Skip to content

F
Fairseq-S2T
Commit be9c1ab4 by xuchen
Options

optimize the shell script

parent b23817e0
正在显示 包含 244 行增加 和 473 行删除
egs/librispeech/asr/conf/train.yaml → egs/librispeech/asr/conf/base.yaml
train-subset: train_st train-subset: train-clean-100,train-clean-360,train-other-500
valid-subset: dev_st valid-subset: dev-clean
max-epoch: 50 max-epoch: 100
max-update: 100000 max-update: 300000
num-workers: 8 num-workers: 8
patience: 10 patience: 10
......
egs/librispeech/asr/conf/conformer.yaml 0 → 100644
arch: s2t_conformer_s
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
egs/librispeech/asr/conf/train_ctc_debug.yaml → egs/librispeech/asr/conf/ctc_debug.yaml
...@@ -12,7 +12,7 @@ log-interval: 100 ...@@ -12,7 +12,7 @@ log-interval: 100
seed: 1 seed: 1
report-accuracy: True report-accuracy: True
arch: s2t_transformer_s #arch: s2t_transformer_s
share-decoder-input-output-embed: True share-decoder-input-output-embed: True
optimizer: adam optimizer: adam
clip-norm: 10.0 clip-norm: 10.0
...@@ -26,13 +26,13 @@ ctc-weight: 0.3 ...@@ -26,13 +26,13 @@ ctc-weight: 0.3
criterion: label_smoothed_cross_entropy_with_ctc criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1 label_smoothing: 0.1
conv-kernel-sizes: 5,5 #conv-kernel-sizes: 5,5
conv-channels: 1024 conv-channels: 1024
dropout: 0.1 dropout: 0.1
activation-fn: relu activation-fn: relu
encoder-embed-dim: 256 #encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048 encoder-ffn-embed-dim: 2048
encoder-layers: 3 encoder-layers: 12
decoder-layers: 3 decoder-layers: 3
encoder-attention-heads: 4 encoder-attention-heads: 4
...@@ -42,8 +42,8 @@ cnn-module-kernel: 31 ...@@ -42,8 +42,8 @@ cnn-module-kernel: 31
adpater: subsample adpater: subsample
#decoder-embed-dim: 256 decoder-embed-dim: 256
#decoder-ffn-embed-dim: 2048 decoder-ffn-embed-dim: 2048
#decoder-attention-heads: 4 decoder-attention-heads: 4
#attention-dropout: 0.1 attention-dropout: 0.1
#activation-dropout: 0.1 activation-dropout: 0.1
egs/librispeech/asr/conf/dlcl.yaml 0 → 100644
use-enc-dlcl: True
use-dec-dlcl: True
egs/librispeech/asr/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/librispeech/asr/conf/train_ctc_conformer_rpr.yaml → egs/librispeech/asr/conf/pyramid.yaml
train-subset: train_st arch: pys2t_transformer_s
valid-subset: dev_st encoder-embed-dim: 512
pyramid-stages: 4
max-epoch: 50 pyramid-layers: 2_2_5_3
max-update: 100000 encoder-attention-type: reduced
pyramid-attn-sample-ratios: 8_4_2_1
pyramid-sr-ratios: 2_2_2_2
pyramid-embed-dims: 64_128_256_512
pyramid-reduced-embed: conv
pyramid-embed-norm: True
pyramid-position-embed: 1_1_1_1
pyramid-kernel-sizes: 5_5_5_5
pyramid-ffn-ratios: 8_8_8_4
pyramid-heads: 1_2_4_8
train-subset: train-clean-100,train-clean-360,train-other-500
valid-subset: dev-clean
max-epoch: 100
max-update: 300000
num-workers: 8 num-workers: 8
patience: 10 patience: 10
...@@ -14,7 +29,6 @@ report-accuracy: True ...@@ -14,7 +29,6 @@ report-accuracy: True
#load-pretrained-encoder-from: #load-pretrained-encoder-from:
#load-pretrained-decoder-from: #load-pretrained-decoder-from:
arch: s2t_conformer_s
share-decoder-input-output-embed: True share-decoder-input-output-embed: True
optimizer: adam optimizer: adam
clip-norm: 10.0 clip-norm: 10.0
...@@ -24,31 +38,19 @@ warmup-updates: 10000 ...@@ -24,31 +38,19 @@ warmup-updates: 10000
lr: 2e-3 lr: 2e-3
#adam_betas: (0.9,0.98) #adam_betas: (0.9,0.98)
ctc-weight: 0.3 criterion: label_smoothed_cross_entropy
criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1 label_smoothing: 0.1
conv-kernel-sizes: 5,5
conv-channels: 1024 conv-channels: 1024
dropout: 0.1 dropout: 0.1
activation-fn: relu activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048 encoder-ffn-embed-dim: 2048
encoder-layers: 12 encoder-layers: 12
decoder-layers: 6 decoder-layers: 6
encoder-attention-heads: 4 encoder-attention-heads: 4
macaron-style: True decoder-embed-dim: 256
use-cnn-module: True decoder-ffn-embed-dim: 2048
cnn-module-kernel: 31 decoder-attention-heads: 4
attention-dropout: 0.1
encoder-attention-type: relative activation-dropout: 0.1
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/librispeech/asr/conf/pyramid_enc6.yaml 0 → 100644
arch: pys2t_transformer_s
encoder-embed-dim: 512
pyramid-stages: 3
pyramid-layers: 3_6_3
encoder-attention-type: reduced
pyramid-attn-sample-ratios: 4_2_1
pyramid-sr-ratios: 2_2_2
pyramid-embed-dims: 128_256_512
pyramid-reduced-embed: conv
pyramid-embed-norm: True
pyramid-position-embed: 1_1_1
pyramid-kernel-sizes: 5_5_5
pyramid-ffn-ratios: 8_8_4
pyramid-heads: 2_4_8
train-subset: train-clean-100,train-clean-360,train-other-500
valid-subset: dev-clean
max-epoch: 100
max-update: 300000
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:
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
conv-channels: 1024
dropout: 0.1
activation-fn: relu
encoder-ffn-embed-dim: 2048
encoder-layers: 6
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
egs/librispeech/asr/conf/train_sate.yaml → egs/librispeech/asr/conf/pyramid_stage3.yaml
train-subset: train_st arch: pys2t_transformer_s
valid-subset: dev_st encoder-embed-dim: 512
pyramid-stages: 3
max-epoch: 50 pyramid-layers: 3_6_3
max-update: 100000 encoder-attention-type: reduced
pyramid-attn-sample-ratios: 4_2_1
pyramid-sr-ratios: 2_2_2
pyramid-embed-dims: 128_256_512
pyramid-reduced-embed: conv
pyramid-embed-norm: True
pyramid-position-embed: 1_1_1
pyramid-kernel-sizes: 5_5_5
pyramid-ffn-ratios: 8_8_4
pyramid-heads: 2_4_8
train-subset: train-clean-100,train-clean-360,train-other-500
valid-subset: dev-clean
max-epoch: 100
max-update: 300000
num-workers: 8 num-workers: 8
patience: 10 patience: 10
...@@ -12,11 +27,8 @@ seed: 1 ...@@ -12,11 +27,8 @@ seed: 1
report-accuracy: True report-accuracy: True
#load-pretrained-encoder-from: #load-pretrained-encoder-from:
#load-pretrained-acoustic-encoder-from:
#load-pretrained-text-encoder-from:
#load-pretrained-decoder-from: #load-pretrained-decoder-from:
arch: s2t_sate
share-decoder-input-output-embed: True share-decoder-input-output-embed: True
optimizer: adam optimizer: adam
clip-norm: 10.0 clip-norm: 10.0
...@@ -29,28 +41,16 @@ lr: 2e-3 ...@@ -29,28 +41,16 @@ lr: 2e-3
criterion: label_smoothed_cross_entropy criterion: label_smoothed_cross_entropy
label_smoothing: 0.1 label_smoothing: 0.1
encoder-normalize-before: True
decoder-normalize-before: True
conv-kernel-sizes: 5,5
conv-channels: 1024 conv-channels: 1024
dropout: 0.1 dropout: 0.1
activation-fn: relu activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048 encoder-ffn-embed-dim: 2048
encoder-layers: 12 encoder-layers: 12
text-encoder-layers: 6
decoder-layers: 6 decoder-layers: 6
encoder-attention-heads: 4 encoder-attention-heads: 4
macaron-style: True decoder-embed-dim: 256
use-cnn-module: True decoder-ffn-embed-dim: 2048
cnn-module-kernel: 31 decoder-attention-heads: 4
attention-dropout: 0.1
acoustic-encoder: transformer activation-dropout: 0.1
adapter: league
#decoder-embed-dim: 256
#decoder-ffn-embed-dim: 2048
#decoder-attention-heads: 4
#attention-dropout: 0.1
#activation-dropout: 0.1
egs/librispeech/asr/conf/rpr.yaml
encoder-attention-type: relative encoder-attention-type: rel_selfattn
decoder-attention-type: relative
max-encoder-relative-length: 100
max-decoder-relative-length: 20
\ No newline at end of file
egs/librispeech/asr/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/librispeech/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/librispeech/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/librispeech/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/librispeech/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/librispeech/asr/decode.sh
...@@ -3,7 +3,7 @@ ...@@ -3,7 +3,7 @@
gpu_num=1 gpu_num=1
data_dir= data_dir=
test_subset=(test-cleam test-other) test_subset=(test-clean test-other)
exp_name= exp_name=
if [ "$#" -eq 1 ]; then if [ "$#" -eq 1 ]; then
...@@ -13,7 +13,7 @@ fi ...@@ -13,7 +13,7 @@ fi
n_average=10 n_average=10
beam_size=5 beam_size=5
len_penalty=1.0 len_penalty=1.0
max_tokens=10000 max_tokens=80000
dec_model=checkpoint_best.pt dec_model=checkpoint_best.pt
cmd="./run.sh cmd="./run.sh
......
egs/librispeech/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 $gpu_num ]]; then
break break
fi fi
......
egs/librispeech/asr/local/path.sh deleted 100755 → 0
MAIN_ROOT=$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 ${MAIN_ROOT}/tools && make moses.done" >&2
return 1
fi
# NOTE(kan-bayashi): Use UTF-8 in Python to avoid UnicodeDecodeError when LC_ALL=C
export PYTHONIOENCODING=UTF-8
egs/librispeech/asr/local/utils.sh
...@@ -5,17 +5,18 @@ get_devices(){ ...@@ -5,17 +5,18 @@ get_devices(){
device=() device=()
while : while :
do do
record=`mktemp -t temp.record.XXXXXX` record=$(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 $gpu_num ]]; then
break break
fi fi
......
egs/librispeech/asr/run.sh
...@@ -20,7 +20,7 @@ stop_stage=0 ...@@ -20,7 +20,7 @@ stop_stage=0
######## hardware ######## ######## hardware ########
# devices # devices
device=() #device=()
gpu_num=8 gpu_num=8
update_freq=1 update_freq=1
...@@ -42,19 +42,19 @@ specific_prefix=valid ...@@ -42,19 +42,19 @@ specific_prefix=valid
specific_dir=/home/xuchen/st/data/mustc/st_lcrm/en-de specific_dir=/home/xuchen/st/data/mustc/st_lcrm/en-de
asr_vocab_prefix=spm_unigram10000_st_share asr_vocab_prefix=spm_unigram10000_st_share
org_data_dir=/media/data/${dataset} org_data_dir=~/st/data/${dataset}
data_dir=~/st/data/${dataset} data_dir=~/st/data/${dataset}
test_subset=dev-clean,dev-other,test-clean,test-other test_subset=dev-clean,dev-other,test-clean,test-other
# exp # exp
exp_prefix=${time} exp_prefix=$(date "+%m%d")
extra_tag= extra_tag=
extra_parameter= extra_parameter=
exp_tag=baseline exp_tag=baseline
exp_name= exp_name=
# config # config
train_config=train_ctc.yaml train_config=ctc
data_config=config.yaml data_config=config.yaml
# training setting # training setting
...@@ -79,10 +79,10 @@ fi ...@@ -79,10 +79,10 @@ fi
. ./local/parse_options.sh || exit 1; . ./local/parse_options.sh || exit 1;
# full path
train_config=$pwd_dir/conf/${train_config}
if [[ -z ${exp_name} ]]; then if [[ -z ${exp_name} ]]; then
exp_name=${exp_prefix}_$(basename ${train_config%.*})_${exp_tag} config_string=${train_config//,/_}
# exp_name=${exp_prefix}_$(basename ${train_config%.*})_${exp_tag}
exp_name=${exp_prefix}_${config_string}_${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
...@@ -102,7 +102,6 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then ...@@ -102,7 +102,6 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
if [[ ! -e ${data_dir} ]]; then if [[ ! -e ${data_dir} ]]; then
mkdir -p ${data_dir} mkdir -p ${data_dir}
fi fi
source ~/tools/audio/bin/activate
cmd="python ${root_dir}/examples/speech_to_text/prep_librispeech_data.py cmd="python ${root_dir}/examples/speech_to_text/prep_librispeech_data.py
--data-root ${org_data_dir} --data-root ${org_data_dir}
...@@ -120,7 +119,7 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then ...@@ -120,7 +119,7 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
--speed-perturb" --speed-perturb"
fi fi
echo -e "\033[34mRun command: \n${cmd} \033[0m" echo -e "\033[34mRun command: \n${cmd} \033[0m"
[[ $eval -eq 1 ]] && eval $cmd [[ $eval -eq 1 ]] && eval ${cmd}
fi fi
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
...@@ -129,7 +128,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then ...@@ -129,7 +128,7 @@ 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)
...@@ -146,12 +145,31 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then ...@@ -146,12 +145,31 @@ 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
...@@ -160,7 +178,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then ...@@ -160,7 +178,7 @@ 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
...@@ -213,8 +231,8 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then ...@@ -213,8 +231,8 @@ 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}
...@@ -222,7 +240,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then ...@@ -222,7 +240,7 @@ 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
...@@ -245,7 +263,7 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then ...@@ -245,7 +263,7 @@ 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)
...@@ -253,8 +271,6 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then ...@@ -253,8 +271,6 @@ 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 ${result_file}
......
egs/librispeech/asr/train.sh
...@@ -2,18 +2,23 @@ ...@@ -2,18 +2,23 @@
# training the model # training the model
gpu_num=8 gpu_num=4
update_freq=2 update_freq=1
max_tokens=20000 max_tokens=200000
exp_tag=
config_list=(base)
config_list=(pyramid)
# exp full name
exp_name=
extra_tag= extra_tag=
extra_parameter= extra_parameter=
#extra_tag="${extra_tag}" #extra_tag="${extra_tag}"
#extra_parameter="${extra_parameter} " #extra_parameter="${extra_parameter} "
exp_tag= train_config=$(echo ${config_list[*]} | sed 's/ /,/g')
train_config=train_ctc.yaml
cmd="./run.sh cmd="./run.sh
--stage 1 --stage 1
...@@ -24,6 +29,9 @@ cmd="./run.sh ...@@ -24,6 +29,9 @@ cmd="./run.sh
--max_tokens ${max_tokens} --max_tokens ${max_tokens}
" "
if [[ -n ${exp_name} ]]; then
cmd="$cmd --exp_name ${exp_name}"
fi
if [[ -n ${exp_tag} ]]; then if [[ -n ${exp_tag} ]]; then
cmd="$cmd --exp_tag ${exp_tag}" cmd="$cmd --exp_tag ${exp_tag}"
fi fi
...@@ -31,8 +39,9 @@ if [[ -n ${extra_tag} ]]; then ...@@ -31,8 +39,9 @@ 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/librispeech/asr/conf/train_ctc_sate_conformer_rpr.yaml → egs/mustc/asr/conf/pyramid_enc6.yaml
train-subset: train_st arch: pys2t_transformer_s
valid-subset: dev_st encoder-embed-dim: 512
pyramid-stages: 3
pyramid-layers: 2_2_2
pyramid-sr-ratios: 2_2_2
pyramid-embed-dims: 128_256_512
pyramid-reduced-embed: conv
pyramid-embed-norm: True
pyramid-position-embed: 1_0_0
pyramid-kernel-sizes: 5_5_5
pyramid-ffn-ratios: 8_8_4
pyramid-heads: 2_4_8
train-subset: train_asr
valid-subset: dev_asr
max-epoch: 50 max-epoch: 50
max-update: 100000 max-update: 100000
...@@ -12,11 +25,8 @@ seed: 1 ...@@ -12,11 +25,8 @@ seed: 1
report-accuracy: True report-accuracy: True
#load-pretrained-encoder-from: #load-pretrained-encoder-from:
#load-pretrained-acoustic-encoder-from:
#load-pretrained-text-encoder-from:
#load-pretrained-decoder-from: #load-pretrained-decoder-from:
arch: s2t_sate
share-decoder-input-output-embed: True share-decoder-input-output-embed: True
optimizer: adam optimizer: adam
clip-norm: 10.0 clip-norm: 10.0
...@@ -26,35 +36,17 @@ warmup-updates: 10000 ...@@ -26,35 +36,17 @@ warmup-updates: 10000
lr: 2e-3 lr: 2e-3
#adam_betas: (0.9,0.98) #adam_betas: (0.9,0.98)
ctc-weight: 0.3 criterion: label_smoothed_cross_entropy
criterion: label_smoothed_cross_entropy_with_ctc
label_smoothing: 0.1 label_smoothing: 0.1
encoder-normalize-before: True
decoder-normalize-before: True
conv-kernel-sizes: 5,5
conv-channels: 1024 conv-channels: 1024
dropout: 0.1 dropout: 0.1
activation-fn: relu activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048 encoder-ffn-embed-dim: 2048
encoder-layers: 12 encoder-layers: 6
text-encoder-layers: 6
decoder-layers: 6 decoder-layers: 6
encoder-attention-heads: 4 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-embed-dim: 256
decoder-ffn-embed-dim: 2048 decoder-ffn-embed-dim: 2048
decoder-attention-heads: 4 decoder-attention-heads: 4
......
egs/mustc/asr/conf/rpr.yaml
encoder-attention-type: relative encoder-attention-type: rel_selfattn
decoder-attention-type: relative
max-encoder-relative-length: 100
max-decoder-relative-length: 20
egs/mustc/asr/decode.sh
...@@ -13,7 +13,7 @@ fi ...@@ -13,7 +13,7 @@ fi
n_average=10 n_average=10
beam_size=5 beam_size=5
len_penalty=1.0 len_penalty=1.0
max_tokens=10000 max_tokens=80000
dec_model=checkpoint_best.pt dec_model=checkpoint_best.pt
cmd="./run.sh cmd="./run.sh
......
egs/mustc/asr/local/monitor.sh
...@@ -8,7 +8,7 @@ do ...@@ -8,7 +8,7 @@ do
all_devices=$(seq 0 "$(sed '1,2d' ${record} | wc -l)"); all_devices=$(seq 0 "$(sed '1,2d' ${record} | wc -l)");
count=0 count=0
for dev in "${all_devices[@]}" for dev in ${all_devices[@]}
do do
line=$((dev + 2)) line=$((dev + 2))
use=$(head -n $line ${record} | tail -1 | cut -d '|' -f3 | cut -d '/' -f1) use=$(head -n $line ${record} | tail -1 | cut -d '|' -f3 | cut -d '/' -f1)
......
egs/mustc/asr/local/utils.sh
...@@ -10,7 +10,7 @@ get_devices(){ ...@@ -10,7 +10,7 @@ get_devices(){
all_devices=$(seq 0 "$(sed '1,2d' ${record} | wc -l)"); all_devices=$(seq 0 "$(sed '1,2d' ${record} | wc -l)");
count=0 count=0
for dev in "${all_devices[@]}" for dev in ${all_devices[@]}
do do
line=$((dev + 2)) line=$((dev + 2))
use=$(head -n $line ${record} | tail -1 | cut -d '|' -f3 | cut -d '/' -f1) use=$(head -n $line ${record} | tail -1 | cut -d '|' -f3 | cut -d '/' -f1)
......
egs/mustc/asr/run.sh
...@@ -91,8 +91,9 @@ fi ...@@ -91,8 +91,9 @@ fi
. ./local/parse_options.sh || exit 1; . ./local/parse_options.sh || exit 1;
if [[ -z ${exp_name} ]]; then if [[ -z ${exp_name} ]]; then
config_string=${train_config//,/_}
# exp_name=${exp_prefix}_$(basename ${train_config%.*})_${exp_tag} # exp_name=${exp_prefix}_$(basename ${train_config%.*})_${exp_tag}
exp_name=${exp_prefix}_${train_config}_${exp_tag} exp_name=${exp_prefix}_${config_string}_${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
...@@ -170,7 +171,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then ...@@ -170,7 +171,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
config_list="${train_config//,/ }" config_list="${train_config//,/ }"
idx=0 idx=0
for config in "${config_list[@]}" for config in ${config_list[@]}
do do
config_path=$pwd_dir/conf/${config}.yaml config_path=$pwd_dir/conf/${config}.yaml
if [[ ! -f ${config_path} ]]; then if [[ ! -f ${config_path} ]]; then
...@@ -297,7 +298,7 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then ...@@ -297,7 +298,7 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
[[ -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} ${data_dir}
......
egs/mustc/asr/train.sh
...@@ -7,7 +7,7 @@ update_freq=1 ...@@ -7,7 +7,7 @@ update_freq=1
max_tokens=40000 max_tokens=40000
exp_tag= exp_tag=
config_list=(ctc local_attn) config_list=(pyramid)
# exp full name # exp full name
exp_name= exp_name=
......
egs/mustc/st/conf/rpr.yaml
encoder-attention-type: relative encoder-attention-type: rel_selfattn
decoder-attention-type: relative #encoder-attention-type: relative
max-encoder-relative-length: 100 #decoder-attention-type: relative
max-decoder-relative-length: 20 #max-encoder-relative-length: 100
#max-decoder-relative-length: 20
egs/mustc/st/local/monitor.sh
...@@ -8,7 +8,7 @@ do ...@@ -8,7 +8,7 @@ do
all_devices=$(seq 0 "$(sed '1,2d' ${record} | wc -l)"); all_devices=$(seq 0 "$(sed '1,2d' ${record} | wc -l)");
count=0 count=0
for dev in "${all_devices[@]}" for dev in ${all_devices[@]}
do do
line=$((dev + 2)) line=$((dev + 2))
use=$(head -n $line ${record} | tail -1 | cut -d '|' -f3 | cut -d '/' -f1) use=$(head -n $line ${record} | tail -1 | cut -d '|' -f3 | cut -d '/' -f1)
......
egs/mustc/st/local/utils.sh
...@@ -10,7 +10,7 @@ get_devices(){ ...@@ -10,7 +10,7 @@ get_devices(){
all_devices=$(seq 0 "$(sed '1,2d' ${record} | wc -l)"); all_devices=$(seq 0 "$(sed '1,2d' ${record} | wc -l)");
count=0 count=0
for dev in "${all_devices[@]}" for dev in ${all_devices[@]}
do do
line=$((dev + 2)) line=$((dev + 2))
use=$(head -n $line ${record} | tail -1 | cut -d '|' -f3 | cut -d '/' -f1) use=$(head -n $line ${record} | tail -1 | cut -d '|' -f3 | cut -d '/' -f1)
......
egs/mustc/st/run.sh
...@@ -49,7 +49,7 @@ asr_vocab_prefix=spm_unigram10000_st_share ...@@ -49,7 +49,7 @@ asr_vocab_prefix=spm_unigram10000_st_share
st_vocab_prefix=spm_unigram10000_st_share st_vocab_prefix=spm_unigram10000_st_share
org_data_dir=~/st/data/${dataset} org_data_dir=~/st/data/${dataset}
data_dir=~/st/data/${dataset}/asr data_dir=~/st/data/${dataset}/st
test_subset=tst-COMMON test_subset=tst-COMMON
# exp # exp
...@@ -99,8 +99,9 @@ fi ...@@ -99,8 +99,9 @@ fi
. ./local/parse_options.sh || exit 1; . ./local/parse_options.sh || exit 1;
if [[ -z ${exp_name} ]]; then if [[ -z ${exp_name} ]]; then
config_string=${train_config//,/_}
# exp_name=${exp_prefix}_$(basename ${train_config%.*})_${exp_tag} # exp_name=${exp_prefix}_$(basename ${train_config%.*})_${exp_tag}
exp_name=${exp_prefix}_${train_config}_${exp_tag} exp_name=${exp_prefix}_${config_string}_${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
...@@ -211,7 +212,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then ...@@ -211,7 +212,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
config_list="${train_config//,/ }" config_list="${train_config//,/ }"
idx=0 idx=0
for config in "${config_list[@]}" for config in ${config_list[@]}
do do
config_path=$pwd_dir/conf/${config}.yaml config_path=$pwd_dir/conf/${config}.yaml
if [[ ! -f ${config_path} ]]; then if [[ ! -f ${config_path} ]]; then
......
egs/mustc/st/train.sh
...@@ -6,7 +6,7 @@ gpu_num=8 ...@@ -6,7 +6,7 @@ gpu_num=8
update_freq=1 update_freq=1
max_tokens=40000 max_tokens=40000
exp_tag= exp_tag=baseline
config_list=(ctc local_attn) config_list=(ctc local_attn)
# exp full name # exp full name
......
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