Bookolot deep dive into books

страница 93

93 / 588 русская дореформенная уверенность 0.96 человеком не проверено

Провенанс

transcript transcript
2026-09-30T03:43:11+00:00 machine-generated
normalization normalization
2026-10-02T18:14:53+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=JD3355",
    "media_title": "Cметы и раскладки Бессарабского Земства на 1886 год",
    "modification_date": "2026-09-30T03:43:11+00:00",
    "originating_media_file": "93.tif",
    "processing": [
      {
        "application_name": "kraken blla",
        "application_parameters": {
          "device": "cuda",
          "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": "cuda"
        },
        "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": "sha256:607ad5ab75d7ccfd16f2e3dbd263088e2e9ccc3a6edcd0148cec183951fc3e73",
    "transcript_id": "bookolot:JD3355:93:ocr-v1",
    "transcript_language": [
      "ru-petr1708"
    ],
    "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=JD3355",
    "media_title": "Cметы и раскладки Бессарабского Земства на 1886 год",
    "modification_date": "2026-10-02T18:14:53+00:00",
    "originating_media_file": "93.tif",
    "parent_transcript_id": "bookolot:JD3355:93:ocr-v1",
    "processing": [
      {
        "application_name": "bookolot.rag.normalize",
        "application_parameters": {
          "normalizer_version": 3,
          "script": "ru_prereform"
        },
        "application_provider": "Bookolot",
        "application_repo": "https://github.com/selic/bookolot",
        "application_type": "spelling normalization",
        "application_version": "fb8b81d-dirty"
      }
    ],
    "provider": "Bookolot",
    "transcript_checksum": "sha256:dfd64e454402bdc05e7065d0d228c283ddd5f5d24c5bb76ccb34449aa763ea42",
    "transcript_id": "bookolot:JD3355:93:modern-v3",
    "transcript_language": [
      "ru-t-ru-petr1708"
    ],
    "type": "normalization"
  }
]
Скан этой строки 93

уверенно стоит взглянуть проверьте скан Открыть скан целиком

Текст как напечатаносовременная орфографияоба

как напечатано − 1 + современная орфография − 2 +

  1. 0 89 0.98
  2. 1 Цѣнность 0.99
  3. 2 всѣхъ деся- 1.00
  4. 3 Ивсу.В С ей.нъ, тя 0.72
  5. 4 Подъ 0.99
  6. 5 nо 30 руó. СадМИ. 0.80
  7. 6 десятину. 0.81
  8. 7 Цѣнность Итого об̆щая 0.91
  9. 8 всѣхъ деся- ценность зе 0.90
  10. 9 тинъ, считая мель и лѣсу, 0.96
  11. 10 но 45 руб. облаемыхъ 0.83
  12. 11 десятину. 0.93
  13. 12 сбо рами. 0.88
  14. 13 Десят. Десят. Рубли. Десят. РублН. РублН. 0.88
  15. 14 .... 0.82
  16. 15 34 1.00
  17. 16 34 1.00
  18. 17 34 1.00
  19. 18 54 1.00
  20. 19 20 1.00
  21. 20 2 0.98
  22. 21 12 1.00
  23. 22 12 1.00
  24. 23 20 0.70
  25. 24 2212 0.73
  26. 25 25 1.00
  27. 26 195 1.00
  28. 27 1020 1.00
  29. 28 1020 1.00
  30. 29 1020 1.00
  31. 30 27 0.99
  32. 31 15 1.00
  33. 32 1635 1.00
  34. 33 885 0.79
  35. 34 165 1.00
  36. 35 600 0.99
  37. 36 48 0.97
  38. 37 600 0.98
  39. 38 37 0.96
  40. 39 435 1.00
  41. 40 165 1.00
  42. 41 180 0.93
  43. 42 360 0.97
  44. 43 165 1.00
  45. 44 780 0.99
  46. 45 135 1.00
  47. 46 675 0.94
  48. 47 150 0.95
  49. 48 337--50 0.88
  50. 49 765 1.00
  51. 50 195 1.00
  52. 51 240 1.00
  53. 52 1020 1.00
  54. 53 1020 1.00
  55. 54 1020 0.99
  56. 55 270 0.99
  57. 56 150 1.00
  58. 57 1635 1.00
  59. 58 885 0.99
  60. 59 81 0.95
  61. 60 165 1.00
  62. 61 600 1.00
  63. 62 480 0.99
  64. 63 600 0.95
  65. 64 375 0.96
  66. 65 435 1.00
  67. 66 165 1.00
  68. 67 180 0.99
  69. 68 360 1.00
  70. 69 120 1.00
  71. 70 165 1.00
  72. 71 78 0.96
  73. 72 375 1.00
  74. 73 135 1.00
  75. 74 67 0.84
  76. 75 150 1.00
  77. 76 337 — 50 0.89
  78. 77 765 1.00