Bookolot deep dive into books

страница 52

48 / 63 русская дореформенная уверенность 0.63 человеком не проверено

Провенанс

transcript transcript
2026-09-29T22:26:48+00:00 machine-generated
normalization normalization
2026-10-02T18:13:43+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=JD2765",
    "media_title": "Denejniy otcet Kisinevskoj Uezdnoj Zemskoj Upravi",
    "modification_date": "2026-09-29T22:26:48+00:00",
    "originating_media_file": "52.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": "sha256:42a65eaef374b456f15376f6ca84138a753702610521d8e11522b2ac3bd5d01d",
    "transcript_id": "bookolot:JD2765:52: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=JD2765",
    "media_title": "Denejniy otcet Kisinevskoj Uezdnoj Zemskoj Upravi",
    "modification_date": "2026-10-02T18:13:43+00:00",
    "originating_media_file": "52.tif",
    "parent_transcript_id": "bookolot:JD2765:52: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": "sha256:9cfed33d32e58e7cdf41014a629475f61e0fa0305b72bd8442850dc85dbd7241",
    "transcript_id": "bookolot:JD2765:52:modern-v3",
    "transcript_language": [
      "ru-t-ru-petr1708"
    ],
    "type": "normalization"
  }
]
Скан этой строки 52

уверенно стоит взглянуть проверьте скан Открыть скан целиком

Текст как напечатаносовременная орфографияоба

как напечатано − 3 + современная орфография − 5 +

  1. 0 ܩ 0.19
  2. 1 2 0.27
  3. 2 ׳ 0.43
  4. 3 57 0.99
  5. 4 - 0.50
  6. 5 - 0.43
  7. 6 ܀ 0.27
  8. 7 D 0.28
  9. 8 сына 0.97
  10. 9 א 0.39
  11. 10 ב 0.14
  12. 11 пvg-2Hф 0.52
  13. 12 Н10 0.60
  14. 13 32 0.38
  15. 14 истребленіе 0.91
  16. 15 DHH 0.56
  17. 16 пороха 0.99
  18. 17 0 0.85
  19. 18 пок 0.76
  20. 19 я истр 0.93
  21. 20 L 0.71
  22. 21 облавъ 1.00
  23. 22 Pad 0.42
  24. 23 хищныхъ 0.97
  25. 24 X 0.65
  26. 25 оборота 0.99
  27. 26 ОнОГО 0.51
  28. 27 выселеню 0.98
  29. 28 . 0.57
  30. 29 люде 0.87
  31. 30 XI 0.58
  32. 31 ществт 0.94
  33. 32 несвоев 0.99
  34. 33 3a 0.45
  35. 34 ia 0.48
  36. 35 бернску 0.97
  37. 36 ene 0.57
  38. 37 сбор 0.80
  39. 38 J 0.44
  40. 39 наг 0.89
  41. 40 азныя пособіл 0.91
  42. 41 BLറd 0.45
  43. 42 рachar 0.80
  44. 43 oo 0.58
  45. 44 sLO! 0.41
  46. 45 coбie 0.61
  47. 46 льн 0.74
  48. 47 = 0.28
  49. 48 ܀ 0.28
  50. 49 инев 0.82
  51. 50 4 0.38
  52. 51 rie 0.91
  53. 52 a 0.49
  54. 53 T 0.32
  55. 54 ב 0.74
  56. 55 Ѣт 0.57
  57. 56 eOLO 0.52
  58. 57 пчислен 0.89
  59. 58 ܘ 0.40