Merge branch 'main' of github.com:alibaba-damo-academy/FunASR merge

游雁

2024-02-22 543d900522403eccb4e387cbc41c5dce24091d1d

Merge branch 'main' of github.com:alibaba-damo-academy/FunASR
merge

 funasr/models/paraformer/decoder.py

@@ -117,6 +117,22 @@

        return x, tgt_mask, memory, memory_mask, cache

    def get_attn_mat(self, tgt, tgt_mask, memory, memory_mask=None, cache=None):
        residual = tgt
        tgt = self.norm1(tgt)
        tgt = self.feed_forward(tgt)

        x = tgt
        if self.self_attn is not None:
            tgt = self.norm2(tgt)
            x, cache = self.self_attn(tgt, tgt_mask, cache=cache)
            x = residual + x

        residual = x
        x = self.norm3(x)
        x_src_attn, attn_mat = self.src_attn(x, memory, memory_mask, ret_attn=True)
        return attn_mat

    def forward_one_step(self, tgt, tgt_mask, memory, memory_mask=None, cache=None):
        """Compute decoded features.

@@ -397,6 +413,46 @@
        )
        return logp.squeeze(0), state

    def forward_asf2(
        self,
        hs_pad: torch.Tensor,
        hlens: torch.Tensor,
        ys_in_pad: torch.Tensor,
        ys_in_lens: torch.Tensor,
    ):

        tgt = ys_in_pad
        tgt_mask = myutils.sequence_mask(ys_in_lens, device=tgt.device)[:, :, None]

        memory = hs_pad
        memory_mask = myutils.sequence_mask(hlens, device=memory.device)[:, None, :]

        tgt, tgt_mask, memory, memory_mask, _ = self.decoders[0](tgt, tgt_mask, memory, memory_mask)
        attn_mat = self.model.decoders[1].get_attn_mat(tgt, tgt_mask, memory, memory_mask)
        return attn_mat
    
    def forward_asf6(
        self,
        hs_pad: torch.Tensor,
        hlens: torch.Tensor,
        ys_in_pad: torch.Tensor,
        ys_in_lens: torch.Tensor,
    ):

        tgt = ys_in_pad
        tgt_mask = myutils.sequence_mask(ys_in_lens, device=tgt.device)[:, :, None]

        memory = hs_pad
        memory_mask = myutils.sequence_mask(hlens, device=memory.device)[:, None, :]

        tgt, tgt_mask, memory, memory_mask, _ = self.decoders[0](tgt, tgt_mask, memory, memory_mask)
        tgt, tgt_mask, memory, memory_mask, _ = self.decoders[1](tgt, tgt_mask, memory, memory_mask)
        tgt, tgt_mask, memory, memory_mask, _ = self.decoders[2](tgt, tgt_mask, memory, memory_mask)
        tgt, tgt_mask, memory, memory_mask, _ = self.decoders[3](tgt, tgt_mask, memory, memory_mask)
        tgt, tgt_mask, memory, memory_mask, _ = self.decoders[4](tgt, tgt_mask, memory, memory_mask)
        attn_mat = self.decoders[5].get_attn_mat(tgt, tgt_mask, memory, memory_mask)
        return attn_mat

    def forward_chunk(
        self,
        memory: torch.Tensor,

 funasr/models/seaco_paraformer/model.py

@@ -19,11 +19,9 @@

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
@@ -76,7 +74,7 @@
                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':
            self.bias_embed = torch.nn.Embedding(self.vocab_size, self.inner_dim)
        else:
@@ -225,12 +223,8 @@
            
            # 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
@@ -241,9 +235,6 @@
                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)
@@ -274,6 +265,8 @@
                                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:
@@ -281,26 +274,20 @@
        _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,