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
67939d0d
D
DeepSpeech
项目概览
PaddlePaddle
/
DeepSpeech
10 个月 前同步成功
通知
200
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
前往新版Gitcode,体验更适合开发者的 AI 搜索 >>
提交
67939d0d
编写于
5月 14, 2022
作者:
X
xiongxinlei
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
add check asr server model type, test=doc
上级
15271445
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
30 addition
and
15 deletion
+30
-15
demos/streaming_asr_server/conf/application.yaml
demos/streaming_asr_server/conf/application.yaml
+3
-2
paddlespeech/server/engine/asr/online/asr_engine.py
paddlespeech/server/engine/asr/online/asr_engine.py
+27
-13
未找到文件。
demos/streaming_asr_server/conf/application.yaml
浏览文件 @
67939d0d
...
...
@@ -29,7 +29,8 @@ asr_online:
cfg_path
:
decode_method
:
force_yes
:
True
device
:
cpu
# cpu or gpu:id
device
:
'
cpu'
# cpu or gpu:id
decode_method
:
"
attention_rescoring"
am_predictor_conf
:
device
:
# set 'gpu:id' or 'cpu'
switch_ir_optim
:
True
...
...
@@ -42,4 +43,4 @@ asr_online:
window_ms
:
25
# ms
shift_ms
:
10
# ms
sample_rate
:
16000
sample_width
:
2
\ No newline at end of file
sample_width
:
2
paddlespeech/server/engine/asr/online/asr_engine.py
浏览文件 @
67939d0d
...
...
@@ -13,6 +13,7 @@
# limitations under the License.
import
copy
import
os
import
sys
from
typing
import
Optional
import
numpy
as
np
...
...
@@ -588,7 +589,7 @@ class ASRServerExecutor(ASRExecutor):
self
.
pretrained_models
=
pretrained_models
def
_init_from_path
(
self
,
model_type
:
str
=
'deepspeech2online_aishell'
,
model_type
:
str
=
None
,
am_model
:
Optional
[
os
.
PathLike
]
=
None
,
am_params
:
Optional
[
os
.
PathLike
]
=
None
,
lang
:
str
=
'zh'
,
...
...
@@ -599,6 +600,12 @@ class ASRServerExecutor(ASRExecutor):
"""
Init model and other resources from a specific path.
"""
if
not
model_type
or
not
lang
or
not
sample_rate
:
logger
.
error
(
"The model type or lang or sample rate is None, please input an valid server parameter yaml"
)
return
False
self
.
model_type
=
model_type
self
.
sample_rate
=
sample_rate
sample_rate_str
=
'16k'
if
sample_rate
==
16000
else
'8k'
...
...
@@ -1028,20 +1035,27 @@ class ASREngine(BaseEngine):
self
.
device
=
paddle
.
get_device
()
logger
.
info
(
f
"paddlespeech_server set the device:
{
self
.
device
}
"
)
paddle
.
set_device
(
self
.
device
)
except
BaseException
:
except
BaseException
as
e
:
logger
.
error
(
"Set device failed, please check if device
is already used and the parameter 'device' in the yaml file"
f
"Set device failed, please check if device '
{
self
.
device
}
'
is already used and the parameter 'device' in the yaml file"
)
self
.
executor
.
_init_from_path
(
model_type
=
self
.
config
.
model_type
,
am_model
=
self
.
config
.
am_model
,
am_params
=
self
.
config
.
am_params
,
lang
=
self
.
config
.
lang
,
sample_rate
=
self
.
config
.
sample_rate
,
cfg_path
=
self
.
config
.
cfg_path
,
decode_method
=
self
.
config
.
decode_method
,
am_predictor_conf
=
self
.
config
.
am_predictor_conf
)
logger
.
error
(
"If all GPU or XPU is used, you can set the server to 'cpu'"
)
sys
.
exit
(
-
1
)
if
not
self
.
executor
.
_init_from_path
(
model_type
=
self
.
config
.
model_type
,
am_model
=
self
.
config
.
am_model
,
am_params
=
self
.
config
.
am_params
,
lang
=
self
.
config
.
lang
,
sample_rate
=
self
.
config
.
sample_rate
,
cfg_path
=
self
.
config
.
cfg_path
,
decode_method
=
self
.
config
.
decode_method
,
am_predictor_conf
=
self
.
config
.
am_predictor_conf
):
logger
.
error
(
"Init the ASR server occurs error, please check the server configuration yaml"
)
return
False
logger
.
info
(
"Initialize ASR server engine successfully."
)
return
True
...
...
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