diff --git a/examples/ted_en_zh/st1/local/data.sh b/examples/ted_en_zh/st1/local/data.sh
index 72d141e7d..8b829a8a1 100755
--- a/examples/ted_en_zh/st1/local/data.sh
+++ b/examples/ted_en_zh/st1/local/data.sh
@@ -2,7 +2,7 @@
 
 set -e
 
-stage=1
+stage=3
 stop_stage=100
 dict_dir=data/lang_char
 
@@ -14,6 +14,7 @@ data_dir=./TED_EnZh
 target_dir=data/ted_en_zh
 dumpdir=data/dump
 do_delta=false
+nj=20
 
 source ${MAIN_ROOT}/utils/parse_options.sh
 
@@ -40,11 +41,11 @@ if [ ${stage} -le -1 ] && [ ${stop_stage} -ge -1 ]; then
         exit 1
     fi
 
-    # # extract data 
-    # echo "data Extraction"
-    # python3 local/ted_en_zh.py \
-    # --tgt-dir=${target_dir} \
-    # --src-dir=${data_dir}
+    # extract data 
+    echo "data Extraction"
+    python3 local/ted_en_zh.py \
+    --tgt-dir=${target_dir} \
+    --src-dir=${data_dir}
 
 fi
 prep_dir=${target_dir}/data_prep 
@@ -99,7 +100,7 @@ if [ ${stage} -le 0 ] && [ ${stop_stage} -ge 0 ]; then
     done
 fi
 
-feat_tr_dir=${dumpdir}/train/delta${do_delta}; mkdir -p ${feat_tr_dir}
+feat_tr_dir=${dumpdir}/train_sp/delta${do_delta}; mkdir -p ${feat_tr_dir}
 feat_dt_dir=${dumpdir}/dev/delta${do_delta}; mkdir -p ${feat_dt_dir}
 feat_trans_dir=${dumpdir}/test/delta${do_delta}; mkdir -p ${feat_trans_dir}
 if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
@@ -109,7 +110,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
     fbankdir=data/fbank
     # Generate the fbank features; by default 80-dimensional fbanks with pitch on each frame
     for x in train dev test; do
-        steps/make_fbank_pitch.sh --cmd "$train_cmd" --nj 32 --write_utt2num_frames true \
+        steps/make_fbank_pitch.sh --cmd "$train_cmd" --nj ${nj} --write_utt2num_frames true \
             ${prep_dir}/${x}.en-zh data/make_fbank/${x} ${fbankdir}
     done
     
@@ -123,7 +124,7 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
     rm -r ${prep_dir}/temp*.en-zh 
     utils/fix_data_dir.sh ${prep_dir}/train_sp.en-zh
 
-    steps/make_fbank_pitch.sh --cmd "$train_cmd" --nj 32 --write_utt2num_frames true \
+    steps/make_fbank_pitch.sh --cmd "$train_cmd" --nj ${nj} --write_utt2num_frames true \
         ${prep_dir}/train_sp.en-zh exp/make_fbank/train_sp.en-zh ${fbankdir}
 
     for lang in en zh; do
@@ -155,14 +156,14 @@ if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then
         rm -rf ${prep_dir}/${x}.en-zh.*.tmp
     done
 
-    compute-cmvn-stats scp:${prep_dir}/train_sp.en-zh/feats.scp ${prep_dir}/train_sp.en-zh/cmvn.ark
+    compute-cmvn-stats scp:${prep_dir}/train_sp.en-zh.zh/feats.scp ${prep_dir}/train_sp.en-zh.zh/cmvn.ark
 
-    dump.sh --cmd "$train_cmd" --nj 80 --do_delta $do_delta \
-        ${prep_dir}/train_sp.en-zh/feats.scp ${prep_dir}/train_sp.en-zh/cmvn.ark ${prep_dir}/dump_feats/train_sp.en-zh ${feat_tr_dir}
-    dump.sh --cmd "$train_cmd" --nj 32 --do_delta $do_delta \
-        ${prep_dir}/dev.en-zh/feats.scp ${prep_dir}/train_sp.en-zh/cmvn.ark ${prep_dir}/dump_feats/dev.en-zh ${feat_dt_dir}
-    dump.sh --cmd "$train_cmd" --nj 32 --do_delta $do_delta \
-        ${prep_dir}/test.en-zh/feats.scp ${prep_dir}/train_sp.en-zh/cmvn.ark ${prep_dir}/dump_feats/test.en-zh ${feat_trans_dir}
+    dump.sh --cmd "$train_cmd" --nj ${nj} --do_delta $do_delta \
+        ${prep_dir}/train_sp.en-zh.zh/feats.scp ${prep_dir}/train_sp.en-zh.zh/cmvn.ark ${prep_dir}/dump_feats/train_sp.en-zh.zh ${feat_tr_dir}
+    dump.sh --cmd "$train_cmd" --nj ${nj} --do_delta $do_delta \
+        ${prep_dir}/dev.en-zh.zh/feats.scp ${prep_dir}/train_sp.en-zh.zh/cmvn.ark ${prep_dir}/dump_feats/dev.en-zh.zh ${feat_dt_dir}
+    dump.sh --cmd "$train_cmd" --nj ${nj} --do_delta $do_delta \
+        ${prep_dir}/test.en-zh.zh/feats.scp ${prep_dir}/train_sp.en-zh.zh/cmvn.ark ${prep_dir}/dump_feats/test.en-zh.zh ${feat_trans_dir}
 fi
 
 dict=${dict_dir}/ted_en_zh_${bpemode}${nbpe}_joint.txt
@@ -170,9 +171,6 @@ nlsyms=${dict_dir}/ted_en_zh_non_lang_syms.txt
 bpemodel=${dict_dir}/ted_en_zh_${bpemode}${nbpe}
 if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
     echo "stage 2: Dictionary and Json Data Preparation"
-    # echo "make a non-linguistic symbol list for all languages"
-    # grep sp1.0 ${prep_dir}/train_sp.en-zh.*/text | cut -f 2- -d' ' | grep -o -P '&[^;];'| sort | uniq > ${nlsyms}
-    # cat ${nlsyms}
 
     echo "make a joint source and target dictionary"
     echo "<unk> 1" > ${dict} # <unk> must be 1, 0 will be used for "blank" in CTC
@@ -183,20 +181,27 @@ if [ ${stage} -le 2 ] && [ ${stop_stage} -ge 2 ]; then
     wc -l ${dict}
 
     echo "make json files"
-    data2json.sh --nj 16 --feat ${feat_tr_dir}/feats.scp --text ${prep_dir}/train_sp.en-zh.zh/text --bpecode ${bpemodel}.model --lang zh \
+    data2json.sh --nj ${nj} --feat ${feat_tr_dir}/feats.scp --text ${prep_dir}/train_sp.en-zh.zh/text --bpecode ${bpemodel}.model --lang zh \
         ${prep_dir}/train_sp.en-zh.zh ${dict} > ${feat_tr_dir}/data_${bpemode}${nbpe}.json
     data2json.sh --feat ${feat_dt_dir}/feats.scp --text ${prep_dir}/dev.en-zh.zh/text --bpecode ${bpemodel}.model --lang zh \
         ${prep_dir}/dev.en-zh.zh ${dict} > ${feat_dt_dir}/data_${bpemode}${nbpe}.json
-    data2json.sh --feat ${feat_dt_dir}/feats.scp --text ${prep_dir}/test.en-zh.zh/text --bpecode ${bpemodel}.model --lang zh \
+    data2json.sh --feat ${feat_trans_dir}/feats.scp --text ${prep_dir}/test.en-zh.zh/text --bpecode ${bpemodel}.model --lang zh \
         ${prep_dir}/test.en-zh.zh ${dict} > ${feat_trans_dir}/data_${bpemode}${nbpe}.json
     echo "update json (add source references)"
     # update json (add source references)
-    for x in ${train_set} ${train_dev}; do
+    for x in train_sp dev; do
         feat_dir=${dumpdir}/${x}/delta${do_delta}
-        data_dir=data/$(echo ${x} | cut -f 1 -d ".").en-zh.en
-        update_json.sh --text ${data_dir}/text.${src_case} --bpecode ${bpemodel}.model \
+        data_dir=${prep_dir}/$(echo ${x} | cut -f 1 -d ".").en-zh.en
+        update_json.sh --text ${data_dir}/text --bpecode ${bpemodel}.model \
             ${feat_dir}/data_${bpemode}${nbpe}.json ${data_dir} ${dict}
     done
 fi
+
+if [ ${stage} -le 3 ] && [ ${stop_stage} -ge 3 ]; then
+    echo "stage 3: Format the Json Data"
+    python3 local/espnet_json_to_manifest.py --json-file ${feat_tr_dir}/data_${bpemode}${nbpe}.json --manifest-file data/manifest.train
+    python3 local/espnet_json_to_manifest.py --json-file ${feat_dt_dir}/data_${bpemode}${nbpe}.json --manifest-file data/manifest.dev
+    python3 local/espnet_json_to_manifest.py --json-file ${feat_trans_dir}/data_${bpemode}${nbpe}.json --manifest-file data/manifest.test
+fi
 echo "Ted En-Zh Data preparation done."
 exit 0
diff --git a/examples/ted_en_zh/st1/local/data_prep.sh b/examples/ted_en_zh/st1/local/data_prep.sh
new file mode 100755
index 000000000..339cee1eb
--- /dev/null
+++ b/examples/ted_en_zh/st1/local/data_prep.sh
@@ -0,0 +1,54 @@
+#!/bin/bash
+
+# Copyright 2019 Kyoto University (Hirofumi Inaguma)
+#  Apache 2.0  (http://www.apache.org/licenses/LICENSE-2.0)
+
+export LC_ALL=C
+
+data_dir=${1}
+
+for set in train dev test; do
+# for set in train; do
+    dst=${target_dir}/${set}
+    for lang in en zh; do
+
+        if [ ${lang} = 'en' ]; then
+            echo "remove punctuation $lang"
+            # remove punctuation
+            local/remove_punctuation.pl < ${dst}/${lang}.org > ${dst}/${lang}.raw
+        else
+            cp ${dst}/${lang}.org ${dst}/${lang}.raw
+        fi
+
+        paste -d " " ${dst}/.yaml ${dst}/${lang}.raw | sort > ${dst}/text.${lang}
+
+
+    done
+    # error check
+    n=$(cat ${dst}/.yaml | wc -l)
+    n_en=$(cat ${dst}/en.raw | wc -l)
+    n_tgt=$(cat ${dst}/zh.raw | wc -l)
+    [ ${n} -ne ${n_en} ] && echo "Warning: expected ${n} data data files, found ${n_en}" && exit 1;
+    [ ${n} -ne ${n_tgt} ] && echo "Warning: expected ${n} data data files, found ${n_tgt}" && exit 1;
+
+    echo "done text processing"
+    cat ${dst}/wav.scp.org | uniq | sort -k1,1 -u > ${dst}/wav.scp
+    cat ${dst}/utt2spk.org | uniq | sort -k1,1 -u > ${dst}/utt2spk
+
+    cat ${dst}/utt2spk | utt2spk_to_spk2utt.pl | sort -k1,1 -u > ${dst}/spk2utt
+    rm -rf ${target_dir}/data_prep/${set}.en-zh
+    mkdir -p ${target_dir}/data_prep/${set}.en-zh
+    echo "remove duplicate lines..."
+    cut -d ' ' -f 1 ${dst}/text.en | sort | uniq -c | sort -n -k1 -r | grep -v '1 ted-en-zh' \
+        | sed 's/^[ \t]*//' > ${dst}/duplicate_lines
+    cut -d ' ' -f 1 ${dst}/text.en | sort | uniq -c | sort -n -k1 -r | grep '1 ted-en-zh' \
+        | cut -d '1' -f 2- | sed 's/^[ \t]*//' > ${dst}/reclist
+    reduce_data_dir.sh ${dst} ${dst}/reclist ${target_dir}/data_prep/${set}.en-zh
+    echo "done wav processing"
+    for l in en zh; do
+        cp ${dst}/text.${l} ${target_dir}/data_prep/${set}.en-zh/text.${l}
+    done
+    fix_data_dir.sh --utt_extra_files \
+    "text.en text.zh" \
+    ${target_dir}/data_prep/${set}.en-zh
+done      
\ No newline at end of file
diff --git a/examples/ted_en_zh/st1/local/divide_lang.sh b/examples/ted_en_zh/st1/local/divide_lang.sh
new file mode 100755
index 000000000..4e5f85c86
--- /dev/null
+++ b/examples/ted_en_zh/st1/local/divide_lang.sh
@@ -0,0 +1,48 @@
+#!/bin/bash
+
+# Copyright 2019 Kyoto University (Hirofumi Inaguma)
+#           2021 PaddlePaddle
+#  Apache 2.0  (http://www.apache.org/licenses/LICENSE-2.0)
+
+. ./path.sh
+
+if [ "$#" -ne 2 ]; then
+    echo "Usage: $0 <set> <lang>>"
+    echo "e.g.: $0 dev"
+    exit 1
+fi
+
+set=$1
+lang=$2
+export LC_ALL=en_US.UTF-8
+# Copy stuff intoc its final locations [this has been moved from the format_data script]
+# for En
+mkdir -p ${set}.en
+for f in spk2utt utt2spk segments wav.scp feats.scp utt2num_frames; do
+    if [ -f ${set}/${f} ]; then
+        sort ${set}/${f} > ${set}.en/${f}
+    fi
+done
+sort ${set}/text.en | sed $'s/[^[:print:]]//g' > ${set}.en/text 
+
+utils/fix_data_dir.sh ${set}.en
+if [ -f ${set}.en/feats.scp ]; then
+    utils/validate_data_dir.sh ${set}.en || exit 1;
+else
+    utils/validate_data_dir.sh --no-feats --no-wav ${set}.en || exit 1;
+fi
+
+# for target language
+mkdir -p ${set}.${lang}
+for f in spk2utt utt2spk segments wav.scp feats.scp utt2num_frames; do
+    if [ -f ${set}/${f} ]; then
+        sort ${set}/${f} > ${set}.${lang}/${f}
+    fi
+done
+sort ${set}/text.${lang} | sed $'s/[^[:print:]]//g' > ${set}.${lang}/text 
+utils/fix_data_dir.sh  ${set}.${lang}
+if [ -f ${set}.${lang}/feats.scp ]; then
+    utils/validate_data_dir.sh ${set}.${lang} || exit 1;
+else
+    utils/validate_data_dir.sh --no-feats --no-wav ${set}.${lang} || exit 1;
+fi
diff --git a/examples/ted_en_zh/st1/local/espnet_json_to_manifest.py b/examples/ted_en_zh/st1/local/espnet_json_to_manifest.py
new file mode 100644
index 000000000..60d254367
--- /dev/null
+++ b/examples/ted_en_zh/st1/local/espnet_json_to_manifest.py
@@ -0,0 +1,27 @@
+#!/usr/bin/env python
+import argparse
+import json
+
+
+def main(args):
+    with open(args.json_file, 'r') as fin:
+        data_json = json.load(fin)
+
+    with open(args.manifest_file, 'w') as fout:
+        for key, value in data_json['utts'].items():
+            value['utt'] = key
+            fout.write(json.dumps(value, ensure_ascii=False))
+            fout.write("\n")
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(description=__doc__)
+    parser.add_argument(
+        '--json-file', type=str, default=None, help="espnet data json file.")
+    parser.add_argument(
+        '--manifest-file',
+        type=str,
+        default='manifest.train',
+        help='manifest data json line file.')
+    args = parser.parse_args()
+    main(args)
diff --git a/examples/ted_en_zh/st1/local/remove_punctuation.pl b/examples/ted_en_zh/st1/local/remove_punctuation.pl
new file mode 100755
index 000000000..89e19c6f4
--- /dev/null
+++ b/examples/ted_en_zh/st1/local/remove_punctuation.pl
@@ -0,0 +1,25 @@
+#!/usr/bin/perl
+
+use warnings;
+use strict;
+
+binmode(STDIN,":utf8");
+binmode(STDOUT,":utf8");
+
+while(<STDIN>) {
+  $_ = " $_ ";
+
+  # remove punctuation except apostrophe
+  s/<space>/spacemark/g;  # for scoring
+  s/'/apostrophe/g;
+  s/[[:punct:]]//g;
+  s/apostrophe/'/g;
+  s/spacemark/<space>/g;  # for scoring
+
+  # remove whitespace
+  s/\s+/ /g;
+  s/^\s+//;
+  s/\s+$//;
+
+  print "$_\n";
+}