MUSE — Multilingual Sentiment & Sarcasm Engine

Sarcasm is the hard case for sentiment analysis: the words and the tone disagree, so reading the transcript alone gets it wrong.

MUSE reads both signals against each other — language through mBERT embeddings and a trained classifier, tone through pitch and energy features from Librosa — then fuses them. Around that sits a full pipeline: Whisper transcribes and detects the language, a router translates across seven languages via NLLB-200 or Marian, and RoBERTa handles sentiment.

Built with JWT authentication, bcrypt-hashed passwords, per-user analysis history in MongoDB, an admin panel, and PDF export with embedded Noto fonts so Indic scripts render properly rather than as boxes.

My part: the feature extraction and late-fusion pipeline, the sarcasm classifier and its evaluation, the translation router, and the React/Flask application end to end.