We study the effect of applying a language model (LM) on the output of Automatic Speech Recognition (ASR) systems for Indic languages. We fine-tune wav2vec 2.0 models for 18 Indic languages and adjust the results with language models trained on text derived from a variety of sources. Our findings demonstrate that the average Character Error Rate (CER) decreases by over 28 \% and the average Word Error Rate (WER) decreases by about 36 \% after decoding with LM. We show that a large LM may not provide a substantial improvement as compared to a diverse one. We also demonstrate that high quality transcriptions can be obtained on domain-specific data without retraining the ASR model and show results on biomedical domain.
@article{arxiv.2203.16595,
title = {Improving Speech Recognition for Indic Languages using Language Model},
author = {Ankur Dhuriya and Harveen Singh Chadha and Anirudh Gupta and Priyanshi Shah and Neeraj Chhimwal and Rishabh Gaur and Vivek Raghavan},
journal= {arXiv preprint arXiv:2203.16595},
year = {2022}
}