alkove.Voiceprint

class Voiceprint(data: dict)

A voice, bound to this version’s Timbre: give it to Focus (voiceprint=), compare it (Timbre.verify), store to_json().

Methods

from_json()

Voiceprint.from_json(j: Union[dict, str]) -> Optional[Voiceprint]

None for a print of another Timbre: it no longer means anything, learn it again.

merge()

Voiceprint.merge(prints: Sequence[Voiceprint]) -> Voiceprint

One print with the centers of several (near and far, phone and headset): a voice is as close as its closest center.

to_json()

to_json() -> dict

The print as plain JSON, to store and read back with Voiceprint.from_json.

similarity()

similarity(other: Voiceprint) -> float

The cosine of the closest pair of centers.

Attributes

Attribute	Type	Description
embedding	np.ndarray	What Focus takes: 192 numbers.