Preparing Input for SGX 3

Each batch of input to SGX consists of a set of audio files and corresponding text transcripts. Providing transcripts is optional but preferred as this helps the analysis provide higher quality output. If you do not wish to use transcripts, simply omit them from the input.

Each transcript is a plain-text transcription of what was said in the audio file. Here is an example: 

So he ran out of the way and the next morning it turned out that his servant had actually
died in the landslide further up the hill sometime before he warned him so that's my ghost
story

See Transcription Guidelines on best practices for transcribing speech.

In SGX you have different options for how to organize your input batch, whether as a directory or as a file list.

In this section