mirror of
https://github.com/modelscope/FunASR
synced 2025-09-15 14:48:36 +08:00
e04489ce4c
* contextual&seaco ONNX export * update ContextualEmbedderExport2 * update ContextualEmbedderExport2 * update code * onnx (#1482) * qwenaudio qwenaudiochat * qwenaudio qwenaudiochat * whisper * whisper * llm * llm * llm * llm * llm * llm * llm * llm * export onnx * export onnx * export onnx * dingding * dingding * llm * doc * onnx * onnx * onnx * onnx * onnx * onnx * v1.0.15 * qwenaudio * qwenaudio * issue doc * update * update * bugfix * onnx * update export calling * update codes * remove useless code * update code --------- Co-authored-by: zhifu gao <zhifu.gzf@alibaba-inc.com>
50 lines
1.3 KiB
Python
50 lines
1.3 KiB
Python
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
|
|
# Copyright 2019 Shigeki Karita
|
|
# Apache 2.0 (http://www.apache.org/licenses/LICENSE-2.0)
|
|
|
|
"""Positionwise feed forward layer definition."""
|
|
|
|
import torch
|
|
|
|
from funasr.models.transformer.layer_norm import LayerNorm
|
|
|
|
|
|
class PositionwiseFeedForward(torch.nn.Module):
|
|
"""Positionwise feed forward layer.
|
|
|
|
Args:
|
|
idim (int): Input dimenstion.
|
|
hidden_units (int): The number of hidden units.
|
|
dropout_rate (float): Dropout rate.
|
|
|
|
"""
|
|
|
|
def __init__(self, idim, hidden_units, dropout_rate, activation=torch.nn.ReLU()):
|
|
"""Construct an PositionwiseFeedForward object."""
|
|
super(PositionwiseFeedForward, self).__init__()
|
|
self.w_1 = torch.nn.Linear(idim, hidden_units)
|
|
self.w_2 = torch.nn.Linear(hidden_units, idim)
|
|
self.dropout = torch.nn.Dropout(dropout_rate)
|
|
self.activation = activation
|
|
|
|
def forward(self, x):
|
|
"""Forward function."""
|
|
return self.w_2(self.dropout(self.activation(self.w_1(x))))
|
|
|
|
|
|
class PositionwiseFeedForwardDecoderSANMExport(torch.nn.Module):
|
|
def __init__(self, model):
|
|
super().__init__()
|
|
self.w_1 = model.w_1
|
|
self.w_2 = model.w_2
|
|
self.activation = model.activation
|
|
self.norm = model.norm
|
|
|
|
def forward(self, x):
|
|
x = self.activation(self.w_1(x))
|
|
x = self.w_2(self.norm(x))
|
|
return x
|
|
|