Bookolot deep dive into books

страница 38

38 / 44 русская дореформенная уверенность 0.84 человеком не проверено

Провенанс

transcript transcript
2026-09-29T22:05:17+00:00 machine-generated
normalization normalization
2026-10-02T18:15:50+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=JD3373",
    "media_title": "Instrukctia dlja zemskih bol'nic Sorocskago Uezda",
    "modification_date": "2026-09-29T22:05:17+00:00",
    "originating_media_file": "38.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": "sha256:722b92675217b3b5602ecbe3d6164bc073a6ac7acb837549e859d301b472ee7f",
    "transcript_id": "bookolot:JD3373:38: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=JD3373",
    "media_title": "Instrukctia dlja zemskih bol'nic Sorocskago Uezda",
    "modification_date": "2026-10-02T18:15:50+00:00",
    "originating_media_file": "38.tif",
    "parent_transcript_id": "bookolot:JD3373:38: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": "sha256:0b5f207a0d088539a39d1d5dc2fd503002a66f4abf5e3159e16993481c4413e6",
    "transcript_id": "bookolot:JD3373:38:modern-v3",
    "transcript_language": [
      "ru-t-ru-petr1708"
    ],
    "type": "normalization"
  }
]
Скан этой строки 38

уверенно стоит взглянуть проверьте скан Открыть скан целиком

Текст как напечатаносовременная орфографияоба

как напечатано − 3 + современная орфография − 5 +

  1. 0 Мѣсацъ 0.88
  2. 1 38 0.98
  3. 2 Форма лит II. 0.94
  4. 3 ו 0.57
  5. 4 года. 0.91
  6. 5 10 0.98
  7. 6 11 0.74
  8. 7 13 0.98
  9. 8 1 0.97
  10. 9 15 0.99
  11. 10 16 0.99
  12. 11 17 0.97
  13. 12 18 0.93
  14. 13 1 0.65
  15. 14 20 1.00
  16. 15 21 1.00
  17. 16 22 0.97
  18. 17 23 1.00
  19. 18 24 0.91
  20. 19 25 1.00
  21. 20 26 1.00
  22. 21 27 0.99
  23. 22 28 0.82
  24. 23 29 0.96
  25. 24 3 0.98
  26. 25 31 0.94
  27. 26 чви 0.51
  28. 27 Lенщи 0.68
  29. 28 на испытані 0.84
  30. 29 пare 0.63
  31. 30 Военныхъ 1.00
  32. 31 вобранцев 0.98
  33. 32 a 0.62
  34. 33 ускны 0.98
  35. 34 ч8 0.69
  36. 35 Въ теченіи дня 0.97
  37. 36 Прибыло 0.99
  38. 37 ищив 0.87
  39. 38 испытаніи 0.80
  40. 39 иы 0.72
  41. 40 Военныхъ 0.99
  42. 41 вобранцев 0.88
  43. 42 ж 0.57
  44. 43 тавныхт 0.91
  45. 44 Убыло 0.99
  46. 45 испытани 0.90
  47. 46 изыв 0.81
  48. 47 Военныхъ 0.94
  49. 48 вобранцев 0.94
  50. 49 жащи 0.83
  51. 50 ускнь 0.98
  52. 51 kakaaka 0.25
  53. 52 вных 0.96
  54. 53 жтинъ 0.89
  55. 54 енши 0.57
  56. 55 Осталось 0.95
  57. 56 нa 0.65
  58. 57 аспытан 0.89
  59. 58 Воєныхь 0.88
  60. 59 овобранцев 0.93
  61. 60 и 0.49
  62. 61 чио 0.68
  63. 62 тabi 0.70
  64. 63 курн. 0.75
  65. 64 по прімн 0.71
  66. 65 4xed 0.50
  67. 66 во ныхъ 0.73
  68. 67 СосТоитъ 0.67
  69. 68 ITOTO 0.79