Need Help: "long" & "short" models support for Traditional Chinese (zh-tw) in Speech-to-Text v2

Google Cloud Build with AI AI APIs
1

Hello everyone,

I’m currently facing an issue with the Google Cloud Speech-to-Text API v2 and was wondering if anyone here could offer some insight or a workaround. According to the documentation (https://shorturl.at/gAHO9), the “long” model should support the Traditional Chinese language code (zh-tw). However, when I attempt to use this combination, it seems that the “long” model does not actually support zh-tw.

error_message.png
error_message.png391×185 12.8 KB

Following is my configuration:

configuration.png
configuration.png950×896 73.9 KB

Has anyone else encountered this problem?

8 Likes
2

yes, me for kk-KZ, but I have no answer for your and my question about “long” model in V2

1 Like
3

After extensive trial and error, I found that only the “chirp” model is compatible with zh-tw. Perhaps you could give it a try.

4

It doesn’t work good with kk-kz

1 Like
5

The model “chirp” does not exist in the location named “global”, which region are you using ?

5 Likes