How was the aligner configured? about librispeech-alignments HOT 7 OPEN

Which alignments did you check? I used default parameters for the textgrid ones, but I applied a cleaning script to get the txt ones. I don't have that script anymore unfortunately.

from librispeech-alignments.

I checked both just to be sure. I noticed the discrepancy after trying to run my own cleaned alignments through synthesizer preprocessing script in your sv2tts repo. There's an assertion in the split_on_silences function that checks if the first and last words are silences and that's where I errored out.

I'm wondering if there were updates to the MFA that may have caused this.

from librispeech-alignments.

Ah right, sorry I didn't remember that until you mentioned it. Yes, I normalized everything in such a way that a sentences ends and starts with a silence, even if it's a 0-duration one. It was just out of convenience, I can't really remember why.

Silences are represented as empty words, e.g. in the first sentence there is a silence from 0s to 0.49s and the word 'GO' is pronounced from 0.49s to 0.89s. Each sentence is guaranteed to start and end with a silence, even if its duration is 0, this is for parsing convenience.

from librispeech-alignments.

Do you happen to recall (generally) how you normalized those sentences to determine those silences?

from librispeech-alignments.

Hi @sjmelsom, I want to create alignments on VCTK dataset, and I have no idea how to use the MFA. Is it possible to share your work regarding the creation of alignments?

from librispeech-alignments.

@stray128 I would recommend that you head over to the MFA docs. They provide a reasonable amount of material that will help you get started.

from librispeech-alignments.

Thanks, @sjmelsom. Also, I have another question for you. did you train the synthesizer model on the alignments you generated? If so, Were the results good when you surpass the number of steps that @CorentinJ trained?

from librispeech-alignments.