Bookolot deep dive into books

страница 21

21 / 44 русская дореформенная уверенность 0.69 человеком не проверено

Провенанс

transcript transcript
2026-09-29T22:01:18+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": "2026-09-29T22:01:18+00:00",
    "originating_media_file": "21.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": "sha256:45da4504866df2187f704296c437cbfb2556e08e3908d92de722ed4900d74800",
    "transcript_id": "bookolot:JD3373:21: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": "21.tif",
    "parent_transcript_id": "bookolot:JD3373:21: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:a527013317a22eba15c2c94227763ee1129b0842bdb85c6a17f2f7053d216ec3",
    "transcript_id": "bookolot:JD3373:21:modern-v3",
    "transcript_language": [
      "ru-t-ru-petr1708"
    ],
    "type": "normalization"
  }
]
Скан этой строки 21

уверенно стоит взглянуть проверьте скан Открыть скан целиком

Текст как напечатаносовременная орфографияоба

как напечатано − 4 + современная орфография − 3 +

  1. 0 Форма лит. A. 0.90
  2. 1 курнал 0.87
  3. 2 рiемнао 0.67
  4. 3 MRI 0.43
  5. 4 - 0.57
  6. 5 пбылъ. 0.83
  7. 6 ся 0.61
  8. 7 патилъ за леченіе 0.87
  9. 8 Умотритель бодьниц 0.95
  10. 9 урнал 0.96
  11. 10 pieн 0.88
  12. 11 льпой 0.94
  13. 12 былъ 0.84
  14. 13 ся 0.69
  15. 14 ечні 0.75
  16. 15 LH 0.31
  17. 16 inнaro 0.60
  18. 17 radeo 0.60
  19. 18 VПИН9V09 BVHIW3E 0.62
  20. 19 (01-BEHI 0.61
  21. 20 rendA 0.76
  22. 21 рieнна 0.65
  23. 22 с 0.67
  24. 23 год 0.86
  25. 24 co 0.89
  26. 25 ьной 0.87
  27. 26 - 0.53
  28. 27 мбылъ 0.76
  29. 28 eueni 0.73
  30. 29 атил 0.94
  31. 30 Смотрителъ бохьниць 0.90
  32. 31 erenA 0.54
  33. 32 Iрiенао 0.74
  34. 33 - 0.21
  35. 34 н 0.41
  36. 35 ra 0.66
  37. 36 - 0.48
  38. 37 H 0.42
  39. 38 - 0.51
  40. 39 од 0.93
  41. 40 былъ 0.79
  42. 41 c 0.55
  43. 42 teчeнie 0.56
  44. 43 LL 0.42
  45. 44 мотритель больниц, 0.88