Error on Accompaniment and Vocal separation Tab

[FarshadGrayson]

Every time i try to use it , i get the same error , and no , my file doesn't have spaces or underlines in it's name .

Traceback (most recent call last): File "D:\RVC0813Nvidia\infer-web.py", line 345, in uvr pre_fun = func( File "D:\RVC0813Nvidia\infer_uvr5.py", line 40, in init model = model.half().to(device) File "D:\RVC0813Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 1145, in to return self._apply(convert) File "D:\RVC0813Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply module._apply(fn) File "D:\RVC0813Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply module._apply(fn) File "D:\RVC0813Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 797, in _apply module._apply(fn) [Previous line repeated 2 more times] File "D:\RVC0813Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 820, in _apply param_applied = fn(param) File "D:\RVC0813Nvidia\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: misaligned address 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.

[RVC-Boss]

what's your GPU?

[FarshadGrayson]

what's your GPU?

Nvidia RTX 3070 Ti

[FarshadGrayson]

no one can help me ???? i can't create datasets without this .