grothedev

huh, well it appears to be working now, and i don't remember what i changed. weird. i'll respond with anymore info i find out.

related question: why train only on publicly available data from the internet? if you want quality language and good knowledge, wouldn't you want to train on things like textbooks, historical...

yes. if the training data isn't released (at least the titles of the data items) then it's not technically completely open source.

oh, ok. i can start working on that this week if it's not already being worked on.

roger that! i'll look into it

which library supports voice?

is there any specification about what type of filter processing is allowed to be done on the backend?