-
Hi! Thank you for the port. Have you been able to get results on inference stage? I successfully train model, validation losses are decreasing, but at inference there's garbage.
I started logging log…
-
I've been trying to get TensorflowTTS to train on Cloud TPUs because they're really fast and easy to access with the TRC, starting with MB-MelGAN+HiFi-GAN discriminator. I've already implemented all c…
-
What's a rough estimate for training time of the 22Khz v1 pretrained model provided here?
---
I'm currently training a 44Khz config.
At the moment I'm training using 3 GPU's, `batch_size=24` an…
-
In the HifiGAN paper, figure3 shows the differ between generated waveform-mel and Tacotron2 generated mel. Those two mel-spectrogram may be have different length, then how to padding the two mel-sequ…
-
Hello, I ran into similar trouble as #52 while trying to fine-tune the Universal_V1 checkpoint using ground-truth aligned TC2 outputs.
In my case, the fine-tuning breaks as soon as it reaches the v…
-
https://github.com/kan-bayashi/ParallelWaveGAN/search?q=upsample_kernal_sizes
In my option, just leaving the typos is okay (assuming nobody cares). If we want to fix it, it would be very nice not t…
-
I'm using [PyTorch Lightning CLI](https://pytorch-lightning.readthedocs.io/en/1.4.9/common/lightning_cli.html) utility and I'm having an issue with two classes that need an instance of [MelSpectrogram…
-
Hi, I'm having trouble initializing 3 different functions inside a dictionary.
I have the following code:
```python
class MyDataModule(pl.LightningDataModule):
def __init__(
self,
…
-
Congratulations and thank you for this great work.
We were able to easily adapt it (doubling fft params and changing upsample rates to [8,8,4,2]) to produce 44khz 16bit audio with very high quality.…
-
Hi, is it possible for you to share the pretrained model of vocoder discriminator so that I can fine tune it on some specific voice ?
thank you.