Dev gzf exp (#1627)

zhifu gao

2024-04-17 e8f80e96f99cb856423d030c7d055c302a6d3278

 funasr/models/paraformer/model.py

@@ -181,15 +181,12 @@
                text: (Batch, Length)
                text_lengths: (Batch,)
        """
        # import pdb;
        # pdb.set_trace()
        if len(text_lengths.size()) > 1:
            text_lengths = text_lengths[:, 0]
        if len(speech_lengths.size()) > 1:
            speech_lengths = speech_lengths[:, 0]
        
        batch_size = speech.shape[0]
        
        
        # Encoder
        encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
@@ -475,6 +472,8 @@
        speech = speech.to(device=kwargs["device"])
        speech_lengths = speech_lengths.to(device=kwargs["device"])
        # Encoder
        if kwargs.get("fp16", False):
            speech = speech.half()
        encoder_out, encoder_out_lens = self.encode(speech, speech_lengths)
        if isinstance(encoder_out, tuple):
            encoder_out = encoder_out[0]