Results of multi-speaker training

[Ranzige]

First of all, thank you for your excellent work，The data set I currently have contains 8 speaker, each of which is expected for about 20 minutes. Train according to your method and the results of model validation are poor.

Can you help me see why?

[begeekmyfriend]

20min for each speaker corpus seems too little for deep learning. I suggest 2 hours at least.

[Ranzige]

Thank you very much for your reply, the current audio length of each speaker 40 minutes, about 170 speaker, but I just want to train a few of them, what method can be used to other not used speaker audio to be better training results?

[begeekmyfriend]

Unseen speaker TTS is another model that is out of range of this project...