search

fatchord / WaveRNN

WaveRNN Vocoder + TTS
https://fatchord.github.io/model_outputs/
MIT License
2.14k stars 698 forks source link

How to train better？ #194

Open 1zxLi opened 4 years ago

1zxLi commented 4 years ago

I did not modify any parameters. After 400K epochs, the loss oscillated around 5.3 and could not continue to converge. Is there a more suitable parameter setting scheme to continue to optimize the loss? （ljspeech data）

xuexidi commented 4 years ago

I met the same problem...

harryfyodor commented 3 years ago

I met the same problem too, I do not modify anything, but the loss is around 5.3 after 600k steps. The samples it generated is terrible under this situtation.

harryfyodor commented 3 years ago

I did not modify any parameters. After 400K epochs, the loss oscillated around 5.3 and could not continue to converge. Is there a more suitable parameter setting scheme to continue to optimize the loss? （ljspeech data）

Hi, i met the same problem too, have you solved it?