HSFDA Project

Introduction

The HSFDA project aims to address the problem of speech enhancement, utilizing techniques such as deep learning.

File Descriptions

• main.py: The main entry point of the project, used to launch the program and execute core functionalities.
• ssl.py: Self-supervised model processing.
• trainer.py: Defines the model training process.
• model directory: Contains model definitions and pre-trained models.
• requirements.txt: A list of project dependencies. You can install them using pip install -r requirements.txt.

How to Use

1. Install the required dependencies:

   pip install -r requirements.txt

2.Download the pre-trained speech model and dataset 3.python main.py