search

r9y9 / deepvoice3_pytorch

PyTorch implementation of convolutional neural networks-based text-to-speech synthesis models
https://r9y9.github.io/deepvoice3_pytorch/
Other
1.97k stars 485 forks source link

Integer division error and multispeaker evaluation error #214

Closed ilyalasy closed 4 years ago

ilyalasy commented 4 years ago

Fixed two small bugs:

  1. Runtime Integer division error which is caused by line 669.
  2. Runtime cudnn assertion error when evaluating multispeaker model with less than 11 speakers. It is caused by hard-coded value here.