Article complete

AI4Bharat Launches IndicTrans3 for 22 Indic Languages

AI4Bharat has also announced plans to release the training data soon, further contributing to the open-source AI ecosystem.

A vibrant orange background featuring a stylized elephant logo, surrounded by people in a festive setting.

Key takeaways

  • AI4Bharat launches IndicTrans3, a multilingual translation model for 22 Indic languages.
  • IndicTrans3 optimizes document-level translations, aiming for performance comparable to global leaders.
  • AI4Bharat plans to release training data soon, enhancing the open-source AI ecosystem.
  • Mitesh Khapra emphasizes commitment to advancing Indian language AI through open-source contributions.
  • IndicTrans2, the predecessor, has been widely adopted by Indian companies for research and development.

Takeaways drafted with AI from the article text.

AI4Bharat, the AI lab at IIT Madras, has introduced IndicTrans3-beta, a state-of-the-art (SOTA) multilingual translation model designed to support translations across 22 Indic languages. 

The model is optimised for document-level machine translation (MT) and aims to deliver performance on par with leading global translation models.

The key features of IndicTrans3 include high-accuracy translations, support for multiple Indian languages, and real-world optimisation for diverse applications. 

AI4Bharat has also announced plans to release the training data soon, further contributing to the open-source AI ecosystem.

Mitesh Khapra, the head of AI4Bharat, posted on LinkedIn, saying, “Over the past 4 years, we at AI4Bharat have been on a mission to accelerate Indian language AI —building large-scale datasets, models, and tools, and releasing everything open-source for the community. Now, all our contributions are available on Hugging Face!”

Khapra also thanks EkStep Foundation, Nilekani Philanthropies, and Bhashini (MeitY), for helping in the development.

IndicTrans2, the previous version of the multilingual translation model, has been heavily adopted by several Indian companies for AI research and development.

Last year in November, AI4Bharat announced the launch of BhasaAnuvaad, a speech translation dataset tailored for Indian languages, boasting coverage across 13 languages and approximately 44,400 hours of audio. 

This marks the largest publicly accessible speech translation resource of its kind for Indian linguistic diversity.

Read: Why India Needs More AI4Bharats

Published Updated

Spotted an error? Tell our editors. Read our editorial standards and corrections.

More in this story

AI4Bharat · 5 stories
  1. AI4Bharat Rolls Out IndicLLMSuite for Building LLMs in Indian Languages
  2. Bhavish Aggarwal Compares OpenAI to East India Company
  3. AI4Bharat Introduces AI Residency Program for 2024-2025
  4. Indian Govt, Sarvam AI Discuss Building India’s Sovereign LLM
  5. You are here: AI4Bharat Launches IndicTrans3 for 22 Indic Languages
About the author

Journalist

Mohit writes about AI in simple, explainable, and often funny words. He's especially passionate about chatting with those building AI for Bharat, with the occasional detour into AGI.

All stories
Belamy · Daily

The day’s AI news, before your first meeting.