Konkani ASR

dc.contributor.author	Fadte, S.S.
dc.contributor.author	Thakkar, G.
dc.contributor.author	Pawar, J.D.
dc.date.accessioned	2024-07-20T05:47:28Z
dc.date.available	2024-07-20T05:47:28Z
dc.date.issued	2023
dc.identifier.citation	Proc. 20th International Conference on Natural Language Processing (ICON). 2023; 393-397.	en_US
dc.identifier.uri	https://aclanthology.org/2023.icon-1.31/
dc.identifier.uri	http://irgu.unigoa.ac.in/drs/handle/unigoa/7339
dc.description.abstract	Konkani is a resource-scarce language, mainly spoken on the west coast of India. The lack of resources directly impacts the development of language technology tools and services. Therefore, the development of digital resources is required to aid in the improvement of this situation. This paper describes the work on the Automatic Speech Recognition (ASR) System for Konkani language. We have created the ASR by fine-tuning the whisper-small ASR model with 100 hours of Konkani speech corpus data. The baseline model showed a word error rate (WER) of 17, which serves as evidence for the efficacy of the fine-tuning procedure in establishing ASR accuracy for Konkani language.	en_US
dc.publisher	NLP Association of India (NLPAI)	en_US
dc.subject	Computer Science and Technology	en_US
dc.title	Konkani ASR	en_US
dc.type	Conference article	en_US