A gadget for visually impaired individuals. Viz allows you to capture images in real-time and ask questions about them.
Clone the repository and cd into it.
git clone https://github.com/victorknox/Viz.git
cd Viz
Run the following installations.
pip install transformers torch gtts speech_recognition cv2
Run the Python script to start an interactive session with Viz.
python main.py
You can now press the spacebar to capture a picture through your webcam and speak into your speaker to ask questions, and viz will answer it for you!
To start with, Take a picture and try asking Viz:
"What is this?
Here's a quick demo: https://youtube.com/shorts/fEqUHTUywHs?si=qaFrzw17Ncmv4sKW