=== SHIRE RAY OPENVOICE PROFILE EXTRACTION ===
UTC: 2026-08-03T07:24:17+00:00
Plaintext workspace: RAM-backed /dev/shm
PASS: Archive contains exactly 10 WAV files and the matching manifest.
PASS: All 10 WAV hashes and properties verified (46.951s).
/home/ray/ARMOR/voice/runtime/openvoice-v1/lib/python3.12/site-packages/torch/nn/utils/weight_norm.py:143: FutureWarning: `torch.nn.utils.weight_norm` is deprecated in favor of `torch.nn.utils.parametrizations.weight_norm`.
  WeightNorm.apply(module, name, dim)
/home/ray/ARMOR/voice/runtime/openvoice-v1/lib/python3.12/site-packages/torch/functional.py:704: UserWarning: stft with return_complex=False is deprecated. In a future pytorch release, stft will return complex tensors for all inputs, and return_complex=False will raise an error.
Note: you can still call torch.view_as_real on the complex output to recover the old return format. (Triggered internally at ../aten/src/ATen/native/SpectralOps.cpp:873.)
  return _VF.stft(  # type: ignore[attr-defined]
Loaded checkpoint '/home/ray/ARMOR/voice/models/MyShell-OpenVoice-official/checkpoints/converter/checkpoint.pth'
missing/unexpected keys: [] []
PASS: Ray speaker embedding extracted and reloaded successfully.
Embedding shape: [1, 256, 1]
Watermark network: disabled

PASS: Ray OpenVoice speaker profile extracted.
Embedding: /home/ray/ARMOR/voice/profiles/ray-authorised-v1/openvoice-v1-target-se.pth
Embedding SHA-256: 7922e34f45f456270226e0a7465e3b11edc99aafbe19bd79aa55a739c16b013c
Metadata: /home/ray/ARMOR/voice/profiles/ray-authorised-v1/openvoice-v1-target-se.json
Evidence: /SHiREVault/Backup/OSBackups/SHIRE-VOICE-RAY-PROFILE-EXTRACTION-20260803T072417Z
PASS: All temporary plaintext audio was removed from RAM.
PASS: Encrypted dataset remains unchanged.
PASS: Sentinel remains protected and was not restarted.
Academy unchanged. Forge remains locked.
No synthetic audio was generated.