machine learning13 min read
My Model Thought Tamil Was Telugu: Open-Source Language ID for Hinglish, Tanglish and Kanglish
Bhasha tags every word of code-mixed Indian text with its language. My test said Tamil scored 0.87; human-labelled comments said 0.72.Continue reading on Towards AI »
By Latent AI LabsTowards AI

Read the full story
Originally published by Towards AI on Oct 30, 2026.
Comments
Sign in to join the discussion.