Re:Forward Transformer TTS – a non-autoregressive Transforme...
by microtherion on Tuesday June 02, 2020 @09:08PM
(#23398555)
I cannot speak for the authors, but my impression is that the vocoder (WaveRNN) part of current TTS systems takes much more computing than the part that this research addresses, so this may not help all that much.
[ Parent
| on HN ]
There are no comments on this comment yet.