Timestamp of the end of the word, in milliseconds.
Speech language. 2 letter ISO code or default
.
Length of the word, in milliseconds.
Technical name of ASR model.
The id of the speaker.
Timestamp of the beginning of the word, in milliseconds.
Concatenated words of the segment.
Identifies the utterance this event transcribes.
Words decoded for the segment.
Confidence of the decoding, from 0 to 1.