From 1d4ab65c8bfebaecbcb0eec0064bae9a321cad75 Mon Sep 17 00:00:00 2001 From: 游雁 <zhifu.gzf@alibaba-inc.com> Date: 星期二, 14 二月 2023 16:27:37 +0800 Subject: [PATCH] export model --- funasr/runtime/python/grpc/Readme.md | 64 +++++++++++++++++++++++++++++-- 1 files changed, 59 insertions(+), 5 deletions(-) diff --git a/funasr/runtime/python/grpc/Readme.md b/funasr/runtime/python/grpc/Readme.md index 5da42a6..053b3d0 100644 --- a/funasr/runtime/python/grpc/Readme.md +++ b/funasr/runtime/python/grpc/Readme.md @@ -1,16 +1,70 @@ -## using paraformer with grpc - +# Using paraformer with grpc We can send streaming audio data to server in real-time with grpc client every 10 ms e.g., and get transcribed text when stop speaking. The audio data is in streaming, the asr inference process is in offline. +## Steps -Step 1) Generate protobuf file for grpc +Step 1) Prepare server environment (on server). + + Install modelscope and funasr with pip or with cuda-docker image. + + Option 1: Install modelscope and funasr with [pip](https://github.com/alibaba-damo-academy/FunASR#installation) + + Option 2: or install with cuda-docker image as: + ``` +CID=`docker run --network host -d -it --gpus '"device=0"' registry.cn-hangzhou.aliyuncs.com/modelscope-repo/modelscope:ubuntu20.04-cuda11.3.0-py37-torch1.11.0-tf1.15.5-1.2.0` +echo $CID +docker exec -it $CID /bin/bash +``` + Get funasr source code and get into grpc directory. +``` +git clone https://github.com/alibaba-damo-academy/FunASR +cd FunASR/funasr/runtime/python/grpc/ +``` + + +Step 2) Optional, generate protobuf file (run on server, the two generated pb files are both used for server and client). +``` +# Optional, Install dependency. +python -m pip install grpcio grpcio-tools +``` + +``` +# 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 ``` -Step 2) start grpc server +Step 3) Start grpc server (on server). +``` +# Optional, Install dependency. +python -m pip install grpcio grpcio-tools +``` +``` +# Start server. +python grpc_main_server.py --port 10095 +``` + +Step 4) Start grpc client (on client with microphone). +``` +# Optional, Install dependency. +python -m pip install pyaudio webrtcvad grpcio grpcio-tools +``` +``` +# Start client. +python grpc_main_client_mic.py --host 127.0.0.1 --port 10095 +``` -Step 3) start grpc client \ No newline at end of file +## Workflow in desgin + + + +## Reference +We borrow from or refer to some code as: + +1)https://github.com/wenet-e2e/wenet/tree/main/runtime/core/grpc + +2)https://github.com/Open-Speech-EkStep/inference_service/blob/main/realtime_inference_service.py \ No newline at end of file -- Gitblit v1.9.1