Top Level Project Planning:
- Data Collection: “Hamlet” dataset
- Data Preprocessing:
- Tokenization
- converted into sequences,
- padded
- sequences are then split into training and testing sets
- Model Building:
- 1 embedding layer
- 2 LSTM layers
- 1 dense output layer (softmax activation function)
- Model Training:
- early stopping
- Model Evaluation
- Deployment
Streamlit Web App:
- Load LSTM model
- Load tokenizer
- Function to predict next word
- Streamlit component
