All the current OCRopus sources can be found in the ./ocropy subdirectory.
Install them with:

    $ cd ocropy
    $ sudo apt-get install $(cat PACKAGES)
    $ python setup.py download_models
    $ sudo python setup.py install
    $ ./run-test

Other subdirectories contain examples for training etc.:

  - fraktur-boxes: An example of training OCRopus models on the same box
    files that are used for Tesseract training.  This is a good way of
    getting OCRopus training started.

  - uw3-500: An example of running the recognizer on text lines and
    training OCRopus models with unaligned data.