{
  "task": "P1_verification_v12_fixed",
  "fix": "V12: Removed double-padding bug from V11. extract_hubert_features() no longer adds extra 2s padding since run_inference() already handles it.",
  "date": "2026-04-09T01:08:22.753687",
  "model": "/Users/yanfenma/.openclaw/groups/workspace-oc_90142ae290925820dcbac9717011d4af/models/one_voice_rvc_v2_kaggle_v10.pth",
  "model_size_mb": 139.3,
  "pipeline": "edge-tts → HuBERT + pyworld → 2x interp → SynthesizerTrn [V12 FIXED]",
  "total_tests": 3,
  "successful": 3,
  "total_duration_sec": 29.88,
  "total_time_sec": 129.96,
  "tests": [
    {
      "test": "greeting",
      "style": "Casual greeting",
      "text": "Hello! I am One, the very first NumberBlock! I love counting and playing with all my friends!",
      "source_file": "/Users/yanfenma/.openclaw/groups/workspace-oc_90142ae290925820dcbac9717011d4af/output/p1_verification_v12_fixed/source/source_greeting.wav",
      "output_file": "/Users/yanfenma/.openclaw/groups/workspace-oc_90142ae290925820dcbac9717011d4af/output/p1_verification_v12_fixed/v12_test_greeting.wav",
      "source_duration_sec": 9.24,
      "duration_sec": 9.22,
      "duration_ratio": 1.0,
      "sample_rate": 40000,
      "f0_up_key": 0,
      "f0_method": "pyworld_harvest",
      "pipeline": "edge-tts → HuBERT(transformers) + pyworld → F.interpolate(2x) → SynthesizerTrnMs768NSFsid [V12 FIXED single-pad]",
      "inference_time_sec": 34.12,
      "model": "/Users/yanfenma/.openclaw/groups/workspace-oc_90142ae290925820dcbac9717011d4af/models/one_voice_rvc_v2_kaggle_v10.pth",
      "model_info": "RVC v2 official | 200 epochs | 6087 samples | Tesla P100-PCIE-16GB | cuda | V10",
      "status": "success"
    },
    {
      "test": "counting",
      "style": "Educational counting",
      "text": "One, two, three, four, five! Let's count together! One plus one equals two! That's math magic!",
      "source_file": "/Users/yanfenma/.openclaw/groups/workspace-oc_90142ae290925820dcbac9717011d4af/output/p1_verification_v12_fixed/source/source_counting.wav",
      "output_file": "/Users/yanfenma/.openclaw/groups/workspace-oc_90142ae290925820dcbac9717011d4af/output/p1_verification_v12_fixed/v12_test_counting.wav",
      "source_duration_sec": 11.21,
      "duration_sec": 11.2,
      "duration_ratio": 1.0,
      "sample_rate": 40000,
      "f0_up_key": 0,
      "f0_method": "pyworld_harvest",
      "pipeline": "edge-tts → HuBERT(transformers) + pyworld → F.interpolate(2x) → SynthesizerTrnMs768NSFsid [V12 FIXED single-pad]",
      "inference_time_sec": 36.87,
      "model": "/Users/yanfenma/.openclaw/groups/workspace-oc_90142ae290925820dcbac9717011d4af/models/one_voice_rvc_v2_kaggle_v10.pth",
      "model_info": "RVC v2 official | 200 epochs | 6087 samples | Tesla P100-PCIE-16GB | cuda | V10",
      "status": "success"
    },
    {
      "test": "emotional",
      "style": "Excited/emotional",
      "text": "I'm so happy today! The sun is shining and we're going to have a wonderful adventure! Let's go, everyone!",
      "source_file": "/Users/yanfenma/.openclaw/groups/workspace-oc_90142ae290925820dcbac9717011d4af/output/p1_verification_v12_fixed/source/source_emotional.wav",
      "output_file": "/Users/yanfenma/.openclaw/groups/workspace-oc_90142ae290925820dcbac9717011d4af/output/p1_verification_v12_fixed/v12_test_emotional.wav",
      "source_duration_sec": 9.48,
      "duration_sec": 9.46,
      "duration_ratio": 1.0,
      "sample_rate": 40000,
      "f0_up_key": 2,
      "f0_method": "pyworld_harvest",
      "pipeline": "edge-tts → HuBERT(transformers) + pyworld → F.interpolate(2x) → SynthesizerTrnMs768NSFsid [V12 FIXED single-pad]",
      "inference_time_sec": 38.07,
      "model": "/Users/yanfenma/.openclaw/groups/workspace-oc_90142ae290925820dcbac9717011d4af/models/one_voice_rvc_v2_kaggle_v10.pth",
      "model_info": "RVC v2 official | 200 epochs | 6087 samples | Tesla P100-PCIE-16GB | cuda | V10",
      "status": "success"
    }
  ]
}