Public models in Transkribus

Have a look at this overview of the publicly available models in Transkribus we offer so far. For every model you will find a short description of the training material, which languages the model can be useful for and who has created and trained it. We are working on making more and more models available for Transkribus users, so they can benefit from the network effect and save work and time.

0
Models currently available

Featured Models

HTR+
Model name: Transkribus Typewriter 0.1
This is a general model for typwritten documents, it has been trained on 655000 words and the CER on the validation set is 1.28%.
Transkribus Team
Dutch, English, Finnish, German
n/a
Latin alphabet
Typewritten
1.28
HTR+
Model name: Transkribus print 0.3
This extended Transkribus print model includes typewritten, computer print outs and ‘decorative fonts’ (Schmuckschriften) material. It should be able to read historical Dutch, German, English, Finnish, French, and Swedish with ...
Transkribus Team
Dutch, English, Finnish, French, German, Swedish
n/a
Latin alphabet
Print
1.5
HTR+
Model name: Transkribus German Kurrent M2
This is a global model, which recognizes German Kurrent, Sütterlin and Fraktur scripts from 17th to 20th century. The training data set includes nearly 500 000 words and has a CER on the ...
Transkribus Team, University of Innsbruck
German
17th, 18th, 19th, 20th
German Kurrent, Sütterlin, Fraktur
Handwritten
5.29

All Public Models

Advanced search
Century
Select centuries
Language
Select languages
Material
Select material
Script
Select script
Engine
CER on validation set
0%9%

“CER” stands for “Character Error Rate” and defines how many percent of the characters had been transcribed the wrong way by the neural network.

HTR+
Model name: Charter Scripts XIII-XV_M1
This is a combination model of ground truth of different charter scripts from different projects and institutions, aiming at building a generic model. It is mainly based on documents from ...
Tobias Hodel
French, German, Latin
n/a
Latin alphabet
Handwritten
6.32
HTR+
Model name: Danish 1870-1950
This is a general model for Danish Handwriting from late 19th and 20th Century. It is based on the model which follows next in this document (RoyalDanishLibrary_20thCentury+) and parish council ...
Aarhus City Archives
Danish
19th, 20th
Latin alphabet
Handwritten
4.28
HTR+
Model name: Danish 1870-1950 v3.5
Newer incrementation of Danish 1870-1950 with added material and further experimentation with base models. Using material from The Royal Danish Library, Aarhus City Archive, Faxe Archive, Næstved Archive and Gentofte ...
Aarhus City Archives
Danish
19th, 20th
Latin alphabet
Handwritten
5.91
HTR+
Model name: RoyalDanishLibrary_20thCentury+
This is a general model for Danish cursive handwriting of the 20th century based on 16 different scribes. It had been created by Jakob K. Meile and his collegues in ...
Royal Danish Library
Danish
20th
Latin alphabet
Handwritten
3.99
HTR+
Model name: Danish Fraktur SB 19th century v.2.35
This model is based on more than 500 pages (about 30 900 words) of the Royal Danish Court & State Calendar and a few pages of the Danish High Court ...
Poul Steen
Danish
19th
Gothic Script
Print
0.97
HTR+
Model name: Gjentofte 1881-1913 Denmark 1000 epochs
This model is based on protocols from meeting in the locally elected community counsel. It is written in turn by the counsel members during the meeting and of varying quality, ...
Gentofte Community Archive Transkribus Team
Danish
19th, 20th
Latin alphabet
Handwritten
4.43
HTR+
Model name: Devanagari mixed M1
This model recognizes the South Asian Devanagari-script. It is based on ca. 200 pages of late 19th and early 20th century books by the Indian Naval Kishore Press. The books were mainly ...
Heidelberg University Library
N/A
19th, 20th
Devanagari
Print
HTR+
Model name: Devanagari_nagara_M1
The model recognized South Asian Devanagari-script. It is based on 65 pages of late 19th century books by the Indian Naval Kishore Press, all printed with the same type. The ...
Heidelberg University Library
N/A
19th
Devanagari
Print
HTR+
Model name: Dutch Mountains (18th Century)
This model is a combination of the 18th Century models from the Amsterdam City Archives (3500+ scans of 15 notarial handwritings) and the National Archives of the Netherlands (3500+ scans of VOC handwritings). ...
Amsterdam City Archives and National Archives of the Netherlands
Dutch
18th
Latin alphabet
Handwritten
5.67
HTR+
Model name: Dutch_Gothic_Print
This model is based on printed texts in the Gothic font that was used in the Low Countries, during the 16th, 17th and 18th century. The type of sources used ...
Entangled Histories (National Library Netherlands)
Dutch
16th, 17th, 18th
Gothic Script
Print
1.71
HTR+
Model name: IJsberg
careful transcription of dozens of different handwritings coming from the 17th, 18th and 19th century and comprises scans from the Incoming Documents from the Dutch East India Company (Overgekomen Brieven ...
National Archives Netherlands
Dutch
17th, 18th, 19th
Latin alphabet
Handwritten
HTR+
Model name: Dutch Margaretha Turnor 17th Century
This is the first model created by the Utrecht Archives. It is based on a thousand letters of Margaretha Turnor, who wrote to her husband during the late 17th century. ...
The Utrecht Archives
Dutch
17th
Latin alphabet
Handwritten
1.83
HTR+
Model name: Dutch Notarial Model 18th Century
This is the first 18th Century general model created by the City Archives of Amsterdam. It is based on thousands of scans from in total 15 different notaries who worked ...
City Archives of Amsterdam
Dutch
18th
Latin alphabet
Handwritten
5.27
HTR+
Model name: Dutch manuscript poetry 1603-1636
The model was trained on an extensive manuscript of early modern poetry, in separate hands (of which one is the most important) using different types of writing and special lay-outs ...
Bram Caers
Dutch
17th
Latin alphabet
Handwritten
4.78
HTR+
Model name: Dutch_Romantype_Print
This model is based on printed texts in the Roman-type fonts that were used in the Low Countries, during the late 16th, 17th, 18th and 19th century. Some pages may ...
Entangled Histories project (National Library of the Netherlands)
Dutch
16th, 17th, 18th, 19th
Latin alphabet
Handwritten
1.17
HTR+
Model name: Typewritten/print_early_1900
The National Archives Netherlands have made this model for typewritten and print writings which were used in the Netherlands during the late 19th and early 20th century. 72100 words have ...
National Archives Netherlands
Dutch
19th, 20th
Latin alphabet
Print, Typewritten
3.24
HTR+
Model name: English Writing M1
This model was trained on over 50,000 words from papers written by the English philosopher Jeremy Bentham (1748–1832) and his secretaries. In the best cases, it generates an output where ...
University College London – Bentham project
English
18th, 19th
Latin alphabet
Handwritten
5
HTR+
Model name: Transkribus English Handwriting M2
This model has been trained on the manuscripts of the British philosopher Jeremy Bentham (1748-1832) which have been made available in the course of the Bentham project of the University ...
University College London – Bentham project
English
18th, 19th
Latin alphabet
Handwritten
6.32
HTR+
Model name: Estonian Court Records 19thC
This model is based on Uue-Põltsamaa Municipal Court Records (est. Vallakohus, ger. Gemeindegericht) from the years 1852-1866. It has been trained with 50 000 words and the CER for the ...
Estonian National Archives
Estonian
19th
Latin alphabet
Handwritten
3.55
HTR+
Model name: Manuscripts of Ethiopia and Eritrea
This is a model for the transcription of Manuscripts from Ethiopia and Eritrea in Classical Ethiopic (Gǝʿǝz). It has been trained as part of the Beta maṣāḥǝft project and in ...
Project Beta maṣāḥǝft: Manuscripts of Ethiopia and Eritrea
Ethiopic
n/a
Latin alphabet
Handwritten
HTR+
Model name: NLF_Newseye_GT_FI_M2+
This model works well with Finnish print from 18th century to midth of 20th century. For standard text in newspapers from that time error rates much below 1% were measured.The ...
Newseye-project
Finnish
18th, 19th, 20th
Latin alphabet
Print
0.61
HTR+
Model name: NAF Court Records M10
This model is based on Renovated District Court Records (Fi: Kihlakunnanoikeuksien renovoidut tuomiokirjat, Swe: Häradsrätternas renoverade domböcker) from the years 1809-1870. Models training set consists of 2841 double-pages and the ...
National Archives Finland
Swedish
19th
Latin alphabet
Handwritten
HTR+
Model name: BnF_Newseye_M2+
The model works well with French print from late 18th century to mid of 20th century. For standard text in French newspapers from that time error rates much below 1% ...
Newseye-project
French
18th, 19th, 20th
Latin alphabet
Print
2.73
HTR+
Model name: French_18thC_Print
This model is based on printed texts in French (Romantype Font) that was used in Flanders (Low Countries), during the 18th century. The type of sources used for this model, ...
Entangled Histories project (National Library Netherlands)
French
18th
Latin alphabet
Print
0.65
HTR+
Model name: Parallèle des Anciens et des Modernes M2
This model is based on a printed text in French at the end of 17th century : Parallèle des Anciens et des Modernes by Charles Perrault (1688-1697, publisher : Jean-Baptiste ...
Project: Un choc de modernité : Anciens et Modernes au tournant des XVIIe et XVIIIe siècles
French
17th
Latin alphabet
Print
2.7
HTR+
Model name: HIMANIS Chancery M1+
As part of the HIMANIS project (lead by D. Stutzmann, C. Kermorvant & E. Vidal), the text edition provided by P. Guérin and encoded in TEI by the Ecole nationale ...
HIMANIS project
French, Latin
n/a
Latin alphabet
Handwritten
5.33
HTR+
Model name: LaMOP-Livre_Rouge_1
This model is based on the book “Y//3 Livre Rouge, Châtelet de Paris (11..-1790)” (Archives Nationales de France) and the model was released by Hugo Regazzi (Universite Paris 1/LaMOP), Pierre ...
Paris University
French
n/a
Latin alphabet
Handwritten
8
HTR+
Model name: ONB_Newseye_GT_M1+
Thanks to the Library Labs of the Austrian National Library and the NewsEye project we are happy to announce the release of a free model which is capable to read German Fraktur documents especially from the ...
Austrian National Library and NewsEye project
German
19th, 20th
Gothic Script
Print
1.65
HTR+
Model name: NZZ Gold Standard M1+
The model is based on 167 title pages from the Neue Zürcher Zeitung (NZZ) covering the years 1780 to 1940. About 273 400 words had been trained for this model and the CER ...
University of Zurich
German
18th, 19th, 20th
Gothic Script
Print
0.45
HTR+
Model name: German_Kurrent_XIX_M2
This model has a large train (3038000 words) and test set for German Kurrent (19th century). The ground truth stems from different projects and partners and is biased towards Swiss ...
Tobias Hodel
German
19th
German Kurrent
Handwritten
7.24
HTR+
Model name: German_Kurrent_XVI-XVIII_M1
This model has a large train (1579200 words) and test set for German Kurrent (16th -18th century). The ground truth stems from different projects and partners and is biased towards ...
Tobias Hodel
German
16th, 17th, 18th
German Kurrent
Handwritten
8.42
HTR+
Model name: German Fraktur 18th Century – WrDiarium_M9
This model has been trained on 829 400 words from the „Wien[n]erisches Diarium“ / „Wiener Zeitung“ (1703-1799), which is an Austrian newspaper. The CER on the validation set is 0.79%.The ...
Austrian Centre for Digital Humanities and Cultural Heritage at the Austrian Academy of Sciences
German
18th
German Kurrent
Print
0.79
HTR+
Model name: Transkribus German Kurrent M2
This is a global model, which recognizes German Kurrent, Sütterlin and Fraktur scripts from 17th to 20th century. The training data set includes nearly 500 000 words and has a CER on the ...
Transkribus Team, University of Innsbruck
German
17th, 18th, 19th, 20th
German Kurrent, Sütterlin, Fraktur
Handwritten
5.29
HTR+
Model name: Italian Administrative Hands, 1550-1700
The Italian Administrative Hands model features a variety of Italian-language documents from state archives in Milan, Venice, Florence, Pisa, and Genoa. The training set represents a spectrum of humanistic, italic ...
Rachel Midura (Virginia Tech), Jake Dyble (Exeter/Pisa), Antonio Iodice (Exeter/Genoa), and Sara Mansutti (Cork).
Italian
16th, 17th
Latin alphabet
Handwritten
HTR+
Model name: Gothic_Book_Scripts_XIII-XV_M4
This model is capable of recognizing book scripts from the 13th to the 15th century. It is based on documents from a variety of projects, among others Parzival (Universität Bern) ...
Tobias Hodel
German, Latin
n/a
Gothic Script
HTR+
Model name: Noscemus GM 3.0
The Noscemus general model is able to read printed Latin text, especially from the 16th, 17th and 18th century. The model was released by Stefan Zathammer and is based on ...
Noscemus project (University of Innsbruck)
English, German, Greek, Italian, Latin
15th, 16th, 17th, 18th
Latin alphabet, Gothic Script, Greek alphabet
Print
HTR+
Model name: Medieval Protocolbook ‘s-Hertogenbosch by Townclerck Petrus de Os sr., 1497-1542
The Huygens Institute for History of the Netherlands, an institute of the Royal Netherlands Academy of Arts and Sciences, is unlocking the Aldermen Records of ‘s-Hertogenbosch 1366-1811. Because the protocolbooks ...
Geerturi van Synghel (Huygens ING)
Dutch, Latin
15th, 16th
Gothic Script
Handwritten
4.11
HTR+
Model name: NeoLatin_Ravenstein_1643-1772
This model is based on the transcription of the “Litterae Annuae Parochiae Ravensteijn SJ ab Anno 1643 ad Annum 1772”. The annual letters were kept at the Archivum Neerlandicum Societatis ...
Several contributors
Latin
17th, 18th
Latin alphabet
Handwritten
3.58
HTR+
Model name: Transkribus print 0.3
This extended Transkribus print model includes typewritten, computer print outs and ‘decorative fonts’ (Schmuckschriften) material. It should be able to read historical Dutch, German, English, Finnish, French, and Swedish with ...
Transkribus Team
Dutch, English, Finnish, French, German, Swedish
n/a
Latin alphabet
Print
1.5
HTR+
Model name: Combined_Full_VKS_2
Prof. Achim Rabus from the University of Freiburg has released two specialized models which are able to read Russian Curch Slavonic. The first model is called VMC_Test_4+: Training data consist of ...
Achim Rabus (University of Freiburg)
Church Slavonic
11th, 16th
Cyrillic alphabet
Handwritten
3.92
HTR+
Model name: VMC_Test_4+
Prof. Achim Rabus from the University of Freiburg has released two specialized models which are able to read Russian Curch Slavonic. The first model is called VMC_Test_4+: Training data consist of ...
Achim Rabus (University of Freiburg)
Church Slavonic
16th
Cyrillic alphabet
Handwritten
3.72
HTR+
Model name: NLF_Newseye_GT_SV_M2+
This model works well with Swedish print from late 18th century to midth of 20th century. For standard text in newspapers from that time error rates much below 1% were ...
Newseye-project
Swedish
18th, 19th, 20th
Latin alphabet
Print
4
HTR+
Model name: Gothenburg_police_reports_1868-1902
This model is trained on reports from the Gothenburg Police Detective department 1868-1902, held at the Swedish National Archives in Gothenburg. The groundtruth for the model training consists of transcibed ...
Swedish National Archives
Swedish
19th
Latin alphabet
Handwritten
2.7
HTR+
Model name: Jaemtlands_domsagasM1+
The model “Jaemtlands_domsagasM1+” is trained on 5946 pages (ca. 491 300 words) from court books from Jämtland county in Sweden – Jämtlands läns domsaga, from the years 1647-1688. The books are ...
Swedish
17th
Latin alphabet
Handwritten
6.32
HTR+
Model name: Transkribus Typewriter 0.1
This is a general model for typwritten documents, it has been trained on 655000 words and the CER on the validation set is 1.28%.
Transkribus Team
Dutch, English, Finnish, German
n/a
Latin alphabet
Typewritten
1.28
PyLaia
Model name: Dutch_Gothic_Print_Pylaia
This model is based on printed texts in the Gothic font that was used in the Low Countries, during the 16th, 17th and 18th century. The type of sources used ...
Entangled Histories project
Dutch
16th, 17th, 18th
Gothic Script
Print
2
PyLaia
Model name: Dutch_Romantype_Pylaia
This model is based on printed texts in the Roman font that was used in the Low Countries, during the 16th, 17th and 18th century. The type of sources used ...
Entangled Histories project
Dutch
16th, 17th, 18th
Latin alphabet
Print
1.4
PyLaia
Model name: French_18thC_Pylaia
This model is based on printed texts in French (Romantype Font) that was used in Flanders (Low Countries), during the 18th century. The type of sources used for this model, ...
Entangled Histories project
French
18th
Latin alphabet
Print
0.91
PyLaia
Model name: DAT 18. Jh M3b_Pylaia
The model has been trained on 19th century newspapers in German Fraktur. Print style for umlaut varies throughout (superscript “e” vs öäü). 102900 words have been trained and the CER ...
TU Darmstadt
German
19th
Gothic Script
Print
0.3
PyLaia
Model name: German_Kurrent_XIX_pylaia
This model has a large train (5100400 words) and test set for German Kurrent (19th century). The ground truth stems from different projects and partners and is biased towards Swiss ...
Tobias Hodel
German
19th
German Kurrent
Handwritten
6.9
PyLaia
Model name: Acta_17 PyLaia
This PyLaia model was trained on the basis of more than 594000 words from about 1000 different writers during the period 1580-1705. The CER on the validation set is 5.8%. ...
University of Greifswald
German, Latin, Low German
16th, 17th, 18th
Latin alphabet, German
Handwritten
5.8
PyLaia
Model name: Pylaia_NeoLatin_Ravenstein
This model is based on the transcription of the “Litterae Annuae Parochiae Ravensteijn SJ ab Anno 1643 ad Annum 1772”.The annual letters were kept at the Archivum Neerlandicum Societatis Iesu ...
Annemieke Romein
Latin
17th, 18th
Latin alphabet
Handwritten
4
PyLaia
Model name: German_Kurrent_17th-18th
Already got to know one of our biggest models in Transkribus? That is the German_Kurrent_17th-18th model by the University of Greifswald. Different kinds of texts have been part of the ...
University of Greifswald
German
17th, 18th, 19th
German Kurrent
Handwritten
5.5
HTR+
Model name: Latin Portuguese Print 17th century
This model is based on the Index of censorship printed by Pedro Craesbeeck, a key Lisbon printer of the early seventeenth century. It has been carried out by Hervé Baudry (hbaudry@fcsh.unl.pt) ...
Hervé Baudry
Latin, Portuguese, Spanish
17th
Latin alphabet
Print
1.44
HTR+
Model name: Glagolitic printings
The model is the result of a collaboration between the University Library Tübingen and the Slavic Department Freiburg (Achim Rabus). Selected pages from different printings of the Tübingen-Urach tradition have ...
University Library Tübingen, Slavic Department Freiburg (Achim Rabus)
Church Slavonic
Glagolitic
Print
4.24
HTR+
Model name: Handwritten Glagolitic
This model is based on Ground Truth from the manuscripts Cod. Vind. Slav. 3 (Breviary of Vid of Omišalj) and II. beramski brevijar. It can be used for transcribing different ...
Slavic Department Freiburg (Achim Rabus)
Croatian
14th, 15th
Glagolitic
Handwritten
5.73
HTR+
Model name: Acta_17 HTR+
The training data of this model is based on legal texts and court writings from the Responsa of the Greifswald Law Faculty and can cope with simple German and Latin ...
Dirk Alvermann, Elisabeth Heigl and Anna Brandt of the University of Greifswald
German, Latin
16th, 17th, 18th
Latin alphabet, German
Handwritten
6.3
HTR+
Model name: UCL–University of Toronto #7
This new public model for the recognition of medieval Latin has been released thanks to a collaboration between the Bentham Project of the University College London and the DEEDS (Documents ...
Bentham Project (University College London), DEEDS-project (University of Toronto)
Latin
14th, 15th, 13th
Latin alphabet
Handwritten
0.8
HTR+
Model name: Republic_7
This model is based on the handwritten resolutions of the Dutch States-General (1576-1796). It has been created during the project ‘REPUBLIC’, which aims to provide an online searchable edition of ...
REPUBLIC Project (Huygens ING)
Dutch
17th, 18th
Latin alphabet
Handwritten
2.99
HTR+
Model name: Land registers (Verfachbücher) Tyrol, 1750-1800
This model is trained on about 105.000 words from the so-called “Verfachbücher” from the Tyrolean Pustertal valley and based on the public Model German_Kurrent_XVI-XVIII_M1. The ground truth material covers several ...
Projects “Reading in the Alps. Private book ownership in the Catholically dominated Central Alps 1750–1800” and “Living in the Alps”
German
18th
German Kurrent
Handwritten
5.5
HTR+
Model name: BBM Bulliot French C19th handwritten 2021
This model has been created within the scope of “Bulliot, Bibracte et moi”, winner of a French Ministry of Culture’scall for Innovative Digital Services. That is a “citizen science” project ...
Project “Bulliot, Bibracte et moi"
French
19th
Latin alphabet
Handwritten
7.73