We are excited to announce that new models had been made available to the Transkribus crowd recently. Getting closer to our goal of being a platform for model sharing and thanks to our hard-working users a total of 17 models is free for public use so far. These models cover different epochs and languages like English, French, German, Italian, Dutch and Devanagari. Via this link you can access the file with an overview of the models. Also you can learn which institution or person has created the model and find a description, which documents it is suitable for: https://transkribus.eu/wiki/images/d/d6/Public_Models_in_Transkribus.pdf
If you are keen on sharing a model yourself, please get in touch and we will check the details (firstname.lastname@example.org). In case the data your model is trained on is sensitive and can not be published, we can take care that only the neural network is made available to other users, but the data is hidden. This way the model can “only” be used and no data behind is shown.
We are happy about seeing the Transkribus platform and community grow and are stoked about the great work our users are doing. Thanks again for your effort and keep transcribing…
Copyright © 2020 READ-COOP SCE