I hardly understand what's going on. I think this is just something that eats noises and spits out labels. Like "Here is where the phoneme is". But using mathemagic. I should probably try it sometime.
As much as I'd like to be the person who makes an OTO generating SHIRO wrapper, my coding skills are roughly equivalent to shoving the alphabet through a cheese grater repeatedly and gluing the remains to a piece of paper.
I don't even get what it means by alignment
maybe i'm just tired
I tried downloading it and following the instructions on the page and I still don't get it LMAO
I now have an HSMM file and a bunch of audacity label files. The audacity labels don't even line up with the audio. I probably did something wrong
What are the labels though