htr-united.yml

authors:
- name: Pinche
  orcid: 0000-0002-7843-5050
  roles:
  - transcriber
  - aligner
  - project-manager
  - quality-control
  - support
  surname: Ariane
- name: Camps
  roles:
  - transcriber
  surname: Jean-Baptiste
- name: Mariotti
  roles:
  - transcriber
  surname: Viola
- name: Nolibois
  roles:
  - transcriber
  surname: Alice
- name: Carnaille
  roles:
  - transcriber
  surname: Camille
- name: Deleville
  roles:
  - transcriber
  surname: Prunelle
- name: Lecomte
  roles:
  - transcriber
  surname: Sophie
- name: Meylan
  roles:
  - transcriber
  surname: Aminoel
- name: Ventura
  roles:
  - transcriber
  surname: Simone
- name: Dugaz
  roles:
  - transcriber
  surname: Lucien
characters:
  members:
  - e
  - i
  - s
  - t
  - n
  - a
  - r
  - u
  - o
  - l
  - c
  - d
  - m
  - p
  - .
  - q
  - f
  - g
  - ̃
  - z
  - b
  - h
  - ⁊
  - y
  - ':'
  - E
  - x
  - Q
  - L
  - S
  - ꝑ
  - D
  - ̾
  - ͥ
  - C
  - ꝯ
  - ͣ
  - A
  - I
  - M
  - "'"
  - ꝰ
  - ́
  - T
  - P
  - O
  - k
  - N
  - '9'
  - U
  - ͬ
  - G
  - R
  - ᷑
  - F
  - 
  - ͤ
  - '&'
  - '1'
  - B
  - ꝓ
  - H
  - ͦ
  - ᷤ
  - '7'
  - '2'
  - Λ
  - ÷
  - ł
  - '6'
  - '0'
  - '3'
  - '8'
  - '4'
  - ̽
  - w
  - '-'
  - '5'
  - ','
  - ͭ
  - ¶
  - Y
  - ẜ
  -  
  - ⟦
  - ⟧
  - ͨ
  - ̈
  - X
  - ħ
  - K
  - δ
  - /
  - ŧ
  - j
  mode: NFD
citation-file-link: https://github.com/HTR-United/cremma-medieval/blob/main/citation.cff
description: Transcription corpora for training HTR models for medieval manuscripts
  from the 12th to the 15th century.
format: Alto-XML
hands:
  count: 1-per-folder
  precision: exact
language:
- fra
- fro
license:
- name: CC-BY 4.0
  url: https://creativecommons.org/licenses/by/4.0/
production-software: eScriptorium + Kraken
project-name: CremmaLab
project-website: https://cremmalab.hypotheses.org
schema: https://htr-united.github.io/schema/2022-04-15/schema.json
script:
- iso: Latn
script-type: only-manuscript
time:
  notAfter: '1499'
  notBefore: '1100'
title: Cremma Medieval
transcription-guidelines: "As the data come from different projects, transcriptions\
  \ have been standardized to strengthen HTR models. We chose a graphemic transcription\
  \ method, following D. Stutzmann definitions (see bibliography), to have a sign\
  \ in the image corresponding to a sign in our text: all the abbreviations are kept,\
  \ and u/v or i/j are not distinguished. The spaces in the dataset are not homogeneously\
  \ represented, sometimes transcriptions reproduce the manuscript spacing while others\
  \ use lexical spaces. It must be stressed that spaces are the most important source\
  \ of error in medieval HTR models. Most of the transcription follow the layout segmentation\
  \ of the SegmOnto ontology (https://github.com/SegmOnto/examples), separating the\
  \ main column, margin, numbering, drop capital, etc. All the recommendations are\
  \ described in\n  the following document  : Ariane Pinche, Guide de transcription\
  \ pour les manuscrits du Xe au XVe siècle, 2022, ⟨hal-03697382>, en ligne : <https://hal.archives-ouvertes.fr/hal-03697382>."
url: https://github.com/HTR-United/cremma-medieval
volume:
- count: 612134
  metric: characters
- count: 279
  metric: files
- count: 22913
  metric: lines
- count: 1889
  metric: regions