Language "zh" is not supported by the EspeakBackend.name

TTS (Text-to-Speech)
#1

Hi,

I’m trying to train a new Chinese tts dataset using Tacotron2 on Dev branch

If I set “use_phonme”=true, and “phoneme_language”=zh, then following errors occur:

Screenshot%20from%202019-10-04%2019-34-40
Screenshot from 2019-10-04 19-34-40.png1168×435 73.1 KB
Screenshot%20from%202019-10-04%2019-34-52
Screenshot from 2019-10-04 19-34-52.png1214×491 107 KB

The version is eSpeak text-to-speech: 1.48.03 and phonemizer-1.1
available backends: festival-2.5.0, espeak-ng-1.49.2, segments-2.1.0

It’s confusing again that espeak with language “zh” worked well on master branch training tacotron

Anyone been through this before? Thanks!

#2

Do you manage to make Espeak output speech on the command line using zh? If you can’t get that working then phonemiser (and in turn TTS) is also likely to struggle.

I’ve no experience with training for Chinese but I wonder whether you might be better off with espeak-ng, and if you use that, then I believe the language code is slightly different: cmn

1 Like