Automatic Speech Recognition

The aim of this tool is to perform Automatic Speech Recognition (ASR), capitalization and punctuation of input audios. The input JSON object includes the audios (or folder) to be processed along with the language of the audios as well as the input folder where said audio files are stored in and the output folder in which the results are to be stored. The output JSON object contains the rich transcriptions of each audio with time codes and confidence scores. The tool currently functions with English, Spanish and Arabic.

ASGARD Reference: VICOM_A_001