diff --git a/demos/speech_server/README.md b/demos/speech_server/README.md index a2f6f221..46d8f7c2 100644 --- a/demos/speech_server/README.md +++ b/demos/speech_server/README.md @@ -182,6 +182,52 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee ``` +### 6. CLS Client Usage +**Note:** The response time will be slightly longer when using the client for the first time +- Command Line (Recommended) + ``` + paddlespeech_client cls --server_ip 127.0.0.1 --port 8090 --input ./zh.wav + ``` + + Usage: + + ```bash + paddlespeech_client cls --help + ``` + Arguments: + - `server_ip`: server ip. Default: 127.0.0.1 + - `port`: server port. Default: 8090 + - `input`(required): Audio file to be classified. + - `topk`: topk scores of classification result. + + Output: + ```bash + [2022-03-09 20:44:39,974] [ INFO] - {'success': True, 'code': 200, 'message': {'description': 'success'}, 'result': {'topk': 1, 'results': [{'class_name': 'Speech', 'prob': 0.9027184844017029}]}} + [2022-03-09 20:44:39,975] [ INFO] - Response time 0.104360 s. + + + ``` + +- Python API + ```python + from paddlespeech.server.bin.paddlespeech_client import CLSClientExecutor + + clsclient_executor = CLSClientExecutor() + clsclient_executor( + input="./zh.wav", + server_ip="127.0.0.1", + port=8090, + topk=1) + + ``` + + Output: + ```bash + {'success': True, 'code': 200, 'message': {'description': 'success'}, 'result': {'topk': 1, 'results': [{'class_name': 'Speech', 'prob': 0.9027184844017029}]}} + Response time 0.150897 s. + + ``` + ## Models supported by the service ### ASR model @@ -189,3 +235,6 @@ Get all models supported by the ASR service via `paddlespeech_server stats --tas ### TTS model Get all models supported by the TTS service via `paddlespeech_server stats --task tts`, where static models can be used for paddle inference inference. + +### CLS model +Get all models supported by the CLS service via `paddlespeech_server stats --task cls`, where static models can be used for paddle inference inference. diff --git a/demos/speech_server/README_cn.md b/demos/speech_server/README_cn.md index 762248a1..1328ca27 100644 --- a/demos/speech_server/README_cn.md +++ b/demos/speech_server/README_cn.md @@ -80,7 +80,7 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee ``` -### 4. ASR客户端使用方法 +### 4. ASR 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) ``` @@ -129,7 +129,7 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee ``` -### 5. TTS客户端使用方法 +### 5. TTS 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) @@ -185,9 +185,59 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee ``` + ### 5. CLS 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 cls --server_ip 127.0.0.1 --port 8090 --input ./zh.wav + ``` + + 使用帮助: + + ```bash + paddlespeech_client cls --help + ``` + 参数: + - `server_ip`: 服务端ip地址，默认: 127.0.0.1。 + - `port`: 服务端口，默认: 8090。 + - `input`(必须输入): 用于分类的音频文件。 + - `topk`: 分类结果的topk。 + + 输出: + ```bash + [2022-03-09 20:44:39,974] [ INFO] - {'success': True, 'code': 200, 'message': {'description': 'success'}, 'result': {'topk': 1, 'results': [{'class_name': 'Speech', 'prob': 0.9027184844017029}]}} + [2022-03-09 20:44:39,975] [ INFO] - Response time 0.104360 s. + + + ``` + +- Python API + ```python + from paddlespeech.server.bin.paddlespeech_client import CLSClientExecutor + + clsclient_executor = CLSClientExecutor() + clsclient_executor( + input="./zh.wav", + server_ip="127.0.0.1", + port=8090, + topk=1) + + ``` + + 输出: + ```bash + {'success': True, 'code': 200, 'message': {'description': 'success'}, 'result': {'topk': 1, 'results': [{'class_name': 'Speech', 'prob': 0.9027184844017029}]}} + Response time 0.150897 s. + + ``` + + ## 服务支持的模型 ### ASR支持的模型 通过 `paddlespeech_server stats --task asr` 获取ASR服务支持的所有模型，其中静态模型可用于 paddle inference 推理。 ### TTS支持的模型 通过 `paddlespeech_server stats --task tts` 获取TTS服务支持的所有模型，其中静态模型可用于 paddle inference 推理。 + +### CLS支持的模型 +通过 `paddlespeech_server stats --task cls` 获取CLS服务支持的所有模型，其中静态模型可用于 paddle inference 推理。 diff --git a/paddlespeech/server/bin/paddlespeech_server.py b/paddlespeech/server/bin/paddlespeech_server.py index 3d71f091..7e7f03b2 100644 --- a/paddlespeech/server/bin/paddlespeech_server.py +++ b/paddlespeech/server/bin/paddlespeech_server.py @@ -103,13 +103,14 @@ class ServerStatsExecutor(): '--task', type=str, default=None, - choices=['asr', 'tts'], + choices=['asr', 'tts', 'cls'], help='Choose speech task.', required=True) - self.task_choices = ['asr', 'tts'] + self.task_choices = ['asr', 'tts', 'cls'] self.model_name_format = { 'asr': 'Model-Language-Sample Rate', - 'tts': 'Model-Language' + 'tts': 'Model-Language', + 'cls': 'Model-Sample Rate' } def show_support_models(self, pretrained_models: dict): @@ -173,54 +174,25 @@ class ServerStatsExecutor(): "Failed to get the table of TTS pretrained models supported in the service." ) return False - - @stats_wrapper - def __call__( - self, - task: str=None, ): - """ - Python API to call an executor. - """ - self.task = task - if self.task not in self.task_choices: - print("Please input correct speech task, choices = ['asr', 'tts']") - - elif self.task == 'asr': + + elif self.task == 'cls': try: - from paddlespeech.cli.asr.infer import pretrained_models - print( - "Here is the table of ASR pretrained models supported in the service." - ) - self.show_support_models(pretrained_models) - - # show ASR static pretrained model - from paddlespeech.server.engine.asr.paddleinference.asr_engine import pretrained_models - print( - "Here is the table of ASR static pretrained models supported in the service." - ) - self.show_support_models(pretrained_models) - - except BaseException: - print( - "Failed to get the table of ASR pretrained models supported in the service." - ) - - elif self.task == 'tts': - try: - from paddlespeech.cli.tts.infer import pretrained_models - print( - "Here is the table of TTS pretrained models supported in the service." + from paddlespeech.cli.cls.infer import pretrained_models + logger.info( + "Here is the table of CLS pretrained models supported in the service." ) self.show_support_models(pretrained_models) - # show TTS static pretrained model - from paddlespeech.server.engine.tts.paddleinference.tts_engine import pretrained_models - print( - "Here is the table of TTS static pretrained models supported in the service." + # show CLS static pretrained model + from paddlespeech.server.engine.cls.paddleinference.cls_engine import pretrained_models + logger.info( + "Here is the table of CLS static pretrained models supported in the service." ) self.show_support_models(pretrained_models) + return True except BaseException: - print( - "Failed to get the table of TTS pretrained models supported in the service." + logger.error( + "Failed to get the table of CLS pretrained models supported in the service." ) + return False