{
  "text": "日本人和偽日本人三種分辨方法。\n第一個,如果他對著C國的國旗行禮,說我是日本人,T國是C國的,他就是假的日本人。\n我們不會為C國的國旗行禮,而且學生也都沒有教過T國是C國的,所以不會有這個思想。\n第二個,如果他在錄影宣傳我愛C國,他就是假的日本人。\n有可能會有喜歡C國的日本人,但我們不會在錄影隨便搭喊。\n連一個日本人都不會從日本飛到T國主張愛C國。\n第三個,講原子彈相關的梗。\n當然我們有時候會批判或是諷刺日本政府、文化、社會等等。\n但是真正的日本人絕對不會講到原子彈相關的梗。\n這不是說我們以為日本人是受害者,而是說當時被轟炸的一般民眾都是戰爭的犧牲者。\n他們又不是決定開戰的人。\n好了,你們也會分日本跟假的日本人嗎?",
  "language": "zh",
  "duration": 51.176813,
  "segments": [
    {
      "id": 0,
      "seek": 0,
      "start": 0.0,
      "end": 2.4,
      "text": "日本人和偽日本人三種分辨方法。",
      "tokens": [
        50365,
        27311,
        4035,
        12565,
        6344,
        27311,
        4035,
        10960,
        16516,
        6627,
        9830,
        101,
        9249,
        11148,
        1543,
        50485
      ],
      "temperature": 0,
      "avg_logprob": -0.19983457010003586,
      "compression_ratio": 1.6727272727272726,
      "no_speech_prob": 8.728180504735672e-12,
      "source": "whisper",
      "text_original": "日本人和為日本人三種分辨方法。",
      "correction_applied": true,
      "correction_source": "llm_correct_a_presegmentation"
    },
    {
      "id": 1,
      "seek": 0,
      "start": 2.4,
      "end": 8.5,
      "text": "第一個,如果他對著C國的國旗行禮,說我是日本人,T國是C國的,他就是假的日本人。",
      "tokens": [
        50485,
        40760,
        11,
        13119,
        5000,
        8350,
        19382,
        34,
        8053,
        1546,
        8053,
        4479,
        245,
        8082,
        11,
        15914,
        27311,
        4035,
        11,
        51,
        8053,
        1541,
        34,
        8053,
        1546,
        11,
        5000,
        5620,
        31706,
        1546,
        27311,
        4035,
        1543,
        50790
      ],
      "temperature": 0,
      "avg_logprob": -0.19983457010003586,
      "compression_ratio": 1.6727272727272726,
      "no_speech_prob": 8.728180504735672e-12,
      "source": "whisper",
      "text_original": "第一個,如果他回著C國的國旗行,我是日本人,T國是C國的,他就是假的日本人。",
      "correction_applied": true,
      "correction_source": "llm_correct_a_presegmentation"
    },
    {
      "id": 2,
      "seek": 0,
      "start": 8.5,
      "end": 15.200000000000001,
      "text": "我們不會為C國的國旗行禮,而且學生也都沒有教過T國是C國的,所以不會有這個思想。",
      "tokens": [
        50790,
        5884,
        21121,
        6344,
        34,
        8053,
        1546,
        8053,
        4479,
        245,
        11,
        22942,
        21372,
        8244,
        6404,
        7182,
        6963,
        21936,
        8816,
        51,
        8053,
        1541,
        34,
        8053,
        1546,
        11,
        7239,
        21121,
        2412,
        6287,
        8870,
        7093,
        1543,
        51125
      ],
      "temperature": 0,
      "avg_logprob": -0.19983457010003586,
      "compression_ratio": 1.6727272727272726,
      "no_speech_prob": 8.728180504735672e-12,
      "source": "whisper",
      "text_original": "我們不會為C國的國旗,而且學生也都沒有教過T國是C國的,所以不會有這個思想。",
      "correction_applied": true,
      "correction_source": "llm_correct_a_presegmentation"
    },
    {
      "id": 3,
      "seek": 0,
      "start": 15.200000000000001,
      "end": 19.8,
      "text": "第二個,如果他在錄影宣傳我愛C國,他就是假的日本人。",
      "tokens": [
        51125,
        49085,
        11,
        13119,
        5000,
        3581,
        9567,
        226,
        12760,
        2415,
        96,
        40852,
        1654,
        15157,
        34,
        8053,
        11,
        5000,
        5620,
        31706,
        1546,
        27311,
        4035,
        1543,
        51355
      ],
      "temperature": 0,
      "avg_logprob": -0.19983457010003586,
      "compression_ratio": 1.6727272727272726,
      "no_speech_prob": 8.728180504735672e-12,
      "source": "whisper"
    },
    {
      "id": 4,
      "seek": 0,
      "start": 19.8,
      "end": 24.400000000000002,
      "text": "有可能會有喜歡C國的日本人,但我們不會在錄影隨便搭喊。",
      "tokens": [
        51355,
        2412,
        16657,
        6236,
        2412,
        21385,
        34,
        8053,
        1546,
        27311,
        4035,
        11,
        8395,
        5884,
        21121,
        3581,
        9567,
        226,
        12760,
        48890,
        27364,
        22220,
        255,
        5234,
        232,
        1543,
        51585
      ],
      "temperature": 0,
      "avg_logprob": -0.19983457010003586,
      "compression_ratio": 1.6727272727272726,
      "no_speech_prob": 8.728180504735672e-12,
      "source": "whisper"
    },
    {
      "id": 5,
      "seek": 0,
      "start": 24.400000000000002,
      "end": 28.6,
      "text": "連一個日本人都不會從日本飛到T國主張愛C國。",
      "tokens": [
        51585,
        36252,
        8990,
        27311,
        4035,
        7182,
        21121,
        21068,
        27311,
        34629,
        4511,
        51,
        8053,
        13557,
        18889,
        15157,
        34,
        8053,
        1543,
        51795
      ],
      "temperature": 0,
      "avg_logprob": -0.19983457010003586,
      "compression_ratio": 1.6727272727272726,
      "no_speech_prob": 8.728180504735672e-12,
      "source": "whisper"
    },
    {
      "id": 6,
      "seek": 2860,
      "start": 28.6,
      "end": 31.5,
      "text": "第三個,講原子彈相關的梗。",
      "tokens": [
        50365,
        35878,
        3338,
        11,
        11932,
        19683,
        7626,
        7391,
        230,
        15106,
        14899,
        1546,
        19017,
        245,
        1543,
        50510
      ],
      "temperature": 0,
      "avg_logprob": -0.1477608894234273,
      "compression_ratio": 1.4044117647058822,
      "no_speech_prob": 9.047994124766756e-12,
      "source": "whisper"
    },
    {
      "id": 7,
      "seek": 2860,
      "start": 31.5,
      "end": 36.4,
      "text": "當然我們有時候會批判或是諷刺日本政府、文化、社會等等。",
      "tokens": [
        50510,
        21707,
        5884,
        2412,
        14010,
        6236,
        3416,
        117,
        2437,
        97,
        19780,
        1541,
        11067,
        115,
        2437,
        118,
        27311,
        41116,
        1231,
        17174,
        23756,
        1231,
        27658,
        6236,
        36000,
        1543,
        50755
      ],
      "temperature": 0,
      "avg_logprob": -0.1477608894234273,
      "compression_ratio": 1.4044117647058822,
      "no_speech_prob": 9.047994124766756e-12,
      "source": "whisper"
    },
    {
      "id": 8,
      "seek": 2860,
      "start": 36.4,
      "end": 40.2,
      "text": "但是真正的日本人絕對不會講到原子彈相關的梗。",
      "tokens": [
        50755,
        11189,
        6303,
        15789,
        1546,
        27311,
        4035,
        6948,
        243,
        2855,
        21121,
        11932,
        4511,
        19683,
        7626,
        7391,
        230,
        15106,
        14899,
        1546,
        19017,
        245,
        1543,
        50945
      ],
      "temperature": 0,
      "avg_logprob": -0.1477608894234273,
      "compression_ratio": 1.4044117647058822,
      "no_speech_prob": 9.047994124766756e-12,
      "source": "whisper"
    },
    {
      "id": 9,
      "seek": 2860,
      "start": 40.2,
      "end": 46.400000000000006,
      "text": "這不是說我們以為日本人是受害者,而是說當時被轟炸的一般民眾都是戰爭的犧牲者。",
      "tokens": [
        50945,
        2664,
        7296,
        4622,
        5884,
        3588,
        6344,
        27311,
        4035,
        1541,
        23151,
        14694,
        12444,
        11,
        11070,
        1541,
        4622,
        13118,
        6611,
        23238,
        17819,
        253,
        4804,
        116,
        1546,
        2257,
        49640,
        16113,
        29595,
        22796,
        23209,
        8164,
        255,
        1546,
        20083,
        8244,
        12444,
        1543,
        51255
      ],
      "temperature": 0,
      "avg_logprob": -0.1477608894234273,
      "compression_ratio": 1.4044117647058822,
      "no_speech_prob": 9.047994124766756e-12,
      "source": "whisper",
      "text_original": "這不是說我們以為日本人是受害者,而是說當時被轟炸的一般民眾都是戰爭的私生者。",
      "correction_applied": true,
      "correction_source": "llm_correct_a_presegmentation"
    },
    {
      "id": 10,
      "seek": 2860,
      "start": 46.400000000000006,
      "end": 48.0,
      "text": "他們又不是決定開戰的人。",
      "tokens": [
        51255,
        20486,
        17047,
        7296,
        33540,
        12088,
        8949,
        23209,
        29979,
        1543,
        51335
      ],
      "temperature": 0,
      "avg_logprob": -0.1477608894234273,
      "compression_ratio": 1.4044117647058822,
      "no_speech_prob": 9.047994124766756e-12,
      "source": "whisper"
    },
    {
      "id": 11,
      "seek": 2860,
      "start": 48.0,
      "end": 51.0,
      "text": "好了,你們也會分日本跟假的日本人嗎?",
      "tokens": [
        51335,
        12621,
        11,
        19891,
        6404,
        6236,
        6627,
        27311,
        9678,
        31706,
        1546,
        27311,
        4035,
        7434,
        30,
        51485
      ],
      "temperature": 0,
      "avg_logprob": -0.1477608894234273,
      "compression_ratio": 1.4044117647058822,
      "no_speech_prob": 9.047994124766756e-12,
      "source": "whisper"
    }
  ],
  "transcript_selection": {
    "schema": "videonote.transcript_selection.v1",
    "status": "SELECTED",
    "requested_language": "zh",
    "duration": 51.176813,
    "reference_path": null,
    "reference_kind": null,
    "reference_language": null,
    "selected_source": "whisper_segmented",
    "decision_reason": "source_unavailable_or_untrusted_whisper_passed",
    "whisper_rejected": false,
    "source_profile": {
      "segment_count": 0,
      "duration_coverage": 0.0,
      "usable_full": false,
      "usable_partial": false,
      "hallucination_region_count": 0,
      "hallucination_regions": [],
      "language": {
        "requested": "zh",
        "matched": false
      }
    },
    "whisper_profile": {
      "segment_count": 12,
      "multilingual": false,
      "first_start": 0.0,
      "final_end": 51.0,
      "duration_coverage": 0.996545,
      "maximum_gap_seconds": 0.0,
      "inverted_count": 0,
      "language": {
        "requested": "zh",
        "matched": true,
        "latin": 10,
        "han": 260,
        "kana": 0,
        "hangul": 0
      },
      "hallucination_region_count": 0,
      "hallucination_regions": [],
      "usable_full": true,
      "usable_partial": true
    },
    "comparison": {
      "window_seconds": 30.0,
      "compared_window_count": 0,
      "median_score": 0.0,
      "divergent_window_count": 0,
      "divergent_ratio": 0.0,
      "divergent_windows": []
    },
    "timestamp_alignment": {
      "applied": false,
      "estimated_offset_seconds": 0.0,
      "matched_segment_count": 0,
      "match_scores": []
    },
    "caption_timing_repair": null,
    "filled_source_profile": null,
    "whisper_duration_guard": {
      "media_duration": 51.177,
      "rejected_segment_count": 0,
      "rejected_segments": []
    }
  },
  "presegmentation_correction": {
    "applied": true,
    "correction_count": 4
  }
}