PulseAugur
EN
LIVE 22:25:44

Open-source AI models process Indian languages, masking PII and classifying text

By PulseAugur Editorial · [1 sources] ·

Two open-source AI models, Chitragupta and Yama, have been developed to process Indian languages. Chitragupta is designed to detect and mask sensitive personal data such as Aadhaar, PAN, and UPI details across 13 Indian languages. Yama functions as a zero-shot classifier, enabling users to categorize text with custom labels in plain English. Both models are available under the Apache-2.0 license and can be run locally on a user's own hardware, ensuring data privacy. AI

IMPACT Provides specialized tools for processing Indian languages, enhancing data privacy and classification capabilities for regional text.

RANK_REASON The cluster describes the release of open-source AI models for specific language processing tasks, which falls under the category of tools.

Read on Towards AI →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Open-source AI models process Indian languages, masking PII and classifying text

How we ranked this

Signal score
42 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
The cluster describes the release of open-source AI models for specific language processing tasks, which falls under the category of tools.
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
product, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Breaking (< 6h)
Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

Full methodology in our editorial standards.

COVERAGE [1]

  1. Towards AI TIER_1 English(EN) · Latent AI Labs ·

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

    <h4>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.</h4><figure><img alt="Cover: “Yama judges. Chitragupta keeps the records.” beside a register card whose n…

RELATED ENTITIES

RELATED TOPICS