-
Is the code in this project still implemented with tacotron? I see that the encoder module in hparams.py still uses the cbhg module.
-
I've been working on reproducing [1806.04558](https://arxiv.org/pdf/1806.04558.pdf) as part of my master's thesis. I don't know if you're familiar with the paper, but it describes a framework based on…
-
After training the speech synthesiser for 100k epochs, I can't get it to synthesise due to this dimensions error. Could you help me with it please? Thanks in advance!
Using TensorFlow backend.
Com…
-
On and before **Feb 9, 2019**, the pytorch version is already 1.0.0
What I did:
virtualenv -p python3 vocoder
cd vocoder && . bin/activate
git clone https://github.com/r9y9/wavenet_vocoder && …
-
Hi,
I am currently working on parallel WaveNet and noticed that it is one of your planned TODOS.
Till now I can only generate wavs that are distinguishable but with a lot of noise. From my expe…
-
Hi,
Thanks so much for such a thorough implementation of WaveNet. I just wondered, do your default hparams channel sizes reflect those used in the final version of the original paper? I'm new to …
-
Hi,
many thanks for this great project.
I am trying to reproduce unconditional speech samples. Is it possible to achieve good sound quality (comparable to the samples provided by google's wavenet) …
-
Samples this repo sound too real to be true. What's the difference between these repos?
https://github.com/kan-bayashi/PytorchWaveNetVocoder
-
I trained this model with the default params and wavenet_params.json config file. Both the trained model generated wav file is white noise. The loss is around 1.563 after step 99999.
I meet the…
-
I have trained wavenet for a long time but the audio generated is too noisy (there is constant low-frequency noise). It strange because I have trained it in 5 different datasets before but no problem …