1 Star 0 Fork 0

东方佑/acoustic_model

加入 Gitee
与超过 1200万 开发者一起发现、参与优秀开源项目,私有仓库也完全免费 :)
免费加入
克隆/下载
jasper.py 680 Bytes
一键复制 编辑 原始数据 按行查看 历史
"""
Citing from jasper from Nvidia
"""
import torch
import torch.nn as nn
import torch.functional as F
class SubBlock(nn.Module):
def __init__(self, dropout):
super(SubBlock, self).__init__()
self.conv = nn.Conv1d(in_channels=256, out_channels=256,
kernel_size=11, stride=1, padding=5)
self.batch_norm = nn.BatchNorm1d(num_features=256)
self.activation = nn.ReLU()
self.dropout = nn.Dropout(p=dropout)
def forward(self, x):
x = self.conv(x)
x = self.batch_norm(x)
x = self.activation(x)
return self.dropout(x)
class Block():
def __init__(self):
pass
马建仓 AI 助手
尝试更多
代码解读
代码找茬
代码优化
1
https://gitee.com/chenyang918/acoustic_model.git
git@gitee.com:chenyang918/acoustic_model.git
chenyang918
acoustic_model
acoustic_model
master

搜索帮助

D67c1975 1850385 1daf7b77 1850385