diff --git a/demos/streaming_asr_server/README.md b/demos/streaming_asr_server/README.md index 48cfbaf35206970fa4275d0c09bb1df6e67085c0..d693dc4198a070eb519b2c9d83ac81309b89dc62 100644 --- a/demos/streaming_asr_server/README.md +++ b/demos/streaming_asr_server/README.md @@ -29,7 +29,7 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav ### 3. Server Usage - Command Line (Recommended) - + **Note:** The default deployment of the server is on the 'CPU' device, which can be deployed on the 'GPU' by modifying the 'device' parameter in the service configuration file. ```bash # in PaddleSpeech/demos/streaming_asr_server start the service paddlespeech_server start --config_file ./conf/ws_conformer_application.yaml @@ -110,6 +110,7 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav ``` - Python API + **Note:** The default deployment of the server is on the 'CPU' device, which can be deployed on the 'GPU' by modifying the 'device' parameter in the service configuration file. ```python # in PaddleSpeech/demos/streaming_asr_server directory from paddlespeech.server.bin.paddlespeech_server import ServerExecutor @@ -361,8 +362,9 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav ## Punctuation service ### 1. Server usage - + - Command Line + **Note:** The default deployment of the server is on the 'CPU' device, which can be deployed on the 'GPU' by modifying the 'device' parameter in the service configuration file. ``` bash In PaddleSpeech/demos/streaming_asr_server directory to lanuch punctuation service paddlespeech_server start --config_file conf/punc_application.yaml @@ -401,7 +403,7 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav ``` - Python API - + **Note:** The default deployment of the server is on the 'CPU' device, which can be deployed on the 'GPU' by modifying the 'device' parameter in the service configuration file. ```python # 在 PaddleSpeech/demos/streaming_asr_server 目录 from paddlespeech.server.bin.paddlespeech_server import ServerExecutor @@ -467,6 +469,9 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav ## Join streaming asr and punctuation server + +By default, each server is deployed on the 'CPU' device and speech recognition and punctuation prediction can be deployed on different 'GPU' by modifying the' device 'parameter in the service configuration file respectively. + We use `streaming_ asr_server.py` and `punc_server.py` two services to lanuch streaming speech recognition and punctuation prediction services respectively. And the `websocket_client.py` script can be used to call streaming speech recognition and punctuation prediction services at the same time. ### 1. Start two server diff --git a/demos/streaming_asr_server/README_cn.md b/demos/streaming_asr_server/README_cn.md index 67f62860713278dbb2e81984e754f768fa2c845f..db9cbb5eb02d42d90948aa4ce75c0384b7a2beee 100644 --- a/demos/streaming_asr_server/README_cn.md +++ b/demos/streaming_asr_server/README_cn.md @@ -36,7 +36,7 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav ### 3. 服务端使用方法 - 命令行 (推荐使用) - + **注意:** 默认部署在 `cpu` 设备上，可以通过修改服务配置文件中 `device` 参数部署在 `gpu` 上。 ```bash # 在 PaddleSpeech/demos/streaming_asr_server 目录启动服务 paddlespeech_server start --config_file ./conf/ws_conformer_application.yaml @@ -117,6 +117,7 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav ``` - Python API + **注意:** 默认部署在 `cpu` 设备上，可以通过修改服务配置文件中 `device` 参数部署在 `gpu` 上。 ```python # 在 PaddleSpeech/demos/streaming_asr_server 目录 from paddlespeech.server.bin.paddlespeech_server import ServerExecutor @@ -371,6 +372,7 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav ### 1. 服务端使用方法 - 命令行 + **注意:** 默认部署在 `cpu` 设备上，可以通过修改服务配置文件中 `device` 参数部署在 `gpu` 上。 ``` bash 在 PaddleSpeech/demos/streaming_asr_server 目录下启动标点预测服务 paddlespeech_server start --config_file conf/punc_application.yaml @@ -410,7 +412,7 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav ``` - Python API - + **注意:** 默认部署在 `cpu` 设备上，可以通过修改服务配置文件中 `device` 参数部署在 `gpu` 上。 ```python # 在 PaddleSpeech/demos/streaming_asr_server 目录 from paddlespeech.server.bin.paddlespeech_server import ServerExecutor @@ -476,6 +478,8 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav ## 联合流式语音识别和标点预测 +**注意:** By default, each server is deployed on the 'CPU' device. Voice recognition and punctuation prediction can be deployed on different 'GPUs' by modifying the' device 'parameter in the service configuration file. + 使用 `streaming_asr_server.py` 和 `punc_server.py` 两个服务，分别启动流式语音识别和标点预测服务。调用 `websocket_client.py` 脚本可以同时调用流式语音识别和标点预测服务。 ### 1. 启动服务 diff --git a/demos/streaming_asr_server/conf/punc_application.yaml b/demos/streaming_asr_server/conf/punc_application.yaml index e0d068710e63f5835cea7f07cf272c1fe5c74ee7..f947525e16478cbbf739c0281cb2234467b82972 100644 --- a/demos/streaming_asr_server/conf/punc_application.yaml +++ b/demos/streaming_asr_server/conf/punc_application.yaml @@ -28,7 +28,7 @@ text_python: cfg_path: # [optional] ckpt_path: # [optional] vocab_file: # [optional] - device: gpu:0 # set 'gpu:id' or 'cpu' + device: 'cpu' # set 'gpu:id' or 'cpu' diff --git a/demos/streaming_asr_server/conf/ws_conformer_application.yaml b/demos/streaming_asr_server/conf/ws_conformer_application.yaml index 42473555a9302f02566c6377fb5eb1e93faea7be..20a50008760abe5b6cdd92b562800648b2dd370a 100644 --- a/demos/streaming_asr_server/conf/ws_conformer_application.yaml +++ b/demos/streaming_asr_server/conf/ws_conformer_application.yaml @@ -29,7 +29,7 @@ asr_online: cfg_path: decode_method: force_yes: True - device: gpu:3 # cpu or gpu:id + device: 'cpu' # cpu or gpu:id am_predictor_conf: device: # set 'gpu:id' or 'cpu' switch_ir_optim: True @@ -42,4 +42,4 @@ asr_online: window_ms: 25 # ms shift_ms: 10 # ms sample_rate: 16000 - sample_width: 2 \ No newline at end of file + sample_width: 2 diff --git a/demos/streaming_asr_server/test.sh b/demos/streaming_asr_server/test.sh old mode 100644 new mode 100755