DaegyeomKim

During learning, the gradient norm of the nar model comes out as nan, so learning is not going well. I think there is no problem with the data and there...

about zero-shot inference

31

Hello p0p4k, I'm reaching out to you again with a question. Thanks to your great help, I've successfully trained and inferred the Korean pflow model. During the inference process, I...

NAN loss

8

Hello p0p4k, I've begun training a PFlow Korean model using the code you shared. However, I encountered a nan loss during the training process. I used a publicly available Korean...

about n_spks

6

Hello p0p4k, I am deeply grateful for the code you have provided. I have a question while adapting it to a Korean version. I am preparing to use a speech-to-text...

about audio2mesh training

1

Hello, I am currently training the audio2mesh model using my own data. The data consists of videos of 41 men and women with fixed head positions and minimal facial expression...

add another special_tokens

4

Hello, I would like to train a model by adding new tokens and corresponding audio sounds that are not included in the additional_special_tokens of the QwenTokenizer. For example, I want...

Questions about model structure

2

Dear p0p4k, I am currently engaged in research on Korean voice synthesis models and have been utilizing your well-crafted vits2_pytorch implementation for training a Korean model. It has been functioning...