TransferLearning-CLVC icon indicating copy to clipboard operation
TransferLearning-CLVC copied to clipboard

missing of VCC_features.h5

Open chikiuso opened this issue 4 years ago • 0 comments

hi, I run the command :

python3 prepare_h5.py --mode 0 -vcc "training"

it created the file "VCC_audio.h5", but it seems the file " VCC_features.h5" is missing, is this file necessary? as the following error show when I run - python3 prepare_h5.py --mode 1 :

File "prepare_h5.py", line 62, in create_vcc_spk_h5 embedder = embedder.cuda().eval() if use_cuda else embedder.cpu().eval() File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 265, in cuda return self._apply(lambda t: t.cuda(device)) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/module.py", line 193, in _apply module._apply(fn) File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/rnn.py", line 127, in _apply self.flatten_parameters() File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/rnn.py", line 123, in flatten_parameters self.batch_first, bool(self.bidirectional)) RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED

thanks for your help.

chikiuso avatar Oct 07 '20 02:10 chikiuso