[Sandy F]

Thank you, I think I know what to do now.

Based on my preliminary observations, I think that the voice built on carefully selected, domain-specific data performs better overall than the Arctic A voice or (to my surprise) a voice that combines both datasets. I’d like to see if listeners agree.

[Sandy F]

Thanks, that makes sense. One last thing: if the model randomly generates sequences, how do you ‘force’ it to generate a particular sequence?

[Author]

Posts