Festival voice broke

[Sandra T]

Sorry, I know I’m pretty late on this. I downloaded the voice config file for Festival and loaded it for the first time today and the voice came out choppy and super quick. It doesn’t sound the same each time I play it, and is not understandable at all. I tried starting Festival without the config file but the voice is still broken, even though the default voice was working fine before. Other sounds work fine on the VM.

Also, when I manually run the TTS pipeline step by step, at the POS stage Festival returns

-=-=-=-=-=- EST Error -=-=-=-=-=-
{FND} Feature Word not defined

-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-

Has anyone else encountered these issues?

Edit: I reset the PATH to the default directory and the voice seems to be working again (although the POS thing is still broken), so it’s something to do with the different versions of Festival? Or something went wrong with my file copying?

[Simon]

You have two separate problems. The solution to the choppy sound issue is probably this.

The “Feature Word not defined” error means that either

a) you are not using the correct voice (which is loaded by config.scm)

or

b) you omitted a step in the pipeline

Don’t change the PATH back to what it was before – this will pick up the old version of Festival, which will not work for the assignment.

[Sandra T]

The voice fix worked! Also I swore I wasn’t missing any steps but I actually was, thank you so much!

[Author]

Posts