-
i use LJSpeech with defult config .
i see this in config:
# This configuration requires 12 GB GPU memory and takes ~3 days on TITAN V.
and i want know how i can change config file for my 8gb gpu.
…
-
Recently Baidu [released](https://github.com/PaddlePaddle/Parakeet#pre-trained-models-and-audio-samples) mel2wav pretrained model which is close to WaveNet in terms of quality but much faster. Its con…
qo4on updated
4 years ago
-
It is mentioned in the paper that using more GPUs accelerates the training. I have three NVIDIA K80s and using the flags
`--nnodes 1 --nproc_per_node 3 -c`
Binds all three GPUs and ramps them u…
-
This must be the funniest bug report I ever made.
### Reproduction:
* Ryzen 7 3700 with 8 cores, 32 GB RAM
* Linux 64bit
* git clone TTS
* virtualenv
* build
* `pip install -U pip setuptools …
-
I observed a interesting behaviour after 138K iters where discriminator dominated the training and generator exploded in both train and validation losses. Do you have any idea why and how to prevent …
-
I am using Tacotron2 trained on a custom dataset on V3 Config, along with a custom trained ParallelWaveGAN FROM @kan-bayashi implementation. Everything works well but i have two concerns.
Q1 - Is t…
-
If you don't mind, I like to share my progress with PWGAN with TTS.
Here is the first try results:
https://soundcloud.com/user-565970875/sets/ljspeech_tacotron_5233_paralle
Results are not bet…
-
Thank you so much for an amazing paper and repository.
I have built waveGAN model in PyTorch (https://github.com/lukysummer/WaveGAN-in-PyTorch), and currently training it for the articulation of nu…
-
Hello everyone!
I am new to learn audio WavGAN and I am trying to run this code on Linux 16.04 for piano train [dataset](http://deepyeti.ucsd.edu/cdonahue/mancini_piano.tar.gz) containing 15 (.wav…
-
Hi ,
Thanks for your implementation.
I am curious about whether to normalize the input. I did not find the code that normalize the input to a certain range, but the output activation function o…