Enhancing Pipeline with Speech Probability for Reduced Hallucination

#96

by rizwanishaq - opened Mar 22

Mar 22

Could Adding Speech Probability to the Pipeline Input Minimize High No-Speech-Probability Transcriptions in the Original Whisper Model?

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment