Re:Show HN: Text-to-speech and speech-to-text open-source so...
by ftreml on Sunday January 26, 2020 @05:44PM
(#22155367)
in our tests the performance was comparable, so we had no reason to switch from kaldi to something else (german data only). after all, what matters the most is the available training data.
are there ready trained models available for wav2letter ?
[ Parent
| on HN ]
Re:Show HN: Text-to-speech and speech-to-text open-source so...
by grizzles on Sunday January 26, 2020 @05:55PM
(#22155428)
Oops, there I go being Anglocentric again. The datasets are out there; but idk if there are German trained models. Fortunately wav2letter++ looks like it's been built to be very friendly to train a more extensive one if there isn't. My understanding is they are still releasing parts of it.