search

andabi / deep-voice-conversion

Deep neural networks for voice conversion (voice style transfer) in Tensorflow
MIT License
3.92k stars 845 forks source link

Stuck when running train1 #47

Closed asssssasssssin closed 6 years ago

asssssasssssin commented 6 years ago

I have put the TIMIT dataset in './datasets', and set the corresponding datapath in 'default.yaml'.

When I ran 'python3 train1.py case', an error showed up looked like this: untitled Then it finally stuck at here: image

Does anyone have any idea to solve this problem? Please let me know. Thank you.

asssssasssssin commented 6 years ago

I used https://github.com/andabi/deep-voice-conversion/tree/ba7dab2fa603efbd2099c1ceba177f3668155664 , and modify by https://github.com/andabi/deep-voice-conversion/pull/30 , then it worked.

But it got acc: 0.0066193854, loss: 4.800442, at train1. I found it stop at epoch1 and done!

iamxiaoyubei commented 5 years ago

I used https://github.com/andabi/deep-voice-conversion/tree/ba7dab2fa603efbd2099c1ceba177f3668155664 , and modify by

30

, then it worked.

But it got acc: 0.0066193854, loss: 4.800442, at train1. I found it stop at epoch1 and done!

acc: 0.011408651 loss: 4.5185957 @asssssasssssin After doing your instruction, I also got the same problem with you. Have you solved it? Plz help me! Thank you!