Post
53
Spanglish. Hinglish. Franglais. Real users don't speak textbook languages 🌍
500M+ Indians type messages like the below example, Most NLP pipelines fail silently on code-switched text, so I built something to start closing that gap for regional language
Fine-tuned MuRIL on 3,000 synthetic Hinglish examples. 97.6% F1.
Not perfect, but open, working, and hopefully useful.
"bhai mera refund kab aayega" → refund_status ✓
"wrong item aaya hai" → exchange_product ✓
"payment cut ho gaya order nahi hua" → payment_issue ✓
🤖 Hari5115/hinglish-retail-intent-classifier
📦 Hari5115/hinglish-retail-intent-dataset
🚀 Hari5115/hinglish-retail-intent-demo
Building for multilingual markets? Have real code-switched data? Would love to connect 🙏
#Hindi #IndianAI #RegionalNLP #NLP #MultilingualAI #OpenSource
500M+ Indians type messages like the below example, Most NLP pipelines fail silently on code-switched text, so I built something to start closing that gap for regional language
Fine-tuned MuRIL on 3,000 synthetic Hinglish examples. 97.6% F1.
Not perfect, but open, working, and hopefully useful.
"bhai mera refund kab aayega" → refund_status ✓
"wrong item aaya hai" → exchange_product ✓
"payment cut ho gaya order nahi hua" → payment_issue ✓
🤖 Hari5115/hinglish-retail-intent-classifier
📦 Hari5115/hinglish-retail-intent-dataset
🚀 Hari5115/hinglish-retail-intent-demo
Building for multilingual markets? Have real code-switched data? Would love to connect 🙏
#Hindi #IndianAI #RegionalNLP #NLP #MultilingualAI #OpenSource