Skip to content

collegecoder25/Bengali-Song-Mood-Detector

Repository files navigation

Bengali Song Mood Predictor: A Machine Learning Endeavor

Discover the mood or emotion associated with Bengali songs through the innovative Bengali Song Mood Predictor project. Driven by a passion for artificial intelligence and machine learning, this endeavor aims to predict the mood of Bengali songs using cutting-edge technologies and a custom-made dataset.

Project Overview

In collaboration with esteemed guidance from Prof. Sudipta Chakrabarty, a prominent faculty member of the Department of Computer Science and Engineering - Artificial Intelligence and Machine Learning (CSE-AIML) and Computer Science and Engineering - Data Science (CSE-DS) at Techno Main Salt Lake, our team embarked on an exciting journey to develop this mood prediction model.

Key Components

  • Custom Dataset: To ensure accuracy and relevance, we meticulously curated a custom dataset of Bengali songs, each meticulously labeled with specific emotions, including happiness, sadness, and more. This handcrafted dataset forms the backbone of our mood prediction model.

  • Python Libraries: Leveraging the power of Python, we harnessed various libraries such as Numpy, Pandas, Scikit-learn, Seaborn, TensorFlow, Keras, and Pickle to construct and train the model. These industry-standard tools enabled us to unlock the full potential of our project.

  • Web App: To provide a user-friendly experience, we created a local web app where users can explore the emotions of their favorite Bengali songs effortlessly. For seamless functionality, the system requires the scaler save file (scaler.pkl), the saved model file (my_model), and the dataset file (dataset.csv).

Contributors

This ambitious project was a collective effort, demonstrating the strength of collaboration and teamwork:

Unleashing the Power of Emotion Recognition

The ability to predict emotions in Bengali songs holds tremendous potential across various domains, from enhancing music streaming platforms' recommendations to creating personalized playlists that resonate with individual feelings. Our project opens doors to novel applications in the realm of artificial intelligence and music appreciation.

Join the Journey

You can be part of this exciting venture by exploring our code repository on GitHub. Feel free to contribute, provide feedback, and witness the harmony of technology and emotions intertwining in Bengali Song Mood Predictor.

GitHub Repository

Note: This project is purely academic and not intended for commercial use.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages