Batch Input Options

There are three input options for defining an SGX processing job: directory input, file list input, and transcript list input. These are detailed below.

Directory Input

The simplest way to provide input is to place all your input files for the batch into a directory. For example:

Each transcript (.txt) file in the input contains the transcript of the audio file with the same base name. For example, p364_025.txt contains the transcript for audio file p364_025.wav.

File List Input

Another option is to provide a text file containing a list of the input files in the batch. For example:

CODE

D:\Voiceover_01\audio\p364_025.wav 
D:\Voiceover_01\audio\p364_026.wav 
D:\Voiceover_01\audio\p364_027.wav 
D:\Voiceover_01\audio\p364_028.wav 
D:\Voiceover_01\transcripts\p364_025.txt 
D:\Voiceover_01\transcripts\p364_026.txt 
D:\Voiceover_01\transcripts\p364_027.txt 
D:\Voiceover_01\transcripts\p364_028.txt

The advantage of a list is that the input files for a given batch do not have to exist in the same directory, which may be convenient depending on your data organization.

Note that you may also list the files as relative paths:

CODE

audio\p364_028.wav
audio\p364_029.wav
audio\p364_030.wav
audio\p364_031.wav
audio\p364_032.wav
audio\p364_033.wav
audio\p364_034.wav
audio\p364_035.wav
transcripts\p364_028.txt
transcripts\p364_029.txt
transcripts\p364_030.txt
transcripts\p364_031.txt
transcripts\p364_032.txt
transcripts\p364_033.txt
transcripts\p364_034.txt

The relative paths will be resolved using the location of the input list file as the base directory. For example, if the above file is D:\Voiceover_01\batch_01.txt, then each of the relative paths will be expanded based on the directory D:\Voiceover_01\.

Transcript List Input

In the above methods, transcripts are divided into individual .txt files. Another approach is to place all of your transcripts for a batch into a single file (either .txt or .csv). The format of this file is such that there is one transcript per line, and it is preceded by the name of the corresponding audio file. The base name and transcript are separated by a comma. For example:

CODE

p364_025.wav,Hey point that thing at someone else
p364_026.wav,I just heard from the scout there is a convoy approaching
p364_027.wav,So I just walked up the beach and there was this great thing coming out of the water so I ran I hope it's not following me

This list provides transcripts for p364_025.wav, p364_026.wav, and p364_027.wav. The audio files may also be full paths; it does not matter:

CODE

D:\Voiceover_01\audio\p364_025.wav,Hey point that thing at someone else
D:\Voiceover_01\audio\p364_026.wav,I just heard from the scout there is a convoy approaching
D:\Voiceover_01\audio\p364_027.wav,So I just walked up the beach and there was this great thing coming out of the water so I ran I hope it's not following me

In fact, the only important information is the base name of the audio file, so the audio file suffixes could be omitted:

CODE

p364_025,Hey point that thing at someone else
p364_026,I just heard from the scout there is a convoy approaching
p364_027,So I just walked up the beach and there was this great thing coming out of the water so I ran I hope it's not following me