search

DigitalPhonetics / IMS-Toucan

Multilingual and Controllable Text-to-Speech Toolkit of the Speech and Language Technologies Group at the University of Stuttgart.
Apache License 2.0
1.36k stars 152 forks source link

I am not able to find Indian-english accent ("en-in"). #180

Closed dhattareddy closed 3 weeks ago

dhattareddy commented 1 month ago

I am trying to generate audio with reference audio. i want to get the output audio in Indian-english accent. I am not able to find it. I want to know whether the "en-in" accent is supported or not. If it supports, how can i give the lang_id?

Flux9665 commented 1 month ago

All 7000+ languages from the ISO-639-3 list are supported. en-in is not in this list, so it is not supported. You could use the set_phonemizer_language

https://github.com/DigitalPhonetics/IMS-Toucan/blob/53742f8c7fd1f09623a045955224c6e53c64c0ef/InferenceInterfaces/ToucanTTSInterface.py#L124

and set_accent_language

https://github.com/DigitalPhonetics/IMS-Toucan/blob/53742f8c7fd1f09623a045955224c6e53c64c0ef/InferenceInterfaces/ToucanTTSInterface.py#L127

method separately and set the first one to English and the other one to one of the Indian languages. Improved support for the 22 official languages of India will be part of the next release in a few days.