update docs

雾聪

2024-05-15 079fe36edd80fd2f3a8fdecf7d4b510836495dc9

 runtime/docs/SDK_advanced_guide_online.md

@@ -8,7 +8,9 @@

| TIME       | INFO                                                                                | IMAGE VERSION                       | IMAGE ID     |
|------------|-------------------------------------------------------------------------------------|-------------------------------------|--------------|
| 2024.01.25 | Optimization of the client-side | funasr-runtime-sdk-online-cpu-0.1.7  | 81fca20da2ed      |
| 2024.05.15 | Adapting to FunASR 1.0 model structure | funasr-runtime-sdk-online-cpu-0.1.10 | 1c2adfcff84d |
| 2024.03.05 | docker image supports ARM64 platform, update modelscope | funasr-runtime-sdk-online-cpu-0.1.9 | 4a875e08c7a2 |
| 2024.01.25 | Optimization of the client-side | funasr-runtime-sdk-online-cpu-0.1.7  | 2aa23805572e      |
| 2024.01.03 | The 2pass-offline mode supports Ngram language model decoding and WFST hotwords, while also addressing known crash issues and memory leak problems | funasr-runtime-sdk-online-cpu-0.1.6  | f99925110d27      |
| 2023.11.09 | fix bug: without online results                                                     | funasr-runtime-sdk-online-cpu-0.1.5 | b16584b6d38b      |
| 2023.11.08 | supporting server-side loading of hotwords, adaptation to runtime structure changes | funasr-runtime-sdk-online-cpu-0.1.4 | 691974017c38 |
@@ -28,9 +30,9 @@
### 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-0.1.7
sudo docker pull registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.10
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-0.1.7
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-0.1.10
```

### Launching the Server
@@ -45,7 +47,7 @@
  --online-model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online-onnx  \
  --punc-dir damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727-onnx \
  --lm-dir damo/speech_ngram_lm_zh-cn-ai-wesp-fst \
  --itn-dir thuduj12/fst_itn_zh > log.out 2>&1 &
  --itn-dir thuduj12/fst_itn_zh > log.txt 2>&1 &

# If you want to close ssl，please add：--certfile 0
```
@@ -59,7 +61,7 @@
For illustration, we will use the Python language client, which supports audio formats (.wav, .pcm) and a multi-file list wav.scp input.

```shell
python3 wss_client_asr.py --host "127.0.0.1" --port 10095 --mode 2pass
python3 funasr_wss_client.py --host "127.0.0.1" --port 10096 --mode 2pass
```

------------------
@@ -83,7 +85,7 @@
```shell
cd /workspace/FunASR/runtime
nohup bash run_server_2pass.sh \
  --model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-onnx \
  --model-dir damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx \
  --online-model-dir damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online-onnx \
  --vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx \
  --punc-dir damo/punc_ct-transformer_zh-cn-common-vad_realtime-vocab272727-onnx \
@@ -91,7 +93,7 @@
  --itn-dir thuduj12/fst_itn_zh \
  --certfile  ../../../ssl_key/server.crt \
  --keyfile ../../../ssl_key/server.key \
  --hotword ../../hotwords.txt > log.out 2>&1 &
  --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: