-
Hi, I am currently training a wavernn, however, it's hard to train. Have you ever trained a good model? Would you mind to share your loss curve at training phase.
-
For testing, I use mulaw(8bit) and raw(16bit).
1. After I have run 'Python wavenet_preprocess.py', I can get these files.
 computing linear loss, `num_mels` should have been `num_freq`. See Keith Ito's [version](h…
-
**URL**: https://r9y9.github.io/wavenet_vocoder/
**Browser / Version**: Firefox 60.0
**Operating System**: Ubuntu
**Tested Another Browser**: Yes
**Problem type**: Video or audio doesn't play
**…
-
Can we use wavernn to make TTS, what is the input, thank you
-
It seems the decreasing of loss during WaveNet training unsteady. Is it all right for the results or should I wait more steps? The predicted wavs under `logs-WaveNet/wavs` sound OK but the ones under …
-
is there a module to replace the "lws"?
-
I'm just starting to use the project and I was on English until now. But my goal is to make a voice in German and/or french. Both languages contain some specifics characters (for example: à é è ä ö ü …
-
As I understand it, the difference between Google's model and the pretrained available here is the quality and size of the training set.
Would it be possible to take a high quality long librivox re…
-
First of all, thank you for great implementation of Tacotron 2. I'm trying to training Vietnamese language with my own dataset. The dataset is 22.05kHz, about 6 hours, already trimmed all silence. But…