Commit 12201609 by xuchen

shell and yaml

parent d88a22ef
......@@ -30,6 +30,3 @@ encoder-attention-heads: 8
decoder-embed-dim: 512
decoder-ffn-embed-dim: 2048
decoder-attention-heads: 8
\ No newline at end of file
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
ctc-weight: 0.3
\ No newline at end of file
# share-ctc-and-embed: True
\ No newline at end of file
inter-ctc-weight: 0.2
inter-ctc-layers: 6,9
inter-ctc-drop-prob: 0
share-inter-ctc: True
ctc-pae: none
# ctc-pae: inter_league
......
......@@ -3,10 +3,11 @@ inter-mixup-layer: -1
inter-mixup-decoder-layer: 0
inter-mixup-prob: 1.0
inter-mixup-ratio: 1.0
inter-mixup-beta: 0.5
inter-mixup-beta: 0.2
inter-mixup-keep-org: False
inter-mixup-decoder-emb: False
ctc-mixup-consistent-weight: 0
inter-ctc-mixup-consistent-weight: 0
mixup-consistent-weight: 0
cal-mixup-loss: True
no-specaugment: False
......
arch: pdss2t_transformer_s_8
pds-fusion: True
share-decoder-input-output-embed: True
optimizer: adam
......@@ -23,6 +22,3 @@ encoder-attention-heads: 4
decoder-embed-dim: 256
decoder-ffn-embed-dim: 2048
decoder-attention-heads: 4
\ No newline at end of file
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
\ No newline at end of file
......@@ -38,6 +38,3 @@ encoder-attention-heads: 4
decoder-embed-dim: 256
decoder-ffn-embed-dim: 2048
decoder-attention-heads: 4
\ No newline at end of file
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
\ No newline at end of file
......@@ -38,6 +38,3 @@ encoder-attention-heads: 4
decoder-embed-dim: 256
decoder-ffn-embed-dim: 2048
decoder-attention-heads: 4
\ No newline at end of file
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
\ No newline at end of file
......@@ -38,6 +38,3 @@ encoder-attention-heads: 4
decoder-embed-dim: 256
decoder-ffn-embed-dim: 2048
decoder-attention-heads: 4
\ No newline at end of file
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
......@@ -38,6 +38,3 @@ encoder-attention-heads: 8
decoder-embed-dim: 512
decoder-ffn-embed-dim: 2048
decoder-attention-heads: 8
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
......@@ -23,13 +23,8 @@ subsampling-norm: none
subsampling-activation: glu
dropout: 0.1
attention-dropout: 0.1
activation-dropout: 0.1
activation-fn: relu
encoder-embed-dim: 256
encoder-ffn-embed-dim: 2048
encoder-layers: 18
encoder-attention-heads: 4
\ No newline at end of file
#load-pretrained-encoder-from:
\ No newline at end of file
encoder-attention-type: rel_selfattn
# encoder-attention-type: relative
# max-encoder-relative-length: 100
\ No newline at end of file
encoder-attention-type: rel_pos
#encoder-attention-type: rel_pos_legacy
#encoder-attention-type: rel_selfattn
#encoder-attention-type: relative
#decoder-attention-type: relative
#max-encoder-relative-length: 100
#max-decoder-relative-length: 20
......@@ -19,8 +19,8 @@ max_tokens=80000
dec_model=checkpoint_best.pt
cmd="./run.sh
--stage 3
--stop_stage 3
--stage 2
--stop_stage 2
--gpu_num ${gpu_num}
--exp_name ${exp_name}
--n_average ${n_average}
......
#!/usr/bin/env bash
gpu_num=4
cmd="sh train.sh"
......
......@@ -4,7 +4,7 @@
gpu_num=2
update_freq=1
max_tokens=160000
max_tokens=100000
extra_tag=
extra_parameter=
......@@ -33,7 +33,7 @@ train_config=$(echo ${config_list[*]} | sed 's/ /,/g')
cmd="./run.sh
--stage 1
--stop_stage 1
--stop_stage 2
--gpu_num ${gpu_num}
--update_freq ${update_freq}
--train_config ${train_config}
......
......@@ -30,3 +30,8 @@ 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
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
\ No newline at end of file
......@@ -3,7 +3,7 @@ valid-subset: dev-other,dev-clean
max-epoch: 300
max-update: 300000
patience: 50
patience: 20
post-process: sentencepiece
# best-checkpoint-metric: loss
......@@ -18,8 +18,8 @@ best_checkpoint_metric: dec_wer
maximize_best_checkpoint_metric: False
validate-interval: 5
# no-epoch-checkpoints: True
keep-last-epochs: 10
no-epoch-checkpoints: True
# keep-last-epochs: 10
keep-best-checkpoints: 10
num-workers: 8
......
macaron-style: True
use-cnn-module: True
cnn-module-kernel: 31
cnn-module-kernel: 15
encoder-attention-type: rel_pos
encoder-activation-fn: swish
layer-padding-mask: True
\ No newline at end of file
......@@ -5,10 +5,13 @@ share-inter-ctc: True
ctc-pae: none
# ctc-pae: inter_league
# ctc-pae-ground-truth-ratio: 0.1
# pae-gumbel: True
# pae-distribution-hard: True
# pae-drop-prob: 0.0
# pae-distribution-cutoff: 10
# share-pae-and-ctc: True
# pae-embed-norm: True
# pae-out-norm: True
......
......@@ -3,11 +3,15 @@ inter-mixup-layer: -1
inter-mixup-decoder-layer: 0
inter-mixup-prob: 1.0
inter-mixup-ratio: 1.0
inter-mixup-beta: 0.5
inter-mixup-beta: 0.2
inter-mixup-keep-org: False
inter-mixup-decoder-emb: False
ctc-mixup-consistent-weight: 0
inter-ctc-mixup-consistent-weight: 0
mixup-consistent-weight: 0
cal-mixup-loss: True
no-specaugment: False
layer-out-norm: False
inter-mixup-ratio-decay: False
inter-mixup-ratio-decay-params: 20000,40000,0
\ No newline at end of file
arch: pdss2t_transformer_s_8
pds-fusion: True
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
......
arch: pdss2t_transformer_s_8
# pds-ctc: 1_1_0
encoder-embed-dim: 256
pds-stages: 3
pds-layers: 4_4_4
......
......@@ -2,7 +2,6 @@ arch: pdss2t_transformer_sd_32
encoder-embed-dim: 256
pds-stages: 5
# ctc-layer: 12
pds-layers: 3_3_4_4_4
pds-ratios: 2_2_2_2_2
pds-fusion: False
......
encoder-attention-type: rel_selfattn
encoder-attention-type: rel_pos
#encoder-attention-type: rel_pos_legacy
#encoder-attention-type: rel_selfattn
#encoder-attention-type: relative
#decoder-attention-type: relative
#max-encoder-relative-length: 100
#max-decoder-relative-length: 20
......@@ -17,8 +17,8 @@ max_tokens=100000
dec_model=checkpoint_best.pt
cmd="./run.sh
--stage 3
--stop_stage 3
--stage 2
--stop_stage 2
--gpu_num ${gpu_num}
--exp_name ${exp_name}
--n_average ${n_average}
......
......@@ -14,7 +14,7 @@ get_devices(){
do
line=$((dev + 2))
use=$(head -n $line ${record} | tail -1 | cut -d '|' -f3 | cut -d '/' -f1)
if [[ $use -lt 100 ]]; then
if [[ $use -lt 1000 ]]; then
device[$count]=$dev
count=$((count + 1))
if [[ $count -eq $gpu_num ]]; then
......
......@@ -2,8 +2,7 @@
# Processing LibriSpeech Datasets
# Copyright 2021 Natural Language Processing Laboratory
# Xu Chen (xuchenneu@163.com)
# Copyright 2021 Chen Xu (xuchennlp@outlook.com)
# Set bash to 'debug' mode, it will exit on :
# -e 'error', -u 'undefined variable', -o ... 'error in pipeline', -x 'print commands',
......@@ -16,27 +15,26 @@ eval=1
time=$(date "+%m%d_%H%M")
stage=1
stop_stage=4
stop_stage=2
######## hardware ########
# devices
######## Hardware ########
# Devices
device=(0)
gpu_num=8
update_freq=1
max_tokens=100000
root_dir=/opt/tiger
# data_root_dir=/mnt/bd/data-model
data_root_dir=/mnt/bn/nas-xc-1
code_dir=${root_dir}/s2t
pwd_dir=$PWD
root_dir=${ST_ROOT}
data_root_dir=${root_dir}
# dataset
code_dir=${root_dir}/S2T
# Dataset
src_lang=en
lang=${src_lang}
dataset=librispeech
data_tag=asr_mlo
data_tag=asr
task=speech_to_text
vocab_type=unigram
......@@ -60,22 +58,17 @@ test_subset=dev-clean,dev-other,test-clean,test-other,all
# exp
sub_tag=
exp_prefix=$(date "+%m%d")
# exp_subfix=${ARNOLD_JOB_ID}_${ARNOLD_TASK_ID}_${ARNOLD_TRIAL_ID}
extra_tag=
extra_parameter=
exp_tag=baseline
exp_name=
# config
# Training Settings
train_config=base
data_config=config.yaml
# training setting
fp16=1
max_tokens=100000
step_valid=0
# decoding setting
# Decoding Settings
dec_model=checkpoint_best.pt
cer=0
ctc_infer=0
......@@ -87,8 +80,12 @@ len_penalty=1.0
single=0
epoch_ensemble=0
best_ensemble=1
infer_parameters=
infer_score=0
# infer_parameters="--cal-monotonic-cross-attn-weights --cal-localness --localness-window 0.1 --cal-topk-cross-attn-weights --topk-cross-attn-weights 15 --cal-entropy"
data_config=config.yaml
# Parsing Options
if [[ ${speed_perturb} -eq 1 ]]; then
data_dir=${data_dir}_sp
exp_prefix=${exp_prefix}_sp
......@@ -116,13 +113,6 @@ export NCCL_IB_HCA=$ARNOLD_RDMA_DEVICE:1
export NCCL_IB_GID_INDEX=3
export NCCL_SOCKET_IFNAME=eth0
HOSTS=$ARNOLD_WORKER_HOSTS
HOST=(${HOSTS//,/ })
HOST_SPLIT=(${HOST//:/ })
PORT=${HOST_SPLIT[1]}
INIT_METHOD="tcp://${ARNOLD_WORKER_0_HOST}:${ARNOLD_WORKER_0_PORT}"
DIST_RANK=$((ARNOLD_ID * ARNOLD_WORKER_GPU))
export PATH=$PATH:${code_dir}/scripts
. ./local/parse_options.sh || exit 1;
......@@ -136,22 +126,27 @@ if [[ -z ${exp_name} ]]; then
exp_name=${exp_name}_${exp_subfix}
fi
fi
ckpt_dir=${code_dir}/checkpoints/
model_dir=${code_dir}/checkpoints/${data_model_subfix}/${sub_tag}/${exp_name}
echo "stage: $stage"
echo "stop_stage: $stop_stage"
ckpt_dir=${root_dir}/checkpoints/
model_dir=${root_dir}/checkpoints/${data_model_subfix}/${sub_tag}/${exp_name}
# Start
cd ${code_dir}
echo "Start Stage: $stage"
echo "Stop Stage: $stop_stage"
if [[ `pip list | grep fairseq | wc -l` -eq 0 ]]; then
echo "Default Stage: env configure"
pip3 install -e ${code_dir}
fi
if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
echo "stage -1: Data Download"
# pass
echo "Stage -1: Data Download"
fi
if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
### Task dependent. You have to make data the following preparation part by yourself.
### But you can utilize Kaldi recipes in most cases
echo "stage 0: Data Preparation"
echo "Stage 0: Data Preparation"
if [[ ! -e ${data_dir} ]]; then
mkdir -p ${data_dir}
......@@ -160,8 +155,6 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
cmd="python3 ${code_dir}/examples/speech_to_text/prep_librispeech_data.py
--data-root ${org_data_dir}
--output-root ${data_dir}
--cmvn-type global
--gcmvn-max-num 300000
--vocab-type ${vocab_type}
--vocab-size ${vocab_size}"
......@@ -178,17 +171,8 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
[[ $eval -eq 1 ]] && eval ${cmd}
fi
echo "stage 1: env configure"
if [[ `pip list | grep fairseq | wc -l` -eq 0 ]]; then
pip3 install -e ${code_dir} -i https://bytedpypi.byted.org/simple --no-build-isolation --default-timeout=10000
fi
if [[ -d /mnt/bn/nas-xc-1/checkpoints && ! -d ${code_dir}/checkpoints ]]; then
ln -s /mnt/bn/nas-xc-1/checkpoints ${code_dir}
fi
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
echo "stage 2: ASR Network Training"
if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
echo "Stage 1: Network Training"
[[ ! -d ${data_dir} ]] && echo "The data dir ${data_dir} is not existing!" && exit 1;
if [[ -z ${device} || ${#device[@]} -eq 0 ]]; then
......@@ -198,6 +182,7 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
source ./local/utils.sh
device=$(get_devices $gpu_num 0)
fi
export CUDA_VISIBLE_DEVICES=${device}
fi
echo -e "data=${data_dir} model=${model_dir}"
......@@ -249,8 +234,6 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
cmd="${cmd}
--distributed-world-size $gpu_num
--ddp-backend no_c10d"
# --distributed-init-method ${INIT_METHOD}
# --distributed-rank ${DIST_RANK}"
fi
if [[ $fp16 -eq 1 ]]; then
cmd="${cmd}
......@@ -291,18 +274,13 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
echo "${time} | ${data_dir} | ${exp_name} | ${model_dir} " >> $log
tail -n 50 ${log} > tmp.log
mv tmp.log $log
# export CUDA_VISIBLE_DEVICES=${device}
log=${model_dir}/train.log
cmd="${cmd} 2>&1 | tee -a ${log}"
#cmd="nohup ${cmd} >> ${log} 2>&1 &"
if [[ $eval -eq 1 ]]; then
# tensorboard
if [[ -z ${ARNOLD_TENSORBOARD_CURRENT_PORT} ]]; then
port=6666
else
port=${ARNOLD_TENSORBOARD_CURRENT_PORT}
fi
tensorboard --logdir ${model_dir} --port ${port} --bind_all &
echo "${cmd}" > ${model_dir}/cmd
......@@ -312,8 +290,8 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
fi
fi
if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
echo "stage 3: ASR Decoding"
if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
echo "Stage 2: Decoding"
dec_models=
if [[ ${single} -eq 1 ]]; then
dec_models=${dec_model}
......@@ -355,8 +333,8 @@ if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
source ./local/utils.sh
device=$(get_devices $gpu_num 0)
fi
export CUDA_VISIBLE_DEVICES=${device}
fi
# export CUDA_VISIBLE_DEVICES=${device}
for dec_model in ${dec_models[@]}; do
suffix=beam${beam_size}_alpha${len_penalty}_tokens${max_tokens}
......@@ -419,13 +397,13 @@ if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
echo -e "\033[34mRun command: \n${cmd} \033[0m"
cd ${code_dir}
if [[ $eval -eq 1 ]]; then
src_ctc_file=translation-${subset}.txt.ctc
if [[ -f ${model_dir}/${src_ctc_file} ]]; then
rm ${model_dir}/${src_ctc_file}
ctc_file=translation-${subset}.ctc
if [[ -f ${model_dir}/${ctc_file} ]]; then
rm ${model_dir}/${ctc_file}
fi
cd ${code_dir}
eval $cmd
echo "" >> ${result_file}
tail -n 2 ${model_dir}/generate-${subset}.txt >> ${result_file}
......@@ -441,27 +419,27 @@ if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
fi
trans_file=translation-${subset}-${suffix}.txt
if [[ ${ctc_infer} -eq 1 && -f ${model_dir}/${src_ctc_file} ]]; then
if [[ ${ctc_infer} -eq 1 && -f ${model_dir}/${ctc_file} ]]; then
ref_file=${model_dir}/${subset}.${src_lang}
if [[ ! -f ${ref_file} ]]; then
python3 ./local/extract_txt_from_tsv.py ${data_dir}/${subset}.tsv ${ref_file} "src_text"
fi
if [[ -f ${ref_file} ]]; then
src_ctc=$(mktemp -t temp.record.XXXXXX)
ctc=$(mktemp -t temp.record.XXXXXX)
cd ./local
./cal_wer.sh ${model_dir} ${subset} ${trans_file} ${src_ctc_file} ${ref_file} > ${src_ctc}
./cal_wer.sh ${model_dir} ${subset} ${trans_file} ${ctc_file} ${ref_file} > ${ctc}
cd ..
echo "CTC WER" >> ${result_file}
tail -n 2 ${src_ctc} >> ${result_file}
tail -n 2 ${ctc} >> ${result_file}
src_bleu=$(mktemp -t temp.record.XXXXXX)
cd local
./cal_ctc_bleu.sh ${model_dir} ${subset} ${trans_file} ${src_ctc_file} ${ref_file} ${tokenizer} ${src_lang} > ${src_bleu}
./cal_ctc_bleu.sh ${model_dir} ${subset} ${trans_file} ${ctc_file} ${ref_file} ${tokenizer} ${src_lang} > ${src_bleu}
cd ..
cat ${src_bleu} >> ${result_file}
rm ${src_ctc} ${src_bleu}
rm ${ctc} ${src_bleu}
else
echo "No reference for source language."
fi
......
......@@ -59,7 +59,7 @@ train_config=$(echo ${config_list[*]} | sed 's/ /,/g')
cmd="./run.sh
--stage 1
--stop_stage 4
--stop_stage 2
--gpu_num ${gpu_num}
--update_freq ${update_freq}
--train_config ${train_config}
......
......@@ -85,8 +85,8 @@ dec_model=checkpoint_best.pt
n_average=10
beam_size=5
len_penalty=1.0
infer_score=1
infer_parameters="--cal-monotonic-cross-attn-weights --cal-localness --localness-window 0.1 --cal-topk-cross-attn-weights --topk-cross-attn-weights 15 --cal-entropy"
infer_score=0
# infer_parameters="--cal-monotonic-cross-attn-weights --cal-localness --localness-window 0.1 --cal-topk-cross-attn-weights --topk-cross-attn-weights 15 --cal-entropy"
# Parsing Options
if [[ ${speed_perturb} -eq 1 ]]; then
......
......@@ -33,7 +33,7 @@ train_config=$(echo ${config_list[*]} | sed 's/ /,/g')
cmd="./run.sh
--stage 1
--stop_stage 4
--stop_stage 2
--gpu_num ${gpu_num}
--update_freq ${update_freq}
--train_config ${train_config}
......
......@@ -84,8 +84,8 @@ dec_model=checkpoint_best.pt
n_average=10
beam_size=5
len_penalty=1.0
infer_score=1
infer_parameters="--cal-monotonic-cross-attn-weights --cal-localness --localness-window 0.1 --cal-topk-cross-attn-weights --topk-cross-attn-weights 15 --cal-entropy"
infer_score=0
# infer_parameters="--cal-monotonic-cross-attn-weights --cal-localness --localness-window 0.1 --cal-topk-cross-attn-weights --topk-cross-attn-weights 15 --cal-entropy"
# Parsing Options
. ./local/parse_options.sh || exit 1;
......
arch: s2t_transformer_s
arch: s2t_transformer_m
share-decoder-input-output-embed: True
optimizer: adam
clip-norm: 10.0
......
ctc-weight: 0.3
share-ctc-and-embed: True
\ No newline at end of file
share-inter-ctc: True
# inter-ctc-weight: 0.2
# inter-ctc-layers: 6,9
ctc-pae: none
\ No newline at end of file
inter-mixup: True
inter-mixup-layer: -1
inter-mixup-decoder-layer: 0
inter-mixup-prob: 1.0
inter-mixup-ratio: 1.0
inter-mixup-beta: 0.2
inter-mixup-keep-org: False
inter-mixup-decoder-emb: False
ctc-mixup-consistent-weight: 0
inter-ctc-mixup-consistent-weight: 0
mixup-consistent-weight: 0
cal-mixup-loss: True
no-specaugment: False
layer-out-norm: False
......
arch: pdss2t_transformer_s_32
encoder-embed-dim: 256
pds-stages: 5
pds-layers: 2_2_3_3_2
......
......@@ -8,7 +8,7 @@ pds-fusion: False
pds-fusion-method: all_conv2
pds-fusion-layers: 0_1_1_1
pds-fusion-weight: 0.2_0.3_0.5
pds-embed-dims: 256_256_256_256
pds-embed-dims: 256_256_256
pds-ds-method: conv
pds-embed-norm: True
pds-position-embed: 1_1_1
......
arch: pdss2t_transformer_s_16
arch: pdss2t_transformer_m_16
encoder-embed-dim: 512
pds-stages: 4
......@@ -13,7 +13,7 @@ pds-ds-method: conv
pds-embed-norm: True
pds-position-embed: 1_1_1_1
pds-kernel-sizes: 5_5_5_5
pds-ffn-ratios: 8_8_8_8
pds-ffn-ratios: 4_4_4_4
pds-attn-heads: 8_8_8_8
share-decoder-input-output-embed: True
......@@ -33,11 +33,11 @@ activation-fn: relu
encoder-ffn-embed-dim: 2048
encoder-layers: 12
decoder-layers: 6
encoder-attention-heads: 4
encoder-attention-heads: 8
decoder-embed-dim: 512
decoder-ffn-embed-dim: 2048
decoder-attention-heads: 4
decoder-attention-heads: 8
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
\ No newline at end of file
arch: pdss2t_transformer_s_16
arch: pdss2t_transformer_m_32
encoder-embed-dim: 512
pds-stages: 5
......@@ -13,7 +13,7 @@ pds-ds-method: conv
pds-embed-norm: True
pds-position-embed: 1_1_1_1_1
pds-kernel-sizes: 5_5_5_5_5
pds-ffn-ratios: 8_8_8_8_8
pds-ffn-ratios: 4_4_4_4_4
pds-attn-heads: 8_8_8_8_8
share-decoder-input-output-embed: True
......@@ -33,11 +33,8 @@ activation-fn: relu
encoder-ffn-embed-dim: 2048
encoder-layers: 12
decoder-layers: 6
encoder-attention-heads: 4
encoder-attention-heads: 8
decoder-embed-dim: 512
decoder-ffn-embed-dim: 2048
decoder-attention-heads: 4
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
\ No newline at end of file
decoder-attention-heads: 8
\ No newline at end of file
arch: pdss2t_transformer_s_8
arch: pdss2t_transformer_m_8
encoder-embed-dim: 512
pds-stages: 4
......@@ -13,7 +13,7 @@ pds-ds-method: conv
pds-embed-norm: True
pds-position-embed: 1_1_1_1
pds-kernel-sizes: 5_5_5_5
pds-ffn-ratios: 8_8_8_8
pds-ffn-ratios: 4_4_4_4
pds-attn-heads: 8_8_8_8
share-decoder-input-output-embed: True
......@@ -33,11 +33,11 @@ activation-fn: relu
encoder-ffn-embed-dim: 2048
encoder-layers: 12
decoder-layers: 6
encoder-attention-heads: 4
encoder-attention-heads: 8
decoder-embed-dim: 512
decoder-ffn-embed-dim: 2048
decoder-attention-heads: 4
decoder-attention-heads: 8
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
\ No newline at end of file
arch: pdss2t_transformer_s_16
arch: pdss2t_transformer_sd_16
encoder-embed-dim: 256
pds-stages: 4
......@@ -31,7 +31,7 @@ label_smoothing: 0.1
dropout: 0.1
activation-fn: relu
encoder-ffn-embed-dim: 2048
encoder-layers: 12
encoder-layers: 18
decoder-layers: 6
encoder-attention-heads: 4
......
arch: pdss2t_transformer_s_32
arch: pdss2t_transformer_sd_32
encoder-embed-dim: 256
pds-stages: 5
......
arch: pdss2t_transformer_s_8
arch: pdss2t_transformer_sd_8
encoder-embed-dim: 256
pds-stages: 4
......@@ -38,6 +38,3 @@ encoder-attention-heads: 4
decoder-embed-dim: 256
decoder-ffn-embed-dim: 2048
decoder-attention-heads: 4
#load-pretrained-encoder-from:
#load-pretrained-decoder-from:
\ No newline at end of file
encoder-attention-type: rel_pos
#encoder-attention-type: rel_pos_legacy
#encoder-attention-type: rel_selfattn
#encoder-attention-type: relative
......
......@@ -3,7 +3,7 @@
gpu_num=1
data_dir=
test_subset=(tst-COMMON)
test_subset=(dev tst-COMMON)
exp_name=
if [ "$#" -eq 1 ]; then
......
......@@ -85,9 +85,8 @@ ctc_infer=0
n_average=10
beam_size=5
len_penalty=1.0
infer_score=1
infer_parameters="--cal-monotonic-cross-attn-weights --cal-localness --localness-window 0.1 --cal-topk-cross-attn-weights --topk-cross-attn-weights 15 --cal-entropy"
infer_score=0
# infer_parameters="--cal-monotonic-cross-attn-weights --cal-localness --localness-window 0.1 --cal-topk-cross-attn-weights --topk-cross-attn-weights 15 --cal-entropy"
# Parsing Options
if [[ ${share_dict} -eq 1 ]]; then
......@@ -428,7 +427,6 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
--path ${model_dir}/${dec_model}
--results-path ${model_dir}
--max-tokens ${max_tokens}
--batch-size 1
--beam ${beam_size}
--skip-invalid-size-inputs-valid-test
--lenpen ${len_penalty}"
......
#!/usr/bin/env bash
# training the model
gpu_num=8
update_freq=1
max_tokens=40000
......@@ -37,7 +39,7 @@ train_config=$(echo ${config_list[*]} | sed 's/ /,/g')
cmd="./run.sh
--stage 1
--stop_stage 4
--stop_stage 2
--gpu_num ${gpu_num}
--update_freq ${update_freq}
--train_config ${train_config}
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论