📜 Next-Word Prediction Using Word-Level LSTM

An AI model that predicts the next word in a sentence using a word-level LSTM.

---

✨ Features

• 🔠 Word-level tokenization for deeper semantic understanding.

• 🤖 LSTM-based Sequential model trained on Harry Potter and Percy Jackson books.

• 📊 Model comparison across different LSTM layers and architectures in Model_Comparisons.csv.

• 📉 Loss graphs included for visualizing training performance.

• 💾 Demo predicts the next word based on custom input.

  Note: Sometimes makes predictions that cannot be found in the original dictionary

---

🛠 Installation and Setup

1. Clone the repository:

git clone https://github.com/RJ601/Next-Word-Prediction-Using-Word-Level-LSTM.git
cd Next-Word-Prediction-Using-Word-Level-LSTM

2. Install dependencies:

pip install -r requirements.txt

---

🚀 Usage

👉 Open LSTM_Model_Training.ipynb, optionally modify the hyperparameters, and run all cells.

---

🔧 Tools, Libraries, and Dataset

• Platform: Jupyter Notebook
• Language: Python 3.9.23

Libraries Used:

• tensorflow==2.19.0
• keras==3.10.0
• scikit-learn==1.6.1
• matplotlib==3.9.4
• numpy==2.0.2
• pandas==2.3.0
• nltk==3.9.1

---

📝 License

This project is licensed under the MIT License. Feel free to use, modify, or share it with attribution.