~geb/numen#10: 
Support more VOSK models

Thanks for numen!!!

The man page says, "Properly supporting/testing different speech recognition models and spoken languages is on the todo list, but numen should work with any of the small models from https://alphacephei.com/vosk/models."

Are large/non-English/punctuation models merely untested or is there a known incompatibility that prevents their use with numen?

Given that /etc/numen/scripts/transcripts expects words to be all lowercase and space-separated, support for punctuation models may require some tweaking.

Thank you!!!

Joseph

Status
RESOLVED CLOSED
Submitter
~breatheoutbreathein
Assigned to
No-one
Submitted
9 months ago
Updated
9 months ago
Labels
No labels applied.

~geb REPORTED CLOSED 9 months ago

The -small and -lgraph models should work, and I've had a good report form a user with the small French model. The big ones don't usually because their vocabulary can't be limited at runtime.

I've not looked into punctuation models yet.

John

~breatheoutbreathein 9 months ago

"~geb" outgoing@sr.ht writes:

The -small and -lgraph models should work, and I've had a good report form a user with the small French model. The big ones don't usually because their vocabulary can't be limited at runtime.

I've not looked into punctuation models yet.

Thank you for the info!

Joseph

Register here or Log in to comment, or comment via email.