class pixeltable.functions.whisper.WhisperSegment

One segment of a transcription, with its timing and decoding statistics.

attr avg_logprob

avg_logprob: float

Average log probability of the tokens in the segment’s decoding window.

compression_ratio: float

Compression ratio of the text in the segment’s decoding window; a high value indicates repetitive output.

end: float

Segment end, in seconds from the start of the audio.

id: int

Index of the segment in the transcription’s segments list.

no_speech_prob: float

Probability that the segment’s decoding window contains no speech.

seek: int

Start of the segment’s decoding window, in 10 ms frames.

start: float

Segment start, in seconds from the start of the audio.

temperature: float

Sampling temperature of the segment’s decoding window.

text: str

The segment’s text.

tokens: list[int]

Token IDs of the segment; can include timestamp tokens.

words: NotRequired[list[WhisperWord]]

Timings of the segment’s words; empty or absent unless word_timestamps=True.