haiku123412/moodyyyy

🎭 Moodyyyy - Real Time Emotion Detection

A web application that detects emotions in text using a fine tuned Transformer model, built with HuggingFace Transformers, PyTorch, and Streamlit.

Live Demo

Click here to try it live <!-- We'll add the real link after deployment tomorrow -->

How It Works

1. 1.User enters any text in the input box
2. 2.The app passes the text through a fine-tuned DistilRoBERTa model
3. 3.The model returns confidence scores for 7 emotions: joy, sadness, anger, fear, surprise, disgust, and neutral
4. 4.Results are displayed with a confidence bar chart

Tech Stack

Run Locally

# 1. Clone the repo
git clone https://github.com/YOUR_USERNAME/moodlens.git
cd moodlens

# 2. Create virtual environment
python -m venv venv
venv\Scripts\activate  # Windows

# 3. Install dependencies
pip install -r requirements.txt

# 4. Run the app
streamlit run app.py

Model Details

• —Model: j-hartmann/emotion-english-distilroberta-base
• —Architecture: DistilRoBERTa (distilled version of RoBERTa, based on BERT)
• —Approach: Transfer Learning — using a model pre-trained and fine-tuned on emotion datasets
• —Emotions Detected: joy, sadness, anger, fear, surprise, disgust, neutral

Author

Your Name — LinkedIn | GitHub