Zobrazeno 1 - 10
of 15
pro vyhledávání: '"kraken_pytorch"'
Autor:
Stefan Weil
This German handwriting recognition model has been trained with ground truth from different sources. It is based on a model for printed text. Details of the training process can be found here: https://github.com/UB-Mannheim/kraken/wiki/Training-Germa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e31ca405b963fcaa845ad59153b406d6
Autor:
Stefan Weil
Recognition model for 19th century German Fraktur texts, trained with ground truth from Austrian Newspapers. The ground truth which was used for the training is available from Mannheim University Library (see also details on the training process): ht
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d46be2d33d2f900fbe69fe2d06e3c0cd
Transcription Guidelines See Ariane Pinche's guideline: https://hal.archives-ouvertes.fr/hal-03697382 Adaptation for latin on https://github.com/htR-United/cremma-medieval-lat Repositories https://github.com/htR-United/cremma-medieval-lat https://git
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::9e503dbb8317239ce98ff0d302c4a824
Autor:
Benjamin Kiessling
This is an experimental recognition model for Fraktur prints trained on Austrian, Swiss, and Swedish newspapers, collections of the university library of Mannheim and Göttingen and the OCR-D corpus.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b3c1a294c606461c5f4f171df6a06a89
Autor:
Benjamin Kiessling
This is a text recognition model trained on the OpenITI dataset of printed Arabic-script text available at [0] in its state of 2022-09-03. It encompasses Urdu (~11k lines) material in a variety of typefaces. The model has been obtained by fine-tuning
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8af6c719ae9267d49aa30792c72c77f6
Autor:
Benjamin Kiessling
This is a text recognition model trained on the OpenITI dataset of printed Arabic-script text available at [0] in its state of 2022-09-03. It encompasses Ottoman (~7100 lines) material in a variety of typefaces. The model has been obtained by fine-tu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c5de161b621811a6bc7be3a39bd7dc7b
Autor:
Benjamin Kiessling
This is a text recognition model trained on the OpenITI dataset of printed Arabic-script text available at [0] in its state of 2022-09-03. It encompasses real world Arabic (~23k lines) material in a variety of typefaces augmented by synthetic data in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::92fbd0530f0b37feec40d002b10a388f
Autor:
Benjamin Kiessling
This is a text recognition model trained on the OpenITI dataset of printed Arabic-script text available at [0] in its state of 2022-09-03. It encompasses Persian (~17k lines) material in a variety of typefaces. The model has been obtained by fine-tun
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3843b2effdba128de7dd592d67f2f39e
Autor:
Benjamin Kiessling
Printed Arabic-Script Base Model Trained on the OpenITI Corpus ============================================================== This is a text recognition model trained on the OpenITI dataset of printed Arabic-script text available at [0] in its state
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::d5bf51f20e2be6813806ea78a77c7639
Autor:
Chagué, Alix, Clérice, Thibault
Data were used from all French evenly mixed repository in HTR-United where images and transcription were readily available. Only the data from the 1600 to 2100 were used. 100 pages of Spanish Letters (19th) and a little of English are included (20th)
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::73a2f894ab589a7ef2080e55ff01a869