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