From b0887f17678e0e5c4bd895e36695b242f2f1aee8 Mon Sep 17 00:00:00 2001
From: mengzhe.cmz <mengzhe.cmz@alibaba-inc.com>
Date: 星期四, 23 三月 2023 19:59:28 +0800
Subject: [PATCH] Merge branch 'dev_gzf' of github.com:alibaba-damo-academy/FunASR into dev_gzf

---
 egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh   |   95 ++++
 funasr/runtime/onnxruntime/readme.md                                                                        |    2 
 egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/README.md     |   38 +
 funasr/runtime/python/benchmark_onnx.md                                                                     |   20 
 funasr/runtime/python/websocket/ASR_client.py                                                               |   95 ++++
 funasr/runtime/python/utils/compute_wer.py                                                                  |  157 +++++++
 egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/utils         |    1 
 funasr/runtime/python/grpc/Readme.md                                                                        |   23 
 funasr/runtime/python/utils/proce_text.py                                                                   |   31 +
 funasr/runtime/python/websocket/requirements_server.txt                                                     |    1 
 funasr/export/export_model.py                                                                               |    4 
 funasr/runtime/python/websocket/ASR_server.py                                                               |  191 +++++++++
 funasr/runtime/python/utils/infer.py                                                                        |   48 ++
 funasr/bin/punctuation_infer_vadrealtime.py                                                                 |   30 -
 egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.sh      |   70 +++
 egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/RESULTS.md |   20 
 egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py      |  108 ----
 funasr/runtime/python/websocket/README.md                                                                   |   46 ++
 funasr/tasks/abs_task.py                                                                                    |    6 
 funasr/runtime/python/utils/infer.sh                                                                        |   74 +++
 /dev/null                                                                                                   |   48 --
 funasr/bin/vad_inference_online.py                                                                          |    7 
 egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md  |   11 
 funasr/runtime/python/websocket/requirements_client.txt                                                     |    2 
 egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py   |  108 ----
 egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/utils      |    1 
 26 files changed, 941 insertions(+), 296 deletions(-)

diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/README.md b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/README.md
deleted file mode 100644
index 1587d3d..0000000
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/README.md
+++ /dev/null
@@ -1,30 +0,0 @@
-# ModelScope Model
-
-## How to finetune and infer using a pretrained Paraformer-large Model
-
-### Finetune
-
-- Modify finetune training related parameters in `finetune.py`
-    - <strong>output_dir:</strong> # result dir
-    - <strong>data_dir:</strong> # the dataset dir needs to include files: train/wav.scp, train/text; validation/wav.scp, validation/text.
-    - <strong>batch_bins:</strong> # batch size
-    - <strong>max_epoch:</strong> # number of training epoch
-    - <strong>lr:</strong> # learning rate
-
-- Then you can run the pipeline to finetune with:
-```python
-    python finetune.py
-```
-
-### Inference
-
-Or you can use the finetuned model for inference directly.
-
-- Setting parameters in `infer.py`
-    - <strong>data_dir:</strong> # the dataset dir
-    - <strong>output_dir:</strong> # result dir
-
-- Then you can run the pipeline to infer with:
-```python
-    python infer.py
-```
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/RESULTS.md b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/RESULTS.md
deleted file mode 100644
index 5eeae37..0000000
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/RESULTS.md
+++ /dev/null
@@ -1,23 +0,0 @@
-# Paraformer-Large
-- Model link: <https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/summary>
-- Model size: 220M
-
-# Environments
-- date: `Fri Feb 10 13:34:24 CST 2023`
-- python version: `3.7.12`
-- FunASR version: `0.1.6`
-- pytorch version: `pytorch 1.7.0`
-- Git hash: ``
-- Commit date: ``
-
-# Beachmark Results
-
-## AISHELL-1
-- Decode config:
-  - Decode without CTC
-  - Decode without LM
-
-| testset CER(%) | base model|finetune model |
-|:--------------:|:---------:|:-------------:|
-| dev            | 1.75      |1.62           |
-| test           | 1.95      |1.78           |
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/finetune.py b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/finetune.py
deleted file mode 100644
index 5817f0e..0000000
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/finetune.py
+++ /dev/null
@@ -1,36 +0,0 @@
-import os
-
-from modelscope.metainfo import Trainers
-from modelscope.trainers import build_trainer
-
-from funasr.datasets.ms_dataset import MsDataset
-from funasr.utils.modelscope_param import modelscope_args
-
-
-def modelscope_finetune(params):
-    if not os.path.exists(params.output_dir):
-        os.makedirs(params.output_dir, exist_ok=True)
-    # dataset split ["train", "validation"]
-    ds_dict = MsDataset.load(params.data_path)
-    kwargs = dict(
-        model=params.model,
-        data_dir=ds_dict,
-        dataset_type=params.dataset_type,
-        work_dir=params.output_dir,
-        batch_bins=params.batch_bins,
-        max_epoch=params.max_epoch,
-        lr=params.lr)
-    trainer = build_trainer(Trainers.speech_asr_trainer, default_args=kwargs)
-    trainer.train()
-
-
-if __name__ == '__main__':
-    params = modelscope_args(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch", data_path="./data")
-    params.output_dir = "./checkpoint"              # m妯″瀷淇濆瓨璺緞
-    params.data_path = "./example_data/"            # 鏁版嵁璺緞
-    params.dataset_type = "small"                   # 灏忔暟鎹噺璁剧疆small锛岃嫢鏁版嵁閲忓ぇ浜�1000灏忔椂锛岃浣跨敤large
-    params.batch_bins = 2000                       # batch size锛屽鏋渄ataset_type="small"锛宐atch_bins鍗曚綅涓篺bank鐗瑰緛甯ф暟锛屽鏋渄ataset_type="large"锛宐atch_bins鍗曚綅涓烘绉掞紝
-    params.max_epoch = 50                           # 鏈�澶ц缁冭疆鏁�
-    params.lr = 0.00005                             # 璁剧疆瀛︿範鐜�
-    
-    modelscope_finetune(params)
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/infer.py b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/infer.py
deleted file mode 100644
index 2fceb48..0000000
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/infer.py
+++ /dev/null
@@ -1,101 +0,0 @@
-import os
-import shutil
-from multiprocessing import Pool
-
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-
-from funasr.utils.compute_wer import compute_wer
-
-
-def modelscope_infer_core(output_dir, split_dir, njob, idx, batch_size, ngpu, model):
-    output_dir_job = os.path.join(output_dir, "output.{}".format(idx))
-    if ngpu > 0:
-        use_gpu = 1
-        gpu_id = int(idx) - 1
-    else:
-        use_gpu = 0
-        gpu_id = -1
-    if "CUDA_VISIBLE_DEVICES" in os.environ.keys():
-        gpu_list = os.environ['CUDA_VISIBLE_DEVICES'].split(",")
-        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
-    else:
-        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
-    inference_pipline = pipeline(
-        task=Tasks.auto_speech_recognition,
-        model=model,
-        output_dir=output_dir_job,
-        batch_size=batch_size,
-        ngpu=use_gpu,
-    )
-    audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
-    inference_pipline(audio_in=audio_in)
-
-
-def modelscope_infer(params):
-    # prepare for multi-GPU decoding
-    ngpu = params["ngpu"]
-    njob = params["njob"]
-    batch_size = params["batch_size"]
-    output_dir = params["output_dir"]
-    model = params["model"]
-    if os.path.exists(output_dir):
-        shutil.rmtree(output_dir)
-    os.mkdir(output_dir)
-    split_dir = os.path.join(output_dir, "split")
-    os.mkdir(split_dir)
-    if ngpu > 0:
-        nj = ngpu
-    elif ngpu == 0:
-        nj = njob
-    wav_scp_file = os.path.join(params["data_dir"], "wav.scp")
-    with open(wav_scp_file) as f:
-        lines = f.readlines()
-        num_lines = len(lines)
-        num_job_lines = num_lines // nj
-    start = 0
-    for i in range(nj):
-        end = start + num_job_lines
-        file = os.path.join(split_dir, "wav.{}.scp".format(str(i + 1)))
-        with open(file, "w") as f:
-            if i == nj - 1:
-                f.writelines(lines[start:])
-            else:
-                f.writelines(lines[start:end])
-        start = end
-
-    p = Pool(nj)
-    for i in range(nj):
-        p.apply_async(modelscope_infer_core,
-                      args=(output_dir, split_dir, njob, str(i + 1), batch_size, ngpu, model))
-    p.close()
-    p.join()
-
-    # combine decoding results
-    best_recog_path = os.path.join(output_dir, "1best_recog")
-    os.mkdir(best_recog_path)
-    files = ["text", "token", "score"]
-    for file in files:
-        with open(os.path.join(best_recog_path, file), "w") as f:
-            for i in range(nj):
-                job_file = os.path.join(output_dir, "output.{}/1best_recog".format(str(i + 1)), file)
-                with open(job_file) as f_job:
-                    lines = f_job.readlines()
-                f.writelines(lines)
-
-    # If text exists, compute CER
-    text_in = os.path.join(params["data_dir"], "text")
-    if os.path.exists(text_in):
-        text_proc_file = os.path.join(best_recog_path, "token")
-        compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.cer"))
-
-
-if __name__ == "__main__":
-    params = {}
-    params["model"] = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch"
-    params["data_dir"] = "./data/test"
-    params["output_dir"] = "./results"
-    params["ngpu"] = 1 # if ngpu > 0, will use gpu decoding
-    params["njob"] = 1 # if ngpu = 0, will use cpu decoding
-    params["batch_size"] = 64
-    modelscope_infer(params)
\ No newline at end of file
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/infer_after_finetune.py b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/infer_after_finetune.py
deleted file mode 100644
index fafe565..0000000
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/infer_after_finetune.py
+++ /dev/null
@@ -1,48 +0,0 @@
-import json
-import os
-import shutil
-
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-from modelscope.hub.snapshot_download import snapshot_download
-
-from funasr.utils.compute_wer import compute_wer
-
-def modelscope_infer_after_finetune(params):
-    # prepare for decoding
-
-    try:
-        pretrained_model_path = snapshot_download(params["modelscope_model_name"], cache_dir=params["output_dir"])
-    except BaseException:
-        raise BaseException(f"Please download pretrain model from ModelScope firstly.")
-    shutil.copy(os.path.join(params["output_dir"], params["decoding_model_name"]), os.path.join(pretrained_model_path, "model.pb"))
-    decoding_path = os.path.join(params["output_dir"], "decode_results")
-    if os.path.exists(decoding_path):
-        shutil.rmtree(decoding_path)
-    os.mkdir(decoding_path)
-
-    # decoding
-    inference_pipeline = pipeline(
-        task=Tasks.auto_speech_recognition,
-        model=pretrained_model_path,
-        output_dir=decoding_path,
-        batch_size=params["batch_size"]
-    )
-    audio_in = os.path.join(params["data_dir"], "wav.scp")
-    inference_pipeline(audio_in=audio_in)
-
-    # computer CER if GT text is set
-    text_in = os.path.join(params["data_dir"], "text")
-    if os.path.exists(text_in):
-        text_proc_file = os.path.join(decoding_path, "1best_recog/token")
-        compute_wer(text_in, text_proc_file, os.path.join(decoding_path, "text.cer"))
-
-
-if __name__ == '__main__':
-    params = {}
-    params["modelscope_model_name"] = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch"
-    params["output_dir"] = "./checkpoint"
-    params["data_dir"] = "./data/test"
-    params["decoding_model_name"] = "valid.acc.ave_10best.pb"
-    params["batch_size"] = 64
-    modelscope_infer_after_finetune(params)
\ No newline at end of file
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/README.md b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/README.md
deleted file mode 100644
index 1587d3d..0000000
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/README.md
+++ /dev/null
@@ -1,30 +0,0 @@
-# ModelScope Model
-
-## How to finetune and infer using a pretrained Paraformer-large Model
-
-### Finetune
-
-- Modify finetune training related parameters in `finetune.py`
-    - <strong>output_dir:</strong> # result dir
-    - <strong>data_dir:</strong> # the dataset dir needs to include files: train/wav.scp, train/text; validation/wav.scp, validation/text.
-    - <strong>batch_bins:</strong> # batch size
-    - <strong>max_epoch:</strong> # number of training epoch
-    - <strong>lr:</strong> # learning rate
-
-- Then you can run the pipeline to finetune with:
-```python
-    python finetune.py
-```
-
-### Inference
-
-Or you can use the finetuned model for inference directly.
-
-- Setting parameters in `infer.py`
-    - <strong>data_dir:</strong> # the dataset dir
-    - <strong>output_dir:</strong> # result dir
-
-- Then you can run the pipeline to infer with:
-```python
-    python infer.py
-```
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/RESULTS.md b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/RESULTS.md
deleted file mode 100644
index 71d9fee..0000000
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/RESULTS.md
+++ /dev/null
@@ -1,25 +0,0 @@
-# Paraformer-Large
-- Model link: <https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/summary>
-- Model size: 220M
-
-# Environments
-- date: `Fri Feb 10 13:34:24 CST 2023`
-- python version: `3.7.12`
-- FunASR version: `0.1.6`
-- pytorch version: `pytorch 1.7.0`
-- Git hash: ``
-- Commit date: ``
-
-# Beachmark Results
-
-## AISHELL-2
-- Decode config: 
-  - Decode without CTC
-  - Decode without LM
-
-| testset      | base model|finetune model|
-|:------------:|:---------:|:------------:|
-| dev_ios      | 2.80      |2.60          |
-| test_android | 3.13      |2.84          |
-| test_ios     | 2.85      |2.82          |
-| test_mic     | 3.06      |2.88          |
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/finetune.py b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/finetune.py
deleted file mode 100644
index c46d676..0000000
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/finetune.py
+++ /dev/null
@@ -1,36 +0,0 @@
-import os
-
-from modelscope.metainfo import Trainers
-from modelscope.trainers import build_trainer
-
-from funasr.datasets.ms_dataset import MsDataset
-from funasr.utils.modelscope_param import modelscope_args
-
-
-def modelscope_finetune(params):
-    if not os.path.exists(params.output_dir):
-        os.makedirs(params.output_dir, exist_ok=True)
-    # dataset split ["train", "validation"]
-    ds_dict = MsDataset.load(params.data_path)
-    kwargs = dict(
-        model=params.model,
-        data_dir=ds_dict,
-        dataset_type=params.dataset_type,
-        work_dir=params.output_dir,
-        batch_bins=params.batch_bins,
-        max_epoch=params.max_epoch,
-        lr=params.lr)
-    trainer = build_trainer(Trainers.speech_asr_trainer, default_args=kwargs)
-    trainer.train()
-
-
-if __name__ == '__main__':
-    params = modelscope_args(model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch", data_path="./data")
-    params.output_dir = "./checkpoint"              # m妯″瀷淇濆瓨璺緞
-    params.data_path = "./example_data/"            # 鏁版嵁璺緞
-    params.dataset_type = "small"                   # 灏忔暟鎹噺璁剧疆small锛岃嫢鏁版嵁閲忓ぇ浜�1000灏忔椂锛岃浣跨敤large
-    params.batch_bins = 2000                       # batch size锛屽鏋渄ataset_type="small"锛宐atch_bins鍗曚綅涓篺bank鐗瑰緛甯ф暟锛屽鏋渄ataset_type="large"锛宐atch_bins鍗曚綅涓烘绉掞紝
-    params.max_epoch = 50                           # 鏈�澶ц缁冭疆鏁�
-    params.lr = 0.00005                             # 璁剧疆瀛︿範鐜�
-    
-    modelscope_finetune(params)
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/infer.py b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/infer.py
deleted file mode 100644
index d70af72..0000000
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/infer.py
+++ /dev/null
@@ -1,101 +0,0 @@
-import os
-import shutil
-from multiprocessing import Pool
-
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-
-from funasr.utils.compute_wer import compute_wer
-
-
-def modelscope_infer_core(output_dir, split_dir, njob, idx, batch_size, ngpu, model):
-    output_dir_job = os.path.join(output_dir, "output.{}".format(idx))
-    if ngpu > 0:
-        use_gpu = 1
-        gpu_id = int(idx) - 1
-    else:
-        use_gpu = 0
-        gpu_id = -1
-    if "CUDA_VISIBLE_DEVICES" in os.environ.keys():
-        gpu_list = os.environ['CUDA_VISIBLE_DEVICES'].split(",")
-        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
-    else:
-        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
-    inference_pipline = pipeline(
-        task=Tasks.auto_speech_recognition,
-        model=model,
-        output_dir=output_dir_job,
-        batch_size=batch_size,
-        ngpu=use_gpu,
-    )
-    audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
-    inference_pipline(audio_in=audio_in)
-
-
-def modelscope_infer(params):
-    # prepare for multi-GPU decoding
-    ngpu = params["ngpu"]
-    njob = params["njob"]
-    batch_size = params["batch_size"]
-    output_dir = params["output_dir"]
-    model = params["model"]
-    if os.path.exists(output_dir):
-        shutil.rmtree(output_dir)
-    os.mkdir(output_dir)
-    split_dir = os.path.join(output_dir, "split")
-    os.mkdir(split_dir)
-    if ngpu > 0:
-        nj = ngpu
-    elif ngpu == 0:
-        nj = njob
-    wav_scp_file = os.path.join(params["data_dir"], "wav.scp")
-    with open(wav_scp_file) as f:
-        lines = f.readlines()
-        num_lines = len(lines)
-        num_job_lines = num_lines // nj
-    start = 0
-    for i in range(nj):
-        end = start + num_job_lines
-        file = os.path.join(split_dir, "wav.{}.scp".format(str(i + 1)))
-        with open(file, "w") as f:
-            if i == nj - 1:
-                f.writelines(lines[start:])
-            else:
-                f.writelines(lines[start:end])
-        start = end
-
-    p = Pool(nj)
-    for i in range(nj):
-        p.apply_async(modelscope_infer_core,
-                      args=(output_dir, split_dir, njob, str(i + 1), batch_size, ngpu, model))
-    p.close()
-    p.join()
-
-    # combine decoding results
-    best_recog_path = os.path.join(output_dir, "1best_recog")
-    os.mkdir(best_recog_path)
-    files = ["text", "token", "score"]
-    for file in files:
-        with open(os.path.join(best_recog_path, file), "w") as f:
-            for i in range(nj):
-                job_file = os.path.join(output_dir, "output.{}/1best_recog".format(str(i + 1)), file)
-                with open(job_file) as f_job:
-                    lines = f_job.readlines()
-                f.writelines(lines)
-
-    # If text exists, compute CER
-    text_in = os.path.join(params["data_dir"], "text")
-    if os.path.exists(text_in):
-        text_proc_file = os.path.join(best_recog_path, "token")
-        compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.cer"))
-
-
-if __name__ == "__main__":
-    params = {}
-    params["model"] = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch"
-    params["data_dir"] = "./data/test"
-    params["output_dir"] = "./results"
-    params["ngpu"] = 1 # if ngpu > 0, will use gpu decoding
-    params["njob"] = 1 # if ngpu = 0, will use cpu decoding
-    params["batch_size"] = 64
-    modelscope_infer(params)
\ No newline at end of file
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/infer_after_finetune.py b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/infer_after_finetune.py
deleted file mode 100644
index 731cafe..0000000
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/infer_after_finetune.py
+++ /dev/null
@@ -1,48 +0,0 @@
-import json
-import os
-import shutil
-
-from modelscope.pipelines import pipeline
-from modelscope.utils.constant import Tasks
-from modelscope.hub.snapshot_download import snapshot_download
-
-from funasr.utils.compute_wer import compute_wer
-
-def modelscope_infer_after_finetune(params):
-    # prepare for decoding
-
-    try:
-        pretrained_model_path = snapshot_download(params["modelscope_model_name"], cache_dir=params["output_dir"])
-    except BaseException:
-        raise BaseException(f"Please download pretrain model from ModelScope firstly.")
-    shutil.copy(os.path.join(params["output_dir"], params["decoding_model_name"]), os.path.join(pretrained_model_path, "model.pb"))
-    decoding_path = os.path.join(params["output_dir"], "decode_results")
-    if os.path.exists(decoding_path):
-        shutil.rmtree(decoding_path)
-    os.mkdir(decoding_path)
-
-    # decoding
-    inference_pipeline = pipeline(
-        task=Tasks.auto_speech_recognition,
-        model=pretrained_model_path,
-        output_dir=decoding_path,
-        batch_size=params["batch_size"]
-    )
-    audio_in = os.path.join(params["data_dir"], "wav.scp")
-    inference_pipeline(audio_in=audio_in)
-
-    # computer CER if GT text is set
-    text_in = os.path.join(params["data_dir"], "text")
-    if os.path.exists(text_in):
-        text_proc_file = os.path.join(decoding_path, "1best_recog/token")
-        compute_wer(text_in, text_proc_file, os.path.join(decoding_path, "text.cer"))
-
-
-if __name__ == '__main__':
-    params = {}
-    params["modelscope_model_name"] = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch"
-    params["output_dir"] = "./checkpoint"
-    params["data_dir"] = "./data/test"
-    params["decoding_model_name"] = "valid.acc.ave_10best.pb"
-    params["batch_size"] = 64
-    modelscope_infer_after_finetune(params)
\ No newline at end of file
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md
index a044361..79cc3c3 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/README.md
@@ -21,23 +21,26 @@
 
 Or you can use the finetuned model for inference directly.
 
-- Setting parameters in `infer.py`
+- Setting parameters in `infer.sh`
     - <strong>model:</strong> # model name on ModelScope
     - <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
     - <strong>output_dir:</strong> # result dir
-    - <strong>ngpu:</strong> # the number of GPUs for decoding, if `ngpu` > 0, use GPU decoding
-    - <strong>njob:</strong> # the number of jobs for CPU decoding, if `ngpu` = 0, use CPU decoding, please set `njob`
     - <strong>batch_size:</strong> # batchsize of inference
+    - <strong>gpu_inference:</strong> # whether to perform gpu decoding, set false for cpu decoding
+    - <strong>gpuid_list:</strong> # set gpus, e.g., gpuid_list="0,1"
+    - <strong>njob:</strong> # the number of jobs for CPU decoding, if `gpu_inference`=false, use CPU decoding, please set `njob`
 
 - Then you can run the pipeline to infer with:
 ```python
-    python infer.py
+    sh infer.sh
 ```
 
 - Results
 
 The decoding results can be found in `$output_dir/1best_recog/text.cer`, which includes recognition results of each sample and the CER metric of the whole test set.
 
+If you decode the SpeechIO test sets, you can use textnorm with `stage`=3, and `DETAILS.txt`, `RESULTS.txt` record the results and CER after text normalization.
+
 ### Inference using local finetuned model
 
 - Modify inference related parameters in `infer_after_finetune.py`
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/RESULTS.md b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/RESULTS.md
index ec95be3..4e06daf 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/RESULTS.md
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/RESULTS.md
@@ -17,22 +17,22 @@
   - Decode without CTC
   - Decode without LM
 
-| testset   | CER(%)|
-|:---------:|:-----:|
-| dev       | 1.75  |
-| test      | 1.95  |
+| CER(%)    | Pretrain model|[Finetune model](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell1-vocab8404-pytorch/summary) |
+|:---------:|:-------------:|:-------------:|
+| dev       | 1.75          |1.62           |
+| test      | 1.95          |1.78           |
 
 ## AISHELL-2
 - Decode config: 
   - Decode without CTC
   - Decode without LM
 
-| testset      | CER(%)|
-|:------------:|:-----:|
-| dev_ios      | 2.80  |
-| test_android | 3.13  |
-| test_ios     | 2.85  |
-| test_mic     | 3.06  |
+| CER(%)       | Pretrain model|[Finetune model](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-aishell2-vocab8404-pytorch/summary)|
+|:------------:|:-------------:|:------------:|
+| dev_ios      | 2.80          |2.60          |
+| test_android | 3.13          |2.84          |
+| test_ios     | 2.85          |2.82          |
+| test_mic     | 3.06          |2.88          |
 
 ## Wenetspeech
 - Decode config: 
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py
index 795a1e7..6726a41 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.py
@@ -1,101 +1,25 @@
 import os
 import shutil
-from multiprocessing import Pool
-
+import argparse
 from modelscope.pipelines import pipeline
 from modelscope.utils.constant import Tasks
 
-from funasr.utils.compute_wer import compute_wer
-
-
-def modelscope_infer_core(output_dir, split_dir, njob, idx, batch_size, ngpu, model):
-    output_dir_job = os.path.join(output_dir, "output.{}".format(idx))
-    if ngpu > 0:
-        use_gpu = 1
-        gpu_id = int(idx) - 1
-    else:
-        use_gpu = 0
-        gpu_id = -1
-    if "CUDA_VISIBLE_DEVICES" in os.environ.keys():
-        gpu_list = os.environ['CUDA_VISIBLE_DEVICES'].split(",")
-        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
-    else:
-        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
-    inference_pipline = pipeline(
+def modelscope_infer(args):
+    os.environ['CUDA_VISIBLE_DEVICES'] = str(args.gpuid)
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
-        model=model,
-        output_dir=output_dir_job,
-        batch_size=batch_size,
-        ngpu=use_gpu,
+        model=args.model,
+        output_dir=args.output_dir,
+        batch_size=args.batch_size,
     )
-    audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
-    inference_pipline(audio_in=audio_in)
-
-
-def modelscope_infer(params):
-    # prepare for multi-GPU decoding
-    ngpu = params["ngpu"]
-    njob = params["njob"]
-    batch_size = params["batch_size"]
-    output_dir = params["output_dir"]
-    model = params["model"]
-    if os.path.exists(output_dir):
-        shutil.rmtree(output_dir)
-    os.mkdir(output_dir)
-    split_dir = os.path.join(output_dir, "split")
-    os.mkdir(split_dir)
-    if ngpu > 0:
-        nj = ngpu
-    elif ngpu == 0:
-        nj = njob
-    wav_scp_file = os.path.join(params["data_dir"], "wav.scp")
-    with open(wav_scp_file) as f:
-        lines = f.readlines()
-        num_lines = len(lines)
-        num_job_lines = num_lines // nj
-    start = 0
-    for i in range(nj):
-        end = start + num_job_lines
-        file = os.path.join(split_dir, "wav.{}.scp".format(str(i + 1)))
-        with open(file, "w") as f:
-            if i == nj - 1:
-                f.writelines(lines[start:])
-            else:
-                f.writelines(lines[start:end])
-        start = end
-
-    p = Pool(nj)
-    for i in range(nj):
-        p.apply_async(modelscope_infer_core,
-                      args=(output_dir, split_dir, njob, str(i + 1), batch_size, ngpu, model))
-    p.close()
-    p.join()
-
-    # combine decoding results
-    best_recog_path = os.path.join(output_dir, "1best_recog")
-    os.mkdir(best_recog_path)
-    files = ["text", "token", "score"]
-    for file in files:
-        with open(os.path.join(best_recog_path, file), "w") as f:
-            for i in range(nj):
-                job_file = os.path.join(output_dir, "output.{}/1best_recog".format(str(i + 1)), file)
-                with open(job_file) as f_job:
-                    lines = f_job.readlines()
-                f.writelines(lines)
-
-    # If text exists, compute CER
-    text_in = os.path.join(params["data_dir"], "text")
-    if os.path.exists(text_in):
-        text_proc_file = os.path.join(best_recog_path, "token")
-        compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.cer"))
-
+    inference_pipeline(audio_in=args.audio_in)
 
 if __name__ == "__main__":
-    params = {}
-    params["model"] = "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
-    params["data_dir"] = "./data/test"
-    params["output_dir"] = "./results"
-    params["ngpu"] = 1 # if ngpu > 0, will use gpu decoding
-    params["njob"] = 1 # if ngpu = 0, will use cpu decoding
-    params["batch_size"] = 64
-    modelscope_infer(params)
\ No newline at end of file
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--model', type=str, default="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch")
+    parser.add_argument('--audio_in', type=str, default="./data/test")
+    parser.add_argument('--output_dir', type=str, default="./results/")
+    parser.add_argument('--batch_size', type=int, default=64)
+    parser.add_argument('--gpuid', type=str, default="0")
+    args = parser.parse_args()
+    modelscope_infer(args)
\ No newline at end of file
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh
new file mode 100644
index 0000000..f080257
--- /dev/null
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/infer.sh
@@ -0,0 +1,95 @@
+#!/usr/bin/env bash
+
+set -e
+set -u
+set -o pipefail
+
+stage=1
+stop_stage=2
+model="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+data_dir="./data/test"
+output_dir="./results"
+batch_size=64
+gpu_inference=true    # whether to perform gpu decoding
+gpuid_list="0,1"    # set gpus, e.g., gpuid_list="0,1"
+njob=4    # the number of jobs for CPU decoding, if gpu_inference=false, use CPU decoding, please set njob
+
+
+if ${gpu_inference}; then
+    nj=$(echo $gpuid_list | awk -F "," '{print NF}')
+else
+    nj=$njob
+    batch_size=1
+    gpuid_list=""
+    for JOB in $(seq ${nj}); do
+        gpuid_list=$gpuid_list"-1,"
+    done
+fi
+
+mkdir -p $output_dir/split
+split_scps=""
+for JOB in $(seq ${nj}); do
+    split_scps="$split_scps $output_dir/split/wav.$JOB.scp"
+done
+perl utils/split_scp.pl ${data_dir}/wav.scp ${split_scps}
+
+if [ $stage -le 1 ] && [ $stop_stage -ge 1 ];then
+    echo "Decoding ..."
+    gpuid_list_array=(${gpuid_list//,/ })
+    for JOB in $(seq ${nj}); do
+        {
+        id=$((JOB-1))
+        gpuid=${gpuid_list_array[$id]}
+        mkdir -p ${output_dir}/output.$JOB
+        python infer.py \
+            --model ${model} \
+            --audio_in ${output_dir}/split/wav.$JOB.scp \
+            --output_dir ${output_dir}/output.$JOB \
+            --batch_size ${batch_size} \
+            --gpuid ${gpuid}
+        }&
+    done
+    wait
+
+    mkdir -p ${output_dir}/1best_recog
+    for f in token score text; do
+        if [ -f "${output_dir}/output.1/1best_recog/${f}" ]; then
+          for i in $(seq "${nj}"); do
+              cat "${output_dir}/output.${i}/1best_recog/${f}"
+          done | sort -k1 >"${output_dir}/1best_recog/${f}"
+        fi
+    done
+fi
+
+if [ $stage -le 2 ] && [ $stop_stage -ge 2 ];then
+    echo "Computing WER ..."
+    python utils/proce_text.py ${output_dir}/1best_recog/text ${output_dir}/1best_recog/text.proc
+    python utils/proce_text.py ${data_dir}/text ${output_dir}/1best_recog/text.ref
+    python utils/compute_wer.py ${output_dir}/1best_recog/text.ref ${output_dir}/1best_recog/text.proc ${output_dir}/1best_recog/text.cer
+    tail -n 3 ${output_dir}/1best_recog/text.cer
+fi
+
+if [ $stage -le 3 ] && [ $stop_stage -ge 3 ];then
+    echo "SpeechIO TIOBE textnorm"
+    echo "$0 --> Normalizing REF text ..."
+    ./utils/textnorm_zh.py \
+        --has_key --to_upper \
+        ${data_dir}/text \
+        ${output_dir}/1best_recog/ref.txt
+
+    echo "$0 --> Normalizing HYP text ..."
+    ./utils/textnorm_zh.py \
+        --has_key --to_upper \
+        ${output_dir}/1best_recog/text.proc \
+        ${output_dir}/1best_recog/rec.txt
+    grep -v $'\t$' ${output_dir}/1best_recog/rec.txt > ${output_dir}/1best_recog/rec_non_empty.txt
+
+    echo "$0 --> computing WER/CER and alignment ..."
+    ./utils/error_rate_zh \
+        --tokenizer char \
+        --ref ${output_dir}/1best_recog/ref.txt \
+        --hyp ${output_dir}/1best_recog/rec_non_empty.txt \
+        ${output_dir}/1best_recog/DETAILS.txt | tee ${output_dir}/1best_recog/RESULTS.txt
+    rm -rf ${output_dir}/1best_recog/rec.txt ${output_dir}/1best_recog/rec_non_empty.txt
+fi
+
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/utils b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/utils
new file mode 120000
index 0000000..2ac163f
--- /dev/null
+++ b/egs_modelscope/asr/paraformer/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/utils
@@ -0,0 +1 @@
+../../../../egs/aishell/transformer/utils
\ No newline at end of file
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/README.md b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/README.md
index 1587d3d..8bf63e5 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/README.md
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/README.md
@@ -6,8 +6,9 @@
 
 - Modify finetune training related parameters in `finetune.py`
     - <strong>output_dir:</strong> # result dir
-    - <strong>data_dir:</strong> # the dataset dir needs to include files: train/wav.scp, train/text; validation/wav.scp, validation/text.
-    - <strong>batch_bins:</strong> # batch size
+    - <strong>data_dir:</strong> # the dataset dir needs to include files: `train/wav.scp`, `train/text`; `validation/wav.scp`, `validation/text`
+    - <strong>dataset_type:</strong> # for dataset larger than 1000 hours, set as `large`, otherwise set as `small`
+    - <strong>batch_bins:</strong> # batch size. For dataset_type is `small`, `batch_bins` indicates the feature frames. For dataset_type is `large`, `batch_bins` indicates the duration in ms
     - <strong>max_epoch:</strong> # number of training epoch
     - <strong>lr:</strong> # learning rate
 
@@ -20,11 +21,38 @@
 
 Or you can use the finetuned model for inference directly.
 
-- Setting parameters in `infer.py`
-    - <strong>data_dir:</strong> # the dataset dir
+- Setting parameters in `infer.sh`
+    - <strong>model:</strong> # model name on ModelScope
+    - <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
     - <strong>output_dir:</strong> # result dir
+    - <strong>batch_size:</strong> # batchsize of inference
+    - <strong>gpu_inference:</strong> # whether to perform gpu decoding, set false for cpu decoding
+    - <strong>gpuid_list:</strong> # set gpus, e.g., gpuid_list="0,1"
+    - <strong>njob:</strong> # the number of jobs for CPU decoding, if `gpu_inference`=false, use CPU decoding, please set `njob`
 
 - Then you can run the pipeline to infer with:
 ```python
-    python infer.py
+    sh infer.sh
 ```
+
+- Results
+
+The decoding results can be found in `$output_dir/1best_recog/text.cer`, which includes recognition results of each sample and the CER metric of the whole test set.
+
+### Inference using local finetuned model
+
+- Modify inference related parameters in `infer_after_finetune.py`
+    - <strong>modelscope_model_name: </strong> # model name on ModelScope
+    - <strong>output_dir:</strong> # result dir
+    - <strong>data_dir:</strong> # the dataset dir needs to include `test/wav.scp`. If `test/text` is also exists, CER will be computed
+    - <strong>decoding_model_name:</strong> # set the checkpoint name for decoding, e.g., `valid.cer_ctc.ave.pb`
+    - <strong>batch_size:</strong> # batchsize of inference  
+
+- Then you can run the pipeline to finetune with:
+```python
+    python infer_after_finetune.py
+```
+
+- Results
+
+The decoding results can be found in `$output_dir/decoding_results/text.cer`, which includes recognition results of each sample and the CER metric of the whole test set.
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py
index 0b508fb..b4f633a 100644
--- a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.py
@@ -1,101 +1,25 @@
 import os
 import shutil
-from multiprocessing import Pool
-
+import argparse
 from modelscope.pipelines import pipeline
 from modelscope.utils.constant import Tasks
 
-from funasr.utils.compute_wer import compute_wer
-
-
-def modelscope_infer_core(output_dir, split_dir, njob, idx, batch_size, ngpu, model):
-    output_dir_job = os.path.join(output_dir, "output.{}".format(idx))
-    if ngpu > 0:
-        use_gpu = 1
-        gpu_id = int(idx) - 1
-    else:
-        use_gpu = 0
-        gpu_id = -1
-    if "CUDA_VISIBLE_DEVICES" in os.environ.keys():
-        gpu_list = os.environ['CUDA_VISIBLE_DEVICES'].split(",")
-        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_list[gpu_id])
-    else:
-        os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
-    inference_pipline = pipeline(
+def modelscope_infer(args):
+    os.environ['CUDA_VISIBLE_DEVICES'] = str(args.gpuid)
+    inference_pipeline = pipeline(
         task=Tasks.auto_speech_recognition,
-        model=model,
-        output_dir=output_dir_job,
-        batch_size=batch_size,
-        ngpu=use_gpu,
+        model=args.model,
+        output_dir=args.output_dir,
+        batch_size=args.batch_size,
     )
-    audio_in = os.path.join(split_dir, "wav.{}.scp".format(idx))
-    inference_pipline(audio_in=audio_in)
-
-
-def modelscope_infer(params):
-    # prepare for multi-GPU decoding
-    ngpu = params["ngpu"]
-    njob = params["njob"]
-    batch_size = params["batch_size"]
-    output_dir = params["output_dir"]
-    model = params["model"]
-    if os.path.exists(output_dir):
-        shutil.rmtree(output_dir)
-    os.mkdir(output_dir)
-    split_dir = os.path.join(output_dir, "split")
-    os.mkdir(split_dir)
-    if ngpu > 0:
-        nj = ngpu
-    elif ngpu == 0:
-        nj = njob
-    wav_scp_file = os.path.join(params["data_dir"], "wav.scp")
-    with open(wav_scp_file) as f:
-        lines = f.readlines()
-        num_lines = len(lines)
-        num_job_lines = num_lines // nj
-    start = 0
-    for i in range(nj):
-        end = start + num_job_lines
-        file = os.path.join(split_dir, "wav.{}.scp".format(str(i + 1)))
-        with open(file, "w") as f:
-            if i == nj - 1:
-                f.writelines(lines[start:])
-            else:
-                f.writelines(lines[start:end])
-        start = end
-
-    p = Pool(nj)
-    for i in range(nj):
-        p.apply_async(modelscope_infer_core,
-                      args=(output_dir, split_dir, njob, str(i + 1), batch_size, ngpu, model))
-    p.close()
-    p.join()
-
-    # combine decoding results
-    best_recog_path = os.path.join(output_dir, "1best_recog")
-    os.mkdir(best_recog_path)
-    files = ["text", "token", "score"]
-    for file in files:
-        with open(os.path.join(best_recog_path, file), "w") as f:
-            for i in range(nj):
-                job_file = os.path.join(output_dir, "output.{}/1best_recog".format(str(i + 1)), file)
-                with open(job_file) as f_job:
-                    lines = f_job.readlines()
-                f.writelines(lines)
-
-    # If text exists, compute CER
-    text_in = os.path.join(params["data_dir"], "text")
-    if os.path.exists(text_in):
-        text_proc_file = os.path.join(best_recog_path, "token")
-        compute_wer(text_in, text_proc_file, os.path.join(best_recog_path, "text.cer"))
-
+    inference_pipeline(audio_in=args.audio_in)
 
 if __name__ == "__main__":
-    params = {}
-    params["model"] = "damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1"
-    params["data_dir"] = "./data/test"
-    params["output_dir"] = "./results"
-    params["ngpu"] = 1 # if ngpu > 0, will use gpu decoding
-    params["njob"] = 1 # if ngpu = 0, will use cpu decoding
-    params["batch_size"] = 64
-    modelscope_infer(params)
\ No newline at end of file
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--model', type=str, default="damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1")
+    parser.add_argument('--audio_in', type=str, default="./data/test")
+    parser.add_argument('--output_dir', type=str, default="./results/")
+    parser.add_argument('--batch_size', type=int, default=64)
+    parser.add_argument('--gpuid', type=str, default="0")
+    args = parser.parse_args()
+    modelscope_infer(args)
\ No newline at end of file
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.sh b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.sh
new file mode 100644
index 0000000..cdf81dc
--- /dev/null
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/infer.sh
@@ -0,0 +1,70 @@
+#!/usr/bin/env bash
+
+set -e
+set -u
+set -o pipefail
+
+stage=1
+stop_stage=2
+model="damo/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1"
+data_dir="./data/test"
+output_dir="./results"
+batch_size=64
+gpu_inference=true    # whether to perform gpu decoding
+gpuid_list="0,1"    # set gpus, e.g., gpuid_list="0,1"
+njob=4    # the number of jobs for CPU decoding, if gpu_inference=false, use CPU decoding, please set njob
+
+
+if ${gpu_inference}; then
+    nj=$(echo $gpuid_list | awk -F "," '{print NF}')
+else
+    nj=$njob
+    batch_size=1
+    gpuid_list=""
+    for JOB in $(seq ${nj}); do
+        gpuid_list=$gpuid_list"-1,"
+    done
+fi
+
+mkdir -p $output_dir/split
+split_scps=""
+for JOB in $(seq ${nj}); do
+    split_scps="$split_scps $output_dir/split/wav.$JOB.scp"
+done
+perl utils/split_scp.pl ${data_dir}/wav.scp ${split_scps}
+
+if [ $stage -le 1 ] && [ $stop_stage -ge 1 ];then
+    echo "Decoding ..."
+    gpuid_list_array=(${gpuid_list//,/ })
+    for JOB in $(seq ${nj}); do
+        {
+        id=$((JOB-1))
+        gpuid=${gpuid_list_array[$id]}
+        mkdir -p ${output_dir}/output.$JOB
+        python infer.py \
+            --model ${model} \
+            --audio_in ${output_dir}/split/wav.$JOB.scp \
+            --output_dir ${output_dir}/output.$JOB \
+            --batch_size ${batch_size} \
+            --gpuid ${gpuid}
+        }&
+    done
+    wait
+
+    mkdir -p ${output_dir}/1best_recog
+    for f in token score text; do
+        if [ -f "${output_dir}/output.1/1best_recog/${f}" ]; then
+          for i in $(seq "${nj}"); do
+              cat "${output_dir}/output.${i}/1best_recog/${f}"
+          done | sort -k1 >"${output_dir}/1best_recog/${f}"
+        fi
+    done
+fi
+
+if [ $stage -le 2 ] && [ $stop_stage -ge 2 ];then
+    echo "Computing WER ..."
+    python utils/proce_text.py ${output_dir}/1best_recog/text ${output_dir}/1best_recog/text.proc
+    python utils/proce_text.py ${data_dir}/text ${output_dir}/1best_recog/text.ref
+    python utils/compute_wer.py ${output_dir}/1best_recog/text.ref ${output_dir}/1best_recog/text.proc ${output_dir}/1best_recog/text.cer
+    tail -n 3 ${output_dir}/1best_recog/text.cer
+fi
diff --git a/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/utils b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/utils
new file mode 120000
index 0000000..2ac163f
--- /dev/null
+++ b/egs_modelscope/asr/paraformer/speech_paraformer_asr_nat-zh-cn-8k-common-vocab8358-tensorflow1/utils
@@ -0,0 +1 @@
+../../../../egs/aishell/transformer/utils
\ No newline at end of file
diff --git a/funasr/bin/punctuation_infer_vadrealtime.py b/funasr/bin/punctuation_infer_vadrealtime.py
index ea8c041..ce1cee8 100644
--- a/funasr/bin/punctuation_infer_vadrealtime.py
+++ b/funasr/bin/punctuation_infer_vadrealtime.py
@@ -226,7 +226,7 @@
     ):
         results = []
         split_size = 10
-
+        cache_in = param_dict["cache"]
         if raw_inputs != None:
             line = raw_inputs.strip()
             key = "demo"
@@ -234,34 +234,12 @@
                 item = {'key': key, 'value': ""}
                 results.append(item)
                 return results
-            result, _, cache = text2punc(line, cache)
-            item = {'key': key, 'value': result, 'cache': cache}
+            result, _, cache = text2punc(line, cache_in)
+            param_dict["cache"] = cache
+            item = {'key': key, 'value': result}
             results.append(item)
             return results
 
-        for inference_text, _, _ in data_path_and_name_and_type:
-            with open(inference_text, "r", encoding="utf-8") as fin:
-                for line in fin:
-                    line = line.strip()
-                    segs = line.split("\t")
-                    if len(segs) != 2:
-                        continue
-                    key = segs[0]
-                    if len(segs[1]) == 0:
-                        continue
-                    result, _ = text2punc(segs[1])
-                    item = {'key': key, 'value': result}
-                    results.append(item)
-        output_path = output_dir_v2 if output_dir_v2 is not None else output_dir
-        if output_path != None:
-            output_file_name = "infer.out"
-            Path(output_path).mkdir(parents=True, exist_ok=True)
-            output_file_path = (Path(output_path) / output_file_name).absolute()
-            with open(output_file_path, "w", encoding="utf-8") as fout:
-                for item_i in results:
-                    key_out = item_i["key"]
-                    value_out = item_i["value"]
-                    fout.write(f"{key_out}\t{value_out}\n")
         return results
 
     return _forward
diff --git a/funasr/bin/vad_inference_online.py b/funasr/bin/vad_inference_online.py
index faee1fc..dadfd8c 100644
--- a/funasr/bin/vad_inference_online.py
+++ b/funasr/bin/vad_inference_online.py
@@ -30,14 +30,7 @@
 from funasr.models.frontend.wav_frontend import WavFrontend
 from funasr.bin.vad_inference import Speech2VadSegment
 
-header_colors = '\033[95m'
-end_colors = '\033[0m'
 
-global_asr_language: str = 'zh-cn'
-global_sample_rate: Union[int, Dict[Any, int]] = {
-    'audio_fs': 16000,
-    'model_fs': 16000
-}
 
 
 class Speech2VadSegmentOnline(Speech2VadSegment):
diff --git a/funasr/export/export_model.py b/funasr/export/export_model.py
index f6ba616..b1161cb 100644
--- a/funasr/export/export_model.py
+++ b/funasr/export/export_model.py
@@ -14,7 +14,7 @@
 # torch_version = float(".".join(torch.__version__.split(".")[:2]))
 # assert torch_version > 1.9
 
-class ASRModelExportParaformer:
+class ModelExport:
     def __init__(
         self,
         cache_dir: Union[Path, str] = None,
@@ -240,7 +240,7 @@
     parser.add_argument('--calib_num', type=int, default=200, help='calib max num')
     args = parser.parse_args()
 
-    export_model = ASRModelExportParaformer(
+    export_model = ModelExport(
         cache_dir=args.export_dir,
         onnx=args.type == 'onnx',
         quant=args.quantize,
diff --git a/funasr/runtime/onnxruntime/readme.md b/funasr/runtime/onnxruntime/readme.md
index 16d9dc7..317376f 100644
--- a/funasr/runtime/onnxruntime/readme.md
+++ b/funasr/runtime/onnxruntime/readme.md
@@ -42,7 +42,7 @@
 瀵煎嚭onnx妯″瀷锛孾璇﹁](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/export)锛屽弬鑰冪ず渚嬶紝浠巑odelscope涓ā鍨嬪鍑猴細
 
 ```shell
-python -m funasr.export.export_model --model-name damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type onnx --quantize False
+python -m funasr.export.export_model --model-name damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type onnx --quantize True
 ```
 
 ## Building Guidance for Linux/Unix
diff --git a/funasr/runtime/python/benchmark_onnx.md b/funasr/runtime/python/benchmark_onnx.md
index ca7556b..533798a 100644
--- a/funasr/runtime/python/benchmark_onnx.md
+++ b/funasr/runtime/python/benchmark_onnx.md
@@ -25,6 +25,16 @@
 
 ## [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) 
 
+Number of Parameter: 220M 
+
+Storage size: 880MB
+
+Storage size after int8-quant: 237MB
+
+CER: 1.95%
+
+CER after int8-quant: 1.95%
+
  ### Intel(R) Xeon(R) Platinum 8369B CPU @ 2.90GHz   16core-32processor    with avx512_vnni
 
 | concurrent-tasks | processing time(s) |   RTF   | Speedup Rate |
@@ -73,6 +83,16 @@
 
 ## [Paraformer](https://modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8358-tensorflow1/summary)
 
+Number of Parameter: 68M 
+
+Storage size: 275MB
+
+Storage size after int8-quant: 81MB
+
+CER: 3.73%
+
+CER after int8-quant: 3.78%
+
  ### Intel(R) Xeon(R) Platinum 8369B CPU @ 2.90GHz   16core-32processor    with avx512_vnni
 
 | concurrent-tasks | processing time(s) |  RTF   | Speedup Rate |
diff --git a/funasr/runtime/python/grpc/Readme.md b/funasr/runtime/python/grpc/Readme.md
index e020007..2df666d 100644
--- a/funasr/runtime/python/grpc/Readme.md
+++ b/funasr/runtime/python/grpc/Readme.md
@@ -26,23 +26,28 @@
 
 Step 1-2) Optional, Prepare server onnxruntime environment (on server). 
 
-Install [`rapid_paraformer`](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/python/onnxruntime).
+Install [`onnx_paraformer`](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/python/onnxruntime).
 
-- Build the rapid_paraformer `whl`
+- Build the onnx_paraformer `whl`
 ```
 git clone https://github.com/alibaba/FunASR.git && cd FunASR
 cd funasr/runtime/python/onnxruntime/rapid_paraformer
-python setup.py bdist_wheel
+python setup.py build
+python setup.py install
 ```
 
-- Install the build `whl`
-```
-pip install dist/rapid_paraformer-0.0.1-py3-none-any.whl
-```
+[//]: # ()
+[//]: # (- Install the build `whl`)
+
+[//]: # (```)
+
+[//]: # (pip install dist/rapid_paraformer-0.0.1-py3-none-any.whl)
+
+[//]: # (```)
 
 Export the model, more details ref to [export docs](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/python/onnxruntime).
-```
-python -m funasr.export.export_model 'damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch' "./export" true
+```shell
+python -m funasr.export.export_model --model-name damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type onnx --quantize True
 ```
 
 Step 2) Optional, generate protobuf file (run on server, the two generated pb files are both used for server and client).
diff --git a/funasr/runtime/python/utils/compute_wer.py b/funasr/runtime/python/utils/compute_wer.py
new file mode 100755
index 0000000..349a3f6
--- /dev/null
+++ b/funasr/runtime/python/utils/compute_wer.py
@@ -0,0 +1,157 @@
+import os
+import numpy as np
+import sys
+
+def compute_wer(ref_file,
+                hyp_file,
+                cer_detail_file):
+    rst = {
+        'Wrd': 0,
+        'Corr': 0,
+        'Ins': 0,
+        'Del': 0,
+        'Sub': 0,
+        'Snt': 0,
+        'Err': 0.0,
+        'S.Err': 0.0,
+        'wrong_words': 0,
+        'wrong_sentences': 0
+    }
+
+    hyp_dict = {}
+    ref_dict = {}
+    with open(hyp_file, 'r') as hyp_reader:
+        for line in hyp_reader:
+            key = line.strip().split()[0]
+            value = line.strip().split()[1:]
+            hyp_dict[key] = value
+    with open(ref_file, 'r') as ref_reader:
+        for line in ref_reader:
+            key = line.strip().split()[0]
+            value = line.strip().split()[1:]
+            ref_dict[key] = value
+
+    cer_detail_writer = open(cer_detail_file, 'w')
+    for hyp_key in hyp_dict:
+        if hyp_key in ref_dict:
+           out_item = compute_wer_by_line(hyp_dict[hyp_key], ref_dict[hyp_key])
+           rst['Wrd'] += out_item['nwords']
+           rst['Corr'] += out_item['cor']
+           rst['wrong_words'] += out_item['wrong']
+           rst['Ins'] += out_item['ins']
+           rst['Del'] += out_item['del']
+           rst['Sub'] += out_item['sub']
+           rst['Snt'] += 1
+           if out_item['wrong'] > 0:
+               rst['wrong_sentences'] += 1
+           cer_detail_writer.write(hyp_key + print_cer_detail(out_item) + '\n')
+           cer_detail_writer.write("ref:" + '\t' + "".join(ref_dict[hyp_key]) + '\n')
+           cer_detail_writer.write("hyp:" + '\t' + "".join(hyp_dict[hyp_key]) + '\n')
+
+    if rst['Wrd'] > 0:
+        rst['Err'] = round(rst['wrong_words'] * 100 / rst['Wrd'], 2)
+    if rst['Snt'] > 0:
+        rst['S.Err'] = round(rst['wrong_sentences'] * 100 / rst['Snt'], 2)
+
+    cer_detail_writer.write('\n')
+    cer_detail_writer.write("%WER " + str(rst['Err']) + " [ " + str(rst['wrong_words'])+ " / " + str(rst['Wrd']) +
+                            ", " + str(rst['Ins']) + " ins, " + str(rst['Del']) + " del, " + str(rst['Sub']) + " sub ]" + '\n')
+    cer_detail_writer.write("%SER " + str(rst['S.Err']) + " [ " + str(rst['wrong_sentences']) + " / " + str(rst['Snt']) + " ]" + '\n')
+    cer_detail_writer.write("Scored " + str(len(hyp_dict)) + " sentences, " + str(len(hyp_dict) - rst['Snt']) + " not present in hyp." + '\n')
+
+     
+def compute_wer_by_line(hyp,
+                        ref):
+    hyp = list(map(lambda x: x.lower(), hyp))
+    ref = list(map(lambda x: x.lower(), ref))
+
+    len_hyp = len(hyp)
+    len_ref = len(ref)
+
+    cost_matrix = np.zeros((len_hyp + 1, len_ref + 1), dtype=np.int16)
+
+    ops_matrix = np.zeros((len_hyp + 1, len_ref + 1), dtype=np.int8)
+
+    for i in range(len_hyp + 1):
+        cost_matrix[i][0] = i
+    for j in range(len_ref + 1):
+        cost_matrix[0][j] = j
+
+    for i in range(1, len_hyp + 1):
+        for j in range(1, len_ref + 1):
+            if hyp[i - 1] == ref[j - 1]:
+                cost_matrix[i][j] = cost_matrix[i - 1][j - 1]
+            else:
+                substitution = cost_matrix[i - 1][j - 1] + 1
+                insertion = cost_matrix[i - 1][j] + 1
+                deletion = cost_matrix[i][j - 1] + 1
+
+                compare_val = [substitution, insertion, deletion]
+
+                min_val = min(compare_val)
+                operation_idx = compare_val.index(min_val) + 1
+                cost_matrix[i][j] = min_val
+                ops_matrix[i][j] = operation_idx
+
+    match_idx = []
+    i = len_hyp
+    j = len_ref
+    rst = {
+        'nwords': len_ref,
+        'cor': 0,
+        'wrong': 0,
+        'ins': 0,
+        'del': 0,
+        'sub': 0
+    }
+    while i >= 0 or j >= 0:
+        i_idx = max(0, i)
+        j_idx = max(0, j)
+
+        if ops_matrix[i_idx][j_idx] == 0:  # correct
+            if i - 1 >= 0 and j - 1 >= 0:
+                match_idx.append((j - 1, i - 1))
+                rst['cor'] += 1
+
+            i -= 1
+            j -= 1
+
+        elif ops_matrix[i_idx][j_idx] == 2:  # insert
+            i -= 1
+            rst['ins'] += 1
+
+        elif ops_matrix[i_idx][j_idx] == 3:  # delete
+            j -= 1
+            rst['del'] += 1
+
+        elif ops_matrix[i_idx][j_idx] == 1:  # substitute
+            i -= 1
+            j -= 1
+            rst['sub'] += 1
+
+        if i < 0 and j >= 0:
+            rst['del'] += 1
+        elif j < 0 and i >= 0:
+            rst['ins'] += 1
+
+    match_idx.reverse()
+    wrong_cnt = cost_matrix[len_hyp][len_ref]
+    rst['wrong'] = wrong_cnt
+
+    return rst
+
+def print_cer_detail(rst):
+    return ("(" + "nwords=" + str(rst['nwords']) + ",cor=" + str(rst['cor'])
+            + ",ins=" + str(rst['ins']) + ",del=" + str(rst['del']) + ",sub="
+            + str(rst['sub']) + ") corr:" + '{:.2%}'.format(rst['cor']/rst['nwords'])
+            + ",cer:" + '{:.2%}'.format(rst['wrong']/rst['nwords']))
+
+if __name__ == '__main__':
+    if len(sys.argv) != 4:
+        print("usage : python compute-wer.py test.ref test.hyp test.wer")
+        sys.exit(0)
+
+    ref_file = sys.argv[1]
+    hyp_file = sys.argv[2]
+    cer_detail_file = sys.argv[3]
+    compute_wer(ref_file, hyp_file, cer_detail_file)
diff --git a/funasr/runtime/python/utils/infer.py b/funasr/runtime/python/utils/infer.py
new file mode 100644
index 0000000..f5b2233
--- /dev/null
+++ b/funasr/runtime/python/utils/infer.py
@@ -0,0 +1,48 @@
+import os
+import time
+import sys
+import librosa
+from funasr.utils.types import str2bool
+
+import argparse
+parser = argparse.ArgumentParser()
+parser.add_argument('--model_dir', type=str, required=True)
+parser.add_argument('--backend', type=str, default='onnx', help='["onnx", "torch"]')
+parser.add_argument('--wav_file', type=str, default=None, help='amp fallback number')
+parser.add_argument('--quantize', type=str2bool, default=False, help='quantized model')
+parser.add_argument('--intra_op_num_threads', type=int, default=1, help='intra_op_num_threads for onnx')
+parser.add_argument('--output_dir', type=str, default=None, help='amp fallback number')
+args = parser.parse_args()
+
+
+from funasr.runtime.python.libtorch.torch_paraformer import Paraformer
+if args.backend == "onnx":
+	from funasr.runtime.python.onnxruntime.rapid_paraformer import Paraformer
+	
+model = Paraformer(args.model_dir, batch_size=1, quantize=args.quantize, intra_op_num_threads=args.intra_op_num_threads)
+
+wav_file_f = open(args.wav_file, 'r')
+wav_files = wav_file_f.readlines()
+
+output_dir = args.output_dir
+if not os.path.exists(output_dir):
+	os.makedirs(output_dir)
+if os.name == 'nt':   # Windows
+	newline = '\r\n'
+else:   # Linux Mac
+	newline = '\n'
+text_f = open(os.path.join(output_dir, "text"), "w", newline=newline)
+token_f = open(os.path.join(output_dir, "token"), "w", newline=newline)
+
+for i, wav_path_i in enumerate(wav_files):
+	wav_name, wav_path = wav_path_i.strip().split()
+	result = model(wav_path)
+	text_i = "{} {}\n".format(wav_name, result[0]['preds'][0])
+	token_i = "{} {}\n".format(wav_name, result[0]['preds'][1])
+	text_f.write(text_i)
+	text_f.flush()
+	token_f.write(token_i)
+	token_f.flush()
+text_f.close()
+token_f.close()
+	
diff --git a/funasr/runtime/python/utils/infer.sh b/funasr/runtime/python/utils/infer.sh
new file mode 100644
index 0000000..c9a1b77
--- /dev/null
+++ b/funasr/runtime/python/utils/infer.sh
@@ -0,0 +1,74 @@
+
+split_scps_tool=split_scp.pl
+inference_tool=infer.py
+proce_text_tool=proce_text.py
+compute_wer_tool=compute_wer.py
+
+nj=32
+stage=0
+stop_stage=2
+
+scp="/nfs/haoneng.lhn/funasr_data/aishell-1/data/test/wav.scp"
+label_text="/nfs/haoneng.lhn/funasr_data/aishell-1/data/test/text"
+export_root="/nfs/zhifu.gzf/export"
+
+
+#:<<!
+model_name="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+backend="onnx" # "torch"
+quantize='true' # 'False'
+fallback_op_num_torch=20
+tag=${model_name}/${backend}_quantize_${quantize}_${fallback_op_num_torch}
+!
+
+output_dir=${export_root}/logs/${tag}/split$nj
+mkdir -p ${output_dir}
+echo ${output_dir}
+
+
+if [ $stage -le 0 ] && [ $stop_stage -ge 0 ];then
+
+    python -m funasr.export.export_model --model-name ${model_name} --export-dir ${export_root} --type ${backend} --quantize ${quantize} --audio_in ${scp} --fallback-num ${fallback_op_num_torch}
+
+fi
+
+
+if [ $stage -le 1 ] && [ $stop_stage -ge 1 ];then
+
+  model_dir=${export_root}/${model_name}
+  split_scps=""
+  for JOB in $(seq ${nj}); do
+      split_scps="$split_scps $output_dir/wav.$JOB.scp"
+  done
+
+  perl ${split_scps_tool} $scp ${split_scps}
+
+
+  for JOB in $(seq ${nj}); do
+    {
+      core_id=`expr $JOB - 1`
+      taskset -c ${core_id} python ${inference_tool} --backend ${backend} --model_dir ${model_dir} --wav_file ${output_dir}/wav.$JOB.scp --quantize ${quantize} --output_dir ${output_dir}/${JOB} &> ${output_dir}/log.$JOB.txt
+    }&
+
+  done
+  wait
+
+  mkdir -p ${output_dir}/1best_recog
+  for f in token text; do
+      if [ -f "${output_dir}/1/${f}" ]; then
+        for JOB in $(seq "${nj}"); do
+            cat "${output_dir}/${JOB}/${f}"
+        done | sort -k1 >"${output_dir}/1best_recog/${f}"
+      fi
+  done
+
+fi
+
+if [ $stage -le 2 ] && [ $stop_stage -ge 2 ];then
+    echo "Computing WER ..."
+    python ${proce_text_tool} ${output_dir}/1best_recog/text ${output_dir}/1best_recog/text.proc
+    python ${proce_text_tool} ${label_text} ${output_dir}/1best_recog/text.ref
+    python ${compute_wer_tool} ${output_dir}/1best_recog/text.ref ${output_dir}/1best_recog/text.proc ${output_dir}/1best_recog/text.cer
+    tail -n 3 ${output_dir}/1best_recog/text.cer
+fi
+
diff --git a/funasr/runtime/python/utils/proce_text.py b/funasr/runtime/python/utils/proce_text.py
new file mode 100755
index 0000000..9e517a4
--- /dev/null
+++ b/funasr/runtime/python/utils/proce_text.py
@@ -0,0 +1,31 @@
+
+import sys
+import re
+
+in_f = sys.argv[1]
+out_f = sys.argv[2]
+
+
+with open(in_f, "r", encoding="utf-8") as f:
+  lines = f.readlines()
+
+with open(out_f, "w", encoding="utf-8") as f:
+  for line in lines:
+    outs = line.strip().split(" ", 1)
+    if len(outs) == 2:
+      idx, text = outs
+      text = re.sub("</s>", "", text)
+      text = re.sub("<s>", "", text)
+      text = re.sub("@@", "", text)
+      text = re.sub("@", "", text)
+      text = re.sub("<unk>", "", text)
+      text = re.sub(" ", "", text)
+      text = text.lower()
+    else:
+      idx = outs[0]
+      text = " "
+
+    text = [x for x in text]
+    text = " ".join(text)
+    out = "{} {}\n".format(idx, text)
+    f.write(out)
diff --git a/funasr/runtime/python/websocket/ASR_client.py b/funasr/runtime/python/websocket/ASR_client.py
new file mode 100644
index 0000000..8010b18
--- /dev/null
+++ b/funasr/runtime/python/websocket/ASR_client.py
@@ -0,0 +1,95 @@
+import pyaudio
+# import websocket #鍖哄埆鏈嶅姟绔繖閲屾槸 websocket-client搴�
+import time
+import websockets
+import asyncio
+from queue import Queue
+# import threading
+import argparse
+
+parser = argparse.ArgumentParser()
+parser.add_argument("--host",
+                    type=str,
+                    default="localhost",
+                    required=False,
+                    help="host ip, localhost, 0.0.0.0")
+parser.add_argument("--port",
+                    type=int,
+                    default=10095,
+                    required=False,
+                    help="grpc server port")
+parser.add_argument("--chunk_size",
+                    type=int,
+                    default=300,
+                    help="ms")
+
+args = parser.parse_args()
+
+voices = Queue()
+async def ws_client():
+    global ws # 瀹氫箟涓�涓叏灞�鍙橀噺ws锛岀敤浜庝繚瀛榳ebsocket杩炴帴瀵硅薄
+    # uri = "ws://11.167.134.197:8899"
+    uri = "ws://{}:{}".format(args.host, args.port)
+    ws = await websockets.connect(uri, subprotocols=["binary"]) # 鍒涘缓涓�涓暱杩炴帴
+    ws.max_size = 1024 * 1024 * 20
+    print("connected ws server")
+    
+async def send(data):
+    global ws # 寮曠敤鍏ㄥ眬鍙橀噺ws
+    try:
+        await ws.send(data) # 閫氳繃ws瀵硅薄鍙戦�佹暟鎹�
+    except Exception as e:
+        print('Exception occurred:', e)
+    
+
+
+asyncio.get_event_loop().run_until_complete(ws_client()) # 鍚姩鍗忕▼
+
+
+# 鍏朵粬鍑芥暟鍙互閫氳繃璋冪敤send(data)鏉ュ彂閫佹暟鎹紝渚嬪锛�
+async def test():
+    #print("2")
+    global voices
+    FORMAT = pyaudio.paInt16
+    CHANNELS = 1
+    RATE = 16000
+    CHUNK = int(RATE / 1000 * args.chunk_size)
+
+    p = pyaudio.PyAudio()
+
+    stream = p.open(format=FORMAT,
+                    channels=CHANNELS,
+                    rate=RATE,
+                    input=True,
+                    frames_per_buffer=CHUNK)
+
+    while True:
+
+        data = stream.read(CHUNK)
+        
+        voices.put(data)
+        #print(voices.qsize())
+        await asyncio.sleep(0.01)
+    
+      
+
+
+
+async def ws_send():
+    global voices
+    print("started to sending data!")
+    while True:
+        while not voices.empty():
+            data = voices.get()
+            voices.task_done()
+            await send(data)
+            await asyncio.sleep(0.01)
+        await asyncio.sleep(0.01)
+
+async def main():
+    task = asyncio.create_task(test()) # 鍒涘缓涓�涓悗鍙颁换鍔�
+    task2 = asyncio.create_task(ws_send()) # 鍒涘缓涓�涓悗鍙颁换鍔�
+     
+    await asyncio.gather(task, task2)
+
+asyncio.run(main())
diff --git a/funasr/runtime/python/websocket/ASR_server.py b/funasr/runtime/python/websocket/ASR_server.py
new file mode 100644
index 0000000..20de20a
--- /dev/null
+++ b/funasr/runtime/python/websocket/ASR_server.py
@@ -0,0 +1,191 @@
+import asyncio
+import websockets
+import time
+from queue import Queue
+import threading
+import argparse
+
+from modelscope.pipelines import pipeline
+from modelscope.utils.constant import Tasks
+from modelscope.utils.logger import get_logger
+import logging
+
+logger = get_logger(log_level=logging.CRITICAL)
+logger.setLevel(logging.CRITICAL)
+
+
+parser = argparse.ArgumentParser()
+parser.add_argument("--host",
+                    type=str,
+                    default="0.0.0.0",
+                    required=False,
+                    help="host ip, localhost, 0.0.0.0")
+parser.add_argument("--port",
+                    type=int,
+                    default=10095,
+                    required=False,
+                    help="grpc server port")
+parser.add_argument("--asr_model",
+                    type=str,
+                    default="damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch",
+                    help="model from modelscope")
+parser.add_argument("--vad_model",
+                    type=str,
+                    default="damo/speech_fsmn_vad_zh-cn-16k-common-pytorch",
+                    help="model from modelscope")
+
+parser.add_argument("--punc_model",
+                    type=str,
+                    default="damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727",
+                    help="model from modelscope")
+parser.add_argument("--ngpu",
+                    type=int,
+                    default=1,
+                    help="0 for cpu, 1 for gpu")
+
+args = parser.parse_args()
+
+print("model loading")
+voices = Queue()
+speek = Queue()
+
+# vad
+inference_pipeline_vad = pipeline(
+    task=Tasks.voice_activity_detection,
+    model=args.vad_model,
+    model_revision=None,
+    output_dir=None,
+    batch_size=1,
+    mode='online',
+    ngpu=args.ngpu,
+)
+param_dict_vad = {'in_cache': dict(), "is_final": False}
+  
+# asr
+param_dict_asr = {}
+# param_dict["hotword"] = "灏忎簲 灏忎簲鏈�"  # 璁剧疆鐑瘝锛岀敤绌烘牸闅斿紑
+inference_pipeline_asr = pipeline(
+    task=Tasks.auto_speech_recognition,
+    model=args.asr_model,
+    param_dict=param_dict_asr,
+    ngpu=args.ngpu,
+)
+
+param_dict_punc = {'cache': list()}
+inference_pipeline_punc = pipeline(
+    task=Tasks.punctuation,
+    model=args.punc_model,
+    model_revision=None,
+    ngpu=args.ngpu,
+)
+
+print("model loaded")
+
+
+
+async def ws_serve(websocket, path):
+    global voices
+    try:
+        async for message in websocket:
+            voices.put(message)
+            #print("put")
+    except websockets.exceptions.ConnectionClosedError as e:
+        print('Connection closed with exception:', e)
+    except Exception as e:
+        print('Exception occurred:', e)
+
+start_server = websockets.serve(ws_serve, args.host, args.port, subprotocols=["binary"], ping_interval=None)
+
+
+def vad(data):  # 鎺ㄧ悊
+    global vad_pipline, param_dict_vad
+    #print(type(data))
+    # print(param_dict_vad)
+    segments_result = inference_pipeline_vad(audio_in=data, param_dict=param_dict_vad)
+    # print(segments_result)
+    # print(param_dict_vad)
+    speech_start = False
+    speech_end = False
+    
+    if len(segments_result) == 0 or len(segments_result["text"]) > 1:
+        return speech_start, speech_end
+    if segments_result["text"][0][0] != -1:
+        speech_start = True
+    if segments_result["text"][0][1] != -1:
+        speech_end = True
+    return speech_start, speech_end
+
+def asr():  # 鎺ㄧ悊
+    global inference_pipeline2
+    global speek
+    while True:
+        while not speek.empty():
+            audio_in = speek.get()
+            speek.task_done()
+            rec_result = inference_pipeline_asr(audio_in=audio_in)
+            rec_result_punc = inference_pipeline_punc(text_in=rec_result['text'], param_dict=param_dict_punc)
+            print(rec_result_punc)
+            time.sleep(0.1)
+        time.sleep(0.1)    
+
+
+def main():  # 鎺ㄧ悊
+    frames = []  # 瀛樺偍鎵�鏈夌殑甯ф暟鎹�
+    buffer = []  # 瀛樺偍缂撳瓨涓殑甯ф暟鎹紙鏈�澶氫袱涓墖娈碉級
+    # silence_count = 0  # 缁熻杩炵画闈欓煶鐨勬鏁�
+    # speech_detected = False  # 鏍囪鏄惁妫�娴嬪埌璇煶
+    RECORD_NUM = 0
+    global voices 
+    global speek
+    speech_start, speech_end = False, False
+    while True:
+        while not voices.empty():
+            
+            data = voices.get()
+            #print("闃熷垪鎺掗槦鏁�",voices.qsize())
+            voices.task_done()
+            buffer.append(data)
+            if len(buffer) > 2:
+                buffer.pop(0)  # 濡傛灉缂撳瓨瓒呰繃涓や釜鐗囨锛屽垯鍒犻櫎鏈�鏃╃殑涓�涓�
+            
+            if speech_start:
+                frames.append(data)
+                RECORD_NUM += 1
+            speech_start_i, speech_end_i = vad(data)
+            # print(speech_start_i, speech_end_i)
+            if speech_start_i:
+                speech_start = speech_start_i
+                # if not speech_detected:
+                # print("妫�娴嬪埌浜哄０...")
+                # speech_detected = True  # 鏍囪涓烘娴嬪埌璇煶
+                frames = []
+                frames.extend(buffer)  # 鎶婁箣鍓�2涓闊虫暟鎹揩鍔犲叆
+                # silence_count = 0  # 閲嶇疆闈欓煶娆℃暟
+            if speech_end_i or RECORD_NUM > 300:
+                # silence_count += 1  # 澧炲姞闈欓煶娆℃暟
+                # speech_end = speech_end_i
+                speech_start = False
+                # if RECORD_NUM > 300: #杩欓噷 50 鍙牴鎹渶姹傛敼涓哄悎閫傜殑鏁版嵁蹇暟閲�
+                # print("璇磋瘽缁撴潫鎴栬�呰秴杩囪缃渶闀挎椂闂�...")
+                audio_in = b"".join(frames)
+                #asrt = threading.Thread(target=asr,args=(audio_in,))
+                #asrt.start()
+                speek.put(audio_in)
+                #rec_result = inference_pipeline2(audio_in=audio_in)  # ASR 妯″瀷閲岃窇涓�璺�
+                frames = []  # 娓呯┖鎵�鏈夌殑甯ф暟鎹�
+                buffer = []  # 娓呯┖缂撳瓨涓殑甯ф暟鎹紙鏈�澶氫袱涓墖娈碉級
+                # silence_count = 0  # 缁熻杩炵画闈欓煶鐨勬鏁版竻闆�
+                # speech_detected = False  # 鏍囪鏄惁妫�娴嬪埌璇煶
+                RECORD_NUM = 0
+            time.sleep(0.01)
+        time.sleep(0.01)
+            
+
+
+s = threading.Thread(target=main)
+s.start()
+s = threading.Thread(target=asr)
+s.start()
+
+asyncio.get_event_loop().run_until_complete(start_server)
+asyncio.get_event_loop().run_forever()
\ No newline at end of file
diff --git a/funasr/runtime/python/websocket/README.md b/funasr/runtime/python/websocket/README.md
new file mode 100644
index 0000000..2c0dec1
--- /dev/null
+++ b/funasr/runtime/python/websocket/README.md
@@ -0,0 +1,46 @@
+# Using funasr with websocket
+We can send streaming audio data to server in real-time with grpc client every 300 ms e.g., and get transcribed text when stop speaking.
+The audio data is in streaming, the asr inference process is in offline.
+
+# Steps
+
+## For the Server
+
+Install the modelscope and funasr
+
+```shell
+pip install "modelscope[audio_asr]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
+git clone https://github.com/alibaba/FunASR.git && cd FunASR
+pip install --editable ./
+```
+
+Install the requirements for server
+
+```shell
+cd funasr/runtime/python/websocket
+pip install -r requirements_server.txt
+```
+
+Start server
+
+```shell
+python ASR_server.py --host "0.0.0.0" --port 10095 --asr_model "damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch"
+```
+
+## For the client
+
+Install the requirements for client
+```shell
+git clone https://github.com/alibaba/FunASR.git && cd FunASR
+cd funasr/runtime/python/websocket
+pip install -r requirements_client.txt
+```
+
+Start client
+
+```shell
+python ASR_client.py --host "127.0.0.1" --port 10095 --chunk_size 300
+```
+
+## Acknowledge
+1. We acknowledge [cgisky1980](https://github.com/cgisky1980/FunASR) for contributing the websocket service.
diff --git a/funasr/runtime/python/websocket/requirements_client.txt b/funasr/runtime/python/websocket/requirements_client.txt
new file mode 100644
index 0000000..9498d6d
--- /dev/null
+++ b/funasr/runtime/python/websocket/requirements_client.txt
@@ -0,0 +1,2 @@
+websockets
+pyaudio
\ No newline at end of file
diff --git a/funasr/runtime/python/websocket/requirements_server.txt b/funasr/runtime/python/websocket/requirements_server.txt
new file mode 100644
index 0000000..14774b4
--- /dev/null
+++ b/funasr/runtime/python/websocket/requirements_server.txt
@@ -0,0 +1 @@
+websockets
diff --git a/funasr/tasks/abs_task.py b/funasr/tasks/abs_task.py
index 3f20b4f..c8e408b 100644
--- a/funasr/tasks/abs_task.py
+++ b/funasr/tasks/abs_task.py
@@ -1193,12 +1193,18 @@
             # logging.basicConfig() is invoked in main_worker() instead of main()
             # because it can be invoked only once in a process.
             # FIXME(kamo): Should we use logging.getLogger()?
+            # BUGFIX: Remove previous handlers and reset log level
+            for handler in logging.root.handlers[:]:
+                logging.root.removeHandler(handler)
             logging.basicConfig(
                 level=args.log_level,
                 format=f"[{os.uname()[1].split('.')[0]}]"
                        f" %(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s",
             )
         else:
+            # BUGFIX: Remove previous handlers and reset log level
+            for handler in logging.root.handlers[:]:
+                logging.root.removeHandler(handler)
             # Suppress logging if RANK != 0
             logging.basicConfig(
                 level="ERROR",

--
Gitblit v1.9.1