-
Notifications
You must be signed in to change notification settings - Fork 1.9k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
[server] add paddle inference code #1425
Conversation
…into tts-server3
…into tts-server3
from utils.exception import ServerBaseException | ||
from utils.paddle_predictor import init_predictor | ||
from utils.paddle_predictor import run_model | ||
#from paddle.inference import Config |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
注释删除吧
am_tag = am + '-' + lang | ||
if phones_dict is None: | ||
print("please input phones_dict!") | ||
### 后续下载的模型里加上 phone 和 tone的 dict 就不用这个了 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
注释删除吧。
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这个是之前说的静态模型中没有这些词典,有的话就不需要这个 if 了,用的另一种获取方式词典
speechserving/speechserving/engine/tts/paddleinference/tts_engine.py
Outdated
Show resolved
Hide resolved
speechserving/speechserving/engine/tts/paddleinference/tts_engine.py
Outdated
Show resolved
Hide resolved
…into tts-server3
…into tts-server3
24000, | ||
}, | ||
# pwgan | ||
"pwgan_csmsc-zh": { |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Vocoder的采样率是需要和AM对应的, 所以Voc上也加上采样率,做校验吧。
@@ -0,0 +1,82 @@ | |||
# Copyright (c) 2021 PaddlePaddle Authors. All Rights Reserved. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
这部分代码后面和yinhui对下,看他是否能复用。
…into tts-server3
…into tts-server3
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM
PR types
New features
PR changes
fix audio process code
create a base paddle inference predictor code
create a tts engine code based on paddle inference
Describe
fix audio process code on audio_process.py
create a base paddle inference predictor code including base functions on paddle_predictor.py
create a tts engine code based on paddle inference on tts_engine.py
speech server
#1368
#1369