[fix] better solution for handling empty result (#1796)

Xingchen Song(宋星辰)

2024-06-11 0bd1a4d6a9893e45438505514a063d9deee91f21

 funasr/models/transformer/encoder.py

@@ -64,7 +64,7 @@
        stochastic_depth_rate=0.0,
    ):
        """Construct an EncoderLayer object."""
        super(EncoderLayer, self).__init__()
        super().__init__()
        self.self_attn = self_attn
        self.feed_forward = feed_forward
        self.norm1 = LayerNorm(size)