python/FunASR-XL.git

			@@ -1,14 +1,10 @@
			## paraformer grpc onnx server
			# Service with grpc-cpp

			## For the Server

			#### build ../onnxruntime as it's document
			```
			#put onnx lib and model into /data/asrmodel
			ls /data/asrmodel/
			onnxruntime-linux-x64-1.14.0 speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
			```
			### Build [onnxruntime](./onnxruntime_cpp.md) as it's document

			#### compile and install grpc v1.52.0 in case of grpc bugs
			### Compile and install grpc v1.52.0 in case of grpc bugs
			```
			export GRPC_INSTALL_DIR=/data/soft/grpc
			export PKG_CONFIG_PATH=$GRPC_INSTALL_DIR/lib/pkgconfig
			@@ -24,6 +20,7 @@
			-DCMAKE_INSTALL_PREFIX=$GRPC_INSTALL_DIR \
			../..
			make
			make install
			popd

			echo "export GRPC_INSTALL_DIR=/data/soft/grpc" >> ~/.bashrc
			@@ -32,18 +29,175 @@
			source ~/.bashrc
			```

			#### compile grpc onnx paraformer server
			### Compile and start grpc onnx paraformer server
			```
			#depends on ../onnxruntime
			#file vocab.txt : UTF-8 Unicode text

			# set -DONNXRUNTIME_DIR=/path/to/asrmodel/onnxruntime-linux-x64-1.14.0
			./rebuild.sh
			```

			### 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)

			```shell
			git clone https://github.com/alibaba/FunASR.git && cd FunASR
			cd funasr/runtime/python/grpc
			pip install -r requirements_client.txt
			```

			### Generate protobuf file
			Run on server, the two generated pb files are both used for server and client

			```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__(self, channel):)

			[//]: # ( self.Recognize = channel.stream_stream()

			[//]: # ( '/paraformer.ASR/Recognize',)

			[//]: # ( request_serializer=paraformer_pb2.Request.SerializeToString,)

			[//]: # ( response_deserializer=paraformer_pb2.Response.FromString,)

			[//]: # ( ))

			[//]: # ()
			[//]: # ()
			[//]: # (async def send(channel, data, speaking, isEnd):)

			[//]: # ( stub = RecognizeStub(channel))

			[//]: # ( req = paraformer_pb2.Request())

			[//]: # ( if data:)

			[//]: # ( req.audio_data = data)

			[//]: # ( req.user = 'zz')

			[//]: # ( req.language = 'zh-CN')

			[//]: # ( req.speaking = speaking)

			[//]: # ( req.isEnd = isEnd)

			[//]: # ( q = queue.SimpleQueue())

			[//]: # ( q.put(req))

			[//]: # ( return stub.Recognize(iter(q.get, None)))

			[//]: # ()
			[//]: # (# send the audio data once)

			[//]: # (async def grpc_rec(data, grpc_uri):)

			[//]: # ( with grpc.insecure_channel(grpc_uri) as channel:)

			[//]: # ( b = time.time())

			[//]: # ( response = await send(channel, data, False, False))

			[//]: # ( resp = response.next())

			[//]: # ( text = '')

			[//]: # ( if 'decoding' == resp.action:)

			[//]: # ( resp = response.next())

			[//]: # ( if 'finish' == resp.action:)

			[//]: # ( text = json.loads(resp.sentence)['text'])

			[//]: # ( response = await send(channel, None, False, True))

			[//]: # ( return {)

			[//]: # ( 'text': text,)

			[//]: # ( 'time': time.time() - b,)

			[//]: # ( })

			[//]: # ()
			[//]: # (async def test():)

			[//]: # ( # fc = FunAsrGrpcClient('127.0.0.1', 9900))

			[//]: # ( # t = await fc.rec(wav.tobytes()))

			[//]: # ( # print(t))

			[//]: # ( wav, _ = sf.read('z-10s.wav', dtype='int16'))

			[//]: # ( uri = '127.0.0.1:9900')

			[//]: # ( res = await grpc_rec(wav.tobytes(), uri))

			[//]: # ( print(res))

			[//]: # ()
			[//]: # ()
			[//]: # (if __name__ == '__main__':)

			[//]: # ( asyncio.run(test()))

			[//]: # ()
			[//]: # (```)


			#### start grpc python paraformer client on PC with MIC
			```
			cd ../python/grpc
			python grpc_main_client_mic.py --host $server_ip --port 10108
			```
			## 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.