update cutsplit step

雾聪

2024-03-05 6dcd960fda8be389af355ede4ecc583b036029d4

 funasr/models/seaco_paraformer/model.py

@@ -19,20 +19,18 @@

from funasr.register import tables
from funasr.utils import postprocess_utils
from funasr.metrics.compute_acc import th_accuracy
from funasr.models.paraformer.model import Paraformer
from funasr.utils.datadir_writer import DatadirWriter
from funasr.models.paraformer.search import Hypothesis
from funasr.models.paraformer.cif_predictor import mae_loss
from funasr.train_utils.device_funcs import force_gatherable
from funasr.models.bicif_paraformer.model import BiCifParaformer
from funasr.losses.label_smoothing_loss import LabelSmoothingLoss
from funasr.utils.timestamp_tools import ts_prediction_lfr6_standard
from funasr.models.transformer.utils.add_sos_eos import add_sos_eos
from funasr.utils.timestamp_tools import ts_prediction_lfr6_standard
from funasr.models.transformer.utils.nets_utils import make_pad_mask, pad_list
from funasr.utils.load_utils import load_audio_text_image_video, extract_fbank


import pdb
if LooseVersion(torch.__version__) >= LooseVersion("1.6.0"):
    from torch.cuda.amp import autocast
else:
@@ -66,7 +64,6 @@
  
        # bias encoder
        if self.bias_encoder_type == 'lstm':
            logging.warning("enable bias encoder sampling and contextual training")
            self.bias_encoder = torch.nn.LSTM(self.inner_dim, 
                                              self.inner_dim, 
                                              2, 
@@ -77,9 +74,8 @@
                self.lstm_proj = torch.nn.Linear(self.inner_dim*2, self.inner_dim)
            else:
                self.lstm_proj = None
            self.bias_embed = torch.nn.Embedding(self.vocab_size, self.inner_dim)
            # self.bias_embed = torch.nn.Embedding(self.vocab_size, self.inner_dim)
        elif self.bias_encoder_type == 'mean':
            logging.warning("enable bias encoder sampling and contextual training")
            self.bias_embed = torch.nn.Embedding(self.vocab_size, self.inner_dim)
        else:
            logging.error("Unsupport bias encoder type: {}".format(self.bias_encoder_type))
@@ -132,9 +128,8 @@
        hotword_pad = kwargs.get("hotword_pad")
        hotword_lengths = kwargs.get("hotword_lengths")
        dha_pad = kwargs.get("dha_pad")

        
        batch_size = speech.shape[0]
        self.step_cur += 1
        # for data-parallel
        text = text[:, : text_lengths.max()]
        speech = speech[:, :speech_lengths.max()]
@@ -214,25 +209,24 @@
                               nfilter=50,
                               seaco_weight=1.0):
        # decoder forward

        decoder_out, decoder_hidden, _ = self.decoder(encoder_out, encoder_out_lens, sematic_embeds, ys_pad_lens, return_hidden=True, return_both=True)

        decoder_pred = torch.log_softmax(decoder_out, dim=-1)
        if hw_list is not None:
            hw_lengths = [len(i) for i in hw_list]
            hw_list_ = [torch.Tensor(i).long() for i in hw_list]
            hw_list_pad = pad_list(hw_list_, 0).to(encoder_out.device)
            selected = self._hotword_representation(hw_list_pad, torch.Tensor(hw_lengths).int().to(encoder_out.device))

            contextual_info = selected.squeeze(0).repeat(encoder_out.shape[0], 1, 1).to(encoder_out.device)
            num_hot_word = contextual_info.shape[1]
            _contextual_length = torch.Tensor([num_hot_word]).int().repeat(encoder_out.shape[0]).to(encoder_out.device)
            

            # ASF Core
            if nfilter > 0 and nfilter < num_hot_word:
                for dec in self.seaco_decoder.decoders:
                    dec.reserve_attn = True
                # cif_attended, _ = self.decoder2(contextual_info, _contextual_length, sematic_embeds, ys_pad_lens)
                dec_attended, _ = self.seaco_decoder(contextual_info, _contextual_length, decoder_hidden, ys_pad_lens)
                # cif_filter = torch.topk(self.decoder2.decoders[-1].attn_mat[0][0].sum(0).sum(0)[:-1], min(nfilter, num_hot_word-1))[1].tolist()
                hotword_scores = self.seaco_decoder.decoders[-1].attn_mat[0][0].sum(0).sum(0)[:-1]
                hotword_scores = self.seaco_decoder.forward_asf6(contextual_info, _contextual_length, decoder_hidden, ys_pad_lens)
                hotword_scores = hotword_scores[0].sum(0).sum(0)
                # hotword_scores /= torch.sqrt(torch.tensor(hw_lengths)[:-1].float()).to(hotword_scores.device)
                dec_filter = torch.topk(hotword_scores, min(nfilter, num_hot_word-1))[1].tolist()
                add_filter = dec_filter
@@ -243,15 +237,12 @@
                contextual_info = selected.squeeze(0).repeat(encoder_out.shape[0], 1, 1).to(encoder_out.device)
                num_hot_word = contextual_info.shape[1]
                _contextual_length = torch.Tensor([num_hot_word]).int().repeat(encoder_out.shape[0]).to(encoder_out.device)
                for dec in self.seaco_decoder.decoders:
                    dec.attn_mat = []
                    dec.reserve_attn = False
            
            # SeACo Core
            cif_attended, _ = self.seaco_decoder(contextual_info, _contextual_length, sematic_embeds, ys_pad_lens)
            dec_attended, _ = self.seaco_decoder(contextual_info, _contextual_length, decoder_hidden, ys_pad_lens)
            merged = self._merge(cif_attended, dec_attended)
            

            dha_output = self.hotword_output_layer(merged)  # remove the last token in loss calculation
            dha_pred = torch.log_softmax(dha_output, dim=-1)
            def _merge_res(dec_output, dha_output):
@@ -265,8 +256,8 @@
                # logits = dec_output * dha_mask + dha_output[:,:,:-1] * (1-dha_mask)
                logits = dec_output * dha_mask + dha_output[:,:,:] * (1-dha_mask)
                return logits

            merged_pred = _merge_res(decoder_pred, dha_pred)
            # import pdb; pdb.set_trace()
            return merged_pred
        else:
            return decoder_pred
@@ -276,6 +267,8 @@
                                hotword_lengths):
        if self.bias_encoder_type != 'lstm':
            logging.error("Unsupported bias encoder type")
            
        '''
        hw_embed = self.decoder.embed(hotword_pad)
        hw_embed, (_, _) = self.bias_encoder(hw_embed)
        if self.lstm_proj is not None:
@@ -283,26 +276,20 @@
        _ind = np.arange(0, hw_embed.shape[0]).tolist()
        selected = hw_embed[_ind, [i-1 for i in hotword_lengths.detach().cpu().tolist()]]
        return selected
        '''

    '''
     def calc_predictor(self, encoder_out, encoder_out_lens):
        encoder_out_mask = (~make_pad_mask(encoder_out_lens, maxlen=encoder_out.size(1))[:, None, :]).to(
            encoder_out.device)
        pre_acoustic_embeds, pre_token_length, alphas, pre_peak_index, pre_token_length2 = self.predictor(encoder_out,
                                                                                                          None,
                                                                                                          encoder_out_mask,
                                                                                                          ignore_id=self.ignore_id)
        return pre_acoustic_embeds, pre_token_length, alphas, pre_peak_index


    def calc_predictor_timestamp(self, encoder_out, encoder_out_lens, token_num):
        encoder_out_mask = (~make_pad_mask(encoder_out_lens, maxlen=encoder_out.size(1))[:, None, :]).to(
            encoder_out.device)
        ds_alphas, ds_cif_peak, us_alphas, us_peaks = self.predictor.get_upsample_timestamp(encoder_out,
                                                                                            encoder_out_mask,
                                                                                            token_num)
        return ds_alphas, ds_cif_peak, us_alphas, us_peaks
    '''        
        # hw_embed = self.sac_embedding(hotword_pad)
        hw_embed = self.decoder.embed(hotword_pad)
        hw_embed = torch.nn.utils.rnn.pack_padded_sequence(hw_embed, hotword_lengths.cpu().type(torch.int64), batch_first=True, enforce_sorted=False)
        packed_rnn_output, _ = self.bias_encoder(hw_embed)
        rnn_output = torch.nn.utils.rnn.pad_packed_sequence(packed_rnn_output, batch_first=True)[0]
        if self.lstm_proj is not None:
            hw_hidden = self.lstm_proj(rnn_output)
        else:
            hw_hidden = rnn_output
        _ind = np.arange(0, hw_hidden.shape[0]).tolist()
        selected = hw_hidden[_ind, [i-1 for i in hotword_lengths.detach().cpu().tolist()]]
        return selected      
  
    def inference(self,
                 data_in,
@@ -320,7 +307,6 @@
            logging.info("enable beam_search")
            self.init_beam_search(**kwargs)
            self.nbest = kwargs.get("nbest", 1)
        
        meta_data = {}
        
        # extract fbank feats
@@ -337,7 +323,7 @@
        
        speech = speech.to(device=kwargs["device"])
        speech_lengths = speech_lengths.to(device=kwargs["device"])

        
        # hotword
        self.hotword_list = self.generate_hotwords_list(kwargs.get("hotword", None), tokenizer=tokenizer, frontend=frontend)
        
@@ -346,6 +332,7 @@
        if isinstance(encoder_out, tuple):
            encoder_out = encoder_out[0]
        

        # predictor
        predictor_outs = self.calc_predictor(encoder_out, encoder_out_lens)
        pre_acoustic_embeds, pre_token_length, _, _ = predictor_outs[0], predictor_outs[1], \
@@ -354,15 +341,14 @@
        if torch.max(pre_token_length) < 1:
            return []


        decoder_out = self._seaco_decode_with_ASF(encoder_out, encoder_out_lens,
                                                   pre_acoustic_embeds,
                                                   pre_token_length,
                                                   hw_list=self.hotword_list)

        # decoder_out, _ = decoder_outs[0], decoder_outs[1]
        _, _, us_alphas, us_peaks = self.calc_predictor_timestamp(encoder_out, encoder_out_lens,
                                                                  pre_token_length)
        
        results = []
        b, n, d = decoder_out.size()
        for i in range(b):
@@ -387,9 +373,11 @@
                nbest_hyps = [Hypothesis(yseq=yseq, score=score)]
            for nbest_idx, hyp in enumerate(nbest_hyps):
                ibest_writer = None
                if ibest_writer is None and kwargs.get("output_dir") is not None:
                    writer = DatadirWriter(kwargs.get("output_dir"))
                    ibest_writer = writer[f"{nbest_idx + 1}best_recog"]
                if kwargs.get("output_dir") is not None:
                    if not hasattr(self, "writer"):
                        self.writer = DatadirWriter(kwargs.get("output_dir"))
                    ibest_writer = self.writer[f"{nbest_idx + 1}best_recog"]
                    
                # remove sos/eos and get results
                last_pos = -1
                if isinstance(hyp.yseq, list):
@@ -415,12 +403,11 @@
                        token, timestamp)

                    result_i = {"key": key[i], "text": text_postprocessed,
                                "timestamp": time_stamp_postprocessed,
                                "timestamp": time_stamp_postprocessed
                                }
                    
                    if ibest_writer is not None:
                        ibest_writer["token"][key[i]] = " ".join(token)
                        # ibest_writer["text"][key[i]] = text
                        ibest_writer["timestamp"][key[i]] = time_stamp_postprocessed
                        ibest_writer["text"][key[i]] = text_postprocessed
                else: