News for hackers. Stuff that matters.
Re:Show HN: Text-to-speech and speech-to-text open-source so... by ftreml on Sunday January 26, 2020 @07:04PM (#22155789)
we used existing recipies for training (tuda german), slightly adapted and with additional training data. i am sure with more knowledge we would have made some extra percent ... performance is not really good, but good enough for our purposes, and with a satisfying cost vs quality trade off
Re:Show HN: Text-to-speech and speech-to-text open-source so... by Nimitz14 on Sunday January 26, 2020 @07:30PM (#22155917)
You should look at the latest recipe's for tedlium, librispeech, swbd etc you'll get significantly better results with those models.