Harmon AI: Melody Generator Deep Learning Project

A Deep Learning based Melody Generator build using RNN & LSTM

Table of Contents

• Introduction
• Features
• Future Scope
• Getting Started
• Usage
• Contributing

Introduction

HarmonAI is a deep learning-based melody generator built using RNN & LSTM. It allows users to pass in a seed melody and temperature (randomness) to complete the melody ahead of that.

Features

• Generate melodies based on a seed melody and temperature.
• Explore the creative possibilities of AI-generated music.
• Easy-to-use interface for melody generation.

Future Scope

• Experiment with more Deep Learning models to compare the results.
• Try transfomer based architecture.

Getting Started

Clone the repository

git clone https://github.com/AtharvaMaskar26/harmon-ai.git

install dependencies

pip install -r requirements.txt

Run the streamlit app

streamlit run app.py

Usage

• You can train the model for your own dataset using the preprocess.py and train.py files.

• If you want to try different models, you can check out the code in melodygenerator.py file.

Contributing

• Contributions are welcome! Fork the repository and submit a pull request.
• Report any issues or suggest new features through the issue tracker.