{
  "text": "这一集呢,跟大家推荐一个很小众,但是呢,可能很多人也会用到的这样的一个开源的工具啊。\n这就是Firecrawl刚刚推出的这个叫做OCR-it的这样的一个开源的插件。\n它解决了什么问题呢?我相信呢,肯定大部分人都会碰到。\n比如呢,我们打开这个某度文库下面的这个文档,我本来呢,我就想拷贝一下这里面的一些内容。\n然后呢,我就弹窗了,要求你付费,要求你变成会员。是不是很恶心啊?\n这时呢,如果你装了这个开源插件呢,那么你就可以点击这里啊,框住你想要的区域啊,然后点击捕获。\n这样子呢,你就能拷贝到里面的文本了。\n这还不算啊,你继续往下滚动一页,然后呢,再去捕获。\n然后呢,第二页的文本也拷贝了。\n也就是说,你可以通过这个方法把所有的这个本来需要收费的这样的一个文档全部内容给拷贝出来了。\n然后我们先看一下这个结果。\n下载下来后啊,打开。\n可以看到啊,所有文本都在里面了。\n所以这个工具啊,就是专制那些内容拷贝下载动不动就需要你充会员了,需要你交费了,这样的一些流氓呢。\n好,大家觉得有用的话,点赞,关注,分享,支持一下吧。\n谢谢。",
  "language": "zh",
  "duration": 86.099625,
  "segments": [
    {
      "id": 0,
      "seek": 0,
      "start": 0.0,
      "end": 7.9,
      "text": "这一集呢,跟大家推荐一个很小众,但是呢,可能很多人也会用到的这样的一个开源的工具啊。",
      "tokens": [
        50365,
        5562,
        2257,
        26020,
        6240,
        11,
        47349,
        33597,
        31409,
        238,
        20182,
        4563,
        7322,
        7384,
        245,
        11,
        11189,
        6240,
        11,
        16657,
        20778,
        4035,
        6404,
        12949,
        9254,
        4511,
        1546,
        21209,
        1546,
        20182,
        18937,
        47402,
        1546,
        23323,
        39806,
        4905,
        1543,
        50760
      ],
      "temperature": 0,
      "avg_logprob": -0.20252461677050068,
      "compression_ratio": 1.3223684210526316,
      "no_speech_prob": 9.51358609946329e-12,
      "source": "whisper"
    },
    {
      "id": 1,
      "seek": 0,
      "start": 7.9,
      "end": 14.4,
      "text": "这就是Firecrawl刚刚推出的这个叫做OCR-it的这样的一个开源的插件。",
      "tokens": [
        50760,
        5562,
        5620,
        45651,
        34,
        5901,
        49160,
        49160,
        33597,
        7781,
        1546,
        15368,
        19855,
        10907,
        46,
        18547,
        3927,
        1546,
        21209,
        1546,
        20182,
        18937,
        47402,
        1546,
        11673,
        240,
        20485,
        1543,
        51085
      ],
      "temperature": 0,
      "avg_logprob": -0.20252461677050068,
      "compression_ratio": 1.3223684210526316,
      "no_speech_prob": 9.51358609946329e-12,
      "source": "whisper",
      "text_original": "这就是FireClaw刚刚推出的这个叫做OCRIT的这样的一个开源的插件。",
      "correction_applied": true,
      "correction_source": "llm_correct_a_presegmentation"
    },
    {
      "id": 2,
      "seek": 0,
      "start": 14.4,
      "end": 20.1,
      "text": "它解决了什么问题呢?我相信呢,肯定大部分人都会碰到。",
      "tokens": [
        51085,
        11284,
        17278,
        5676,
        111,
        2289,
        10440,
        34069,
        6240,
        30,
        1654,
        35428,
        6240,
        11,
        14356,
        107,
        12088,
        3582,
        32174,
        4035,
        7182,
        12949,
        16337,
        108,
        4511,
        1543,
        51370
      ],
      "temperature": 0,
      "avg_logprob": -0.20252461677050068,
      "compression_ratio": 1.3223684210526316,
      "no_speech_prob": 9.51358609946329e-12,
      "source": "whisper"
    },
    {
      "id": 3,
      "seek": 0,
      "start": 20.1,
      "end": 27.3,
      "text": "比如呢,我们打开这个某度文库下面的这个文档,我本来呢,我就想拷贝一下这里面的一些内容。",
      "tokens": [
        51370,
        36757,
        6240,
        11,
        15003,
        12467,
        18937,
        15368,
        17238,
        238,
        13127,
        17174,
        6346,
        241,
        47150,
        1546,
        15368,
        17174,
        21416,
        96,
        11,
        1654,
        8802,
        6912,
        6240,
        11,
        22020,
        7093,
        6852,
        115,
        18464,
        251,
        8861,
        35102,
        8833,
        1546,
        38515,
        34742,
        25750,
        1543,
        51730
      ],
      "temperature": 0,
      "avg_logprob": -0.20252461677050068,
      "compression_ratio": 1.3223684210526316,
      "no_speech_prob": 9.51358609946329e-12,
      "source": "whisper"
    },
    {
      "id": 4,
      "seek": 2730,
      "start": 27.3,
      "end": 33.3,
      "text": "然后呢,我就弹窗了,要求你付费,要求你变成会员。是不是很恶心啊?",
      "tokens": [
        50365,
        26636,
        6240,
        11,
        22020,
        5702,
        117,
        30771,
        245,
        2289,
        11,
        4275,
        32718,
        2166,
        41469,
        18464,
        117,
        11,
        4275,
        32718,
        2166,
        2129,
        246,
        11336,
        12949,
        3606,
        246,
        1543,
        23034,
        4563,
        11845,
        114,
        7945,
        4905,
        30,
        50665
      ],
      "temperature": 0,
      "avg_logprob": -0.1423327250358386,
      "compression_ratio": 1.4253731343283582,
      "no_speech_prob": 1.1576283334702175e-11,
      "source": "whisper"
    },
    {
      "id": 5,
      "seek": 2730,
      "start": 33.3,
      "end": 42.7,
      "text": "这时呢,如果你装了这个开源插件呢,那么你就可以点击这里啊,框住你想要的区域啊,然后点击捕获。",
      "tokens": [
        50665,
        5562,
        15729,
        6240,
        11,
        45669,
        8083,
        227,
        2289,
        15368,
        18937,
        47402,
        11673,
        240,
        20485,
        6240,
        11,
        35693,
        2166,
        36781,
        12579,
        6336,
        119,
        35102,
        4905,
        11,
        21416,
        228,
        21632,
        38386,
        4275,
        1546,
        9937,
        118,
        16262,
        253,
        4905,
        11,
        26636,
        12579,
        6336,
        119,
        9890,
        98,
        18464,
        100,
        1543,
        51135
      ],
      "temperature": 0,
      "avg_logprob": -0.1423327250358386,
      "compression_ratio": 1.4253731343283582,
      "no_speech_prob": 1.1576283334702175e-11,
      "source": "whisper",
      "text_original": "这时呢,如果你装了这个开源插件呢,那么你就可以点击这里啊,框住你想要的区域啊,然后点击补货。",
      "correction_applied": true,
      "correction_source": "llm_correct_a_presegmentation"
    },
    {
      "id": 6,
      "seek": 2730,
      "start": 42.7,
      "end": 47.1,
      "text": "这样子呢,你就能拷贝到里面的文本了。",
      "tokens": [
        51135,
        21209,
        7626,
        6240,
        11,
        41045,
        8225,
        6852,
        115,
        18464,
        251,
        4511,
        15759,
        8833,
        1546,
        17174,
        8802,
        2289,
        1543,
        51355
      ],
      "temperature": 0,
      "avg_logprob": -0.1423327250358386,
      "compression_ratio": 1.4253731343283582,
      "no_speech_prob": 1.1576283334702175e-11,
      "source": "whisper"
    },
    {
      "id": 7,
      "seek": 2730,
      "start": 47.1,
      "end": 52.5,
      "text": "这还不算啊,你继续往下滚动一页,然后呢,再去捕获。",
      "tokens": [
        51355,
        5562,
        14852,
        1960,
        19497,
        4905,
        11,
        2166,
        10115,
        100,
        10115,
        255,
        29510,
        4438,
        10415,
        111,
        34961,
        2257,
        10178,
        113,
        11,
        26636,
        6240,
        11,
        8623,
        6734,
        9890,
        98,
        18464,
        100,
        1543,
        51625
      ],
      "temperature": 0,
      "avg_logprob": -0.1423327250358386,
      "compression_ratio": 1.4253731343283582,
      "no_speech_prob": 1.1576283334702175e-11,
      "source": "whisper",
      "text_original": "这还不算啊,你继续往下稳动一页,然后呢,再去补货。",
      "correction_applied": true,
      "correction_source": "llm_correct_a_presegmentation"
    },
    {
      "id": 8,
      "seek": 2730,
      "start": 52.5,
      "end": 55.0,
      "text": "然后呢,第二页的文本也拷贝了。",
      "tokens": [
        51625,
        26636,
        6240,
        11,
        19693,
        10178,
        113,
        1546,
        17174,
        8802,
        6404,
        6852,
        115,
        18464,
        251,
        2289,
        1543,
        51750
      ],
      "temperature": 0,
      "avg_logprob": -0.1423327250358386,
      "compression_ratio": 1.4253731343283582,
      "no_speech_prob": 1.1576283334702175e-11,
      "source": "whisper"
    },
    {
      "id": 9,
      "seek": 5500,
      "start": 55.0,
      "end": 62.3,
      "text": "也就是说,你可以通过这个方法把所有的这个本来需要收费的这样的一个文档全部内容给拷贝出来了。",
      "tokens": [
        50365,
        6404,
        5620,
        8090,
        11,
        42766,
        19550,
        16866,
        15368,
        9249,
        11148,
        16075,
        39300,
        1546,
        15368,
        8802,
        6912,
        35748,
        18681,
        18464,
        117,
        1546,
        21209,
        1546,
        20182,
        17174,
        21416,
        96,
        38714,
        34742,
        25750,
        23197,
        6852,
        115,
        18464,
        251,
        7781,
        34912,
        1543,
        50730
      ],
      "temperature": 0,
      "avg_logprob": -0.1538761226275495,
      "compression_ratio": 1.4490566037735848,
      "no_speech_prob": 1.562527190968055e-11,
      "source": "whisper"
    },
    {
      "id": 10,
      "seek": 5500,
      "start": 62.3,
      "end": 64.3,
      "text": "然后我们先看一下这个结果。",
      "tokens": [
        50730,
        26636,
        15003,
        10108,
        28324,
        15368,
        45641,
        9319,
        1543,
        50830
      ],
      "temperature": 0,
      "avg_logprob": -0.1538761226275495,
      "compression_ratio": 1.4490566037735848,
      "no_speech_prob": 1.562527190968055e-11,
      "source": "whisper"
    },
    {
      "id": 11,
      "seek": 5500,
      "start": 64.3,
      "end": 66.9,
      "text": "下载下来后啊,打开。",
      "tokens": [
        50830,
        4438,
        17819,
        121,
        4438,
        6912,
        13547,
        4905,
        11,
        12467,
        18937,
        1543,
        50960
      ],
      "temperature": 0,
      "avg_logprob": -0.1538761226275495,
      "compression_ratio": 1.4490566037735848,
      "no_speech_prob": 1.562527190968055e-11,
      "source": "whisper"
    },
    {
      "id": 12,
      "seek": 5500,
      "start": 66.9,
      "end": 69.9,
      "text": "可以看到啊,所有文本都在里面了。",
      "tokens": [
        50960,
        6723,
        18032,
        4905,
        11,
        39300,
        17174,
        8802,
        7182,
        3581,
        15759,
        8833,
        2289,
        1543,
        51110
      ],
      "temperature": 0,
      "avg_logprob": -0.1538761226275495,
      "compression_ratio": 1.4490566037735848,
      "no_speech_prob": 1.562527190968055e-11,
      "source": "whisper"
    },
    {
      "id": 13,
      "seek": 5500,
      "start": 69.9,
      "end": 78.8,
      "text": "所以这个工具啊,就是专制那些内容拷贝下载动不动就需要你充会员了,需要你交费了,这样的一些流氓呢。",
      "tokens": [
        51110,
        7239,
        15368,
        23323,
        39806,
        4905,
        11,
        5620,
        940,
        241,
        25491,
        4184,
        13824,
        34742,
        25750,
        6852,
        115,
        18464,
        251,
        4438,
        17819,
        121,
        34961,
        1960,
        34961,
        3111,
        35748,
        2166,
        2347,
        227,
        12949,
        3606,
        246,
        2289,
        11,
        35748,
        2166,
        28455,
        18464,
        117,
        2289,
        11,
        21209,
        1546,
        38515,
        27854,
        6610,
        241,
        6240,
        1543,
        51555
      ],
      "temperature": 0,
      "avg_logprob": -0.1538761226275495,
      "compression_ratio": 1.4490566037735848,
      "no_speech_prob": 1.562527190968055e-11,
      "source": "whisper"
    },
    {
      "id": 14,
      "seek": 7880,
      "start": 78.8,
      "end": 82.1,
      "text": "好,大家觉得有用的话,点赞,关注,分享,支持一下吧。",
      "tokens": [
        50365,
        2131,
        11,
        6868,
        29992,
        2412,
        9254,
        44575,
        11,
        12579,
        5266,
        252,
        11,
        28053,
        26432,
        11,
        30855,
        11,
        35488,
        8861,
        6062,
        1543,
        50530
      ],
      "temperature": 0,
      "avg_logprob": -0.43980332003294964,
      "compression_ratio": 3.3516483516483517,
      "no_speech_prob": 1.5469497210984784e-11,
      "source": "whisper"
    },
    {
      "id": 15,
      "seek": 7880,
      "start": 82.1,
      "end": 86.099625,
      "text": "谢谢。",
      "tokens": [
        50530,
        19879,
        1543,
        50730
      ],
      "temperature": 0,
      "avg_logprob": -0.43980332003294964,
      "compression_ratio": 3.3516483516483517,
      "no_speech_prob": 1.5469497210984784e-11,
      "source": "whisper"
    }
  ],
  "transcript_selection": {
    "schema": "videonote.transcript_selection.v1",
    "status": "SELECTED",
    "requested_language": "zh",
    "duration": 86.099625,
    "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": 16,
      "multilingual": false,
      "first_start": 0.0,
      "final_end": 86.1,
      "duration_coverage": 1.0,
      "maximum_gap_seconds": 0.0,
      "inverted_count": 0,
      "language": {
        "requested": "zh",
        "matched": true,
        "latin": 13,
        "han": 384,
        "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": 86.1,
      "rejected_segment_count": 0,
      "rejected_segments": []
    }
  },
  "presegmentation_correction": {
    "applied": true,
    "correction_count": 3,
    "deterministic_fix_count": 0
  }
}