simulstream.metrics.scorers.quality.mwersegmenter.ResegmentedQualityScoringSample

class simulstream.metrics.scorers.quality.mwersegmenter.ResegmentedQualityScoringSample(audio_name: str, hypothesis: List[str], reference: List[str], source: List[str] | None = None)

Bases: object

A sample containing realigned hypotheses and references.

audio_name

The identifier of the audio file.

Type:: str

hypothesis

Hypothesis lines after realignment.

Type:: List[str]

reference

Reference lines aligned to the hypothesis.

Type:: List[str]

source

Source text (if available).

Type:: Optional[List[str]]

__init__(audio_name: str, hypothesis: List[str], reference: List[str], source: List[str] | None = None) → None

Methods

__init__(audio_name, hypothesis, reference)

Attributes

`source`
`audio_name`
`hypothesis`
`reference`