From 602fe75a1f0a8d64ccb6fc4d69ad510872fdfd13 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 17 三月 2023 20:30:40 +0800
Subject: [PATCH] rtf benchmark

---
 funasr/runtime/python/benchmark_onnx.md |   45 ++++++++++++++++++++++++++++++++++++++++++---
 1 files changed, 42 insertions(+), 3 deletions(-)

diff --git a/funasr/runtime/python/benchmark_onnx.md b/funasr/runtime/python/benchmark_onnx.md
index e0584a5..35c7068 100644
--- a/funasr/runtime/python/benchmark_onnx.md
+++ b/funasr/runtime/python/benchmark_onnx.md
@@ -1,6 +1,29 @@
-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](https://www.openslr.org/33/) , the total audio duration is 36108.919 seconds.
+
+### Tools
+- 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 &
+    ```
+
+
+## [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 +55,20 @@
 |  64 (onnx int8)  |         87         | 0.0024 |    414.7     |
 
 
-### 
\ No newline at end of file
+### 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)

--
Gitblit v1.9.1