diart.blocks.segmentation

Module Contents

Classes

SpeakerSegmentation

class diart.blocks.segmentation.SpeakerSegmentation(model, device=None)

Parameters:

• model (diart.models.SegmentationModel) –

• device (Optional[torch.device]) –

static from_pretrained(model, use_hf_token=True, device=None)

Parameters:

• use_hf_token (Union[Text, bool, None]) –

• device (Optional[torch.device]) –

Return type:

SpeakerSegmentation

__call__(waveform)

Calculate the speaker segmentation of input audio.

Parameters:

waveform (TemporalFeatures, shape (samples, channels) or (batch, samples, channels)) –

Returns:

speaker_segmentation – The batch dimension is omitted if waveform is a SlidingWindowFeature.

Return type:

TemporalFeatures, shape (batch, frames, speakers)