How to get English words instead of Arabic numerals while transcribing English speech? #935
Answered
by
glangford
NanaOrangejuice
asked this question in
Q&A
-
I used transcribe.py to infer English speech, and got results containing Arabic numerals, such as "in 7 days". Can I get "in seven days" in transcribing? |
Beta Was this translation helpful? Give feedback.
Answered by
glangford
Jun 15, 2023
Replies: 1 comment 2 replies
-
Try the initial prompt flag to nudge it or post process the output with something like the num2words. |
Beta Was this translation helpful? Give feedback.
2 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
There is also this approach, see the following discussion:
For
initial_prompt
, see for example