argmaxinc / WhisperKit

On-device Speech Recognition for Apple Silicon
https://takeargmax.com/blog/whisperkit
MIT License
3.17k stars 268 forks source link

Reducing hallucinations by removing zero-length words based on word timestamps #41

Closed atiorh closed 3 months ago

atiorh commented 7 months ago

It would be great if certain patterns in the newly added word timestamps (#38 ) can be leveraged to reduce the incidence rate of hallucinations. This change will require comprehensive re-evaluation of the models since accurate words could also have zero-length based on inaccurate word timestamps.

atiorh commented 3 months ago

Resolved by #90