https://github.com/muhd-umer/deep-suppressor

DeepSuppressor: A deep learning-based approach to speech denoising
https://github.com/muhd-umer/deep-suppressor

audio-denoising deep-learning pytorch signal-processing

Last synced: 6 days ago
JSON representation

DeepSuppressor: A deep learning-based approach to speech denoising

• Host: GitHub
• URL: https://github.com/muhd-umer/deep-suppressor
• Owner: muhd-umer
• License: mit
• Created: 2023-05-11T19:12:05.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2023-12-23T09:53:52.000Z (11 months ago)
• Last Synced: 2024-11-01T09:33:54.283Z (13 days ago)
• Topics: audio-denoising, deep-learning, pytorch, signal-processing
• Language: Python
• Homepage:
• Size: 18.7 MB
• Stars: 12
• Watchers: 2
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# DeepSuppressor

[![License](https://img.shields.io/badge/License-MIT-blue.svg)](https://opensource.org/licenses/MIT)

[![PyTorch](https://img.shields.io/badge/PyTorch-2.0.1-orange.svg)](https://pytorch.org/)

DeepSuppressor is a deep learning-based speech denoiser which can significantly improve the quality of speech signals. The denoiser is trained on a large dataset of clean and noisy speech signals, and it can be used to denoise speech signals in real time or offline.

## Installation

To get started with this project, follow the steps below:

**Clone the repository**

- Clone the repository to your local machine using the following command:

    ```shell

    git clone https://github.com/muhd-umer/deep-suppressor.git

    ```

**Create a new virtual environment**

- It is recommended to create a new virtual environment so that updates/downgrades of packages do not break other projects. To create a new virtual environment, run the following command:

    ```shell

    conda env create -f environment.yml

    ```

- Alternatively, you can use `mamba` (faster than conda) package manager to create a new virtual environment:

    ```fish

    wget -O miniforge.sh \

         "https://github.com/conda-forge/miniforge/releases/latest/download/Miniforge3-$(uname)-$(uname -m).sh"

    bash miniforge.sh -b -p "${HOME}/conda"

    source "${HOME}/conda/etc/profile.d/conda.sh"

    # For mamba support also run the following command

    source "${HOME}/conda/etc/profile.d/mamba.sh"

    conda activate

    mamba env create -f environment.yml

    ```

**Install the dependencies**

- Activate the newly created environment:

    ```shell

    conda activate deep-suppressor

    ```

- Install PyTorch (Stable 2.0.1):

    ```shell

    pip3 install torch==2.0.1 torchvision==0.15.2 torchaudio==2.0.2 --index-url https://download.pytorch.org/whl/cu118

    ```