The following schema describes transcript alignment.
[transcriptAlign] 0 = w ← ctm(READ, input) 1 = w2 ← align(ALIGN, w) 2 = output ← wout(_, w2) DefaultResults = out
0
|
The ctm module reads a CTM file that contains the transcript as produced by speech-to-text. |
1
|
The align module aligns the text transcript by comparing it to the output from a previous speech-to-text operation. |
2
|
The wout module writes the aligned transcript to the output file. |
|