TamilVoiceLab@DravidianLangTech 2026: Investigating Whisper Tamil Large-v2 for Dialectal Tamil Speech Recognition
Year: 2026
Type: conference-paper
Abstract: Automatic Speech Recognition (ASR) for languages rich in dialects and those with limited resources presents significant challenges due to the variations in pronunciation and vocabulary across different regions.This study offers a baseline evaluation of the Whisper Tamil Large-v2 model without fine-tuning for the shared task of Tamil Dialect Speech Recognition.The focus is on the ASR subtask, utilising dialectal Tamil speech recordings gathered from various regional dialects within Tamil Nadu.The pretrained Whisper Tamil Large-v2 model was assessed directly, without any supplementary finetuning or domain adaptation.A total of 579 dialect speech samples were used for experimentation, with performance evaluated based on Word Error Rate (WER).The model recorded a WER of 0.71, indicating that even robust multilingual pretrained models encounter challenges in dialect-rich and low-resource environments.These findings underscore the necessity for dialect-aware adaptation and the importance of balanced dialect training data to develop effective Tamil ASR systems.
Authors: S.b.priya, Bharathi B
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166819334