update

嘉渊

2023-04-24 6427c834dfd97b1f05c6659cdc7ccf010bf82fe1

 funasr/runtime/python/benchmark_onnx.md

@@ -1,26 +1,39 @@
# Benchmark 

### Data set:
Aishell1 test set , the total audio duration is 36108.919 seconds.
Aishell1 [test set](https://www.openslr.org/33/) , the total audio duration is 36108.919 seconds.

### 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
```
- Install ModelScope and FunASR

    ```shell
    pip install "modelscope[audio_asr]" --upgrade -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
    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 &
```
    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) 

Number of Parameter: 220M 

Storage size: 880MB

Storage size after int8-quant: 237MB

CER: 1.95%

CER after int8-quant: 1.95%

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

@@ -69,3 +82,28 @@
|  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)

Number of Parameter: 68M 

Storage size: 275MB

Storage size after int8-quant: 81MB

CER: 3.73%

CER after int8-quant: 3.78%

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

| concurrent-tasks | processing time(s) |  RTF   | Speedup Rate |
|:----------------:|:------------------:|:------:|:------------:|
|  1 (onnx fp32)   |        1173        | 0.0325 |     30.8     |
|  1 (onnx int8)   |        976         | 0.0270 |     37.0     |
|  16 (onnx fp32)  |         91         | 0.0025 |    395.2     |
|  16 (onnx int8)  |         78         | 0.0022 |    463.0     |
|  32 (onnx fp32)  |         60         | 0.0017 |    598.8     |
|  32 (onnx int8)  |         40         | 0.0011 |    892.9     |
|  64 (onnx fp32)  |         55         | 0.0015 |    653.6     |
|  64 (onnx int8)  |         31         | 0.0009 |    1162.8    |
|  96 (onnx fp32)  |         57         | 0.0016 |    632.9     |
|  96 (onnx int8)  |         33         | 0.0009 |    1098.9    |