Spaces:
Running
Running
| title: Vocal Isolator | |
| emoji: 🗣 | |
| colorFrom: white | |
| colorTo: blue | |
| sdk: streamlit | |
| sdk_version: 1.25.0 | |
| app_file: app.py | |
| pinned: false | |
| license: openrail | |
| # Vocal Remover (for now) | |
| A web-based tool for removing vocals from audio files using deep learning. | |
| ## Table of Contents | |
| - [Overview](#overview) | |
| - [Features](#features) | |
| - [Installation](#installation) | |
| - [Usage](#usage) | |
| - [Demo](#demo) | |
| - [Technologies Used](#technologies-used) | |
| - [Contributing](#contributing) | |
| - [License](#license) | |
| - [Useful Research Papers](#useful-research-papers) | |
| ## Overview | |
| The Vocal Isolator is a user-friendly web application that leverages deep learning models to isolate vocals from audio files. It provides an easy and interactive way for users to upload their audio files and process them to obtain vocals-free versions. | |
| ## Features | |
| - Upload audio files in various formats (WAV, MP3, OGG, FLAC). | |
| - Process audio files to remove vocals using a pre-trained deep learning model. | |
| - Display a progress bar during audio processing. | |
| - Play the original and processed audio files in the browser. | |
| - Downloadable WAV file | |
| - Clean and intuitive user interface. | |
| ## Installation | |
| 1. Clone this repository: | |
| ```bash | |
| git clone https://github.com/smotto/Sing-For-Me.git | |
| cd Sing-For-Me | |
| 2. Install the required Python packages: | |
| ```bash | |
| pip install -r requirements.txt | |
| ## Usage | |
| 1. Run the Streamlit app: | |
| ```bash | |
| streamlit run main.py | |
| 2. Access the app in your web browser at http://localhost:8501. | |
| ## Demo | |
| For a live demonstration, visit Demo Link. | |
| ## Technologies Used | |
| * Python | |
| * Streamlit | |
| * PyTorch | |
| * Soundfile and Librosa | |
| ## Contributing | |
| Contributions are welcome! If you have suggestions, bug reports, or feature requests, please open an issue or submit a pull request. | |
| ## License | |
| This project is licensed under the Apache 2.0 License. | |
| ## Useful Research Papers | |
| - [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://arxiv.org/abs/1505.04597) | |
| - [WaveNet: A Generative Model for Raw Audio](https://arxiv.org/abs/1609.03499) | |
| - [Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation](https://arxiv.org/abs/1806.03185) | |
| - [KUIELab-MDX-Net: A Two-Stream Neural Network for Music Demixing](https://arxiv.org/abs/2111.12203) |