Given an output of a Speech-to-Text program, i.e. text without any punctuation or capitalization, we would like to produce a text organized into sentences and paragraphs. Are there existing models in HuggingFace capable of achieving this?
Given an output of a Speech-to-Text program, i.e. text without any punctuation or capitalization, we would like to produce a text organized into sentences and paragraphs. Are there existing models in HuggingFace capable of achieving this?