alokprasad / fastspeech_squeezewave Goto Github PK

Hi,
Which version of PyTorch , CUDA and cuDNN do you use? I always run into this error.
My setup:
Windows 10 Pro
python 3.6.5
torch 1.1.0
Cuda 10.0
cuDNN 7.6

I tried explicitly setting the device to 'cpu' in synthesis.py and fastspeech.py to try running just on cpu.
Also tried model.to(device) and also model arguments .to(device). Same issue happens in both FastSpeech and SqueezeWave for me.

Same result on ubuntu 18.04 with python 3.6.9, torch 1.5, cuda 10.2 and cudnn 8!

hello.when i convert this to onnx.i met this problem,how can i solve that.thank you .

Hello. Did the following lines of code in synthesis.py work for you?

# script for generating torch script
traced_script_module = torch.jit.trace(model, (sequence, src_pos))
traced_script_module.save("traced_fastspeech_model.pt")

I get the following error:

RuntimeError: 0 INTERNAL ASSERT FAILED at ..\torch\csrc\jit\ir\alias_analysis.cpp:318, please report a bug to PyTorch. We don't have an op for aten::to but it isn't a special case. Argument types: Tensor, None, int, Device, bool, bool, bool, int,

Thanks for your great work.
I trained my squeezewave model use original code，and trained on a single GPU and the training dataset is a public Chinese dataset, so I have got a pre_trained model. Now I want to run in CPU. So i use your code with my above pre_trained model. But I only can generate the wav use your test.pt in mel_spectrograms. When I generate the wav use my own data, I got a error. What is the difference between the mel_spectrograms/test.pt and my own mel spectrograms by mel2samp.py.

'SqueezeWave' object has no attribute 'upsample'

hello. when i run the denoiser.py . i met this erro. But when i run the denoiser.py in the waveglow. i can run that.How can i solve this
problem.thank you.

hello, when i use the denoiser.py. i met this erro.How can i solve that.thank you