| | |
| | | if self.self_attn: |
| | | if self.normalize_before: |
| | | tgt = self.norm2(tgt) |
| | | x, _ = self.self_attn(tgt, tgt_mask) |
| | | x = residual + self.dropout(x) |
| | | |
| | | if self.src_attn is not None: |
| | | residual = x |
| | | if self.normalize_before: |
| | | x = self.norm3(x) |
| | | |
| | | x = residual + self.dropout(self.src_attn(x, memory, memory_mask)) |
| | | |
| | | return x, tgt_mask, memory, memory_mask, cache |
| | | |
| | | def forward_chunk(self, tgt, tgt_mask, memory, memory_mask=None, cache=None): |
| | | """Compute decoded features. |
| | | |
| | | Args: |
| | | tgt (torch.Tensor): Input tensor (#batch, maxlen_out, size). |
| | | tgt_mask (torch.Tensor): Mask for input tensor (#batch, maxlen_out). |
| | | memory (torch.Tensor): Encoded memory, float32 (#batch, maxlen_in, size). |
| | | memory_mask (torch.Tensor): Encoded memory mask (#batch, maxlen_in). |
| | | cache (List[torch.Tensor]): List of cached tensors. |
| | | Each tensor shape should be (#batch, maxlen_out - 1, size). |
| | | |
| | | Returns: |
| | | torch.Tensor: Output tensor(#batch, maxlen_out, size). |
| | | torch.Tensor: Mask for output tensor (#batch, maxlen_out). |
| | | torch.Tensor: Encoded memory (#batch, maxlen_in, size). |
| | | torch.Tensor: Encoded memory mask (#batch, maxlen_in). |
| | | |
| | | """ |
| | | # tgt = self.dropout(tgt) |
| | | residual = tgt |
| | | if self.normalize_before: |
| | | tgt = self.norm1(tgt) |
| | | tgt = self.feed_forward(tgt) |
| | | |
| | | x = tgt |
| | | if self.self_attn: |
| | | if self.normalize_before: |
| | | tgt = self.norm2(tgt) |
| | | if self.training: |
| | | cache = None |
| | | x, cache = self.self_attn(tgt, tgt_mask, cache=cache) |
| | |
| | | |
| | | return x, tgt_mask, memory, memory_mask, cache |
| | | |
| | | |
| | | class FsmnDecoderSCAMAOpt(BaseTransformerDecoder): |
| | | """ |
| | | author: Speech Lab, Alibaba Group, China |
| | | Author: Speech Lab of DAMO Academy, Alibaba Group |
| | | SCAMA: Streaming chunk-aware multihead attention for online end-to-end speech recognition |
| | | https://arxiv.org/abs/2006.01713 |
| | | |
| | |
| | | for i in range(self.att_layer_num): |
| | | decoder = self.decoders[i] |
| | | c = cache[i] |
| | | x, tgt_mask, memory, memory_mask, c_ret = decoder( |
| | | x, tgt_mask, memory, memory_mask, c_ret = decoder.forward_chunk( |
| | | x, tgt_mask, memory, memory_mask, cache=c |
| | | ) |
| | | new_cache.append(c_ret) |
| | |
| | | j = i + self.att_layer_num |
| | | decoder = self.decoders2[i] |
| | | c = cache[j] |
| | | x, tgt_mask, memory, memory_mask, c_ret = decoder( |
| | | x, tgt_mask, memory, memory_mask, c_ret = decoder.forward_chunk( |
| | | x, tgt_mask, memory, memory_mask, cache=c |
| | | ) |
| | | new_cache.append(c_ret) |
| | | |
| | | for decoder in self.decoders3: |
| | | x, tgt_mask, memory, memory_mask, _ = decoder( |
| | | x, tgt_mask, memory, memory_mask, _ = decoder.forward_chunk( |
| | | x, tgt_mask, memory, None, cache=None |
| | | ) |
| | | |
| | |
| | | |
| | | class ParaformerSANMDecoder(BaseTransformerDecoder): |
| | | """ |
| | | author: Speech Lab, Alibaba Group, China |
| | | Author: Speech Lab of DAMO Academy, Alibaba Group |
| | | Paraformer: Fast and Accurate Parallel Transformer for Non-autoregressive End-to-End Speech Recognition |
| | | https://arxiv.org/abs/2006.01713 |
| | | """ |
| | |
| | | hlens: torch.Tensor, |
| | | ys_in_pad: torch.Tensor, |
| | | ys_in_lens: torch.Tensor, |
| | | chunk_mask: torch.Tensor = None, |
| | | ) -> Tuple[torch.Tensor, torch.Tensor]: |
| | | """Forward decoder. |
| | | |
| | |
| | | """ |
| | | 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, :] |
| | | if chunk_mask is not None: |
| | | memory_mask = memory_mask * chunk_mask |
| | | if tgt_mask.size(1) != memory_mask.size(1): |
| | | memory_mask = torch.cat((memory_mask, memory_mask[:, -2:-1, :]), dim=1) |
| | | |
| | | x = tgt |
| | | x, tgt_mask, memory, memory_mask, _ = self.decoders( |
| | |
| | | ys.unsqueeze(0), ys_mask, x.unsqueeze(0), cache=state |
| | | ) |
| | | return logp.squeeze(0), state |
| | | |
| | | def forward_chunk( |
| | | self, |
| | | memory: torch.Tensor, |
| | | tgt: torch.Tensor, |
| | | cache: dict = None, |
| | | ) -> Tuple[torch.Tensor, torch.Tensor]: |
| | | """Forward decoder. |
| | | |
| | | Args: |
| | | hs_pad: encoded memory, float32 (batch, maxlen_in, feat) |
| | | hlens: (batch) |
| | | ys_in_pad: |
| | | input token ids, int64 (batch, maxlen_out) |
| | | if input_layer == "embed" |
| | | input tensor (batch, maxlen_out, #mels) in the other cases |
| | | ys_in_lens: (batch) |
| | | Returns: |
| | | (tuple): tuple containing: |
| | | |
| | | x: decoded token score before softmax (batch, maxlen_out, token) |
| | | if use_output_layer is True, |
| | | olens: (batch, ) |
| | | """ |
| | | x = tgt |
| | | if cache["decode_fsmn"] is None: |
| | | cache_layer_num = len(self.decoders) |
| | | if self.decoders2 is not None: |
| | | cache_layer_num += len(self.decoders2) |
| | | new_cache = [None] * cache_layer_num |
| | | else: |
| | | new_cache = cache["decode_fsmn"] |
| | | for i in range(self.att_layer_num): |
| | | decoder = self.decoders[i] |
| | | x, tgt_mask, memory, memory_mask, c_ret = decoder.forward_chunk( |
| | | x, None, memory, None, cache=new_cache[i] |
| | | ) |
| | | new_cache[i] = c_ret |
| | | |
| | | if self.num_blocks - self.att_layer_num > 1: |
| | | for i in range(self.num_blocks - self.att_layer_num): |
| | | j = i + self.att_layer_num |
| | | decoder = self.decoders2[i] |
| | | x, tgt_mask, memory, memory_mask, c_ret = decoder.forward_chunk( |
| | | x, None, memory, None, cache=new_cache[j] |
| | | ) |
| | | new_cache[j] = c_ret |
| | | |
| | | for decoder in self.decoders3: |
| | | |
| | | x, tgt_mask, memory, memory_mask, _ = decoder.forward_chunk( |
| | | x, None, memory, None, cache=None |
| | | ) |
| | | if self.normalize_before: |
| | | x = self.after_norm(x) |
| | | if self.output_layer is not None: |
| | | x = self.output_layer(x) |
| | | cache["decode_fsmn"] = new_cache |
| | | return x |
| | | |
| | | def forward_one_step( |
| | | self, |
| | |
| | | for i in range(self.att_layer_num): |
| | | decoder = self.decoders[i] |
| | | c = cache[i] |
| | | x, tgt_mask, memory, memory_mask, c_ret = decoder( |
| | | x, tgt_mask, memory, memory_mask, c_ret = decoder.forward_chunk( |
| | | x, tgt_mask, memory, None, cache=c |
| | | ) |
| | | new_cache.append(c_ret) |
| | |
| | | j = i + self.att_layer_num |
| | | decoder = self.decoders2[i] |
| | | c = cache[j] |
| | | x, tgt_mask, memory, memory_mask, c_ret = decoder( |
| | | x, tgt_mask, memory, memory_mask, c_ret = decoder.forward_chunk( |
| | | x, tgt_mask, memory, None, cache=c |
| | | ) |
| | | new_cache.append(c_ret) |
| | | |
| | | for decoder in self.decoders3: |
| | | |
| | | x, tgt_mask, memory, memory_mask, _ = decoder( |
| | | x, tgt_mask, memory, memory_mask, _ = decoder.forward_chunk( |
| | | x, tgt_mask, memory, None, cache=None |
| | | ) |
| | | |