WhisperWrite is a powerful tool designed to process audio recordings of any length, surpassing the typical limitations of online APIs. Our tool has been tested with audio files as long as 2 hours, and it performs exceptionally well. Additionally, WhisperWrite can take notes from the audio and provide you with a summary highlighting the main points.

For more information about the project, visit our Devpost page.

Follow these instructions to set up and run WhisperWrite locally on your machine.

Before you begin, make sure you have the following installed on your machine:

• Node.js and npm
• Python 3.x and pip
• virtualenv
• Ollama (for LLaMA2 installation)

1. Clone the repository:

   git clone https://github.com/Aequor29/WhisperWrite

2. Navigate to the project directory:

   cd WhisperWrite/src

1. Install dependencies:

   cd frontend/whisper-write
   npm install

2. Start the development server:

   npm run dev

1. Navigate to the backend directory and install dependencies:

   cd ../backend
   pip install -r requirements.txt

2. Set up the Python environment using virtualenv:

   virtualenv venv
   source venv/bin/activate   # On Windows use `venv\Scripts\activate`

3. Install LLaMA2 using Ollama:

   Follow the instructions on Ollama's website to install LLaMA2.

4. Start the backend server:

   uvicorn main:app --reload

• Ensure both the frontend and backend servers are running simultaneously for the full functionality of WhisperWrite.
• The backend server will handle audio processing and provide summaries based on the audio content.

We welcome contributions! Please feel free to submit a pull request or open an issue if you have any suggestions, improvements, or find any bugs.

This project is licensed under the MIT License.

Thank you for using WhisperWrite! If you have any questions or need further assistance, please contact us or open an issue on GitHub.