{
  "scope": "CPU Whisper small word timestamps and full decoded audio diagnostics; not a lip-sync or human listening score. Decoded AAC samples above full scale can be codec overshoot and do not alone prove waveform clipping. Visual observations inspect six source frames per arm (0.5, 2.5, 4.5, 5.5, 7.5 and 9.5 seconds); proper-name spellings are ASR output, not a verified pronunciation error.",
  "expected_dialogue": "你好，我是知微。今天陪你读书，也聊聊你的故事。",
  "target_speech_interval_seconds": [
    5,
    10
  ],
  "arms": [
    {
      "id": "lightx2v-original-4step",
      "label": "LightX2V 原精度四步",
      "recognized": "你好 我是芝薇今天陪你读书也聊聊你的故事",
      "words": [
        {
          "word": "你好",
          "start": 4.460000000000001,
          "end": 4.98,
          "probability": 0.468161940574646
        },
        {
          "word": " 我是",
          "start": 4.98,
          "end": 5.5,
          "probability": 0.7206525802612305
        },
        {
          "word": "芝",
          "start": 5.5,
          "end": 5.84,
          "probability": 0.7214449346065521
        },
        {
          "word": "薇",
          "start": 5.84,
          "end": 5.94,
          "probability": 0.8910984992980957
        },
        {
          "word": "今天",
          "start": 6.6000000000000005,
          "end": 7.12,
          "probability": 0.6985118389129639
        },
        {
          "word": "陪",
          "start": 7.12,
          "end": 7.3,
          "probability": 0.9931080043315887
        },
        {
          "word": "你",
          "start": 7.3,
          "end": 7.5,
          "probability": 0.9807112812995911
        },
        {
          "word": "读",
          "start": 7.5,
          "end": 7.62,
          "probability": 0.7816160023212433
        },
        {
          "word": "书",
          "start": 7.62,
          "end": 8.0,
          "probability": 0.9993934035301208
        },
        {
          "word": "也",
          "start": 8.0,
          "end": 8.52,
          "probability": 0.5443407893180847
        },
        {
          "word": "聊",
          "start": 8.52,
          "end": 8.7,
          "probability": 0.9916449189186096
        },
        {
          "word": "聊",
          "start": 8.7,
          "end": 8.86,
          "probability": 0.9798868894577026
        },
        {
          "word": "你的",
          "start": 8.86,
          "end": 9.12,
          "probability": 0.9922010898590088
        },
        {
          "word": "故",
          "start": 9.12,
          "end": 9.4,
          "probability": 0.9988248944282532
        },
        {
          "word": "事",
          "start": 9.4,
          "end": 9.6,
          "probability": 0.9994959831237793
        }
      ],
      "asr_start": 4.460000000000001,
      "asr_end": 9.6,
      "speech_timing_description": "ASR 估计 4.46–9.60 秒（跨度 5.14 秒）",
      "visual_observation": "抽帧可见由低头读书转为面对镜头，4.5 秒时已张口。后半段口部动作和微笑较明显，书本、服饰与桌面茶具保持可辨认。",
      "audio_signal": {
        "peak": 1.3414987325668335,
        "samples_at_or_above_full_scale": 1020,
        "first_five_seconds_rms": 0.1280062198638916,
        "final_five_seconds_rms": 0.30663004517555237,
        "finite": true
      }
    },
    {
      "id": "minimax-original-50step",
      "label": "MiniMax-H3 原版 50 步",
      "recognized": "你好 我是芝薇今天陪你读书也聊聊你的故事",
      "words": [
        {
          "word": "你好",
          "start": 4.440000000000001,
          "end": 4.960000000000001,
          "probability": 0.5100014805793762
        },
        {
          "word": " 我是",
          "start": 4.960000000000001,
          "end": 5.48,
          "probability": 0.7007771134376526
        },
        {
          "word": "芝",
          "start": 5.48,
          "end": 5.84,
          "probability": 0.7508285343647003
        },
        {
          "word": "薇",
          "start": 5.84,
          "end": 5.92,
          "probability": 0.8969546854496002
        },
        {
          "word": "今天",
          "start": 6.6000000000000005,
          "end": 7.12,
          "probability": 0.7370511889457703
        },
        {
          "word": "陪",
          "start": 7.12,
          "end": 7.3,
          "probability": 0.9939956068992615
        },
        {
          "word": "你",
          "start": 7.3,
          "end": 7.5,
          "probability": 0.9851073622703552
        },
        {
          "word": "读",
          "start": 7.5,
          "end": 7.62,
          "probability": 0.8739420771598816
        },
        {
          "word": "书",
          "start": 7.62,
          "end": 8.0,
          "probability": 0.9994166195392609
        },
        {
          "word": "也",
          "start": 8.0,
          "end": 8.52,
          "probability": 0.5786786079406738
        },
        {
          "word": "聊",
          "start": 8.52,
          "end": 8.7,
          "probability": 0.9862059950828552
        },
        {
          "word": "聊",
          "start": 8.7,
          "end": 8.86,
          "probability": 0.9825882911682129
        },
        {
          "word": "你的",
          "start": 8.86,
          "end": 9.12,
          "probability": 0.9916279315948486
        },
        {
          "word": "故",
          "start": 9.12,
          "end": 9.38,
          "probability": 0.9988558292388916
        },
        {
          "word": "事",
          "start": 9.38,
          "end": 9.58,
          "probability": 0.9994003772735596
        }
      ],
      "asr_start": 4.440000000000001,
      "asr_end": 9.58,
      "speech_timing_description": "ASR 估计 4.44–9.58 秒（跨度 5.14 秒）",
      "visual_observation": "抽帧可见先低头读书，再抬头面对镜头；4.5 秒时已张口，后半段保持正面交流姿态。书本和双手持续可见，窗格、茶具及衣袖纹理保持可辨认。",
      "audio_signal": {
        "peak": 1.3102874755859375,
        "samples_at_or_above_full_scale": 857,
        "first_five_seconds_rms": 0.12457426637411118,
        "final_five_seconds_rms": 0.2986317276954651,
        "finite": true
      }
    },
    {
      "id": "deployed-4step",
      "label": "上线四步配置",
      "recognized": "您好,我是芝薇。今天陪你读书,也聊聊你的故事。",
      "words": [
        {
          "word": "您",
          "start": 4.0200000000000005,
          "end": 4.5,
          "probability": 0.1568136364221573
        },
        {
          "word": "好,",
          "start": 4.5,
          "end": 4.72,
          "probability": 0.9907346963882446
        },
        {
          "word": "我是",
          "start": 5.34,
          "end": 5.5,
          "probability": 0.961224377155304
        },
        {
          "word": "芝",
          "start": 5.5,
          "end": 5.86,
          "probability": 0.6725572794675827
        },
        {
          "word": "薇。",
          "start": 5.86,
          "end": 5.92,
          "probability": 0.928257554769516
        },
        {
          "word": "今天",
          "start": 6.84,
          "end": 7.12,
          "probability": 0.9649995565414429
        },
        {
          "word": "陪",
          "start": 7.12,
          "end": 7.32,
          "probability": 0.9912581145763397
        },
        {
          "word": "你",
          "start": 7.32,
          "end": 7.5,
          "probability": 0.8851830363273621
        },
        {
          "word": "读",
          "start": 7.5,
          "end": 7.64,
          "probability": 0.8993741571903229
        },
        {
          "word": "书,",
          "start": 7.64,
          "end": 8.02,
          "probability": 0.9991107285022736
        },
        {
          "word": "也",
          "start": 8.42,
          "end": 8.56,
          "probability": 0.9915772676467896
        },
        {
          "word": "聊",
          "start": 8.56,
          "end": 8.7,
          "probability": 0.9841914176940918
        },
        {
          "word": "聊",
          "start": 8.7,
          "end": 8.86,
          "probability": 0.983761727809906
        },
        {
          "word": "你的",
          "start": 8.86,
          "end": 9.12,
          "probability": 0.9728408455848694
        },
        {
          "word": "故",
          "start": 9.12,
          "end": 9.42,
          "probability": 0.9982847571372986
        },
        {
          "word": "事。",
          "start": 9.42,
          "end": 9.6,
          "probability": 0.9994165897369385
        }
      ],
      "asr_start": 4.0200000000000005,
      "asr_end": 9.6,
      "speech_timing_description": "ASR 估计 4.02–9.60 秒（跨度 5.58 秒）",
      "visual_observation": "抽帧可见先读书，再面对镜头开口；后半段有明显口部动作与微笑。书本、衣袖、桌面物件保持可辨认；抽帧不能单独证明连续口型同步。",
      "audio_signal": {
        "peak": 0.9385237097740173,
        "samples_at_or_above_full_scale": 0,
        "first_five_seconds_rms": 0.08741135150194168,
        "final_five_seconds_rms": 0.213079035282135,
        "finite": true
      }
    }
  ]
}
