search

lshqqytiger / ZLUDA

CUDA on AMD GPUs
Apache License 2.0
249 stars 32 forks source link

RuntimeError: cuFFT error: CUFFT_NOT_SUPPORTED #8

Open Bocchi-Chan2023 opened 5 months ago

Bocchi-Chan2023 commented 5 months ago

File "C:\Users[username]\Downloads\RVC1006Nvidia\infer\modules\vc\modules.py", line 189, in vc_single audio_opt = self.pipeline.pipeline( File "C:\Users[username]\Downloads\RVC1006Nvidia\infer\modules\vc\pipeline.py", line 358, in pipeline pitch, pitchf = self.get_f0( File "C:\Users[username]\Downloads\RVC1006Nvidia\infer\modules\vc\pipeline.py", line 158, in get_f0 f0 = self.model_rmvpe.infer_from_audio(x, thred=0.03) File "C:\Users[username]\Downloads\RVC1006Nvidia\infer\lib\rmvpe.py", line 597, in infer_from_audio mel = self.mel_extractor( File "C:\Users[username]\Downloads\RVC1006Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 1511, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "C:\Users[username]\Downloads\RVC1006Nvidia\runtime\lib\site-packages\torch\nn\modules\module.py", line 1520, in _call_impl return forward_call(args, **kwargs) File "C:\Users[username]\Downloads\RVC1006Nvidia\infer\lib\rmvpe.py", line 472, in forward fft = torch.stft( File "C:\Users[username]\Downloads\RVC1006Nvidia\runtime\lib\site-packages\torch\functional.py", line 660, in stft return _VF.stft(input, n_fft, hop_length, win_length, window, # type: ignore[attr-defined] RuntimeError: cuFFT error: CUFFT_NOT_SUPPORTED

Traceback (most recent call last): File "C:\Users[username]\Downloads\RVC1006Nvidia\runtime\lib\site-packages\gradio\routes.py", line 321, in run_predict output = await app.blocks.process_api( File "C:\Users[username]\Downloads\RVC1006Nvidia\runtime\lib\site-packages\gradio\blocks.py", line 1007, in process_api data = self.postprocess_data(fn_index, result["prediction"], state) File "C:\Users[username]\Downloads\RVC1006Nvidia\runtime\lib\site-packages\gradio\blocks.py", line 953, in postprocess_data prediction_value = block.postprocess(prediction_value) File "C:\Users[username]\Downloads\RVC1006Nvidia\runtime\lib\site-packages\gradio\components.py", line 2076, in postprocess processing_utils.audio_to_file(sample_rate, data, file.name) File "C:\Users[username]\Downloads\RVC1006Nvidia\runtime\lib\site-packages\gradio\processing_utils.py", line 206, in audio_to_file data = convert_to_16_bit_wav(data) File "C:\Users[username]\Downloads\RVC1006Nvidia\runtime\lib\site-packages\gradio\processing_utils.py", line 219, in convert_to_16_bit_wav if data.dtype in [np.float64, np.float32, np.float16]: AttributeError: 'NoneType' object has no attribute 'dtype'

lshqqytiger commented 5 months ago

We have cufft.dll in release, and you can replace it with torch's. However, I think it will complain about cufftw.

Bocchi-Chan2023 commented 5 months ago

We have cufft.dll in release, and you can replace it with torch's. However, I think it will complain about cufftw.

I got this error after replacing it. Perhaps it is a problem with cufftw. (I got that error by trying to get the program to run without cufftw) Sorry for the lack of information. This is the error that appears when only replacing cufft and nvrtc, cusparse and cublas;

C:\Users[username]\Downloads\RVC1006Nvidia>runtime\python.exe infer-web.py --pycmd runtime\python.exe --port 7897 Traceback (most recent call last): File "C:\Users[username]\Downloads\RVC1006Nvidia\infer-web.py", line 7, in from infer.modules.vc.modules import VC File "C:\Users[username]\Downloads\RVC1006Nvidia\infer\modules\vc\modules.py", line 8, in import torch File "C:\Users[username]\Downloads\RVC1006Nvidia\runtime\lib\site-packages\torch__init__.py", line 130, in raise err OSError: [WinError 127] The specified procedure could not be found. Error loading "C:\Users[username]\Downloads\RVC1006Nvidia\runtime\lib\site-packages\torch\lib\cufftw64_10.dll" or one of its dependencies.