Help: the cloned voice doesn't look like the original at all...
Hi. Very nice TTS model. Sadly, my outputs don't sound like the voice sample at all.
I'm using the oobabooga extension. The audio is created successfully, but it just doesn't sound like the same person.
I am trying to clone a Japanese voice. Here is the voice sample:
This is what I get:
Even if I put the Japanese setting, the cloned voice simply isn't recognizable. What can I do to make it better?
i don’t know what you expected but this sound recognizable to me. you can play with inference parameters for different results
No, this does not. If that's all this TTS can do, then it's not so good (for voice cloning at least).
Can’t tell as all these are subjective matters. But If you have data I can add it to the training so your voice would be ready by the next release.