about train

[qianxixi908]

Hello, I tried to run the train but it showed the following :

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

could you give me some advice on how to solve it ? thanks.

[KimythAnly]

Hi, what dataset did you use?

[qianxixi908]

Thank you for your reply. I used the default dataset ,vctk.

[KimythAnly]

Did you correctly preprocess the data? The folder structure is like

data/features/vctk/mel
├── p225_001.wav.npy
├── p225_002.wav.npy
├── p225_003.wav.npy
...

[qianxixi908]

Thanks for your answer.

Yes, I have handled it as you said. I even used your original sample directly to see if the code can run, but the same error is still reported. And when debugging, the following problems were found:

“config. assert isinstance('dataset'(2083686355952), )object 'dataset' (2083686355952).'feat_path' (2083686356976)”SyntaxError: invalid syntax

[KimythAnly]

Hi, how about the file data/indexes/vctk/indexes.pkl? Its type is dict and contains two keys train and dev while the values are like p311_198.wav.npy.

[qianxixi908]

Hello, thank you for your previous answer. Can you provide some details or codes about the speaker classifier mentioned in the experimental part of the article?

[KimythAnly]

Hi, here is the speaker classifier. It might be slightly different from the one we used in this ariticle due to some code refactoring, but the result should be similar. c_in: The dimension of the content/speaker embedding c_h: We set it to 128. c_out: The number of speakers, which is 80 in this paper.

import torch.nn as nn
from einops import rearrange

class Classifier(nn.Module):
    def __init__(self, c_in, c_h, c_out):
        super(Classifier, self).__init__()
        self.in_layer = nn.Linear(c_in, c_h)
        self.conv_relu_block = nn.Sequential(
            nn.Conv1d(c_h, c_h, 3),
            nn.ReLU(),
            nn.Conv1d(c_h, c_h, 3),
            nn.ReLU(),
            nn.Conv1d(c_h, c_h, 3),
            nn.ReLU(),
        )
        self.out_layer = nn.Linear(c_h, c_out)

    def forward(self, x):
        """
        x: (n, c, t)
        """
        x = rearrange(x, 'n c t -> n t c')
        y = self.in_layer(x)
        y = rearrange(y, 'n t c -> n c t')
        y = self.conv_relu_block(y)
        y = y.mean(-1)
        y = self.out_layer(y)
        return y