Bookolot deep dive into books

страница 2

2 / 222 молдавская кириллица уверенность 0.84 человеком не проверено

Провенанс

transcript transcript
2026-09-17T21:28:40+00:00 machine-generated
transliteration transliteration
2026-09-18T07:36:04+00:00 machine-generated
Полная цепочка TPME
[
  {
    "_schema": {
      "id": "https://doi.org/10.5281/zenodo.21287085",
      "name": "AI4LAM TPME",
      "version": "1.0"
    },
    "conventions": [
      "diplomatic",
      "https://github.com/selic/bookolot/blob/main/docs/transcription-guide.md"
    ],
    "features": {
      "bbox_space": "deskewed page, see deskew step",
      "line_bbox": true,
      "line_confidence": true,
      "word_bbox": false
    },
    "file_format": "ALTO 4",
    "human_review_level": "machine-generated",
    "media_id": "http://www.moldavica.bnrm.md/biblielmo?l=ro\u0026a=d\u0026c=carti\u0026d=JD4398",
    "media_title": "Gramatica limbii moldoveneşti. P. 1 : Fonetica şi morfologia",
    "modification_date": "2026-09-17T21:28:40+00:00",
    "originating_media_file": "2.tif",
    "processing": [
      {
        "application_name": "kraken blla",
        "application_parameters": {
          "device": "cpu",
          "model": "blla.mlmodel (встроенная)"
        },
        "application_provider": "Benjamin Kiessling",
        "application_repo": "https://github.com/mittagessen/kraken",
        "application_type": "line segmentation",
        "application_version": "7.1.1"
      },
      {
        "application_name": "kraken",
        "application_parameters": {
          "device": "cpu"
        },
        "application_provider": "Benjamin Kiessling",
        "application_repo": "https://github.com/mittagessen/kraken",
        "application_type": "OCR",
        "application_version": "7.1.1",
        "inference_model": "ppocrv6_medium (sha256:15313b51ace64cbf)"
      }
    ],
    "provider": "Bookolot",
    "transcript_checksum": "sha256:ee1e5e2156a70db536e5be0cd017527545ebe9485d345c06de9ea52433080582",
    "transcript_id": "bookolot:JD4398:2:ocr-v1",
    "transcript_language": [
      "ro-Cyrl-MD"
    ],
    "type": "transcript"
  },
  {
    "_schema": {
      "id": "https://doi.org/10.5281/zenodo.21287085",
      "name": "AI4LAM TPME",
      "version": "1.0"
    },
    "characteristics_note": "For reading and search only; quote the parent transcript.",
    "human_review_level": "machine-generated",
    "media_id": "http://www.moldavica.bnrm.md/biblielmo?l=ro\u0026a=d\u0026c=carti\u0026d=JD4398",
    "media_title": "Gramatica limbii moldoveneşti. P. 1 : Fonetica şi morfologia",
    "modification_date": "2026-09-18T07:36:04+00:00",
    "originating_media_file": "2.tif",
    "parent_transcript_id": "bookolot:JD4398:2:ocr-v1",
    "processing": [
      {
        "application_name": "bookolot.rag.normalize",
        "application_parameters": {
          "normalizer_version": 3,
          "script": "md_cyrillic"
        },
        "application_provider": "Bookolot",
        "application_repo": "https://github.com/selic/bookolot",
        "application_type": "transliteration",
        "application_version": "851f6b2-dirty"
      }
    ],
    "provider": "Bookolot",
    "transcript_checksum": "sha256:da0385190f1fca62f43f46199617ee413b415771bc7ea0a5ad279f63be15c2a5",
    "transcript_id": "bookolot:JD4398:2:modern-v3",
    "transcript_language": [
      "ro-Latn-t-ro-cyrl-md"
    ],
    "type": "transliteration"
  }
]
Скан этой строки 2

уверенно стоит взглянуть проверьте скан Открыть скан целиком

Текст как напечатанотранслитерацияоба

как напечатано − 2 + транслитерация − 4 +

  1. 0 ИОН д. ЧОбАНУ Ion d. Ciobanu 0.70
  2. 1 ГРАМАТИКА ЛИМбИИ Gramatica Limbii 0.93
  3. 2 МОЛЛОВЕНЕШТЬ Mollovenești 0.85
  4. 3 пАРТя ыНтый partea întâi 0.79
  5. 4 фОНЕТИКА ШИ МОРФОлОЖИЯ fonetica Și Morfolojia 0.84
  6. 5 Eδuцua III Eδiția III 0.77
  7. 6 пPелуPATэ ши комплектAТэ prelurată și complectată 0.81
  8. 7 мануАл пентру шкоАла де шепте ань manual pentru școala de șepte ani 0.93
  9. 8 ши чЯ мижлОчие și cea mijlocie 0.91
  10. 9 Битэрит де Комисариатул Bitărit de Comisariatul 0.89
  11. 10 Нородник де Бнзээмынт ал Norodnic de Bnzăământ al 0.90
  12. 11 РCC Молдовенешть Rss Moldovenești 0.93
  13. 12 ПPOBEPENC PPOBEPENC 0.79
  14. 13 1 1 0.38
  15. 14 Гос. республинанскан Gos. respublinanscan 0.97
  16. 15 БИблИОТЕкА мССР Biblioteca mssr 0.76
  17. 16 им. Н. Н. Нрупсной im. N. N. Nrupsnoi 0.94
  18. 17 656 656 0.93
  19. 18 ЕдИТУРА де СТАТ А мОлДОВЕЙ Editura de Stat A moldovei 0.81
  20. 19 кишинэу chișinău 0.86
  21. 20 1945 1945 0.99