rtf benchmark

游雁

2023-03-17 3aa166516360f3b1ed00e64509f56a2f097388c9

rtf benchmark

 funasr/runtime/python/benchmark_libtorch.md

@@ -4,8 +4,10 @@
Aishell1 [test set](https://www.openslr.org/33/) , the total audio duration is 36108.919 seconds.

### Tools
- Install 
- 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
@@ -13,6 +15,7 @@
```

- recipe

set the model, data path and output_dir

```shell
@@ -20,6 +23,7 @@
```



## [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

 funasr/runtime/python/benchmark_onnx.md

@@ -4,8 +4,10 @@
Aishell1 [test set](https://www.openslr.org/33/) , the total audio duration is 36108.919 seconds.

### Tools
- Install 
- 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
@@ -13,6 +15,7 @@
```

- recipe

set the model, data path and output_dir

```shell