An advanced NLP validation engine for AI-based oral viva systems. It cleans speech transcripts, preserves Indian scripts (Hindi, Bengali, Tamil), scores keyword completeness, and fallbacks to RAG retrieval. Features Llama-Nemotron embeddings, mDeBERTa zero-shot NLI classification, local QA LLMs, and Indic-to-English translation.
multilingual nlp transformers embeddings llama nli rag fastapi tranlation deberta zero-shot-classification indic-nlp speech-validation viva-system
-
Updated
Jul 11, 2026 - Python