From 580b11b57ac4b62f7e2acda73813a4e10e8e4cd3 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 10 十月 2023 17:17:29 +0800
Subject: [PATCH] v0.8.0
---
funasr/runtime/websocket/readme.md | 102 +++++++++------------------------------------------
1 files changed, 18 insertions(+), 84 deletions(-)
diff --git a/funasr/runtime/websocket/readme.md b/funasr/runtime/websocket/readme.md
index d5cba00..f057caa 100644
--- a/funasr/runtime/websocket/readme.md
+++ b/funasr/runtime/websocket/readme.md
@@ -1,102 +1,36 @@
-# ONNXRuntime-cpp for Websocket Server
+# Advanced Development Guide (File transcription service) ([click](../docs/SDK_advanced_guide_offline.md))
+# Real-time Speech Transcription Service Development Guide ([click](../docs/SDK_advanced_guide_online.md))
-## Export the model
-### Install [modelscope and funasr](https://github.com/alibaba-damo-academy/FunASR#installation)
-```shell
-# 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)
-
-```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
-```
-
+# If you want to compile the file yourself, you can follow the steps below.
## Building for Linux/Unix
-
### Download onnxruntime
```shell
-# download an appropriate onnxruntime from https://github.com/microsoft/onnxruntime/releases/tag/v1.14.0
-# here we get a copy of onnxruntime for linux 64
wget https://github.com/microsoft/onnxruntime/releases/download/v1.14.0/onnxruntime-linux-x64-1.14.0.tgz
tar -zxvf onnxruntime-linux-x64-1.14.0.tgz
```
-### Install openblas
+### Download ffmpeg
```shell
+wget https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/dep_libs/ffmpeg-N-111383-g20b8688092-linux64-gpl-shared.tar.xz
+tar -xvf ffmpeg-N-111383-g20b8688092-linux64-gpl-shared.tar.xz
+```
+
+### Install deps
+```shell
+# openblas
sudo apt-get install libopenblas-dev #ubuntu
# sudo yum -y install openblas-devel #centos
+
+# openssl
+apt-get install libssl-dev #ubuntu
+# yum install openssl-devel #centos
```
### Build runtime
```shell
-git clone https://github.com/alibaba-damo-academy/FunASR.git && cd funasr/runtime/websocket
+git clone https://github.com/alibaba-damo-academy/FunASR.git && cd FunASR/funasr/runtime/websocket
mkdir build && cd build
-cmake -DCMAKE_BUILD_TYPE=release .. -DONNXRUNTIME_DIR=/path/to/onnxruntime-linux-x64-1.14.0
-make
+cmake -DCMAKE_BUILD_TYPE=release .. -DONNXRUNTIME_DIR=/path/to/onnxruntime-linux-x64-1.14.0 -DFFMPEG_DIR=/path/to/ffmpeg-N-111383-g20b8688092-linux64-gpl-shared
+make -j 4
```
-## Run the websocket server
-
-```shell
-cd bin
-websocketmain [--model_thread_num <int>] [--decoder_thread_num
- <int>] [--io_thread_num <int>] [--port <int>]
- [--listen_ip <string>] [--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
-
- --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
- --decoder_thread_num <int>
- number of threads for decoder
- --io_thread_num <int>
- number of threads for network io
-
- 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>]
-example:
- websocketmain --am-config /FunASR/funasr/runtime/onnxruntime/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/config.yaml --am-model /FunASR/funasr/runtime/onnxruntime/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/model.onnx --am-cmvn /FunASR/funasr/runtime/onnxruntime/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/am.mvn
-```
-
-## Run websocket client test
-
-```shell
-Usage: websocketclient server_ip port wav_path threads_num
-
-example:
-
-websocketclient 127.0.0.1 8889 funasr/runtime/websocket/test.pcm.wav 64
-
-result json, example like:
-{"text":"涓�浜屼笁鍥涗簲鍏竷鍏節鍗佷竴浜屼笁鍥涗簲鍏竷鍏節鍗�"}
-```
-
--
Gitblit v1.9.1