This project provides a set of tools for audio transcription to create presciptions in matter of seconds using Whisper ASR, with a focus on integration with document editing workflows. It features a user-friendly interface built with customtkinter
and includes functionality for recording audio, transcribing it, and embedding the transcriptions into a document template.
- Python 3.10 or higher
- Git
- Clone the repository:
git clone https://github.com/arjamand/QuickDoc.git cd QuickDoc
- Create a virtual environment (optional but recommended):
python -m venv venv source venv/bin/activate # On Windows use `venv\Scripts\activate`
- Install dependencies:
pip install -r requirements.txt
To run the application, execute the following command in the project root folder:
python app.py
- Select Microphone: Choose your desired microphone from the dropdown.
- Start/Stop Recording: Click the "Start Recording" button to begin audio capture, and click "Stop Recording" to end it.
- View Transcription: The transcribed text will appear in the "Transcription" text box.
- Embed Transcription: Click "Embed Transcription" to add the transcribed text to the document.
- Print/Save Document: Use the "Print Document" or "Save Document" buttons to manage the final document.
- Adjust UI: Use the "Appearance Mode" and "UI Scaling" dropdowns to customize the user interface.
Feel free to contribute to the project by submitting issues, or pull requests.
This project is licensed under the MIT License