pytorch-StarGAN-VC

pytorch-StarGAN-VC copied to clipboard

Given groups=1, weight of size [32, 5, 3, 9], expected input[4, 2, 36, 512] to have 5 channels, but got 2 channels instead

2

looking forward your reply

runningtosun

No files present when I run main.py

2

When I run main.py, I get the following error. Can you tell what is possibly wrong? Traceback (most recent call last): File "main.py", line 93, in main(config) File "main.py", line...

Husnain08

Why the audio "TM3-SF3_iter178000_200005.wav" in samples sound bad. it is the final model result?

aijianiula0601

Pretrained model

2

Could you please share pretrained model (200K iterations) on google drive?

marlon-br

RuntimeError: Assertion `cur_target >= 0 && cur_target < n_classes' failed

2

The number of parameters: 33428 Start training...... /usr/local/lib/python3.7/site-packages/torch/nn/modules/container.py:92: UserWarning: Implicit dimension choice for log_softmax has been deprecated. Change the call to include dim=X as an argument. input = module(input) Traceback...

yourlin

According to the original paper,  line 206 and 207 in solver.py should be changed into following: `out_cls = self.C(x_fake)` `g_loss_cls = CELoss(input=out_cls, target=speaker_idx_trg)` so that the g_loss_cls would train...

deeperlearner

Hi, nice work there, I just have an additional question. The author of the paper indicated that the inference time can be coded in real-time. But as far as I...

tranctan

ValueError: num_samples should be a positive integer value, but got num_samples=0

1

Can you guide how to resolve this issue?

Husnain08

code working fine for tensorflow v2 and fourspeakers directory wasn't used. Instead speakers was used. Made the necessary chnages. The entire code is working fine now.

kcirnez1211

Hi there, Thanks for the code. I am able to work with the code with 4 speakers in folders Speaker and Speaker_test but if I increase the number of the...

sainishalini