Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
PaddlePaddle
models
提交
73c3a602
M
models
项目概览
PaddlePaddle
/
models
大约 1 年 前同步成功
通知
222
Star
6828
Fork
2962
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
602
列表
看板
标记
里程碑
合并请求
255
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
M
models
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
602
Issue
602
列表
看板
标记
里程碑
合并请求
255
合并请求
255
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
提交
73c3a602
编写于
11月 06, 2017
作者:
Y
Yibing Liu
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Add the scoring of last word/char of prefixes in CTC beam search decoder
上级
8bd02c42
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
24 addition
and
6 deletion
+24
-6
.clang_format.hook
.clang_format.hook
+1
-1
deep_speech_2/decoders/swig/ctc_beam_search_decoder.cpp
deep_speech_2/decoders/swig/ctc_beam_search_decoder.cpp
+23
-5
未找到文件。
.clang_format.hook
浏览文件 @
73c3a602
#!/usr/bin/env bash
set
-e
readonly
VERSION
=
"3.
9
"
readonly
VERSION
=
"3.
6
"
version
=
$(
clang-format
-version
)
...
...
deep_speech_2/decoders/swig/ctc_beam_search_decoder.cpp
浏览文件 @
73c3a602
...
...
@@ -110,17 +110,17 @@ std::vector<std::pair<double, std::string>> ctc_beam_search_decoder(
// language model scoring
if
(
ext_scorer
!=
nullptr
&&
(
c
==
space_id
||
ext_scorer
->
is_character_based
()))
{
PathTrie
*
prefix_toscore
=
nullptr
;
PathTrie
*
prefix_to
_
score
=
nullptr
;
// skip scoring the space
if
(
ext_scorer
->
is_character_based
())
{
prefix_toscore
=
prefix_new
;
prefix_to
_
score
=
prefix_new
;
}
else
{
prefix_toscore
=
prefix
;
prefix_to
_
score
=
prefix
;
}
double
score
=
0.0
;
float
score
=
0.0
;
std
::
vector
<
std
::
string
>
ngram
;
ngram
=
ext_scorer
->
make_ngram
(
prefix_toscore
);
ngram
=
ext_scorer
->
make_ngram
(
prefix_to
_
score
);
score
=
ext_scorer
->
get_log_cond_prob
(
ngram
)
*
ext_scorer
->
alpha
;
log_p
+=
score
;
log_p
+=
ext_scorer
->
beta
;
...
...
@@ -131,6 +131,7 @@ std::vector<std::pair<double, std::string>> ctc_beam_search_decoder(
}
// end of loop over prefix
}
// end of loop over vocabulary
prefixes
.
clear
();
// update log probs
root
.
iterate_to_vec
(
prefixes
);
...
...
@@ -147,6 +148,23 @@ std::vector<std::pair<double, std::string>> ctc_beam_search_decoder(
}
}
// end of loop over time
// score the last word/character of each prefix
if
(
ext_scorer
!=
nullptr
)
{
for
(
size_t
i
=
0
;
i
<
beam_size
&&
i
<
prefixes
.
size
();
++
i
)
{
auto
prefix
=
prefixes
[
i
];
if
(
prefix
->
character
!=
space_id
&&
!
prefix
->
is_empty
())
{
float
score
=
0.0
;
std
::
vector
<
std
::
string
>
ngram
=
ext_scorer
->
make_ngram
(
prefix
);
score
=
ext_scorer
->
get_log_cond_prob
(
ngram
)
*
ext_scorer
->
alpha
;
score
+=
ext_scorer
->
beta
;
prefix
->
score
+=
score
;
}
}
}
size_t
num_prefixes
=
std
::
min
(
prefixes
.
size
(),
beam_size
);
std
::
sort
(
prefixes
.
begin
(),
prefixes
.
begin
()
+
num_prefixes
,
prefix_compare
);
// compute aproximate ctc score as the return score, without affecting the
// return order of decoding result. To delete when decoder gets stable.
for
(
size_t
i
=
0
;
i
<
beam_size
&&
i
<
prefixes
.
size
();
++
i
)
{
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录