From 32c5b3cafb4917dbfcae4f6f7d8c4d12a4f6eef4 Mon Sep 17 00:00:00 2001 From: huangmingming <huangmingming@deepscience.cn> Date: 星期一, 30 一月 2023 16:37:06 +0800 Subject: [PATCH] update readme, for step1-optional --- funasr/runtime/python/grpc/Readme.md | 27 ++++++++++++++++++++++----- 1 files changed, 22 insertions(+), 5 deletions(-) diff --git a/funasr/runtime/python/grpc/Readme.md b/funasr/runtime/python/grpc/Readme.md index 5da42a6..812dc70 100644 --- a/funasr/runtime/python/grpc/Readme.md +++ b/funasr/runtime/python/grpc/Readme.md @@ -1,16 +1,33 @@ -## 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) Generate protobuf file for grpc (Optional, paraformer_pb2.py and paraformer_pb2_grpc.py are already generated.) ``` python -m grpc_tools.protoc --proto_path=./proto -I ./proto --python_out=. --grpc_python_out=./ ./proto/paraformer.proto ``` -Step 2) start grpc server +Step 2) start grpc server (on server) +``` +python grpc_main_server.py --port 10095 +``` + +Step 3) start grpc client (on client with microphone) +``` +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 or refer to some code from: + +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