Aki van Galen comments

Repositories
Issues
Comments

Results 2 comments of


                                            Aki van Galen

trained ppg2mel model can not synthesize voice

Hi John, I had also trouble training the conversion model. In my case, the reason was that mask was not correctly created in parse_ourput() in model.py. The following code fixed...

trained ppg2mel model can not synthesize voice

I am using torch==1.4. The original code suggested to install torch==1.1 but apex which is needed for fp16 cannot be installed then. I will check torch==1.1 to be sure.