Find research datasets worth reusing

Text-fig. 11. a, b: Coriaria aff. myrtifolia. a: Oriolo MSF 647. b: Oriolo MSF 704. c, d: Populus aff. alba. c: Oriolo MSF 745. d: Oriolo MSF 725. e: Populus aff. tremula Oriolo MSF 749. f–h: Populus aff. nigra. f: Oriolo MSF 737. g: Oriolo MSF 742. h: Oriolo MSF 738. Scale bars 10 mm (a–d), 50 mm (e–h). in The Late Early Pleistocene Flora Of Oriolo, Faenza (Italy): Assembly Of The Modern Forest Biome

Text-fig. 11. a, b: Coriaria aff. myrtifolia. a: Oriolo MSF 647. b: Oriolo MSF 704. c, d: Populus aff. alba. c: Oriolo MSF 745. d: Oriolo MSF 725. e: Populus aff. tremula Oriolo MSF 749. f–h: Populus aff. nigra. f: Oriolo MSF 737. g: Oriolo MSF 742. h: Oriolo MSF 738. Scale bars 10 mm (a–d), 50 mm (e–h).

Text-fig. 14. a, b: Acer aff. campestre. a: Oriolo MSF 664. b: Oriolo MSF 666. c, d: Acer aff. monspessulanum. c: Oriolo MSF 641. d: Oriolo MSF 662. e: Acer aff. opulus subsp. obtusatum Oriolo MSF 669. f, g: Acer aff. cappadocicum subsp. lobelii. f: Oriolo MSF 675. g: Oriolo MSF 631. h, i: Cornus sp. Oriolo MSF 655, two views of a strongly folded leaf impression. Scale bars 50 mm (a, e–g), 10 mm (b–d, h, i). in The Late Early Pleistocene Flora Of Oriolo, Faenza (Italy): Assembly Of The Modern Forest Biome

Text-fig. 14. a, b: Acer aff. campestre. a: Oriolo MSF 664. b: Oriolo MSF 666. c, d: Acer aff. monspessulanum. c: Oriolo MSF 641. d: Oriolo MSF 662. e: Acer aff. opulus subsp. obtusatum Oriolo MSF 669. f, g: Acer aff. cappadocicum subsp. lobelii. f: Oriolo MSF 675. g: Oriolo MSF 631. h, i: Cornus sp. Oriolo MSF 655, two views of a strongly folded leaf impression. Scale bars 50 mm (a, e–g), 10 mm (b–d, h, i).

Text-fig. A2. a: Ulmus carpinifolia GLED., 1773 syn. of Ulmus minor MILL., 1768, (herbarium E00824885). b: Ulmus carpinifolia GLED., 1773 syn. of Ulmus minor MILL., 1768, (herbarium E00824885). c: Ulmus carpinifolia GLED., 1773 syn. of Ulmus minor MILL., 1768, (herbarium E00824885 detail of (a)). d, e: Ulmus elliptica K.KOCH, 1849 (herbarium E00034393). f, g: Ulmus lancifolia ROXB., 1814, nom. inval. (herbarium NMNH03413489). h: Ulmus lancifolia ROXB., 1814, nom. inval. (herbarium NMNH03413488). Asterisks indicate different types of asymmetric leaf base. Scale bars 50 mm (a, d, e, f), 10 mm (b, c, g, h). in The Late Early Pleistocene Flora Of Oriolo, Faenza (Italy): Assembly Of The Modern Forest Biome

Text-fig. A2. a: Ulmus carpinifolia GLED., 1773 syn. of Ulmus minor MILL., 1768, (herbarium E00824885). b: Ulmus carpinifolia GLED., 1773 syn. of Ulmus minor MILL., 1768, (herbarium E00824885). c: Ulmus carpinifolia GLED., 1773 syn. of Ulmus minor MILL., 1768, (herbarium E00824885 detail of (a)). d, e: Ulmus elliptica K.KOCH, 1849 (herbarium E00034393). f, g: Ulmus lancifolia ROXB., 1814, nom. inval. (herbarium NMNH03413489). h: Ulmus lancifolia ROXB., 1814, nom. inval. (herbarium NMNH03413488). Asterisks indicate different types of asymmetric leaf base. Scale bars 50 mm (a, d, e, f), 10 mm (b, c, g, h).

Text-fig. A3. a: Leaf morphotype 1 Tebano MSF SG 049. b: Leaf morphotype 2 Oriolo MSF 631. c: Leaf morphotype 3 Oriolo MSF n.n. d, f: Leaf morphotype 4. d: Oriolo MSF 891. e: Oriolo MSF 856. f: Oriolo MSF 858. g: Leaf morphotype 5 Oriolo MSF 783. h: Leaf morphotype 6 Oriolo MSF 952. i: Leaf morphotype 7 Oriolo MSF 862. j, l: Leaf morphotype 8. j: Oriolo MSF 912. k: Oriolo MSF 662. l: Oriolo MSF 662-1. m: Leaf morphotype 9 Oriolo MSF 715. n: Leaf morphotype 10 Oriolo MSF 716. o: Leaf morphotype 11, overview and detail of margin Oriolo MSF 880. p–z: Various rosaceous leaves/ leaflets. p: Oriolo MSF 943. q: Oriolo MSF 890. r: Oriolo MSF 950. s: Oriolo MSF 958. t: Oriolo MSF 966 aff. Sorbus. u: Oriolo MSF 956. v: Oriolo MSF 961. w: Oriolo MSF 962. x: Oriolo MSF 874. y: Oriolo MSF 883. z: Oriolo MSF 960. in The Late Early Pleistocene Flora Of Oriolo, Faenza (Italy): Assembly Of The Modern Forest Biome

Text-fig. A3. a: Leaf morphotype 1 Tebano MSF SG 049. b: Leaf morphotype 2 Oriolo MSF 631. c: Leaf morphotype 3 Oriolo MSF n.n. d, f: Leaf morphotype 4. d: Oriolo MSF 891. e: Oriolo MSF 856. f: Oriolo MSF 858. g: Leaf morphotype 5 Oriolo MSF 783. h: Leaf morphotype 6 Oriolo MSF 952. i: Leaf morphotype 7 Oriolo MSF 862. j, l: Leaf morphotype 8. j: Oriolo MSF 912. k: Oriolo MSF 662. l: Oriolo MSF 662-1. m: Leaf morphotype 9 Oriolo MSF 715. n: Leaf morphotype 10 Oriolo MSF 716. o: Leaf morphotype 11, overview and detail of margin Oriolo MSF 880. p–z: Various rosaceous leaves/ leaflets. p: Oriolo MSF 943. q: Oriolo MSF 890. r: Oriolo MSF 950. s: Oriolo MSF 958. t: Oriolo MSF 966 aff. Sorbus. u: Oriolo MSF 956. v: Oriolo MSF 961. w: Oriolo MSF 962. x: Oriolo MSF 874. y: Oriolo MSF 883. z: Oriolo MSF 960.

Text-fig. 4. Graphical visualization of Phytogeographic Reference Regions Assessment (PRRA) of nearest living relative genera of fossil-taxa from late Early Miocene Wiesa assemblage in eastern Germany. Analysis yields only NLRs which have modern distribution area (partly) in E and SE Asia. For relationships of fossil-taxa to nearest living relatives or ecological equivalents, see Tab. 6; taxa used for analysis marked with asterisks. Three geographic resolutions conducted: a – grid with 1.5° latitude/longitude resolution, b – grid with 2°, c – grid with 3°; similarity column indicates cooccurrences of genera of nearest living relatives in single grid box. Maximum value in our analysis: grid box marked with arrow in map a, located in western Yunnan Province, P. R. China and southern Kachin Province, NE Myanmar (east of Myitkyina city), area with 97.371 7–98.874 2° longitude and 24.586 7–25.837 5° latitude, yields 23 co-occurring species of 13 genera (Tab. 7). in Assessment Of Phytogeographic Reference Regions For Cenozoic Vegetation: A Case Study On The Miocene Flora Of Wiesa (Germany)

Text-fig. 4. Graphical visualization of Phytogeographic Reference Regions Assessment (PRRA) of nearest living relative genera of fossil-taxa from late Early Miocene Wiesa assemblage in eastern Germany. Analysis yields only NLRs which have modern distribution area (partly) in E and SE Asia. For relationships of fossil-taxa to nearest living relatives or ecological equivalents, see Tab. 6; taxa used for analysis marked with asterisks. Three geographic resolutions conducted: a – grid with 1.5° latitude/longitude resolution, b – grid with 2°, c – grid with 3°; similarity column indicates cooccurrences of genera of nearest living relatives in single grid box. Maximum value in our analysis: grid box marked with arrow in map a, located in western Yunnan Province, P. R. China and southern Kachin Province, NE Myanmar (east of Myitkyina city), area with 97.371 7–98.874 2° longitude and 24.586 7–25.837 5° latitude, yields 23 co-occurring species of 13 genera (Tab. 7).

opencc-by-4.0Oct 2022View details →

Corpus Criticorum (1450-1650) - Supplement 3 - A BibTeX dataset of early modern publications featuring the notion of critique on their title pages.bib

A comprehensive BibTeX bibliography of early modern publications featuring the notion of Critique on their title pages formed in Zotero. The data was collected by exploiting readily-available pan-European (e.g., the Universal Short Title Catalogue), language-based (e.g., the Germanophone VD17), and national (e.g., Italy’s ICCU) catalogue records. The quasi-totality (217/218) of the title pages were consulted in order to perform data curation (i.e., standardisation) and assure its accuracy (i.e., verification of names, dates, title page wording, etc.).

opencc-by-4.0Aug 2018View details →

GT4HistOCR: Ground Truth for training OCR engines on historical documents in German Fraktur and Early Modern Latin

GT4HistOCR contains ground truth for research in Optical Character Recognition (OCR) technology applied to historical printings in German Fraktur and Early Modern Latin. The ground truth comes in pairs of images of single printed lines as they appear in book pages (*.png) and their corresponding diplomatic transcriptions (*.gt.txt), which are UTF-8 strings preserving the character forms (glyphs) as much as possible within the UNICODE standard. These pairs of line images and their transcriptions can be directly used to train recognition models with, e.g., the open source OCR engines OCRopy or Tesseract. A total of 313,173 ground truth lines are provided. Please note that the subcorpora making up this collection used different transcription guidelines, so it is a bad idea to train a recognition model on the total collection! Rather train individual models for each subcorpus. Fur further information about the subcorpora, please see the README file and the accompanying publication. If these data are useful for you, please cite the accompanying publication: <pre>@article{<a href="http://springmann.net/publications.html#springmann2018gt4hist">springmann2018gt4hist</a>, author = {Uwe Springmann and Christian Reul and Stefanie Dipper and Johannes Baiter}, title = {{Ground Truth for training {OCR} engines on historical documents in German Fraktur and Early Modern Latin}}, journal = {J. Lang. Technol. Comput. Linguistics}, volume = {33}, number = {1}, pages = {97--114}, year = {2018}, url = {https://jlcl.org/content/2-allissues/1-heft1-2018/jlcl_2018-1_5.pdf} }</pre>

opencc-by-4.0Dec 2018View details →

Shared unique tetragrams between early modern plays

This spreadsheet lists plays in Martin Mueller’s corpus Shakespeare His Contemporaries according to dislegomena consisting of at least four words i.e. tetragrams that occur in only two plays of the period.

opencc-by-4.0Apr 2017View details →

Phrasal repetitions between Arden of Faversham and other early modern plays

This spreadsheet ranks Arden of Faversham against all other plays in Martin Mueller’s corpus Shakespeare His Contemporaries according to the number and type of shared phrases

opencc-by-4.0Dec 2012View details →

Text-fig. 4. Dendrogram (Ward's method, squared Euclidean distance) showing the relationship between the studied fossil vegetation assemblages of Hrádek/N. (48), Wackersdorf (49), Berzdorf and Wiesa (50) and the Mydlovary Fm. (51) and the studied modern vegetation units from SE China and Japan (Teodoridis et al. 2011a, 2012, Appendix – this volume). in A Review Of The Early Miocene Mastixioid Flora Of The Kristina Mine At Hrádek Nad Nisou In North Bohemia (The Czech Republic)

Text-fig. 4. Dendrogram (Ward's method, squared Euclidean distance) showing the relationship between the studied fossil vegetation assemblages of Hrádek/N. (48), Wackersdorf (49), Berzdorf and Wiesa (50) and the Mydlovary Fm. (51) and the studied modern vegetation units from SE China and Japan (Teodoridis et al. 2011a, 2012, Appendix – this volume).

opencc-by-4.0Nov 2014View details →

Fig. 2 in A new brittle star from the early Carboniferous of Poland and its implications on Paleozoic modern-type ophiuroid systematics

Fig. 2. Ophiurin brittle star Aganaster jagiellonicus sp. nov. from the upper Tournaisian to lower Visean (lower Carboniferous) Mazurowe Doły Formation, Rudawa Group of Czatkowice quarry, Dębnik Massif, southern Poland; MZUJ T/0282, holotype. A. General view of the specimen, exposing the ventral side (also illustrated by O'Hara et al. 2014). B. Oral skeleton. C. Detail of the oral skeleton; photograph (C1), interpretative drawing (C2). D. Detail of basal arm segments; photograph (D1), interpretative drawing (D2).

opencc-by-4.0Nov 2014View details →

Fig. 1 in A new brittle star from the early Carboniferous of Poland and its implications on Paleozoic modern-type ophiuroid systematics

Fig. 1. Geographical position of the investigated specimen (map after Salata 2013, with modifications).

opencc-by-4.0Nov 2014View details →

Fig. 3 in A new brittle star from the early Carboniferous of Poland and its implications on Paleozoic modern-type ophiuroid systematics

Fig. 3. Ophiurin brittle star Aganaster jagiellonicus sp. nov. from the upper Tournaisian to lower Visean (lower Carboniferous) Mazurowe Doły Formation, Rudawa Group of Czatkowice quarry, Dębnik Massif, southern Poland; MZUJ T/0282, holotype. Detail of ventral side (A); median arm segments, showing the transition from between-plate tentacle pores to within-plate tentacle pores (B); median arm segments in ventro-lateral view (C); proximal arm segments in dorso-lateral view (D).

openmit-licenseDec 2022View details →

Early Modern Danish Postils v0.2.0

This release is an update from the previous release in two major ways: <ol> <li> brochmand_sabbati_sanctificatio_sommer.txt and brochmand_sabbati_sanctificatio_vinter.txt have been revised to exclude header, footer, and marginalia in order to avoid noise and be consistent with the other texts in the corpus. </li> <li> hemmingsen_postilla.txt, luther_husspostille.txt, and medelby_ungdommens_postil.txt have all been split up into smaller components, since the books from which the data were derived were originally bound with multiple smaller parts (such as winter, summer, and festal parts). To the extent these could be identified, the smaller separate files have replaced the single large file to enable better comparative studies of individual parts. If author based comparative studies are desired, this can easily be achieved by merging the relevant texts. </li> </ol>

opencc-by-4.0May 2023View details →

Main and extended tables for the 207-word Swadesh list of Early Sranan and Modern Sranan with parts of speech, semantic categories, source languages and semantic and lexical changes

The dataset was made for the purposes of the author's master thesis, titled <a href="https://repozitorij.uni-lj.si/Dokument.php?id=170462&lang=slv">"Socio-Cultural Motivations for the Acquisition of Lexical Items in Sranan Tongo’s Core Vocabulary"</a>. The dataset includes two worksheets. The first is titled "Main table", and it includes all the data, where each Swadesh gloss (1 to 207) is assigned one ID (No., first column), even if there are multiple Modern Sranan (MSr) equivalents. The second worksheet, titled "Extended table", includes additional IDs (No., first column) by hyphenating, so that each MSr equivalent has its separate ID number (e. g. gloss numbered 2 has 3 MSr equivalents, so these are now numbered 2-1, 2-2, and 2-3, respectively).  This allowed the author to also make a clearer distinction according to source languages, as the MSr equivalents for the same gloss sometimes come from different source languages. More about the methodology of the tables and their importance for the research is available in the thesis, available <a href="https://repozitorij.uni-lj.si/Dokument.php?id=170462&lang=slv">at this link</a>.

opencc-by-4.0Sep 2023View details →

Normalisation of Early Modern Science: Digitized Corpus of 17th- and 18th-Century Sources

This dataset contains a digitized corpus of early modern natural philosophy works that underlie the European Research Commission-funded Starting Grant “The Normalisation of Natural Philosophy: How Teaching Practices Shaped the Evolution of Early Modern Science,” (grant agreement No. 801653 NaturalPhilosophy), led by Dr. Andrea Sangiacomo at the Faculty of Philosophy at the University of Groningen. The methodology we used for the digitization of the present dataset is described in the paper: <ul> <li>A. Sangiacomo, H. Hogenbirk, R. Tanasescu, A. Karaisl, N White. 2022. “Reading in the Mist: High-Quality Optical Character Recognition Based on Early Modern Digitized Books.” Digital Scholarship in the Humanities. https://bit.ly/3vwvwKI</li> </ul> The inventory of the present dataset is available at <a href="https://zenodo.org/record/5566681">DOI: 10.5281/zenodo.5566681</a> The methodology behind the retrieval, cleaning, and annotation of the above inventory is described in the paper: <ul> <li>Sangiacomo, Andrea; Tanasescu, Raluca; Donker, Silvia; Hogenbirk, Hugo. 2021. “Mapping the Evolution of Early Modern Natural Philosophy: Corpus Collection and Authority Acknowledgement,” published in the Annals of Science (DOI: 10.1080/00033790.2021.1992502; permanent link: <a href="https://doi.org/10.1080/00033790.2021.1992502">https://doi.org/10.1080/00033790.2021.1992502</a></li> </ul> The dictionaries from which we selected the data in worksheets 2-5 in the inventory are the following: <ul> <li>Wiep van Bunge, Henri Krop, Bart Leeuwenburgh, Paul Schuurman, Han van Ruler and Michiel Wielema, Dictionary of Seventeenth- and Eighteenth-Century Dutch Philosophers (London: Bloomsbury, 2003);</li> <li>John Yolton, Valdimir Price and John Stephens. Dictionary of Eighteenth-Century British Philosophers (London: Bloomsbury, 1999);</li> <li>Andrew Pyle. Dictionary of Seventeenth-Century British Philosophers (London: Bloomsbury, 2000);</li> <li>Luc Foisneau. Dictionary of Seventeenth-Century French Philosophers (London: Bloomsbury, 2008);</li> <li>Heiner F. Klemme and Manfred Kuehn. Dictionary of Eighteenth-Century Philosophers (London: Bloomsbury, 2011).</li> </ul> University of Groningen Team: <ul> <li>Andrea Sangiacomo (principal investigator)</li> <li>Raluca Tanasescu (postdoctoral researcher)</li> <li>Silvia Donker and Hugo Hogenbirk (PhD students)</li> <li>Cristian A. Marocico (scientific programmer, Center for Information Technology)</li> <li>Wim Breakman (bibliographer, University of Groningen Library)</li> </ul>

opencc-by-4.0Nov 2020View details →

Patterns of Knowledge Circulation in Early Modern East-Central Europe: Tracing Jewish Kabbalistic Textual Units in Multiple-Text Manuscripts

This presentation will provide initial insights into the first comprehensive study of the networks of production and circulation of Jewish esoteric texts in early modern East-Central Europe (1500-1750). This study, which is funded by the German Research Foundation and has begun in 2019, aims to collect datasets and quantitatively analyse the transmission and reception of Jewish esoteric traditions recorded in manuscript form. In doing so, the study makes use of network analysis methods and utilises digital database environment (provided by LAB 1100) that facilitates analysis and visualisation of data with complex temporal, geographical and relational attributes. The scholarship on Jewish books, both in manuscripts and in print, and kabbalah has centred chiefly on studying individual figures, narrowing the focus of study to singular individuals and groups. Such an approach, although important, stops short of unearthing broader patterns and dissemination of ideas, which could be available through analysis of a larger selection of sources. Virtually no study has been to date devoted to examining broader networks of esoteric textual knowledge exchange from the perspective of the material evidence of such interactions. Such examination may offer a more comprehensive view on East-Central European dynamics of creating, transmitting, and re-appropriating kabbalistic and esoteric sources. Of special interest is the phenomenon of copying, transcription and compiling of kabbalistic textual units in multiple-text manuscripts, often of complex codicological structure, which abound as the most universal medium of dissemination for esoteric (kabbalistic) texts. In recent years, substantial methodological changes occurred in the field of manuscript studies, which emphasise positioning and contextualizing manuscripts as material objects within their social and cultural milieus, and rediscovers the network of ‘manuscript cultures,’ i.e. ‘the urban micro-cultures,’ which left their imprints on both the external aspects and the contents of the codices. The current presentation will highlight potentials and challenges of network analysis for the study of circulation of textual units and their variants in multiple complex and composite manuscripts, whose transcription gives evidence to conscious decisions of those involved in their dissemination and subsequent transmission in East-Central Europe. As the study will have run for just over one year by the date of the conference, the presentation will refrain from offering final conclusions, but remain open to discussions and suggestions from scholars deploying similar methods to the study of manuscripts and manuscript cultures.

opencc-by-4.0Mar 2024View details →

TRIDIS: HTR model for Multilingual Medieval and Early Modern Documentary Manuscripts (11th-16th)

TRIDIS (Tria Digita Scribunt) is a Handwriting Text Recognition model trained on semi-diplomatic transcriptions from medieval and Early Modern Manuscripts. It is suitable for work on documentary manuscripts, that is, manuscripts arising from legal, administrative, and memorial practices more commonly from the Late Middle Ages (13th century and onwards). It can also show good performance on documents from other domains, such as literature books, scholarly treatises and cartularies providing a versatile tool for historians and philologists in transforming and analyzing historical texts. A paper presenting the first version of the model is available here: Sergio Torres Aguilar, Vincent Jolivet. Handwritten Text Recognition for Documentary Medieval Manuscripts. Journal of Data Mining and Digital Humanities. 2023. https://hal.science/hal-03892163   <h3>Transcriptions rules :</h3> Since the majority of the training documents come from diplomatic editions, the transcriptions were normalized to contemporary reading standards, and abbreviations were expanded with the aim of facilitating a more fluid reading of the document. The following rules were applied: <ul> <li>The abbreviations have been expanded, both those by suspension (<code>facimꝰ</code> ---> <code>facimus</code>) and by contraction (<code>dñi</code> --> <code>domini</code>). Likewise, those using conventional signs (<code>⁊</code> --> <code>et</code> ; <code>ꝓ</code> --> <code>pro</code>) have been resolved. </li> <li>The named entities (names of persons, places and institutions) have been <code>capitalized</code>. The beginning of a block of text as well as the original capitals used by the scribe are also capitalized.</li> <li>The consonantal <code>i</code> and <code>u</code> characters have been transcribed as <code>j</code> and <code>v</code> in both French and Latin.</li> <li>The punctuation marks used in the manuscript like: <code>.</code> or <code>/</code> or <code>|</code> have not been systematically transcribed as the transcription has been standardized with modern punctuation.</li> <li>Corrections and words that appear cancelled in the manuscript have been transcribed surrounded by the sign <code>$</code> at the beginning and at the end.</li> </ul>   <h3>Versions :</h3> Version 1 of the model was trained on charters and registers dataset from the Late Medieval period (12th-15th centuries). The training and evaluation involved 1855 pages, 120k lines of text, and almost 1M tokens, conducted using three freely available ground-truth corpora: <ul> <li>The Alcar-HOME database: <a href="../record/5600884" target="_new">https://zenodo.org/record/5600884</a></li> <li>The e-NDP corpus: <a href="../record/7575693" target="_new">https://zenodo.org/record/7575693</a></li> <li>The Himanis project: <a href="../record/5535306" target="_new">https://zenodo.org/record/5535306</a></li> </ul> Version 2 of the model has added new datasets from feudal books and legal proceedings (14th-16th centuries), incorporating an additional 115k lines and more than 1.2M tokens to the previous version using other corpora like: <ul> <li>Königsfelden Abbey corpus: <a href="../record/5179361" target="_new">https://zenodo.org/record/5179361</a></li> <li>Monumenta Luxemburgensia.</li> </ul>   <h3>Accuracy</h3> TRIDIS was trained using a CNN+RNN+CTC architecture within the Kraken suite (https://kraken.re/). This final model operates in a multilingual environment (Latin, Old French, and Old Spanish) and is capable of recognizing several Latin script families (mostly Textualis and Cursiva) in documents produced circa 11th - 16th centuries. During evaluation, the model showed an accuracy of 93.1% on the validation set and a CER (Character Error Ratio) of about 0.11 to 0.15 on four external unseen datasets. Fine-tuning the model with 10 ground-truth pages can improve these results to a CER of between 0.06 to 0.10, respectively. <h3>Other formats</h3> The ground truth used for version 2 was also employed to train a Transformer HTR model that combines TrOCR as the encoder with a RoBERTa medieval model as the decoder. This model exhibits a slighly better performance in terms of CER metrics to the current TRIDIS version and shows an improved WER by about 25%. The model is available on the Hugging Face Hub: <a href="https://huggingface.co/magistermilitum/tridis_HTR">magistermilitum/tridis_HTR</a>

opencc-by-4.0Mar 2024View details →

Database of Early Modern Tax Registers of the White Forest (Central Poland)

The creation of the database and research using its contents were funded by a project financed by the National Science Centre (Poland), grant no. 2021/43/B/HS3/02636.