Skip to content

Our capstone project aimed at detecting swaras in Hindustani Classical Music. Each swara was meticulously labeled using Label Studio, serving as training data for our model. Leveraging object detection techniques, we developed a robust algorithm capable of accurately predicting swaras. This repository contains the codebase, dataset, and documentati

License

Notifications You must be signed in to change notification settings

c-viswanath/Swara-Detection-using-TensorFlow

 
 

Repository files navigation

Swara-Detection-using-TensorFlow

Description: Our capstone project aimed at detecting swaras in Hindustani Classical Music. Each swara was meticulously labeled using Label Studio, serving as training data for our model. Leveraging object detection techniques, we developed a robust algorithm capable of accurately predicting swaras. This repository contains the codebase, dataset, and documentation detailing our methodology and results, contributing to the advancement of music analysis and cultural preservation.

Technologies Used:

Label Studio Object detection algorithms Python, TensorFlow

Impact: This project holds significance in the realm of music analysis and cultural preservation, offering a novel approach to automatically detect swaras in Hindustani Classical Music recordings. By making the codebase and dataset publicly available on GitHub, we aim to foster collaboration, facilitate reproducibility, and encourage further research in this domain.

Contributors: Vadali S S Bharadwaja, C Viswanath,Arupa Nanada Swain, A Anushruth Reddy

About

Our capstone project aimed at detecting swaras in Hindustani Classical Music. Each swara was meticulously labeled using Label Studio, serving as training data for our model. Leveraging object detection techniques, we developed a robust algorithm capable of accurately predicting swaras. This repository contains the codebase, dataset, and documentati

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%