-
Hello, I tried to train LJ speech model from scratch using default config. The training is running fine with some exception below.
> Traceback (most recent call last):
File "/home/tan/StyleTTS2…
-
Thank you for the code and work.
I'm trying to run the second stage training, and step into the breakpoint part since the g_loss is None, any thoughts on that?
https://github.com/yl4579/StyleTTS2/…
haoqi updated
7 months ago
-
Hey, I was wondering what sort of changes it would take to the training script to be able to train HiFiGAN on higher quality data like [LibriTTS ](https://www.openslr.org/60/)or [LibriTTS-R](https://w…
-
ERROR: Cannot install -r requirements.txt (line 126), -r requirements.txt (line 127), -r requirements.txt (line 128), -r requirements.txt (line 132), -r requirements.txt (line 133), -r requirements.tx…
-
-
```
100% 8659/8659 [20:58
-
This issue is for tracking TODO lists which are supposed to be cherry-picked to the release branch. Following is [release branch](https://github.com/pytorch/audio/tree/release/2.0) for the 2.0.1 relea…
-
Might be interesting to compare embeddings trained on speakerID
https://huggingface.co/speechbrain/spkrec-xvect-voxceleb
-
### Describe the bug
Hi all,
I've used huggingface hosted models like "microsoft/wavlm-large" and whisper to perform some speech classification tasks. This has worked well. Now I would like to u…
-
I've managed to create a few models now using FT but on some of my datasets I get this error :
`(styletts) root@DESKTOP-G461NBO:/mnt/h/StyleTTS23# accelerate launch --mixed_precision=fp16 --num_pro…