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
49cb2579
D
DeepSpeech
项目概览
PaddlePaddle
/
DeepSpeech
大约 1 年 前同步成功
通知
206
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
49cb2579
编写于
9月 06, 2022
作者:
H
Hui Zhang
提交者:
GitHub
9月 06, 2022
浏览文件
操作
浏览文件
下载
差异文件
Merge pull request #2354 from THUzyt21/test
fix a small bug for benchmank
上级
025faa03
59e7444e
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
9 addition
and
8 deletion
+9
-8
examples/hey_snips/kws0/conf/mdtc.yaml
examples/hey_snips/kws0/conf/mdtc.yaml
+2
-2
tests/test_tipc/prepare.sh
tests/test_tipc/prepare.sh
+7
-6
未找到文件。
examples/hey_snips/kws0/conf/mdtc.yaml
浏览文件 @
49cb2579
...
...
@@ -3,7 +3,7 @@
# Data #
###########################################
dataset
:
'
paddlespeech.audio.datasets:HeySnips'
data_dir
:
'
/PATH/TO/DATA
/hey_snips_research_6k_en_train_eval_clean_ter'
data_dir
:
'
../tests
/hey_snips_research_6k_en_train_eval_clean_ter'
############################################
# Network Architecture #
...
...
@@ -46,4 +46,4 @@ num_workers: 16
checkpoint
:
'
./checkpoint/epoch_100/model.pdparams'
score_file
:
'
./scores.txt'
stats_file
:
'
./stats.0.txt'
img_file
:
'
./det.png'
\ No newline at end of file
img_file
:
'
./det.png'
tests/test_tipc/prepare.sh
浏览文件 @
49cb2579
...
...
@@ -22,7 +22,7 @@ model_name=$(func_parser_value "${lines[1]}")
echo
"model_name:"
${
model_name
}
trainer_list
=
$(
func_parser_value
"
${
lines
[14]
}
"
)
if
[
${
MODE
}
=
"benchmark_train"
]
;
then
if
[
[
${
MODE
}
=
"benchmark_train"
]
]
;
then
curPath
=
$(
readlink
-f
"
$(
dirname
"
$0
"
)
"
)
echo
"curPath:"
${
curPath
}
# /PaddleSpeech/tests/test_tipc
cd
${
curPath
}
/../..
...
...
@@ -36,10 +36,10 @@ if [ ${MODE} = "benchmark_train" ];then
pip
install
jsonlines
pip list
cd
-
if
[
${
model_name
}
==
"conformer"
]
;
then
if
[
[
${
model_name
}
==
"conformer"
]
]
;
then
# set the URL for aishell_tiny dataset
conformer_aishell_URL
=
${
conformer_aishell_URL
:-
"None"
}
if
[
${
conformer_aishell_URL
}
==
'None'
]
;
then
if
[
[
${
conformer_aishell_URL
}
==
'None'
]
]
;
then
echo
"please contact author to get the URL.
\n
"
exit
else
...
...
@@ -66,7 +66,7 @@ if [ ${MODE} = "benchmark_train" ];then
sed
-i
"s#data/#test_tipc/conformer/benchmark_train/data/#g"
${
curPath
}
/conformer/benchmark_train/conf/preprocess.yaml
fi
if
[
${
model_name
}
==
"pwgan"
]
;
then
if
[
[
${
model_name
}
==
"pwgan"
]
]
;
then
# 下载 csmsc 数据集并解压缩
wget
-nc
https://weixinxcxdb.oss-cn-beijing.aliyuncs.com/gwYinPinKu/BZNSYP.rar
mkdir
-p
BZNSYP
...
...
@@ -80,9 +80,10 @@ if [ ${MODE} = "benchmark_train" ];then
python ../paddlespeech/t2s/exps/gan_vocoder/normalize.py
--metadata
=
dump/test/raw/metadata.jsonl
--dumpdir
=
dump/test/norm
--stats
=
dump/train/feats_stats.npy
fi
if
[
${
model_name
}
==
"mdtc"
]
;
then
if
[
[
${
model_name
}
==
"mdtc"
]
]
;
then
# 下载 Snips 数据集并解压缩
wget
-nc
https://paddlespeech.bj.bcebos.com/datasets/hey_snips_kws_4.0.tar.gz.1 https://paddlespeech.bj.bcebos.com/datasets/hey_snips_https://paddlespeech.bj.bcebos.com/datasets/hey_snips_kws_4.0.tar.gz.2
wget https://paddlespeech.bj.bcebos.com/datasets/hey_snips_kws_4.0.tar.gz.1
wget https://paddlespeech.bj.bcebos.com/datasets/hey_snips_kws_4.0.tar.gz.2
cat
hey_snips_kws_4.0.tar.gz.
*
>
hey_snips_kws_4.0.tar.gz
rm
hey_snips_kws_4.0.tar.gz.
*
tar
-xzf
hey_snips_kws_4.0.tar.gz
...
...
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