Author

Naveen Kumar

Contact Info

• Email
• Linked In
• GitHub

Project Description

Anuvaad (https://anuvaad.sunbird.org/) has document text extraction and translation capabilities from/to Englisht to 11 official languages in India. Bhashini (https://bhashini.gov.in/en) also has APIs that support TextToSpeech (TTS), ASR (Automatic Speech Recognition), Real time speech to speech translation and transliteration capabilities to a lot of the official languages in India.

Features to be implemented:

All these capabilities provided by Anuvaad and Bhashini are powerful and can be leveraged for building other solutions. The ask here is to build a framework agnostic library that can expose java script functions to leverage these capabilities that are available and make it available as an NPM module. The idea is that this library can be integrated with content editors/web frontends that need translation & transliteration capability for Indic languages. The library should also allow for multiple file formats (pdf first priority) to be uploaded for text extraction.