Changing speed of speech

[sgulasekaran]

Is there a way to sample z such that the speed of speech is changed, .i.e, make it faster or slower ?

I tried with different sigma but that seems to control variability in speech and couldn't really change speed.

The paper also didn't talk about it. Any thoughts on this ?

[rafaelvalle]

Yes, we're looking into it!

[rafaelvalle]

An alternative way to change speed is to train Flowtron with a token duration predictor, modifying the attention mechanism to work the hard alignments and then scale the durations during inference. The ground truth durations can be obtained from Flowtron alignments. This works quite well for us and provides a mechanism to directly control speech rate.

[rafaelvalle]

We'll soon make Flowtron Parallel available https://twitter.com/RafaelValleArt/status/1281268833504751616?s=20

[sgulasekaran]

Great, really excited and looking forward to it.

[artemg]

@rafaelvalle any updates on Flowtron Parallel?

[evelynyhc]

hello, is there any function to change the speech rate when inference?