train update

游雁

2024-03-27 9b4e9cc8a0311e5243d69b73ed073e7ea441982e

 funasr/models/paraformer_streaming/model.py

@@ -235,8 +235,7 @@
        decoder_out_1st = None
        pre_loss_att = None
        if self.sampling_ratio > 0.0:
            if self.step_cur < 2:
                logging.info("enable sampler in paraformer, sampling_ratio: {}".format(self.sampling_ratio))

            if self.use_1st_decoder_loss:
                sematic_embeds, decoder_out_1st, pre_loss_att = \
                    self.sampler_with_grad(encoder_out, encoder_out_lens, ys_pad,
@@ -246,8 +245,6 @@
                    self.sampler(encoder_out, encoder_out_lens, ys_pad,
                                 ys_pad_lens, pre_acoustic_embeds, scama_mask)
        else:
            if self.step_cur < 2:
                logging.info("disable sampler in paraformer, sampling_ratio: {}".format(self.sampling_ratio))
            sematic_embeds = pre_acoustic_embeds
        
        # 1. Forward decoder
@@ -502,8 +499,7 @@
            logging.info("enable beam_search")
            self.init_beam_search(**kwargs)
            self.nbest = kwargs.get("nbest", 1)
        

            
        if len(cache) == 0:
            self.init_cache(cache, **kwargs)
        
@@ -535,10 +531,14 @@
        for i in range(n):
            kwargs["is_final"] = _is_final and i == n -1
            audio_sample_i = audio_sample[i*chunk_stride_samples:(i+1)*chunk_stride_samples]

            # extract fbank feats
            speech, speech_lengths = extract_fbank([audio_sample_i], data_type=kwargs.get("data_type", "sound"),
                                                   frontend=frontend, cache=cache["frontend"], is_final=kwargs["is_final"])
            if kwargs["is_final"] and len(audio_sample_i) < 960:
                cache["encoder"]["tail_chunk"] = True
                speech = cache["encoder"]["feats"]
                speech_lengths = torch.tensor([speech.shape[1]], dtype=torch.int64).to(speech.device)
            else:
                # extract fbank feats
                speech, speech_lengths = extract_fbank([audio_sample_i], data_type=kwargs.get("data_type", "sound"),
                                                       frontend=frontend, cache=cache["frontend"], is_final=kwargs["is_final"])
            time3 = time.perf_counter()
            meta_data["extract_feat"] = f"{time3 - time2:0.3f}"
            meta_data["batch_data_time"] = speech_lengths.sum().item() * frontend.frame_shift * frontend.lfr_n / 1000
@@ -557,11 +557,15 @@
            self.init_cache(cache, **kwargs)
        
        if kwargs.get("output_dir"):
            writer = DatadirWriter(kwargs.get("output_dir"))
            ibest_writer = writer[f"{1}best_recog"]
            if not hasattr(self, "writer"):
                self.writer = DatadirWriter(kwargs.get("output_dir"))
            ibest_writer = self.writer[f"{1}best_recog"]
            ibest_writer["token"][key[0]] = " ".join(tokens)
            ibest_writer["text"][key[0]] = text_postprocessed
        

        return result, meta_data


    
    def export(self, **kwargs):
        from .export_meta import export_rebuild_model
        models = export_rebuild_model(model=self, **kwargs)
        return models