EnggRoom

Full Version: Thread
You're currently viewing a stripped down version of our content. View the full version with proper formatting.
My name is Rohit Yaduvanshi a student of Devi Ahilya University, Indore, India.
I have requirement of a project named as speaker diarization.
My requirement as 
  • The project should take a wav files as input.
  • After input, recognize the no of speakers in the wav file and conert the audio conversation into text with respect to user.
  • For examle, suppose a audio file contains the conversation between two people, therefore the project should give output as 
  • speaker 1 : How are you?
  • Speaker 2 : I am fine?
  • Speaker 1 : When you are coming to indore.
  • etc.