Automatically Generate Custom Vocabulary List for Microsoft Cognitive Services Custom Speech Service
Automatically generate a custom vocabulary list for Cognitive Services Custom Speech Service from your text corpus.
This R script allows you to quickly parse your text file of target text into single words and ngrams, compare these to lists of common words or ngrams, and generate a list of less frequent words and ngrams. You can review these less frequent words and ngrams, and generate your custom vocabulary list for training the Custom Speech Service