Speaker Models¶

aana.core.models.speaker ¶

SpeakerDiarizationSegments ¶

SpeakerDiarizationSegments = list[SpeakerDiarizationSegment]

List of SpeakerDiarizationSegment objects.

PyannoteSpeakerDiarizationParams ¶

Bases: BaseModel

A model for the pyannote Speaker Diarization model parameters.

ATTRIBUTE	DESCRIPTION
`min_speakers`	The minimum number of speakers present in the audio. TYPE: `int \| None`
`max_speakers`	The maximum number of speakers present in the audio. TYPE: `int \| None`

SpeakerDiarizationSegment ¶

Bases: BaseModel

Pydantic schema for Segment from Speaker Diarization model.

ATTRIBUTE	DESCRIPTION
`time_interval`	The start and end time of the segment TYPE: `TimeInterval`
`speaker`	speaker assignment of the model in the format "SPEAKER_XX" TYPE: `str`

to_dict ¶

to_dict()

Generate dictionary with start, end and speaker keys from SpeakerDiarizationSegment.

RETURNS	DESCRIPTION
`dict`	Dictionary with start, end and speaker keys TYPE: `dict`

Source code in aana/core/models/speaker.py

def to_dict(self) -> dict:
    """Generate dictionary with start, end and speaker keys from SpeakerDiarizationSegment.

    Returns:
        dict: Dictionary with start, end and speaker keys
    """
    return {
        "start": self.time_interval.start,
        "end": self.time_interval.end,
        "speaker": self.speaker,
    }