| | |
|---|
| | | |
|---|
| | | from typing import Optional |
|---|
| | | from typing import Sequence |
|---|
| | | from typing import Tuple |
|---|
| | | |
|---|
| | | import numpy as np |
|---|
| | | import torch |
|---|
| | | from typeguard import check_argument_types |
|---|
| | | |
|---|
| | | from funasr.modules.nets_utils import make_pad_mask |
|---|
| | | from funasr.modules.rnn.encoders import RNN |
|---|
| | |
|---|
| | | |
|---|
| | | class RNNEncoder(AbsEncoder): |
|---|
| | | """RNNEncoder class. |
|---|
| | | |
|---|
| | | Args: |
|---|
| | | input_size: The number of expected features in the input |
|---|
| | | output_size: The number of output features |
|---|
| | |
|---|
| | | use_projection: Use projection layer or not |
|---|
| | | num_layers: Number of recurrent layers |
|---|
| | | dropout: dropout probability |
|---|
| | | |
|---|
| | | """ |
|---|
| | | |
|---|
| | | def __init__( |
|---|
| | |
|---|
| | | dropout: float = 0.0, |
|---|
| | | subsample: Optional[Sequence[int]] = (2, 2, 1, 1), |
|---|
| | | ): |
|---|
| | | assert check_argument_types() |
|---|
| | | super().__init__() |
|---|
| | | self._output_size = output_size |
|---|
| | | self.rnn_type = rnn_type |
|---|
