htr-united.yml

authors:
- name: Chiffoleau
  roles:
  - project-manager
  - aligner
  surname: Floriane
characters:
  members:
  - e
  - s
  - a
  - n
  - r
  - i
  - t
  - u
  - o
  - l
  - d
  - c
  - m
  - p
  - ́
  - ','
  - v
  - .
  - f
  - q
  - g
  - ̀
  - '-'
  - E
  - b
  - ’
  - "'"
  - h
  - A
  - L
  - N
  - x
  - j
  - S
  - R
  - I
  - T
  - M
  - ̂
  - C
  - P
  - y
  - O
  - ;
  - '1'
  - £
  - U
  - D
  - B
  - F
  - J
  - G
  - '"'
  - '0'
  - z
  - V
  - '9'
  - '2'
  - ':'
  - X
  -  
  - €
  - H
  - '5'
  - '!'
  - '3'
  - '4'
  - ̧
  - °
  - W
  - Y
  - '6'
  - '8'
  - '?'
  - '7'
  - K
  - Q
  - /
  - (
  - )
  - k
  - œ
  - w
  - ̈
  - …
  - Z
  - –
  - '&'
  - '%'
  - '='
  - $
  - _
  mode: NFD
description: OCR ground Truth dataset based on French 20th typewritten letters
format: Alto-XML
hands:
  count: less-than-11
  precision: exact
language:
- fra
license:
- name: CC-BY 4.0
  url: https://creativecommons.org/licenses/by/4.0/
production-software: eScriptorium + Kraken
project-name: DAHN
project-website: https://digitalintellectuals.hypotheses.org/category/dahn
schema: https://htr-united.github.io/schema/2022-04-15/schema.json
script:
- iso: Latn
script-type: only-typed
time:
  notAfter: '1924'
  notBefore: '1914'
title: DAHN Corpus
url: https://github.com/HTR-United/dahncorpus
volume:
- count: 475849
  metric: characters
- count: 547
  metric: files
- count: 12539
  metric: lines
- count: 527
  metric: pages
- count: 547
  metric: regions