update

嘉渊

2023-04-24 6427c834dfd97b1f05c6659cdc7ccf010bf82fe1

 funasr/models/e2e_vad.py

old mode 100755
new mode 100644
@@ -192,7 +192,7 @@


class E2EVadModel(nn.Module):
    def __init__(self, encoder: FSMN, vad_post_args: Dict[str, Any]):
    def __init__(self, encoder: FSMN, vad_post_args: Dict[str, Any], frontend=None):
        super(E2EVadModel, self).__init__()
        self.vad_opts = VADXOptions(**vad_post_args)
        self.windows_detector = WindowDetector(self.vad_opts.window_size_ms,
@@ -215,6 +215,7 @@
        self.sil_pdf_ids = self.vad_opts.sil_pdf_ids
        self.noise_average_decibel = -100.0
        self.pre_end_silence_detected = False
        self.next_seg = True

        self.output_data_buf = []
        self.output_data_buf_offset = 0
@@ -228,6 +229,7 @@
        self.data_buf_all = None
        self.waveform = None
        self.ResetDetection()
        self.frontend = frontend

    def AllResetDetection(self):
        self.is_final = False
@@ -244,6 +246,7 @@
        self.sil_pdf_ids = self.vad_opts.sil_pdf_ids
        self.noise_average_decibel = -100.0
        self.pre_end_silence_detected = False
        self.next_seg = True

        self.output_data_buf = []
        self.output_data_buf_offset = 0
@@ -441,10 +444,10 @@
                        - 1)) / self.vad_opts.noise_frame_num_used_for_snr

        return frame_state

     
    def forward(self, feats: torch.Tensor, waveform: torch.tensor, in_cache: Dict[str, torch.Tensor] = dict(),
                is_final: bool = False
                ) -> List[List[List[int]]]:
                ) -> Tuple[List[List[List[int]]], Dict[str, torch.Tensor]]:
        self.waveform = waveform  # compute decibel for each frame
        self.ComputeDecibel()
        self.ComputeScores(feats, in_cache)
@@ -468,8 +471,45 @@
        if is_final:
            # reset class variables and clear the dict for the next query
            self.AllResetDetection()
            in_cache.clear()
        return segments
        return segments, in_cache

    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
                ) -> Tuple[List[List[List[int]]], Dict[str, torch.Tensor]]:
        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.ComputeScores(feats, in_cache)
        self.ComputeDecibel()
        if not is_final:
            self.DetectCommonFrames()
        else:
            self.DetectLastFrames()
        segments = []
        for batch_num in range(0, feats.shape[0]):  # only support batch_size = 1 now
            segment_batch = []
            if len(self.output_data_buf) > 0:
                for i in range(self.output_data_buf_offset, len(self.output_data_buf)):
                    if not self.output_data_buf[i].contain_seg_start_point:
                        continue
                    if not self.next_seg and not self.output_data_buf[i].contain_seg_end_point:
                        continue
                    start_ms = self.output_data_buf[i].start_ms if self.next_seg else -1
                    if self.output_data_buf[i].contain_seg_end_point:
                        end_ms = self.output_data_buf[i].end_ms
                        self.next_seg = True
                        self.output_data_buf_offset += 1
                    else:
                        end_ms = -1
                        self.next_seg = False
                    segment = [start_ms, end_ms]
                    segment_batch.append(segment)
            if segment_batch:
                segments.append(segment_batch)
        if is_final:
            # reset class variables and clear the dict for the next query
            self.AllResetDetection()
        return segments, in_cache

    def DetectCommonFrames(self) -> int:
        if self.vad_state_machine == VadStateMachine.kVadInStateEndPointDetected: