Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
norden.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
Moin! Dies ist die Mastodon-Instanz für Nordlichter, Schnacker und alles dazwischen. Folge dem Leuchtturm.

Administered by:

Server stats:

3.4K
active users

norden.social: AboutStatusProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.7

#HTR

0 posts0 participants0 posts today
Public *
Henrik Schönemann

In light of current news coming out of UK, a repost:
@SafeguardingResearch has torrents of #trans (healthcare) related resources on SciOp:
sciop.net/tags/trans

Those are all webarchives, easily offline/locally re-playable via replayweb.page/

Re torrenting:
sciop.net/docs/using/torrentin

Most of them come from a list originally made by @dee; mostly webarchived by @ashley
#ProtectTransLives #HTR

sciop.nettrans - Tag - SciOpPreserving Public Information
Public *
Henrik Schönemann

Circling back to the starting point of @SafeguardingResearch, there are now torrents of #trans healthcare related resources on SciOp:
sciop.net/tags/trans

Those are all webarchives, easily offline/locally re-playable via replayweb.page/

Re torrenting:
sciop.net/docs/using/torrentin

Most of them come from a list originally made by @dee; mostly webarchived by @ashley
#ProtectTransLives #HTR

sciop.nettrans - Tag - SciOpPreserving Public Information
Continued thread
Public *
Annika Rockenberger (she/they)

🧵 2/2
tl;dr #neurodivergent #freeassociation #musings

Combining proof-reading with textual markup and manual entity recognition, it becomes the perfect hyper focus activity.
I use #Transkribus for my #HTR and for the last few days, I have been unlucky with the traffic for both model training and text recognition. The queues are long and take a lot of time and I am deprived of my error hunting and current hyper fixation on #Mongolia #BogdKhanate #EasternChina #TravelDiaries #TEI #Encoding

Public
David Haskiya

A bit depressing how often university research projects doing HTR are unwilling to share their training data with a public agency who wants to combine it with other training data and create an openly licensed HTR-model. To me it seems contrary to an Open Science-ethos, a waste of effort, and be counter-productive to future research.

(Sorry if this comes off as a gripe.)

#HTR#OpenScience#OpenData
Public
Jens Mittelbach

Ahead of Print in BFP: New article: Digitale Erschließung historischer Bibliotheken. The Bibliotheca Eugeniana Digital project applies digital humanities to explore a major Baroque book collection. #DigitalHumanities #HistoricalBooks #MachineLearning #HTR #Visualization

doi.org/10.1515/bfp-2024-0074

De Gruyter · Digitale Erschließung historischer Bibliotheken: Erkenntnisse und Perspektiven aus dem Projekt Bibliotheca Eugeniana DigitalZusammenfassung Die Bibliotheca Eugeniana, eine bedeutende barocke Buchsammlung, wurde nach dem Tod von Prinz Eugen von Savoyen in die Österreichische Nationalbibliothek integriert. Das Projekt „Bibliotheca Eugeniana Digital“ nutzt Methoden der digitalen Geisteswissenschaften, um die Sammlung neu zu erschließen. Zu den Ergebnissen zählen eine digitale Edition des handschriftlichen Katalogs mit Verknüpfungen zum modernen Katalog, zusätzlichen Metadaten und einer visuellen Schnittstelle zur Erkundung.
Public
FIZ ISE Research Group

Very happy to have Heleen Wilbrink and Annelot Vijn from Utrecht Archives in our (online) Journal Club today taking about recent projects related to Records in Context (RiC-O) and Persons in Context ontologies as well as on transkribus-based HTR, LLM-based post processing and information extraction.

#archives @epoz @tabea @AnnaJacyszyn @heikef @enorouzi @joerg @sourisnumerique @GenAsefa #ontologies #semanticweb #lod #dh #culturalheritage #htr #transkribus #llms #journalclub

Screenshot of our Zoom-Session of the FIZ ISE Journal Club featuring Heleen Wilbrink and Annelot Vijn from Utrecht Archives.
Public
David Haskiya

We've launched an updated version of our HTRFlow demo-app on HuggingFace.

huggingface.co/spaces/Riksarki

Try it out and give us your feedback!

There are lots of architectural updates under the hood, making it easier for us to maintain the app and add new capabilities like support for Pylaia-models. It's now basically a client to our HTR/OCR-pipeline software HTRFlow Core.

huggingface.coHTRFLOW - a Hugging Face Space by Riksarkivethtrflow demo app
#HTR#ML#OpenSource
Public *
David Haskiya

We've made #Swedish language training data for development of #HTR models available for download, riksarkivet.se/psidata/traning

This data, together with data from other archives whose training data is not for us to publish, is the basis for our HTR-model Swedish Lion Libre, huggingface.co/collections/Rik

If you do use the training data, the model or, even better, you have ground-truth data you'd like to share, just get in touch!

RiksarkivetTräningsdata för HTR-modeller - RiksarkivetDatasetet innehåller noggrant och manuellt avskrivna och uppdelade texter från arkivhandlingar på Riksarkivet.
#TrainingData#AI#Archives
Public
Thekla Kluttig

Das Missverhältnis zwischen den bestehenden technischen Möglichkeiten + Erwartungshaltungen von Nutzenden und den tatsächlichen Möglichkeiten / der Realität sehr vieler (großer wie kleiner) Archive wird immer krasser.
#archivistodon #Erschließung #HTR / #ATR #Familienforschung
compgen.de/2024/12/kuenstliche

Verein für Computergenealogie e.V. (CompGen) · Künstliche Intelligenz im Dienst der Genealogie
More from Verein für Computergenealogie e.V. (CompGen)
Public
Annika Rockenberger (she/they)

📣 The #SustainableDSE network had the honour to showcase the newly launched digital collection and research platform for the 🇳🇴 Norwegian Folklore Archives, SAMLA. Read about the archives and how the various documents were transcribed using #Transkribus for #ATR #HTR on our #Blog dsenetwork.hypotheses.org/314 #Folklore #Folkloristics #Norway #Archive

Sustainable Digital Scholarly Editions NetworkSearchable Norwegian Tradition Archives – The SAMLA ProjectThe SAMLA project has digitized three Norwegian tradition archives containing written traditions and folklore. The use of machine assisted text recognition is applied to make the material searchable and readable, and, by that, more accessible for the public. SAMLA summarized SAMLA is both the name of a digitizing project and the end product: a digital […]
Public *
Henrik Schönemann

I'm looking for some good #HTR-Models for Sütterlin - and I know, stuff isn't magic.
(But I'm still stuck in 2021 & have probably missed new developments...)
Currently I only know of some transkribus-models, but haven't tested them yet. And @stefan_hessbrueggen mentioned 'transformer-based/vision-to-text models'
- readcoop.eu/model/transkribus-
- readcoop.eu/model/german-kurre
- zenodo.org/records/7933463 (thanks @awinkler!)

#DigitalHumanities #digitalhistory @histodons

READ-COOPTranskribus German handwriting M1This model includes Transkribus German Kurrent M2 and some sets containing german language Latin script. It works best for documents/collections with
Replied in thread
Public
Annika Rockenberger (she/they)

@raphaelaheil Thank you again for your wonderful presentation and workshops! We've written up a blog post about the events. Read it on the #BærUt #SustainableDSE weblog on #Hypotheses.org dsenetwork.hypotheses.org/128 #HTR #ATR #AstridLindgren #Manuscript #Shorthand #Stenography #Python #Loghi #PyTorch

Sustainable Digital Scholarly Editions NetworkDIY Automatic Text Recognition – Two Workshops and a Keynote on Astrid Lindgren’s Shorthand ManuscriptsWhat do you do with a couple thousand pages of manuscript entirely written in shorthand? Well, you train an automatic text recognition model to transcribe the intricate shorthand notation into human and machine-readable text! The Network for Sustainable Digital Scholarly Editions was delighted to host Raphaela Heil, a computer scientist from Uppsala University and The […]
ExploreLive feeds
About