diff --git a/demos/streaming_asr_server/README.md b/demos/streaming_asr_server/README.md index 3de2f386..d693dc41 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 @@ -355,4 +356,278 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav [2022-04-21 15:59:08,016] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了身体健康'} [2022-04-21 15:59:08,024] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了身体健康'} [2022-04-21 15:59:12,883] [ INFO] - final receive msg={'status': 'ok', 'signal': 'finished', 'asr_results': '我认为跑步最重要的就是给我带来了身体健康'} - ``` \ No newline at end of file + ``` + + +## 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 + ``` + + + Usage: + ```bash + paddlespeech_server start --help + ``` + + Arguments: + - `config_file`: configuration file. + - `log_file`: log file. + + + Output: + ``` bash + [2022-05-02 17:59:26,285] [ INFO] - Create the TextEngine Instance + [2022-05-02 17:59:26,285] [ INFO] - Init the text engine + [2022-05-02 17:59:26,285] [ INFO] - Text Engine set the device: gpu:0 + [2022-05-02 17:59:26,286] [ INFO] - File /home/users/xiongxinlei/.paddlespeech/models/ernie_linear_p3_wudao-punc-zh/ernie_linear_p3_wudao-punc-zh.tar.gz md5 checking... + [2022-05-02 17:59:30,810] [ INFO] - Use pretrained model stored in: /home/users/xiongxinlei/.paddlespeech/models/ernie_linear_p3_wudao-punc-zh/ernie_linear_p3_wudao-punc-zh.tar + W0502 17:59:31.486552 9595 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 10.2, Runtime API Version: 10.2 + W0502 17:59:31.491360 9595 device_context.cc:465] device: 0, cuDNN Version: 7.6. + [2022-05-02 17:59:34,688] [ INFO] - Already cached /home/users/xiongxinlei/.paddlenlp/models/ernie-1.0/vocab.txt + [2022-05-02 17:59:34,701] [ INFO] - Init the text engine successfully + INFO: Started server process [9595] + [2022-05-02 17:59:34] [INFO] [server.py:75] Started server process [9595] + INFO: Waiting for application startup. + [2022-05-02 17:59:34] [INFO] [on.py:45] Waiting for application startup. + INFO: Application startup complete. + [2022-05-02 17:59:34] [INFO] [on.py:59] Application startup complete. + INFO: Uvicorn running on http://0.0.0.0:8190 (Press CTRL+C to quit) + [2022-05-02 17:59:34] [INFO] [server.py:206] Uvicorn running on http://0.0.0.0:8190 (Press CTRL+C to quit) + ``` + +- 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 + + server_executor = ServerExecutor() + server_executor( + config_file="./conf/punc_application.yaml", + log_file="./log/paddlespeech.log") + ``` + + Output: + ``` + [2022-05-02 18:09:02,542] [ INFO] - Create the TextEngine Instance + [2022-05-02 18:09:02,543] [ INFO] - Init the text engine + [2022-05-02 18:09:02,543] [ INFO] - Text Engine set the device: gpu:0 + [2022-05-02 18:09:02,545] [ INFO] - File /home/users/xiongxinlei/.paddlespeech/models/ernie_linear_p3_wudao-punc-zh/ernie_linear_p3_wudao-punc-zh.tar.gz md5 checking... + [2022-05-02 18:09:06,919] [ INFO] - Use pretrained model stored in: /home/users/xiongxinlei/.paddlespeech/models/ernie_linear_p3_wudao-punc-zh/ernie_linear_p3_wudao-punc-zh.tar + W0502 18:09:07.523002 22615 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 10.2, Runtime API Version: 10.2 + W0502 18:09:07.527882 22615 device_context.cc:465] device: 0, cuDNN Version: 7.6. + [2022-05-02 18:09:10,900] [ INFO] - Already cached /home/users/xiongxinlei/.paddlenlp/models/ernie-1.0/vocab.txt + [2022-05-02 18:09:10,913] [ INFO] - Init the text engine successfully + INFO: Started server process [22615] + [2022-05-02 18:09:10] [INFO] [server.py:75] Started server process [22615] + INFO: Waiting for application startup. + [2022-05-02 18:09:10] [INFO] [on.py:45] Waiting for application startup. + INFO: Application startup complete. + [2022-05-02 18:09:10] [INFO] [on.py:59] Application startup complete. + INFO: Uvicorn running on http://0.0.0.0:8190 (Press CTRL+C to quit) + [2022-05-02 18:09:10] [INFO] [server.py:206] Uvicorn running on http://0.0.0.0:8190 (Press CTRL+C to quit) + ``` + +### 2. Client usage +**Note** The response time will be slightly longer when using the client for the first time + +- Command line + ``` + paddlespeech_client text --server_ip 127.0.0.1 --port 8190 --input "我认为跑步最重要的就是给我带来了身体健康" + ``` + + Output + ``` + [2022-05-02 18:12:29,767] [ INFO] - The punc text: 我认为跑步最重要的就是给我带来了身体健康。 + [2022-05-02 18:12:29,767] [ INFO] - Response time 0.096548 s. + ``` + +- Python3 API + + ```python + from paddlespeech.server.bin.paddlespeech_client import TextClientExecutor + + textclient_executor = TextClientExecutor() + res = textclient_executor( + input="我认为跑步最重要的就是给我带来了身体健康", + server_ip="127.0.0.1", + port=8190,) + print(res) + ``` + + Output: + ``` bash + 我认为跑步最重要的就是给我带来了身体健康。 + ``` + + +## 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 + +``` bash +Note: streaming speech recognition and punctuation prediction are configured on different graphics cards through configuration files +bash server.sh +``` + +### 2. Call client +- Command line + ``` + paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8290 --punc.server_ip 127.0.0.1 --punc.port 8190 --input ./zh.wav + ``` + Output: + ``` + [2022-05-02 18:57:46,961] [ INFO] - asr websocket client start + [2022-05-02 18:57:46,961] [ INFO] - endpoint: ws://127.0.0.1:8290/paddlespeech/asr/streaming + [2022-05-02 18:57:46,982] [ INFO] - client receive msg={"status": "ok", "signal": "server_ready"} + [2022-05-02 18:57:46,999] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,011] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,023] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,035] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,046] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,057] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,068] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,079] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,222] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,230] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,239] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,247] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,255] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,263] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,271] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,462] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:57:47,525] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:57:47,589] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:57:47,649] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:57:47,708] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:57:47,766] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:57:47,824] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:57:47,881] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:57:48,130] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:57:48,200] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:57:48,265] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:57:48,327] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:57:48,389] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:57:48,448] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:57:48,505] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:57:48,754] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:57:48,821] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:57:48,881] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:57:48,939] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:57:49,011] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:57:49,080] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:57:49,146] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:57:49,210] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:57:49,452] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:57:49,516] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:57:49,581] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:57:49,645] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:57:49,706] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:57:49,763] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:57:49,818] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:57:50,064] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:57:50,125] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:57:50,186] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:57:50,245] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:57:50,301] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:57:50,358] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:57:50,414] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:57:50,469] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:57:50,712] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:57:50,776] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:57:50,837] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:57:50,897] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:57:50,956] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:57:51,012] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:57:51,276] [ INFO] - client final receive msg={'status': 'ok', 'signal': 'finished', 'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:57:51,277] [ INFO] - asr websocket client finished + [2022-05-02 18:57:51,277] [ INFO] - 我认为跑步最重要的就是给我带来了身体健康。 + [2022-05-02 18:57:51,277] [ INFO] - Response time 4.316903 s. + ``` + +- Use script + ``` + python3 websocket_client.py --server_ip 127.0.0.1 --port 8290 --punc.server_ip 127.0.0.1 --punc.port 8190 --wavfile ./zh.wav + ``` + Output: + ``` + [2022-05-02 18:29:22,039] [ INFO] - Start to do streaming asr client + [2022-05-02 18:29:22,040] [ INFO] - asr websocket client start + [2022-05-02 18:29:22,040] [ INFO] - endpoint: ws://127.0.0.1:8290/paddlespeech/asr/streaming + [2022-05-02 18:29:22,041] [ INFO] - start to process the wavscp: ./zh.wav + [2022-05-02 18:29:22,122] [ INFO] - client receive msg={"status": "ok", "signal": "server_ready"} + [2022-05-02 18:29:22,351] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,360] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,368] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,376] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,384] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,392] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,400] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,408] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,549] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,558] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,567] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,575] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,583] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,591] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,599] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,822] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:29:22,879] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:29:22,937] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:29:22,995] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:29:23,052] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:29:23,107] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:29:23,161] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:29:23,213] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:29:23,454] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:29:23,515] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:29:23,575] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:29:23,630] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:29:23,684] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:29:23,736] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:29:23,789] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:29:24,030] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:29:24,095] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:29:24,156] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:29:24,213] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:29:24,268] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:29:24,323] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:29:24,377] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:29:24,429] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:29:24,671] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:29:24,736] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:29:24,797] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:29:24,857] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:29:24,918] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:29:24,975] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:29:25,029] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:29:25,271] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:29:25,336] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:29:25,398] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:29:25,458] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:29:25,521] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:29:25,579] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:29:25,652] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:29:25,722] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:29:25,969] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:29:26,034] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:29:26,095] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:29:26,163] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:29:26,229] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:29:26,294] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:29:26,565] [ INFO] - client final receive msg={'status': 'ok', 'signal': 'finished', 'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:29:26,566] [ INFO] - asr websocket client finished : 我认为跑步最重要的就是给我带来了身体健康。 + ``` + + \ No newline at end of file diff --git a/demos/streaming_asr_server/README_cn.md b/demos/streaming_asr_server/README_cn.md index bb1d3772..b768c435 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 @@ -363,3 +364,278 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav [2022-04-21 15:59:08,024] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了身体健康'} [2022-04-21 15:59:12,883] [ INFO] - final receive msg={'status': 'ok', 'signal': 'finished', 'asr_results': '我认为跑步最重要的就是给我带来了身体健康'} ``` + + + +## 标点预测 + +### 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 + ``` + + + 使用方法： + + ```bash + paddlespeech_server start --help + ``` + + 参数： + - `config_file`: 服务的配置文件。 + - `log_file`: log 文件。 + + + 输出： + ``` bash + [2022-05-02 17:59:26,285] [ INFO] - Create the TextEngine Instance + [2022-05-02 17:59:26,285] [ INFO] - Init the text engine + [2022-05-02 17:59:26,285] [ INFO] - Text Engine set the device: gpu:0 + [2022-05-02 17:59:26,286] [ INFO] - File /home/users/xiongxinlei/.paddlespeech/models/ernie_linear_p3_wudao-punc-zh/ernie_linear_p3_wudao-punc-zh.tar.gz md5 checking... + [2022-05-02 17:59:30,810] [ INFO] - Use pretrained model stored in: /home/users/xiongxinlei/.paddlespeech/models/ernie_linear_p3_wudao-punc-zh/ernie_linear_p3_wudao-punc-zh.tar + W0502 17:59:31.486552 9595 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 10.2, Runtime API Version: 10.2 + W0502 17:59:31.491360 9595 device_context.cc:465] device: 0, cuDNN Version: 7.6. + [2022-05-02 17:59:34,688] [ INFO] - Already cached /home/users/xiongxinlei/.paddlenlp/models/ernie-1.0/vocab.txt + [2022-05-02 17:59:34,701] [ INFO] - Init the text engine successfully + INFO: Started server process [9595] + [2022-05-02 17:59:34] [INFO] [server.py:75] Started server process [9595] + INFO: Waiting for application startup. + [2022-05-02 17:59:34] [INFO] [on.py:45] Waiting for application startup. + INFO: Application startup complete. + [2022-05-02 17:59:34] [INFO] [on.py:59] Application startup complete. + INFO: Uvicorn running on http://0.0.0.0:8190 (Press CTRL+C to quit) + [2022-05-02 17:59:34] [INFO] [server.py:206] Uvicorn running on http://0.0.0.0:8190 (Press CTRL+C to quit) + ``` + +- 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 + + server_executor = ServerExecutor() + server_executor( + config_file="./conf/punc_application.yaml", + log_file="./log/paddlespeech.log") + ``` + + 输出 + ``` + [2022-05-02 18:09:02,542] [ INFO] - Create the TextEngine Instance + [2022-05-02 18:09:02,543] [ INFO] - Init the text engine + [2022-05-02 18:09:02,543] [ INFO] - Text Engine set the device: gpu:0 + [2022-05-02 18:09:02,545] [ INFO] - File /home/users/xiongxinlei/.paddlespeech/models/ernie_linear_p3_wudao-punc-zh/ernie_linear_p3_wudao-punc-zh.tar.gz md5 checking... + [2022-05-02 18:09:06,919] [ INFO] - Use pretrained model stored in: /home/users/xiongxinlei/.paddlespeech/models/ernie_linear_p3_wudao-punc-zh/ernie_linear_p3_wudao-punc-zh.tar + W0502 18:09:07.523002 22615 device_context.cc:447] Please NOTE: device: 0, GPU Compute Capability: 6.1, Driver API Version: 10.2, Runtime API Version: 10.2 + W0502 18:09:07.527882 22615 device_context.cc:465] device: 0, cuDNN Version: 7.6. + [2022-05-02 18:09:10,900] [ INFO] - Already cached /home/users/xiongxinlei/.paddlenlp/models/ernie-1.0/vocab.txt + [2022-05-02 18:09:10,913] [ INFO] - Init the text engine successfully + INFO: Started server process [22615] + [2022-05-02 18:09:10] [INFO] [server.py:75] Started server process [22615] + INFO: Waiting for application startup. + [2022-05-02 18:09:10] [INFO] [on.py:45] Waiting for application startup. + INFO: Application startup complete. + [2022-05-02 18:09:10] [INFO] [on.py:59] Application startup complete. + INFO: Uvicorn running on http://0.0.0.0:8190 (Press CTRL+C to quit) + [2022-05-02 18:09:10] [INFO] [server.py:206] Uvicorn running on http://0.0.0.0:8190 (Press CTRL+C to quit) + ``` + +### 2. 标点预测客户端使用方法 +**注意：** 初次使用客户端时响应时间会略长 + +- 命令行 (推荐使用) + ``` + paddlespeech_client text --server_ip 127.0.0.1 --port 8190 --input "我认为跑步最重要的就是给我带来了身体健康" + ``` + + 输出 + ``` + [2022-05-02 18:12:29,767] [ INFO] - The punc text: 我认为跑步最重要的就是给我带来了身体健康。 + [2022-05-02 18:12:29,767] [ INFO] - Response time 0.096548 s. + ``` + +- Python3 API + + ```python + from paddlespeech.server.bin.paddlespeech_client import TextClientExecutor + + textclient_executor = TextClientExecutor() + res = textclient_executor( + input="我认为跑步最重要的就是给我带来了身体健康", + server_ip="127.0.0.1", + port=8190,) + print(res) + ``` + + 输出： + ``` bash + 我认为跑步最重要的就是给我带来了身体健康。 + ``` + + +## 联合流式语音识别和标点预测 +**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` 参数将语音识别和标点预测部署在不同的 `gpu` 上。 + +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 + +``` bash +注意：流式语音识别和标点预测通过配置文件配置到不同的显卡上 +bash server.sh +``` + +### 2. 调用服务 +- 使用命令行： + ``` + paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8290 --punc.server_ip 127.0.0.1 --punc.port 8190 --input ./zh.wav + ``` + 输出： + ``` + [2022-05-02 18:57:46,961] [ INFO] - asr websocket client start + [2022-05-02 18:57:46,961] [ INFO] - endpoint: ws://127.0.0.1:8290/paddlespeech/asr/streaming + [2022-05-02 18:57:46,982] [ INFO] - client receive msg={"status": "ok", "signal": "server_ready"} + [2022-05-02 18:57:46,999] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,011] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,023] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,035] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,046] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,057] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,068] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,079] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,222] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,230] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,239] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,247] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,255] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,263] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,271] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:57:47,462] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:57:47,525] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:57:47,589] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:57:47,649] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:57:47,708] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:57:47,766] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:57:47,824] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:57:47,881] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:57:48,130] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:57:48,200] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:57:48,265] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:57:48,327] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:57:48,389] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:57:48,448] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:57:48,505] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:57:48,754] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:57:48,821] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:57:48,881] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:57:48,939] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:57:49,011] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:57:49,080] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:57:49,146] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:57:49,210] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:57:49,452] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:57:49,516] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:57:49,581] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:57:49,645] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:57:49,706] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:57:49,763] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:57:49,818] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:57:50,064] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:57:50,125] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:57:50,186] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:57:50,245] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:57:50,301] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:57:50,358] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:57:50,414] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:57:50,469] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:57:50,712] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:57:50,776] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:57:50,837] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:57:50,897] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:57:50,956] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:57:51,012] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:57:51,276] [ INFO] - client final receive msg={'status': 'ok', 'signal': 'finished', 'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:57:51,277] [ INFO] - asr websocket client finished + [2022-05-02 18:57:51,277] [ INFO] - 我认为跑步最重要的就是给我带来了身体健康。 + [2022-05-02 18:57:51,277] [ INFO] - Response time 4.316903 s. + ``` + +- 使用脚本调用 + ``` + python3 websocket_client.py --server_ip 127.0.0.1 --port 8290 --punc.server_ip 127.0.0.1 --punc.port 8190 --wavfile ./zh.wav + ``` + 输出： + ``` + [2022-05-02 18:29:22,039] [ INFO] - Start to do streaming asr client + [2022-05-02 18:29:22,040] [ INFO] - asr websocket client start + [2022-05-02 18:29:22,040] [ INFO] - endpoint: ws://127.0.0.1:8290/paddlespeech/asr/streaming + [2022-05-02 18:29:22,041] [ INFO] - start to process the wavscp: ./zh.wav + [2022-05-02 18:29:22,122] [ INFO] - client receive msg={"status": "ok", "signal": "server_ready"} + [2022-05-02 18:29:22,351] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,360] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,368] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,376] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,384] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,392] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,400] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,408] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,549] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,558] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,567] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,575] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,583] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,591] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,599] [ INFO] - client receive msg={'result': ''} + [2022-05-02 18:29:22,822] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:29:22,879] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:29:22,937] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:29:22,995] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:29:23,052] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:29:23,107] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:29:23,161] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:29:23,213] [ INFO] - client receive msg={'result': '我认为，跑'} + [2022-05-02 18:29:23,454] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:29:23,515] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:29:23,575] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:29:23,630] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:29:23,684] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:29:23,736] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:29:23,789] [ INFO] - client receive msg={'result': '我认为，跑步最重要的。'} + [2022-05-02 18:29:24,030] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:29:24,095] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:29:24,156] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:29:24,213] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:29:24,268] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:29:24,323] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:29:24,377] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:29:24,429] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是。'} + [2022-05-02 18:29:24,671] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:29:24,736] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:29:24,797] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:29:24,857] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:29:24,918] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:29:24,975] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:29:25,029] [ INFO] - client receive msg={'result': '我认为，跑步最重要的就是给。'} + [2022-05-02 18:29:25,271] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:29:25,336] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:29:25,398] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:29:25,458] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:29:25,521] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:29:25,579] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:29:25,652] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:29:25,722] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了。'} + [2022-05-02 18:29:25,969] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:29:26,034] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:29:26,095] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:29:26,163] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:29:26,229] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:29:26,294] [ INFO] - client receive msg={'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:29:26,565] [ INFO] - client final receive msg={'status': 'ok', 'signal': 'finished', 'result': '我认为跑步最重要的就是给我带来了身体健康。'} + [2022-05-02 18:29:26,566] [ INFO] - asr websocket client finished : 我认为跑步最重要的就是给我带来了身体健康。 + ``` + + \ No newline at end of file diff --git a/demos/streaming_asr_server/conf/punc_application.yaml b/demos/streaming_asr_server/conf/punc_application.yaml new file mode 100644 index 00000000..f947525e --- /dev/null +++ b/demos/streaming_asr_server/conf/punc_application.yaml @@ -0,0 +1,35 @@ +# This is the parameter configuration file for PaddleSpeech Serving. + +################################################################################# +# SERVER SETTING # +################################################################################# +host: 0.0.0.0 +port: 8190 + +# The task format in the engin_list is: _ +# task choices = ['asr_python'] +# protocol = ['http'] (only one can be selected). +# http only support offline engine type. +protocol: 'http' +engine_list: ['text_python'] + + +################################################################################# +# ENGINE CONFIG # +################################################################################# + +################################### Text ######################################### +################### text task: punc; engine_type: python ####################### +text_python: + task: punc + model_type: 'ernie_linear_p3_wudao' + lang: 'zh' + sample_rate: 16000 + cfg_path: # [optional] + ckpt_path: # [optional] + vocab_file: # [optional] + 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 50c7a727..20a50008 100644 --- a/demos/streaming_asr_server/conf/ws_conformer_application.yaml +++ b/demos/streaming_asr_server/conf/ws_conformer_application.yaml @@ -4,7 +4,7 @@ # SERVER SETTING # ################################################################################# host: 0.0.0.0 -port: 8090 +port: 8290 # The task format in the engin_list is: _ # task choices = ['asr_online'] @@ -29,7 +29,7 @@ asr_online: cfg_path: decode_method: force_yes: True - device: # 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/punc_server.py b/demos/streaming_asr_server/punc_server.py new file mode 100644 index 00000000..eefa0fb4 --- /dev/null +++ b/demos/streaming_asr_server/punc_server.py @@ -0,0 +1,38 @@ +# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +import argparse + +from paddlespeech.cli.log import logger +from paddlespeech.server.bin.paddlespeech_server import ServerExecutor +if __name__ == "__main__": + parser = argparse.ArgumentParser( + prog='paddlespeech_server.start', add_help=True) + parser.add_argument( + "--config_file", + action="store", + help="yaml file of the app", + default=None, + required=True) + + parser.add_argument( + "--log_file", + action="store", + help="log file", + default="./log/paddlespeech.log") + logger.info("start to parse the args") + args = parser.parse_args() + + logger.info("start to launch the punctuation server") + punc_server = ServerExecutor() + punc_server(config_file=args.config_file, log_file=args.log_file) diff --git a/demos/streaming_asr_server/server.sh b/demos/streaming_asr_server/server.sh new file mode 100755 index 00000000..04858321 --- /dev/null +++ b/demos/streaming_asr_server/server.sh @@ -0,0 +1,5 @@ +export CUDA_VISIBLE_DEVICE=0,1,2,3 + +nohup python3 punc_server.py --config_file conf/punc_application.yaml > punc.log 2>&1 & + +nohup python3 streaming_asr_server.py --config_file conf/ws_conformer_application.yaml > streaming_asr.log 2>&1 & diff --git a/demos/streaming_asr_server/streaming_asr_server.py b/demos/streaming_asr_server/streaming_asr_server.py new file mode 100644 index 00000000..011b009a --- /dev/null +++ b/demos/streaming_asr_server/streaming_asr_server.py @@ -0,0 +1,38 @@ +# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved. +# +# Licensed under the Apache License, Version 2.0 (the "License"); +# you may not use this file except in compliance with the License. +# You may obtain a copy of the License at +# +# http://www.apache.org/licenses/LICENSE-2.0 +# +# Unless required by applicable law or agreed to in writing, software +# distributed under the License is distributed on an "AS IS" BASIS, +# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. +# See the License for the specific language governing permissions and +# limitations under the License. +import argparse + +from paddlespeech.cli.log import logger +from paddlespeech.server.bin.paddlespeech_server import ServerExecutor +if __name__ == "__main__": + parser = argparse.ArgumentParser( + prog='paddlespeech_server.start', add_help=True) + parser.add_argument( + "--config_file", + action="store", + help="yaml file of the app", + default=None, + required=True) + + parser.add_argument( + "--log_file", + action="store", + help="log file", + default="./log/paddlespeech.log") + logger.info("start to parse the args") + args = parser.parse_args() + + logger.info("start to launch the streaming asr server") + streaming_asr_server = ServerExecutor() + streaming_asr_server(config_file=args.config_file, log_file=args.log_file) diff --git a/demos/streaming_asr_server/test.sh b/demos/streaming_asr_server/test.sh old mode 100644 new mode 100755 index fe8155cf..912d67a2 --- a/demos/streaming_asr_server/test.sh +++ b/demos/streaming_asr_server/test.sh @@ -1,5 +1,8 @@ # download the test wav wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav -# read the wav and pass it to service -python3 websocket_client.py --wavfile ./zh.wav +# read the wav and pass it to only streaming asr service +python3 websocket_client.py --server_ip 127.0.0.1 --port 8290 --wavfile ./zh.wav + +# read the wav and call streaming and punc service +python3 websocket_client.py --server_ip 127.0.0.1 --port 8290 --punc.server_ip 127.0.0.1 --punc.port 8190 --wavfile ./zh.wav diff --git a/paddlespeech/server/bin/paddlespeech_client.py b/paddlespeech/server/bin/paddlespeech_client.py index cd1cd51a..8677279b 100644 --- a/paddlespeech/server/bin/paddlespeech_client.py +++ b/paddlespeech/server/bin/paddlespeech_client.py @@ -411,6 +411,18 @@ class ASROnlineClientExecutor(BaseExecutor): '--lang', type=str, default="zh_cn", help='language') self.parser.add_argument( '--audio_format', type=str, default="wav", help='audio format') + self.parser.add_argument( + '--punc.server_ip', + type=str, + default=None, + dest="punc_server_ip", + help='Punctuation server ip') + self.parser.add_argument( + '--punc.port', + type=int, + default=8190, + dest="punc_server_port", + help='Punctuation server port') def execute(self, argv: List[str]) -> bool: args = self.parser.parse_args(argv) @@ -428,7 +440,9 @@ class ASROnlineClientExecutor(BaseExecutor): port=port, sample_rate=sample_rate, lang=lang, - audio_format=audio_format) + audio_format=audio_format, + punc_server_ip=args.punc_server_ip, + punc_server_port=args.punc_server_port) time_end = time.time() logger.info(res) logger.info("Response time %f s." % (time_end - time_start)) @@ -445,12 +459,30 @@ class ASROnlineClientExecutor(BaseExecutor): port: int=8091, sample_rate: int=16000, lang: str="zh_cn", - audio_format: str="wav"): - """ - Python API to call an executor. + audio_format: str="wav", + punc_server_ip: str=None, + punc_server_port: str=None): + """Python API to call asr online executor. + + Args: + input (str): the audio file to be send to streaming asr service. + server_ip (str, optional): streaming asr server ip. Defaults to "127.0.0.1". + port (int, optional): streaming asr server port. Defaults to 8091. + sample_rate (int, optional): audio sample rate. Defaults to 16000. + lang (str, optional): audio language type. Defaults to "zh_cn". + audio_format (str, optional): audio format. Defaults to "wav". + punc_server_ip (str, optional): punctuation server ip. Defaults to None. + punc_server_port (str, optional): punctuation server port. Defaults to None. + + Returns: + str: the audio text """ logger.info("asr websocket client start") - handler = ASRWsAudioHandler(server_ip, port) + handler = ASRWsAudioHandler( + server_ip, + port, + punc_server_ip=punc_server_ip, + punc_server_port=punc_server_port) loop = asyncio.get_event_loop() res = loop.run_until_complete(handler.run(input)) logger.info("asr websocket client finished")