The goal of this project is to develop a human-like agent using artificial intelligence. The agent will be able to communicate with the user via speech just like a normal human, solve problems and much more. You can read more details about the vision for this project here.
- Clone the repository.
- Create your preferred virtual environment.
- Go to the repository folder and run
pip install -r requirements.txtto install all the required packages. - If you encounter any installation issues please make sure you have installed required libraries using following commands (on Ubuntu):
sudo apt-get install portaudio19-dev libcairo2-dev libgirepository1.0-dev pkg-config python3-dev - To use the trained models you have to retrieve them using git lfs like this:
git lfs pull. - You can now run the software by running main.py.
- You need to have a camera connected to your computer.
- You need to have a microphone connected to your computer.
- You may also want to use headphones or speakers to hear the robot's speech.
- You may have to have a robot connected to your computer (see here). If you don't the software will still run, you just won't be able to control the robot.
- Many modules require OpenAI API key to function. You can get one here. This is required.
If you would like to replicate the training of the models, you can download the datasets here.
You can run the training of the models by running Training/Module/Aspect/trainer.py. For example, if you would like to train the Face Recognition model,
you would run the file Training/Vision/FaceRecognition/trainer.py.
If you'd like to contribute to the project or want to learn more details about the project, you can find more detailed documentation in the Documentation folder.
Note that there may be bugs or unresolved issues in the code. If you find any, please report them in the Issues section.