|
@@ -501,6 +501,8 @@ class E2EVadModel(nn.Module):
|
|
|
def forward_online(self, feats: torch.Tensor, waveform: torch.tensor, in_cache: Dict[str, torch.Tensor] = dict(),
|
|
def forward_online(self, feats: torch.Tensor, waveform: torch.tensor, in_cache: Dict[str, torch.Tensor] = dict(),
|
|
|
is_final: bool = False, max_end_sil: int = 800
|
|
is_final: bool = False, max_end_sil: int = 800
|
|
|
) -> Tuple[List[List[List[int]]], Dict[str, torch.Tensor]]:
|
|
) -> Tuple[List[List[List[int]]], Dict[str, torch.Tensor]]:
|
|
|
|
|
+ if not in_cache:
|
|
|
|
|
+ self.AllResetDetection()
|
|
|
self.max_end_sil_frame_cnt_thresh = max_end_sil - self.vad_opts.speech_to_sil_time_thres
|
|
self.max_end_sil_frame_cnt_thresh = max_end_sil - self.vad_opts.speech_to_sil_time_thres
|
|
|
self.waveform = waveform # compute decibel for each frame
|
|
self.waveform = waveform # compute decibel for each frame
|
|
|
|
|
|