Why are you splitting the text?
Your output requires the spaces (and presumably other punctuation) and split will remove all whitespace - which includes the spaces.
Instead, think about processing the input character-by-character:
If it's a digit, add it to the output.
Otherwise, if it (and the following characters) match one of your "known words" add the digit for that to the output and skip the rest of the word.
Otherwise, add it to the output.
Think about how you would do it manually, and consider ways to "computerise" that. If you are having problems getting started at all, then this may help: How to Write Code to Solve a Problem, A Beginner's Guide