ide8 / tacotron2 Goto Github PK

After 750 epochs, we tested the created tacotron model via inference.ipynb and realized that for same input text sequence we get different generated output audio file. Additionally, there is always a large empty space at the beginning of the audio file of approximately 30 seconds. Just to mention, the data was previously preprocessed as explained in the readme file. Sometimes there is just a noise in the audio file, and the other times there is some speaking at the end of the audio file.
Do you have any experience with this issue?

hey it will be good, if you can share your pretrained model with proper alignment, i am training from scratch since 6 days and not getting any alignment

Hi

First of all, thanks for the repository.

I am trying to train another dataset in other language using this repository, and since I do not have any pretrained waveglow model I cannot train a new Tacotron2 model... Is there any way to perform Griffin Lim on the inferred Mel spectrograms? I am having some issues regarding tensor dimensionality and I did not manage to get any audio...

Thanks in advance

Ander

What dataset do you train & test your network? I cannt find any information about it except how to process data.