How to list speaker_id from pre-trained multi-speaker TTS model? #7345
arthurwu4work
started this conversation in
General
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
Hi,
How to list speaker_id from pre-trained multi-speaker TTS nemo model ?
I used the
tts_en_fastpitch_multispeaker.nemo
the document (here) say this model have 10 speakers
but the speaker_id is not 0-9
and in the NGC (here)
The speaker IDs go from 1 to 20.
I tried to use range(30) to generate audio from speaker_id 0-29
It works sucessfully, why ?
( a lot of them just sound the same. )
where can I know what is the correct speaker_id ?
All I could find out was
list_available_model()
Is it possible to list available speaker_id from pre-trained multi-speaker TTS nemo model ?
thank you
Beta Was this translation helpful? Give feedback.
All reactions