{ "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.", "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 今天陪你讀書也聊聊你的故事", "words": [ { "word": "你好", "start": 4.520000000000001, "end": 5.000000000000001, "probability": 0.4759526252746582 }, { "word": " 我是", "start": 5.000000000000001, "end": 5.48, "probability": 0.6711855530738831 }, { "word": "芝", "start": 5.48, "end": 5.84, "probability": 0.7062749713659286 }, { "word": "薇", "start": 5.84, "end": 5.94, "probability": 0.8936715126037598 }, { "word": " 今天", "start": 6.9, "end": 7.12, "probability": 0.992720365524292 }, { "word": "陪", "start": 7.12, "end": 7.3, "probability": 0.992363840341568 }, { "word": "你", "start": 7.3, "end": 7.5, "probability": 0.9828341007232666 }, { "word": "讀", "start": 7.5, "end": 7.6, "probability": 0.8002204596996307 }, { "word": "書", "start": 7.6, "end": 8.02, "probability": 0.9620335102081299 }, { "word": "也", "start": 8.02, "end": 8.52, "probability": 0.518186628818512 }, { "word": "聊", "start": 8.52, "end": 8.7, "probability": 0.99346524477005 }, { "word": "聊", "start": 8.7, "end": 8.86, "probability": 0.9723032116889954 }, { "word": "你的", "start": 8.86, "end": 9.12, "probability": 0.9830270409584045 }, { "word": "故", "start": 9.12, "end": 9.4, "probability": 0.9992664456367493 }, { "word": "事", "start": 9.4, "end": 9.6, "probability": 0.9996438026428223 } ], "asr_start": 4.520000000000001, "asr_end": 9.6, "speech_timing_description": "ASR 估计 4.52–9.60 秒（跨度 5.08 秒）", "visual_observation": "抽帧可见从读书转向镜头，4.5 秒时已张口；人物、衣服和桌面物件保持可辨认。说话时微笑和口部张幅较大。", "audio_signal": { "peak": 1.307417869567871, "samples_at_or_above_full_scale": 1713, "first_five_seconds_rms": 0.13370922207832336, "final_five_seconds_rms": 0.33520373702049255, "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": 4.520000000000001, "end": 5.000000000000001, "probability": 0.44559162855148315 }, { "word": " 我是", "start": 5.000000000000001, "end": 5.48, "probability": 0.7207739949226379 }, { "word": "芝", "start": 5.48, "end": 5.84, "probability": 0.7476098537445068 }, { "word": "薇", "start": 5.84, "end": 5.94, "probability": 0.8984614014625549 }, { "word": " 今天", "start": 6.9, "end": 7.12, "probability": 0.9930223822593689 }, { "word": "陪", "start": 7.12, "end": 7.3, "probability": 0.9927383959293365 }, { "word": "你", "start": 7.3, "end": 7.5, "probability": 0.9851257801055908 }, { "word": "读", "start": 7.5, "end": 7.62, "probability": 0.8166076242923737 }, { "word": "书", "start": 7.62, "end": 8.0, "probability": 0.9992983341217041 }, { "word": "也", "start": 8.0, "end": 8.52, "probability": 0.6091889142990112 }, { "word": "聊", "start": 8.52, "end": 8.7, "probability": 0.9844983220100403 }, { "word": "聊", "start": 8.7, "end": 8.86, "probability": 0.9824956655502319 }, { "word": "你的", "start": 8.86, "end": 9.12, "probability": 0.9911148548126221 }, { "word": "故", "start": 9.12, "end": 9.4, "probability": 0.9988242983818054 }, { "word": "事", "start": 9.4, "end": 9.56, "probability": 0.9993960857391357 } ], "asr_start": 4.520000000000001, "asr_end": 9.56, "speech_timing_description": "ASR 估计 4.52–9.56 秒（跨度 5.04 秒）", "visual_observation": "抽查帧中的转头时序、构图与持书动作和原精度四步接近，未看到明显的整体质量跃升；局部细节仍需看原始视频。", "audio_signal": { "peak": 1.3405354022979736, "samples_at_or_above_full_scale": 1511, "first_five_seconds_rms": 0.13235589861869812, "final_five_seconds_rms": 0.3318886160850525, "finite": true } }, { "id": "deployed-4step", "label": "上线四步配置", "recognized": "你好 我是芝薇 今天陪你讀書也聊聊你的故事", "words": [ { "word": "你好", "start": 4.52, "end": 5.0, "probability": 0.5006723999977112 }, { "word": " 我是", "start": 5.0, "end": 5.48, "probability": 0.6925023794174194 }, { "word": "芝", "start": 5.48, "end": 5.84, "probability": 0.7152585983276367 }, { "word": "薇", "start": 5.84, "end": 5.96, "probability": 0.9045699238777161 }, { "word": " 今天", "start": 6.2, "end": 7.12, "probability": 0.9938246011734009 }, { "word": "陪", "start": 7.12, "end": 7.3, "probability": 0.9933652281761169 }, { "word": "你", "start": 7.3, "end": 7.5, "probability": 0.9855194091796875 }, { "word": "讀", "start": 7.5, "end": 7.6, "probability": 0.7456988096237183 }, { "word": "書", "start": 7.6, "end": 8.12, "probability": 0.9652389287948608 }, { "word": "也", "start": 8.12, "end": 8.54, "probability": 0.5430667996406555 }, { "word": "聊", "start": 8.54, "end": 8.72, "probability": 0.994694173336029 }, { "word": "聊", "start": 8.72, "end": 8.88, "probability": 0.9724268317222595 }, { "word": "你的", "start": 8.88, "end": 9.12, "probability": 0.983274519443512 }, { "word": "故", "start": 9.12, "end": 9.4, "probability": 0.9991660118103027 }, { "word": "事", "start": 9.4, "end": 9.64, "probability": 0.9996378421783447 } ], "asr_start": 4.52, "asr_end": 9.64, "speech_timing_description": "ASR 估计 4.52–9.64 秒（跨度 5.12 秒）", "visual_observation": "抽查帧中保持了书斋构图、持书动作和对镜头说话；面部轮廓、口部动作与发丝局部细节和原精度组有细微差别。", "audio_signal": { "peak": 0.9693443775177002, "samples_at_or_above_full_scale": 0, "first_five_seconds_rms": 0.0929427519440651, "final_five_seconds_rms": 0.22446703910827637, "finite": true } } ], "visual_review_scope": "Observed six source frames at 0.5, 2.5, 4.5, 5.5, 7.5 and 9.5 seconds and full-resolution 7.5-second frames. No frame-by-frame lip-sync or perceptual ranking is claimed.", "name_transcription_note": "The requested name is 知微; Whisper transcribes the homophone 芝薇. This alone does not establish a spoken pronunciation error." }