AudioTranscribeWhisperVadSettings interface

Settings for whisper-cpp VAD model see: AudioTranscribeWhisperSettings

Signature:

export interface AudioTranscribeWhisperVadSettings

Properties

Property Type Description

maxSpeechDurationS?

number

(Optional) Max duration of a speech segment before forcing a new segment.

minSilenceDurationMs?

number

(Optional) Min silence duration to consider speech as ended.

minSpeechDurationMs?

number

(Optional) Min duration for a valid speech segment.

model

string

The file name of the GGML-format whisper VAD model, ie a GGML silero-vad model.

Model downloads: https://huggingface.co/ggml-org/whisper-vad

samplesOverlap?

number

(Optional) Overlap in seconds when copying audio samples from speech segment.

speechPadMs?

number

(Optional) Padding added before and after speech segments.

threshold?

number

(Optional) Probability threshold to consider as speech.