0

I have been developing a Python application that takes an audio file and puts it through Whisper API and spits it out in a .docx file. Does anyone know how to add speaker differentiation to it.

Example without speaker differentiation

Hey, have you seen my keys anywhere? I think I saw them on the kitchen counter earlier. Let me check again.

Example with speaker differentiation

Speaker 1: Hey, have you seen my keys anywhere?

Speaker 2: I think I saw them on the kitchen counter earlier. Let me check again.

Any guidance would be great. Thanks!

I have already tried looking this up online though it is not making much sense to me. I haven't been able to find documentation that links closely to using the whisper api

Tom Hayward
  • 1
  • 1
  • Please clarify your specific problem or provide additional details to highlight exactly what you need. As it's currently written, it's hard to tell exactly what you're asking. – Community Jul 24 '23 at 18:40

0 Answers0