Bookolot deep dive into books

страница 99

99 / 222 молдавская кириллица уверенность 0.69 человеком не проверено

Провенанс

transcript transcript
2026-09-18T05:14:26+00:00 machine-generated
transliteration transliteration
2026-09-18T07:36:18+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=JD4398",
    "media_title": "Gramatica limbii moldoveneşti. P. 1 : Fonetica şi morfologia",
    "modification_date": "2026-09-18T05:14:26+00:00",
    "originating_media_file": "99.tif",
    "processing": [
      {
        "application_name": "kraken blla",
        "application_parameters": {
          "device": "cpu",
          "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": "cpu"
        },
        "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": "sha256:3286fecbc0f1468385a5ca82869783d4aaa52e04161eba30d9930252f46d5b8f",
    "transcript_id": "bookolot:JD4398:99:ocr-v1",
    "transcript_language": [
      "ro-Cyrl-MD"
    ],
    "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=JD4398",
    "media_title": "Gramatica limbii moldoveneşti. P. 1 : Fonetica şi morfologia",
    "modification_date": "2026-09-18T07:36:18+00:00",
    "originating_media_file": "99.tif",
    "parent_transcript_id": "bookolot:JD4398:99:ocr-v1",
    "processing": [
      {
        "application_name": "bookolot.rag.normalize",
        "application_parameters": {
          "normalizer_version": 3,
          "script": "md_cyrillic"
        },
        "application_provider": "Bookolot",
        "application_repo": "https://github.com/selic/bookolot",
        "application_type": "transliteration",
        "application_version": "851f6b2-dirty"
      }
    ],
    "provider": "Bookolot",
    "transcript_checksum": "sha256:a0ff842070966ec649b0e32b51def65270e3dd6f38abd0f045a65df0d9132dd7",
    "transcript_id": "bookolot:JD4398:99:modern-v3",
    "transcript_language": [
      "ro-Latn-t-ro-cyrl-md"
    ],
    "type": "transliteration"
  }
]
Скан этой строки 99

уверенно стоит взглянуть проверьте скан Открыть скан целиком

Текст как напечатанотранслитерацияоба

как напечатано − 4 + транслитерация − 2 +

  1. 0 wneer 0.71
  2. 1 găzilo 0.92
  3. 2 ng 0.81
  4. 3 em 0.58
  5. 4 nelo 0.82
  6. 5 lbăstr 0.95
  7. 6 ad 0.48
  8. 7 a 0.28
  9. 8 relo 0.98
  10. 9 zen 0.66
  11. 10 vec 0.87
  12. 11 ov 0.65
  13. 12 verz 0.89
  14. 13 nzele 0.89
  15. 14 e 0.57
  16. 15 sâlitoar 0.98
  17. 16 lelo 1.00
  18. 17 sâlitoia 0.97
  19. 18 icele 0.89
  20. 19 titel 0.90
  21. 20 hume 0.95
  22. 21 88 0.51
  23. 22 umadevn 0.79
  24. 23 0 0.45
  25. 24 umadevnuo 0.62
  26. 25 @ 0.59
  27. 26 A 0.28
  28. 27 @ 0.40
  29. 28 + 0.14
  30. 29 pieg 0.64
  31. 30 g 0.55
  32. 31 eg 0.83
  33. 32 lbăstr 0.92
  34. 33 i 0.78
  35. 34 n 0.58
  36. 35 uumumu 0.80
  37. 36 umume 1.00
  38. 37 s 0.43
  39. 38 g 0.65
  40. 39 6 0.68
  41. 40 ܘ 0.37
  42. 41 ל 0.44
  43. 42 t 0.37
  44. 43 6ăt 0.54
  45. 44 n 0.47
  46. 45 ilo 0.86
  47. 46 m 0.69
  48. 47 du 0.51
  49. 48 șl 0.56
  50. 49 i 0.93
  51. 50 vv 0.43
  52. 51 șilo 0.97
  53. 52 ben 0.60
  54. 53 rk 0.36
  55. 54 e 0.79
  56. 55 îlpilo 0.90
  57. 56 ec 0.56
  58. 57 liKW 0.34
  59. 58 z 0.52
  60. 59 da 0.72
  61. 60 acilo 0.99
  62. 61 humo 0.83
  63. 62 s 0.50
  64. 63 zer 0.56
  65. 64 ze 0.56
  66. 65 lit 0.74
  67. 66 șlo 0.94
  68. 67 ne 0.71
  69. 68 66 0.66
  70. 69 lăreas 0.82
  71. 70 umadevnuox 0.76
  72. 71 adevnuor 0.63
  73. 72 ilăș 0.88
  74. 73 ăs 0.75
  75. 74 iiii iii ii 0.87