Get the timing of each word in a subtitle

I already have the subtitles for the videos and I need an algorithm that identifies the timing (beginning and end) of each word in the audio without using paid APIs.

Coding in Python.

Ex:
word: 'Hi', Start: 0, End: 1
word: 'How', Start: 1, End: 2
word: 'are', Start: 2, End: 3
word: 'you', Start: 3, End: 4