[Quantization] run calib without grad

wanchen.swc

2023-03-16 6ca0d1f54c8b698e3315edab8aa9ba7227d7c9e7

 funasr/punctuation/abs_model.py

@@ -25,3 +25,7 @@
    @abstractmethod
    def forward(self, input: torch.Tensor, hidden: torch.Tensor) -> Tuple[torch.Tensor, torch.Tensor]:
        raise NotImplementedError

    @abstractmethod
    def with_vad(self) -> bool:
        raise NotImplementedError