Added all

2026-04-28 09:28:49 +02:00
parent 03bc6bb8b4
commit ae7f3026a3
50 changed files with 3233 additions and 183 deletions
--- a/pages-for-tests/translated/008/008_cleaned.png
+++ b/pages-for-tests/translated/008/008_cleaned.png
--- a/pages-for-tests/translated/008/008_translated.png
+++ b/pages-for-tests/translated/008/008_translated.png
--- a/pages-for-tests/translated/008/bubbles.json
+++ b/pages-for-tests/translated/008/bubbles.json
@@ -0,0 +1,516 @@
+{
+  "1": {
+    "order": 1,
+    "region_type": "sfx",
+    "background_type": "complex",
+    "confidence": 0.4573,
+    "ocr_source": "vision-base",
+    "raw_ocr": "TK4F6",
+    "corrected_ocr": "TK4F6",
+    "translation_input": "TK4F6",
+    "translated": "",
+    "flags": [
+      "SFX"
+    ],
+    "bubble_groups": [
+      "TK4F6"
+    ],
+    "box": {
+      "x": 1066,
+      "y": 169,
+      "w": 100,
+      "h": 35
+    },
+    "lines": [
+      "TK4F6"
+    ]
+  },
+  "2": {
+    "order": 2,
+    "region_type": "dialogue",
+    "background_type": "complex",
+    "confidence": 0.499,
+    "ocr_source": "vision-base",
+    "raw_ocr": "UNK• IS ALL'S MQST PAMQUG... O.'O\"O",
+    "corrected_ocr": "UNK• IS ALL'S MQST PAMQUG... O.'O\"O",
+    "translation_input": "UNK• IS ALL'S MQST PAMQUG... O.'O\"O",
+    "translated": "UNK• ÉS EL MQST PAMQUG DE TOTS... O.'O\"O",
+    "flags": [
+      "BUBBLE",
+      "SEGMENTED"
+    ],
+    "bubble_groups": [
+      "UNK•",
+      "IS",
+      "ALL'S",
+      "MQST",
+      "PAMQUG... O.'O\"O"
+    ],
+    "box": {
+      "x": 414,
+      "y": 149,
+      "w": 173,
+      "h": 140
+    },
+    "lines": [
+      "UNK•",
+      "IS",
+      "ALL'S",
+      "MQST",
+      "PAMQUG... O.'O\"O"
+    ]
+  },
+  "3": {
+    "order": 3,
+    "region_type": "sfx",
+    "background_type": "complex",
+    "confidence": 0.5057,
+    "ocr_source": "vision-base",
+    "raw_ocr": "TANK...",
+    "corrected_ocr": "TANK...",
+    "translation_input": "TANK...",
+    "translated": "",
+    "flags": [
+      "SFX"
+    ],
+    "bubble_groups": [
+      "TANK..."
+    ],
+    "box": {
+      "x": 1079,
+      "y": 228,
+      "w": 96,
+      "h": 32
+    },
+    "lines": [
+      "TANK..."
+    ]
+  },
+  "4": {
+    "order": 4,
+    "region_type": "sfx",
+    "background_type": "complex",
+    "confidence": 0.3799,
+    "ocr_source": "vision-base",
+    "raw_ocr": "'I,CCY.",
+    "corrected_ocr": "'I,CCY.",
+    "translation_input": "'I,CCY.",
+    "translated": "",
+    "flags": [
+      "SFX",
+      "LOW_CONF"
+    ],
+    "bubble_groups": [
+      "'I,CCY."
+    ],
+    "box": {
+      "x": 323,
+      "y": 351,
+      "w": 61,
+      "h": 43
+    },
+    "lines": [
+      "'I,CCY."
+    ]
+  },
+  "5": {
+    "order": 5,
+    "region_type": "sfx",
+    "background_type": "complex",
+    "confidence": 0.5179,
+    "ocr_source": "vision-base",
+    "raw_ocr": "THAR6",
+    "corrected_ocr": "THAR6",
+    "translation_input": "THAR6",
+    "translated": "",
+    "flags": [
+      "SFX"
+    ],
+    "bubble_groups": [
+      "THAR6"
+    ],
+    "box": {
+      "x": 1066,
+      "y": 477,
+      "w": 85,
+      "h": 28
+    },
+    "lines": [
+      "THAR6"
+    ]
+  },
+  "6": {
+    "order": 6,
+    "region_type": "dialogue",
+    "background_type": "complex",
+    "confidence": 0.5321,
+    "ocr_source": "vision-base",
+    "raw_ocr": "VQST ILA PXHTLARAFTN&",
+    "corrected_ocr": "VQST ILA PXHTLARAFTN&",
+    "translation_input": "VQST ILA PXHTLARAFTN&",
+    "translated": "VQST ILA PXHTLARAFTN&",
+    "flags": [
+      "BUBBLE",
+      "SEGMENTED"
+    ],
+    "bubble_groups": [
+      "VQST",
+      "ILA PXHTLARAFTN&"
+    ],
+    "box": {
+      "x": 29,
+      "y": 507,
+      "w": 176,
+      "h": 51
+    },
+    "lines": [
+      "VQST",
+      "ILA PXHTLARAFTN&"
+    ]
+  },
+  "7": {
+    "order": 7,
+    "region_type": "dialogue",
+    "background_type": "complex",
+    "confidence": 0.4246,
+    "ocr_source": "vision-base",
+    "raw_ocr": "PQU61NFR OLL!",
+    "corrected_ocr": "PQU61NFR OLL!",
+    "translation_input": "PQU61NFR OLL!",
+    "translated": "PQU61NFR OLL!",
+    "flags": [
+      "LOW_CONF",
+      "BUBBLE",
+      "SEGMENTED"
+    ],
+    "bubble_groups": [
+      "PQU61NFR",
+      "OLL!"
+    ],
+    "box": {
+      "x": 58,
+      "y": 594,
+      "w": 116,
+      "h": 51
+    },
+    "lines": [
+      "PQU61NFR",
+      "OLL!"
+    ]
+  },
+  "8": {
+    "order": 8,
+    "region_type": "sfx",
+    "background_type": "complex",
+    "confidence": 0.3996,
+    "ocr_source": "vision-base",
+    "raw_ocr": "THIN66.",
+    "corrected_ocr": "THIN66.",
+    "translation_input": "THIN66.",
+    "translated": "",
+    "flags": [
+      "SFX",
+      "LOW_CONF"
+    ],
+    "bubble_groups": [
+      "THIN66."
+    ],
+    "box": {
+      "x": 649,
+      "y": 705,
+      "w": 95,
+      "h": 30
+    },
+    "lines": [
+      "THIN66."
+    ]
+  },
+  "10": {
+    "order": 9,
+    "region_type": "dialogue",
+    "background_type": "complex",
+    "confidence": 0.353,
+    "ocr_source": "vision-base",
+    "raw_ocr": "JI",
+    "corrected_ocr": "J!",
+    "translation_input": "J!",
+    "translated": "",
+    "flags": [
+      "LOW_CONF",
+      "HEAVY_CORRECTION"
+    ],
+    "bubble_groups": [
+      "JI"
+    ],
+    "box": {
+      "x": 1056,
+      "y": 744,
+      "w": 8,
+      "h": 10
+    },
+    "lines": [
+      "JI"
+    ]
+  },
+  "9": {
+    "order": 10,
+    "region_type": "reaction",
+    "background_type": "complex",
+    "confidence": 0.4044,
+    "ocr_source": "vision-base",
+    "raw_ocr": "I'RI",
+    "corrected_ocr": "I'R!",
+    "translation_input": "I'R!",
+    "translated": "JO!",
+    "flags": [
+      "LOW_CONF"
+    ],
+    "bubble_groups": [
+      "I'RI"
+    ],
+    "box": {
+      "x": 156,
+      "y": 790,
+      "w": 61,
+      "h": 70
+    },
+    "lines": [
+      "I'RI"
+    ]
+  },
+  "12": {
+    "order": 11,
+    "region_type": "dialogue",
+    "background_type": "complex",
+    "confidence": 0.4957,
+    "ocr_source": "vision-base",
+    "raw_ocr": "SPMS LIK$ GRFAK THO",
+    "corrected_ocr": "SPMS LIK$ GRFAK THO",
+    "translation_input": "SPMS LIK$ GRFAK THO",
+    "translated": "SPMS LIK$ GRFAK THO",
+    "flags": [
+      "BUBBLE",
+      "SEGMENTED"
+    ],
+    "bubble_groups": [
+      "SPMS",
+      "LIK$",
+      "GRFAK",
+      "THO"
+    ],
+    "box": {
+      "x": 623,
+      "y": 832,
+      "w": 92,
+      "h": 139
+    },
+    "lines": [
+      "SPMS",
+      "LIK$",
+      "GRFAK",
+      "THO"
+    ]
+  },
+  "11": {
+    "order": 12,
+    "region_type": "dialogue",
+    "background_type": "complex",
+    "confidence": 0.5007,
+    "ocr_source": "vision-base",
+    "raw_ocr": "FSPECIALLY WHEN PLAYERS •SLALA PUNK• AGRFSSIVELY PURR£NA TH$ PALL INRO TH¢ MOOP",
+    "corrected_ocr": "FSPECIALLY WHEN PLAYERS •SLALA PUNK• AGRFSSIVELY PURR£NA TH$ PALL INRO TH¢ MOOP",
+    "translation_input": "FSPECIALLY WHEN PLAYERS •SLALA PUNK• AGRFSSIVELY PURR£NA TH$ PALL INRO TH¢ MOOP",
+    "translated": "ESPECIALMENT QUAN ELS JUGADORS •SLALA PUNK• AGRFSSIVAMENT PURR£NA TH$ PALL INRO TH¢ MOOP",
+    "flags": [
+      "BUBBLE",
+      "SEGMENTED"
+    ],
+    "bubble_groups": [
+      "FSPECIALLY",
+      "WHEN PLAYERS",
+      "•SLALA PUNK•",
+      "AGRFSSIVELY",
+      "PURR£NA TH$",
+      "PALL INRO",
+      "TH¢ MOOP"
+    ],
+    "box": {
+      "x": 962,
+      "y": 812,
+      "w": 198,
+      "h": 197
+    },
+    "lines": [
+      "FSPECIALLY",
+      "WHEN PLAYERS",
+      "•SLALA PUNK•",
+      "AGRFSSIVELY",
+      "PURR£NA TH$",
+      "PALL INRO",
+      "TH¢ MOOP"
+    ]
+  },
+  "13": {
+    "order": 13,
+    "region_type": "dialogue",
+    "background_type": "complex",
+    "confidence": 0.4589,
+    "ocr_source": "vision-base",
+    "raw_ocr": "'SLAM PUNK.",
+    "corrected_ocr": "'SLAM PUNK.",
+    "translation_input": "'SLAM PUNK.",
+    "translated": "'SLAM PUNK.",
+    "flags": [
+      "BUBBLE",
+      "SEGMENTED"
+    ],
+    "bubble_groups": [
+      "'SLAM",
+      "PUNK."
+    ],
+    "box": {
+      "x": 23,
+      "y": 925,
+      "w": 104,
+      "h": 68
+    },
+    "lines": [
+      "'SLAM",
+      "PUNK."
+    ]
+  },
+  "14": {
+    "order": 14,
+    "region_type": "dialogue",
+    "background_type": "complex",
+    "confidence": 0.5096,
+    "ocr_source": "vision-base",
+    "raw_ocr": "PLUS, RUKAVIA KUWS SLOA PUNKS ARE SO",
+    "corrected_ocr": "PLUS, RUKAVIA KUWS SLOA PUNKS ARE SO",
+    "translation_input": "PLUS, RUKAVIA KUWS SLOA PUNKS ARE SO",
+    "translated": "A MÉS, RUKAVIA KUWS SLOA PUNKS SÓN SO",
+    "flags": [
+      "BUBBLE",
+      "SEGMENTED"
+    ],
+    "bubble_groups": [
+      "PLUS,",
+      "RUKAVIA KUWS",
+      "SLOA PUNKS",
+      "ARE SO"
+    ],
+    "box": {
+      "x": 394,
+      "y": 1407,
+      "w": 162,
+      "h": 91
+    },
+    "lines": [
+      "PLUS,",
+      "RUKAVIA KUWS",
+      "SLOA PUNKS",
+      "ARE SO"
+    ]
+  },
+  "15": {
+    "order": 15,
+    "region_type": "dialogue",
+    "background_type": "complex",
+    "confidence": 0.5154,
+    "ocr_source": "vision-base",
+    "raw_ocr": "PURINA JUNIOR",
+    "corrected_ocr": "PURINA JUNIOR",
+    "translation_input": "PURINA JUNIOR",
+    "translated": "PURINA JUNIOR",
+    "flags": [
+      "BUBBLE",
+      "SEGMENTED"
+    ],
+    "bubble_groups": [
+      "PURINA",
+      "JUNIOR"
+    ],
+    "box": {
+      "x": 1018,
+      "y": 1428,
+      "w": 104,
+      "h": 51
+    },
+    "lines": [
+      "PURINA",
+      "JUNIOR"
+    ]
+  },
+  "16": {
+    "order": 16,
+    "region_type": "dialogue",
+    "background_type": "complex",
+    "confidence": 0.4819,
+    "ocr_source": "vision-base",
+    "raw_ocr": "ONLY PTP H¢ ¢N¢R•IZ¢ SOWN SCHOOL'S TH$ THS ' WIRS...,OPPONPMRS •YM STOOP IT VIAS",
+    "corrected_ocr": "ONLY PTP H¢ ¢N¢R•IZ¢ SOWN SCHOOL'S TH$ THS ' WIRS...,OPPONPMRS •YM STOOP IT VIAS",
+    "translation_input": "ONLY PTP H¢ ¢N¢R•IZ¢ SOWN SCHOOL'S TH$ THS ' WIRS...,OPPONPMRS •YM STOOP IT VIAS",
+    "translated": "NOMÉS PTP H¢ ¢N¢R•IZ¢ SOWN SCHOOL'S TH$ THS ' WIRS...,OPPONPMRS •YM STOP IT VIAS",
+    "flags": [
+      "BUBBLE",
+      "SEGMENTED"
+    ],
+    "bubble_groups": [
+      "ONLY PTP",
+      "H¢ ¢N¢R•IZ¢",
+      "SOWN",
+      "SCHOOL'S",
+      "TH$ THS ' WIRS...,OPPONPMRS",
+      "•YM STOOP",
+      "IT VIAS"
+    ],
+    "box": {
+      "x": 594,
+      "y": 1433,
+      "w": 248,
+      "h": 273
+    },
+    "lines": [
+      "ONLY PTP",
+      "H¢ ¢N¢R•IZ¢",
+      "SOWN",
+      "SCHOOL'S",
+      "TH$ THS ' WIRS...,OPPONPMRS",
+      "•YM STOOP",
+      "IT VIAS"
+    ]
+  },
+  "17": {
+    "order": 17,
+    "region_type": "dialogue",
+    "background_type": "complex",
+    "confidence": 0.5012,
+    "ocr_source": "vision-base",
+    "raw_ocr": "ISAN ONC$ SLAM PUNKSP PIIRINA A AAAA$;",
+    "corrected_ocr": "ISAN ONC$ SLAM PUNKSP PIIRINA A AAAA$;",
+    "translation_input": "ISAN ONC$ SLAM PUNKSP PIIRINA A AAAA$;",
+    "translated": "ISAN ONC$ SLAM PUNKSP PIIRINA A AAAA$;",
+    "flags": [
+      "BUBBLE",
+      "SEGMENTED"
+    ],
+    "bubble_groups": [
+      "ISAN ONC$",
+      "SLAM PUNKSP",
+      "PIIRINA A",
+      "AAAA$;"
+    ],
+    "box": {
+      "x": 971,
+      "y": 1514,
+      "w": 195,
+      "h": 112
+    },
+    "lines": [
+      "ISAN ONC$",
+      "SLAM PUNKSP",
+      "PIIRINA A",
+      "AAAA$;"
+    ]
+  }
+}
--- a/pages-for-tests/translated/008/debug_clusters.png
+++ b/pages-for-tests/translated/008/debug_clusters.png
--- a/pages-for-tests/translated/008/output.txt
+++ b/pages-for-tests/translated/008/output.txt
@@ -0,0 +1,19 @@
+BUBBLE|ORDER|TYPE|CONF|OCR_SOURCE|ORIGINAL|CORRECTED|BUBBLE_GROUPS|TRANSLATED|FLAGS
+────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
+#1|1|sfx|0.46|vision-base|TK4F6|TK4F6|TK4F6||SFX
+#2|2|dialogue|0.50|vision-base|UNK• IS ALL'S MQST PAMQUG... O.'O"O|UNK• IS ALL'S MQST PAMQUG... O.'O"O|UNK• || IS || ALL'S || MQST || PAMQUG... O.'O"O|UNK• ÉS EL MQST PAMQUG DE TOTS... O.'O"O|BUBBLE,SEGMENTED
+#3|3|sfx|0.51|vision-base|TANK...|TANK...|TANK...||SFX
+#4|4|sfx|0.38|vision-base|'I,CCY.|'I,CCY.|'I,CCY.||SFX,LOW_CONF
+#5|5|sfx|0.52|vision-base|THAR6|THAR6|THAR6||SFX
+#6|6|dialogue|0.53|vision-base|VQST ILA PXHTLARAFTN&|VQST ILA PXHTLARAFTN&|VQST || ILA PXHTLARAFTN&|VQST ILA PXHTLARAFTN&|BUBBLE,SEGMENTED
+#7|7|dialogue|0.42|vision-base|PQU61NFR OLL!|PQU61NFR OLL!|PQU61NFR || OLL!|PQU61NFR OLL!|LOW_CONF,BUBBLE,SEGMENTED
+#8|8|sfx|0.40|vision-base|THIN66.|THIN66.|THIN66.||SFX,LOW_CONF
+#10|9|dialogue|0.35|vision-base|JI|J!|JI||LOW_CONF,HEAVY_CORRECTION
+#9|10|reaction|0.40|vision-base|I'RI|I'R!|I'RI|JO!|LOW_CONF
+#12|11|dialogue|0.50|vision-base|SPMS LIK$ GRFAK THO|SPMS LIK$ GRFAK THO|SPMS || LIK$ || GRFAK || THO|SPMS LIK$ GRFAK THO|BUBBLE,SEGMENTED
+#11|12|dialogue|0.50|vision-base|FSPECIALLY WHEN PLAYERS •SLALA PUNK• AGRFSSIVELY PURR£NA TH$ PALL INRO TH¢ MOOP|FSPECIALLY WHEN PLAYERS •SLALA PUNK• AGRFSSIVELY PURR£NA TH$ PALL INRO TH¢ MOOP|FSPECIALLY || WHEN PLAYERS || •SLALA PUNK• || AGRFSSIVELY || PURR£NA TH$ || PALL INRO || TH¢ MOOP|ESPECIALMENT QUAN ELS JUGADORS •SLALA PUNK• AGRFSSIVAMENT PURR£NA TH$ PALL INRO TH¢ MOOP|BUBBLE,SEGMENTED
+#13|13|dialogue|0.46|vision-base|'SLAM PUNK.|'SLAM PUNK.|'SLAM || PUNK.|'SLAM PUNK.|BUBBLE,SEGMENTED
+#14|14|dialogue|0.51|vision-base|PLUS, RUKAVIA KUWS SLOA PUNKS ARE SO|PLUS, RUKAVIA KUWS SLOA PUNKS ARE SO|PLUS, || RUKAVIA KUWS || SLOA PUNKS || ARE SO|A MÉS, RUKAVIA KUWS SLOA PUNKS SÓN SO|BUBBLE,SEGMENTED
+#15|15|dialogue|0.52|vision-base|PURINA JUNIOR|PURINA JUNIOR|PURINA || JUNIOR|PURINA JUNIOR|BUBBLE,SEGMENTED
+#16|16|dialogue|0.48|vision-base|ONLY PTP H¢ ¢N¢R•IZ¢ SOWN SCHOOL'S TH$ THS ' WIRS...,OPPONPMRS •YM STOOP IT VIAS|ONLY PTP H¢ ¢N¢R•IZ¢ SOWN SCHOOL'S TH$ THS ' WIRS...,OPPONPMRS •YM STOOP IT VIAS|ONLY PTP || H¢ ¢N¢R•IZ¢ || SOWN || SCHOOL'S || TH$ THS ' WIRS...,OPPONPMRS || •YM STOOP || IT VIAS|NOMÉS PTP H¢ ¢N¢R•IZ¢ SOWN SCHOOL'S TH$ THS ' WIRS...,OPPONPMRS •YM STOP IT VIAS|BUBBLE,SEGMENTED
+#17|17|dialogue|0.50|vision-base|ISAN ONC$ SLAM PUNKSP PIIRINA A AAAA$;|ISAN ONC$ SLAM PUNKSP PIIRINA A AAAA$;|ISAN ONC$ || SLAM PUNKSP || PIIRINA A || AAAA$;|ISAN ONC$ SLAM PUNKSP PIIRINA A AAAA$;|BUBBLE,SEGMENTED