[refator] optimize grpc server pipeline and instruction

funasr/runtime/grpc/Readme.md

@@ -2,17 +2,20 @@
 
 ## For the Server
 
-### Build [onnxruntime](./onnxruntime_cpp.md) as it's document
+### 1. Build [onnxruntime](../websocket/readme.md) as it's document
 
-### Compile and install grpc v1.52.0 in case of grpc bugs
-```
-export GRPC_INSTALL_DIR=/data/soft/grpc
-export PKG_CONFIG_PATH=$GRPC_INSTALL_DIR/lib/pkgconfig
+### 2. Compile and install grpc v1.52.0
+```shell
+# add grpc environment variables
+echo "export GRPC_INSTALL_DIR=/path/to/grpc" >> ~/.bashrc
+echo "export PKG_CONFIG_PATH=\$GRPC_INSTALL_DIR/lib/pkgconfig" >> ~/.bashrc
+echo "export PATH=\$GRPC_INSTALL_DIR/bin/:\$PKG_CONFIG_PATH:\$PATH" >> ~/.bashrc
+source ~/.bashrc
 
-git clone -b v1.52.0 --depth=1  https://github.com/grpc/grpc.git
-cd grpc
-git submodule update --init --recursive
+# install grpc
+git clone --recurse-submodules -b v1.52.0 --depth 1 --shallow-submodules https://github.com/grpc/grpc
 
+cd grpc
 mkdir -p cmake/build
 pushd cmake/build
 cmake -DgRPC_INSTALL=ON \
@@ -22,182 +25,57 @@ cmake -DgRPC_INSTALL=ON \
 make
 make install
 popd
-
-echo "export GRPC_INSTALL_DIR=/data/soft/grpc" >> ~/.bashrc
-echo "export PKG_CONFIG_PATH=\$GRPC_INSTALL_DIR/lib/pkgconfig" >> ~/.bashrc
-echo "export PATH=\$GRPC_INSTALL_DIR/bin/:\$PKG_CONFIG_PATH:\$PATH" >> ~/.bashrc
-source ~/.bashrc
 ```
 
-### Compile and start grpc onnx paraformer server
-```
-# set -DONNXRUNTIME_DIR=/path/to/asrmodel/onnxruntime-linux-x64-1.14.0
-./rebuild.sh
-```
+### 3. Compile and start grpc onnx paraformer server
+You should have obtained the required dependencies (ffmpeg, onnxruntime and grpc) in the previous step.
 
-### Start grpc paraformer server
-```
-
-./cmake/build/paraformer-server   --port-id <string> [--punc-quant <string>]
-                                  [--punc-dir <string>] [--vad-quant <string>]
-                                  [--vad-dir <string>] [--quantize <string>]
-                                  --model-dir <string> [--] [--version] [-h]
-Where:
-   --port-id <string>
-     (required)  port id
-   --model-dir <string>
-     (required)  the asr model path, which contains model.onnx, config.yaml, am.mvn
-   --quantize <string>
-     false (Default), load the model of model.onnx in model_dir. If set true, load the model of model_quant.onnx in model_dir
-
-   --vad-dir <string>
-     the vad model path, which contains model.onnx, vad.yaml, vad.mvn
-   --vad-quant <string>
-     false (Default), load the model of model.onnx in vad_dir. If set true, load the model of model_quant.onnx in vad_dir
-
-   --punc-dir <string>
-     the punc model path, which contains model.onnx, punc.yaml
-   --punc-quant <string>
-     false (Default), load the model of model.onnx in punc_dir. If set true, load the model of model_quant.onnx in punc_dir
-  
-   Required: --port-id <string>  --model-dir <string>
-   If use vad, please add: --vad-dir <string>
-   If use punc, please add: --punc-dir <string>
-```
-
-## For the client
-
-### Install the requirements as in [grpc-python](./docs/grpc_python.md)
+If no, run [download_ffmpeg](../onnxruntime/third_party/download_ffmpeg.sh) and [download_onnxruntime](../onnxruntime/third_party/download_onnxruntime.sh)
 
 ```shell
-git clone https://github.com/alibaba/FunASR.git && cd FunASR
-cd funasr/runtime/python/grpc
-pip install -r requirements_client.txt
+cd /cfs/user/burkliu/work2023/FunASR/funasr/runtime/grpc
+./build.sh
 ```
 
-### Generate protobuf file
-Run on server, the two generated pb files are both used for server and client
+### 4. Download paraformer model
+To do.
 
+### 5. Start grpc paraformer server
 ```shell
-# paraformer_pb2.py and paraformer_pb2_grpc.py are already generated, 
-# regenerate it only when you make changes to ./proto/paraformer.proto file.
-python -m grpc_tools.protoc  --proto_path=./proto -I ./proto    --python_out=. --grpc_python_out=./ ./proto/paraformer.proto
-```
-
-### Start grpc client
-```
-# Start client.
-python grpc_main_client_mic.py --host 127.0.0.1 --port 10095
-```
-
-[//]: # (```)
-
-[//]: # (# go to ../python/grpc to find this package)
-
-[//]: # (import paraformer_pb2)
-
-[//]: # ()
-[//]: # ()
-[//]: # (class RecognizeStub:)
-
-[//]: # (    def __init__&#40;self, channel&#41;:)
-
-[//]: # (        self.Recognize = channel.stream_stream&#40;)
-
-[//]: # (                '/paraformer.ASR/Recognize',)
-
-[//]: # (                request_serializer=paraformer_pb2.Request.SerializeToString,)
-
-[//]: # (                response_deserializer=paraformer_pb2.Response.FromString,)
-
-[//]: # (                &#41;)
-
-[//]: # ()
-[//]: # ()
-[//]: # (async def send&#40;channel, data, speaking, isEnd&#41;:)
+# run as default
+./run_server.sh
+
+# or run server directly
+./build/bin/paraformer-server \
+  --port-id <string> \
+  --offline-model-dir <string> \
+  --online-model-dir <string> \
+  --quantize <string> \
+  --vad-dir <string> \
+  --vad-quant <string> \
+  --punc-dir <string> \
+  --punc-quant <string>
 
-[//]: # (    stub = RecognizeStub&#40;channel&#41;)
-
-[//]: # (    req = paraformer_pb2.Request&#40;&#41;)
-
-[//]: # (    if data:)
-
-[//]: # (        req.audio_data = data)
-
-[//]: # (    req.user = 'zz')
-
-[//]: # (    req.language = 'zh-CN')
-
-[//]: # (    req.speaking = speaking)
-
-[//]: # (    req.isEnd = isEnd)
-
-[//]: # (    q = queue.SimpleQueue&#40;&#41;)
-
-[//]: # (    q.put&#40;req&#41;)
-
-[//]: # (    return stub.Recognize&#40;iter&#40;q.get, None&#41;&#41;)
-
-[//]: # ()
-[//]: # (# send the audio data once)
-
-[//]: # (async def grpc_rec&#40;data, grpc_uri&#41;:)
-
-[//]: # (    with grpc.insecure_channel&#40;grpc_uri&#41; as channel:)
-
-[//]: # (        b = time.time&#40;&#41;)
-
-[//]: # (        response = await send&#40;channel, data, False, False&#41;)
-
-[//]: # (        resp = response.next&#40;&#41;)
-
-[//]: # (        text = '')
-
-[//]: # (        if 'decoding' == resp.action:)
-
-[//]: # (            resp = response.next&#40;&#41;)
-
-[//]: # (            if 'finish' == resp.action:)
-
-[//]: # (                text = json.loads&#40;resp.sentence&#41;['text'])
-
-[//]: # (        response = await send&#40;channel, None, False, True&#41;)
-
-[//]: # (        return {)
-
-[//]: # (                'text': text,)
-
-[//]: # (                'time': time.time&#40;&#41; - b,)
-
-[//]: # (                })
-
-[//]: # ()
-[//]: # (async def test&#40;&#41;:)
-
-[//]: # (    # fc = FunAsrGrpcClient&#40;'127.0.0.1', 9900&#41;)
-
-[//]: # (    # t = await fc.rec&#40;wav.tobytes&#40;&#41;&#41;)
-
-[//]: # (    # print&#40;t&#41;)
-
-[//]: # (    wav, _ = sf.read&#40;'z-10s.wav', dtype='int16'&#41;)
-
-[//]: # (    uri = '127.0.0.1:9900')
+Where:
+  --port-id <string> (required) the port server listen to
 
-[//]: # (    res = await grpc_rec&#40;wav.tobytes&#40;&#41;, uri&#41;)
+  --offline-model-dir <string> (required) the offline asr model path
+  --online-model-dir <string> (required) the online asr model path
+  --quantize <string> (optional) false (Default), load the model of model.onnx in model_dir. If set true, load the model of model_quant.onnx in model_dir
 
-[//]: # (    print&#40;res&#41;)
+  --vad-dir <string> (required) the vad model path
+  --vad-quant <string> (optional) false (Default), load the model of model.onnx in vad_dir. If set true, load the model of model_quant.onnx in vad_dir
 
-[//]: # ()
-[//]: # ()
-[//]: # (if __name__ == '__main__':)
+  --punc-dir <string> (required) the punc model path
+  --punc-quant <string> (optional) false (Default), load the model of model.onnx in punc_dir. If set true, load the model of model_quant.onnx in punc_dir
+```
 
-[//]: # (    asyncio.run&#40;test&#40;&#41;&#41;)
+## For the client
+Currently we only support python grpc server.
 
-[//]: # ()
-[//]: # (```)
+Install the requirements as in [grpc-python](../python/grpc/Readme.md)
 
 
 ## Acknowledge
 1. This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR).
-2. We acknowledge [DeepScience](https://www.deepscience.cn) for contributing the grpc service.
+2. We acknowledge burkliu (刘柏基, liubaiji@xverse.cn) for contributing the grpc service.

funasr/runtime/grpc/build.sh

@@ -1,14 +1,15 @@
 #!/bin/bash
 
+mode=debug #[debug|release]
+onnxruntime_dir=`pwd`/../onnxruntime/onnxruntime-linux-x64-1.14.0
+ffmpeg_dir=`pwd`/../onnxruntime/ffmpeg-N-111383-g20b8688092-linux64-gpl-shared
+
+
 rm build -rf
 mkdir -p build
 cd build
 
-mode=debug #[debug|release]
-
-cmake -DCMAKE_BUILD_TYPE=$mode ../ \
-  -DONNXRUNTIME_DIR=/cfs/user/burkliu/work2023/FunASR/funasr/runtime/onnxruntime/onnxruntime-linux-x64-1.14.0 \
-  -DFFMPEG_DIR=/cfs/user/burkliu/work2023/FunASR/funasr/runtime/onnxruntime/ffmpeg-N-111383-g20b8688092-linux64-gpl-shared
+cmake -DCMAKE_BUILD_TYPE=$mode ../ -DONNXRUNTIME_DIR=$onnxruntime_dir -DFFMPEG_DIR=$ffmpeg_dir
 cmake --build . -j 4
 
-echo "Build build/paraformer_server successfully!"
+echo "Build server successfully!"

funasr/runtime/grpc/run_server.sh

@@ -2,11 +2,11 @@
 
 ./build/bin/paraformer-server \
   --port-id 10100 \
-  --offline-model-dir /cfs/user/burkliu/data/funasr_models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx \
-  --online-model-dir /cfs/user/burkliu/data/funasr_models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online \
+  --offline-model-dir funasr_models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx \
+  --online-model-dir funasr_models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online \
   --quantize true \
-  --vad-dir /cfs/user/burkliu/data/funasr_models/damo/speech_fsmn_vad_zh-cn-16k-common-onnx \
+  --vad-dir funasr_models/damo/speech_fsmn_vad_zh-cn-16k-common-onnx \
   --vad-quant true \
-  --punc-dir /cfs/user/burkliu/data/funasr_models/damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727 \
+  --punc-dir funasr_models/damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727 \
   --punc-quant true \
   2>&1