IIT-M : ASR English Evaluation Benchmark

About Dataset

This is the Indian English ASR benchmark dataset, contributed by the Speech Lab at IIT-Madras. The dataset was released as part of the ASR challenges under the National Language Translation Mission (NLTM), funded by the Ministry of Electronics and Information Technology (MeitY). It is designed to support the evaluation and development of Automatic Speech Recognition (ASR) systems for Indian English in general-use scenarios. The dataset provides high-quality and diverse audio samples, making it a critical resource for advancing speech recognition technologies for Indian English.