class pixeltable.functions.whisper.WhisperSegment
One segment of a transcription, with its timing and decoding statistics.
attr avg_logprob
Average log probability of the tokens in the segment’s decoding window.
attr compression_ratio
Compression ratio of the text in the segment’s decoding window; a high value indicates repetitive output.
attr end
Segment end, in seconds from the start of the audio.
attr id
Index of the segment in the transcription’s segments list.
attr no_speech_prob
Probability that the segment’s decoding window contains no speech.
attr seek
Start of the segment’s decoding window, in 10 ms frames.
attr start
Segment start, in seconds from the start of the audio.
attr temperature
Sampling temperature of the segment’s decoding window.
attr text
The segment’s text.
attr tokens
Token IDs of the segment; can include timestamp tokens.
attr words
Timings of the segment’s words; empty or absent unless word_timestamps=True.Last modified on September 30, 2026
