Jackson Ding

Multi-language model

2

Hi, thank you for your excellent repo! Do you have any plan to develop a multi-language model?

training loss is nan

2

Hello, I am training Chinese data with a weight of 830m. At the beginning, the loss is normal, but after 2000 steps, there is a situation of "loss is nan"...

CUDA out of memory

1

hello, Im training on part xl of gigaspeech using 4*A100 80G, still report cuda out of memory. how to fix it?

About masking when training TTS enhanced model

2

Hello, thanks for this excellent work! I am training a TTS model and would like to ask if it is necessary to add any terminator to Y in the prepare_input_target...

About cosy2's flow matching training config

1

Hi,cosy2 is a excellent work! can you please tell me the scratch config of training flow matching in cosy2?