Skip to main content
Version: 0.10.0

Type Alias: VadOptions

VadOptions = object

Defined in: extensions/speech/tasks/fsmnVoiceActivityDetection.ts:42

Tunable thresholds controlling how per-frame speech probabilities are turned into speech VadSegments.

Properties

mergeGapMs?

readonly optional mergeGapMs: number

Defined in: extensions/speech/tasks/fsmnVoiceActivityDetection.ts:55

Segments closer than this gap are merged into one.


minSilenceDurationMs?

readonly optional minSilenceDurationMs: number

Defined in: extensions/speech/tasks/fsmnVoiceActivityDetection.ts:51

Minimum duration below threshold required to close a segment.


minSpeechDurationMs?

readonly optional minSpeechDurationMs: number

Defined in: extensions/speech/tasks/fsmnVoiceActivityDetection.ts:49

Minimum duration a region must stay above the threshold to open a segment.


speechPadMs?

readonly optional speechPadMs: number

Defined in: extensions/speech/tasks/fsmnVoiceActivityDetection.ts:53

Padding added to both ends of every detected segment.


speechThreshold?

readonly optional speechThreshold: number

Defined in: extensions/speech/tasks/fsmnVoiceActivityDetection.ts:44

Minimum speech probability (0-1) for a frame to count as speech.