India’s Sovereign Move - Sarvam Vision Cracks the Code across 22 Indian languages
Sarvam Vision is an AI model from Sarvam AI that excels in optical character recognition (OCR) for 22 Indian languages, outperforming global models like Gemini and GPT-4o on Indic benchmarks. This achievement supports India's push for sovereign AI by digitizing real-world documents and archives in local scripts.
Sarvam Vision, a 3-billion-parameter model, handles "messy" scanned paperwork across languages like Hindi (95.91% accuracy), Bengali (92.61%), Tamil (93.42%), Marathi (93.13%), and even low-resource ones like Santali and Dogri (over 80%).
It structures data natively without relying on English translation layers, enabling applications in cultural recovery and document intelligence.
The model powers India's sovereign AI infrastructure under the IndiaAI Mission, where Sarvam was selected to build a national LLM.
This launch fits Sarvam's broader stack, including prior models like Sarvam-Translate (also for 22 languages) and audio models for code-mixed speech.
By focusing on Indic challenges ignored by Western AI, it unlocks centuries of knowledge in non-English archives.
Recent demos, like digitizing historical texts, highlight its real-world impact beyond benchmarks.
Credit : AIM Network.