Merge remote-tracking branch 'origin/main'

2025-09-15 14:48:36 +08:00 · 2023-11-10 11:05:14 +08:00 · 2023-11-10 11:05:14 +08:00 · 73f4c8be50
commit 73f4c8be50
parent a0d5a61d10 64cdafaae8
6 changed files with 164 additions and 35 deletions
--- a/README.md
+++ b/README.md
@ -54,7 +54,7 @@ FunASR has open-sourced a large number of pre-trained models on industrial data.
 |:--------------------------------------------------------------------------------------------------------------------------------------------------------------------:|:---------------------------------------------------------------------------:|:--------------------------------:|:----------:|
 | <nobr>paraformer-zh ([⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch/summary)  [🤗]() )</nobr> |             speech recognition, with timestamps, non-streaming              |      60000 hours, Mandarin       |    220M    |
 |             <nobr>paraformer-zh-spk ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large-vad-punc-spk_asr_nat-zh-cn/summary)  [🤗]() )</nobr>             | speech recognition with speaker diarization, with timestamps, non-streaming |      60000 hours, Mandarin       |    220M    |
-|    <nobr>paraformer-zh-online ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [🤗]() )</nobr>     |                      speech recognition, non-streaming                      |      60000 hours, Mandarin       |    220M    |
+|    <nobr>paraformer-zh-online ( [⭐](https://modelscope.cn/models/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-online/summary) [🤗]() )</nobr>     |                        speech recognition, streaming                        |      60000 hours, Mandarin       |    220M    |
 |      <nobr>paraformer-en ( [⭐](https://www.modelscope.cn/models/damo/speech_paraformer-large-vad-punc_asr_nat-en-16k-common-vocab10020/summary) [🤗]() )</nobr>      |             speech recognition, with timestamps, non-streaming              |       50000 hours, English       |    220M    |
 |                                                            <nobr>paraformer-en-spk ([🤗]() [⭐]() )</nobr>                                                            |         speech recognition with speaker diarization, non-streaming          |       50000 hours, English       |    220M    |
 |                  <nobr>conformer-en ( [⭐](https://modelscope.cn/models/damo/speech_conformer_asr-en-16k-vocab4199-pytorch/summary) [🤗]() )</nobr>                   |                      speech recognition, non-streaming                      |       50000 hours, English       |    220M    |
--- a/docs/installation/docker.md
+++ b/docs/installation/docker.md
@ -37,11 +37,11 @@ sudo systemctl start docker
 ### 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
--- a/docs/installation/docker_zh.md
+++ b/docs/installation/docker_zh.md
@ -37,11 +37,11 @@ sudo systemctl start docker
 ### 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
--- a/funasr/quick_start.md
+++ b/funasr/quick_start.md
@ -28,37 +28,99 @@ python funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode 2pass --chunk

 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.
+
+##### Docker Installation (optional)
+###### If you have already installed Docker, skip this step.

-##### The real-time transcription service, Mandarin (CPU)
-###### Server Deployment
-You can use the following command to complete the deployment:
 ```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 @@ Testing [samples](https://isv-data.oss-cn-hangzhou.aliyuncs.com/ics/MaaS/ASR/sam
 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 @@ from modelscope.utils.constant import Tasks

 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')
--- a/funasr/quick_start_zh.md
+++ b/funasr/quick_start_zh.md
@ -5,11 +5,11 @@

 您可以通过如下几种方式使用FunASR功能:

- 服务部署SDK
+- 服务部署社区软件包
 - 工业模型egs
 - 学术模型egs

-### 服务部署SDK
+### 服务部署社区软件包

 #### python版本示例

@ -29,37 +29,104 @@ python funasr_wss_client.py --host "127.0.0.1" --port 10095 --mode 2pass --chunk
 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

-集成有，VAD，ASR与标点恢复模型，支持上百路并发请求
+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。
+
+##### 准备工作：docker安装（可选）
+###### 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;
+sudo bash install_docker.sh
+```

 ##### 实时语音听写服务部署

+###### docker镜像下载与启动
+通过下述命令拉取并启动FunASR软件包docker镜像（[获取最新镜像版本](https://github.com/alibaba-damo-academy/FunASR/blob/main/runtime/docs/SDK_advanced_guide_online_zh.md)）：
+
 ```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
+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
+```
+
+###### 服务端启动
+docker启动之后，启动 funasr-wss-server-2pass服务程序：
+```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 &
+
+# 如果您想关闭ssl，增加参数：--certfile 0
+# 如果您想使用时间戳或者nn热词模型进行部署，请设置--model-dir为对应模型：
+#   damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx（时间戳）
+#   damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404-onnx（nn热词）
+# 如果您想在服务端加载热词，请在宿主机文件./funasr-runtime-resources/models/hotwords.txt配置热词（docker映射地址为/workspace/models/hotwords.txt）:
+#   每行一个热词，格式(热词 权重)：阿里巴巴 20
 ```

 ##### 客户端测试与使用
 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](../runtime/docs/SDK_tutorial_online_zh.md)）
+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)）

 ##### 离线文件转写服务部署
-###### 服务端部署
+
+###### 镜像启动
+
+通过下述命令拉取并启动FunASR软件包docker镜像（[获取最新镜像版本](https://github.com/alibaba-damo-academy/FunASR/blob/main/runtime/docs/SDK_advanced_guide_offline_zh.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
 ```
+
+###### 服务端启动
+
+docker启动之后，启动 funasr-wss-server服务程序：
+```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 &
+
+# 如果您想关闭ssl，增加参数：--certfile 0
+# 如果您想使用时间戳或者nn热词模型进行部署，请设置--model-dir为对应模型：
+#   damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx（时间戳）
+#   damo/speech_paraformer-large-contextual_asr_nat-zh-cn-16k-common-vocab8404-onnx（nn热词）
+# 如果您想在服务端加载热词，请在宿主机文件./funasr-runtime-resources/models/hotwords.txt配置热词（docker映射地址为/workspace/models/hotwords.txt）:
+#   每行一个热词，格式(热词 权重)：阿里巴巴 20
+```
+
 ###### 客户端测试
 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 offline --audio_in "../audio/asr_example.wav"
 ```
-更多例子参考（[点击此处](../runtime/docs/SDK_tutorial_zh.md)）
+更多例子参考（[点击此处](https://github.com/alibaba-damo-academy/FunASR/blob/main/runtime/docs/SDK_advanced_guide_offline_zh.md)）



@ -74,7 +141,7 @@ from modelscope.utils.constant import Tasks

 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')
--- a/runtime/docs/SDK_advanced_guide_offline_zh.md
+++ b/runtime/docs/SDK_advanced_guide_offline_zh.md
@ -38,7 +38,7 @@ docker安装失败请参考 [Docker Installation](https://alibaba-damo-academy.g

 ### 镜像启动

-通过下述命令拉取并启动FunASR runtime-SDK的docker镜像：
+通过下述命令拉取并启动FunASR软件包的docker镜像：

 ```shell
 sudo docker pull \