Voice Mapping

Given a clear audio of speech and the same speech as string, you have to write a code to map each word from the string to the position of the word in the audio. You have to mark the beginning and end of each word in the audio (in milliseconds). I have attached the sample audios which you can find in audio folder. The text for each audio can be extracted manually from corresponding html files in the html folder. The audios are very clear and the algorithm is expected to have 100% accuracy. You are free to choose any libraries and any programming language. This project is for a client. The project will be awarded and payment will be done only when the algo reaches 100% accuracy and the client is happy and makes payment. In order to win trust in me, you may visit my employer/freelacer profiles. I am trying to expand a network of trusted clients and dependable coders. With me, you wont have to worry about bidding on projects, and you can just let me know whenever you are free, and I will have a project for you. I assure you that I won't keep the money that belongs to you, however, I won't be willing to award you the project before the project is done, because if I do, and if you turn out to be the wrong person, then my ratings will be screwed from both sides for no reason which I try to avoid at any cost.