It is interesting field, looking inside the models what they are doing, how they are doing, I think i am going to give it a chance, and i will have good deadline of 12th sep, cause that’s when the application deadline is, idea is learning as i make progress and i need, not trying to learn and explore all the research paper at once!
let’s see how it goes, for the research project i am thinking about exploring the audio models like whisper and looking into it, how they work and how they do some things, why they react in certain ways!