Skip to content

F
Fairseq-S2T
Commit 1a7d6fb8 by xuchen
Options

optimize the shell script

parent 07f0ab14
正在显示 包含 179 行增加 和 1257 行删除
egs/mustc/st/conf/train.yaml → egs/mustc/asr/conf/base.yaml
train-subset: train_st train-subset: train_asr
valid-subset: dev_st valid-subset: dev_asr
max-epoch: 50 max-epoch: 50
max-update: 100000 max-update: 100000
......
egs/mustc/asr/conf/conformer.yaml 0 → 100644
arch: s2t_conformer_s
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
egs/mustc/st/conf/train_ctc.yaml → egs/mustc/asr/conf/ctc.yaml
train-subset: train_st train-subset: train_asr
valid-subset: dev_st valid-subset: dev_asr
max-epoch: 50 max-epoch: 50
max-update: 100000 max-update: 100000
......
egs/mustc/asr/conf/dlcl.yaml 0 → 100644
use-enc-dlcl: True
use-dec-dlcl: True
egs/mustc/st/conf/train_local_attn.yaml → egs/mustc/asr/conf/local_attn.yaml
encoder-attention-type: local encoder-attention-type: local
hard-mask-window: 20 hard-mask-window: 0
gauss-mask-sigma: 0 gauss-mask-sigma: 3
init-mask-weight: 0 init-mask-weight: 0
\ No newline at end of file
egs/mustc/asr/conf/rpr.yaml 0 → 100644
encoder-attention-type: relative
decoder-attention-type: relative
max-encoder-relative-length: 100
max-decoder-relative-length: 20
egs/mustc/asr/conf/train_ctc_conformer.yaml deleted 100644 → 0
train-subset: train_st
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_conformer_s
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 2e-3
#adam_betas: (0.9,0.98)
ctc-weight: 0.3
criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1
conv-kernel-sizes: 5,5
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 12
decoder-layers: 6
encoder-attention-heads: 4
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
decoder-embed-dim: 256
decoder-ffn-embed-dim: 2048
decoder-attention-heads: 4
attention-dropout: 0.1
activation-dropout: 0.1
egs/mustc/asr/conf/train_ctc_conformer_rpr.yaml deleted 100644 → 0
train-subset: train_st
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_conformer_s
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 2e-3
#adam_betas: (0.9,0.98)
ctc-weight: 0.3
criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1
conv-kernel-sizes: 5,5
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 12
decoder-layers: 6
encoder-attention-heads: 4
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
encoder-attention-type: relative
decoder-attention-type: relative
max-encoder-relative-length: 100
max-decoder-relative-length: 20
#decoder-embed-dim: 256
#decoder-ffn-embed-dim: 2048
#decoder-attention-heads: 4
#attention-dropout: 0.1
#activation-dropout: 0.1
egs/mustc/asr/conf/train_ctc_rpr.yaml deleted 100644 → 0
train-subset: train_st
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_transformer_s
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 2e-3
#adam_betas: (0.9,0.98)
ctc-weight: 0.3
criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1
conv-kernel-sizes: 5,5
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 12
decoder-layers: 6
encoder-attention-heads: 4
encoder-attention-type: relative
decoder-attention-type: relative
max-encoder-relative-length: 100
max-decoder-relative-length: 20
decoder-embed-dim: 256
decoder-ffn-embed-dim: 2048
decoder-attention-heads: 4
attention-dropout: 0.1
activation-dropout: 0.1
egs/mustc/asr/conf/train_ctc_sate_conformer.yaml deleted 100644 → 0
train-subset: train_st
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-acoustic-encoder-from:
#load-pretrained-text-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_sate
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 2e-3
#adam_betas: (0.9,0.98)
ctc-weight: 0.3
criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1
encoder-normalize-before: True
decoder-normalize-before: True
conv-kernel-sizes: 5,5
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 12
text-encoder-layers: 6
decoder-layers: 6
encoder-attention-heads: 4
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
acoustic-encoder: conformer
adapter: league
#decoder-embed-dim: 256
#decoder-ffn-embed-dim: 2048
#decoder-attention-heads: 4
#attention-dropout: 0.1
#activation-dropout: 0.1
egs/mustc/asr/conf/train_ctc_sate_conformer_rpr.yaml deleted 100644 → 0
train-subset: train_st
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-acoustic-encoder-from:
#load-pretrained-text-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_sate
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 2e-3
#adam_betas: (0.9,0.98)
ctc-weight: 0.3
criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1
encoder-normalize-before: True
decoder-normalize-before: True
conv-kernel-sizes: 5,5
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 12
text-encoder-layers: 6
decoder-layers: 6
encoder-attention-heads: 4
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
acoustic-encoder: conformer
adapter: league
encoder-attention-type: relative
decoder-attention-type: relative
max-encoder-relative-length: 100
max-decoder-relative-length: 20
decoder-embed-dim: 256
decoder-ffn-embed-dim: 2048
decoder-attention-heads: 4
attention-dropout: 0.1
activation-dropout: 0.1
egs/mustc/asr/conf/train_ctc_sate_rpr.yaml deleted 100644 → 0
train-subset: train_st
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-acoustic-encoder-from:
#load-pretrained-text-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_sate
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 2e-3
#adam_betas: (0.9,0.98)
ctc-weight: 0.3
criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1
encoder-normalize-before: True
decoder-normalize-before: True
conv-kernel-sizes: 5,5
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 12
text-encoder-layers: 6
decoder-layers: 6
encoder-attention-heads: 4
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
acoustic-encoder: transformer
adapter: league
encoder-attention-type: relative
decoder-attention-type: relative
max-encoder-relative-length: 100
max-decoder-relative-length: 20
#decoder-embed-dim: 256
#decoder-ffn-embed-dim: 2048
#decoder-attention-heads: 4
#attention-dropout: 0.1
#activation-dropout: 0.1
egs/mustc/asr/conf/train_ctc_templete.yaml deleted 100644 → 0
train-subset: train_st
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_conformer_m
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 1e-3
#adam_betas: (0.9,0.98)
ctc-weight: 0.3
criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1
conv-kernel-sizes: 5,5
conv-channels: 1024
#dropout: 0.1
#activation-fn: relu
#encoder-embed-dim: 256
#encoder-ffn-embed-dim: 2048
#encoder-layers: 12
#decoder-layers: 6
#encoder-attention-heads: 4
#decoder-embed-dim: 256
#decoder-ffn-embed-dim: 2048
#decoder-attention-heads: 4
#attention-dropout: 0.1
#activation-dropout: 0.1
# conformer
#macaron-style: True
#use-cnn-module: True
#cnn-module-kernel: 31
# relative position encoding
#encoder-attention-type: relative
#decoder-attention-type: relative
#max-encoder-relative-length: 100
#max-decoder-relative-length: 20
egs/mustc/asr/conf/train_sate.yaml deleted 100644 → 0
train-subset: train_st
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-acoustic-encoder-from:
#load-pretrained-text-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_sate
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 2e-3
#adam_betas: (0.9,0.98)
criterion: label_smoothed_cross_entropy
label_smoothing: 0.1
encoder-normalize-before: True
decoder-normalize-before: True
conv-kernel-sizes: 5,5
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 12
text-encoder-layers: 6
decoder-layers: 6
encoder-attention-heads: 4
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
acoustic-encoder: transformer
adapter: league
#decoder-embed-dim: 256
#decoder-ffn-embed-dim: 2048
#decoder-attention-heads: 4
#attention-dropout: 0.1
#activation-dropout: 0.1
egs/mustc/asr/conf/train_sate_rpr.yaml deleted 100644 → 0
train-subset: train_st,train_covost
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-acoustic-encoder-from:
#load-pretrained-text-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_sate
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 2e-3
#adam_betas: (0.9,0.98)
criterion: label_smoothed_cross_entropy
label_smoothing: 0.1
encoder-normalize-before: True
decoder-normalize-before: True
conv-kernel-sizes: 5,5
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 12
text-encoder-layers: 6
decoder-layers: 6
encoder-attention-heads: 4
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
acoustic-encoder: transformer
adapter: league
encoder-attention-type: relative
decoder-attention-type: relative
max-encoder-relative-length: 100
max-decoder-relative-length: 20
#decoder-embed-dim: 256
#decoder-ffn-embed-dim: 2048
#decoder-attention-heads: 4
#attention-dropout: 0.1
#activation-dropout: 0.1
egs/mustc/asr/decode.sh
...@@ -31,9 +31,9 @@ cmd="./run.sh ...@@ -31,9 +31,9 @@ cmd="./run.sh
if [[ -n ${data_dir} ]]; then if [[ -n ${data_dir} ]]; then
cmd="$cmd --data_dir ${data_dir}" cmd="$cmd --data_dir ${data_dir}"
fi fi
if [[ -n ${test_subset} ]]; then if [[ ${#test_subset[@]} -eq 0 ]]; then
test_subset=`echo ${test_subset[*]} | sed 's/ /,/g'` subsets=$(echo ${test_subset[*]} | sed 's/ /,/g')
cmd="$cmd --test_subset ${test_subset}" cmd="$cmd --test_subset ${subsets}"
fi fi
echo $cmd echo $cmd
......
egs/mustc/asr/local/monitor.sh
gpu_num=1 gpu_num=1
cmd="sh train.sh"
while : while :
do do
all_devices=$(seq 0 `gpustat | sed '1,2d' | wc -l`); record=$(mktemp -t temp.record.XXXXXX)
gpustat > $record
all_devices=$(seq 0 "$(sed '1,2d' ${record} | wc -l)");
count=0 count=0
for dev in ${all_devices[@]} for dev in "${all_devices[@]}"
do do
line=`expr $dev + 2` line=$((dev + 2))
use=`gpustat -p | head -n $line | tail -1 | cut -d '|' -f4 | wc -w` use=$(head -n $line ${record} | tail -1 | cut -d '|' -f3 | cut -d '/' -f1)
if [[ $use -eq 0 ]]; then
if [[ $use -lt 100 ]]; then
device[$count]=$dev device[$count]=$dev
count=`expr $count + 1` count=$((count + 1))
if [[ $count -eq $gpu_num ]]; then if [[ $count -eq $gpu_num ]]; then
break break
fi fi
......
egs/mustc/asr/local/path.sh deleted 100755 → 0
MAIN_ROOT=$PWD/../../..
KALDI_ROOT=$MAIN_ROOT/tools/kaldi
export PATH=$PWD/utils/:$KALDI_ROOT/tools/openfst/bin:$PATH
[ ! -f $KALDI_ROOT/tools/config/common_path.sh ] && echo >&2 "The standard file $KALDI_ROOT/tools/config/common_path.sh is not present -> Exit!" && exit 1
. $KALDI_ROOT/tools/config/common_path.sh
export LC_ALL=C
export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:$MAIN_ROOT/src/lib
export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:$MAIN_ROOT/tools/chainer_ctc/ext/warp-ctc/build
. "${MAIN_ROOT}"/tools/activate_python.sh && . "${MAIN_ROOT}"/tools/extra_path.sh
export PATH=$MAIN_ROOT/utils:$MAIN_ROOT/espnet/bin:$PATH
export OMP_NUM_THREADS=1
# check extra module installation
if ! which tokenizer.perl > /dev/null; then
echo "Error: it seems that moses is not installed." >&2
echo "Error: please install moses as follows." >&2
echo "Error: cd ${MAIN_ROOT}/tools && make moses.done" >&2
return 1
fi
# NOTE(kan-bayashi): Use UTF-8 in Python to avoid UnicodeDecodeError when LC_ALL=C
export PYTHONIOENCODING=UTF-8
egs/mustc/asr/local/utils.sh
...@@ -5,17 +5,18 @@ get_devices(){ ...@@ -5,17 +5,18 @@ get_devices(){
device=() device=()
while : while :
do do
record=`mktemp -t temp.record.XXXXXX` record=$(mktemp -t temp.record.XXXXXX)
gpustat > $record gpustat > $record
all_devices=$(seq 0 `cat $record | sed '1,2d' | wc -l`); all_devices=$(seq 0 "$(sed '1,2d' ${record} | wc -l)");
count=0 count=0
for dev in ${all_devices[@]} for dev in "${all_devices[@]}"
do do
line=`expr $dev + 2` line=$((dev + 2))
use=`cat $record | head -n $line | tail -1 | cut -d '|' -f3 | cut -d '/' -f1` use=$(head -n $line ${record} | tail -1 | cut -d '|' -f3 | cut -d '/' -f1)
if [[ $use -lt 100 ]]; then if [[ $use -lt 100 ]]; then
device[$count]=$dev device[$count]=$dev
count=`expr $count + 1` count=$((count + 1))
if [[ $count -eq $gpu_num ]]; then if [[ $count -eq $gpu_num ]]; then
break break
fi fi
......
egs/mustc/asr/run.sh
...@@ -32,12 +32,12 @@ src_lang=en ...@@ -32,12 +32,12 @@ src_lang=en
tgt_lang=de tgt_lang=de
lang=${src_lang}-${tgt_lang} lang=${src_lang}-${tgt_lang}
dataset=mustc-v2 dataset=mustc
task=speech_to_text task=speech_to_text
vocab_type=unigram vocab_type=unigram
vocab_size=5000 vocab_size=5000
speed_perturb=0 speed_perturb=0
lcrm=1 lcrm=0
tokenizer=0 tokenizer=0
use_specific_dict=0 use_specific_dict=0
...@@ -45,19 +45,19 @@ specific_prefix=valid ...@@ -45,19 +45,19 @@ specific_prefix=valid
specific_dir=/home/xuchen/st/data/mustc/st_lcrm/en-de specific_dir=/home/xuchen/st/data/mustc/st_lcrm/en-de
asr_vocab_prefix=spm_unigram10000_st_share asr_vocab_prefix=spm_unigram10000_st_share
org_data_dir=/media/data/${dataset} org_data_dir=~/st/data/${dataset}
data_dir=~/st/data/${dataset}/asr data_dir=~/st/data/${dataset}/asr
test_subset=tst-COMMON test_subset=tst-COMMON
# exp # exp
exp_prefix=${time} exp_prefix=$(date "+%m%d")
extra_tag= extra_tag=
extra_parameter= extra_parameter=
exp_tag=baseline exp_tag=baseline
exp_name= exp_name=
# config # config
train_config=train_ctc.yaml train_config=ctc
data_config=config_asr.yaml data_config=config_asr.yaml
# training setting # training setting
...@@ -90,10 +90,9 @@ fi ...@@ -90,10 +90,9 @@ fi
. ./local/parse_options.sh || exit 1; . ./local/parse_options.sh || exit 1;
# full path
train_config=$pwd_dir/conf/${train_config}
if [[ -z ${exp_name} ]]; then if [[ -z ${exp_name} ]]; then
exp_name=${exp_prefix}_$(basename ${train_config%.*})_${exp_tag} # exp_name=${exp_prefix}_$(basename ${train_config%.*})_${exp_tag}
exp_name=${exp_prefix}_${train_config}_${exp_tag}
if [[ -n ${extra_tag} ]]; then if [[ -n ${extra_tag} ]]; then
exp_name=${exp_name}_${extra_tag} exp_name=${exp_name}_${extra_tag}
fi fi
...@@ -112,7 +111,6 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then ...@@ -112,7 +111,6 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
if [[ ! -e ${data_dir}/${lang} ]]; then if [[ ! -e ${data_dir}/${lang} ]]; then
mkdir -p ${data_dir}/${lang} mkdir -p ${data_dir}/${lang}
fi fi
source ~/tools/audio/bin/activate
cmd="python ${root_dir}/examples/speech_to_text/prep_mustc_data.py cmd="python ${root_dir}/examples/speech_to_text/prep_mustc_data.py
--data-root ${org_data_dir} --data-root ${org_data_dir}
...@@ -142,7 +140,6 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then ...@@ -142,7 +140,6 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
echo -e "\033[34mRun command: \n${cmd} \033[0m" echo -e "\033[34mRun command: \n${cmd} \033[0m"
[[ $eval -eq 1 ]] && eval ${cmd} [[ $eval -eq 1 ]] && eval ${cmd}
deactivate
fi fi
data_dir=${data_dir}/${lang} data_dir=${data_dir}/${lang}
...@@ -153,7 +150,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then ...@@ -153,7 +150,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
if [[ -z ${device} || ${#device[@]} -eq 0 ]]; then if [[ -z ${device} || ${#device[@]} -eq 0 ]]; then
if [[ ${gpu_num} -eq 0 ]]; then if [[ ${gpu_num} -eq 0 ]]; then
device=() device=""
else else
source ./local/utils.sh source ./local/utils.sh
device=$(get_devices $gpu_num 0) device=$(get_devices $gpu_num 0)
...@@ -170,12 +167,31 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then ...@@ -170,12 +167,31 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
cp ${BASH_SOURCE[0]} ${model_dir} cp ${BASH_SOURCE[0]} ${model_dir}
cp ${PWD}/train.sh ${model_dir} cp ${PWD}/train.sh ${model_dir}
cp ${train_config} ${model_dir}
config_list="${train_config//,/ }"
idx=0
for config in "${config_list[@]}"
do
config_path=$pwd_dir/conf/${config}.yaml
if [[ ! -f ${config_path} ]]; then
echo "No config file ${config_path}"
exit
fi
cp ${config_path} ${model_dir}
if [[ idx -eq 0 ]]; then
extra_parameter="${extra_parameter}
--train-config ${config_path}"
else
extra_parameter="${extra_parameter}
--train-config${idx} ${config_path}"
fi
idx=$((idx + 1))
done
cmd="python3 -u ${root_dir}/fairseq_cli/train.py cmd="python3 -u ${root_dir}/fairseq_cli/train.py
${data_dir} ${data_dir}
--config-yaml ${data_config} --config-yaml ${data_config}
--train-config ${train_config}
--task ${task} --task ${task}
--max-tokens ${max_tokens} --max-tokens ${max_tokens}
--skip-invalid-size-inputs-valid-test --skip-invalid-size-inputs-valid-test
...@@ -184,7 +200,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then ...@@ -184,7 +200,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
--save-dir ${model_dir} --save-dir ${model_dir}
--tensorboard-logdir ${model_dir}" --tensorboard-logdir ${model_dir}"
if [[ -n ${extra_parameter} ]]; then if [[ -n ${extra_parameter} ]]; then
cmd="${cmd} cmd="${cmd}
${extra_parameter}" ${extra_parameter}"
fi fi
...@@ -237,8 +253,8 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then ...@@ -237,8 +253,8 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
# save info # save info
log=./history.log log=./history.log
echo "${time} | ${device} | ${data_dir} | ${model_dir} " >> $log echo "${time} | ${device} | ${data_dir} | ${exp_name} | ${model_dir} " >> $log
cat $log | tail -n 50 > tmp.log tail -n 50 ${log} > tmp.log
mv tmp.log $log mv tmp.log $log
export CUDA_VISIBLE_DEVICES=${device} export CUDA_VISIBLE_DEVICES=${device}
...@@ -246,7 +262,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then ...@@ -246,7 +262,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
if [[ $eval -eq 1 ]]; then if [[ $eval -eq 1 ]]; then
eval $cmd eval $cmd
sleep 2s sleep 2s
tail -n `wc -l ${model_dir}/train.log | awk '{print $1+1}'` -f ${model_dir}/train.log tail -n "$(wc -l ${model_dir}/train.log | awk '{print $1+1}')" -f ${model_dir}/train.log
fi fi
fi fi
wait wait
...@@ -269,7 +285,7 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then ...@@ -269,7 +285,7 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
if [[ -z ${device} || ${#device[@]} -eq 0 ]]; then if [[ -z ${device} || ${#device[@]} -eq 0 ]]; then
if [[ ${gpu_num} -eq 0 ]]; then if [[ ${gpu_num} -eq 0 ]]; then
device=() device=""
else else
source ./local/utils.sh source ./local/utils.sh
device=$(get_devices $gpu_num 0) device=$(get_devices $gpu_num 0)
...@@ -277,13 +293,11 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then ...@@ -277,13 +293,11 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
fi fi
export CUDA_VISIBLE_DEVICES=${device} export CUDA_VISIBLE_DEVICES=${device}
#tmp_file=$(mktemp ${model_dir}/tmp-XXXXX)
#trap 'rm -rf ${tmp_file}' EXIT
result_file=${model_dir}/decode_result result_file=${model_dir}/decode_result
[[ -f ${result_file} ]] && rm ${result_file} [[ -f ${result_file} ]] && rm ${result_file}
test_subset=(${test_subset//,/ }) test_subset=${test_subset//,/ }
for subset in ${test_subset[@]}; do for subset in "${test_subset[@]}"; do
subset=${subset}_asr subset=${subset}_asr
cmd="python ${root_dir}/fairseq_cli/generate.py cmd="python ${root_dir}/fairseq_cli/generate.py
${data_dir} ${data_dir}
......
egs/mustc/asr/train.sh
...@@ -3,30 +3,21 @@ ...@@ -3,30 +3,21 @@
# training the model # training the model
gpu_num=8 gpu_num=8
update_freq=2 update_freq=1
max_tokens=20000 max_tokens=40000
exp_tag=
config_list=(ctc local_attn)
# exp full name
exp_name= exp_name=
extra_tag= extra_tag=
extra_parameter= extra_parameter=
#extra_tag="${extra_tag}" #extra_tag="${extra_tag}"
#extra_parameter="${extra_parameter} " #extra_parameter="${extra_parameter} "
#extra_tag="${extra_tag}_encdlcl" train_config=$(echo ${config_list[*]} | sed 's/ /,/g')
#extra_parameter="${extra_parameter} --use-enc-dlcl"
#extra_tag="${extra_tag}_decdlcl"
#extra_parameter="${extra_parameter} --use-dec-dlcl"
exp_tag=baseline
train_config=train_ctc.yaml
#train_config=train_ctc_conformer.yaml
#train_config=train_ctc_conformer_rpr.yaml
#train_config=train_ctc_sate.yaml
#train_config=train_ctc_sate_rpr.yaml
#train_config=train_ctc_sate_conformer.yaml
#train_config=train_ctc_sate_conformer_rpr.yaml
cmd="./run.sh cmd="./run.sh
--stage 1 --stage 1
...@@ -47,8 +38,9 @@ if [[ -n ${extra_tag} ]]; then ...@@ -47,8 +38,9 @@ if [[ -n ${extra_tag} ]]; then
cmd="$cmd --extra_tag ${extra_tag}" cmd="$cmd --extra_tag ${extra_tag}"
fi fi
if [[ -n ${extra_parameter} ]]; then if [[ -n ${extra_parameter} ]]; then
cmd="$cmd --extra_parameter \"${extra_parameter}\"" # cmd="$cmd --extra_parameter \"${extra_parameter}\""
cmd="$cmd --extra_parameter ${extra_parameter}"
fi fi
echo $cmd echo ${cmd}
eval $cmd eval ${cmd}
egs/mustc/st/binary.sh
...@@ -15,9 +15,7 @@ src_lang=en ...@@ -15,9 +15,7 @@ src_lang=en
tgt_lang=de tgt_lang=de
splits=(2019) splits=(2019)
source ~/tools/audio/bin/activate splits=$(echo ${splits[*]} | sed 's/ /_/g')
splits=`echo ${splits[*]} | sed 's/ /,/g'`
cp -r ${vocab_dir}/${asr_vocab_prefix}.* ${data_dir}/${src_lang}-${tgt_lang} cp -r ${vocab_dir}/${asr_vocab_prefix}.* ${data_dir}/${src_lang}-${tgt_lang}
cp -r ${vocab_dir}/${st_vocab_prefix}.* ${data_dir}/${src_lang}-${tgt_lang} cp -r ${vocab_dir}/${st_vocab_prefix}.* ${data_dir}/${src_lang}-${tgt_lang}
...@@ -48,4 +46,3 @@ cmd="python ${root_dir}/examples/speech_to_text/prep_st_data.py ...@@ -48,4 +46,3 @@ cmd="python ${root_dir}/examples/speech_to_text/prep_st_data.py
echo -e "\033[34mRun command: \n${cmd} \033[0m" echo -e "\033[34mRun command: \n${cmd} \033[0m"
[[ $eval -eq 1 ]] && eval ${cmd} [[ $eval -eq 1 ]] && eval ${cmd}
deactivate
egs/mustc/st/conf/conformer.yaml 0 → 100644
arch: s2t_conformer_s
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
egs/mustc/st/conf/dlcl.yaml 0 → 100644
use-enc-dlcl: True
use-dec-dlcl: True
egs/mustc/st/conf/local_attn.yaml 0 → 100644
encoder-attention-type: local
hard-mask-window: 0
gauss-mask-sigma: 3
init-mask-weight: 0
\ No newline at end of file
egs/mustc/st/conf/rpr.yaml 0 → 100644
encoder-attention-type: relative
decoder-attention-type: relative
max-encoder-relative-length: 100
max-decoder-relative-length: 20
egs/mustc/st/conf/sate.yaml 0 → 100644
arch: s2t_sate_s
acoustic-encoder: transformer
adapter: league
#load-pretrained-encoder-from:
#load-pretrained-acoustic-encoder-from:
#load-pretrained-text-encoder-from:
#load-pretrained-decoder-from:
egs/mustc/st/conf/train_ctc_conformer.yaml deleted 100644 → 0
train-subset: train_st
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_conformer_s
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 2e-3
#adam_betas: (0.9,0.98)
ctc-weight: 0.3
criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1
conv-kernel-sizes: 5,5
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 12
decoder-layers: 6
encoder-attention-heads: 4
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
decoder-embed-dim: 256
decoder-ffn-embed-dim: 2048
decoder-attention-heads: 4
attention-dropout: 0.1
activation-dropout: 0.1
egs/mustc/st/conf/train_ctc_conformer_rpr.yaml deleted 100644 → 0
train-subset: train_st
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_conformer_s
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 2e-3
#adam_betas: (0.9,0.98)
ctc-weight: 0.3
criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1
conv-kernel-sizes: 5,5
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 12
decoder-layers: 6
encoder-attention-heads: 4
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
encoder-attention-type: relative
decoder-attention-type: relative
max-encoder-relative-length: 100
max-decoder-relative-length: 20
#decoder-embed-dim: 256
#decoder-ffn-embed-dim: 2048
#decoder-attention-heads: 4
#attention-dropout: 0.1
#activation-dropout: 0.1
egs/mustc/st/conf/train_ctc_rpr.yaml deleted 100644 → 0
train-subset: train_st
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_transformer_s
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 2e-3
#adam_betas: (0.9,0.98)
ctc-weight: 0.3
criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1
conv-kernel-sizes: 5,5
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 12
decoder-layers: 6
encoder-attention-heads: 4
encoder-attention-type: relative
decoder-attention-type: relative
max-encoder-relative-length: 100
max-decoder-relative-length: 20
decoder-embed-dim: 256
decoder-ffn-embed-dim: 2048
decoder-attention-heads: 4
attention-dropout: 0.1
activation-dropout: 0.1
egs/mustc/st/conf/train_ctc_sate.yaml deleted 100644 → 0
train-subset: train_st
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-acoustic-encoder-from:
#load-pretrained-text-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_sate
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 2e-3
#adam_betas: (0.9,0.98)
ctc-weight: 0.3
criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1
encoder-normalize-before: True
decoder-normalize-before: True
conv-kernel-sizes: 5,5
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 12
text-encoder-layers: 6
decoder-layers: 6
encoder-attention-heads: 4
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
acoustic-encoder: transformer
adapter: league
#decoder-embed-dim: 256
#decoder-ffn-embed-dim: 2048
#decoder-attention-heads: 4
#attention-dropout: 0.1
#activation-dropout: 0.1
egs/mustc/st/conf/train_ctc_sate_conformer.yaml deleted 100644 → 0
train-subset: train_st
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-acoustic-encoder-from:
#load-pretrained-text-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_sate
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 2e-3
#adam_betas: (0.9,0.98)
ctc-weight: 0.3
criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1
encoder-normalize-before: True
decoder-normalize-before: True
conv-kernel-sizes: 5,5
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 12
text-encoder-layers: 6
decoder-layers: 6
encoder-attention-heads: 4
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
acoustic-encoder: conformer
adapter: league
#decoder-embed-dim: 256
#decoder-ffn-embed-dim: 2048
#decoder-attention-heads: 4
#attention-dropout: 0.1
#activation-dropout: 0.1
egs/mustc/st/conf/train_ctc_sate_conformer_rpr.yaml deleted 100644 → 0
train-subset: train_st
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-acoustic-encoder-from:
#load-pretrained-text-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_sate
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 2e-3
#adam_betas: (0.9,0.98)
ctc-weight: 0.3
criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1
encoder-normalize-before: True
decoder-normalize-before: True
conv-kernel-sizes: 5,5
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 12
text-encoder-layers: 6
decoder-layers: 6
encoder-attention-heads: 4
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
acoustic-encoder: conformer
adapter: league
encoder-attention-type: relative
decoder-attention-type: relative
max-encoder-relative-length: 100
max-decoder-relative-length: 20
decoder-embed-dim: 256
decoder-ffn-embed-dim: 2048
decoder-attention-heads: 4
attention-dropout: 0.1
activation-dropout: 0.1
egs/mustc/st/conf/train_ctc_sate_rpr.yaml deleted 100644 → 0
train-subset: train_st
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-acoustic-encoder-from:
#load-pretrained-text-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_sate
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 2e-3
#adam_betas: (0.9,0.98)
ctc-weight: 0.3
criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1
encoder-normalize-before: True
decoder-normalize-before: True
conv-kernel-sizes: 5,5
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 12
text-encoder-layers: 6
decoder-layers: 6
encoder-attention-heads: 4
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
acoustic-encoder: transformer
adapter: league
encoder-attention-type: relative
decoder-attention-type: relative
max-encoder-relative-length: 100
max-decoder-relative-length: 20
#decoder-embed-dim: 256
#decoder-ffn-embed-dim: 2048
#decoder-attention-heads: 4
#attention-dropout: 0.1
#activation-dropout: 0.1
egs/mustc/st/conf/train_ctc_templete.yaml deleted 100644 → 0
train-subset: train_st
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_conformer_m
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 1e-3
#adam_betas: (0.9,0.98)
ctc-weight: 0.3
criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1
conv-kernel-sizes: 5,5
conv-channels: 1024
#dropout: 0.1
#activation-fn: relu
#encoder-embed-dim: 256
#encoder-ffn-embed-dim: 2048
#encoder-layers: 12
#decoder-layers: 6
#encoder-attention-heads: 4
#decoder-embed-dim: 256
#decoder-ffn-embed-dim: 2048
#decoder-attention-heads: 4
#attention-dropout: 0.1
#activation-dropout: 0.1
# conformer
#macaron-style: True
#use-cnn-module: True
#cnn-module-kernel: 31
# relative position encoding
#encoder-attention-type: relative
#decoder-attention-type: relative
#max-encoder-relative-length: 100
#max-decoder-relative-length: 20
egs/mustc/st/conf/train_sate.yaml deleted 100644 → 0
train-subset: train_st
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-acoustic-encoder-from:
#load-pretrained-text-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_sate
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 2e-3
#adam_betas: (0.9,0.98)
criterion: label_smoothed_cross_entropy
label_smoothing: 0.1
encoder-normalize-before: True
decoder-normalize-before: True
conv-kernel-sizes: 5,5
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 12
text-encoder-layers: 6
decoder-layers: 6
encoder-attention-heads: 4
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
acoustic-encoder: transformer
adapter: league
#decoder-embed-dim: 256
#decoder-ffn-embed-dim: 2048
#decoder-attention-heads: 4
#attention-dropout: 0.1
#activation-dropout: 0.1
egs/mustc/st/conf/train_sate_rpr.yaml deleted 100644 → 0
train-subset: train_st,train_covost
valid-subset: dev_st
max-epoch: 50
max-update: 100000
num-workers: 8
patience: 10
no-progress-bar: True
log-interval: 100
seed: 1
report-accuracy: True
#load-pretrained-encoder-from:
#load-pretrained-acoustic-encoder-from:
#load-pretrained-text-encoder-from:
#load-pretrained-decoder-from:
arch: s2t_sate
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
lr-scheduler: inverse_sqrt
warmup-init-lr: 1e-7
warmup-updates: 10000
lr: 2e-3
#adam_betas: (0.9,0.98)
criterion: label_smoothed_cross_entropy
label_smoothing: 0.1
encoder-normalize-before: True
decoder-normalize-before: True
conv-kernel-sizes: 5,5
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 12
text-encoder-layers: 6
decoder-layers: 6
encoder-attention-heads: 4
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
acoustic-encoder: transformer
adapter: league
encoder-attention-type: relative
decoder-attention-type: relative
max-encoder-relative-length: 100
max-decoder-relative-length: 20
#decoder-embed-dim: 256
#decoder-ffn-embed-dim: 2048
#decoder-attention-heads: 4
#attention-dropout: 0.1
#activation-dropout: 0.1
egs/mustc/st/decode.sh
...@@ -31,9 +31,9 @@ cmd="./run.sh ...@@ -31,9 +31,9 @@ cmd="./run.sh
if [[ -n ${data_dir} ]]; then if [[ -n ${data_dir} ]]; then
cmd="$cmd --data_dir ${data_dir}" cmd="$cmd --data_dir ${data_dir}"
fi fi
if [[ -n ${test_subset} ]]; then if [[ ${#test_subset[@]} -eq 0 ]]; then
test_subset=`echo ${test_subset[*]} | sed 's/ /,/g'` subsets=$(echo ${test_subset[*]} | sed 's/ /,/g')
cmd="$cmd --test_subset ${test_subset}" cmd="$cmd --test_subset ${subsets}"
fi fi
echo $cmd echo $cmd
......
egs/mustc/st/local/monitor.sh
...@@ -3,15 +3,19 @@ cmd="sh train.sh" ...@@ -3,15 +3,19 @@ cmd="sh train.sh"
while : while :
do do
all_devices=$(seq 0 `gpustat | sed '1,2d' | wc -l`); record=$(mktemp -t temp.record.XXXXXX)
gpustat > $record
all_devices=$(seq 0 "$(sed '1,2d' ${record} | wc -l)");
count=0 count=0
for dev in ${all_devices[@]} for dev in "${all_devices[@]}"
do do
line=`expr $dev + 2` line=$((dev + 2))
use=`gpustat -p | head -n $line | tail -1 | cut -d '|' -f4 | wc -w` use=$(head -n $line ${record} | tail -1 | cut -d '|' -f3 | cut -d '/' -f1)
if [[ $use -eq 0 ]]; then
if [[ $use -lt 100 ]]; then
device[$count]=$dev device[$count]=$dev
count=`expr $count + 1` count=$((count + 1))
if [[ $count -eq $gpu_num ]]; then if [[ $count -eq $gpu_num ]]; then
break break
fi fi
......
egs/mustc/st/local/path.sh deleted 100755 → 0
MAIN_ROOT=$PWD/../../..
KALDI_ROOT=$MAIN_ROOT/tools/kaldi
export PATH=$PWD/utils/:$KALDI_ROOT/tools/openfst/bin:$PATH
[ ! -f $KALDI_ROOT/tools/config/common_path.sh ] && echo >&2 "The standard file $KALDI_ROOT/tools/config/common_path.sh is not present -> Exit!" && exit 1
. $KALDI_ROOT/tools/config/common_path.sh
export LC_ALL=C
export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:$MAIN_ROOT/src/lib
export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:$MAIN_ROOT/tools/chainer_ctc/ext/warp-ctc/build
. "${MAIN_ROOT}"/tools/activate_python.sh && . "${MAIN_ROOT}"/tools/extra_path.sh
export PATH=$MAIN_ROOT/utils:$MAIN_ROOT/espnet/bin:$PATH
export OMP_NUM_THREADS=1
# check extra module installation
if ! which tokenizer.perl > /dev/null; then
echo "Error: it seems that moses is not installed." >&2
echo "Error: please install moses as follows." >&2
echo "Error: cd ${MAIN_ROOT}/tools && make moses.done" >&2
return 1
fi
# NOTE(kan-bayashi): Use UTF-8 in Python to avoid UnicodeDecodeError when LC_ALL=C
export PYTHONIOENCODING=UTF-8
egs/mustc/st/local/utils.sh
...@@ -5,17 +5,18 @@ get_devices(){ ...@@ -5,17 +5,18 @@ get_devices(){
device=() device=()
while : while :
do do
record=`mktemp -t temp.record.XXXXXX` record=$(mktemp -t temp.record.XXXXXX)
gpustat > $record gpustat > $record
all_devices=$(seq 0 `cat $record | sed '1,2d' | wc -l`); all_devices=$(seq 0 "$(sed '1,2d' ${record} | wc -l)");
count=0 count=0
for dev in ${all_devices[@]} for dev in "${all_devices[@]}"
do do
line=`expr $dev + 2` line=$((dev + 2))
use=`cat $record | head -n $line | tail -1 | cut -d '|' -f3 | cut -d '/' -f1` use=$(head -n $line ${record} | tail -1 | cut -d '|' -f3 | cut -d '/' -f1)
if [[ $use -lt 100 ]]; then if [[ $use -lt 100 ]]; then
device[$count]=$dev device[$count]=$dev
count=`expr $count + 1` count=$((count + 1))
if [[ $count -eq $gpu_num ]]; then if [[ $count -eq $gpu_num ]]; then
break break
fi fi
......
egs/mustc/st/run.sh
...@@ -48,8 +48,8 @@ specific_dir=/home/xuchen/st/data/mustc/st_lcrm/en-de ...@@ -48,8 +48,8 @@ specific_dir=/home/xuchen/st/data/mustc/st_lcrm/en-de
asr_vocab_prefix=spm_unigram10000_st_share asr_vocab_prefix=spm_unigram10000_st_share
st_vocab_prefix=spm_unigram10000_st_share st_vocab_prefix=spm_unigram10000_st_share
org_data_dir=/media/data/${dataset} org_data_dir=~/st/data/${dataset}
data_dir=~/st/data/${dataset}/st data_dir=~/st/data/${dataset}/asr
test_subset=tst-COMMON test_subset=tst-COMMON
# exp # exp
...@@ -60,9 +60,7 @@ exp_tag=baseline ...@@ -60,9 +60,7 @@ exp_tag=baseline
exp_name= exp_name=
# config # config
train_config=train_ctc.yaml train_config=ctc
train_config1=
train_config2=
# training setting # training setting
fp16=1 fp16=1
...@@ -100,10 +98,9 @@ fi ...@@ -100,10 +98,9 @@ fi
. ./local/parse_options.sh || exit 1; . ./local/parse_options.sh || exit 1;
# full path
train_config=$pwd_dir/conf/${train_config}
if [[ -z ${exp_name} ]]; then if [[ -z ${exp_name} ]]; then
exp_name=${exp_prefix}_$(basename ${train_config%.*})_${exp_tag} # exp_name=${exp_prefix}_$(basename ${train_config%.*})_${exp_tag}
exp_name=${exp_prefix}_${train_config}_${exp_tag}
if [[ -n ${extra_tag} ]]; then if [[ -n ${extra_tag} ]]; then
exp_name=${exp_name}_${extra_tag} exp_name=${exp_name}_${extra_tag}
fi fi
...@@ -122,7 +119,6 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then ...@@ -122,7 +119,6 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
if [[ ! -e ${data_dir}/${lang} ]]; then if [[ ! -e ${data_dir}/${lang} ]]; then
mkdir -p ${data_dir}/${lang} mkdir -p ${data_dir}/${lang}
fi fi
source ~/tools/audio/bin/activate
cmd="python ${root_dir}/examples/speech_to_text/prep_mustc_data.py cmd="python ${root_dir}/examples/speech_to_text/prep_mustc_data.py
--data-root ${org_data_dir} --data-root ${org_data_dir}
...@@ -185,7 +181,6 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then ...@@ -185,7 +181,6 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
echo -e "\033[34mRun command: \n${cmd} \033[0m" echo -e "\033[34mRun command: \n${cmd} \033[0m"
[[ $eval -eq 1 ]] && eval ${cmd} [[ $eval -eq 1 ]] && eval ${cmd}
deactivate
fi fi
data_dir=${data_dir}/${lang} data_dir=${data_dir}/${lang}
...@@ -196,7 +191,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then ...@@ -196,7 +191,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
if [[ -z ${device} || ${#device[@]} -eq 0 ]]; then if [[ -z ${device} || ${#device[@]} -eq 0 ]]; then
if [[ ${gpu_num} -eq 0 ]]; then if [[ ${gpu_num} -eq 0 ]]; then
device=() device=""
else else
source ./local/utils.sh source ./local/utils.sh
device=$(get_devices $gpu_num 0) device=$(get_devices $gpu_num 0)
...@@ -213,12 +208,31 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then ...@@ -213,12 +208,31 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
cp ${BASH_SOURCE[0]} ${model_dir} cp ${BASH_SOURCE[0]} ${model_dir}
cp ${PWD}/train.sh ${model_dir} cp ${PWD}/train.sh ${model_dir}
cp ${train_config} ${model_dir}
config_list="${train_config//,/ }"
idx=0
for config in "${config_list[@]}"
do
config_path=$pwd_dir/conf/${config}.yaml
if [[ ! -f ${config_path} ]]; then
echo "No config file ${config_path}"
exit
fi
cp ${config_path} ${model_dir}
if [[ idx -eq 0 ]]; then
extra_parameter="${extra_parameter}
--train-config ${config_path}"
else
extra_parameter="${extra_parameter}
--train-config${idx} ${config_path}"
fi
idx=$((idx + 1))
done
cmd="python3 -u ${root_dir}/fairseq_cli/train.py cmd="python3 -u ${root_dir}/fairseq_cli/train.py
${data_dir} ${data_dir}
--config-yaml ${data_config} --config-yaml ${data_config}
--train-config ${train_config}
--task ${task} --task ${task}
--max-tokens ${max_tokens} --max-tokens ${max_tokens}
--skip-invalid-size-inputs-valid-test --skip-invalid-size-inputs-valid-test
...@@ -227,14 +241,6 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then ...@@ -227,14 +241,6 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
--save-dir ${model_dir} --save-dir ${model_dir}
--tensorboard-logdir ${model_dir}" --tensorboard-logdir ${model_dir}"
if [[ -n ${train_config1} ]]; then
cmd="${cmd}
--train-config1 ${train_config1}"
fi
if [[ -n ${train_config2} ]]; then
cmd="${cmd}
--train-config2 ${train_config2}"
fi
if [[ -n ${extra_parameter} ]]; then if [[ -n ${extra_parameter} ]]; then
cmd="${cmd} cmd="${cmd}
${extra_parameter}" ${extra_parameter}"
...@@ -297,8 +303,8 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then ...@@ -297,8 +303,8 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
# save info # save info
log=./history.log log=./history.log
echo "${time} | ${device} | ${data_dir} | ${model_dir} " >> $log echo "${time} | ${device} | ${data_dir} | ${exp_name} | ${model_dir} " >> $log
cat $log | tail -n 50 > tmp.log tail -n 50 ${log} > tmp.log
mv tmp.log $log mv tmp.log $log
export CUDA_VISIBLE_DEVICES=${device} export CUDA_VISIBLE_DEVICES=${device}
...@@ -306,7 +312,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then ...@@ -306,7 +312,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
if [[ $eval -eq 1 ]]; then if [[ $eval -eq 1 ]]; then
eval $cmd eval $cmd
sleep 2s sleep 2s
tail -n `wc -l ${model_dir}/train.log | awk '{print $1+1}'` -f ${model_dir}/train.log tail -n "$(wc -l ${model_dir}/train.log | awk '{print $1+1}')" -f ${model_dir}/train.log
fi fi
fi fi
wait wait
...@@ -329,7 +335,7 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then ...@@ -329,7 +335,7 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
if [[ -z ${device} || ${#device[@]} -eq 0 ]]; then if [[ -z ${device} || ${#device[@]} -eq 0 ]]; then
if [[ ${gpu_num} -eq 0 ]]; then if [[ ${gpu_num} -eq 0 ]]; then
device=() device=""
else else
source ./local/utils.sh source ./local/utils.sh
device=$(get_devices $gpu_num 0) device=$(get_devices $gpu_num 0)
...@@ -340,8 +346,8 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then ...@@ -340,8 +346,8 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
result_file=${model_dir}/decode_result result_file=${model_dir}/decode_result
[[ -f ${result_file} ]] && rm ${result_file} [[ -f ${result_file} ]] && rm ${result_file}
test_subset=(${test_subset//,/ }) test_subset=${test_subset//,/ }
for subset in ${test_subset[@]}; do for subset in "${test_subset[@]}"; do
subset=${subset}_st subset=${subset}_st
cmd="python ${root_dir}/fairseq_cli/generate.py cmd="python ${root_dir}/fairseq_cli/generate.py
${data_dir} ${data_dir}
......
egs/mustc/st/train.sh
...@@ -6,29 +6,18 @@ gpu_num=8 ...@@ -6,29 +6,18 @@ gpu_num=8
update_freq=1 update_freq=1
max_tokens=40000 max_tokens=40000
exp_tag=
config_list=(ctc local_attn)
# exp full name
exp_name= exp_name=
extra_tag= extra_tag=
extra_parameter= extra_parameter=
#extra_tag="${extra_tag}" #extra_tag="${extra_tag}"
#extra_parameter="${extra_parameter} " #extra_parameter="${extra_parameter} "
#extra_tag="${extra_tag}_encdlcl" train_config=$(echo ${config_list[*]} | sed 's/ /,/g')
#extra_parameter="${extra_parameter} --use-enc-dlcl"
#extra_tag="${extra_tag}_decdlcl"
#extra_parameter="${extra_parameter} --use-dec-dlcl"
exp_tag=baseline
train_config=train_ctc.yaml
#train_config=train_ctc_conformer.yaml
#train_config=train_ctc_conformer_rpr.yaml
#train_config=train_ctc_sate.yaml
#train_config=train_ctc_sate_rpr.yaml
#train_config=train_ctc_sate_conformer.yaml
#train_config=train_ctc_sate_conformer_rpr.yaml
train_config1=train_local_attn.yaml
cmd="./run.sh cmd="./run.sh
--stage 1 --stage 1
...@@ -39,9 +28,6 @@ cmd="./run.sh ...@@ -39,9 +28,6 @@ cmd="./run.sh
--max_tokens ${max_tokens} --max_tokens ${max_tokens}
" "
if [[ -n ${train_config1} ]]; then
cmd="$cmd --train_config1 ${train_config1}"
fi
if [[ -n ${exp_name} ]]; then if [[ -n ${exp_name} ]]; then
cmd="$cmd --exp_name ${exp_name}" cmd="$cmd --exp_name ${exp_name}"
fi fi
...@@ -52,8 +38,9 @@ if [[ -n ${extra_tag} ]]; then ...@@ -52,8 +38,9 @@ if [[ -n ${extra_tag} ]]; then
cmd="$cmd --extra_tag ${extra_tag}" cmd="$cmd --extra_tag ${extra_tag}"
fi fi
if [[ -n ${extra_parameter} ]]; then if [[ -n ${extra_parameter} ]]; then
cmd="$cmd --extra_parameter \"${extra_parameter}\"" # cmd="$cmd --extra_parameter \"${extra_parameter}\""
cmd="$cmd --extra_parameter ${extra_parameter}"
fi fi
echo $cmd echo ${cmd}
eval $cmd eval ${cmd}
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论