From 6013d3c4a9afa81f8f7bdca4e3d9fe84639eb39b Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期五, 28 四月 2023 16:38:03 +0800
Subject: [PATCH] Merge pull request #441 from alibaba-damo-academy/dev_lhn

---
 funasr/runtime/onnxruntime/readme.md |   69 ++++++++++++++++++++--------------
 1 files changed, 40 insertions(+), 29 deletions(-)

diff --git a/funasr/runtime/onnxruntime/readme.md b/funasr/runtime/onnxruntime/readme.md
index 65c320f..436c7df 100644
--- a/funasr/runtime/onnxruntime/readme.md
+++ b/funasr/runtime/onnxruntime/readme.md
@@ -4,9 +4,10 @@
 ### Install [modelscope and funasr](https://github.com/alibaba-damo-academy/FunASR#installation)
 
 ```shell
-pip3 install torch torchaudio
-pip install -U modelscope
-pip install -U funasr
+# pip3 install torch torchaudio
+pip install -U modelscope funasr
+# For the users in China, you could install with the command:
+# pip install -U modelscope funasr -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html -i https://mirror.sjtu.edu.cn/pypi/web/simple
 ```
 
 ### Export [onnx model](https://github.com/alibaba-damo-academy/FunASR/tree/main/funasr/export)
@@ -38,37 +39,47 @@
 cmake  -DCMAKE_BUILD_TYPE=release .. -DONNXRUNTIME_DIR=/path/to/onnxruntime-linux-x64-1.14.0
 make
 ```
-
-[//]: # (### The structure of a qualified onnxruntime package.)
-
-[//]: # (```)
-
-[//]: # (onnxruntime_xxx)
-
-[//]: # (鈹溾攢鈹�鈹�include)
-
-[//]: # (鈹斺攢鈹�鈹�lib)
-
-[//]: # (```)
-
-## Building for Windows
-
-Ref to win/
-
-
 ## Run the demo
 
 ```shell
-tester /path/models_dir /path/wave_file quantize(true or false)
-```
+./funasr-onnx-offline     [--wav-scp <string>] [--wav-path <string>]
+                          [--punc-config <string>] [--punc-model <string>]
+                          --am-config <string> --am-cmvn <string>
+                          --am-model <string> [--vad-config <string>]
+                          [--vad-cmvn <string>] [--vad-model <string>] [--]
+                          [--version] [-h]
+Where:
+   --wav-scp <string>
+     wave scp path
+   --wav-path <string>
+     wave file path
 
-The structure of /path/models_dir
-```
-config.yaml, am.mvn, model.onnx(or model_quant.onnx)
-```
+   --punc-config <string>
+     punc config path
+   --punc-model <string>
+     punc model path
 
+   --am-config <string>
+     (required)  am config path
+   --am-cmvn <string>
+     (required)  am cmvn path
+   --am-model <string>
+     (required)  am model path
+
+   --vad-config <string>
+     vad config path
+   --vad-cmvn <string>
+     vad cmvn path
+   --vad-model <string>
+     vad model path
+  
+   Required: --am-config <string> --am-cmvn <string> --am-model <string> 
+   If use vad, please add: [--vad-config <string>] [--vad-cmvn <string>] [--vad-model <string>]
+   If use punc, please add: [--punc-config <string>] [--punc-model <string>] 
+```
 
 ## Acknowledge
 1. This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR).
-2. We acknowledge [mayong](https://github.com/RapidAI/RapidASR/tree/main/cpp_onnx) for contributing the onnxruntime(cpp api).
-3. We borrowed a lot of code from [FastASR](https://github.com/chenkui164/FastASR) for audio frontend and text-postprocess.
+2. We acknowledge mayong for contributing the onnxruntime of Paraformer and CT_Transformer, [repo-asr](https://github.com/RapidAI/RapidASR/tree/main/cpp_onnx), [repo-punc](https://github.com/RapidAI/RapidPunc).
+3. We acknowledge [ChinaTelecom](https://github.com/zhuzizyf/damo-fsmn-vad-infer-httpserver) for contributing the VAD runtime.
+4. We borrowed a lot of code from [FastASR](https://github.com/chenkui164/FastASR) for audio frontend and text-postprocess.

--
Gitblit v1.9.1