From bf8360d250ec4deae4b7dd9927bbb7fec105852b Mon Sep 17 00:00:00 2001
From: Yabin Li <wucong.lyb@alibaba-inc.com>
Date: 星期一, 21 八月 2023 11:26:54 +0800
Subject: [PATCH] Update readme.md
---
funasr/runtime/docs/SDK_advanced_guide_offline.md | 17 ++++++++++++-----
1 files changed, 12 insertions(+), 5 deletions(-)
diff --git a/funasr/runtime/docs/SDK_advanced_guide_offline.md b/funasr/runtime/docs/SDK_advanced_guide_offline.md
index e813a8a..2bf9f31 100644
--- a/funasr/runtime/docs/SDK_advanced_guide_offline.md
+++ b/funasr/runtime/docs/SDK_advanced_guide_offline.md
@@ -36,9 +36,9 @@
Use the following command to pull and launch the Docker image for the FunASR runtime-SDK:
```shell
-sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-latest
+sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.2.0
-sudo docker run -p 10095:10095 -it --privileged=true -v /root:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-latest
+sudo docker run -p 10095:10095 -it --privileged=true -v /root:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.2.0
```
Introduction to command parameters:
@@ -59,6 +59,11 @@
--vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx \
--model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx \
--punc-dir damo/punc_ct-transformer_zh-cn-common-vocab272727-onnx > log.out 2>&1 &
+
+# If you want to close ssl锛宲lease add锛�--certfile 0
+# If you want to deploy the timestamp or hotword model, please set --model-dir to the corresponding model:
+# speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx锛坱imestamp锛�
+# damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404-onnx锛坔otword锛�
```
More details about the script run_server.sh:
@@ -92,8 +97,8 @@
--port: Port number that the server listens on. Default is 10095.
--decoder-thread-num: Number of inference threads that the server starts. Default is 8.
--io-thread-num: Number of IO threads that the server starts. Default is 1.
---certfile <string>: SSL certificate file. Default is ../../../ssl_key/server.crt.
---keyfile <string>: SSL key file. Default is ../../../ssl_key/server.key.
+--certfile <string>: SSL certificate file. Default is ../../../ssl_key/server.crt. If you want to close ssl锛宻et ""
+--keyfile <string>: SSL key file. Default is ../../../ssl_key/server.key. If you want to close ssl锛宻et ""
```
The FunASR-wss-server also supports loading models from a local path (see Preparing Model Resources for detailed instructions on preparing local model resources). Here is an example:
@@ -183,6 +188,7 @@
--output_dir: the path to the recognition result output.
--ssl: whether to use SSL encryption. The default is to use SSL.
--mode: offline mode.
+--hotword If am is hotword model, setting hotword: *.txt(one hotword perline) or hotwords seperate by space (could be: 闃块噷宸村反 杈炬懇闄�)
```
### c++-client
@@ -199,6 +205,7 @@
--output_dir: the path to the recognition result output.
--ssl: whether to use SSL encryption. The default is to use SSL.
--mode: offline mode.
+--hotword If am is hotword model, setting hotword: *.txt(one hotword perline) or hotwords seperate by space (could be: 闃块噷宸村反 杈炬懇闄�)
```
### Custom client
@@ -207,7 +214,7 @@
```text
# First communication
-{"mode": "offline", "wav_name": wav_name, "is_speaking": True}
+{"mode": "offline", "wav_name": wav_name, "is_speaking": True, "hotwords": "hotword1|hotword2"}
# Send wav data
Bytes data
# Send end flag
--
Gitblit v1.9.1