mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00

History

游雁 fefeadbd0b grpc docs		2023-05-12 09:43:49 +08:00
..
proto	websocket docs	2023-05-08 22:36:07 +08:00
.gitignore	adjust import lib order	2023-01-30 17:18:20 +08:00
grpc_client.py	adjust import lib order	2023-01-30 17:18:20 +08:00
grpc_main_client_mic.py	adjust import lib order	2023-01-30 17:18:20 +08:00
grpc_main_client.py	debug onnxruntime multithread bugs	2023-04-11 10:35:29 +08:00
grpc_main_server.py	grpc	2023-03-20 17:31:51 +08:00
grpc_server.py	grpc onnx	2023-04-06 17:46:46 +08:00
paraformer_pb2_grpc.py	fix client, add pb file	2023-01-29 19:01:36 +08:00
paraformer_pb2.py	fix client, add pb file	2023-01-29 19:01:36 +08:00
Readme.md	grpc docs	2023-05-12 09:43:49 +08:00
requirements_client.txt	grpc readme	2023-03-24 11:09:14 +08:00
requirements_server.txt	grpc readme	2023-03-24 11:09:14 +08:00

Readme.md

Service with grpc-python

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.

For the Server

Prepare server environment

Install the modelscope and funasr

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

Install the requirements

cd funasr/runtime/python/grpc
pip install -r requirements_server.txt

Generate protobuf file

Run on server, the two generated pb files are both used for server and client

# 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 server

# Start server.
python grpc_main_server.py --port 10095 --backend pipeline

For the client

Install the requirements

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

# 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

Workflow in desgin

Acknowledge

This project is maintained by FunASR community.