The align
module compares speech-to-text output with a normalized transcript file to produce a transcript that contains a timestamp for each word.
|
The w is the time-marked word series.
w is the output time-marked word series.
The |
The schema that implements this feature is:
[MyTranscriptAlign] w ← ctm (READ, input) w2 ← align(SCORE, input) output ← wout(_, w2)
|