mexca.audio.identification

Speech segment and speaker identification.

Module Contents

Classes

SpeakerIdentifier

Identify speech segments and cluster speakers using speaker diarization.

Functions

cli()

Command line interface for identifying speech segments and speakers.

class mexca.audio.identification.SpeakerIdentifier(num_speakers: Optional[int] = None, use_auth_token: Union[bool, str] = True)

Identify speech segments and cluster speakers using speaker diarization.

Wrapper class for pyannote.audio.SpeakerDiarization.

Parameters

• num_speakers (int, optional) – Number of speakers to which speech segments will be assigned during the clustering (oracle speakers). If None, the number of speakers is estimated from the audio signal.

• use_auth_token (bool or str, default=True) – Whether to use the HuggingFace authentication token stored on the machine (if bool) or a HuggingFace authentication token with access to the models pyannote/speaker-diarization and pyannote/segmentation (if str).

Notes

This class requires pretrained models for speaker diarization and segmentation from HuggingFace. To download the models accept the user conditions on hf.co/pyannote/speaker-diarization and hf.co/pyannote/segmentation. Then generate an authentication token on hf.co/settings/tokens.

property pipeline: pyannote.audio.Pipeline

The pretrained speaker diarization pipeline. See pyannote.audio.SpeakerDiarization for details.

apply(filepath: str) → mexca.data.SpeakerAnnotation

Identify speech segments and speakers.

Parameters

filepath (str) – Path to the audio file.

Returns

A data class object that contains detected speech segments and speakers.

Return type

SpeakerAnnotation

mexca.audio.identification.cli()

Command line interface for identifying speech segments and speakers. See identify-speakers -h for details.