Some of you might already have come across the word “PyLaia” in connection with Transkribus. Actually, it is one more recognition engine, which has been developed by UPVLC (Universitat Politècnica de València).
PyLaia basically requires the same workflow as HTR+. First of all, please request the PyLaia training feature via firstname.lastname@example.org, by dropping us a short email indicating the email address you are registered with in Transkribus. We will then enable your account for it. Afterwards PyLaia is accessible via the same “Train”-button as HTR+. You can also use the Ground Truth you have already trained with HTR+ for PyLaia, this way you can compare the results of the two trainings directly. Of course, you can also use PyLaia in order to train new material. PyLaia models will be stored together with all other models on the left side of the “Model”-interface and you can choose it for recognition in the same way as with the HTR+ models. Also, the results in Character Error Rate are usually similar.
The price for recognition with PyLaia will be significantly lower than with HTR+. The exact prices will be made public on our homepage (https://readcoop.eu/) soon, as we plan to start the payment model of Transkribus with 19th of October 2020. It will be very interesting for us to see how PyLaia will perform on you documents and therefore we would like to very much encourage you to try it out. Thanks, and keep transcribing! 😊