| | |
|---|
| | | import torch |
|---|
| | | import torch.nn as nn |
|---|
| | | from funasr.modules.streaming_utils.chunk_utilis import overlap_chunk |
|---|
| | | from typeguard import check_argument_types |
|---|
| | | import numpy as np |
|---|
| | | from funasr.modules.nets_utils import make_pad_mask |
|---|
| | | from funasr.modules.attention import MultiHeadSelfAttention, MultiHeadedAttentionSANM |
|---|
| | |
|---|
| | | |
|---|
| | | class SelfAttentionEncoder(AbsEncoder): |
|---|
| | | """ |
|---|
| | | author: Speech Lab, Alibaba Group, China |
|---|
| | | Author: Speech Lab of DAMO Academy, Alibaba Group |
|---|
| | | Self attention encoder in OpenNMT framework |
|---|
| | | """ |
|---|
| | | |
|---|
| | |
|---|
| | | tf2torch_tensor_name_prefix_tf: str = "seq2seq/encoder", |
|---|
| | | out_units=None, |
|---|
| | | ): |
|---|
| | | assert check_argument_types() |
|---|
| | | super().__init__() |
|---|
| | | self._output_size = output_size |
|---|
| | | |
|---|
| | |
|---|
| | | position embedded tensor and mask |
|---|
| | | """ |
|---|
| | | masks = (~make_pad_mask(ilens)[:, None, :]).to(xs_pad.device) |
|---|
| | | xs_pad *= self.output_size()**0.5 |
|---|
| | | xs_pad = xs_pad * self.output_size()**0.5 |
|---|
| | | if self.embed is None: |
|---|
| | | xs_pad = xs_pad |
|---|
| | | elif ( |
|---|
