Live Updates
UPSC · English

SraVaani

Published 16 Aug 2026. Access the PDF directly or read the stored explanation below.

UPSC Daily Current Affairs Science & Technology English 16 Aug 2026

SraVaani

Prelims:

Science & Technology
Mains:

GS Paper II: Issues relating to development and inclusion, GS Paper III: Developments and applications of Science & Technology

Current relevance:

               Researchers at the SPIRE Lab of the Indian Institute of Science (IISc), Bengaluru, in collaboration with ARTPARK and Google, have released SraVaani.

 


Highlights:

1.        About SraVaani:                 

                     i.       SraVaani is a multilingual Indian speech-recognition model trained on 65 Indian languages and dialects.

                   ii.       It has been developed by researchers at IISc's SPIRE Lab, in collaboration with ARTPARK and Google.

                 iii.       It extends Automatic Speech Recognition (ASR) beyond widely supported languages to include several regional and non-scheduled Indian languages.

                iv.       The model is freely and publicly available on Hugging Face under an MIT licence.

2.      Purpose & Key Advantage:

           i.            SraVaani seeks to address the underrepresentation of regional and non-scheduled Indian languages in existing speech technologies.

         ii.            More than 40 of the languages covered by the model are not officially supported by existing speech-recognition systems.

       iii.            Its multilingual approach can help extend speech-based AI technologies to a wider range of India's linguistic communities.

3.      Significance:

           i.            Linguistic Inclusion: Expands speech-recognition capabilities beyond scheduled and widely supported Indian languages.

         ii.            Inclusive AI: Helps bring speech-based artificial intelligence to languages and dialects that remain underserved by existing technologies.

       iii.            Open Accessibility: Its availability under an MIT licence enables free public access to the model.

      iv.            Indian-language AI: Demonstrates efforts to develop AI systems capable of handling India's extensive linguistic diversity.

 

Source: THE HINDU - https://www.thehindu.com/news/national/karnataka/first-multilingual-indian-speech-recognition-model-trained-on-65-languages-and-dialects-released/article71341129.ece

 

Back to All Titbits
WhatsApp Book Free Demo