$$ FineTune Not Work !

[developeranalyser]

A custom dataset was generated for the basis of the words that are read incorrectly and the v1 large model was trained on the text to voice and I received the output of the pth file and loaded the model with load_state_dict and tested how to read....... and There was no change in the sentences he had been taught and he reads wrongly as before. That is, he was trained, but no change was achieved

I spent more than 3 months to do this!!

What do you think is the reason for this problem? Has anyone been able to train the v1 large model for text to voice and get results?????

Please help if you know Thankful