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
DeepSpeech
提交
0c6dddb1
D
DeepSpeech
项目概览
PaddlePaddle
/
DeepSpeech
大约 2 年 前同步成功
通知
210
Star
8425
Fork
1598
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
245
列表
看板
标记
里程碑
合并请求
3
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
D
DeepSpeech
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
245
Issue
245
列表
看板
标记
里程碑
合并请求
3
合并请求
3
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
未验证
提交
0c6dddb1
编写于
5月 31, 2022
作者:
小湉湉
提交者:
GitHub
5月 31, 2022
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #1991 from yt605155624/fix_mfa
[TTS]gen lexicon with tone in mfa, test=tts
上级
aa3d151d
9a253bc0
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
2 addition
and
7 deletion
+2
-7
examples/other/mfa/local/reorganize_baker.py
examples/other/mfa/local/reorganize_baker.py
+0
-3
examples/other/mfa/run.sh
examples/other/mfa/run.sh
+2
-4
未找到文件。
examples/other/mfa/local/reorganize_baker.py
浏览文件 @
0c6dddb1
...
@@ -42,9 +42,6 @@ def get_transcripts(path: Union[str, Path]):
...
@@ -42,9 +42,6 @@ def get_transcripts(path: Union[str, Path]):
for
i
in
range
(
0
,
len
(
lines
),
2
):
for
i
in
range
(
0
,
len
(
lines
),
2
):
sentence_id
=
lines
[
i
].
split
()[
0
]
sentence_id
=
lines
[
i
].
split
()[
0
]
transcription
=
lines
[
i
+
1
].
strip
()
transcription
=
lines
[
i
+
1
].
strip
()
# tones are dropped here
# since the lexicon does not consider tones, too
transcription
=
" "
.
join
([
item
[:
-
1
]
for
item
in
transcription
.
split
()])
transcripts
[
sentence_id
]
=
transcription
transcripts
[
sentence_id
]
=
transcription
return
transcripts
return
transcripts
...
...
examples/other/mfa/run.sh
100644 → 100755
浏览文件 @
0c6dddb1
...
@@ -4,7 +4,7 @@ mkdir -p $EXP_DIR
...
@@ -4,7 +4,7 @@ mkdir -p $EXP_DIR
LEXICON_NAME
=
'simple'
LEXICON_NAME
=
'simple'
if
[
!
-f
"
$EXP_DIR
/
$LEXICON_NAME
.lexicon"
]
;
then
if
[
!
-f
"
$EXP_DIR
/
$LEXICON_NAME
.lexicon"
]
;
then
echo
"generating lexicon..."
echo
"generating lexicon..."
python
local
/generate_lexicon.py
"
$EXP_DIR
/
$LEXICON_NAME
"
--with-r
python
local
/generate_lexicon.py
"
$EXP_DIR
/
$LEXICON_NAME
"
--with-r
--with-tone
echo
"lexicon done"
echo
"lexicon done"
fi
fi
...
@@ -16,6 +16,7 @@ if [ ! -d $EXP_DIR/baker_corpus ]; then
...
@@ -16,6 +16,7 @@ if [ ! -d $EXP_DIR/baker_corpus ]; then
echo
"transcription for each audio file is saved with the same namd in
$EXP_DIR
/baker_corpus "
echo
"transcription for each audio file is saved with the same namd in
$EXP_DIR
/baker_corpus "
fi
fi
echo
"detecting oov..."
echo
"detecting oov..."
python
local
/detect_oov.py
$EXP_DIR
/baker_corpus
$EXP_DIR
/
"
$LEXICON_NAME
.lexicon"
python
local
/detect_oov.py
$EXP_DIR
/baker_corpus
$EXP_DIR
/
"
$LEXICON_NAME
.lexicon"
echo
"detecting oov done. you may consider regenerate lexicon if there is unexpected OOVs."
echo
"detecting oov done. you may consider regenerate lexicon if there is unexpected OOVs."
...
@@ -44,6 +45,3 @@ if [ ! -d "$EXP_DIR/baker_alignment" ]; then
...
@@ -44,6 +45,3 @@ if [ ! -d "$EXP_DIR/baker_alignment" ]; then
echo
"model:
$EXP_DIR
/baker_model"
echo
"model:
$EXP_DIR
/baker_model"
fi
fi
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