There is a newer version of this record available.

Dataset Open Access

Scans and transcriptions of the VOC and the Haarlem notarial deeds archives

Liesbeth Keijser


JSON Export

{
  "files": [
    {
      "links": {
        "self": "https://zenodo.org/api/files/697588eb-1f72-438e-8074-164afdaa792b/HTR%20results%20NHA%20Notarial%201617%20PAGE.zip"
      }, 
      "checksum": "md5:46cef4b6dd3002fdd1a060edc2d013bc", 
      "bucket": "697588eb-1f72-438e-8074-164afdaa792b", 
      "key": "HTR results NHA Notarial 1617 PAGE.zip", 
      "type": "zip", 
      "size": 3280149083
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/697588eb-1f72-438e-8074-164afdaa792b/HTR%20results%20NHA%20Notarial%201617%20TXT.zip"
      }, 
      "checksum": "md5:d8ee4b47dd640d6cf9b264b800c914ca", 
      "bucket": "697588eb-1f72-438e-8074-164afdaa792b", 
      "key": "HTR results NHA Notarial 1617 TXT.zip", 
      "type": "zip", 
      "size": 133387379
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/697588eb-1f72-438e-8074-164afdaa792b/HTR%20results%20NHA%20Notarial%201972%20PAGE.zip"
      }, 
      "checksum": "md5:98abdaafec31000590390d66d457be2f", 
      "bucket": "697588eb-1f72-438e-8074-164afdaa792b", 
      "key": "HTR results NHA Notarial 1972 PAGE.zip", 
      "type": "zip", 
      "size": 10224852802
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/697588eb-1f72-438e-8074-164afdaa792b/HTR%20results%20NHA%20Notarial%201972%20TXT.zip"
      }, 
      "checksum": "md5:80716cb025b328e0309d6e2b00f1d289", 
      "bucket": "697588eb-1f72-438e-8074-164afdaa792b", 
      "key": "HTR results NHA Notarial 1972 TXT.zip", 
      "type": "zip", 
      "size": 412936174
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/697588eb-1f72-438e-8074-164afdaa792b/HTR%20results%20VOC%20PAGE.zip"
      }, 
      "checksum": "md5:63765847db358429cdf8c12305085eb4", 
      "bucket": "697588eb-1f72-438e-8074-164afdaa792b", 
      "key": "HTR results VOC PAGE.zip", 
      "type": "zip", 
      "size": 17887243231
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/697588eb-1f72-438e-8074-164afdaa792b/HTR%20results%20VOC%20TXT.zip"
      }, 
      "checksum": "md5:23431e2779e9cadce798adba47ff57ea", 
      "bucket": "697588eb-1f72-438e-8074-164afdaa792b", 
      "key": "HTR results VOC TXT.zip", 
      "type": "zip", 
      "size": 710830346
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/697588eb-1f72-438e-8074-164afdaa792b/Notarial%20deeds%20Ground%20Truths%20of%20the%20trainingset%20in%20PAGE%20xml.7z"
      }, 
      "checksum": "md5:8b8d2fa465c8d1dad71d0fd5817f93da", 
      "bucket": "697588eb-1f72-438e-8074-164afdaa792b", 
      "key": "Notarial deeds Ground Truths of the trainingset in PAGE xml.7z", 
      "type": "7z", 
      "size": 54461642
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/697588eb-1f72-438e-8074-164afdaa792b/Notarial%20deeds%20Images%20of%20the%20training%20set.7z"
      }, 
      "checksum": "md5:eaf0c2bf0033cb129d5c747a2be039ea", 
      "bucket": "697588eb-1f72-438e-8074-164afdaa792b", 
      "key": "Notarial deeds Images of the training set.7z", 
      "type": "7z", 
      "size": 7203628715
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/697588eb-1f72-438e-8074-164afdaa792b/VOC%20Ground%20truths%20of%20the%20trainingset%20in%20PAGE%20xml.7z"
      }, 
      "checksum": "md5:ca68bf64bd40af7593090d1425766e94", 
      "bucket": "697588eb-1f72-438e-8074-164afdaa792b", 
      "key": "VOC Ground truths of the trainingset in PAGE xml.7z", 
      "type": "7z", 
      "size": 144231651
    }, 
    {
      "links": {
        "self": "https://zenodo.org/api/files/697588eb-1f72-438e-8074-164afdaa792b/VOC%20Images%20of%20the%20trainingset.7z"
      }, 
      "checksum": "md5:84dcb6e819ad897e81ac26150c428e3e", 
      "bucket": "697588eb-1f72-438e-8074-164afdaa792b", 
      "key": "VOC Images of the trainingset.7z", 
      "type": "7z", 
      "size": 18485261890
    }
  ], 
  "owners": [
    80914
  ], 
  "doi": "10.5281/zenodo.3906480", 
  "stats": {
    "version_unique_downloads": 1288.0, 
    "unique_views": 860.0, 
    "views": 972.0, 
    "version_views": 12803.0, 
    "unique_downloads": 258.0, 
    "version_unique_views": 10795.0, 
    "volume": 5555718950200.0, 
    "version_downloads": 2824.0, 
    "downloads": 1001.0, 
    "version_volume": 12428381695256.0
  }, 
  "links": {
    "doi": "https://doi.org/10.5281/zenodo.3906480", 
    "conceptdoi": "https://doi.org/10.5281/zenodo.3517776", 
    "bucket": "https://zenodo.org/api/files/697588eb-1f72-438e-8074-164afdaa792b", 
    "conceptbadge": "https://zenodo.org/badge/doi/10.5281/zenodo.3517776.svg", 
    "html": "https://zenodo.org/record/3906480", 
    "latest_html": "https://zenodo.org/record/4638495", 
    "badge": "https://zenodo.org/badge/doi/10.5281/zenodo.3906480.svg", 
    "latest": "https://zenodo.org/api/records/4638495"
  }, 
  "conceptdoi": "10.5281/zenodo.3517776", 
  "created": "2020-06-29T13:34:16.651018+00:00", 
  "updated": "2021-04-15T10:20:30.454084+00:00", 
  "conceptrecid": "3517776", 
  "revision": 20, 
  "id": 3906480, 
  "metadata": {
    "access_right_category": "success", 
    "doi": "10.5281/zenodo.3906480", 
    "description": "<p>The National Archives of the Netherlands and the Noord-Hollands Archief started a collaboration with the Transkribus HTR (Handwritten Text Recognition) platform in order to semi automatically transcribe 2 million pages of old Dutch texts. The archives are 17th and 18th century material from the Dutch East-Asia Company (VOC) and 19th century notarial deeds from the city of Haarlem.<br>\nIn order to train the HTR software, human made transciptions had to be made.&nbsp;</p>\n\n<p>These datasets contain the scans (.jpg images) with the transcriptions in ALTO xml format (word level) that have been made in order to train the HTR-model for text recognition.<br>\n<br>\nThe first set contains scans and transcriptions from the Verenigde Oost-Indische Compagnie (VOC) archive, it&#39;s inventory can be found here:&nbsp;<a href=\"http://www.gahetna.nl/archievenoverzicht/pdf/NL-HaNA_1.04.02.ead.pdf\">http://www.gahetna.nl/archievenoverzicht/pdf/NL-HaNA_1.04.02.ead.pdf</a></p>\n\n<p><strong>Inventory numbers</strong><br>\nThe transcipts are samples of the following inventory numbers: 7527-9540</p>\n\n<p><strong>Country/place</strong><br>\nDutch Indies (modern day Indonesia) / Batavia&nbsp;(modern day Jakarta)</p>\n\n<p><strong>Language</strong><br>\nDutch</p>\n\n<p><strong>Number of transcriptions</strong><br>\n4735&nbsp;(mostly split)</p>\n\n<p>-------------------------------------------------------------</p>\n\n<p>The second set contains scans and transcriptions from the Notarial deeds of Haarlem, it&#39;s inventories can be found here:<br>\n<a href=\"https://noord-hollandsarchief.nl/bronnen/archieven?mivast=236&amp;mizig=210&amp;miadt=236&amp;micode=1972&amp;milang=nl&amp;miview=inv2\">https://noord-hollandsarchief.nl/bronnen/archieven?mivast=236&amp;mizig=210&amp;miadt=236&amp;micode=1972&amp;milang=nl&amp;miview=inv2</a><br>\n<a href=\"https://noord-hollandsarchief.nl/bronnen/archieven?mivast=236&amp;mizig=210&amp;miadt=236&amp;micode=1617&amp;milang=nl&amp;miview=inv2\">https://noord-hollandsarchief.nl/bronnen/archieven?mivast=236&amp;mizig=210&amp;miadt=236&amp;micode=1617&amp;milang=nl&amp;miview=inv2</a></p>\n\n<p>This set also contains scans and transcriptions from other notarial archives, from&nbsp;Dutch provinces. They are however few in number.</p>\n\n<p><strong>Inventory numbers</strong><br>\nThe transcipts are samples of the following inventory numbers: 1617_1593&nbsp;until 1617_1805 and 1972_5&nbsp;until 1972_813</p>\n\n<p><strong>Country/place</strong><br>\nThe Netherlands&nbsp;/ Haarlem</p>\n\n<p><strong>Language</strong><br>\nDutch and sometimes French</p>\n\n<p><strong>Number of transcriptions</strong><br>\n1615&nbsp;(mostly spread)</p>\n\n<p>-------------------------------------------------------------</p>\n\n<p>The following HTR model was used for recognition: &quot;IJsberg&quot;. More information about the model van be found here:&nbsp;<a href=\"https://transkribus.eu/wiki/images/d/d6/Public_Models_in_Transkribus.pdf\">https://transkribus.eu/wiki/images/d/d6/Public_Models_in_Transkribus.pdf</a>. See the chapter &quot;Dutch Handwriting&quot;.</p>\n\n<p>-------------------------------------------------------------</p>\n\n<p>Update: upon request, PageXML files of the transcriptions have been added and are seperately downloadable.</p>\n\n<p>Version 3.0: The first HTR results from the VOC-collection are available in .txt format,&nbsp;Inventory numbers 7527-9540.</p>\n\n<p>Version 3.1: The HTR results from the VOC-collection are also available in PAGE xml format.&nbsp;</p>\n\n<p>Version 4.0: About 30 missing inventory numbers have been added to the VOC transcriptions. The HTR results of the&nbsp;Notarial Deeds from the NHA archives have been added. An example on full text searchable research can be found here (Dutch):&nbsp;<a href=\"https://kia.pleio.nl/groups/view/55812425/htr-en-ocr/blog/view/55814752/reconstructie-van-een-verijdelde-slavenopstand-met-behulp-van-automatische-handschriftherkenning-en-text-mining\">https://kia.pleio.nl/groups/view/55812425/htr-en-ocr/blog/view/55814752/reconstructie-van-een-verijdelde-slavenopstand-met-behulp-van-automatische-handschriftherkenning-en-text-mining</a></p>", 
    "language": "odt", 
    "title": "Scans and transcriptions of the VOC and the Haarlem notarial deeds archives", 
    "license": {
      "id": "CC-BY-4.0"
    }, 
    "relations": {
      "version": [
        {
          "count": 10, 
          "index": 5, 
          "parent": {
            "pid_type": "recid", 
            "pid_value": "3517776"
          }, 
          "is_last": false, 
          "last_child": {
            "pid_type": "recid", 
            "pid_value": "4638495"
          }
        }
      ]
    }, 
    "version": "4.0", 
    "keywords": [
      "Transciptions", 
      "Verenigde Oost-Indische Compagnie", 
      "Notarial deeds", 
      "Nationaal Archief", 
      "Noord-Hollands Archief", 
      "Transkribus"
    ], 
    "publication_date": "2020-01-21", 
    "creators": [
      {
        "affiliation": "National Archive Netherlands", 
        "name": "Liesbeth Keijser"
      }
    ], 
    "access_right": "open", 
    "resource_type": {
      "type": "dataset", 
      "title": "Dataset"
    }, 
    "related_identifiers": [
      {
        "scheme": "doi", 
        "identifier": "10.5281/zenodo.3517776", 
        "relation": "isVersionOf"
      }
    ]
  }
}
12,803
2,824
views
downloads
All versions This version
Views 12,803972
Downloads 2,8241,001
Data volume 12.4 TB5.6 TB
Unique views 10,795860
Unique downloads 1,288258

Share

Cite as