-
I get this error whenever I run train_finetune.py
(I am using WSL2)
```
File "/home/mastaldal/anaconda3/envs/StyleTTS2/lib/python3.10/site-packages/transformers/models/albert/modeling_albert.py", …
-
Request per https://github.com/yl4579/StyleTTS2/issues/96#issuecomment-1828819805. Current finetuning script is quite slow because it doesn't support accelerate due to #7, but a lot of people are fine…
-
Since it is mentioned that we can use XPhoneBert instead of the provided PL-BERT checkpoints for better multi-lingual inference, could you shed some light on how to load the [XphoneBert checkpoints](h…
-
Trying to fine-tune the model for custom data. After I run the below command
accelerate launch --mixed_precision=fp16 --num_processes=1 train_finetune_accelerate.py --config_path ./Configs/config_…
-
Hi, I am getting a weird sound in every generated clip most of times.
https://drive.google.com/file/d/1hjuxDqn4d5eKbMYoYynleWV3NwCXmQWD/view?usp=sharing
-
I'm using the command as specified in the README (`python train_finetune.py --config_path ./Configs/config_top19.yml`), and got this error (which seems related to the DDP bug?):
```
Epochs: 12
Vali…
-
Hello,
Thanks for the great work.
I'm trying to train a model on my dataset using an A5000 (24GB VRAM). I kept getting OOM at the beginning of Stage 1. I kept reducing batch size, and finally, the t…
-
-
It looks good, but the training seems to crash (on my computer) and I don't see how to actually run the software/model.
Can the readme be expanded to explain how to get going on it?
-
https://github.com/yl4579/StyleTTS2/blob/2f2dece35b9cad63215ae38bf991b856d1d1c063/train_second.py#L681C1-L681C32
Apologies if I am misunderstanding something, but it seems this line (681) in train_se…