From 4db549b8007565b4c7f02ef07a4062217ecab1eb Mon Sep 17 00:00:00 2001 From: Guillaume Klein Date: Wed, 24 May 2023 15:49:36 +0200 Subject: [PATCH] Make get_speech_timestamps backward compatible with the previous usage (#259) --- faster_whisper/vad.py | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/faster_whisper/vad.py b/faster_whisper/vad.py index cf3b626..a937812 100644 --- a/faster_whisper/vad.py +++ b/faster_whisper/vad.py @@ -40,19 +40,22 @@ class VadOptions(NamedTuple): def get_speech_timestamps( - audio: np.ndarray, vad_options: Optional[VadOptions] = None + audio: np.ndarray, + vad_options: Optional[VadOptions] = None, + **kwargs, ) -> List[dict]: """This method is used for splitting long audios into speech chunks using silero VAD. Args: audio: One dimensional float array. vad_options: Options for VAD processing. + kwargs: VAD options passed as keyword arguments for backward compatibility. Returns: List of dicts containing begin and end samples of each speech chunk. """ if vad_options is None: - vad_options = VadOptions() + vad_options = VadOptions(**kwargs) threshold = vad_options.threshold min_speech_duration_ms = vad_options.min_speech_duration_ms