#Issue with Serbian and Serbian (Latin)

1 messages · Page 1 of 1 (latest)

surreal violet
#

It seems that somehow this 2 languages switched places. No matter what language I choose for Conversation agent (HA) Serbian or Serbian (Latin), input for TTS is in Serbian (Latin) when responding. Microsoft STT can handle both alphabets and when Serbian is selected in Conversation agent correctly uses Cyrillic alphabet. When Serbian (Latin) is selected I get Latin alphabet for Serbian, that is OK.

What is not OK is that language for response stays always on Serbian (Latin) and Microsoft TTS can't process that.
Any advice is welcome, thanks

chilly vector
surreal violet
#

I am looking at intents for "language: sr-Latn" and
responses:
errors:
no_intent: "Nažalost, nerazumem" is what I get on both languages

no_intent: "Извини, нисам то могао да разумем" this is what I should get when I select "language: "sr""
#

So since I am using Microsoft for both STT and TTS, STT resolve correctly depend on language selected, but TTS can only process "language: "sr"" and I get response in "language: sr-Latn" and maybe there is an error

#

language: sr-Latn
language: "sr"

chilly vector
#

yeah, raising an issue on the repo is the best way to get the right sets of eyes on a problem like this.

surreal violet
#

"" probably should not be there for Serbian

chilly vector
#

include all this info in the issue

surreal violet
#

anything else that can be useful?

chilly vector
#

if more info is needed generarlly someone will ask for it. best thing to do is to put all the details in then keep an eye on the issue in case someone has extra questions

surreal violet
#

thanks @chilly vector

surreal violet
#

opened issue best I could 🙂

chilly vector
#

awesome, give it some time to get some eyes and hopefully someone will be able to narrow down the problem