https://twitter.com/charliebholtz/status/1724815159590293764
Clone this repo, and setup and activate a virtualenv:
python3 -m pip install virtualenv
python3 -m virtualenv venv
source venv/bin/activate
Then, install the dependencies:
pip install -r requirements.txt
Download llava model from ollama
-> download ollama
-> cmd console, type: ollama run llava
In on terminal, run the webcam capture:
python capture_webcam.py
In another terminal, run the narrator:
python narrator_llava_xtts.py