Why all the sounds I generate are noise？

[Moonmore]

I followed all the steps in the readme to complete the data preprocessing and model training. Why is the final generated voice empty?

[leminhnguyen]

Hi @Moonmore Please check the training voice, it should be 22050Hz, 1 channel (mono) and 16 bit-depth.

[Moonmore]

Hi @Moonmore Please check the training voice, it should be 22050Hz, 1 channel (mono) and 16 bit-depth.

I refer to the aishell3 dataset used by the author. Then I again determined the composition of the training data.it is 22050khz，mono and 16 bit. I’m sorry I have a problem uploading pictures here.

[lee9871]

how do you deal this problem

[lee9871]

i have same problem

[Moonmore]

i have same problem

Refactoring the code.

[azman-i]

can you please elaborate the solution @Moonmore?