[fix] Fix a bug in seaco_paraformer model "inference" function (#1639)

querryton

2024-04-20 01df8f330ccc754223d5e2d688dc0a55d27f2dcc

[fix] Fix a bug in seaco_paraformer model "inference" function (#1639)

 funasr/models/seaco_paraformer/model.py

@@ -350,7 +350,7 @@
        pre_acoustic_embeds, pre_token_length = predictor_outs[0], predictor_outs[1]
        pre_token_length = pre_token_length.round().long()
        if torch.max(pre_token_length) < 1:
            return []
            return ([],)

        decoder_out = self._seaco_decode_with_ASF(encoder_out, 
                                                  encoder_out_lens,