Method streaming_frame

espnet2/enh/encoder/abs_encoder.py:25–39

Stream frame. It splits the continuous audio into frame-level audio chunks in the streaming *simulation*. It is noted that this function takes the entire long audio as input for a streaming simulation. You may refer to this function to manage your streaming input

(self, audio: torch.Tensor)

        raise NotImplementedError

    def streaming_frame(self, audio: torch.Tensor):
        """Stream frame.

        It splits the continuous audio into frame-level
        audio chunks in the streaming *simulation*. It is noted that this
        function takes the entire long audio as input for a streaming simulation.
        You may refer to this function to manage your streaming input
        buffer in a real streaming application.

        Args:
            audio: (B, T)
        Returns:
            chunked: List [(B, frame_size),]
        """
        raise NotImplementedError