Merge pull request #367 from alibaba-damo-academy/dev_lhn2

hnluo

2023-04-17 24f73665e2d8ea8e4de2fe4f900bc539d7f7b989

 funasr/runtime/python/onnxruntime/README.md

@@ -1,10 +1,6 @@
## Using funasr with ONNXRuntime


### Introduction
- Model comes from [speech_paraformer](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary).


### Steps:
1. Export the model.
   - Command: (`Tips`: torch >= 1.11.0 is required.)
@@ -25,16 +21,21 @@

install from pip
```shell
pip install --upgrade funasr_onnx -i https://pypi.Python.org/simple
pip install -U funasr_onnx
# For the users in China, you could install with the command:
# pip install -U funasr_onnx -i https://mirror.sjtu.edu.cn/pypi/web/simple

```

or install from source code

```shell
git clone https://github.com/alibaba/FunASR.git && cd FunASR
cd funasr/runtime/python/funasr_onnx
python setup.py build
python setup.py install
cd funasr/runtime/python/onnxruntime
pip install -e ./
# For the users in China, you could install with the command:
# pip install -e ./ -i https://mirror.sjtu.edu.cn/pypi/web/simple

```

3. Run the demo.
@@ -54,17 +55,9 @@
        print(result)
        ```

## Speed
## Performance benchmark

Environment：Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz

Test [wav, 5.53s, 100 times avg.](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav)

| Backend |        RTF        |
|:-------:|:-----------------:|
| Pytorch |       0.110       |
|  Onnx   |       0.038       |

Please ref to [benchmark](https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/runtime/python/benchmark_onnx.md)

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