Haohan Guo
Haohan Guo
it's weird because the residual dropout should be placed before residual connection in Transformer.
Yes. At least it shows that dropout is very important in Transformer-TTS. But it should be used in a different way. Thanks for your sharing. On Thu, Jul 11, 2019...
I also have this problem when using the original configuration in your code
No... Now I still can only train it with a guided duration
Thanks for your comments. I will fix them in the next version.
Thanks for your attention. You can use ASR tools to extract the hidden vector in its model as the PPG, extract X-Vector as the speaker embedding, and extract F0 using...
It really depends on your ASR model. Usually, we adopt the bottleneck features in the ASR model or the output of the softmax layer. You need to compare them, and...
Due to the un-public data, I didn't upload the detailed example. When I get available resources, I will provide it in the next version.