提交

kongdeqiang

2026-03-13 28ccfbfc51068a663a80764e14074df5edf2b5ba

 runtime/docs/SDK_advanced_guide_online.md

@@ -32,9 +32,9 @@
### Pull Docker Image
Use the following command to pull and start the FunASR software package docker image:
```shell
sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.12
sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.13
mkdir -p ./funasr-runtime-resources/models
sudo docker run -p 10096:10095 -it --privileged=true -v $PWD/funasr-runtime-resources/models:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.12
sudo docker run -p 10096:10095 -it --privileged=true -v $PWD/funasr-runtime-resources/models:/workspace/models registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.13
```

### Launching the Server
@@ -98,10 +98,11 @@
  --hotword ../../hotwords.txt > log.txt 2>&1 &

# If you want to close ssl，please add：--certfile 0
# If you want to deploy the timestamp or nn hotword model, please set --model-dir to the corresponding model:
# speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx（timestamp）
# damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404-onnx（hotword）

# If you want to deploy the SenseVoiceSmall, timestamp or nn hotword model, please set --model-dir to the corresponding model:
#   iic/SenseVoiceSmall-onnx
#   speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx（timestamp）
#   damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404-onnx（hotword）
# The ASR results “<|zh|><|NEUTRAL|><|Speech|> ” in SenseVoiceSmall-onnx means spoken language、speech emotion、audio event
```

### More details about the script run_server_2pass.sh: