asr_inference pipeline supports combine tp model

shixian.shi

2023-03-21 8cd93a1fc77e8a4a119f248ec0eb9018a74f728b

 funasr/models/encoder/opennmt_encoders/self_attention_encoder.py

@@ -272,7 +272,7 @@
            position embedded tensor and mask
        """
        masks = (~make_pad_mask(ilens)[:, None, :]).to(xs_pad.device)
        xs_pad *= self.output_size()**0.5
        xs_pad = xs_pad * self.output_size()**0.5
        if self.embed is None:
            xs_pad = xs_pad
        elif (