From fae856e23d45fd27d5fd55fd036e8e3fc7b24915 Mon Sep 17 00:00:00 2001
From: 雾聪 <wucong.lyb@alibaba-inc.com>
Date: 星期五, 02 六月 2023 23:00:08 +0800
Subject: [PATCH] update funasr-onnx-offline
---
funasr/runtime/websocket/readme.md | 85 +++++++++++++++++++++++-------------------
1 files changed, 47 insertions(+), 38 deletions(-)
diff --git a/funasr/runtime/websocket/readme.md b/funasr/runtime/websocket/readme.md
index d5cba00..d2a54e9 100644
--- a/funasr/runtime/websocket/readme.md
+++ b/funasr/runtime/websocket/readme.md
@@ -1,4 +1,4 @@
-# ONNXRuntime-cpp for Websocket Server
+# Service with websocket-cpp
## Export the model
### Install [modelscope and funasr](https://github.com/alibaba-damo-academy/FunASR#installation)
@@ -33,7 +33,12 @@
```
### Build runtime
+required openssl lib
+
```shell
+#install openssl lib first
+apt-get install libssl-dev
+
git clone https://github.com/alibaba-damo-academy/FunASR.git && cd funasr/runtime/websocket
mkdir build && cd build
cmake -DCMAKE_BUILD_TYPE=release .. -DONNXRUNTIME_DIR=/path/to/onnxruntime-linux-x64-1.14.0
@@ -43,60 +48,64 @@
```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]
+ ./websocketmain [--model_thread_num <int>] [--decoder_thread_num <int>]
+ [--io_thread_num <int>] [--port <int>] [--listen_ip
+ <string>] [--punc-quant <string>] [--punc-dir <string>]
+ [--vad-quant <string>] [--vad-dir <string>] [--quantize
+ <string>] --model-dir <string> [--keyfile <string>]
+ [--certfile <string>] [--] [--version] [-h]
Where:
- --wav-scp <string>
- wave scp path
- --wav-path <string>
- wave file path
+ --model-dir <string>
+ (required) the asr model path, which contains model.onnx, config.yaml, am.mvn
+ --quantize <string>
+ false (Default), load the model of model.onnx in model_dir. If set true, load the model of model_quant.onnx in model_dir
- --punc-config <string>
- punc config path
- --punc-model <string>
- punc model path
+ --vad-dir <string>
+ the vad model path, which contains model.onnx, vad.yaml, vad.mvn
+ --vad-quant <string>
+ false (Default), load the model of model.onnx in vad_dir. If set true, load the model of model_quant.onnx in vad_dir
- --am-config <string>
- (required) am config path
- --am-cmvn <string>
- (required) am cmvn path
- --am-model <string>
- (required) am model path
+ --punc-dir <string>
+ the punc model path, which contains model.onnx, punc.yaml
+ --punc-quant <string>
+ false (Default), load the model of model.onnx in punc_dir. If set true, load the model of model_quant.onnx in punc_dir
- --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
+ number of threads for decoder, default:8
--io_thread_num <int>
- number of threads for network io
+ number of threads for network io, default:8
+ --port <int>
+ listen port, default:8889
+ --certfile <string>
+ path of certficate for WSS connection. if it is empty, it will be in WS mode.
+ --keyfile <string>
+ path of keyfile for WSS connection
- 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>]
+ Required: --model-dir <string>
+ If use vad, please add: --vad-dir <string>
+ If use punc, please add: --punc-dir <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
+ websocketmain --model-dir /FunASR/funasr/runtime/onnxruntime/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
```
## Run websocket client test
```shell
-Usage: websocketclient server_ip port wav_path threads_num
+Usage: ./websocketclient server_ip port wav_path threads_num is_ssl
+
+is_ssl is 1 means use wss connection, or use ws connection
example:
-websocketclient 127.0.0.1 8889 funasr/runtime/websocket/test.pcm.wav 64
+websocketclient 127.0.0.1 8889 funasr/runtime/websocket/test.pcm.wav 64 0
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�"}
+{"mode":"offline","text":"娆㈣繋澶у鏉ヤ綋楠岃揪鎽╅櫌鎺ㄥ嚭鐨勮闊宠瘑鍒ā鍨�","wav_name":"wav2"}
```
+
+## Acknowledge
+1. This project is maintained by [FunASR community](https://github.com/alibaba-damo-academy/FunASR).
+2. We acknowledge [zhaoming](https://github.com/zhaomingwork/FunASR/tree/add-offline-websocket-srv/funasr/runtime/websocket) for contributing the websocket(cpp-api).
+
+
--
Gitblit v1.9.1