| | |
|---|
| | | |
|---|
| | | from funasr.modules.streaming_utils import utils as myutils |
|---|
| | | from funasr.models.decoder.transformer_decoder import BaseTransformerDecoder |
|---|
| | | from typeguard import check_argument_types |
|---|
| | | |
|---|
| | | from funasr.modules.attention import MultiHeadedAttentionSANMDecoder, MultiHeadedAttentionCrossAtt |
|---|
| | | from funasr.modules.embedding import PositionalEncoding |
|---|
| | |
|---|
| | | tf2torch_tensor_name_prefix_tf: str = "seq2seq/decoder", |
|---|
| | | embed_tensor_name_prefix_tf: str = None, |
|---|
| | | ): |
|---|
| | | assert check_argument_types() |
|---|
| | | super().__init__( |
|---|
| | | vocab_size=vocab_size, |
|---|
| | | encoder_output_size=encoder_output_size, |
|---|
| | |
|---|
| | | att_layer_num: int = 6, |
|---|
| | | kernel_size: int = 21, |
|---|
| | | sanm_shfit: int = 0, |
|---|
| | | lora_list: List[str] = None, |
|---|
| | | lora_rank: int = 8, |
|---|
| | | lora_alpha: int = 16, |
|---|
| | | lora_dropout: float = 0.1, |
|---|
| | | tf2torch_tensor_name_prefix_torch: str = "decoder", |
|---|
| | | tf2torch_tensor_name_prefix_tf: str = "seq2seq/decoder", |
|---|
| | | ): |
|---|
| | | assert check_argument_types() |
|---|
| | | super().__init__( |
|---|
| | | vocab_size=vocab_size, |
|---|
| | | encoder_output_size=encoder_output_size, |
|---|
| | |
|---|
| | | attention_dim, self_attention_dropout_rate, kernel_size, sanm_shfit=sanm_shfit |
|---|
| | | ), |
|---|
| | | MultiHeadedAttentionCrossAtt( |
|---|
| | | attention_heads, attention_dim, src_attention_dropout_rate |
|---|
| | | attention_heads, attention_dim, src_attention_dropout_rate, lora_list, lora_rank, lora_alpha, lora_dropout |
|---|
| | | ), |
|---|
| | | PositionwiseFeedForwardDecoderSANM(attention_dim, linear_units, dropout_rate), |
|---|
| | | dropout_rate, |
|---|
| | |
|---|
| | | """ |
|---|
| | | 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) |
|---|
| | | |
|---|
| | | memory = hs_pad |
|---|
| | | memory_mask = myutils.sequence_mask(hlens, device=memory.device)[:, None, :] |
|---|
| | | |
|---|
| | | x = tgt |
|---|
| | | x, tgt_mask, memory, memory_mask, _ = self.decoders( |
|---|
