Any way to make NER tagging with float(2.0) and inferencing with str(2)

One of the NER attribute is tagged with float (3.0, 2.0, ...) while the text file I am trying to inference from are in string format of (3, 2, ...).

The Spacy model I used can't pick up the numbers interchangeably with or without a (.0) tail.

Anyone has any idea how to solve this issue?

Many thanks!