yl4579 / StarGANv2-VC

StarGANv2-VC: A Diverse, Unsupervised, Non-parallel Framework for Natural-Sounding Voice Conversion
MIT License
466 stars 110 forks source link

RuntimeError: Argument #4: Padding size should be less than the corresponding input dimension, but got: padding (1024, 1024) at dimension 2 of input [1, 400401, 2] #85

Closed yurong58 closed 1 year ago

yurong58 commented 1 year ago

Hi, thank you for this amazing contribution and works. I encounter a problem when I want to train with my own datasets. I didn't change the original dataset but only adding another file to the Data. The difference is my audio is in Chinese, I am not sure if this is the reason why it appears this error. And also my audio size is larger than those you provided. I have changed the num_domain in config_yml from 20 to 21 too. Please help me with this error. Big thanks! Screenshot from 2023-05-01 18-15-57

yl4579 commented 1 year ago

I'm sorry but the error you provided was quite unclear. Could you please tell me what line in which file did this problem occur?

yurong58 commented 1 year ago

I have solved this error, thanks!