Immabot
January 28, 2020, 11:38am
1
Hey @erogol and TTS community
I’m trying to train the WaveRNN model for Tacotron2 which I’ve already trained
and i’m getting the following error.I cannot generate mel-spectrograms from the Tacotron2 model.
I’m getting the following error-
I think the dataset loader isn’t being created properly.Can you explain what the paths in below figures are supposed to be.
I’d appreciate any sorts of help on this.
Thanks!
Mike
erogol
(Egolge)
January 29, 2020, 10:48am
2
can you try the notebook on the latest dev branch? If it does not work either, then there is a bug.
Immabot
January 30, 2020, 10:03am
3
Hey @erogol ,It Worked.Thanks.Appreciate it.
But I encountered another problem while training the vocoder.
I checked the WaveRNN/config.json file.I didn’t find a variable named mulaw.
Can you help solve this?
Thanks!
erogol
(Egolge)
January 30, 2020, 10:05am
4
you can add mulaw field. It is just a json in the end.
Immabot
January 30, 2020, 10:15am
5
Hey @erogol ,
Actually there are 3 fields-
mulaw,use_aux_net and use_upsample_net.
What are it’s values supposed to be?
erogol
(Egolge)
January 30, 2020, 10:17am
6
can you link me the branch you use ?
erogol
(Egolge)
January 30, 2020, 10:18am
8
erogol
(Egolge)
January 30, 2020, 10:20am
9
otherwise, if you use auxnet, set use_aux_net=true
and use_upsample_net
likewise.
Immabot
January 30, 2020, 10:20am
10
Okay.
Thanks again.
Appreciate it.