msb-public
/
PaddleSpeech
mirror of https://github.com/PaddlePaddle/PaddleSpeech
1
0
Code Issues Projects Releases Wiki Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Branches Tags
${ item.name }
Create tag ${ searchTerm }
Create branch ${ searchTerm }
from '8f5e61090b'
${ noResults }
PaddleSpeech/paddlespeech/server
History
Hui Zhang e04cd18846
Merge pull request #2050 from zh794390558/onnx_quant 		2 years ago
..
bin rename readme and fixed conflict 2 years ago
conf support onnx quantize 2 years ago
engine Merge pull request #2048 from KPatr1ck/import_bug 2 years ago
restful update engine, test=doc 2 years ago
tests update the vector readme, test=doc 3 years ago
utils code format 2 years ago
ws ds2 inference as sepearte engine for streaming asr 2 years ago
README.md update the vector and text readme, test=doc 3 years ago
README_cn.md [server] update readme (#1851) 3 years ago
__init__.py add server cls, test=doc 3 years ago
base_commands.py added engine type and asr inference , test=doc 3 years ago
entry.py added engine type and asr inference , test=doc 3 years ago
executor.py add server demo, test=doc 3 years ago
util.py Refactor paddleaudio to paddlespeech.audio 2 years ago

README.md

PaddleSpeech Server Command Line

(简体中文|English)

The simplest approach to use PaddleSpeech Server including server and client.

PaddleSpeech Server

Help

paddlespeech_server help

Start the server

First set the service-related configuration parameters, similar to ./conf/application.yaml. Set engine_list, which represents the speech tasks included in the service to be started. Note: If the service can be started normally in the container, but the client access IP is unreachable, you can try to replace the host address in the configuration file with the local IP address.

Then start the service:

paddlespeech_server start --config_file ./conf/application.yaml

PaddleSpeech Client

Help

paddlespeech_client help

Access speech recognition services

paddlespeech_client asr --server_ip 127.0.0.1 --port 8090 --input input_16k.wav

Access text to speech services

paddlespeech_client tts --server_ip 127.0.0.1 --port 8090 --input "你好，欢迎使用百度飞桨深度学习框架！" --output output.wav

Access audio classification services

paddlespeech_client cls --server_ip 127.0.0.1 --port 8090 --input input.wav

Online ASR Server

Lanuch online asr server

paddlespeech_server start --config_file conf/ws_conformer_application.yaml

Access online asr server

paddlespeech_client asr_online  --server_ip 127.0.0.1 --port 8090 --input input_16k.wav

Online TTS Server

Lanuch online tts server

paddlespeech_server start --config_file conf/tts_online_application.yaml

Access online tts server

paddlespeech_client tts_online  --server_ip 127.0.0.1 --port 8092 --input "您好，欢迎使用百度飞桨深度学习框架！" --output output.wav

Speaker Verification

Lanuch speaker verification server

paddlespeech_server start --config_file conf/vector_application.yaml

Extract speaker embedding from aduio

paddlespeech_client vector --task spk  --server_ip 127.0.0.1 --port 8090 --input 85236145389.wav

Get score with speaker audio embedding

paddlespeech_client vector --task score  --server_ip 127.0.0.1 --port 8090 --enroll 123456789.wav --test 85236145389.wav