diff --git a/README.md b/README.md
index a4511b972..e7ff1b10e 100644
--- a/README.md
+++ b/README.md
@@ -97,7 +97,7 @@ FunASR has open-sourced a large number of pre-trained models on industrial data.
 <a name="quick-start"></a>
 ## Quick Start
 
-Below is a quick start tutorial. Test audio files ([Mandarin](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav), [English]()).
+Below is a quick start tutorial. Test audio files ([Mandarin](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav), [English](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_en.wav)).
 
 ### Command-line usage
 
diff --git a/README_zh.md b/README_zh.md
index 3e58aa77a..46af926ee 100644
--- a/README_zh.md
+++ b/README_zh.md
@@ -91,7 +91,7 @@ FunASR开源了大量在工业数据上预训练模型，您可以在[模型许
 <a name="快速开始"></a>
 ## 快速开始
 
-下面为快速上手教程，测试音频（[中文](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav)，[英文]()）
+下面为快速上手教程，测试音频（[中文](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/vad_example.wav)，[英文](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_en.wav)）
 
 ### 可执行命令行
 
diff --git a/data/list/train.jsonl b/data/list/train.jsonl
new file mode 100644
index 000000000..618af3880
--- /dev/null
+++ b/data/list/train.jsonl
@@ -0,0 +1,4 @@
+{"key": "BAC009S0764W0121", "source": "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/BAC009S0764W0121.wav", "source_len": 90, "target": "甚至出现交易几乎停滞的情况", "target_len": 13}
+{"key": "BAC009S0916W0489", "source": "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/BAC009S0916W0489.wav", "source_len": 90, "target": "湖北一公司以员工名义贷款数十员工负债千万", "target_len": 20}
+{"key": "asr_example_cn_en", "source": "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cn_en.wav", "source_len": 91, "target": "所有只要处理 data 不管你是做 machine learning 做 deep learning 做 data analytics 做 data science 也好 scientist 也好通通都要都做的基本功啊那 again 先先对有一些也许对", "target_len": 19}
+{"key": "ID0012W0014", "source": "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_en.wav", "source_len": 88, "target": "he tried to think how it could be", "target_len": 8}
diff --git a/data/list/train_text.txt b/data/list/train_text.txt
index f4d4fe457..2fc2aa54f 100644
--- a/data/list/train_text.txt
+++ b/data/list/train_text.txt
@@ -1,2 +1,4 @@
-ID0012W0013 当客户风险承受能力评估依据发生变化时
-ID0012W0014 杨涛不得不将工厂关掉
\ No newline at end of file
+BAC009S0764W0121 甚至出现交易几乎停滞的情况
+BAC009S0916W0489 湖北一公司以员工名义贷款数十员工负债千万
+asr_example_cn_en 所有只要处理 data 不管你是做 machine learning 做 deep learning 做 data analytics 做 data science 也好 scientist 也好通通都要都做的基本功啊那 again 先先对有一些也许对
+ID0012W0014 he tried to think how it could be
\ No newline at end of file
diff --git a/data/list/train_wav.scp b/data/list/train_wav.scp
index 325a340c6..210f3cb48 100644
--- a/data/list/train_wav.scp
+++ b/data/list/train_wav.scp
@@ -1,2 +1,4 @@
-ID0012W0013 /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/wav/D0012/ID0012W0013.wav
-ID0012W0014 /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/wav/D0012/ID0012W0014.wav
\ No newline at end of file
+BAC009S0764W0121 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/BAC009S0764W0121.wav
+BAC009S0916W0489 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/BAC009S0916W0489.wav
+asr_example_cn_en https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_cn_en.wav
+ID0012W0014 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_en.wav
\ No newline at end of file
diff --git a/data/list/val.jsonl b/data/list/val.jsonl
new file mode 100644
index 000000000..8cd75ad2b
--- /dev/null
+++ b/data/list/val.jsonl
@@ -0,0 +1,2 @@
+{"key": "ID0012W0013", "source": "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav", "source_len": 88, "target": "欢迎大家来体验达摩院推出的语音识别模型", "target_len": 19}
+{"key": "ID0012W0014", "source": "https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_en.wav", "source_len": 88, "target": "he tried to think how it could be", "target_len": 8}
diff --git a/data/list/val_text.txt b/data/list/val_text.txt
index f4d4fe457..c1aa42d57 100644
--- a/data/list/val_text.txt
+++ b/data/list/val_text.txt
@@ -1,2 +1,2 @@
-ID0012W0013 当客户风险承受能力评估依据发生变化时
-ID0012W0014 杨涛不得不将工厂关掉
\ No newline at end of file
+ID0012W0013 欢迎大家来体验达摩院推出的语音识别模型
+ID0012W0014 he tried to think how it could be
\ No newline at end of file
diff --git a/data/list/val_wav.scp b/data/list/val_wav.scp
index 325a340c6..4054ad33b 100644
--- a/data/list/val_wav.scp
+++ b/data/list/val_wav.scp
@@ -1,2 +1,2 @@
-ID0012W0013 /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/wav/D0012/ID0012W0013.wav
-ID0012W0014 /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/wav/D0012/ID0012W0014.wav
\ No newline at end of file
+ID0012W0013 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav
+ID0012W0014 https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_en.wav
\ No newline at end of file
diff --git a/examples/industrial_data_pretraining/contextual_paraformer/finetune_from_local.sh b/examples/industrial_data_pretraining/bicif_paraformer/finetune.sh
similarity index 53%
rename from examples/industrial_data_pretraining/contextual_paraformer/finetune_from_local.sh
rename to examples/industrial_data_pretraining/bicif_paraformer/finetune.sh
index 4dbe8552f..885e5c0e2 100644
--- a/examples/industrial_data_pretraining/contextual_paraformer/finetune_from_local.sh
+++ b/examples/industrial_data_pretraining/bicif_paraformer/finetune.sh
@@ -1,52 +1,47 @@
 # Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
 #  MIT License  (https://opensource.org/licenses/MIT)
 
-# method2, finetune from local model
-
-workspace=`pwd`
-
-echo "current path: ${workspace}" # /xxxx/funasr/examples/industrial_data_pretraining/paraformer
-
-# download model
-local_path_root=${workspace}/modelscope_models
-mkdir -p ${local_path_root}
-local_path=${local_path_root}/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
-git clone https://www.modelscope.cn/iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404.git ${local_path}
-
+# method1, finetune from model hub
 
 # which gpu to train or finetune
 export CUDA_VISIBLE_DEVICES="0,1"
 gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
 
+# model_name from model_hub, or model_dir in local path
+
+## option 1, download model automatically
+model_name_or_model_dir="iic/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+model_revision="v2.0.4"
+
+## option 2, download model by git
+#local_path_root=${workspace}/modelscope_models
+#mkdir -p ${local_path_root}/${model_name_or_model_dir}
+#git clone https://www.modelscope.cn/${model_name_or_model_dir}.git ${local_path_root}/${model_name_or_model_dir}
+#model_name_or_model_dir=${local_path_root}/${model_name_or_model_dir}
+
+
 # data dir, which contains: train.json, val.json
 data_dir="../../../data/list"
 
 train_data="${data_dir}/train.jsonl"
 val_data="${data_dir}/val.jsonl"
 
-
 # generate train.jsonl and val.jsonl from wav.scp and text.txt
-python -m funasr.datasets.audio_datasets.scp2jsonl \
+scp2jsonl \
 ++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
 ++data_type_list='["source", "target"]' \
 ++jsonl_file_out="${train_data}"
 
-python -m funasr.datasets.audio_datasets.scp2jsonl \
+scp2jsonl \
 ++scp_file_list='["../../../data/list/val_wav.scp", "../../../data/list/val_text.txt"]' \
 ++data_type_list='["source", "target"]' \
 ++jsonl_file_out="${val_data}"
 
 
-tokens="${local_path}/tokens.json"
-cmvn_file="${local_path}/am.mvn"
-
-# output dir
+# exp output dir
 output_dir="./outputs"
 log_file="${output_dir}/log.txt"
 
-config_name="config.yaml"
-
-init_param="${local_path}/model.pt"
 
 mkdir -p ${output_dir}
 echo "log_file: ${log_file}"
@@ -55,17 +50,18 @@ torchrun \
 --nnodes 1 \
 --nproc_per_node ${gpu_num} \
 ../../../funasr/bin/train.py \
---config-path "${local_path}" \
---config-name "${config_name}" \
+++model="${model_name_or_model_dir}" \
+++model_revision="${model_revision}" \
 ++train_data_set_list="${train_data}" \
 ++valid_data_set_list="${val_data}" \
-++tokenizer_conf.token_list="${tokens}" \
-++frontend_conf.cmvn_file="${cmvn_file}" \
-++dataset_conf.batch_size=32 \
-++dataset_conf.batch_type="example" \
+++dataset_conf.batch_size=20000 \
+++dataset_conf.batch_type="token" \
 ++dataset_conf.num_workers=4 \
-++train_conf.max_epoch=20 \
-++optim_conf.lr=0.0002 \
+++train_conf.max_epoch=50 \
 ++train_conf.log_interval=1 \
-++init_param="${init_param}" \
-++output_dir="${output_dir}" &> ${log_file}
+++train_conf.resume=false \
+++train_conf.validate_interval=2000 \
+++train_conf.save_checkpoint_interval=2000 \
+++train_conf.keep_nbest_models=20 \
+++optim_conf.lr=0.0002 \
+++output_dir="${output_dir}" &> ${log_file}
\ No newline at end of file
diff --git a/examples/industrial_data_pretraining/contextual_paraformer/finetune.sh b/examples/industrial_data_pretraining/contextual_paraformer/finetune.sh
index 98cc73ceb..de8896853 100644
--- a/examples/industrial_data_pretraining/contextual_paraformer/finetune.sh
+++ b/examples/industrial_data_pretraining/contextual_paraformer/finetune.sh
@@ -7,21 +7,39 @@
 export CUDA_VISIBLE_DEVICES="0,1"
 gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
 
-# data dir, which contains: train.json, val.json
-data_dir="/Users/zhifu/funasr1.0/data/list"
+# model_name from model_hub, or model_dir in local path
 
-## generate jsonl from wav.scp and text.txt
-#python -m funasr.datasets.audio_datasets.scp2jsonl \
-#++scp_file_list='["/Users/zhifu/funasr1.0/test_local/wav.scp", "/Users/zhifu/funasr1.0/test_local/text.txt"]' \
-#++data_type_list='["source", "target"]' \
-#++jsonl_file_out=/Users/zhifu/funasr1.0/test_local/audio_datasets.jsonl
+## option 1, download model automatically
+model_name_or_model_dir="iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404"
+model_revision="v2.0.4"
+
+## option 2, download model by git
+#local_path_root=${workspace}/modelscope_models
+#mkdir -p ${local_path_root}/${model_name_or_model_dir}
+#git clone https://www.modelscope.cn/${model_name_or_model_dir}.git ${local_path_root}/${model_name_or_model_dir}
+#model_name_or_model_dir=${local_path_root}/${model_name_or_model_dir}
+
+
+# data dir, which contains: train.json, val.json
+data_dir="../../../data/list"
 
 train_data="${data_dir}/train.jsonl"
 val_data="${data_dir}/val.jsonl"
 
+# generate train.jsonl and val.jsonl from wav.scp and text.txt
+scp2jsonl \
+++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
+++data_type_list='["source", "target"]' \
+++jsonl_file_out="${train_data}"
+
+scp2jsonl \
+++scp_file_list='["../../../data/list/val_wav.scp", "../../../data/list/val_text.txt"]' \
+++data_type_list='["source", "target"]' \
+++jsonl_file_out="${val_data}"
+
 
 # exp output dir
-output_dir="/Users/zhifu/exp"
+output_dir="./outputs"
 log_file="${output_dir}/log.txt"
 
 
@@ -31,14 +49,19 @@ echo "log_file: ${log_file}"
 torchrun \
 --nnodes 1 \
 --nproc_per_node ${gpu_num} \
-funasr/bin/train.py \
-++model="iic/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404" \
-++model_revision="v2.0.5" \
+../../../funasr/bin/train.py \
+++model="${model_name_or_model_dir}" \
+++model_revision="${model_revision}" \
 ++train_data_set_list="${train_data}" \
 ++valid_data_set_list="${val_data}" \
-++dataset_conf.batch_size=32 \
-++dataset_conf.batch_type="example" \
+++dataset_conf.batch_size=20000 \
+++dataset_conf.batch_type="token" \
 ++dataset_conf.num_workers=4 \
-++train_conf.max_epoch=20 \
+++train_conf.max_epoch=50 \
+++train_conf.log_interval=1 \
+++train_conf.resume=false \
+++train_conf.validate_interval=2000 \
+++train_conf.save_checkpoint_interval=2000 \
+++train_conf.keep_nbest_models=20 \
 ++optim_conf.lr=0.0002 \
 ++output_dir="${output_dir}" &> ${log_file}
\ No newline at end of file
diff --git a/examples/industrial_data_pretraining/paraformer/finetune.sh b/examples/industrial_data_pretraining/paraformer/finetune.sh
index 9fc8bf06d..720925223 100644
--- a/examples/industrial_data_pretraining/paraformer/finetune.sh
+++ b/examples/industrial_data_pretraining/paraformer/finetune.sh
@@ -1,27 +1,44 @@
 # Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
 #  MIT License  (https://opensource.org/licenses/MIT)
 
-# method1, finetune from model hub
 
 # which gpu to train or finetune
 export CUDA_VISIBLE_DEVICES="0,1"
 gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
 
-# data dir, which contains: train.json, val.json
-data_dir="/Users/zhifu/funasr1.0/data/list"
+# model_name from model_hub, or model_dir in local path
 
-## generate jsonl from wav.scp and text.txt
-#python -m funasr.datasets.audio_datasets.scp2jsonl \
-#++scp_file_list='["/Users/zhifu/funasr1.0/test_local/wav.scp", "/Users/zhifu/funasr1.0/test_local/text.txt"]' \
-#++data_type_list='["source", "target"]' \
-#++jsonl_file_out=/Users/zhifu/funasr1.0/test_local/audio_datasets.jsonl
+## option 1, download model automatically
+model_name_or_model_dir="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+model_revision="v2.0.4"
+
+## option 2, download model by git
+#local_path_root=${workspace}/modelscope_models
+#mkdir -p ${local_path_root}/${model_name_or_model_dir}
+#git clone https://www.modelscope.cn/${model_name_or_model_dir}.git ${local_path_root}/${model_name_or_model_dir}
+#model_name_or_model_dir=${local_path_root}/${model_name_or_model_dir}
+
+
+# data dir, which contains: train.json, val.json
+data_dir="../../../data/list"
 
 train_data="${data_dir}/train.jsonl"
 val_data="${data_dir}/val.jsonl"
 
+# generate train.jsonl and val.jsonl from wav.scp and text.txt
+scp2jsonl \
+++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
+++data_type_list='["source", "target"]' \
+++jsonl_file_out="${train_data}"
+
+scp2jsonl \
+++scp_file_list='["../../../data/list/val_wav.scp", "../../../data/list/val_text.txt"]' \
+++data_type_list='["source", "target"]' \
+++jsonl_file_out="${val_data}"
+
 
 # exp output dir
-output_dir="/Users/zhifu/exp"
+output_dir="./outputs"
 log_file="${output_dir}/log.txt"
 
 
@@ -31,19 +48,19 @@ echo "log_file: ${log_file}"
 torchrun \
 --nnodes 1 \
 --nproc_per_node ${gpu_num} \
-funasr/bin/train.py \
-++model="iic/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
-++model_revision="v2.0.4" \
+../../../funasr/bin/train.py \
+++model="${model_name_or_model_dir}" \
+++model_revision="${model_revision}" \
 ++train_data_set_list="${train_data}" \
 ++valid_data_set_list="${val_data}" \
 ++dataset_conf.batch_size=20000 \
 ++dataset_conf.batch_type="token" \
 ++dataset_conf.num_workers=4 \
 ++train_conf.max_epoch=50 \
-++train_conf.log_interval=10 \
+++train_conf.log_interval=1 \
 ++train_conf.resume=false \
-++train_conf.validate_interval=15 \
-++train_conf.save_checkpoint_interval=15 \
-++train_conf.keep_nbest_models=50 \
+++train_conf.validate_interval=2000 \
+++train_conf.save_checkpoint_interval=2000 \
+++train_conf.keep_nbest_models=20 \
 ++optim_conf.lr=0.0002 \
 ++output_dir="${output_dir}" &> ${log_file}
\ No newline at end of file
diff --git a/examples/industrial_data_pretraining/paraformer/finetune_from_local.sh b/examples/industrial_data_pretraining/paraformer/train_from_local.sh
similarity index 100%
rename from examples/industrial_data_pretraining/paraformer/finetune_from_local.sh
rename to examples/industrial_data_pretraining/paraformer/train_from_local.sh
diff --git a/examples/industrial_data_pretraining/paraformer_streaming/demo.py b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
index 601a531ef..9fcee3a8c 100644
--- a/examples/industrial_data_pretraining/paraformer_streaming/demo.py
+++ b/examples/industrial_data_pretraining/paraformer_streaming/demo.py
@@ -3,13 +3,16 @@
 # Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
 #  MIT License  (https://opensource.org/licenses/MIT)
 
+import os
+
 from funasr import AutoModel
 
-chunk_size = [5, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
-encoder_chunk_look_back = 0 #number of chunks to lookback for encoder self-attention
-decoder_chunk_look_back = 0 #number of encoder chunks to lookback for decoder cross-attention
-wav_file="/Users/zhifu/Downloads/NCYzUhAtZNI_0015.wav"
+chunk_size = [0, 10, 5] #[0, 10, 5] 600ms, [0, 8, 4] 480ms
+encoder_chunk_look_back = 4 #number of chunks to lookback for encoder self-attention
+decoder_chunk_look_back = 1 #number of encoder chunks to lookback for decoder cross-attention
 model = AutoModel(model="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online", model_revision="v2.0.4")
+
+wav_file = os.path.join(model.model_path, "example/asr_example.wav")
 res = model.generate(input=wav_file,
             chunk_size=chunk_size,
             encoder_chunk_look_back=encoder_chunk_look_back,
@@ -17,12 +20,11 @@ res = model.generate(input=wav_file,
             )
 print(res)
 
-# exit()
 
 import soundfile
-import os
 
-# wav_file = os.path.join(model.model_path, "example/asr_example.wav")
+
+wav_file = os.path.join(model.model_path, "example/asr_example.wav")
 speech, sample_rate = soundfile.read(wav_file)
 
 chunk_stride = chunk_size[1] * 960 # 600ms、480ms
diff --git a/examples/industrial_data_pretraining/seaco_paraformer/finetune_from_local.sh b/examples/industrial_data_pretraining/paraformer_streaming/finetune.sh
similarity index 53%
rename from examples/industrial_data_pretraining/seaco_paraformer/finetune_from_local.sh
rename to examples/industrial_data_pretraining/paraformer_streaming/finetune.sh
index 9593671d9..2bfb2bf39 100644
--- a/examples/industrial_data_pretraining/seaco_paraformer/finetune_from_local.sh
+++ b/examples/industrial_data_pretraining/paraformer_streaming/finetune.sh
@@ -1,52 +1,46 @@
 # Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
 #  MIT License  (https://opensource.org/licenses/MIT)
 
-# method2, finetune from local model
-
-workspace=`pwd`
-
-echo "current path: ${workspace}" # /xxxx/funasr/examples/industrial_data_pretraining/paraformer
-
-# download model
-local_path_root=${workspace}/modelscope_models
-mkdir -p ${local_path_root}
-local_path=${local_path_root}/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
-git clone https://www.modelscope.cn/iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch.git ${local_path}
-
 
 # which gpu to train or finetune
 export CUDA_VISIBLE_DEVICES="0,1"
 gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
 
+# model_name from model_hub, or model_dir in local path
+
+## option 1, download model automatically
+model_name_or_model_dir="iic/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8404-online"
+model_revision="v2.0.4"
+
+## option 2, download model by git
+#local_path_root=${workspace}/modelscope_models
+#mkdir -p ${local_path_root}/${model_name_or_model_dir}
+#git clone https://www.modelscope.cn/${model_name_or_model_dir}.git ${local_path_root}/${model_name_or_model_dir}
+#model_name_or_model_dir=${local_path_root}/${model_name_or_model_dir}
+
+
 # data dir, which contains: train.json, val.json
 data_dir="../../../data/list"
 
 train_data="${data_dir}/train.jsonl"
 val_data="${data_dir}/val.jsonl"
 
-
 # generate train.jsonl and val.jsonl from wav.scp and text.txt
-python -m funasr.datasets.audio_datasets.scp2jsonl \
+scp2jsonl \
 ++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
 ++data_type_list='["source", "target"]' \
 ++jsonl_file_out="${train_data}"
 
-python -m funasr.datasets.audio_datasets.scp2jsonl \
+scp2jsonl \
 ++scp_file_list='["../../../data/list/val_wav.scp", "../../../data/list/val_text.txt"]' \
 ++data_type_list='["source", "target"]' \
 ++jsonl_file_out="${val_data}"
 
 
-tokens="${local_path}/tokens.json"
-cmvn_file="${local_path}/am.mvn"
-
-# output dir
+# exp output dir
 output_dir="./outputs"
 log_file="${output_dir}/log.txt"
 
-config_name="config.yaml"
-
-init_param="${local_path}/model.pt"
 
 mkdir -p ${output_dir}
 echo "log_file: ${log_file}"
@@ -55,17 +49,18 @@ torchrun \
 --nnodes 1 \
 --nproc_per_node ${gpu_num} \
 ../../../funasr/bin/train.py \
---config-path "${local_path}" \
---config-name "${config_name}" \
+++model="${model_name_or_model_dir}" \
+++model_revision="${model_revision}" \
 ++train_data_set_list="${train_data}" \
 ++valid_data_set_list="${val_data}" \
-++tokenizer_conf.token_list="${tokens}" \
-++frontend_conf.cmvn_file="${cmvn_file}" \
-++dataset_conf.batch_size=32 \
-++dataset_conf.batch_type="example" \
+++dataset_conf.batch_size=20000 \
+++dataset_conf.batch_type="token" \
 ++dataset_conf.num_workers=4 \
-++train_conf.max_epoch=20 \
-++optim_conf.lr=0.0002 \
+++train_conf.max_epoch=50 \
 ++train_conf.log_interval=1 \
-++init_param="${init_param}" \
-++output_dir="${output_dir}" &> ${log_file}
+++train_conf.resume=false \
+++train_conf.validate_interval=2000 \
+++train_conf.save_checkpoint_interval=2000 \
+++train_conf.keep_nbest_models=20 \
+++optim_conf.lr=0.0002 \
+++output_dir="${output_dir}" &> ${log_file}
\ No newline at end of file
diff --git a/examples/industrial_data_pretraining/seaco_paraformer/finetune.sh b/examples/industrial_data_pretraining/seaco_paraformer/finetune.sh
index 88f0e2314..cfdec7779 100644
--- a/examples/industrial_data_pretraining/seaco_paraformer/finetune.sh
+++ b/examples/industrial_data_pretraining/seaco_paraformer/finetune.sh
@@ -1,27 +1,44 @@
 # Copyright FunASR (https://github.com/alibaba-damo-academy/FunASR). All Rights Reserved.
 #  MIT License  (https://opensource.org/licenses/MIT)
 
-# method1, finetune from model hub
 
 # which gpu to train or finetune
 export CUDA_VISIBLE_DEVICES="0,1"
 gpu_num=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}')
 
-# data dir, which contains: train.json, val.json
-data_dir="/Users/zhifu/funasr1.0/data/list"
+# model_name from model_hub, or model_dir in local path
 
-## generate jsonl from wav.scp and text.txt
-#python -m funasr.datasets.audio_datasets.scp2jsonl \
-#++scp_file_list='["/Users/zhifu/funasr1.0/test_local/wav.scp", "/Users/zhifu/funasr1.0/test_local/text.txt"]' \
-#++data_type_list='["source", "target"]' \
-#++jsonl_file_out=/Users/zhifu/funasr1.0/test_local/audio_datasets.jsonl
+## option 1, download model automatically
+model_name_or_model_dir="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+model_revision="v2.0.4"
+
+## option 2, download model by git
+#local_path_root=${workspace}/modelscope_models
+#mkdir -p ${local_path_root}/${model_name_or_model_dir}
+#git clone https://www.modelscope.cn/${model_name_or_model_dir}.git ${local_path_root}/${model_name_or_model_dir}
+#model_name_or_model_dir=${local_path_root}/${model_name_or_model_dir}
+
+
+# data dir, which contains: train.json, val.json
+data_dir="../../../data/list"
 
 train_data="${data_dir}/train.jsonl"
 val_data="${data_dir}/val.jsonl"
 
+# generate train.jsonl and val.jsonl from wav.scp and text.txt
+scp2jsonl \
+++scp_file_list='["../../../data/list/train_wav.scp", "../../../data/list/train_text.txt"]' \
+++data_type_list='["source", "target"]' \
+++jsonl_file_out="${train_data}"
+
+scp2jsonl \
+++scp_file_list='["../../../data/list/val_wav.scp", "../../../data/list/val_text.txt"]' \
+++data_type_list='["source", "target"]' \
+++jsonl_file_out="${val_data}"
+
 
 # exp output dir
-output_dir="/Users/zhifu/exp"
+output_dir="./outputs"
 log_file="${output_dir}/log.txt"
 
 
@@ -31,14 +48,19 @@ echo "log_file: ${log_file}"
 torchrun \
 --nnodes 1 \
 --nproc_per_node ${gpu_num} \
-funasr/bin/train.py \
-++model="iic/speech_seaco_paraformer_large_asr_nat-zh-cn-16k-common-vocab8404-pytorch" \
-++model_revision="v2.0.6" \
+../../../funasr/bin/train.py \
+++model="${model_name_or_model_dir}" \
+++model_revision="${model_revision}" \
 ++train_data_set_list="${train_data}" \
 ++valid_data_set_list="${val_data}" \
-++dataset_conf.batch_size=32 \
-++dataset_conf.batch_type="example" \
+++dataset_conf.batch_size=20000 \
+++dataset_conf.batch_type="token" \
 ++dataset_conf.num_workers=4 \
-++train_conf.max_epoch=20 \
+++train_conf.max_epoch=50 \
+++train_conf.log_interval=1 \
+++train_conf.resume=false \
+++train_conf.validate_interval=2000 \
+++train_conf.save_checkpoint_interval=2000 \
+++train_conf.keep_nbest_models=20 \
 ++optim_conf.lr=0.0002 \
 ++output_dir="${output_dir}" &> ${log_file}
\ No newline at end of file
diff --git a/funasr/datasets/audio_datasets/scp2jsonl.py b/funasr/datasets/audio_datasets/scp2jsonl.py
index e09a84a61..00754ddb6 100644
--- a/funasr/datasets/audio_datasets/scp2jsonl.py
+++ b/funasr/datasets/audio_datasets/scp2jsonl.py
@@ -29,15 +29,19 @@ def gen_jsonl_from_wav_text_list(path, data_type_list=("source", "target"), json
                 data_file_lists = f.readlines()
                 lines_for_each_th = (len(data_file_lists)-1)//cpu_cores + 1
                 task_num = cpu_cores if len(data_file_lists) > cpu_cores else 1
-                with concurrent.futures.ThreadPoolExecutor(max_workers=cpu_cores) as executor:
-
-                    futures = [executor.submit(parse_context_length, data_file_lists[i*lines_for_each_th:(i+1)*lines_for_each_th], data_type) for i in range(task_num)]
+                # import pdb;pdb.set_trace()
+                if task_num > 1:
+                    with concurrent.futures.ThreadPoolExecutor(max_workers=cpu_cores) as executor:
     
-                    for future in concurrent.futures.as_completed(futures):
-                        
-                        json_dict[data_type].update(future.result())
-            # print(json_dict)
+                        futures = [executor.submit(parse_context_length, data_file_lists[i*lines_for_each_th:(i+1)*lines_for_each_th], data_type) for i in range(task_num)]
         
+                        for future in concurrent.futures.as_completed(futures):
+                            
+                            json_dict[data_type].update(future.result())
+                else:
+                    res = parse_context_length(data_file_lists, data_type)
+                    json_dict[data_type].update(res)
+
         with open(jsonl_file_out, "w") as f:
             for key in json_dict[data_type_list[0]].keys():
                 jsonl_line = {"key": key}
@@ -46,6 +50,7 @@ def gen_jsonl_from_wav_text_list(path, data_type_list=("source", "target"), json
                 jsonl_line = json.dumps(jsonl_line, ensure_ascii=False)
                 f.write(jsonl_line+"\n")
                 f.flush()
+        print(f"processed {len(json_dict[data_type_list[0]])} samples")
                 
     else:
         pass
diff --git a/setup.py b/setup.py
index 5cb56658f..9a69fcd9d 100644
--- a/setup.py
+++ b/setup.py
@@ -140,6 +140,9 @@ setup(
     ],
     entry_points={"console_scripts": [
         "funasr = funasr.bin.inference:main_hydra",
+        "funasr-train = funasr.bin.train:main_hydra",
         "funasr-export = funasr.bin.export:main_hydra",
+        "scp2jsonl = funasr.datasets.audio_datasets.scp2jsonl:main_hydra",
+        "jsonl2scp = funasr.datasets.audio_datasets.jsonl2scp:main_hydra",
     ]},
 )