andabi / deep-voice-conversion

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

How to speed up in between epochs? #27

Closed VictoriaBentell closed 6 years ago

VictoriaBentell commented 6 years ago

Each step in train1 is nice and fast, but once the epoch is finished, it takes about 15 minutes to move onto the next epoch. Is there a known way to make this part faster? And what's going on here that takes so much time?

VictoriaBentell commented 6 years ago

Ok I got it, lowering the batch size down to 8 seems to speed this phase up significantly.