| | |
|---|
| | | |
|---|
| | | Step 1) Prepare server environment (on server). |
|---|
| | | ``` |
|---|
| | | #Optional, modelscope cuda docker is preferred. |
|---|
| | | # Optional, modelscope cuda docker is preferred. |
|---|
| | | 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 |
|---|
| | |
|---|
| | | |
|---|
| | | Step 2) Generate protobuf file (for server and client). |
|---|
| | | ``` |
|---|
| | | #Optional, paraformer_pb2.py and paraformer_pb2_grpc.py are already generated. |
|---|
| | | # 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 4) Start grpc client (on client with microphone). |
|---|
| | | ``` |
|---|
| | | #Install dependency. |
|---|
| | | # Install dependency. |
|---|
| | | python -m pip install pyaudio webrtcvad |
|---|
| | | ``` |
|---|
| | | ``` |
|---|
| | | #Start client. |
|---|
| | | # Start client. |
|---|
| | | python grpc_main_client_mic.py --host 127.0.0.1 --port 10095 |
|---|
| | | ``` |
|---|
| | | |
|---|
