Update load_pretrained_model.py

zhifu gao

2024-01-17 e67ed1d45d5a9d7fb7bb22d15fd2bfef17e9076f

 funasr/models/uniasr/e2e_uni_asr.py

@@ -443,7 +443,10 @@
        # force_gatherable: to-device and to-tensor if scalar for DataParallel
        if self.length_normalized_loss:
            batch_size = int((text_lengths + 1).sum())
<<<<<<< HEAD:funasr/models/uniasr/e2e_uni_asr.py

=======
>>>>>>> main:funasr/models/e2e_uni_asr.py
        loss, stats, weight = force_gatherable((loss, stats, batch_size), loss.device)
        return loss, stats, weight

@@ -538,20 +541,20 @@
                        speech_lengths: (Batch, )
        """
        # with autocast(False):
        #    # 1. Extract feats
        #    feats, feats_lengths = self._extract_feats(speech, speech_lengths)
        #     # 1. Extract feats
        #     feats, feats_lengths = self._extract_feats(speech, speech_lengths)
        #
        #    # 2. Data augmentation
        #    if self.specaug is not None and self.training:
        #       feats, feats_lengths = self.specaug(feats, feats_lengths)
        #     # 2. Data augmentation
        #     if self.specaug is not None and self.training:
        #         feats, feats_lengths = self.specaug(feats, feats_lengths)
        #
        #    # 3. Normalization for feature: e.g. Global-CMVN, Utterance-CMVN
        #    if self.normalize is not None:
        #       feats, feats_lengths = self.normalize(feats, feats_lengths)
        #     # 3. Normalization for feature: e.g. Global-CMVN, Utterance-CMVN
        #     if self.normalize is not None:
        #         feats, feats_lengths = self.normalize(feats, feats_lengths)

        # Pre-encoder, e.g. used for raw input data
        # if self.preencoder is not None:
        #    feats, feats_lengths = self.preencoder(feats, feats_lengths)
        #     feats, feats_lengths = self.preencoder(feats, feats_lengths)
        encoder_out_rm, encoder_out_lens_rm = self.encoder.overlap_chunk_cls.remove_chunk(
            encoder_out,
            encoder_out_lens,
@@ -581,9 +584,9 @@

        # # Post-encoder, e.g. NLU
        # if self.postencoder is not None:
        #    encoder_out, encoder_out_lens = self.postencoder(
        #       encoder_out, encoder_out_lens
        #    )
        #     encoder_out, encoder_out_lens = self.postencoder(
        #         encoder_out, encoder_out_lens
        #     )

        assert encoder_out.size(0) == speech.size(0), (
            encoder_out.size(),