From 3aa166516360f3b1ed00e64509f56a2f097388c9 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=B8=B8=E9=9B=81?= Date: Fri, 17 Mar 2023 19:56:27 +0800 Subject: [PATCH] rtf benchmark --- funasr/runtime/python/benchmark_libtorch.md | 26 ++++++++++++--------- funasr/runtime/python/benchmark_onnx.md | 25 +++++++++++--------- 2 files changed, 29 insertions(+), 22 deletions(-) diff --git a/funasr/runtime/python/benchmark_libtorch.md b/funasr/runtime/python/benchmark_libtorch.md index 7dbc2c70f..43f3b0e93 100644 --- a/funasr/runtime/python/benchmark_libtorch.md +++ b/funasr/runtime/python/benchmark_libtorch.md @@ -4,20 +4,24 @@ 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) diff --git a/funasr/runtime/python/benchmark_onnx.md b/funasr/runtime/python/benchmark_onnx.md index a1ca0db0b..35c7068b5 100644 --- a/funasr/runtime/python/benchmark_onnx.md +++ b/funasr/runtime/python/benchmark_onnx.md @@ -4,20 +4,23 @@ 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)