docs

funasr/runtime/docs/SDK_tutorial_cn.md

@@ -224,13 +224,13 @@ sudo bash funasr-runtime-deploy.sh restart
 
 #### 替换模型并重启FunASR服务
 
-替换正在使用的模型，并重新启动FunASR服务。模型需为ModelScope中的ASR/VAD/PUNC模型。
+替换正在使用的模型，并重新启动FunASR服务。模型需为ModelScope中的ASR/VAD/PUNC模型，或者从ModelScope中模型finetune后的模型。
 
 ```shell
-sudo bash scripts/funasr-runtime-deploy.sh update model <model ID in ModelScope>
+sudo bash funasr-runtime-deploy.sh update model <model ID>
 
 e.g
-sudo bash scripts/funasr-runtime-deploy.sh update model damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
+sudo bash funasr-runtime-deploy.sh update model damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
 ```
 
 ### 测试与使用离线文件转写服务

funasr/runtime/python/libtorch/setup.py

@@ -25,10 +25,13 @@ setuptools.setup(
     long_description=get_readme(),
     long_description_content_type='text/markdown',
     include_package_data=True,
-    install_requires=["librosa", "onnxruntime>=1.7.0",
-                      "scipy", "numpy>=1.19.3",
-                      "typeguard", "kaldi-native-fbank",
-                      "PyYAML>=5.1.2", "torch-quant >= 0.4.0"],
+    install_requires=["librosa",
+                      "onnxruntime>=1.7.0",
+                      "scipy",
+                      "numpy>=1.19.3",
+                      "kaldi-native-fbank",
+                      "PyYAML>=5.1.2",
+                      "torch-quant >= 0.4.0"],
     packages=find_packages(include=["torch_paraformer*"]),
     keywords=[
         'funasr, paraformer, funasr_torch'

funasr/runtime/python/onnxruntime/setup.py

@@ -31,7 +31,6 @@ setuptools.setup(
                       "onnxruntime>=1.7.0",
                       "scipy",
                       "numpy>=1.19.3",
-                      "typeguard==2.13.3",
                       "kaldi-native-fbank",
                       "PyYAML>=5.1.2",
                       "funasr",

funasr/runtime/readme.md

@@ -19,7 +19,7 @@ To meet the needs of different users, we have prepared different tutorials with
 
 ### Technical Principles
 
-The technical principles and documentation behind FunASR explain the underlying technology, recognition accuracy, computational efficiency, and core advantages of the framework, including convenience, high precision, high efficiency, and support for long audio chains. For detailed information, please refer to the documentation available by [docs](). 
+The technical principles and documentation behind FunASR explain the underlying technology, recognition accuracy, computational efficiency, and core advantages of the framework, including convenience, high precision, high efficiency, and support for long audio chains. For detailed information, please refer to the documentation available by [docs](https://mp.weixin.qq.com/s?__biz=MzA3MTQ0NTUyMw==&tempkey=MTIyNF84d05USjMxSEpPdk5GZXBJUFNJNzY0bU1DTkxhV19mcWY4MTNWQTJSYXhUaFgxOWFHZTZKR0JzWC1JRmRCdUxCX2NoQXg0TzFpNmVJX2R1WjdrcC02N2FEcUc3MDhzVVhpNWQ5clU4QUdqNFdkdjFYb18xRjlZMmc5c3RDOTl0U0NiRkJLb05ZZ0RmRlVkVjFCZnpXNWFBVlRhbXVtdWs4bUMwSHZnfn4%3D&chksm=1f2c3254285bbb42bc8f76a82e9c5211518a0bb1ff8c357d085c1b78f675ef2311f3be6e282c#rd). 
 
 ### Deployment Tutorial
 

funasr/runtime/readme_cn.md

@@ -20,7 +20,7 @@ SDK 支持以下几种服务部署：
 
 ### 技术原理揭秘
 
-文档介绍了背后技术原理，识别准确率，计算效率等，以及核心优势介绍：便捷、高精度、高效率、长音频链路，详细文档参考（[点击此处]()）
+文档介绍了背后技术原理，识别准确率，计算效率等，以及核心优势介绍：便捷、高精度、高效率、长音频链路，详细文档参考（[点击此处](https://mp.weixin.qq.com/s?__biz=MzA3MTQ0NTUyMw==&tempkey=MTIyNF84d05USjMxSEpPdk5GZXBJUFNJNzY0bU1DTkxhV19mcWY4MTNWQTJSYXhUaFgxOWFHZTZKR0JzWC1JRmRCdUxCX2NoQXg0TzFpNmVJX2R1WjdrcC02N2FEcUc3MDhzVVhpNWQ5clU4QUdqNFdkdjFYb18xRjlZMmc5c3RDOTl0U0NiRkJLb05ZZ0RmRlVkVjFCZnpXNWFBVlRhbXVtdWs4bUMwSHZnfn4%3D&chksm=1f2c3254285bbb42bc8f76a82e9c5211518a0bb1ff8c357d085c1b78f675ef2311f3be6e282c#rd)）
 
 ### 便捷部署教程
 

setup.py

@@ -11,7 +11,6 @@ from setuptools import setup
 requirements = {
     "install": [
         "setuptools>=38.5.1",
-        "typeguard>=3.0.1",
         "humanfriendly",
         "scipy>=1.4.1",
         "librosa",