract":"We fine-tuned the Wav2vec2-based model on about 160 hours of Vietnamese speech dataset from different resources, including VIOS, COMMON VOICE, FOSD, and VLSP (100h) using Connectionist Temporal Classification (CTC). As a result, we gain 10.78% and 15.05% (without Language Model) WER on COMMON VOICE and VIOS datasets, respectively.","url_abs":"https://github.com/khanld/ASR-Wa2vec-Finetune","url_pdf":"https://github.com/khanld/ASR-Wa2vec-Finetune","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":"vietnamese-automatic-speech-recognition-using","repo_url":"https://github.com/khanld/ASR-Wa2vec-Finetune","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":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}