Yama Judges, Chitragupta Keeps the Records: Open-Source AI for Indian Languages

Detect and redact Aadhaar, PAN and UPI data in Hindi, Hinglish and 11 more languages, then classify the text with your own labels. Two Apache-2.0 models that run locally. Source: Image by the author. TL;DR Chitragupta (arunp0/chitragupta-pii-indic) is a free, open-source model that finds and masks personal data in Indian text: Aadhaar, PAN, voter ID, GSTIN, UPI ID, IFSC, card and bank numbers, phone numbers, emails, addresses, dates of birth and names, in 13 languages. Yama (arunp0/yama-indic) is its companion: a zero-shot classifier that answers plain-English questions about the same kinds of