From 129cfcd9f283dea0d64f2e20b77662febc2d802c Mon Sep 17 00:00:00 2001 From: 游雁 <zhifu.gzf@alibaba-inc.com> Date: 星期四, 23 三月 2023 10:01:32 +0800 Subject: [PATCH] cer tool --- funasr/runtime/python/grpc/Readme.md | 36 ++++++++++++++++++++++++++++++++++-- 1 files changed, 34 insertions(+), 2 deletions(-) diff --git a/funasr/runtime/python/grpc/Readme.md b/funasr/runtime/python/grpc/Readme.md index 053b3d0..2df666d 100644 --- a/funasr/runtime/python/grpc/Readme.md +++ b/funasr/runtime/python/grpc/Readme.md @@ -5,7 +5,7 @@ ## Steps -Step 1) Prepare server environment (on server). +Step 1-1) Prepare server modelscope pipeline environment (on server). Install modelscope and funasr with pip or with cuda-docker image. @@ -24,6 +24,31 @@ cd FunASR/funasr/runtime/python/grpc/ ``` +Step 1-2) Optional, Prepare server onnxruntime environment (on server). + +Install [`onnx_paraformer`](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/python/onnxruntime). + +- Build the onnx_paraformer `whl` +``` +git clone https://github.com/alibaba/FunASR.git && cd FunASR +cd funasr/runtime/python/onnxruntime/rapid_paraformer +python setup.py build +python setup.py install +``` + +[//]: # () +[//]: # (- Install the build `whl`) + +[//]: # (```) + +[//]: # (pip install dist/rapid_paraformer-0.0.1-py3-none-any.whl) + +[//]: # (```) + +Export the model, more details ref to [export docs](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/runtime/python/onnxruntime). +```shell +python -m funasr.export.export_model --model-name damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch --export-dir ./export --type onnx --quantize True +``` Step 2) Optional, generate protobuf file (run on server, the two generated pb files are both used for server and client). ``` @@ -44,9 +69,16 @@ ``` ``` # Start server. -python grpc_main_server.py --port 10095 +python grpc_main_server.py --port 10095 --backend pipeline ``` +If you want run server with onnxruntime, please set `backend` and `onnx_dir` paramater. +``` +# Start server. +python grpc_main_server.py --port 10095 --backend onnxruntime --onnx_dir /models/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch +``` + + Step 4) Start grpc client (on client with microphone). ``` # Optional, Install dependency. -- Gitblit v1.9.1