VoiceTyper Whisper

VoiceTyper is a script that uses the faster-whisper library to listen to your microphone after pressing a hotkey (Ctrl+Shift+R). It transcribes your speech in real time and writes the recognized text both to the console and to wherever your text cursor is currently focused (for example, in a text editor or browser input field).

Requirements

• Python 3.10
• For GPU acceleration: NVIDIA GPU with CUDA support (see below)

Installation

1. Create and activate a Python 3.10 virtual environment.
2. Install dependencies:

   pip install -r requirements.txt
   

3. For GPU support, install the correct PyTorch version for your CUDA version. Visit https://pytorch.org/get-started/locally/ for details.
   • Example for CUDA 12.1:

     pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu121
     

Usage

Run the main script:

python main.py

Press Ctrl+Shift+R to start/stop recording.

Notes

• Make sure your Python version is exactly 3.10 for compatibility.
• If you use a different CUDA version, adjust the PyTorch installation command accordingly.
• For more information, see the official PyTorch documentation.