Bookolot deep dive into books

страница 52

52 / 222 молдавская кириллица уверенность 0.91 человеком не проверено

Провенанс

transcript transcript
2026-09-18T05:08:55+00:00 machine-generated
transliteration transliteration
2026-09-18T07:36:11+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": "2026-09-18T05:08:55+00:00",
    "originating_media_file": "52.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:c0aab966227b1ce2c01bd3c37f497f59b484d8bd74959a3aaf5bd7e29286eebd",
    "transcript_id": "bookolot:JD4398:52: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": "2026-09-18T07:36:11+00:00",
    "originating_media_file": "52.tif",
    "parent_transcript_id": "bookolot:JD4398:52: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": "sha256:8903b9309c37892474587b8b13ce62500a717c75a9190d27c176371a47b09ed9",
    "transcript_id": "bookolot:JD4398:52:modern-v3",
    "transcript_language": [
      "ro-Latn-t-ro-cyrl-md"
    ],
    "type": "transliteration"
  }
]
Скан этой строки 52

уверенно стоит взглянуть проверьте скан Открыть скан целиком

Текст как напечатанотранслитерацияоба

как напечатано − 2 + транслитерация − 4 +

  1. 0 Articolul substantival. 1.00
  2. 1 La rândul său articolul substantival se împarte în: 0.99
  3. 2 a) articolul nehotărât. 1.00
  4. 3 Articolul nehotărât se pune înnaintea cuvântului, care 1.00
  5. 4 are înțălesul și forma nehotărâtă și stă deosăbit de 0.98
  6. 5 aist cuvânt. De-o vorbă: Niște școlari, o udarnică, un 0.99
  7. 6 om, unei mese, unor cărți. 1.00
  8. 7 Jenul 0.96
  9. 8 Cazuת 0.85
  10. 9 formele articolului nehotărât. 0.99
  11. 10 Număruת 0.78
  12. 11 H. A. 0.91
  13. 12 j. D. 0.85
  14. 13 Masculin 0.99
  15. 14 singular 0.99
  16. 15 yא 0.58
  17. 16 uў 0.53
  18. 17 plural 1.00
  19. 18 niște 0.84
  20. 19 (unii) 0.75
  21. 20 unor 0.82
  22. 21 femenii 0.85
  23. 22 singular 0.99
  24. 23 o 0.75
  25. 24 unei 0.96
  26. 25 plural 1.00
  27. 26 HUșme 0.50
  28. 27 (unele) 0.99
  29. 28 Oע 0.32
  30. 29 b) articolul hotărât. 0.98
  31. 30 Articolul hotărât se pune la sfârșitul cuvântului, 1.00
  32. 31 care are înțălesul și forma hotărâtă, împreunânduse 0.99
  33. 32 cu aist cuvânt la sfârșit. 1.00
  34. 33 De-o vorbă: udarnic-u-lui, frate-le, mas-a, mese-i, 0.99
  35. 34 Jenul 0.97
  36. 35 muncitori-lor, colhoznici-i. 1.00
  37. 36 formele articolului hotărât. 0.98
  38. 37 Masculin 0.99
  39. 38 Femenin 0.88
  40. 39 Cazul 0.79
  41. 40 Numărul 0.87
  42. 41 singular 0.98
  43. 42 plural 1.00
  44. 43 singular 0.99
  45. 44 plural 0.99
  46. 45 H. A. 0.93
  47. 46 j. D. 0.86
  48. 47 l, le 0.94
  49. 48 lў 0.86
  50. 49 lor 0.80
  51. 50 (π), α 0.84
  52. 51 l 0.93
  53. 52 lor 0.97
  54. 53 Articolul adjectival. 1.00
  55. 54 Articolul adjectival se pune înnaintea adjectivului 1.00
  56. 55 ca cuvântul deosăbit, căruia îi dă o însămnătate hotărâtă 0.97
  57. 56 . De-o vorbă: cel bun, celui bun, celei bune. 0.99
  58. 57 52 1.00