whisper-website - Simple Conversion of Speech to Text Using Whisper Model

Whisper Website: Converting Speech to Text with Ease

Whisper Website is a dynamic project that harnesses the power of the Whisper model, a robust tool developed by OpenAI, to seamlessly transform spoken words into written text. This project democratizes speech-to-text conversion by making it accessible and user-friendly for everyone, right from your local machine. Below, we'll explore how to set up and run Whisper Website both using a traditional approach and with Docker on your local server.

Setting Up Whisper Website on Localhost

To get started with hosting Whisper Website directly on your machine, follow these straightforward steps:

Clone the Repository: Begin by cloning the project's repository. Use the following command:
```
git clone [email protected]:Kabanosk/whisper-website.git
```
Navigate to the Project Directory: Change into the project directory using:
```
cd whisper-website
```
Create a Virtual Environment: Set up an isolated environment to manage dependencies:
```
python3 -m venv venv
```
Activate the Virtual Environment: Enable your virtual environment to start using it:
```
source venv/bin/activate
```
Or for some systems, you might use:
```
. venv/bin/activate
```
Install Required Packages: Install the necessary packages from the requirements file:
```
pip install -r requirements.txt
```
Enter the Source Directory: Navigate to where the main scripts are located:
```
cd src
```
Run the Application: Launch the application using:
```
python3 run.py
```
Access the Website: Open your web browser and type in the following URL to access the website:
```
http://127.0.0.1:8000/
```

Running Whisper Website Using Docker on Localhost

For users preferring Docker, the setup is streamlined and efficient. Here’s how to run Whisper Website using Docker:

Initial Setup

Install Docker: If not already installed, refer to Docker's official documentation for guidance.
Clone the Repository: Begin similar to the above method by cloning the repository:
```
git clone [email protected]:Kabanosk/whisper-website.git
```
Enter the Project Directory: Navigate to the project folder:
```
cd whisper-website
```
Build the Docker Image: Create an image that Docker can use to run the web application:
```
docker build -t app .
```
Run the Docker Container: Start the container using:
```
docker run --name app_container -p 80:80 app
```
Open in Browser: Access the website through your browser at:
```
http://127.0.0.1:80/
```

Subsequent Runs

Start the Docker Container: For subsequent uses, simply start the container:
```
docker start app_container
```
Access Again via Browser: Open the same URL as before:
```
http://127.0.0.1:80/
```

Through these simple steps, Whisper Website empowers users to effortlessly convert speech into text. Whether through a direct setup or using Docker, it ensures an easy and flexible integration process, making the world of speech recognition just a click away on your localhost.