mirror of
https://github.com/modelscope/FunASR
synced 2025-09-15 14:48:36 +08:00
33 lines
865 B
Markdown
33 lines
865 B
Markdown
# 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
|
|
```
|
|
python -m grpc_tools.protoc --proto_path=./proto -I ./proto --python_out=. --grpc_python_out=./ ./proto/paraformer.proto
|
|
```
|
|
|
|
Step 2) start grpc server
|
|
```
|
|
python grpc_main_server.py --port 10095
|
|
```
|
|
|
|
Step 3) start grpc client
|
|
```
|
|
python grpc_main_client_mic.py --host 127.0.0.1 --port 10095
|
|
```
|
|
|
|
|
|
## 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 |