Wow, with the Super Model "Titan I", #Transkribus seems to have taken a next very impressive step. In particular, our corpora with very heterogeneous hands are recognised significantly better in our tests so far than models trained specifically on the hands. If this is confirmed, even the time-consuming creation of training data and the model training could become obsolete 🤯
#HTR #ATR #PROPYLÄEN
https://readcoop.eu/introducing-transkribus-super-models-get-access-to-the-text-titan-i/

So far, so impressive! It looks like it worked very well, with a few - expected - issues like the e/o superscripts being misread and some uppercase letters, which look different between the two prints. Correcting these won't take much time. I'll check the remaining four pages and decide whether to improve the current model for this particular print or not afterward! #EthicaComplementoria #Transkribus #DigitalScholarlyEdition

After successfully training and improving my #Transkribus #HTR model for the #EthicaComplementoria prints, I used it on the youngest Ethica from 1728. Typographically, it is still very similar to the editions from the 17th century, so that should not be a big problem. I'll quality-check the first eight pages today and see, whether it is worthwhile improving the model for this particular print.

Hello #Monday crowd! Started the week with a guest lecture for BA students in pedagogy about #DigitalResearchActivities for historical research. They're working w/ syllabi and similar materials from Norway in the early 19th century.
Showed them #Transkribus, @CATMA_app #Recogito and the #NationalLibraryOfNorway's app collection!

And that's it! Sent off the new training set and hopefully improve the issues I have encountered!
I will also use this model for the 1728 print. It's a different printing press, but overall, the two prints are very much alike, and so is the #Fraktur type they use. #Transkribus #EthicaComplementoria #HTR #EarlyModern #PrintHistory

Moving back to the #HTR issues, we have phenomena like these (shown in the image): The layout detection model draws 'short' lines when the text is warped in the book fold. This leads to especially slim letters and punctuation not getting recognized. When I do the corrections, I will also extend the lines to include these characters. Hopefully, it will improve the recognition! #Transkribus #EthicaComplementoria

Doing the extra round of manual quality checking turns out to be quite fun!
The numbers are just ridiculously wrong: a 38 is read as 24 and 42 as 25; I don't know what's happening. Interestingly, it always identifies numbers as numbers, not letters!
Generally, the text is recognised very well; there are minor issues, mainly when #Transkribus occasionally draws too short lines, so slim letters and punctuation are missed.
I worked w/ on and off today, but I almost got another 25 pages proofread!

Exciting! Overnight, the text recognition job was completed and now I get to see how good the transcription is! #EthicaComplementoria #Transkribus #HTR

We are collaborating with #Wikimedia Foundation on the Wikisource Loves Manuscripts project, with a special twist! :apartyblobcat: The transcribed Indonesian manuscripts will be used to train a #Transkribus #HTR model! @BL_DigiSchol Read more here: https://blogs.bl.uk/digital-scholarship/2023/08/the-british-library-loves-manuscripts-on-wikisource.html

It's #Wednesday, and I'm continuing my work on transcribing the #EthicaComplementoria from 1674 using #Transkribus. My "job" ran overnight, and the training results were impressive! So, I did a final check on the layout recognition of the remaining pages and ran a #TextRecognition job on the entire Ethica print. The book contains both the Ethica Complementoria and the Tranchierbuch. The latter has many illustrations and tables, so I've decided to run it separately.

A blog post continuing my series of posts about the #EthicaComplementoria #DigitalScholarlyEdition project on the #GeorgGreflinger weblog: https://greflinger.hypotheses.org/716
Today about #HTR #Transkribus and re-using models.

🧵 3/ #ResearchSupportPartnershipUiO continues after lunch w/ my "adopted" colleagues from the #History section. I had a coordinating & getting-to-know meeting to set up some presentations and show-and-tell sessions for the Depts. #DigitalMeetup that happens every #Tuesday. I offered to do short sessions on #TaDiRAH, #Transkribus, #Tropy and #Tesseract during the fall. I'll use the 1678 #Danish translation of the #EthicaComplementoria as an example for #AutomatedTextRecognition of C17th books!

🧵 2/ #ResearchSupportPartnershipUiO I often get asked about how to quickly search through (handwritten) archival documents. Depending on how many documents we are talking about, there certainly are quicker ways then reading them! But setting up a workflow for #Digitisation, #AutomaticTextRecognition #QualityAssurance aren't done quickly either! Accessible tools like #Transkribus can help a lot here, but they can't do magic. So: plan enough time for these tasks and don't expect 100% accuracy!

Currently we're learning about #Transkribus to transcribe handwritten documents using AI and how to use it in #Wikisource as part of #Wikimania2023

The new #Transkribus interface is looking good. Although it seems there are a few weird broken bits due to CORS but I'm sure that'll all be sorted out.

https://readcoop.eu/coming-soon-new-transkribus-web-app/

Vorgestern fand die Sneak Peek von #Transkribus Next Gen statt. Wir haben gemeinsam mit fast 300 TN aus der ganzen Welt am Webinar teilgenommen. Das neue User Interface wird erst am 30. August 2023 freigeschaltet, aber die Beta-Version ist schon jetzt erreichbar: https://beta.transkribus.eu/

Entwarnung für Poweruser des Expert Clients: Transkribus hat angekündigt den Client auch weiter zu betreiben - trotz des weiteren Ausbaus der Webversion.

#HTR #digitalisierung #archiv #lwl #digitalhumanities

Enabling Handwritten Text Recognition on #Wikisource using #Transkribus OCR Engine: https://diff.wikimedia.org/2023/07/13/enabling-handwritten-text-recognition-on-wikisource-using-transkribus-ocr-engine/

If you have ten thousand words of handwriting, then you can train your own OCR model for use on Wikisource!

First day of #DH2023. I am at the #Transkribus workshop, so hopefully at the end of the day I can say that I know the text recognition platform well enough ;) #HTR #digitalhumanities

Ausgehend vom Reisebericht des Apothekergesellen Wageners aus dem 17. Jahrhundert, gibt Angela Göbel Einblicke in das Modelltraining und die Textbearbeitung in der Handschriftenerkennungssoftware Transkribus. Neuer Beitrag im Blog ➡ Grand Tour digital 👇

https://grandtourdig.hypotheses.org/290

#DigitalHumanities #Transkribus #FrüheNeuzeit #ATR #HTR

Selina Galka stellt im gleichnamigen Blog den Transkribus-Workflow der digitalen Edition "Die Memoiren der Gräfin Schwerin" vor 👇

https://memoiren.hypotheses.org/504

Mit dem Tool Figma wird das Interface der Edition gestaltet.

#DigitalHumanities #Transkribus #Figma #FrüheNeuzeit