Rafael Valle
Rafael Valle
Hi! I noticed that the generated TextGrid files disregard case of the provided text, i.e. everything is set to lower case. Is there a flag to change this behavior?
How does the binary 'lib/align' handle entries in the dictionary with multiple values ? For example: ``` A EY1 A(1) AH1 ```
Looking at the code I only see training loss. Is there any routine that saves both training and validation loss?
I'm hitting the error below when using using the code with a different generator and optimizer. Python3 and tensorflow 1.3.0. with any number between 2 or 4 gpus. The error...
This is more of a doubt than an issue. Why you don't add batch norm to the last layer of your discriminator and generator?
currently, the download page only provides information about the compression algorithm, i.e. MP3, but provides no information about the sampling rate and bit depth of the audio file. it would...
Thank you for making this repo. I've attached a jupyter notebook with an implementation of the wavelet transform and inverse for F0 based on the implementation used in the FastSpeech2...
hey @riverphoenix, thanks for sharing your work. Where you able to get proper attention alignment with the code in your repo? If so, at what loss and number of iterations?
hi! thank you for your work it will be helpful to our community if you upload your model to google drive instead of baidu given that the download process is...
Any solution on the error below? **E tensorflow/core/common_runtime/executor.cc:594] Executor failed to create kernel. Invalid argument: CPU BiasOp only supports NHWC.**