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
3474188b
D
DeepSpeech
项目概览
PaddlePaddle
/
DeepSpeech
大约 1 年 前同步成功
通知
207
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
体验新版 GitCode,发现更多精彩内容 >>
未验证
提交
3474188b
编写于
5月 12, 2022
作者:
小湉湉
提交者:
GitHub
5月 12, 2022
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #1887 from jerryuhoo/fix_preprocess
[tts] normalize wav max value to 1 in preprocess, test=tts
上级
1eec7b5e
167aaa65
变更
4
隐藏空白更改
内联
并排
Showing
4 changed file
with
16 addition
and
4 deletion
+16
-4
paddlespeech/t2s/exps/fastspeech2/preprocess.py
paddlespeech/t2s/exps/fastspeech2/preprocess.py
+4
-1
paddlespeech/t2s/exps/gan_vocoder/preprocess.py
paddlespeech/t2s/exps/gan_vocoder/preprocess.py
+4
-1
paddlespeech/t2s/exps/speedyspeech/preprocess.py
paddlespeech/t2s/exps/speedyspeech/preprocess.py
+4
-1
paddlespeech/t2s/exps/tacotron2/preprocess.py
paddlespeech/t2s/exps/tacotron2/preprocess.py
+4
-1
未找到文件。
paddlespeech/t2s/exps/fastspeech2/preprocess.py
浏览文件 @
3474188b
...
...
@@ -55,8 +55,11 @@ def process_sentence(config: Dict[str, Any],
if
utt_id
in
sentences
:
# reading, resampling may occur
wav
,
_
=
librosa
.
load
(
str
(
fp
),
sr
=
config
.
fs
)
if
len
(
wav
.
shape
)
!=
1
or
np
.
abs
(
wav
).
max
()
>
1.0
:
if
len
(
wav
.
shape
)
!=
1
:
return
record
max_value
=
np
.
abs
(
wav
).
max
()
if
max_value
>
1.0
:
wav
=
wav
/
max_value
assert
len
(
wav
.
shape
)
==
1
,
f
"
{
utt_id
}
is not a mono-channel audio."
assert
np
.
abs
(
wav
).
max
(
)
<=
1.0
,
f
"
{
utt_id
}
is seems to be different that 16 bit PCM."
...
...
paddlespeech/t2s/exps/gan_vocoder/preprocess.py
浏览文件 @
3474188b
...
...
@@ -47,8 +47,11 @@ def process_sentence(config: Dict[str, Any],
if
utt_id
in
sentences
:
# reading, resampling may occur
y
,
_
=
librosa
.
load
(
str
(
fp
),
sr
=
config
.
fs
)
if
len
(
y
.
shape
)
!=
1
or
np
.
abs
(
y
).
max
()
>
1.0
:
if
len
(
y
.
shape
)
!=
1
:
return
record
max_value
=
np
.
abs
(
y
).
max
()
if
max_value
>
1.0
:
y
=
y
/
max_value
assert
len
(
y
.
shape
)
==
1
,
f
"
{
utt_id
}
is not a mono-channel audio."
assert
np
.
abs
(
y
).
max
(
)
<=
1.0
,
f
"
{
utt_id
}
is seems to be different that 16 bit PCM."
...
...
paddlespeech/t2s/exps/speedyspeech/preprocess.py
浏览文件 @
3474188b
...
...
@@ -47,8 +47,11 @@ def process_sentence(config: Dict[str, Any],
if
utt_id
in
sentences
:
# reading, resampling may occur
wav
,
_
=
librosa
.
load
(
str
(
fp
),
sr
=
config
.
fs
)
if
len
(
wav
.
shape
)
!=
1
or
np
.
abs
(
wav
).
max
()
>
1.0
:
if
len
(
wav
.
shape
)
!=
1
:
return
record
max_value
=
np
.
abs
(
wav
).
max
()
if
max_value
>
1.0
:
wav
=
wav
/
max_value
assert
len
(
wav
.
shape
)
==
1
,
f
"
{
utt_id
}
is not a mono-channel audio."
assert
np
.
abs
(
wav
).
max
(
)
<=
1.0
,
f
"
{
utt_id
}
is seems to be different that 16 bit PCM."
...
...
paddlespeech/t2s/exps/tacotron2/preprocess.py
浏览文件 @
3474188b
...
...
@@ -51,8 +51,11 @@ def process_sentence(config: Dict[str, Any],
if
utt_id
in
sentences
:
# reading, resampling may occur
wav
,
_
=
librosa
.
load
(
str
(
fp
),
sr
=
config
.
fs
)
if
len
(
wav
.
shape
)
!=
1
or
np
.
abs
(
wav
).
max
()
>
1.0
:
if
len
(
wav
.
shape
)
!=
1
:
return
record
max_value
=
np
.
abs
(
wav
).
max
()
if
max_value
>
1.0
:
wav
=
wav
/
max_value
assert
len
(
wav
.
shape
)
==
1
,
f
"
{
utt_id
}
is not a mono-channel audio."
assert
np
.
abs
(
wav
).
max
(
)
<=
1.0
,
f
"
{
utt_id
}
is seems to be different that 16 bit PCM."
...
...
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