Bookolot deep dive into books

страница 40

40 / 44 русская дореформенная уверенность 0.82 человеком не проверено

Провенанс

transcript transcript
2026-09-29T22:05:44+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": "2026-09-29T22:05:44+00:00",
    "originating_media_file": "40.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:ee969c9f921a0ba7fbcba50a40af0ba907b7250930cc413cf7d3b4ae4c579669",
    "transcript_id": "bookolot:JD3373:40: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": "40.tif",
    "parent_transcript_id": "bookolot:JD3373:40: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": "sha256:5e30bd1ee3c0bec346879b8df1a83ab7f3b07a671dd9223177b0483ac578914e",
    "transcript_id": "bookolot:JD3373:40:modern-v3",
    "transcript_language": [
      "ru-t-ru-petr1708"
    ],
    "type": "normalization"
  }
]
Скан этой строки 40

уверенно стоит взглянуть проверьте скан Открыть скан целиком

Текст как напечатаносовременная орфографияоба

как напечатано − 4 + современная орфография − 1 +

  1. 0 40 1.00
  2. 1 Аисло мѣсяц 0.91
  3. 2 рислугн 0.89
  4. 3 opa 0.56
  5. 4 Больныхъ 0.99
  6. 5 oрaи- 0.60
  7. 6 рн 0.70
  8. 7 а слабой 0.98
  9. 8 куринной 0.90
  10. 9 Отъ предыдущаго. 0.95
  11. 10 мсяца оставалось 0.95
  12. 11 укурузно 0.95
  13. 12 Франзол̆ 0.88
  14. 13 CAS 0.22
  15. 14 a 0.93
  16. 15 в 0.39
  17. 16 II. T. II.. II . II. . II. . II T. 0.84
  18. 17 CT- 0.74
  19. 18 кан, 0.87
  20. 19 * 0.29
  21. 20 = 0.80
  22. 21 IIIr. II. Φ. II. . 0.86
  23. 22 Число люде 0.84
  24. 23 продуктовый листь 0.97
  25. 24 1 0.54
  26. 25 12 1.00
  27. 26 13 0.99
  28. 27 1 0.39
  29. 28 15 0.90
  30. 29 16 1.00
  31. 30 1 0.80
  32. 31 20 0.99
  33. 32 23 0.98
  34. 33 24 0.90
  35. 34 25 1.00
  36. 35 26 0.88
  37. 36 27 0.86
  38. 37 2 0.75
  39. 38 29 0.85
  40. 39 31 0.99
  41. 40 BCЕго 0.56
  42. 41 Къ 1-му числу 0.96
  43. 42 нѣсяца остается 0.94