This project is dedicated to building a "Synthetic Human" which is called Karen (for now) for which we have assigned the female gender pronoun of "she". She has visual face recognition (opencv/opencv), speech transcription (mozilla/deepspeech), and speech synthesis (festival). Karen is written in Python and is targeted primarily at the single board computer (SBC) platforms like the Raspberry Pi.
Visit our main site: https://projectkaren.ai/
Read the docs: https://docs.projectkaren.ai/
Karen's architecture is divided into two main components: Containers and Devices. The containers focus on communication between other containers and devices are designed to control input and output operations. The most important container is the Brain which is a special type of container as it collects data and provides the skill engine for reacting to inputs. While a Brain does support all the methods of a normal container it is recommended to create a separate container to store all your devices.
Python Module Overview
|karen.containers.Brain||Main service for processing I/O.||8080|
|karen.containers.DeviceContainer||Secondary service for devices.||8081|
Python Device Module Overview
|karen.devices.Speaker||Audio output device for text-to-speech conversion|
|karen.devices.Listener||Microphone device for speech-to-text conversion|
|karen.devices.Watcher||Video/Camera device for object recognition|
|karen.panels.RaspiPanel||Panel device designed for Raspberry Pi 7" screen @ 1024x600|
In version 0.8.0 and later you are no longer required to install the brain, device, and the built-in plugins separately.
Karen is available through pip, but to use the built-in devices there are a few extra libraries you may require. Please visit the Basic Install page for more details.
# Install PIP (Python package manager) if not already installed sudo apt-get -y install python3-pip # Install the required system packages sudo apt-get -y install \ libfann2 \ python3-fann2 \ python3-pyaudio \ python3-pyqt5 \ python3-dev \ festival \ festvox-us-slt-hts \ libportaudio2 \ libasound2-dev \ libatlas-base-dev \ cmake # Optionally create your local environment and then activate it python3 -m venv /path/to/virtual/env --system-site-packages /path/to/virtual/env/bin/activate # Install the required build libraries python3 -m pip install scikit-build # Install required runtime libraries python3 -m pip install urllib3 \ requests \ netifaces \ numpy \ deepspeech \ pyaudio \ webrtcvad \ opencv-contrib-python \ Pillow \ padatious \ fann2 \ traceback # Install the karen module python3 -m pip install karen
To start execute as follows:
python3 -m karen
You can disable any of the built-in devices or containers with
--disable-builtin-[speaker, watcher, listener, panels, brain, container]. Use the
--help option for full listing of command line options including specifying a custom configuration file.
NOTE: The program will create/save a version of the configuration to
~/.karen/config.json along with any other data elements it requires for operation. The configuration file is fairly powerful and will allow you to add/remove devices and containers for custom configurations including 3rd party devices or custom skills.
Troubleshooting: "Cannot find FANN libs"
If you encounter an error trying to install the karen module on the Raspberry Pi then you may need to add a symlink to the library FANN library. This is due to a bug/miss in the "find_fann" function within the Python FANN2 library as it doesn't look for the ARM architecture out-of-the-box. To fix it run the following:
ln -s /usr/lib/arm-linux-gnueabihf/libdoublefann.so.2 /usr/local/bin/libdoublefann.so
Web Control Panel
If everything is working properly you should be able to point your device to the web control panel running on the Brain engine to test it out. The default URL is:
Demo running on Raspberry Pi
Help & Support
Help and additional details is available at https://projectkaren.ai