Bookolot deep dive into books

страница 398

398 / 588 русская дореформенная уверенность 0.88 человеком не проверено

Провенанс

transcript transcript
2026-09-30T05:35:00+00:00 machine-generated
normalization normalization
2026-10-02T18:15:00+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": "2026-09-30T05:35:00+00:00",
    "originating_media_file": "398.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": "sha256:8912d9466c926bd95a8cc41d6bd1fe623c94123f22108d368224bd14eb78a1f8",
    "transcript_id": "bookolot:JD3355:398: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": "2026-10-02T18:15:00+00:00",
    "originating_media_file": "398.tif",
    "parent_transcript_id": "bookolot:JD3355:398: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": "sha256:85b78ea4bad5bf482a968f3078e505a746740ad983ae2ecd12ffa5a1a16694e3",
    "transcript_id": "bookolot:JD3355:398:modern-v3",
    "transcript_language": [
      "ru-t-ru-petr1708"
    ],
    "type": "normalization"
  }
]
Скан этой строки 398

уверенно стоит взглянуть проверьте скан Открыть скан целиком

Текст как напечатаносовременная орфографияоба

как напечатано − 5 + современная орфография − 5 +

  1. 0 393 – 0.78
  2. 1 2 1.00
  3. 2 256 1.00
  4. 3 1asa4 5 0.68
  5. 4 Плавни Сад. 0.85
  6. 5 .. 0.46
  7. 6 3 1200 0.98
  8. 7 . 0.68
  9. 8 1414 /198559 0.92
  10. 9 12 1.00
  11. 10 1414 1985 50 43 1.00
  12. 11 :37300011218 0.96
  13. 12 96 0.74
  14. 13 106 2164 0.99
  15. 14 n 0.51
  16. 15 2 0.11
  17. 16 664 1.00
  18. 17 380 0.82
  19. 18 320 1.00
  20. 19 418 0.99
  21. 20 161870 1180 1635 0.98
  22. 21 122 1.00
  23. 22 300 9 1200 0.95
  24. 23 32 1.00
  25. 24 42 1998 0.95
  26. 25 36 0.89
  27. 26 462 1916 0.98
  28. 27 14 1.00
  29. 28 14 1.00
  30. 29 9 0.68
  31. 30 / 0.49
  32. 31 19 0.90
  33. 32 15 1.00
  34. 33 2655 1200 94 0.93
  35. 34 11935 172 0.97
  36. 35 3728 0.99
  37. 36 416 0.93
  38. 37 129 0.84
  39. 38 ו 0.38
  40. 39 480 1.00
  41. 40 720 0.94
  42. 41 35 1.00
  43. 42 81 1.00
  44. 43 60 1.00
  45. 44 32 1.00
  46. 45 86 0.98
  47. 46 34 1.00
  48. 47 52 1.00
  49. 48 50 0.99
  50. 49 640 22 82 0.91
  51. 50 200 1.00
  52. 51 97 1200 0.93
  53. 52 165 1.00
  54. 53 23 1.00
  55. 54 12 1.00
  56. 55 61 0.96
  57. 56 13 1962 560 1880 0.95
  58. 57 14 1086 0.98
  59. 58 10 1.00
  60. 59 « 13 0.74
  61. 60 414 0.99
  62. 61 3 1450 280 0.99
  63. 62 = 0.28
  64. 63 259 0.99
  65. 64 6335 1152 0.96
  66. 65 2128 1020 0.96
  67. 66 1362 1.00
  68. 67 220 1.00
  69. 68 75 0.99
  70. 69 61 1.00
  71. 70 22 1.00
  72. 71 42 1.00
  73. 72 14 1.00
  74. 73 40 1.00
  75. 74 47 64 0.92
  76. 75 ן 0.25
  77. 76 1 0.18