-
pytorch 1.2
test my model
for i in range(20000):
l=int(random.randint(20,10000))
c=torch.rand(l,80)
out = model((c)) #model=MelGANGenerator
#use from memory_profil…
-
Hi! Thx for the repo. I was curious about the performance on CPU. AFAIK, it is 8x real-time on GPU but could you also share some values about CPU performance?
-
I just want to make sure but is the code associated in [here](https://github.com/kan-bayashi/ParallelWaveGAN/blob/53d14969089b3d3229fe6bfce221234f25a9d836/parallel_wavegan/losses/stft_loss.py#L82) the…
-
I made my own recipe but I got this error when I started training. I have no idea how this error occurred because theoretically it shouldn't depend on which recipe I use. I don't even know which varia…
ghost updated
4 years ago
-
Hello! First of all, thank you so much for the work: it's incredibile! 🥇
I want to retrain the system on an a different voice, with hours of recordings I will make. In order to achieve so, I was t…
-
Dears,
anyone had done this?
from MelGan Generator h5 to tflite.
thanks
-
```
###################################
# ENGLISH MODELS #
###################################
fs, lang = 22050, "English"
# tag = "kan-bayashi/ljspeech_tacotron2"
# tag = "kan-…
-
After I tried to use PyTorch 1.6.0, I got this error when training after 7k steps.
File "/home/train/.local/bin/parallel-wavegan-train", line 11, in
load_entry_point('parallel-wavegan', 'c…
ghost updated
4 years ago
-
Hi, I modify the sample rate, fft_size and hop size as 16000, 1024 and 256 of the _parallel_wavegan_v1.yaml_ of the _VCTK_ corpus. I also modify the upsample_scales as [4, 4, 4, 4] to ensure the prodc…
-
I am trying to run the arctic/vc1 recipe with Docker. I get the following missing dependency error. I'm a bit new to Docker, can anyone guide me on how to install these in the Docker container.
``…