rhasspy / larynx

End to end text to speech system using gruut and onnx

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

German voice

alt131 opened this issue · comments

Did you think about using pavoque-data for German voice?
https://github.com/marytts/pavoque-data/releases/tag/v0.2
It has better quality in comparing with thorsten audio dataset.
It has restriction for commercial using but as I see you already have a voice with that restriction.

I did train a voice with it, actually 🙂

It didn't sound very good, and I now know that I need to do a forced alignment. I just finished training a German Kaldi model this past weekend with the same IPA phonemes, so I will be aligning and training this voice this week 👍

If you already tried it you can close this issue because I didn't have the hardware to train the model by myself and check it in practice.

I'll keep the issue open for now, since I'll be training it soon. Do you know of any good TTS datasets? Or are you interested in contributing your voice?

I'm afraid I say no in both cases but if I find TTS datasets with good quality I will let you know.

I successfully trained this and three other German voices 🙂

https://rhasspy.github.io/larynx/#de-de