WaveRNN-Pytorch

WaveRNN-Pytorch copied to clipboard

hello,when i use C++ inference, i got the speed about 7s. how can i speed up the inference speed, thank you.

li-xx-5

C++ infer

23

hi @geneing ! I used the C++ code for infer! but the speed is so slowly mels shape: (80, 500) take times:53.759968996047974 Seven seconds of audio takes about 53 seconds！...

maozhiqiang

@geneing hi, may i ask how to use the C++inference，thank you

1

@geneing hi, may i ask how to use the C++inference，thank you _Originally posted by @doctor-xiang in https://github.com/geneing/WaveRNN-Pytorch/issues/5#issuecomment-508069817_

1105060120

Looking at the other `loadNext` functions, I'm pretty sure this line should be here

serg06

C++ Vocoder issue - possibly memory allocation

2

Hi @geneing First of all, congratulations on this awesome work! I've been experiencing a possible bug in the c++ implementation. I tried the model on a couple of machines at...

tiberiu44

Target vocoder links to target "Eigen3::Eigen" but the target was not found.

3

hello,everyone.i met this erro. Target"Vocoder"links to target "Eigen3::Eigen" but the target was not found.Perhaps a find_packages() call is missing for an IMPORTED target, or an ALIAS target is missing? How...

li-xx-5

Hello, everyone. Now I am synthesizing a 9s speech file, which needs about 2s, but there is no sound in the synthesized file.i dont know the reason.thank you

li-xx-5

Getting error for training with Tacotron

14

I have used this (https://github.com/Rayhane-mamah/Tacotron-2) implementation for pre-processing. And when I write command for training `python3 train.py --dataset Tacotron training_data` And getting this error ``` x = torch.cat([x.unsqueeze(-1), mels, a1[:,:,:-1]],...

rishikksh20

FYI

begeekmyfriend

Simplified upsampling

3

Hi @geneing, thanks for all your hard work! I was wondering why you decided to abandon the simplified upsampling in your model_simplification branch. Was the audio quality significantly worse?

bshall