Hui Zhang
3 years ago
committed by
GitHub
commit
2886ab9373
@ -0,0 +1,114 @@
|
||||
#!/usr/bin/python
|
||||
import argparse
|
||||
import os
|
||||
|
||||
import yaml
|
||||
|
||||
|
||||
def change_speech_yaml(yaml_name: str, device: str):
|
||||
"""Change the settings of the device under the voice task configuration file
|
||||
|
||||
Args:
|
||||
yaml_name (str): asr or asr_pd or tts or tts_pd
|
||||
cpu (bool): True means set device to "cpu"
|
||||
model_type (dict): change model type
|
||||
"""
|
||||
if "asr" in yaml_name:
|
||||
dirpath = "./conf/asr/"
|
||||
elif 'tts' in yaml_name:
|
||||
dirpath = "./conf/tts/"
|
||||
yamlfile = dirpath + yaml_name + ".yaml"
|
||||
tmp_yamlfile = dirpath + yaml_name + "_tmp.yaml"
|
||||
os.system("cp %s %s" % (yamlfile, tmp_yamlfile))
|
||||
|
||||
with open(tmp_yamlfile) as f, open(yamlfile, "w+", encoding="utf-8") as fw:
|
||||
y = yaml.safe_load(f)
|
||||
if device == 'cpu':
|
||||
print("Set device: cpu")
|
||||
if yaml_name == 'asr':
|
||||
y['device'] = 'cpu'
|
||||
elif yaml_name == 'asr_pd':
|
||||
y['am_predictor_conf']['device'] = 'cpu'
|
||||
elif yaml_name == 'tts':
|
||||
y['device'] = 'cpu'
|
||||
elif yaml_name == 'tts_pd':
|
||||
y['am_predictor_conf']['device'] = 'cpu'
|
||||
y['voc_predictor_conf']['device'] = 'cpu'
|
||||
elif device == 'gpu':
|
||||
print("Set device: gpu")
|
||||
if yaml_name == 'asr':
|
||||
y['device'] = 'gpu:0'
|
||||
elif yaml_name == 'asr_pd':
|
||||
y['am_predictor_conf']['device'] = 'gpu:0'
|
||||
elif yaml_name == 'tts':
|
||||
y['device'] = 'gpu:0'
|
||||
elif yaml_name == 'tts_pd':
|
||||
y['am_predictor_conf']['device'] = 'gpu:0'
|
||||
y['voc_predictor_conf']['device'] = 'gpu:0'
|
||||
else:
|
||||
print("Please set correct device: cpu or gpu.")
|
||||
|
||||
print("The content of '%s': " % (yamlfile))
|
||||
print(yaml.dump(y, default_flow_style=False, sort_keys=False))
|
||||
yaml.dump(y, fw, allow_unicode=True)
|
||||
os.system("rm %s" % (tmp_yamlfile))
|
||||
print("Change %s successfully." % (yamlfile))
|
||||
|
||||
|
||||
def change_app_yaml(task: str, engine_type: str):
|
||||
"""Change the engine type and corresponding configuration file of the speech task in application.yaml
|
||||
|
||||
Args:
|
||||
task (str): asr or tts
|
||||
"""
|
||||
yamlfile = "./conf/application.yaml"
|
||||
tmp_yamlfile = "./conf/application_tmp.yaml"
|
||||
os.system("cp %s %s" % (yamlfile, tmp_yamlfile))
|
||||
with open(tmp_yamlfile) as f, open(yamlfile, "w+", encoding="utf-8") as fw:
|
||||
y = yaml.safe_load(f)
|
||||
y['engine_type'][task] = engine_type
|
||||
path_list = ["./conf/", task, "/", task]
|
||||
if engine_type == 'python':
|
||||
path_list.append(".yaml")
|
||||
|
||||
elif engine_type == 'inference':
|
||||
path_list.append("_pd.yaml")
|
||||
y['engine_backend'][task] = ''.join(path_list)
|
||||
print("The content of './conf/application.yaml': ")
|
||||
print(yaml.dump(y, default_flow_style=False, sort_keys=False))
|
||||
yaml.dump(y, fw, allow_unicode=True)
|
||||
os.system("rm %s" % (tmp_yamlfile))
|
||||
print("Change %s successfully." % (yamlfile))
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument(
|
||||
'--change_task',
|
||||
type=str,
|
||||
default=None,
|
||||
help='Change task',
|
||||
choices=[
|
||||
'app-asr-python',
|
||||
'app-asr-inference',
|
||||
'app-tts-python',
|
||||
'app-tts-inference',
|
||||
'speech-asr-cpu',
|
||||
'speech-asr-gpu',
|
||||
'speech-asr_pd-cpu',
|
||||
'speech-asr_pd-gpu',
|
||||
'speech-tts-cpu',
|
||||
'speech-tts-gpu',
|
||||
'speech-tts_pd-cpu',
|
||||
'speech-tts_pd-gpu',
|
||||
],
|
||||
required=True)
|
||||
args = parser.parse_args()
|
||||
|
||||
types = args.change_task.split("-")
|
||||
if types[0] == "app":
|
||||
change_app_yaml(types[1], types[2])
|
||||
elif types[0] == "speech":
|
||||
change_speech_yaml(types[1], types[2])
|
||||
else:
|
||||
print("Error change task, please check change_task.")
|
||||
@ -0,0 +1,27 @@
|
||||
# This is the parameter configuration file for PaddleSpeech Serving.
|
||||
|
||||
##################################################################
|
||||
# SERVER SETTING #
|
||||
##################################################################
|
||||
host: 127.0.0.1
|
||||
port: 8090
|
||||
|
||||
##################################################################
|
||||
# CONFIG FILE #
|
||||
##################################################################
|
||||
# add engine backend type (Options: asr, tts) and config file here.
|
||||
# Adding a speech task to engine_backend means starting the service.
|
||||
engine_backend:
|
||||
asr: 'conf/asr/asr.yaml'
|
||||
tts: 'conf/tts/tts.yaml'
|
||||
|
||||
# The engine_type of speech task needs to keep the same type as the config file of speech task.
|
||||
# E.g: The engine_type of asr is 'python', the engine_backend of asr is 'XX/asr.yaml'
|
||||
# E.g: The engine_type of asr is 'inference', the engine_backend of asr is 'XX/asr_pd.yaml'
|
||||
#
|
||||
# add engine type (Options: python, inference)
|
||||
engine_type:
|
||||
asr: 'python'
|
||||
tts: 'python'
|
||||
|
||||
|
||||
@ -0,0 +1,8 @@
|
||||
model: 'conformer_wenetspeech'
|
||||
lang: 'zh'
|
||||
sample_rate: 16000
|
||||
cfg_path: # [optional]
|
||||
ckpt_path: # [optional]
|
||||
decode_method: 'attention_rescoring'
|
||||
force_yes: True
|
||||
device: # set 'gpu:id' or 'cpu'
|
||||
@ -0,0 +1,26 @@
|
||||
# This is the parameter configuration file for ASR server.
|
||||
# These are the static models that support paddle inference.
|
||||
|
||||
##################################################################
|
||||
# ACOUSTIC MODEL SETTING #
|
||||
# am choices=['deepspeech2offline_aishell'] TODO
|
||||
##################################################################
|
||||
model_type: 'deepspeech2offline_aishell'
|
||||
am_model: # the pdmodel file of am static model [optional]
|
||||
am_params: # the pdiparams file of am static model [optional]
|
||||
lang: 'zh'
|
||||
sample_rate: 16000
|
||||
cfg_path:
|
||||
decode_method:
|
||||
force_yes: True
|
||||
|
||||
am_predictor_conf:
|
||||
device: # set 'gpu:id' or 'cpu'
|
||||
switch_ir_optim: True
|
||||
glog_info: False # True -> print glog
|
||||
summary: True # False -> do not show predictor config
|
||||
|
||||
|
||||
##################################################################
|
||||
# OTHERS #
|
||||
##################################################################
|
||||
@ -0,0 +1,32 @@
|
||||
# This is the parameter configuration file for TTS server.
|
||||
|
||||
##################################################################
|
||||
# ACOUSTIC MODEL SETTING #
|
||||
# am choices=['speedyspeech_csmsc', 'fastspeech2_csmsc',
|
||||
# 'fastspeech2_ljspeech', 'fastspeech2_aishell3',
|
||||
# 'fastspeech2_vctk']
|
||||
##################################################################
|
||||
am: 'fastspeech2_csmsc'
|
||||
am_config:
|
||||
am_ckpt:
|
||||
am_stat:
|
||||
phones_dict:
|
||||
tones_dict:
|
||||
speaker_dict:
|
||||
spk_id: 0
|
||||
|
||||
##################################################################
|
||||
# VOCODER SETTING #
|
||||
# voc choices=['pwgan_csmsc', 'pwgan_ljspeech', 'pwgan_aishell3',
|
||||
# 'pwgan_vctk', 'mb_melgan_csmsc']
|
||||
##################################################################
|
||||
voc: 'pwgan_csmsc'
|
||||
voc_config:
|
||||
voc_ckpt:
|
||||
voc_stat:
|
||||
|
||||
##################################################################
|
||||
# OTHERS #
|
||||
##################################################################
|
||||
lang: 'zh'
|
||||
device: # set 'gpu:id' or 'cpu'
|
||||
@ -0,0 +1,42 @@
|
||||
# This is the parameter configuration file for TTS server.
|
||||
# These are the static models that support paddle inference.
|
||||
|
||||
##################################################################
|
||||
# ACOUSTIC MODEL SETTING #
|
||||
# am choices=['speedyspeech_csmsc', 'fastspeech2_csmsc']
|
||||
##################################################################
|
||||
am: 'fastspeech2_csmsc'
|
||||
am_model: # the pdmodel file of your am static model (XX.pdmodel)
|
||||
am_params: # the pdiparams file of your am static model (XX.pdipparams)
|
||||
am_sample_rate: 24000
|
||||
phones_dict:
|
||||
tones_dict:
|
||||
speaker_dict:
|
||||
spk_id: 0
|
||||
|
||||
am_predictor_conf:
|
||||
device: # set 'gpu:id' or 'cpu'
|
||||
switch_ir_optim: True
|
||||
glog_info: False # True -> print glog
|
||||
summary: True # False -> do not show predictor config
|
||||
|
||||
|
||||
##################################################################
|
||||
# VOCODER SETTING #
|
||||
# voc choices=['pwgan_csmsc', 'mb_melgan_csmsc','hifigan_csmsc']
|
||||
##################################################################
|
||||
voc: 'pwgan_csmsc'
|
||||
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_sample_rate: 24000
|
||||
|
||||
voc_predictor_conf:
|
||||
device: # set 'gpu:id' or 'cpu'
|
||||
switch_ir_optim: True
|
||||
glog_info: False # True -> print glog
|
||||
summary: True # False -> do not show predictor config
|
||||
|
||||
##################################################################
|
||||
# OTHERS #
|
||||
##################################################################
|
||||
lang: 'zh'
|
||||
@ -0,0 +1,185 @@
|
||||
#!/bin/bash
|
||||
# bash test_server_client.sh
|
||||
|
||||
StartService(){
|
||||
# Start service
|
||||
paddlespeech_server start --config_file $config_file 1>>log/server.log 2>>log/server.log.wf &
|
||||
echo $! > pid
|
||||
|
||||
start_num=$(cat log/server.log.wf | grep "INFO: Uvicorn running on http://" -c)
|
||||
flag="normal"
|
||||
while [[ $start_num -lt $target_start_num && $flag == "normal" ]]
|
||||
do
|
||||
start_num=$(cat log/server.log.wf | grep "INFO: Uvicorn running on http://" -c)
|
||||
# start service failed
|
||||
if [ $(cat log/server.log.wf | grep -i "error" -c) -gt $error_time ];then
|
||||
echo "Service started failed." | tee -a ./log/test_result.log
|
||||
error_time=$(cat log/server.log.wf | grep -i "error" -c)
|
||||
flag="unnormal"
|
||||
fi
|
||||
done
|
||||
}
|
||||
|
||||
ClientTest(){
|
||||
# Client test
|
||||
# test asr client
|
||||
paddlespeech_client asr --server_ip $server_ip --port $port --input ./zh.wav
|
||||
((test_times+=1))
|
||||
paddlespeech_client asr --server_ip $server_ip --port $port --input ./zh.wav
|
||||
((test_times+=1))
|
||||
|
||||
# test tts client
|
||||
paddlespeech_client tts --server_ip $server_ip --port $port --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav
|
||||
((test_times+=1))
|
||||
paddlespeech_client tts --server_ip $server_ip --port $port --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav
|
||||
((test_times+=1))
|
||||
}
|
||||
|
||||
GetTestResult() {
|
||||
# Determine if the test was successful
|
||||
response_success_time=$(cat log/server.log | grep "200 OK" -c)
|
||||
if (( $response_success_time == $test_times )) ; then
|
||||
echo "Testing successfully. The service configuration is: asr engine type: $1; tts engine type: $1; device: $2." | tee -a ./log/test_result.log
|
||||
else
|
||||
echo "Testing failed. The service configuration is: asr engine type: $1; tts engine type: $1; device: $2." | tee -a ./log/test_result.log
|
||||
fi
|
||||
test_times=$response_success_time
|
||||
}
|
||||
|
||||
|
||||
mkdir -p log
|
||||
rm -rf log/server.log.wf
|
||||
rm -rf log/server.log
|
||||
rm -rf log/test_result.log
|
||||
|
||||
config_file=./conf/application.yaml
|
||||
server_ip=$(cat $config_file | grep "host" | awk -F " " '{print $2}')
|
||||
port=$(cat $config_file | grep "port" | awk '/port:/ {print $2}')
|
||||
|
||||
echo "Sevice ip: $server_ip" | tee ./log/test_result.log
|
||||
echo "Sevice port: $port" | tee -a ./log/test_result.log
|
||||
|
||||
# whether a process is listening on $port
|
||||
pid=`lsof -i :"$port"|grep -v "PID" | awk '{print $2}'`
|
||||
if [ "$pid" != "" ]; then
|
||||
echo "The port: $port is occupied, please change another port"
|
||||
exit
|
||||
fi
|
||||
|
||||
# download test audios for ASR client
|
||||
wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespeech.bj.bcebos.com/PaddleAudio/en.wav
|
||||
|
||||
|
||||
target_start_num=0 # the number of start service
|
||||
test_times=0 # The number of client test
|
||||
error_time=0 # The number of error occurrences in the startup failure server.log.wf file
|
||||
|
||||
# start server: asr engine type: python; tts engine type: python; device: gpu
|
||||
echo "Start the service: asr engine type: python; tts engine type: python; device: gpu" | tee -a ./log/test_result.log
|
||||
((target_start_num+=1))
|
||||
StartService
|
||||
|
||||
if [[ $start_num -eq $target_start_num && $flag == "normal" ]]; then
|
||||
echo "Service started successfully." | tee -a ./log/test_result.log
|
||||
ClientTest
|
||||
echo "This round of testing is over." | tee -a ./log/test_result.log
|
||||
|
||||
GetTestResult python gpu
|
||||
else
|
||||
echo "Service failed to start, no client test."
|
||||
target_start_num=$start_num
|
||||
|
||||
fi
|
||||
|
||||
kill -9 `cat pid`
|
||||
rm -rf pid
|
||||
sleep 2s
|
||||
echo "**************************************************************************************" | tee -a ./log/test_result.log
|
||||
|
||||
|
||||
|
||||
# start server: asr engine type: python; tts engine type: python; device: cpu
|
||||
python change_yaml.py --change_task speech-asr-cpu # change asr.yaml device: cpu
|
||||
python change_yaml.py --change_task speech-tts-cpu # change tts.yaml device: cpu
|
||||
|
||||
echo "Start the service: asr engine type: python; tts engine type: python; device: cpu" | tee -a ./log/test_result.log
|
||||
((target_start_num+=1))
|
||||
StartService
|
||||
|
||||
if [[ $start_num -eq $target_start_num && $flag == "normal" ]]; then
|
||||
echo "Service started successfully." | tee -a ./log/test_result.log
|
||||
ClientTest
|
||||
echo "This round of testing is over." | tee -a ./log/test_result.log
|
||||
|
||||
GetTestResult python cpu
|
||||
else
|
||||
echo "Service failed to start, no client test."
|
||||
target_start_num=$start_num
|
||||
|
||||
fi
|
||||
|
||||
kill -9 `cat pid`
|
||||
rm -rf pid
|
||||
sleep 2s
|
||||
echo "**************************************************************************************" | tee -a ./log/test_result.log
|
||||
|
||||
|
||||
# start server: asr engine type: inference; tts engine type: inference; device: gpu
|
||||
python change_yaml.py --change_task app-asr-inference # change application.yaml, asr engine_type: inference; asr engine_backend: asr_pd.yaml
|
||||
python change_yaml.py --change_task app-tts-inference # change application.yaml, tts engine_type: inference; tts engine_backend: tts_pd.yaml
|
||||
|
||||
echo "Start the service: asr engine type: inference; tts engine type: inference; device: gpu" | tee -a ./log/test_result.log
|
||||
((target_start_num+=1))
|
||||
StartService
|
||||
|
||||
if [[ $start_num -eq $target_start_num && $flag == "normal" ]]; then
|
||||
echo "Service started successfully." | tee -a ./log/test_result.log
|
||||
ClientTest
|
||||
echo "This round of testing is over." | tee -a ./log/test_result.log
|
||||
|
||||
GetTestResult inference gpu
|
||||
else
|
||||
echo "Service failed to start, no client test."
|
||||
target_start_num=$start_num
|
||||
|
||||
fi
|
||||
|
||||
kill -9 `cat pid`
|
||||
rm -rf pid
|
||||
sleep 2s
|
||||
echo "**************************************************************************************" | tee -a ./log/test_result.log
|
||||
|
||||
|
||||
# start server: asr engine type: inference; tts engine type: inference; device: cpu
|
||||
python change_yaml.py --change_task speech-asr_pd-cpu # change asr_pd.yaml device: cpu
|
||||
python change_yaml.py --change_task speech-tts_pd-cpu # change tts_pd.yaml device: cpu
|
||||
|
||||
echo "start the service: asr engine type: inference; tts engine type: inference; device: cpu" | tee -a ./log/test_result.log
|
||||
((target_start_num+=1))
|
||||
StartService
|
||||
|
||||
if [[ $start_num -eq $target_start_num && $flag == "normal" ]]; then
|
||||
echo "Service started successfully." | tee -a ./log/test_result.log
|
||||
ClientTest
|
||||
echo "This round of testing is over." | tee -a ./log/test_result.log
|
||||
|
||||
GetTestResult inference cpu
|
||||
else
|
||||
echo "Service failed to start, no client test."
|
||||
target_start_num=$start_num
|
||||
|
||||
fi
|
||||
|
||||
kill -9 `cat pid`
|
||||
rm -rf pid
|
||||
sleep 2s
|
||||
echo "**************************************************************************************" | tee -a ./log/test_result.log
|
||||
|
||||
echo "All tests completed." | tee -a ./log/test_result.log
|
||||
|
||||
# sohw all the test results
|
||||
echo "***************** Here are all the test results ********************"
|
||||
cat ./log/test_result.log
|
||||
|
||||
# Restoring conf is the same as demos/speech_server
|
||||
cp ../../../demos/speech_server/conf/ ./ -rf
|
||||
Loading…
Reference in new issue