Add support for Hebrew language

[thewh1teagle]

What's needed to add support for Hebrew language? The only open tts model in Hebrew currently is mms-tts-heb but the quality is not good.

---

Some questions related

What's needed to create new good model? How many hours of audio + transcriptions? Do we need them with diacritical marks or no need? Should it be a single speaker? Can we use dataset such as ivrit-ai/audio-labeled - 100+ hours of multiple different speakers, used for create speech to text model so maybe the data not suitable for TTS.

As for the training, how different it should be from training English one? can we fine tune good English model even that hebrew is that different and has diacritical marks?

I really want to add Hebrew support, hope it's the right place to start. Thanks

[ips972]

any update?

[thewh1teagle]

@ips972

Follow here https://github.com/thewh1teagle/mishkal

[ips972]

looking for simple openai compat hebrew tts ..

[oyd11]

updating URL, though there's a redirect in the original one too : https://github.com/thewh1teagle/phonikud

[GeorgeS2019]

Done: https://github.com/rhasspy/piper/issues/757#issuecomment-2982457812

[thewh1teagle]

FYI the models in Hebrew are for non commercial / academic use (see the license)

[GeorgeS2019]

https://github.com/rhasspy/piper/issues/792

This is done. Can it be added to the official list of language support, the one with no commercial conditions although lower quality?

[ips972]

#792

This is done. Can it be added to the official list of language support, the one with no commercial conditions although lower quality?

and a newbie guide on how to host it locally and make it work.