this comes at feature extraction

[torn oar]

['extractf0print.py', 'C:\Mangio-RVC-v23.7.0/logs/BachelorBBY', '11', 'rmvpe', '64']
f0fail-32-C:\Mangio-RVC-v23.7.0/logs/BachelorBBY/1_16k_wavs/1_203.wav-Traceback (most recent call last):
File "C:\Mangio-RVC-v23.7.0\extract_f0_print.py", line 383, in go
featur_pit = self.compute_f0(
File "C:\Mangio-RVC-v23.7.0\extract_f0_print.py", line 244, in compute_f0
self.model_rmvpe = RMVPE("rmvpe.pt", is_half=False, device="cuda:0")
File "C:\Mangio-RVC-v23.7.0\rmvpe.py", line 345, in __init
self.mel_extractor = MelSpectrogram(
File "C:\Mangio-RVC-v23.7.0\runtime\lib\site-packages\torch\nn\modules\module.py", line 1145, in to
return self._apply(convert)
File "C:\Mangio-RVC-v23.7.0\runtime\lib\site-packages\torch\nn\modules\module.py", line 844, in _apply
self._buffers[key] = fn(buf)
File "C:\Mangio-RVC-v23.7.0\runtime\lib\site-packages\torch\nn\modules\module.py", line 1143, in convert
return t.to(device, dtype if t.is_floating_point() or t.is_complex() else None, non_blocking)
RuntimeError: CUDA error: CUDA-capable device(s) is/are busy or unavailable
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with TORCH_USE_CUDA_DSA to enable device-side assertions.

[last blaze]

what GPU do you have

[torn oar]

geforce rtx 3060 ti

[echo sky]

seems like some corrupt files or driver issue, or some occasional race condition issue (then try again)