docs

funasr/export/README.md

@@ -5,7 +5,7 @@
 
 The installation is the same as [funasr](https://github.com/alibaba-damo-academy/FunASR/blob/main/README.md#installation)
 ```shell
-pip3 install torch torchaudio
+# pip3 install torch torchaudio
 pip install -U modelscope funasr
 # For the users in China, you could install with the command:
 # pip install -U modelscope funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple
@@ -13,7 +13,7 @@ pip install -U modelscope funasr
 ### Install the quantization tools
 ```shell
 pip install torch-quant # Optional, for torchscript quantization
-pip install onnxruntime # Optional, for onnx quantization
+pip install onnx onnxruntime # Optional, for onnx quantization
 ```
 
 ## Export model

funasr/runtime/python/grpc/Readme.md

@@ -9,9 +9,10 @@ The audio data is in streaming, the asr inference process is in offline.
 Install the modelscope and funasr
 
 ```shell
-pip install "modelscope[audio_asr]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
+pip install -U modelscope funasr
+# For the users in China, you could install with the command:
+# pip install -U modelscope funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple
 git clone https://github.com/alibaba/FunASR.git && cd FunASR
-pip install --editable ./
 ```
 
 Install the requirements

funasr/runtime/python/libtorch/README.md

@@ -4,12 +4,12 @@
 ### Install [modelscope and funasr](https://github.com/alibaba-damo-academy/FunASR#installation)
 
 ```shell
-pip3 install torch torchaudio
+# pip3 install torch torchaudio
 pip install -U modelscope funasr
 # For the users in China, you could install with the command:
 # pip install -U modelscope funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple
 pip install torch-quant # Optional, for torchscript quantization
-pip install onnxruntime # Optional, for onnx quantization
+pip install onnx onnxruntime # Optional, for onnx quantization
 ```
 
 ### Export [onnx model](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/export)

funasr/runtime/python/onnxruntime/README.md

@@ -4,12 +4,12 @@
 ### Install [modelscope and funasr](https://github.com/alibaba-damo-academy/FunASR#installation)
 
 ```shell
-pip3 install torch torchaudio
+#pip3 install torch torchaudio
 pip install -U modelscope funasr
 # For the users in China, you could install with the command:
 # pip install -U modelscope funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple
 pip install torch-quant # Optional, for torchscript quantization
-pip install onnxruntime # Optional, for onnx quantization
+pip install onnx onnxruntime # Optional, for onnx quantization
 ```
 
 ### Export [onnx model](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/export)

funasr/runtime/python/websocket/README.md

@@ -8,9 +8,10 @@ The audio data is in streaming, the asr inference process is in offline.
 Install the modelscope and funasr
 
 ```shell
-pip install "modelscope[audio_asr]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
+pip install -U modelscope funasr
+# For the users in China, you could install with the command:
+# pip install -U modelscope funasr -i https://mirror.sjtu.edu.cn/pypi/web/simple
 git clone https://github.com/alibaba/FunASR.git && cd FunASR
-pip install --editable ./
 ```
 
 Install the requirements for server