AudioTranscribeWhisperVadSettings interface
Settings for whisper-cpp VAD model see: AudioTranscribeWhisperSettings
Signature:
export interface AudioTranscribeWhisperVadSettings
Properties
Property | Type | Description |
---|---|---|
number |
(Optional) Max duration of a speech segment before forcing a new segment. |
|
number |
(Optional) Min silence duration to consider speech as ended. |
|
number |
(Optional) Min duration for a valid speech segment. |
|
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 |
|
number |
(Optional) Overlap in seconds when copying audio samples from speech segment. |
|
number |
(Optional) Padding added before and after speech segments. |
|
number |
(Optional) Probability threshold to consider as speech. |