| | |
|---|
| | | self.vad_opts.frame_in_ms) |
|---|
| | | self.encoder = encoder |
|---|
| | | # init variables |
|---|
| | | self.is_final = False |
|---|
| | | self.data_buf_start_frame = 0 |
|---|
| | | self.frm_cnt = 0 |
|---|
| | | self.latest_confirmed_speech_frame = 0 |
|---|
| | |
|---|
| | | self.frontend = frontend |
|---|
| | | |
|---|
| | | def AllResetDetection(self): |
|---|
| | | self.is_final = False |
|---|
| | | self.data_buf_start_frame = 0 |
|---|
| | | self.frm_cnt = 0 |
|---|
| | | self.latest_confirmed_speech_frame = 0 |
|---|
| | |
|---|
| | | def forward(self, feats: torch.Tensor, waveform: torch.tensor, in_cache: Dict[str, torch.Tensor] = dict(), |
|---|
| | | is_final: bool = False |
|---|
| | | ) -> Tuple[List[List[List[int]]], Dict[str, torch.Tensor]]: |
|---|
| | | if not in_cache: |
|---|
| | | self.AllResetDetection() |
|---|
| | | self.waveform = waveform # compute decibel for each frame |
|---|
| | | self.ComputeDecibel() |
|---|
| | | self.ComputeScores(feats, in_cache) |
|---|
