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
00a6236f
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
提交
00a6236f
编写于
4月 18, 2022
作者:
L
lym0302
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
remove test code, test=doc
上级
9c0ceaac
变更
2
展开全部
隐藏空白更改
内联
并排
Showing
2 changed file
with
0 addition
and
672 deletion
+0
-672
paddlespeech/server/tests/tts/infer/run.sh
paddlespeech/server/tests/tts/infer/run.sh
+0
-62
paddlespeech/server/tests/tts/infer/test_online_tts.py
paddlespeech/server/tests/tts/infer/test_online_tts.py
+0
-610
未找到文件。
paddlespeech/server/tests/tts/infer/run.sh
已删除
100644 → 0
浏览文件 @
9c0ceaac
model_path
=
~/.paddlespeech/models/
am_model_dir
=
$model_path
/fastspeech2_csmsc-zh/fastspeech2_cnndecoder_csmsc_ckpt_1.0.0/
voc_model_dir
=
$model_path
/mb_melgan_csmsc-zh/mb_melgan_csmsc_ckpt_0.1.1/
testdata
=
../../../../t2s/exps/csmsc_test.txt
# get am file
for
file
in
$(
ls
$am_model_dir
)
do
if
[[
$file
==
*
"yaml"
*
]]
;
then
am_config_file
=
$file
elif
[[
$file
==
*
"pdz"
*
]]
;
then
am_ckpt_file
=
$file
elif
[[
$file
==
*
"stat"
*
]]
;
then
am_stat_file
=
$file
elif
[[
$file
==
*
"phone"
*
]]
;
then
phones_dict_file
=
$file
fi
done
# get voc file
for
file
in
$(
ls
$voc_model_dir
)
do
if
[[
$file
==
*
"yaml"
*
]]
;
then
voc_config_file
=
$file
elif
[[
$file
==
*
"pdz"
*
]]
;
then
voc_ckpt_file
=
$file
elif
[[
$file
==
*
"stat"
*
]]
;
then
voc_stat_file
=
$file
fi
done
# run test
# am can choose fastspeech2_csmsc or fastspeech2_cnndecoder_csmsc, where fastspeech2_cnndecoder_csmsc supports streaming inference.
# voc can choose hifigan_csmsc and mb_melgan_csmsc, They can both support streaming inference.
# When am is fastspeech2_cnndecoder_csmsc and am_pad is set to 12, there is no diff between streaming and non-streaming inference results.
# When voc is mb_melgan_csmsc and voc_pad is set to 14, there is no diff between streaming and non-streaming inference results.
# When voc is hifigan_csmsc and voc_pad is set to 20, there is no diff between streaming and non-streaming inference results.
python test_online_tts.py
--am
fastspeech2_cnndecoder_csmsc
\
--am_config
$am_model_dir
/
$am_config_file
\
--am_ckpt
$am_model_dir
/
$am_ckpt_file
\
--am_stat
$am_model_dir
/
$am_stat_file
\
--phones_dict
$am_model_dir
/
$phones_dict_file
\
--voc
mb_melgan_csmsc
\
--voc_config
$voc_model_dir
/
$voc_config_file
\
--voc_ckpt
$voc_model_dir
/
$voc_ckpt_file
\
--voc_stat
$voc_model_dir
/
$voc_stat_file
\
--lang
zh
\
--device
cpu
\
--text
$testdata
\
--output_dir
./output
\
--log_file
./result.log
\
--am_streaming
True
\
--am_pad
12
\
--am_block
42
\
--voc_streaming
True
\
--voc_pad
14
\
--voc_block
14
\
paddlespeech/server/tests/tts/infer/test_online_tts.py
已删除
100644 → 0
浏览文件 @
9c0ceaac
此差异已折叠。
点击以展开。
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