-
|
Is it possible to pass "initial_prompt" and "suppress_tokens" values to be considered by the model when run? |
Beta Was this translation helpful? Give feedback.
Replies: 3 comments 1 reply
-
|
Currently not, no prob to add tho. Do you need different parameters for main and realtime transcription models or do you think one parameter for init prompt and suppress tokens is sufficient? |
Beta Was this translation helpful? Give feedback.
-
|
Amazing. I'm focused on realtime, so that's the only one I care about. |
Beta Was this translation helpful? Give feedback.
-
|
And I'd be curious to know if there's another way to add a list of vocabulary keywords that the model will weigh higher than other words. |
Beta Was this translation helpful? Give feedback.
-
|
There is only grammar sampling as of my knowledge and this restricts to certain words. |
Beta Was this translation helpful? Give feedback.
Currently not, no prob to add tho. Do you need different parameters for main and realtime transcription models or do you think one parameter for init prompt and suppress tokens is sufficient?