WaveGrad

WaveGrad copied to clipboard

Could you provide the evaluation code ? Thank you.

zzw-zwzhang

Audio quality improvements

6

Hi, awesome contribution for TTS community :) I am wondering, did you manage to train a model that would have higher audio quality than the pretrained checkpoint provided with this...

janvainer

Poor Synthesis Quality on 44k Sample Rate

1

Hello, I have two somewhat identical datasets with similar samples. I have trained the WaveGrad with 22k sample rate audios and it is quite good. However, the synthesis quality for...

Malik7115

Hi, when training with f_max = 10000 there is a static noise introduced in the model. We are using our custom dataset. Is there any way to improve upon this?...

Malik7115

I'm fortunate enough to have a machine with an NVIDIA RTX 3090 GPU. However, the GPU-enabled binary versions of PyTorch 1.6.0 available from the PyTorch project won't run on the...

znmeb

slow training in single GPU

1

Huge thanks for implement! I have a question regarding the training time in the single GPU you mentioned. I did the same training procedure in batch size 96 on the...

guanamusic

Interpolation and Conv order in Upsample module

1

Hi, I noticed that in upsampling block, the code does Conv1dWithInitialization and then InterpolationBlock. [code link](https://github.com/ivanvovk/WaveGrad/blob/721c37c216132a2ef0a16adc38439f993998e0b7/model/upsampling.py#L61) But in paper network structure it looks like the reverse order of yours. ...

softrimewu

dilation update

1

I simply updated configs as https://github.com/ivanvovk/WaveGrad/issues/22#issue-938334999.

junjun3518

The order of upsampling_dilations

1

Hi! My name is Junhyeok Lee and I appreciate your works! Maybe I found a slight mistake in your config file. https://github.com/ivanvovk/WaveGrad/blob/721c37c216132a2ef0a16adc38439f993998e0b7/configs/default.json#L6-L12 In Wavegrad Appendix A, they mentioned "The dilation...

junjun3518

How to make it work with TPU?

2

Thank you for releasing the great project. I'd like to train on TPU(v3) on Google Cloud, how can I change the code to make it work?

mulgray