testadmin
/
Parakeet
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Merge pull request #157 from iclementine/cice 

add ci/ce scripts
This commit is contained in:
TianYuan 2021-09-06 11:43:26 +08:00 committed by GitHub
parent a9f0f5c3c0 0dcb7f313f
commit db4122f047
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
6 changed files with 513 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
examples/parallelwave_gan/baker/config.py
View File

@ -13,9 +13,12 @@
# limitations under the License.
import yaml
from pathlib import Path
from yacs.config import CfgNode as Configuration
with open("conf/default.yaml", 'rt') as f:
config_path = (Path(__file__).parent / "conf" / "default.yaml").resolve()
with open(config_path, 'rt') as f:
_C = yaml.safe_load(f)
_C = Configuration(_C)

2
examples/speedyspeech/baker/config.py
View File

@ -18,7 +18,7 @@ from pathlib import Path
config_path = (Path(__file__).parent / "conf" / "default.yaml").resolve()
with open("conf/default.yaml", 'rt') as f:
with open(config_path, 'rt') as f:
_C = yaml.safe_load(f)
_C = Configuration(_C)

35
examples/speedyspeech/baker/inference.py
View File

@ -12,6 +12,7 @@
# See the License for the specific language governing permissions and
# limitations under the License.
import os
import argparse
from pathlib import Path
@ -31,6 +32,8 @@ def main():
type=str,
help="text to synthesize, a 'utt_id sentence' pair per line")
parser.add_argument("--output-dir", type=str, help="output dir")
parser.add_argument(
"--enable-auto-log", action="store_true", help="use auto log")
args, _ = parser.parse_known_args()
@ -48,6 +51,23 @@ def main():
pwg_config.enable_memory_optim()
pwg_predictor = inference.create_predictor(pwg_config)
if args.enable_auto_log:
import auto_log
os.makedirs("output", exist_ok=True)
pid = os.getpid()
logger = auto_log.AutoLogger(
model_name="speedyspeech",
model_precision='float32',
batch_size=1,
data_shape="dynamic",
save_path="./output/auto_log.log",
inference_config=speedyspeech_config,
pids=pid,
process_name=None,
gpu_ids=0,
time_keys=['preprocess_time', 'inference_time', 'postprocess_time'],
warmup=0)
output_dir = Path(args.output_dir)
output_dir.mkdir(parents=True, exist_ok=True)
sentences = []
@ -57,10 +77,16 @@ def main():
sentences.append((utt_id, sentence))
for utt_id, sentence in sentences:
if args.enable_auto_log:
logger.times.start()
phones, tones = text_analysis(sentence)
phones = phones.numpy()
tones = tones.numpy()
if args.enable_auto_log:
logger.times.stamp()
input_names = speedyspeech_predictor.get_input_names()
phones_handle = speedyspeech_predictor.get_input_handle(input_names[0])
tones_handle = speedyspeech_predictor.get_input_handle(input_names[1])
@ -86,9 +112,18 @@ def main():
output_handle = pwg_predictor.get_output_handle(output_names[0])
wav = output_data = output_handle.copy_to_cpu()
if args.enable_auto_log:
logger.times.stamp()
sf.write(output_dir / (utt_id + ".wav"), wav, samplerate=24000)
if args.enable_auto_log:
logger.times.end(stamp=True)
print(f"{utt_id} done!")
if args.enable_auto_log:
logger.report()
if __name__ == "__main__":
main()

58
tests/prepare.sh Normal file
View File

@ -0,0 +1,58 @@
#!/bin/bash
# usage bash prepare.sh MODE
# FILENAME=$1
# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer', 'infer']
MODE=$1
# dataline=$(cat ${FILENAME})
# parser params
IFS=$'\n'
lines=(${dataline})
function func_parser_key(){
strs=$1
IFS=":"
array=(${strs})
tmp=${array[0]}
echo ${tmp}
}
function func_parser_value(){
strs=$1
IFS=":"
array=(${strs})
tmp=${array[1]}
echo ${tmp}
}
IFS=$'\n'
# The training params
model_name=$(func_parser_value "${lines[1]}")
trainer_list=$(func_parser_value "${lines[14]}")
# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer']
if [ ${MODE} = "lite_train_infer" ];then
# pretrain lite train data
wget -nc -P ./pretrain_models/ https://paddlespeech.bj.bcebos.com/Parakeet/speedyspeech_baker_ckpt_0.4.zip
wget -nc -P ./pretrain_models/ https://paddlespeech.bj.bcebos.com/Parakeet/pwg_baker_ckpt_0.4.zip
(cd ./pretrain_models && unzip speedyspeech_baker_ckpt_0.4.zip && unzip pwg_baker_ckpt_0.4.zip)
# generate a config patch
echo 'max_epoch: 30' > lite_train_infer.yaml
# download data
rm -rf ./train_data/mini_BZNSYP
wget -nc -P ./train_data/ https://paddlespeech.bj.bcebos.com/datasets/CE/speedyspeech/mini_BZNSYP.tar.gz
cd ./train_data/ && tar xzf mini_BZNSYP.tar.gz
cd ../
elif [ ${MODE} = "whole_train_infer" ];then
wget -nc -P ./pretrain_models/ https://paddlespeech.bj.bcebos.com/Parakeet/speedyspeech_baker_ckpt_0.4.zip
wget -nc -P ./pretrain_models/ https://paddlespeech.bj.bcebos.com/Parakeet/pwg_baker_ckpt_0.4.zip
(cd ./pretrain_models && unzip speedyspeech_baker_ckpt_0.4.zip && unzip pwg_baker_ckpt_0.4.zip)
rm -rf ./train_data/processed_BZNSYP
wget -nc -P ./train_data/ https://paddlespeech.bj.bcebos.com/datasets/CE/speedyspeech/processed_BZNSYP.tar.gz
cd ./train_data/ && tar xzf processed_BZNSYP.tar.gz
ln -s ./dump ./BZNSYP
cd ../
else
# whole infer using paddle inference library
wget -nc -P ./pretrain_models/ https://paddlespeech.bj.bcebos.com/Parakeet/speedyspeech_pwg_inference_0.4.zip
(cd ./pretrain_models && unzip speedyspeech_pwg_inference_0.4.zip)
fi

51
tests/speedyspeech_params.txt Normal file
View File

@ -0,0 +1,51 @@
===========================train_params===========================
model_name:speedyspeech
python:python3.7
gpu_list:0|0,1
null:null
null:null
null:null
null:null
null:null
null:null
null:null
null:null
null:null
##
trainer:lite_train|norm_train
norm_train:../examples/speedyspeech/baker/train.py --train-metadata=train_data/BZNSYP/train/norm/metadata.jsonl --dev-metadata=train_data/BZNSYP/dev/norm/metadata.jsonl --output-dir=exp/lite --nprocs=1
null:null
null:null
null:null
lite_train:../examples/speedyspeech/baker/train.py --train-metadata=train_data/mini_BZNSYP/train/norm/metadata.jsonl --dev-metadata=train_data/mini_BZNSYP/dev/norm/metadata.jsonl --config=lite_train_infer.yaml --output-dir=exp/default --nprocs=1
null:null
##
===========================eval_params===========================
eval:../examples/speedyspeech/baker/synthesize_e2e.py --speedyspeech-config=../examples/speedyspeech/baker/conf/default.yaml --speedyspeech-checkpoint=pretrain_models/speedyspeech_baker_ckpt_0.4/speedyspeech_snapshot_iter_91800.pdz --speedyspeech-stat=pretrain_models/speedyspeech_baker_ckpt_0.4/speedy_speech_stats.npy --pwg-config=../examples/parallelwave_gan/baker/conf/default.yaml --pwg-checkpoint=pretrain_models/pwg_baker_ckpt_0.4/pwg_snapshot_iter_400000.pdz --pwg-stat=pretrain_models/pwg_baker_ckpt_0.4/pwg_stats.npy --text=../examples/speedyspeech/baker/sentences.txt --output-dir=e2e --inference-dir=inference --device="gpu"
null:null
##
===========================infer_params===========================
null:null
null:null
null:null
null:null
null:null
null:null
null:null
null:null
##
null:null
null:null
null:null
inference:../examples/speedyspeech/baker/inference.py --inference-dir=pretrain_models/speedyspeech_pwg_inference_0.4 --text=../examples/speedyspeech/baker/sentences.txt --output-dir=inference_out --enable-auto-log
--use_gpu:True
null:null
null:null
null:null
null:null
null:null
null:null
null:null
null:null
null:null
null:null

364
tests/test.sh Normal file
View File

@ -0,0 +1,364 @@
#!/bin/bash
# usage: bash test.sh ***.txt MODE
FILENAME=$1
# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer', 'infer']
MODE=$2
dataline=$(cat ${FILENAME})
# parser params
IFS=$'\n'
lines=(${dataline})
function func_parser_key(){
strs=$1
IFS=":"
array=(${strs})
tmp=${array[0]}
echo ${tmp}
}
function func_parser_value(){
strs=$1
IFS=":"
array=(${strs})
tmp=${array[1]}
echo ${tmp}
}
function func_set_params(){
key=$1
value=$2
if [ ${key} = "null" ];then
echo " "
elif [[ ${value} = "null" ]] || [[ ${value} = " " ]] || [ ${#value} -le 0 ];then
echo " "
else
echo "${key}=${value}"
fi
}
function func_parser_params(){
strs=$1
IFS=":"
array=(${strs})
key=${array[0]}
tmp=${array[1]}
IFS="|"
res=""
for _params in ${tmp[*]}; do
IFS="="
array=(${_params})
mode=${array[0]}
value=${array[1]}
if [[ ${mode} = ${MODE} ]]; then
IFS="|"
#echo $(func_set_params "${mode}" "${value}")
echo $value
break
fi
IFS="|"
done
echo ${res}
}
function status_check(){
last_status=$1 # the exit code
run_command=$2
run_log=$3
if [ $last_status -eq 0 ]; then
echo -e "\033[33m Run successfully with command - ${run_command}! \033[0m" | tee -a ${run_log}
else
echo -e "\033[33m Run failed with command - ${run_command}! \033[0m" | tee -a ${run_log}
fi
}
IFS=$'\n'
# The training params
model_name=$(func_parser_value "${lines[1]}")
python=$(func_parser_value "${lines[2]}")
gpu_list=$(func_parser_value "${lines[3]}")
train_use_gpu_key=$(func_parser_key "${lines[4]}")
train_use_gpu_value=$(func_parser_value "${lines[4]}")
autocast_list=$(func_parser_value "${lines[5]}")
autocast_key=$(func_parser_key "${lines[5]}")
epoch_key=$(func_parser_key "${lines[6]}")
epoch_num=$(func_parser_params "${lines[6]}")
save_model_key=$(func_parser_key "${lines[7]}")
train_batch_key=$(func_parser_key "${lines[8]}")
train_batch_value=$(func_parser_params "${lines[8]}")
pretrain_model_key=$(func_parser_key "${lines[9]}")
pretrain_model_value=$(func_parser_value "${lines[9]}")
train_model_name=$(func_parser_value "${lines[10]}")
train_infer_img_dir=$(func_parser_value "${lines[11]}")
train_param_key1=$(func_parser_key "${lines[12]}")
train_param_value1=$(func_parser_value "${lines[12]}")
trainer_list=$(func_parser_value "${lines[14]}")
trainer_norm=$(func_parser_key "${lines[15]}")
norm_trainer=$(func_parser_value "${lines[15]}")
pact_key=$(func_parser_key "${lines[16]}")
pact_trainer=$(func_parser_value "${lines[16]}")
fpgm_key=$(func_parser_key "${lines[17]}")
fpgm_trainer=$(func_parser_value "${lines[17]}")
distill_key=$(func_parser_key "${lines[18]}")
distill_trainer=$(func_parser_value "${lines[18]}")
trainer_key1=$(func_parser_key "${lines[19]}")
trainer_value1=$(func_parser_value "${lines[19]}")
trainer_key2=$(func_parser_key "${lines[20]}")
trainer_value2=$(func_parser_value "${lines[20]}")
eval_py=$(func_parser_value "${lines[23]}")
eval_key1=$(func_parser_key "${lines[24]}")
eval_value1=$(func_parser_value "${lines[24]}")
save_infer_key=$(func_parser_key "${lines[27]}")
export_weight=$(func_parser_key "${lines[28]}")
norm_export=$(func_parser_value "${lines[29]}")
pact_export=$(func_parser_value "${lines[30]}")
fpgm_export=$(func_parser_value "${lines[31]}")
distill_export=$(func_parser_value "${lines[32]}")
export_key1=$(func_parser_key "${lines[33]}")
export_value1=$(func_parser_value "${lines[33]}")
export_key2=$(func_parser_key "${lines[34]}")
export_value2=$(func_parser_value "${lines[34]}")
# parser inference model
infer_model_dir_list=$(func_parser_value "${lines[36]}")
infer_export_list=$(func_parser_value "${lines[37]}")
infer_is_quant=$(func_parser_value "${lines[38]}")
# parser inference
inference_py=$(func_parser_value "${lines[39]}")
use_gpu_key=$(func_parser_key "${lines[40]}")
use_gpu_list=$(func_parser_value "${lines[40]}")
use_mkldnn_key=$(func_parser_key "${lines[41]}")
use_mkldnn_list=$(func_parser_value "${lines[41]}")
cpu_threads_key=$(func_parser_key "${lines[42]}")
cpu_threads_list=$(func_parser_value "${lines[42]}")
batch_size_key=$(func_parser_key "${lines[43]}")
batch_size_list=$(func_parser_value "${lines[43]}")
use_trt_key=$(func_parser_key "${lines[44]}")
use_trt_list=$(func_parser_value "${lines[44]}")
precision_key=$(func_parser_key "${lines[45]}")
precision_list=$(func_parser_value "${lines[45]}")
infer_model_key=$(func_parser_key "${lines[46]}")
image_dir_key=$(func_parser_key "${lines[47]}")
infer_img_dir=$(func_parser_value "${lines[47]}")
save_log_key=$(func_parser_key "${lines[48]}")
benchmark_key=$(func_parser_key "${lines[49]}")
benchmark_value=$(func_parser_value "${lines[49]}")
infer_key1=$(func_parser_key "${lines[50]}")
infer_value1=$(func_parser_value "${lines[50]}")
LOG_PATH="./tests/output"
mkdir -p ${LOG_PATH}
status_log="${LOG_PATH}/results.log"
function func_inference(){
IFS='|'
_python=$1
_script=$2
_model_dir=$3
_log_path=$4
_img_dir=$5
_flag_quant=$6
# inference
for use_gpu in ${use_gpu_list[*]}; do
if [ ${use_gpu} = "False" ] || [ ${use_gpu} = "cpu" ]; then
for use_mkldnn in ${use_mkldnn_list[*]}; do
if [ ${use_mkldnn} = "False" ] && [ ${_flag_quant} = "True" ]; then
continue
fi
for threads in ${cpu_threads_list[*]}; do
for batch_size in ${batch_size_list[*]}; do
_save_log_path="${_log_path}/infer_cpu_usemkldnn_${use_mkldnn}_threads_${threads}_batchsize_${batch_size}.log"
set_infer_data=$(func_set_params "${image_dir_key}" "${_img_dir}")
set_benchmark=$(func_set_params "${benchmark_key}" "${benchmark_value}")
set_batchsize=$(func_set_params "${batch_size_key}" "${batch_size}")
set_cpu_threads=$(func_set_params "${cpu_threads_key}" "${threads}")
set_model_dir=$(func_set_params "${infer_model_key}" "${_model_dir}")
set_infer_params1=$(func_set_params "${infer_key1}" "${infer_value1}")
command="${_python} ${_script} > ${_save_log_path} 2>&1 "
eval $command
last_status=${PIPESTATUS[0]}
eval "cat ${_save_log_path}"
status_check $last_status "${command}" "${status_log}"
done
done
done
elif [ ${use_gpu} = "True" ] || [ ${use_gpu} = "gpu" ]; then
for use_trt in ${use_trt_list[*]}; do
for precision in ${precision_list[*]}; do
if [[ ${_flag_quant} = "False" ]] && [[ ${precision} =~ "int8" ]]; then
continue
fi
if [[ ${precision} =~ "fp16" || ${precision} =~ "int8" ]] && [ ${use_trt} = "False" ]; then
continue
fi
if [[ ${use_trt} = "False" || ${precision} =~ "int8" ]] && [ ${_flag_quant} = "True" ]; then
continue
fi
for batch_size in ${batch_size_list[*]}; do
_save_log_path="${_log_path}/infer_gpu_usetrt_${use_trt}_precision_${precision}_batchsize_${batch_size}.log"
set_infer_data=$(func_set_params "${image_dir_key}" "${_img_dir}")
set_benchmark=$(func_set_params "${benchmark_key}" "${benchmark_value}")
set_batchsize=$(func_set_params "${batch_size_key}" "${batch_size}")
set_tensorrt=$(func_set_params "${use_trt_key}" "${use_trt}")
set_precision=$(func_set_params "${precision_key}" "${precision}")
set_model_dir=$(func_set_params "${infer_model_key}" "${_model_dir}")
set_infer_params1=$(func_set_params "${infer_key1}" "${infer_value1}")
command="${_python} ${_script} > ${_save_log_path} 2>&1 "
eval $command
last_status=${PIPESTATUS[0]}
eval "cat ${_save_log_path}"
status_check $last_status "${command}" "${status_log}"
done
done
done
else
echo "Does not support hardware other than CPU and GPU Currently!"
fi
done
}
if [ ${MODE} = "infer" ]; then
GPUID=$3
if [ ${#GPUID} -le 0 ];then
env=" "
else
env="export CUDA_VISIBLE_DEVICES=${GPUID}"
fi
# set CUDA_VISIBLE_DEVICES
eval $env
export Count=0
IFS="|"
infer_run_exports=(${infer_export_list})
infer_quant_flag=(${infer_is_quant})
for infer_model in ${infer_model_dir_list[*]}; do
# run export
if [ ${infer_run_exports[Count]} != "null" ];then
set_export_weight=$(func_set_params "${export_weight}" "${infer_model}")
set_save_infer_key=$(func_set_params "${save_infer_key}" "${infer_model}")
export_cmd="${python} ${norm_export} ${set_export_weight} ${set_save_infer_key}"
eval $export_cmd
status_export=$?
if [ ${status_export} = 0 ];then
status_check $status_export "${export_cmd}" "${status_log}"
fi
fi
#run inference
is_quant=${infer_quant_flag[Count]}
func_inference "${python}" "${inference_py}" "${infer_model}" "${LOG_PATH}" "${infer_img_dir}" ${is_quant}
Count=$(($Count + 1))
done
else
IFS="|"
export Count=0
USE_GPU_KEY=(${train_use_gpu_value})
for gpu in ${gpu_list[*]}; do
use_gpu=${USE_GPU_KEY[Count]}
Count=$(($Count + 1))
if [ ${gpu} = "-1" ];then
env=""
elif [ ${#gpu} -le 1 ];then
env="export CUDA_VISIBLE_DEVICES=${gpu}"
eval ${env}
elif [ ${#gpu} -le 15 ];then
IFS=","
array=(${gpu})
env="export CUDA_VISIBLE_DEVICES=${array[0]}"
IFS="|"
else
IFS=";"
array=(${gpu})
ips=${array[0]}
gpu=${array[1]}
IFS="|"
env=" "
fi
for autocast in ${autocast_list[*]}; do
for trainer in ${trainer_list[*]}; do
flag_quant=False
if [ ${trainer} = ${pact_key} ]; then
run_train=${pact_trainer}
run_export=${pact_export}
flag_quant=True
elif [ ${trainer} = "${fpgm_key}" ]; then
run_train=${fpgm_trainer}
run_export=${fpgm_export}
elif [ ${trainer} = "${distill_key}" ]; then
run_train=${distill_trainer}
run_export=${distill_export}
elif [ ${trainer} = ${trainer_key1} ]; then
run_train=${trainer_value1}
run_export=${export_value1}
elif [[ ${trainer} = ${trainer_key2} ]]; then
run_train=${trainer_value2}
run_export=${export_value2}
else
run_train=${norm_trainer}
run_export=${norm_export}
fi
if [ ${run_train} = "null" ]; then
continue
fi
set_autocast=$(func_set_params "${autocast_key}" "${autocast}")
set_epoch=$(func_set_params "${epoch_key}" "${epoch_num}")
set_pretrain=$(func_set_params "${pretrain_model_key}" "${pretrain_model_value}")
set_batchsize=$(func_set_params "${train_batch_key}" "${train_batch_value}")
set_train_params1=$(func_set_params "${train_param_key1}" "${train_param_value1}")
set_use_gpu=$(func_set_params "${train_use_gpu_key}" "${use_gpu}")
save_log="${LOG_PATH}/${trainer}_gpus_${gpu}_autocast_${autocast}"
# load pretrain from norm training if current trainer is pact or fpgm trainer
if [ ${trainer} = ${pact_key} ] || [ ${trainer} = ${fpgm_key} ]; then
set_pretrain="${load_norm_train_model}"
fi
set_save_model=$(func_set_params "${save_model_key}" "${save_log}")
if [ ${#gpu} -le 2 ];then # train with cpu or single gpu
cmd="${python} ${run_train} "
elif [ ${#gpu} -le 15 ];then # train with multi-gpu
cmd="${python} ${run_train} --nprocs={#ngpu}"
else # train with multi-machine
cmd="${python} -m paddle.distributed.launch --ips=${ips} --gpus=${gpu} ${run_train} ${set_save_model} ${set_pretrain} ${set_epoch} ${set_autocast} ${set_batchsize} ${set_train_params1}"
fi
# run train
eval "unset CUDA_VISIBLE_DEVICES"
eval $cmd
status_check $? "${cmd}" "${status_log}"
set_eval_pretrain=$(func_set_params "${pretrain_model_key}" "${save_log}/${train_model_name}")
# save norm trained models to set pretrain for pact training and fpgm training
if [ ${trainer} = ${trainer_norm} ]; then
load_norm_train_model=${set_eval_pretrain}
fi
# run eval
if [ ${eval_py} != "null" ]; then
set_eval_params1=$(func_set_params "${eval_key1}" "${eval_value1}")
eval_cmd="${python} ${eval_py} ${set_eval_pretrain} ${set_use_gpu} ${set_eval_params1}"
eval $eval_cmd
status_check $? "${eval_cmd}" "${status_log}"
fi
# run export model
if [ ${run_export} != "null" ]; then
# run export model
save_infer_path="${save_log}"
set_export_weight=$(func_set_params "${export_weight}" "${save_log}/${train_model_name}")
set_save_infer_key=$(func_set_params "${save_infer_key}" "${save_infer_path}")
export_cmd="${python} ${run_export} ${set_export_weight} ${set_save_infer_key}"
eval $export_cmd
status_check $? "${export_cmd}" "${status_log}"
#run inference
eval $env
save_infer_path="${save_log}"
func_inference "${python}" "${inference_py}" "${save_infer_path}" "${LOG_PATH}" "${train_infer_img_dir}" "${flag_quant}"
eval "unset CUDA_VISIBLE_DEVICES"
fi
done # done with: for trainer in ${trainer_list[*]}; do
done # done with: for autocast in ${autocast_list[*]}; do
done # done with: for gpu in ${gpu_list[*]}; do
fi # end if [ ${MODE} = "infer" ]; then