grpc docs

游雁

2023-05-12 fefeadbd0b2b400b57329a15a6edd5a8738fa910

grpc docs

 funasr/runtime/python/grpc/Readme.md

@@ -5,7 +5,6 @@
## For the Server

### Prepare server environment
#### Backend is modelscope pipeline (default)
Install the modelscope and funasr

```shell
@@ -22,18 +21,6 @@
pip install -r requirements_server.txt
```

#### Backend is funasr_onnx (optional)

Install [`funasr_onnx`](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/python/onnxruntime).

```
pip install funasr_onnx -i https://pypi.Python.org/simple
```

Export the model, more details ref to [export docs](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/python/onnxruntime).
```shell
python -m funasr.export.export_model --model-name damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type onnx --quantize True
```

### Generate protobuf file
Run on server, the two generated pb files are both used for server and client
@@ -51,11 +38,6 @@
python grpc_main_server.py --port 10095 --backend pipeline
```

If you want run server with onnxruntime, please set `backend` and `onnx_dir`.
```
# Start server.
python grpc_main_server.py --port 10095 --backend onnxruntime --onnx_dir /models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
```

## For the client

@@ -87,9 +69,5 @@

<div align="left"><img src="proto/workflow.png" width="400"/>

## 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
## Acknowledge
1. This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR).