Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add

游雁

2023-03-17 add315bdb35e09fe705d4eab39e4d2386734f4ae

 funasr/runtime/python/benchmark_onnx.md

@@ -1,6 +1,26 @@
Benchmark [Paraformer-large](https://www.modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary) based on Aishell1 test set , the total audio duration is 36108.919 seconds.
# Benchmark 

(Note: The service has been fully warm up.)
### Data set:
Aishell1 test set , the total audio duration is 36108.919 seconds. (Note: The service has been fully warm up.)

### Tools
- Install 
```shell
git clone https://github.com/alibaba-damo-academy/FunASR.git && cd FunASR
pip install --editable ./
cd funasr/runtime/python/utils
pip install -r requirements.txt
```

- recipe
set the model, data path and output_dir

```shell
nohup bash test_rtf.sh &> log.txt &
```


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

 ### Intel(R) Xeon(R) Platinum 8369B CPU @ 2.90GHz   16core-32processor    with avx512_vnni

@@ -46,4 +66,6 @@
|  64 (onnx fp32)  |        153         | 0.0042 |    235.9     |
|  64 (onnx int8)  |        103         | 0.0029 |    349.9     |
|  96 (onnx fp32)  |        146         | 0.0041 |    247.0     |
|  96 (onnx int8)  |        108         | 0.0030 |    334.1     |
|  96 (onnx int8)  |        108         | 0.0030 |    334.1     |

## [Paraformer](https://modelscope.cn/models/damo/speech_paraformer_asr_nat-zh-cn-16k-common-vocab8358-tensorflow1/summary)