From a large speech audio file and its corresponding body of text, automatically chunk the audio and text into (phrase, audio_snippet) pairs. For use with the Connectionist Temporal Classification (CTC) cost algorithm.
patyork/AutomaticSpeechChunker
From a large speech audio file and its corresponding body of text, automatically chunk the audio and text into (phrase, audio_snippet) pairs. For use with the Connectionist Temporal Classification (CTC) cost algorithm.
Python