When I iterate 13,000 times, why is the synthesized speech a piece of silence

[Text2-m]

[keithito]

It's hard to say without more information, but 13k iterations is probably not enough.

• What are you using for training data?
• What does your loss curve look like?
• Can you the latest alignment image? This should be dumped to the training directory.

[vinnitu]

how many iterations need?

[vinnitu]

It is normal? e78123b6-5aca-4233-9472-ded968904295.zip step-12000-audio.zip

[japita-se]

Me too I have 15k steps for Moilla Dataset. The attention plot seems good but the synthesis produces noise.