rtf benchmark

游雁

2023-03-17 dc5367bbf12ad99a0df242506429f33554ccdea5

 funasr/runtime/python/benchmark_onnx.md

@@ -1,6 +1,8 @@
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.)
Aishell1 test set , the total audio duration is 36108.919 seconds. (Note: The service has been fully warm up.)

## [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

@@ -32,4 +34,20 @@
|  64 (onnx int8)  |         87         | 0.0024 |    414.7     |


### 
### Intel(R) Xeon(R) Platinum 8163 CPU @ 2.50GHz    32core-64processor   without avx512_vnni


| concurrent-tasks | processing time(s) |  RTF   | Speedup Rate |
|:----------------:|:------------------:|:------:|:------------:|
|  1 (onnx fp32)   |        2959        | 0.0820 |     12.2     |
|  1 (onnx int8)   |        2814        | 0.0778 |     12.8     |
|  16 (onnx fp32)  |        373         | 0.0103 |     96.9     |
|  16 (onnx int8)  |        331         | 0.0091 |    109.0     |
|  32 (onnx fp32)  |        211         | 0.0058 |    171.4     |
|  32 (onnx int8)  |        181         | 0.0050 |    200.0     |
|  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     |

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