Open 9SL9 opened 1 year ago
Confidence values are provided on a per-token basis from whisper.cpp. I hadn't planned on an API to interface on the token level, but it may be worth looking in to.
That would be fantastic if it could be considered!
Confidence values are provided on a per-token basis from whisper.cpp. I hadn't planned on an API to interface on the token level, but it may be worth looking in to.
+1 for this. This would allow color highlighting based on that confidence. Which would make human review of transcribed text a million times faster and easier!
Is it possible to get the confidence for an individual segment/word as part of the results?
Thanks