Vakyansh: ASR Toolkit for Low Resource Indic languages
This addresses the lack of speech recognition resources for Indic language speakers, though it is incremental as it applies existing methods (wav2vec 2.0) to new data.
The authors tackled the problem of low-resource speech recognition for Indic languages by creating Vakyansh, an end-to-end toolkit that generated 14,000 hours of speech data in 23 languages and trained state-of-the-art ASR models for 18 languages.
We present Vakyansh, an end to end toolkit for Speech Recognition in Indic languages. India is home to almost 121 languages and around 125 crore speakers. Yet most of the languages are low resource in terms of data and pretrained models. Through Vakyansh, we introduce automatic data pipelines for data creation, model training, model evaluation and deployment. We create 14,000 hours of speech data in 23 Indic languages and train wav2vec 2.0 based pretrained models. These pretrained models are then finetuned to create state of the art speech recognition models for 18 Indic languages which are followed by language models and punctuation restoration models. We open source all these resources with a mission that this will inspire the speech community to develop speech first applications using our ASR models in Indic languages.