Replies: 1 comment
-
I think the model already can capture British English to some degree, though unfortunately most speakers in LibriTTS are American speakers so the accent distributions are skewed. See #95 (comment) for example, one example shared by @WendongGan speaks in British accent, the reference audio is here and the synthesized result is here. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I listen to audio samples and for US English they are impressive. Is there a model equally good for British English. Can somebody share, please? I have pretty week Intel G4560 with integrated graphic (without separate GPU), so I think have no chances at the moment to train. And I really don't understand what is this training all about.
As a point of reference I propose voices from a dictionary. Please, notice that the pronunciation is different for US and British English. I also listened to voices available for coqui-ai and even when they try to imitate British accents the pronunciation of "advantage" is still in US English, at least it seems to me to be the case, although I am not British.
Beta Was this translation helpful? Give feedback.
All reactions