Required Artificial Neural Networks,Deep Learning,Deep Neural Networks,Machine Learning,Natural Language Processing freelancer for Speaker Diarization job

We require a script/program on any simple interface to separate voices of multiple people from a recording.

Steps should be:

1. Upload a voice recording of multiple speakers talking in English (3 - 5 Minutes)
2. Perform speech to text (Spellings, grammar)
3. Generate results with different speaker labels to separate the voices (Speaker Diarization)
a. Speaker 1: This is a sunny day.
b. Speaker 2: What's your plan for tonight?
c. Speaker 1: Umm, nothing special. Looking to go for a hangout with buddies!
d. Speaker 3: I am in too, hey guys how are you doing?
e. Speaker 1: I am great and hope you are as well!

Skills & Expertise Required

Artificial Neural Networks Deep Learning Deep Neural Networks Machine Learning Natural Language Processing