Merge branch 'alibaba-damo-academy:main' into main

veelion

2023-03-24 7687f64729810ce0ffd0b5a38276ebbf75da43eb

 funasr/bin/vad_inference_online.py

@@ -30,7 +30,8 @@
from funasr.models.frontend.wav_frontend import WavFrontend
from funasr.bin.vad_inference import Speech2VadSegment


header_colors = '\033[95m'
end_colors = '\033[0m'


class Speech2VadSegmentOnline(Speech2VadSegment):
@@ -55,7 +56,7 @@
    @torch.no_grad()
    def __call__(
            self, speech: Union[torch.Tensor, np.ndarray], speech_lengths: Union[torch.Tensor, np.ndarray] = None,
            in_cache: Dict[str, torch.Tensor] = dict(), is_final: bool = False
            in_cache: Dict[str, torch.Tensor] = dict(), is_final: bool = False, max_end_sil: int = 800
    ) -> Tuple[torch.Tensor, List[List[int]], torch.Tensor]:
        """Inference

@@ -86,7 +87,8 @@
                "feats": feats,
                "waveform": waveforms,
                "in_cache": in_cache,
                "is_final": is_final
                "is_final": is_final,
                "max_end_sil": max_end_sil
            }
            # a. To device
            batch = to_device(batch, device=self.device)
@@ -217,6 +219,7 @@
        vad_results = []
        batch_in_cache = param_dict['in_cache'] if param_dict is not None else dict()
        is_final = param_dict['is_final'] if param_dict is not None else False
        max_end_sil = param_dict['max_end_sil'] if param_dict is not None else 800
        for keys, batch in loader:
            assert isinstance(batch, dict), type(batch)
            assert all(isinstance(s, str) for s in keys), keys
@@ -224,6 +227,7 @@
            assert len(keys) == _bs, f"{len(keys)} != {_bs}"
            batch['in_cache'] = batch_in_cache
            batch['is_final'] = is_final
            batch['max_end_sil'] = max_end_sil

            # do vad segment
            _, results, param_dict['in_cache'] = speech2vadsegment(**batch)