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
851ffd11
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
851ffd11
编写于
8月 02, 2022
作者:
小湉湉
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
replace default vocoder in seerver to mb_melgan, test=doc
上级
b0b3222f
变更
3
隐藏空白更改
内联
并排
Showing
3 changed file
with
15 addition
and
13 deletion
+15
-13
demos/speech_server/conf/application.yaml
demos/speech_server/conf/application.yaml
+11
-9
demos/streaming_tts_server/conf/tts_online_application.yaml
demos/streaming_tts_server/conf/tts_online_application.yaml
+2
-2
demos/streaming_tts_server/conf/tts_online_ws_application.yaml
.../streaming_tts_server/conf/tts_online_ws_application.yaml
+2
-2
未找到文件。
demos/speech_server/conf/application.yaml
浏览文件 @
851ffd11
...
@@ -7,7 +7,7 @@ host: 0.0.0.0
...
@@ -7,7 +7,7 @@ host: 0.0.0.0
port
:
8090
port
:
8090
# The task format in the engin_list is: <speech task>_<engine type>
# The task format in the engin_list is: <speech task>_<engine type>
# task choices = ['asr_python', 'asr_inference', 'tts_python', 'tts_inference', 'cls_python', 'cls_inference']
# task choices = ['asr_python', 'asr_inference', 'tts_python', 'tts_inference', 'cls_python', 'cls_inference'
, 'text_python', 'vector_python'
]
protocol
:
'
http'
protocol
:
'
http'
engine_list
:
[
'
asr_python'
,
'
tts_python'
,
'
cls_python'
,
'
text_python'
,
'
vector_python'
]
engine_list
:
[
'
asr_python'
,
'
tts_python'
,
'
cls_python'
,
'
text_python'
,
'
vector_python'
]
...
@@ -28,7 +28,6 @@ asr_python:
...
@@ -28,7 +28,6 @@ asr_python:
force_yes
:
True
force_yes
:
True
device
:
# set 'gpu:id' or 'cpu'
device
:
# set 'gpu:id' or 'cpu'
################### speech task: asr; engine_type: inference #######################
################### speech task: asr; engine_type: inference #######################
asr_inference
:
asr_inference
:
# model_type choices=['deepspeech2offline_aishell']
# model_type choices=['deepspeech2offline_aishell']
...
@@ -50,10 +49,11 @@ asr_inference:
...
@@ -50,10 +49,11 @@ asr_inference:
################################### TTS #########################################
################################### TTS #########################################
################### speech task: tts; engine_type: python #######################
################### speech task: tts; engine_type: python #######################
tts_python
:
tts_python
:
# am (acoustic model) choices=['speedyspeech_csmsc', 'fastspeech2_csmsc',
# am (acoustic model) choices=['speedyspeech_csmsc', 'fastspeech2_csmsc',
# 'fastspeech2_ljspeech', 'fastspeech2_aishell3',
# 'fastspeech2_ljspeech', 'fastspeech2_aishell3',
# 'fastspeech2_vctk']
# 'fastspeech2_vctk', 'fastspeech2_mix',
# 'tacotron2_csmsc', 'tacotron2_ljspeech']
am
:
'
fastspeech2_csmsc'
am
:
'
fastspeech2_csmsc'
am_config
:
am_config
:
am_ckpt
:
am_ckpt
:
...
@@ -64,8 +64,10 @@ tts_python:
...
@@ -64,8 +64,10 @@ tts_python:
spk_id
:
0
spk_id
:
0
# voc (vocoder) choices=['pwgan_csmsc', 'pwgan_ljspeech', 'pwgan_aishell3',
# voc (vocoder) choices=['pwgan_csmsc', 'pwgan_ljspeech', 'pwgan_aishell3',
# 'pwgan_vctk', 'mb_melgan_csmsc']
# 'pwgan_vctk', 'mb_melgan_csmsc', 'style_melgan_csmsc',
voc
:
'
pwgan_csmsc'
# 'hifigan_csmsc', 'hifigan_ljspeech', 'hifigan_aishell3',
# 'hifigan_vctk', 'wavernn_csmsc']
voc
:
'
mb_melgan_csmsc'
voc_config
:
voc_config
:
voc_ckpt
:
voc_ckpt
:
voc_stat
:
voc_stat
:
...
@@ -94,7 +96,7 @@ tts_inference:
...
@@ -94,7 +96,7 @@ tts_inference:
summary
:
True
# False -> do not show predictor config
summary
:
True
# False -> do not show predictor config
# voc (vocoder) choices=['pwgan_csmsc', 'mb_melgan_csmsc','hifigan_csmsc']
# voc (vocoder) choices=['pwgan_csmsc', 'mb_melgan_csmsc','hifigan_csmsc']
voc
:
'
pw
gan_csmsc'
voc
:
'
mb_mel
gan_csmsc'
voc_model
:
# the pdmodel file of your vocoder static model (XX.pdmodel)
voc_model
:
# the pdmodel file of your vocoder static model (XX.pdmodel)
voc_params
:
# the pdiparams file of your vocoder static model (XX.pdipparams)
voc_params
:
# the pdiparams file of your vocoder static model (XX.pdipparams)
voc_sample_rate
:
24000
voc_sample_rate
:
24000
...
...
demos/streaming_tts_server/conf/tts_online_application.yaml
浏览文件 @
851ffd11
...
@@ -79,7 +79,7 @@ tts_online-onnx:
...
@@ -79,7 +79,7 @@ tts_online-onnx:
# voc (vocoder) choices=['mb_melgan_csmsc_onnx, hifigan_csmsc_onnx']
# voc (vocoder) choices=['mb_melgan_csmsc_onnx, hifigan_csmsc_onnx']
# Both mb_melgan_csmsc_onnx and hifigan_csmsc_onnx support streaming voc inference
# Both mb_melgan_csmsc_onnx and hifigan_csmsc_onnx support streaming voc inference
voc
:
'
hifi
gan_csmsc_onnx'
voc
:
'
mb_mel
gan_csmsc_onnx'
voc_ckpt
:
voc_ckpt
:
voc_sample_rate
:
24000
voc_sample_rate
:
24000
voc_sess_conf
:
voc_sess_conf
:
...
@@ -100,4 +100,4 @@ tts_online-onnx:
...
@@ -100,4 +100,4 @@ tts_online-onnx:
voc_pad
:
14
voc_pad
:
14
# voc_upsample should be same as n_shift on voc config.
# voc_upsample should be same as n_shift on voc config.
voc_upsample
:
300
voc_upsample
:
300
\ No newline at end of file
demos/streaming_tts_server/conf/tts_online_ws_application.yaml
浏览文件 @
851ffd11
...
@@ -79,7 +79,7 @@ tts_online-onnx:
...
@@ -79,7 +79,7 @@ tts_online-onnx:
# voc (vocoder) choices=['mb_melgan_csmsc_onnx, hifigan_csmsc_onnx']
# voc (vocoder) choices=['mb_melgan_csmsc_onnx, hifigan_csmsc_onnx']
# Both mb_melgan_csmsc_onnx and hifigan_csmsc_onnx support streaming voc inference
# Both mb_melgan_csmsc_onnx and hifigan_csmsc_onnx support streaming voc inference
voc
:
'
hifi
gan_csmsc_onnx'
voc
:
'
mb_mel
gan_csmsc_onnx'
voc_ckpt
:
voc_ckpt
:
voc_sample_rate
:
24000
voc_sample_rate
:
24000
voc_sess_conf
:
voc_sess_conf
:
...
@@ -100,4 +100,4 @@ tts_online-onnx:
...
@@ -100,4 +100,4 @@ tts_online-onnx:
voc_pad
:
14
voc_pad
:
14
# voc_upsample should be same as n_shift on voc config.
# voc_upsample should be same as n_shift on voc config.
voc_upsample
:
300
voc_upsample
:
300
\ No newline at end of file
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