-
I get this error message when I try to finetune. I set batch_size to 12 and max_len to 14. I'm using torch-2.1.1 torchaudio-2.1.1 torchvision-0.16.1 if that matters.
> python train_finetune.py --co…
-
Great work! However, When I reused the LJSpeech to train the model, I encountered some problems as shown in the figure below. train_list, val_list and OOD_text are all original in the project. Can you…
-
Hello, I would like to ask how you solved the issue in styletts2 where punctuation marks could not be paused normally. Because I have seen that the solution is not to use punctuation marks to separate…
-
I get this white noise thing in a second sentence of this text right after word 'attack':
The rebirth gave Ashlock an opportunity to retake control of his life as throughout his life in this new wo…
-
https://github.com/yl4579/StyleTTS2/blob/2c427fc45291d5a046d4d46eb0c99d97b0cc1606/train_second.py#L39
**In 2nd stage training, names of all parameters are added 'module.' as a prefix. However, in the…
-
@yl4579 Hi, yl4579,I have a doubt. For LibriTTS-460 training text, you only gave examples from styletts1, and did not provide train_libritts_list.txt and val_libritts_list.txt of styletts2. But there …
-
I use chinese data to train and remove pl-bert mudule. It is normal until training to stage2 joint train, which train slmadv using differentiable duration. This causes the model to collapse and there …
-
The title says a lot but the issue is sometimes there's the random noise at the end of a generated sample or sometimes there's a metallic sound in the middle of a voice sample.
I have noticed that …
-
I am using python on colab.
https://colab.research.google.com/drive/1Aboxqh-CM6moUWmXp6RU73CnRKUnTo-e#scrollTo=EwJFcaFmsGMb
-
Tune Config
```
{'log_dir': 'Models/LJSpeech',
'save_freq': 5,
'log_interval': 10,
'device': 'cuda',
'epochs': 50,
'batch_size': 8,
'max_len': 400,
'pretrained_model': 'Models/Libri…