From 6a59f94278b4d05f5b7715b11b6dd0bfffc28cce Mon Sep 17 00:00:00 2001
From: 志浩 <neo.dzh@alibaba-inc.com>
Date: 星期四, 15 六月 2023 17:12:15 +0800
Subject: [PATCH] Merge branch 'main' into dev_dzh
---
funasr/runtime/websocket/readme.md | 48 +++++++++++++++++++++++++++++++++++++++++-------
1 files changed, 41 insertions(+), 7 deletions(-)
diff --git a/funasr/runtime/websocket/readme.md b/funasr/runtime/websocket/readme.md
index 078184e..4a1a9d4 100644
--- a/funasr/runtime/websocket/readme.md
+++ b/funasr/runtime/websocket/readme.md
@@ -33,7 +33,15 @@
```
### Build runtime
+required openssl lib
+
```shell
+#install openssl lib for ubuntu
+apt-get install libssl-dev
+#install openssl lib for centos
+yum install openssl-devel
+
+
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
@@ -43,11 +51,12 @@
```shell
cd bin
-./websocketmain [--model_thread_num <int>] [--decoder_thread_num <int>]
+ ./funasr-ws-server [--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> [--] [--version] [-h]
+ <string>] --model-dir <string> [--keyfile <string>]
+ [--certfile <string>] [--] [--version] [-h]
Where:
--model-dir <string>
(required) the asr model path, which contains model.onnx, config.yaml, am.mvn
@@ -70,25 +79,50 @@
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: --model-dir <string>
If use vad, please add: --vad-dir <string>
If use punc, please add: --punc-dir <string>
example:
- websocketmain --model-dir /FunASR/funasr/runtime/onnxruntime/export/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch
+ funasr-ws-server --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
+./funasr-ws-client --server-ip <string>
+ --port <string>
+ --wav-path <string>
+ [--thread-num <int>]
+ [--is-ssl <int>] [--]
+ [--version] [-h]
+
+Where:
+ --server-ip <string>
+ (required) server-ip
+
+ --port <string>
+ (required) port
+
+ --wav-path <string>
+ (required) the input could be: wav_path, e.g.: asr_example.wav;
+ pcm_path, e.g.: asr_example.pcm; wav.scp, kaldi style wav list (wav_id \t wav_path)
+
+ --thread-num <int>
+ thread-num
+
+ --is-ssl <int>
+ 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
+./funasr-ws-client --server-ip 127.0.0.1 --port 8889 --wav-path test.wav --thread-num 1 --is-ssl 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"}
```
--
Gitblit v1.9.1