docs

游雁

2023-11-09 eeb43ced05a5fe5822b71cb89bb50d344c69eeec

docs

 docs/installation/docker.md

@@ -37,11 +37,11 @@
### Image Hub

#### CPU
`registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.1.0`
`registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.3.0`

#### GPU

`registry.cn-hangzhou.aliyuncs.com/modelscope-repo/modelscope:ubuntu20.04-cuda11.3.0-py37-torch1.11.0-tf1.15.5-1.6.0`
`registry.cn-hangzhou.aliyuncs.com/modelscope-repo/modelscope:ubuntu20.04-py38-torch1.11.0-tf1.15.5-1.8.1`

### Pull Image
```shell

 docs/installation/docker_zh.md

@@ -37,11 +37,11 @@
### 镜像仓库

#### CPU
`registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.1.0`
`registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.3.0`

#### GPU

`registry.cn-beijing.aliyuncs.com/modelscope-repo/modelscope:ubuntu20.04-cuda11.7.1-py38-torch2.0.1-tf1.15.5-1.7.0`
`registry.cn-hangzhou.aliyuncs.com/modelscope-repo/modelscope:ubuntu20.04-py38-torch1.11.0-tf1.15.5-1.8.1`

### 拉取镜像
```shell

 funasr/quick_start.md

@@ -28,37 +28,99 @@

For more examples, please refer to [docs](../runtime/python/websocket/README.md).

### C++ version Example
### Service Deployment Software

Currently, offline file transcription service (CPU) is supported, and concurrent requests of hundreds of channels are supported.
Both high-precision, high-efficiency, and high-concurrency file transcription, as well as low-latency real-time speech recognition, are supported. It also supports Docker deployment and multiple concurrent requests.

##### The real-time transcription service, Mandarin (CPU)
###### Server Deployment
You can use the following command to complete the deployment:
##### Docker Installation (optional)
###### If you have already installed Docker, skip this step.

```shell
curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/funasr-runtime-deploy-online-cpu-zh.sh
sudo bash funasr-runtime-deploy-online-cpu-zh.sh install --workspace ./funasr-runtime-resources
curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/install_docker.sh;
sudo bash install_docker.sh
```

##### Real-time Speech Recognition Service Deployment

###### Docker Image Download and Launch
Use the following command to pull and launch the FunASR software package Docker image（[Get the latest image version](https://github.com/alibaba-damo-academy/FunASR/blob/main/runtime/docs/SDK_advanced_guide_online.md)）：

```shell
sudo docker pull \
  registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-online-cpu-0.1.5
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-0.1.5
```

###### Server Start

After Docker is started, start the funasr-wss-server-2pass service program:

```shell
cd FunASR/runtime
nohup bash run_server_2pass.sh \
  --download-model-dir /workspace/models \
  --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  \
  --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 \
  --itn-dir thuduj12/fst_itn_zh \
  --hotword /workspace/models/hotwords.txt > log.out 2>&1 &

# If you want to disable SSL, add the parameter: --certfile 0
# If you want to deploy with a timestamp or nn hotword model, please set --model-dir to the corresponding model:
#   damo/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 (nn hotword)
# If you want to load hotwords on the server side, please configure the hotwords in the host file ./funasr-runtime-resources/models/hotwords.txt (docker mapping address is /workspace/models/hotwords.txt):
#   One hotword per line, format (hotword weight): Alibaba 20
```

###### Client Testing
Testing [samples](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/sample/funasr_samples.tar.gz)

```shell
python3 funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode 2pass
python3 funasr_wss_client.py --host "127.0.0.1" --port 10096 --mode 2pass
```
For more examples, please refer to [docs](../runtime/docs/SDK_tutorial_online_zh.md)
For more examples, please refer to [docs](https://github.com/alibaba-damo-academy/FunASR/blob/main/runtime/docs/SDK_advanced_guide_online.md)


#### File Transcription Service, Mandarin (CPU)

##### Server Deployment

You can use the following command to complete the deployment:
###### Docker Image Download and Launch
Use the following command to pull and launch the FunASR software package Docker image（[Get the latest image version](https://github.com/alibaba-damo-academy/FunASR/blob/main/runtime/docs/SDK_advanced_guide_offline.md)）：

```shell
curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/funasr-runtime-deploy-offline-cpu-zh.sh
sudo bash funasr-runtime-deploy-offline-cpu-zh.sh install --workspace ./funasr-runtime-resources
sudo docker pull \
  registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.3.0
mkdir -p ./funasr-runtime-resources/models
sudo docker run -p 10095:10095 -it --privileged=true \
  -v $PWD/funasr-runtime-resources/models:/workspace/models \
  registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.3.0
```

###### Server Start

After Docker is started, start the funasr-wss-server service program:

```shell
cd FunASR/runtime
nohup bash run_server.sh \
  --download-model-dir /workspace/models \
  --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_cn-en-common-vocab471067-large-onnx \
  --lm-dir damo/speech_ngram_lm_zh-cn-ai-wesp-fst \
  --itn-dir thuduj12/fst_itn_zh \
  --hotword /workspace/models/hotwords.txt > log.out 2>&1 &

# If you want to disable SSL, add the parameter: --certfile 0
# If you want to use timestamp or nn hotword models for deployment, please set --model-dir to the corresponding model:
#   damo/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 (nn hotword)
# If you want to load hotwords on the server side, please configure the hotwords in the host machine file ./funasr-runtime-resources/models/hotwords.txt (docker mapping address is /workspace/models/hotwords.txt):
#   One hotword per line, format (hotword weight): Alibaba 20
```

##### Client Testing
@@ -68,7 +130,7 @@
python3 funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode offline --audio_in "../audio/asr_example.wav"
```

For more examples, please refer to [docs](../runtime/docs/SDK_tutorial_zh.md)
For more examples, please refer to [docs](https://github.com/alibaba-damo-academy/FunASR/blob/main/runtime/docs/SDK_advanced_guide_offline.md)


## Industrial Model Egs
@@ -81,7 +143,7 @@

inference_pipeline = pipeline(
    task=Tasks.auto_speech_recognition,
    model='damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
    model='damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch',
)

rec_result = inference_pipeline(audio_in='https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/test_audio/asr_example_zh.wav')

 funasr/quick_start_zh.md

@@ -29,7 +29,7 @@
更多例子可以参考（[点击此处](../runtime/python/websocket/README.md)）

<a name="cpp版本示例"></a>
#### c++版本示例
#### 服务部署软件包

既可以进行高精度、高效率与高并发的文件转写，也可以进行低延时的实时语音听写。支持Docker化部署，多路请求。

@@ -37,7 +37,7 @@
###### 如果您已安装docker，忽略本步骤

```shell
curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/install_docker.sh；
curl -O https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/shell/install_docker.sh;
sudo bash install_docker.sh
```

@@ -80,7 +80,7 @@
客户端测试（[samples](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/sample/funasr_samples.tar.gz)）

```shell
python3 funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode 2pass
python3 funasr_wss_client.py --host "127.0.0.1" --port 10096 --mode 2pass
```
更多例子参考（[点击此处](https://github.com/alibaba-damo-academy/FunASR/blob/main/runtime/docs/SDK_advanced_guide_online_zh.md)）

@@ -98,7 +98,6 @@
  -v $PWD/funasr-runtime-resources/models:/workspace/models \
  registry.cn-hangzhou.aliyuncs.com/funasr_repo/funasr:funasr-runtime-sdk-cpu-0.3.0
```


###### 服务端启动