Client Background
Client: A leading Entertainment firm in the USA
Industry Type: Entertainment
Services: Music
Organization Size: 100+
Project Objective
The objective of this project is to split a song into its vocals and instrumental.
Project Description
The project aims at taking a Hindi language song as input and separating the vocals(lyrics) from the instrumental music of the song. Save both the vocals and instrumental files separately as output.
Our Solution
I have used Python programming language for this project. The use of a Python library called Spleeter developed by Deezer has been made to achieve our goal.
Spleeter is Deezer source separation library with pretrained models written in Python and uses Tensorflow. It makes it easy to train source separation model (assuming you have a dataset of isolated sources), and provides already trained state of the art model for performing various flavor of separation :
- Vocals (singing voice) / accompaniment separation (2 stems)
- Vocals / drums / bass / other separation (4 stems)
- Vocals / drums / bass / piano / other separation (5 stems)
2 stems and 4 stems models have high performance on the musdb dataset. Spleeter is also very fast as it can perform separation of audio files to 4 stems 100x faster than real-time when run on a GPU.
Project Deliverables
Python tool that takes Hindi song as input and gives two audio files as output: vocals file and instrumental file.
Language/techniques used
Python
Models used
2 Stems model
Skills used
Advanced Python programming
Project Snapshots
