mirror of
https://github.com/snakers4/silero-vad.git
synced 2026-02-05 18:09:22 +08:00
Merge pull request #528 from snakers4/adamnsandle
add neg_threshold parameter explicitly
This commit is contained in:
@@ -195,6 +195,7 @@ def get_speech_timestamps(audio: torch.Tensor,
|
||||
return_seconds: bool = False,
|
||||
visualize_probs: bool = False,
|
||||
progress_tracking_callback: Callable[[float], None] = None,
|
||||
neg_threshold: float = None,
|
||||
window_size_samples: int = 512,):
|
||||
|
||||
"""
|
||||
@@ -237,6 +238,9 @@ def get_speech_timestamps(audio: torch.Tensor,
|
||||
progress_tracking_callback: Callable[[float], None] (default - None)
|
||||
callback function taking progress in percents as an argument
|
||||
|
||||
neg_threshold: float (default = threshold - 0.15)
|
||||
Negative threshold (noise or exit threshold). If model's current state is SPEECH, values BELOW this value are considered as NON-SPEECH.
|
||||
|
||||
window_size_samples: int (default - 512 samples)
|
||||
!!! DEPRECATED, DOES NOTHING !!!
|
||||
|
||||
@@ -298,6 +302,8 @@ def get_speech_timestamps(audio: torch.Tensor,
|
||||
triggered = False
|
||||
speeches = []
|
||||
current_speech = {}
|
||||
|
||||
if neg_threshold is None:
|
||||
neg_threshold = threshold - 0.15
|
||||
temp_end = 0 # to save potential segment end (and tolerate some silence)
|
||||
prev_end = next_start = 0 # to save potential segment limits in case of maximum segment size reached
|
||||
|
||||
Reference in New Issue
Block a user