diff --git a/examples/aishell/asr0/local/train.sh b/examples/aishell/asr0/local/train.sh
index 76b696d9bb1807c4a4a168b7fb6a948d451446b8..256b30d22277e707d63cfc0ea47465b8191c2c3a 100755
--- a/examples/aishell/asr0/local/train.sh
+++ b/examples/aishell/asr0/local/train.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 
-if [ $# != 2 ];then
-    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name"
+if [ $# -lt 2 ] && [ $# -gt 3 ];then
+    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name ips(optional)"
     exit -1
 fi
 
@@ -10,6 +10,13 @@ echo "using $ngpu gpus..."
 
 config_path=$1
 ckpt_name=$2
+ips=$3
+
+if [ ! $ips ];then
+  ips_config=
+else
+  ips_config="--ips="${ips}
+fi
 
 mkdir -p exp
 
@@ -26,7 +33,7 @@ python3 -u ${BIN_DIR}/train.py \
 --output exp/${ckpt_name} \
 --seed ${seed}
 else
-python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${BIN_DIR}/train.py \
+python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${ips_config} ${BIN_DIR}/train.py \
 --ngpu ${ngpu} \
 --config ${config_path} \
 --output exp/${ckpt_name} \
diff --git a/examples/aishell/asr0/run.sh b/examples/aishell/asr0/run.sh
index 3bf9aa12efae0e65e18259992389baffb347c2ab..530c013ac3a382a4643967a490c233205e60c110 100755
--- a/examples/aishell/asr0/run.sh
+++ b/examples/aishell/asr0/run.sh
@@ -6,6 +6,7 @@ gpus=0,1,2,3
 stage=0
 stop_stage=100
 conf_path=conf/deepspeech2.yaml    #conf/deepspeech2.yaml or conf/deepspeech2_online.yaml
+ips=            #xx.xx.xx.xx,xx.xx.xx.xx
 decode_conf_path=conf/tuning/decode.yaml
 avg_num=10
 audio_file=data/demo_01_03.wav
@@ -24,7 +25,7 @@ fi
 
 if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
     # train model, all `ckpt` under `exp` dir
-    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path}  ${ckpt}
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${ckpt} ${ips}
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
diff --git a/examples/aishell/asr1/local/train.sh b/examples/aishell/asr1/local/train.sh
index 5617f7efe5cca2004bd6b6aae8fc8291edf22f34..f514de303b2b270e9090d655ab9eb4156231e959 100755
--- a/examples/aishell/asr1/local/train.sh
+++ b/examples/aishell/asr1/local/train.sh
@@ -17,13 +17,21 @@ if [ ${seed} != 0  ]; then
     echo "using seed $seed & FLAGS_cudnn_deterministic=True ..."
 fi
 
-if [ $# != 2 ];then
-    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name"
+if [ $# -lt 2 ] && [ $# -gt 3 ];then
+    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name ips(optional)"
     exit -1
 fi
 
 config_path=$1
 ckpt_name=$2
+ips=$3
+
+if [ ! $ips ];then
+  ips_config=
+else
+  ips_config="--ips="${ips}
+fi
+echo ${ips_config}
 
 mkdir -p exp
 
@@ -37,7 +45,7 @@ python3 -u ${BIN_DIR}/train.py \
 --benchmark-batch-size ${benchmark_batch_size} \
 --benchmark-max-step ${benchmark_max_step}
 else
-python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${BIN_DIR}/train.py \
+python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${ips_config} ${BIN_DIR}/train.py \
 --ngpu ${ngpu} \
 --seed ${seed} \
 --config ${config_path} \
diff --git a/examples/aishell/asr1/run.sh b/examples/aishell/asr1/run.sh
index cb781b2080c3007a120e8d610a886ef10b5e194b..bd4f50e3f35853845a1aea7331f49c004fcd779f 100644
--- a/examples/aishell/asr1/run.sh
+++ b/examples/aishell/asr1/run.sh
@@ -6,6 +6,7 @@ gpus=0,1,2,3
 stage=0
 stop_stage=50
 conf_path=conf/conformer.yaml
+ips=            #xx.xx.xx.xx,xx.xx.xx.xx
 decode_conf_path=conf/tuning/decode.yaml
 avg_num=30
 audio_file=data/demo_01_03.wav
@@ -23,7 +24,7 @@ fi
 
 if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
     # train model, all `ckpt` under `exp` dir
-    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path}  ${ckpt}
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${ckpt} ${ips}
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
diff --git a/examples/callcenter/asr1/local/train.sh b/examples/callcenter/asr1/local/train.sh
index 03b4588e30cb92c014f18d1509354f3caaa2b311..41da89e227daa424fbd15f94be38b1d34fd8fb8a 100755
--- a/examples/callcenter/asr1/local/train.sh
+++ b/examples/callcenter/asr1/local/train.sh
@@ -1,7 +1,7 @@
 #! /usr/bin/env bash
 
-if [ $# != 2 ];then
-    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name"
+if [ $# -lt 2 ] && [ $# -gt 3 ];then
+    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name ips(optional)"
     exit -1
 fi
 
@@ -10,6 +10,13 @@ echo "using $ngpu gpus..."
 
 config_path=$1
 ckpt_name=$2
+ips=$3
+
+if [ ! $ips ];then
+  ips_config=
+else
+  ips_config="--ips="${ips}
+fi
 
 echo "using ${device}..."
 
@@ -28,7 +35,7 @@ python3 -u ${BIN_DIR}/train.py \
 --output exp/${ckpt_name} \
 --seed ${seed}
 else
-python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${BIN_DIR}/train.py \
+python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${ips_config} ${BIN_DIR}/train.py \
 --ngpu ${ngpu} \
 --config ${config_path} \
 --output exp/${ckpt_name} \
diff --git a/examples/callcenter/asr1/run.sh b/examples/callcenter/asr1/run.sh
index 0c7ffc1e7990319754abaeaa3a6726d3b098fb2b..7e3b912ab4ca558c3106a6cfd4e62cae99c8962e 100644
--- a/examples/callcenter/asr1/run.sh
+++ b/examples/callcenter/asr1/run.sh
@@ -6,6 +6,7 @@ gpus=0,1,2,3
 stage=0
 stop_stage=50
 conf_path=conf/conformer.yaml
+ips=            #xx.xx.xx.xx,xx.xx.xx.xx
 decode_conf_path=conf/tuning/decode.yaml
 avg_num=20
 
@@ -22,7 +23,7 @@ fi
 
 if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
     # train model, all `ckpt` under `exp` dir
-    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path}  ${ckpt}
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${ckpt} ${ips}
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
diff --git a/examples/librispeech/asr0/local/train.sh b/examples/librispeech/asr0/local/train.sh
index ad00653b70b366addcab126f1e63fc64aec1b37c..71659e28dd97fb4a55a1b86785dc9d0b71e32143 100755
--- a/examples/librispeech/asr0/local/train.sh
+++ b/examples/librispeech/asr0/local/train.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 
-if [ $# != 2 ];then
-    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name"
+if [ $# -lt 2 ] && [ $# -gt 3 ];then
+    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name ips(optional)"
     exit -1
 fi
 
@@ -10,6 +10,13 @@ echo "using $ngpu gpus..."
 
 config_path=$1
 ckpt_name=$2
+ips=$3
+
+if [ ! $ips ];then
+  ips_config=
+else
+  ips_config="--ips="${ips}
+fi
 
 mkdir -p exp
 
@@ -26,7 +33,7 @@ python3 -u ${BIN_DIR}/train.py \
 --output exp/${ckpt_name} \
 --seed ${seed}
 else
-python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${BIN_DIR}/train.py \
+python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${ips_config} ${BIN_DIR}/train.py \
 --ngpu ${ngpu} \
 --config ${config_path} \
 --output exp/${ckpt_name} \
diff --git a/examples/librispeech/asr0/run.sh b/examples/librispeech/asr0/run.sh
index 6b1ff6c6d9ef96509e5d25ecd7ad83ff7808d221..38112398a03783a3f9dd6271788a18a5b6835966 100755
--- a/examples/librispeech/asr0/run.sh
+++ b/examples/librispeech/asr0/run.sh
@@ -6,6 +6,7 @@ gpus=0,1,2,3
 stage=0
 stop_stage=100
 conf_path=conf/deepspeech2.yaml
+ips=            #xx.xx.xx.xx,xx.xx.xx.xx
 decode_conf_path=conf/tuning/decode.yaml
 avg_num=5
 audio_file=data/demo_002_en.wav
@@ -23,7 +24,7 @@ fi
 
 if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
     # train model, all `ckpt` under `exp` dir
-    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path}  ${ckpt}
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${ckpt} ${ips}
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
diff --git a/examples/librispeech/asr1/local/train.sh b/examples/librispeech/asr1/local/train.sh
index 3860d85cf8c7a65810c2565a358aec2f537bde6b..f729ed22c997df13335f8d22048d721e57e777b1 100755
--- a/examples/librispeech/asr1/local/train.sh
+++ b/examples/librispeech/asr1/local/train.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 
-if [ $# != 2 ];then
-    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name"
+if [ $# -lt 2 ] && [ $# -gt 3 ];then
+    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name ips(optional)"
     exit -1
 fi
 
@@ -10,6 +10,13 @@ echo "using $ngpu gpus..."
 
 config_path=$1
 ckpt_name=$2
+ips=$3
+
+if [ ! $ips ];then
+  ips_config=
+else
+  ips_config="--ips="${ips}
+fi
 
 mkdir -p exp
 
@@ -29,7 +36,7 @@ python3 -u ${BIN_DIR}/train.py \
 --output exp/${ckpt_name} \
 --seed ${seed}
 else
-python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${BIN_DIR}/train.py \
+python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${ips_config} ${BIN_DIR}/train.py \
 --ngpu ${ngpu} \
 --config ${config_path} \
 --output exp/${ckpt_name} \
diff --git a/examples/librispeech/asr1/run.sh b/examples/librispeech/asr1/run.sh
index 116dae1265fe8833b4ef193a360ce0603dfe8293..a14240ee014ffe2d13b9ccadb2e12d064f45329e 100755
--- a/examples/librispeech/asr1/run.sh
+++ b/examples/librispeech/asr1/run.sh
@@ -8,6 +8,7 @@ gpus=0,1,2,3
 stage=0
 stop_stage=50
 conf_path=conf/transformer.yaml
+ips=            #xx.xx.xx.xx,xx.xx.xx.xx
 decode_conf_path=conf/tuning/decode.yaml
 avg_num=30
 audio_file=data/demo_002_en.wav
@@ -25,7 +26,7 @@ fi
 
 if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
     # train model, all `ckpt` under `exp` dir
-    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path}  ${ckpt}
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${ckpt} ${ips}
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
diff --git a/examples/librispeech/asr2/local/train.sh b/examples/librispeech/asr2/local/train.sh
index 560424ea4fe5b79260d12b3678cae01a16df6226..1f414ad41caa9e067ad74796688df8e6d59a99e1 100755
--- a/examples/librispeech/asr2/local/train.sh
+++ b/examples/librispeech/asr2/local/train.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 
-if [ $# != 2 ];then
-    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name"
+if [ $# -lt 2 ] && [ $# -gt 3 ];then
+    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name ips(optional)"
     exit -1
 fi
 
@@ -10,6 +10,13 @@ echo "using $ngpu gpus..."
 
 config_path=$1
 ckpt_name=$2
+ips=$3
+
+if [ ! $ips ];then
+  ips_config=
+else
+  ips_config="--ips="${ips}
+fi
 
 mkdir -p exp
 
@@ -27,7 +34,7 @@ python3 -u ${BIN_DIR}/train.py \
 --output exp/${ckpt_name} \
 --seed ${seed}
 else
-python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${BIN_DIR}/train.py \
+python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${ips_config} ${BIN_DIR}/train.py \
 --ngpu ${ngpu} \
 --model-name u2_kaldi \
 --config ${config_path} \
diff --git a/examples/librispeech/asr2/run.sh b/examples/librispeech/asr2/run.sh
index c9a794e341881442403b2730316e18ca636978ad..d156159f28120896e6ce745e8db11ec2f1e3cc81 100755
--- a/examples/librispeech/asr2/run.sh
+++ b/examples/librispeech/asr2/run.sh
@@ -9,6 +9,7 @@ gpus=0,1,2,3,4,5,6,7
 stage=0
 stop_stage=50
 conf_path=conf/transformer.yaml
+ips=            #xx.xx.xx.xx,xx.xx.xx.xx
 decode_conf_path=conf/decode/decode_base.yaml
 dict_path=data/lang_char/train_960_unigram5000_units.txt
 avg_num=10
@@ -26,7 +27,7 @@ fi
 
 if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
     # train model, all `ckpt` under `exp` dir
-    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path}  ${ckpt}
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${ckpt} ${ips}
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
diff --git a/examples/mustc/st1/local/train.sh b/examples/mustc/st1/local/train.sh
index 456c94169c69d3bb4afd4bfd3c372c85e817d4e1..db2a575a6e80e874bb3d13ea07437ee9d73d5bb3 100755
--- a/examples/mustc/st1/local/train.sh
+++ b/examples/mustc/st1/local/train.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 
-if [ $# != 3 ];then
-    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name ckpt_path"
+if [ $# -lt 3 ] && [ $# -gt 4 ];then
+    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name ckpt_path ips(optional)"
     exit -1
 fi
 
@@ -11,6 +11,13 @@ echo "using $ngpu gpus..."
 config_path=$1
 ckpt_name=$2
 ckpt_path=$3
+ips=$3
+
+if [ ! $ips ];then
+  ips_config=
+else
+  ips_config="--ips="${ips}
+fi
 
 
 mkdir -p exp
@@ -21,12 +28,21 @@ if [ ${seed} != 0 ]; then
     export FLAGS_cudnn_deterministic=True
 fi
 
+if [ ${ngpu} == 0 ]; then
 python3 -u ${BIN_DIR}/train.py \
 --ngpu ${ngpu} \
 --config ${config_path} \
 --output exp/${ckpt_name} \
 --checkpoint_path "${ckpt_path}" \
 --seed ${seed}
+else
+python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${ips_config} ${BIN_DIR}/train.py \
+--ngpu ${ngpu} \
+--config ${config_path} \
+--output exp/${ckpt_name} \
+--checkpoint_path "${ckpt_path}" \
+--seed ${seed}
+fi
 
 if [ ${seed} != 0 ]; then
     unset FLAGS_cudnn_deterministic
diff --git a/examples/mustc/st1/run.sh b/examples/mustc/st1/run.sh
index 6ceae3b84382285eb374ec272277f9fdb2c7cdca..99ee2295caafb55ee73d8c88209613181cce36a4 100755
--- a/examples/mustc/st1/run.sh
+++ b/examples/mustc/st1/run.sh
@@ -7,6 +7,7 @@ gpus=0,1,2,3
 stage=0
 stop_stage=3
 conf_path=conf/transformer_es.yaml
+ips=            #xx.xx.xx.xx,xx.xx.xx.xx
 decode_conf_path=conf/tuning/decode.yaml
 must_c_path=
 lang=es
@@ -25,7 +26,7 @@ fi
 
 if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
     # train model, all `ckpt` under `exp` dir
-    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path}  ${ckpt} "${ckpt_path}" 
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path}  ${ckpt} "${ckpt_path}" ${ips} 
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
@@ -36,4 +37,4 @@ fi
 if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
     # test ckpt avg_n
     CUDA_VISIBLE_DEVICES=0 ./local/test.sh ${conf_path} ${decode_conf_path} exp/${ckpt}/checkpoints/${avg_ckpt} ${lang} || exit -1
-fi
\ No newline at end of file
+fi
diff --git a/examples/ted_en_zh/st0/local/train.sh b/examples/ted_en_zh/st0/local/train.sh
index ad00653b70b366addcab126f1e63fc64aec1b37c..71659e28dd97fb4a55a1b86785dc9d0b71e32143 100755
--- a/examples/ted_en_zh/st0/local/train.sh
+++ b/examples/ted_en_zh/st0/local/train.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 
-if [ $# != 2 ];then
-    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name"
+if [ $# -lt 2 ] && [ $# -gt 3 ];then
+    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name ips(optional)"
     exit -1
 fi
 
@@ -10,6 +10,13 @@ echo "using $ngpu gpus..."
 
 config_path=$1
 ckpt_name=$2
+ips=$3
+
+if [ ! $ips ];then
+  ips_config=
+else
+  ips_config="--ips="${ips}
+fi
 
 mkdir -p exp
 
@@ -26,7 +33,7 @@ python3 -u ${BIN_DIR}/train.py \
 --output exp/${ckpt_name} \
 --seed ${seed}
 else
-python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${BIN_DIR}/train.py \
+python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${ips_config} ${BIN_DIR}/train.py \
 --ngpu ${ngpu} \
 --config ${config_path} \
 --output exp/${ckpt_name} \
diff --git a/examples/ted_en_zh/st0/run.sh b/examples/ted_en_zh/st0/run.sh
index 1746c025191127e139c297f46b5a04982c456f00..c5a59f6578f06b11106671226d2e5948aeb88264 100755
--- a/examples/ted_en_zh/st0/run.sh
+++ b/examples/ted_en_zh/st0/run.sh
@@ -6,6 +6,7 @@ gpus=0,1,2,3
 stage=0
 stop_stage=50
 conf_path=conf/transformer_mtl_noam.yaml
+ips=            #xx.xx.xx.xx,xx.xx.xx.xx
 decode_conf_path=conf/tuning/decode.yaml
 avg_num=5
 data_path=./TED_EnZh # path to unzipped data
@@ -23,7 +24,7 @@ fi
 
 if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
     # train model, all `ckpt` under `exp` dir
-    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${ckpt}
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${ckpt} ${ips}
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
diff --git a/examples/ted_en_zh/st1/local/train.sh b/examples/ted_en_zh/st1/local/train.sh
index 5da64e99c95af8e23c9f027080cddcd72c0a4d17..3e9295e53b73f114fee2ad710cd66e5ca8aa67b6 100755
--- a/examples/ted_en_zh/st1/local/train.sh
+++ b/examples/ted_en_zh/st1/local/train.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 
-if [ $# != 3 ];then
-    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name ckpt_path"
+if [ $# -lt 3 ] && [ $# -gt 4 ];then
+    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name ips(optional)"
     exit -1
 fi
 
@@ -11,6 +11,15 @@ echo "using $ngpu gpus..."
 config_path=$1
 ckpt_name=$2
 ckpt_path=$3
+ips=$3
+
+if [ ! $ips ];then
+  ips_config=
+else
+  ips_config="--ips="${ips}
+fi
+
+mkdir -p exp
 
 mkdir -p exp
 
@@ -28,7 +37,7 @@ python3 -u ${BIN_DIR}/train.py \
 --checkpoint_path "${ckpt_path}" \
 --seed ${seed}
 else
-python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${BIN_DIR}/train.py \
+python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${ips_config} ${BIN_DIR}/train.py \
 --ngpu ${ngpu} \
 --config ${config_path} \
 --output exp/${ckpt_name} \
diff --git a/examples/ted_en_zh/st1/run.sh b/examples/ted_en_zh/st1/run.sh
index 1808e37b431402452a67d716b33038ec9ea25007..06a407d4493c8a528bd4145a91f70eeec2352645 100755
--- a/examples/ted_en_zh/st1/run.sh
+++ b/examples/ted_en_zh/st1/run.sh
@@ -7,6 +7,7 @@ gpus=0,1,2,3
 stage=1
 stop_stage=4
 conf_path=conf/transformer_mtl_noam.yaml
+ips=            #xx.xx.xx.xx,xx.xx.xx.xx
 decode_conf_path=conf/tuning/decode.yaml
 ckpt_path= # paddle.98 # (finetune from FAT-ST pretrained model)
 avg_num=5
@@ -29,7 +30,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
         echo "Finetune from Pretrained Model" ${ckpt_path}
         ./local/download_pretrain.sh || exit -1
     fi
-    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${ckpt} "${ckpt_path}"
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${ckpt} "${ckpt_path}" ${ips}
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
diff --git a/examples/tiny/asr0/local/train.sh b/examples/tiny/asr0/local/train.sh
index 2f2cff77a8ba8ee740e32046e9115c91689b0493..8b67902fee9074901392f71a056f209b13d806ec 100755
--- a/examples/tiny/asr0/local/train.sh
+++ b/examples/tiny/asr0/local/train.sh
@@ -15,13 +15,20 @@ if [ ${seed} != 0  ]; then
     echo "using seed $seed & FLAGS_cudnn_deterministic=True ..."
 fi
 
-if [ $# != 2 ];then
-    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name"
+if [ $# -lt 2 ] && [ $# -gt 3 ];then
+    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name ips(optional)"
     exit -1
 fi
 
 config_path=$1
 ckpt_name=$2
+ips=$3
+
+if [ ! $ips ];then
+  ips_config=
+else
+  ips_config="--ips="${ips}
+fi
 
 mkdir -p exp
 
@@ -33,7 +40,7 @@ python3 -u ${BIN_DIR}/train.py \
 --profiler-options "${profiler_options}" \
 --seed ${seed}
 else
-python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${BIN_DIR}/train.py \
+python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${ips_config} ${BIN_DIR}/train.py \
 --ngpu ${ngpu} \
 --config ${config_path} \
 --output exp/${ckpt_name} \
diff --git a/examples/tiny/asr0/run.sh b/examples/tiny/asr0/run.sh
index 16f4313038ef875d66a47f9175687f0aa92f752d..3e84d4224c144d7af70014642f71ebc08089f1f9 100755
--- a/examples/tiny/asr0/run.sh
+++ b/examples/tiny/asr0/run.sh
@@ -2,10 +2,11 @@
 set -e
 source path.sh
 
-gpus=0
+gpus=4
 stage=0
 stop_stage=100
 conf_path=conf/deepspeech2.yaml
+ips=            #xx.xx.xx.xx,xx.xx.xx.xx
 decode_conf_path=conf/tuning/decode.yaml
 avg_num=1
 source ${MAIN_ROOT}/utils/parse_options.sh || exit 1;
@@ -21,7 +22,7 @@ fi
 
 if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
     # train model, all `ckpt` under `exp` dir
-    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${ckpt}
+    CUDA_VISIBLE_DEVICES=${gpus} ./local/train.sh ${conf_path} ${ckpt} ${ips}
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
diff --git a/examples/tiny/asr1/local/train.sh b/examples/tiny/asr1/local/train.sh
index 5617f7efe5cca2004bd6b6aae8fc8291edf22f34..459f2e21843273be284d74f6617aafb4c2e6d95d 100755
--- a/examples/tiny/asr1/local/train.sh
+++ b/examples/tiny/asr1/local/train.sh
@@ -17,13 +17,20 @@ if [ ${seed} != 0  ]; then
     echo "using seed $seed & FLAGS_cudnn_deterministic=True ..."
 fi
 
-if [ $# != 2 ];then
-    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name"
+if [ $# -lt 2 ] && [ $# -gt 3 ];then
+    echo "usage: CUDA_VISIBLE_DEVICES=0 ${0} config_path ckpt_name ips(optional)"
     exit -1
 fi
 
 config_path=$1
 ckpt_name=$2
+ips=$3
+
+if [ ! $ips ];then
+  ips_config=
+else
+  ips_config="--ips="${ips}
+fi
 
 mkdir -p exp
 
@@ -37,7 +44,7 @@ python3 -u ${BIN_DIR}/train.py \
 --benchmark-batch-size ${benchmark_batch_size} \
 --benchmark-max-step ${benchmark_max_step}
 else
-python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${BIN_DIR}/train.py \
+python3 -m paddle.distributed.launch --gpus=${CUDA_VISIBLE_DEVICES} ${ips_config} ${BIN_DIR}/train.py \
 --ngpu ${ngpu} \
 --seed ${seed} \
 --config ${config_path} \
diff --git a/examples/tiny/asr1/run.sh b/examples/tiny/asr1/run.sh
index 1651c034c3e76692f10d366a3c21ca85109fd600..ca0a7a01329ecbe8957c50b79d7578d7a66714d4 100755
--- a/examples/tiny/asr1/run.sh
+++ b/examples/tiny/asr1/run.sh
@@ -2,10 +2,11 @@
 set -e
 source path.sh
 
-gpus=0
+gpus=4
 stage=0
 stop_stage=50
 conf_path=conf/transformer.yaml
+ips=            #xx.xx.xx.xx,xx.xx.xx.xx
 decode_conf_path=conf/tuning/decode.yaml
 avg_num=1
 
@@ -22,7 +23,7 @@ fi
 
 if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
     # train model, all `ckpt` under `exp` dir
-    CUDA_VISIBLE_DEVICES=${gpus}  ./local/train.sh ${conf_path}  ${ckpt}
+    CUDA_VISIBLE_DEVICES=${gpus}  ./local/train.sh ${conf_path} ${ckpt} ${ips}
 fi
 
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then