modify onnxruntime environment dependencies

北念

2023-02-21 f53c55cff30ec34bdfde61e318e6910d57d184a8

modify onnxruntime environment dependencies

 funasr/runtime/python/grpc/Readme.md

@@ -5,7 +5,7 @@

## Steps

Step 1) Prepare server environment (on server).  
Step 1-1) Prepare server modelscope pipeline environment (on server).  

         Install modelscope and funasr with pip or with cuda-docker image.

@@ -24,6 +24,26 @@
cd FunASR/funasr/runtime/python/grpc/
```

Step 1-2) Optional, Prepare server onnxruntime environment (on server). 

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

- Build the rapid_paraformer `whl`
```
git clone https://github.com/alibaba/FunASR.git && cd FunASR
cd funasr/runtime/python/onnxruntime/rapid_paraformer
python setup.py bdist_wheel
```

- Install the build `whl`
```
pip install dist/rapid_paraformer-0.0.1-py3-none-any.whl
```

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

Step 2) Optional, generate protobuf file (run on server, the two generated pb files are both used for server and client).
```
@@ -44,9 +64,16 @@
```
```
# Start server.
python grpc_main_server.py --port 10095
python grpc_main_server.py --port 10095 --backend pipeline
```

If you want run server with onnxruntime, please set `backend` and `onnx_dir` paramater.
```
# 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
```


Step 4) Start grpc client (on client with microphone).
```
# Optional, Install dependency.

 funasr/runtime/python/grpc/grpc_server.py

@@ -5,7 +5,7 @@

import paraformer_pb2_grpc
from paraformer_pb2 import Response
from utils.frontend import load_bytes
from rapid_paraformer.utils.frontend import load_bytes


class ASRServicer(paraformer_pb2_grpc.ASRServicer):
@@ -25,9 +25,9 @@
            self.inference_16k_pipeline = pipeline(task=Tasks.auto_speech_recognition, model=model)
        elif self.backend == "onnxruntime":
            try:
                from paraformer_onnx import Paraformer
                from rapid_paraformer.paraformer_onnx import Paraformer
            except ImportError:
                raise ImportError(f"Please install onnxruntime requirements, reference https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/python/onnxruntime/rapid_paraformer")
                raise ImportError(f"Please install onnxruntime environment")
            self.inference_16k_pipeline = Paraformer(model_dir=onnx_dir)
        self.sample_rate = sample_rate


 funasr/runtime/python/grpc/paraformer_onnx.py

File was deleted

 funasr/runtime/python/grpc/utils

File was deleted

 funasr/runtime/python/onnxruntime/README.md

@@ -36,7 +36,7 @@
   - Build the rapid_paraformer `whl`
     ```shell
     git clone https://github.com/alibaba/FunASR.git && cd FunASR
     cd funasr/runtime/python/onnxruntime/rapid_paraformer
     cd funasr/runtime/python/onnxruntime
     python setup.py bdist_wheel
     ```
   - Install the build `whl`