From c5fe181405df43f822b7eeab40737a8ecf3d198f Mon Sep 17 00:00:00 2001 From: xiongxinlei Date: Wed, 27 Apr 2022 20:16:41 +0800 Subject: [PATCH] update the paddlespeech_client asr_online cli, test=doc --- demos/streaming_asr_server/README.md | 8 +- demos/streaming_asr_server/README_cn.md | 202 +++++++++++++++++- examples/voxceleb/sv0/README.md | 2 +- examples/voxceleb/sv0/local/test.sh | 18 +- .../server/bin/paddlespeech_client.py | 75 ++++++- 5 files changed, 295 insertions(+), 10 deletions(-) diff --git a/demos/streaming_asr_server/README.md b/demos/streaming_asr_server/README.md index 83b8e05c..3a10ea0b 100644 --- a/demos/streaming_asr_server/README.md +++ b/demos/streaming_asr_server/README.md @@ -186,16 +186,19 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav ### 4. ASR Client Usage + +#### 4.2 使用 `paddlespeech_client asr_online` **Note:** The response time will be slightly longer when using the client for the first time - Command Line (Recommended) ``` + # if we use paddlespeech_client asr, we must specify the protocol to websocket paddlespeech_client asr --server_ip 127.0.0.1 --port 8090 --input ./zh.wav --protocol websocket ``` Usage: ```bash - paddlespeech_client asr_online --help + paddlespeech_client asr help ``` Arguments: - `server_ip`: server ip. Default: 127.0.0.1 @@ -204,6 +207,9 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav - `sample_rate`: Audio ampling rate, default: 16000. - `lang`: Language. Default: "zh_cn". - `audio_format`: Audio format. Default: "wav". + - `protocol`: protocol between client and server. Streaming asr must be websocket. + - `punc.server_ip`: punctuation server ip. Default: None. + - `punc.server_port`: punctuation server port. Default: None. Output: ```bash diff --git a/demos/streaming_asr_server/README_cn.md b/demos/streaming_asr_server/README_cn.md index 9e5473fe..99c01341 100644 --- a/demos/streaming_asr_server/README_cn.md +++ b/demos/streaming_asr_server/README_cn.md @@ -5,18 +5,27 @@ ## 介绍 这个demo是一个启动流式语音服务和访问服务的实现。 它可以通过使用`paddlespeech_server` 和 `paddlespeech_client`的单个命令或 python 的几行代码来实现。 -流式语音识别服务只支持 `weboscket` 协议，不支持 `http` 协议。 +**流式语音识别服务只支持 `weboscket` 协议，不支持 `http` 协议。** ## 使用方法 ### 1. 安装 -请看 [安装文档](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md). +安装 PaddleSpeech 的详细过程请看 [安装文档](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md)。 推荐使用 **paddlepaddle 2.2.1** 或以上版本。 -你可以从medium，hard 二中方式中选择一种方式安装 PaddleSpeech。 +你可以从medium，hard 两中方式中选择一种方式安装 PaddleSpeech。 ### 2. 准备配置文件 -配置文件可参见 `conf/ws_application.yaml` 和 `conf/ws_conformer_application.yaml` 。 + +流式ASR的服务启动脚本和服务测试脚本存放在 `PaddleSpeech/demos/streaming_asr_server` 目录。 +下载好 `PaddleSpeech` 之后，进入到 `PaddleSpeech/demos/streaming_asr_server` 目录。 +配置文件可参见该目录下 `conf/ws_application.yaml` 和 `conf/ws_conformer_application.yaml` 。 + +目前服务集成的模型有： DeepSpeech2和 conformer模型，对应的配置文件如下： +* DeepSpeech: `conf/ws_application.yaml` +* conformer: `conf/ws_conformer_application.yaml` + + 目前服务集成的模型有： DeepSpeech2和conformer模型。 @@ -185,17 +194,197 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav ``` ### 4. ASR 客户端使用方法 + +#### 4.1 使用`paddlespeech_client asr ` **注意：** 初次使用客户端时响应时间会略长 - 命令行 (推荐使用) ``` + # 使用 paddlespecch_asr 需要指定传入协议为 websocket paddlespeech_client asr --server_ip 127.0.0.1 --port 8090 --input ./zh.wav --protocol websocket + ``` + + 使用帮助: + + ```bash + paddlespeech_client asr 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): 用于识别的音频文件。 + - `sample_rate`: 音频采样率，默认值：16000。 + - `lang`: 模型语言，默认值：zh_cn。 + - `audio_format`: 音频格式，默认值：wav。 + - `protocol` 指定客户端和服务端之间服务的协议。在流式识别中必须指定 websocket。 + - `punc.server_ip` 标点预测服务的ip。默认是None。 + - `punc.server_port` 标点预测服务的端口port。默认是None。 + + 输出: + + ```bash + [2022-04-21 15:59:03,904] [ INFO] - receive msg={"status": "ok", "signal": "server_ready"} + [2022-04-21 15:59:03,960] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:03,973] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:03,987] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,000] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,012] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,024] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,036] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,047] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,607] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,620] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,633] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,645] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,657] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,669] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,680] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:05,176] [ INFO] - receive msg={'asr_results': '我认为跑'} + [2022-04-21 15:59:05,185] [ INFO] - receive msg={'asr_results': '我认为跑'} + [2022-04-21 15:59:05,192] [ INFO] - receive msg={'asr_results': '我认为跑'} + [2022-04-21 15:59:05,200] [ INFO] - receive msg={'asr_results': '我认为跑'} + [2022-04-21 15:59:05,208] [ INFO] - receive msg={'asr_results': '我认为跑'} + [2022-04-21 15:59:05,216] [ INFO] - receive msg={'asr_results': '我认为跑'} + [2022-04-21 15:59:05,224] [ INFO] - receive msg={'asr_results': '我认为跑'} + [2022-04-21 15:59:05,232] [ INFO] - receive msg={'asr_results': '我认为跑'} + [2022-04-21 15:59:05,724] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'} + [2022-04-21 15:59:05,732] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'} + [2022-04-21 15:59:05,740] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'} + [2022-04-21 15:59:05,747] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'} + [2022-04-21 15:59:05,755] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'} + [2022-04-21 15:59:05,763] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'} + [2022-04-21 15:59:05,770] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'} + [2022-04-21 15:59:06,271] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'} + [2022-04-21 15:59:06,279] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'} + [2022-04-21 15:59:06,287] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'} + [2022-04-21 15:59:06,294] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'} + [2022-04-21 15:59:06,302] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'} + [2022-04-21 15:59:06,310] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'} + [2022-04-21 15:59:06,318] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'} + [2022-04-21 15:59:06,326] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'} + [2022-04-21 15:59:06,833] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'} + [2022-04-21 15:59:06,842] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'} + [2022-04-21 15:59:06,850] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'} + [2022-04-21 15:59:06,858] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'} + [2022-04-21 15:59:06,866] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'} + [2022-04-21 15:59:06,874] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'} + [2022-04-21 15:59:06,882] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'} + [2022-04-21 15:59:07,400] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'} + [2022-04-21 15:59:07,408] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'} + [2022-04-21 15:59:07,416] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'} + [2022-04-21 15:59:07,424] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'} + [2022-04-21 15:59:07,432] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'} + [2022-04-21 15:59:07,440] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'} + [2022-04-21 15:59:07,447] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'} + [2022-04-21 15:59:07,455] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'} + [2022-04-21 15:59:07,984] [ 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 15:59:07,992] [ 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 15:59:08,001] [ 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 15:59:08,008] [ 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 15:59:08,016] [ 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'} + [2022-04-21 15:59:12,884] [ INFO] - 我认为跑步最重要的就是给我带来了身体健康 + [2022-04-21 15:59:12,884] [ INFO] - Response time 9.051567 s. + ``` +- Python API + ```python + from paddlespeech.server.bin.paddlespeech_client import ASRClientExecutor + import json + + asrclient_executor = ASRClientExecutor() + res = asrclient_executor( + input="./zh.wav", + server_ip="127.0.0.1", + port=8090, + sample_rate=16000, + lang="zh_cn", + audio_format="wav", + protocol="websocket") + print(res) + ``` + + 输出: + ```bash + [2022-04-21 15:59:03,904] [ INFO] - receive msg={"status": "ok", "signal": "server_ready"} + [2022-04-21 15:59:03,960] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:03,973] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:03,987] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,000] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,012] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,024] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,036] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,047] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,607] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,620] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,633] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,645] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,657] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,669] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:04,680] [ INFO] - receive msg={'asr_results': ''} + [2022-04-21 15:59:05,176] [ INFO] - receive msg={'asr_results': '我认为跑'} + [2022-04-21 15:59:05,185] [ INFO] - receive msg={'asr_results': '我认为跑'} + [2022-04-21 15:59:05,192] [ INFO] - receive msg={'asr_results': '我认为跑'} + [2022-04-21 15:59:05,200] [ INFO] - receive msg={'asr_results': '我认为跑'} + [2022-04-21 15:59:05,208] [ INFO] - receive msg={'asr_results': '我认为跑'} + [2022-04-21 15:59:05,216] [ INFO] - receive msg={'asr_results': '我认为跑'} + [2022-04-21 15:59:05,224] [ INFO] - receive msg={'asr_results': '我认为跑'} + [2022-04-21 15:59:05,232] [ INFO] - receive msg={'asr_results': '我认为跑'} + [2022-04-21 15:59:05,724] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'} + [2022-04-21 15:59:05,732] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'} + [2022-04-21 15:59:05,740] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'} + [2022-04-21 15:59:05,747] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'} + [2022-04-21 15:59:05,755] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'} + [2022-04-21 15:59:05,763] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'} + [2022-04-21 15:59:05,770] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的'} + [2022-04-21 15:59:06,271] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'} + [2022-04-21 15:59:06,279] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'} + [2022-04-21 15:59:06,287] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'} + [2022-04-21 15:59:06,294] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'} + [2022-04-21 15:59:06,302] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'} + [2022-04-21 15:59:06,310] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'} + [2022-04-21 15:59:06,318] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'} + [2022-04-21 15:59:06,326] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是'} + [2022-04-21 15:59:06,833] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'} + [2022-04-21 15:59:06,842] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'} + [2022-04-21 15:59:06,850] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'} + [2022-04-21 15:59:06,858] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'} + [2022-04-21 15:59:06,866] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'} + [2022-04-21 15:59:06,874] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'} + [2022-04-21 15:59:06,882] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给'} + [2022-04-21 15:59:07,400] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'} + [2022-04-21 15:59:07,408] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'} + [2022-04-21 15:59:07,416] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'} + [2022-04-21 15:59:07,424] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'} + [2022-04-21 15:59:07,432] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'} + [2022-04-21 15:59:07,440] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'} + [2022-04-21 15:59:07,447] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'} + [2022-04-21 15:59:07,455] [ INFO] - receive msg={'asr_results': '我认为跑步最重要的就是给我带来了'} + [2022-04-21 15:59:07,984] [ 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 15:59:07,992] [ 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 15:59:08,001] [ 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 15:59:08,008] [ 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 15:59:08,016] [ 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'} + [2022-04-21 15:59:12,884] [ INFO] - 我认为跑步最重要的就是给我带来了身体健康 + ``` + + +#### 4.2 使用 `paddlespeech_client asr_online` + +**注意：** 初次使用客户端时响应时间会略长 +- 命令行 (推荐使用) + ``` + # 使用 paddlespecch_asr 需要指定传入协议为 websocket + paddlespeech_client asr_online --server_ip 127.0.0.1 --port 8090 --input ./zh.wav ``` 使用帮助: ```bash - paddlespeech_client asr_online --help + paddlespeech_client asr help ``` 参数: @@ -205,6 +394,9 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav - `sample_rate`: 音频采样率，默认值：16000。 - `lang`: 模型语言，默认值：zh_cn。 - `audio_format`: 音频格式，默认值：wav。 + - `protocol` 指定客户端和服务端之间服务的协议。在流式识别中必须指定 websocket。 + - `punc.server_ip` 标点预测服务的ip。默认是None。 + - `punc.server_port` 标点预测服务的端口port。默认是None。 输出: diff --git a/examples/voxceleb/sv0/README.md b/examples/voxceleb/sv0/README.md index 1069cfe7..418102b4 100644 --- a/examples/voxceleb/sv0/README.md +++ b/examples/voxceleb/sv0/README.md @@ -146,6 +146,6 @@ tar -xvf sv0_ecapa_tdnn_voxceleb12_ckpt_0_2_0.tar.gz source path.sh # If you have processed the data and get the manifest file， you can skip the following 2 steps -CUDA_VISIBLE_DEVICES= ./local/test.sh ./data sv0_ecapa_tdnn_voxceleb12_ckpt_0_1_2 conf/ecapa_tdnn.yaml +CUDA_VISIBLE_DEVICES= bash ./local/test.sh ./data sv0_ecapa_tdnn_voxceleb12_ckpt_0_1_2/model/ conf/ecapa_tdnn.yaml ``` The performance of the released models are shown in [this](./RESULTS.md) diff --git a/examples/voxceleb/sv0/local/test.sh b/examples/voxceleb/sv0/local/test.sh index 4460a165..800fa67d 100644 --- a/examples/voxceleb/sv0/local/test.sh +++ b/examples/voxceleb/sv0/local/test.sh @@ -33,10 +33,26 @@ dir=$1 exp_dir=$2 conf_path=$3 +# get the gpu nums for training +ngpu=$(echo $CUDA_VISIBLE_DEVICES | awk -F "," '{print NF}') +echo "using $ngpu gpus..." + +# setting training device +device="cpu" +if ${use_gpu}; then + device="gpu" +fi +if [ $ngpu -le 0 ]; then + echo "no gpu, training in cpu mode" + device='cpu' + use_gpu=false +fi + if [ ${stage} -le 1 ] && [ ${stop_stage} -ge 1 ]; then # test the model and compute the eer metrics python3 ${BIN_DIR}/test.py \ --data-dir ${dir} \ --load-checkpoint ${exp_dir} \ - --config ${conf_path} + --config ${conf_path} \ + --device ${device} fi diff --git a/paddlespeech/server/bin/paddlespeech_client.py b/paddlespeech/server/bin/paddlespeech_client.py index a424c82f..6c2bfdd5 100644 --- a/paddlespeech/server/bin/paddlespeech_client.py +++ b/paddlespeech/server/bin/paddlespeech_client.py @@ -35,7 +35,7 @@ from paddlespeech.server.utils.util import wav2base64 __all__ = [ 'TTSClientExecutor', 'TTSOnlineClientExecutor', 'ASRClientExecutor', - 'CLSClientExecutor' + 'ASROnlineClientExecutor', 'CLSClientExecutor' ] @@ -397,6 +397,77 @@ class ASRClientExecutor(BaseExecutor): return res +@cli_client_register( + name='paddlespeech_client.asr_online', + description='visit asr online service') +class ASROnlineClientExecutor(BaseExecutor): + def __init__(self): + super(ASROnlineClientExecutor, self).__init__() + self.parser = argparse.ArgumentParser( + prog='paddlespeech_client.asr_online', add_help=True) + self.parser.add_argument( + '--server_ip', type=str, default='127.0.0.1', help='server ip') + self.parser.add_argument( + '--port', type=int, default=8091, help='server port') + self.parser.add_argument( + '--input', + type=str, + default=None, + help='Audio file to be recognized', + required=True) + self.parser.add_argument( + '--sample_rate', type=int, default=16000, help='audio sample rate') + self.parser.add_argument( + '--lang', type=str, default="zh_cn", help='language') + self.parser.add_argument( + '--audio_format', type=str, default="wav", help='audio format') + + def execute(self, argv: List[str]) -> bool: + args = self.parser.parse_args(argv) + input_ = args.input + server_ip = args.server_ip + port = args.port + sample_rate = args.sample_rate + lang = args.lang + audio_format = args.audio_format + try: + time_start = time.time() + res = self( + input=input_, + server_ip=server_ip, + port=port, + sample_rate=sample_rate, + lang=lang, + audio_format=audio_format) + time_end = time.time() + logger.info(res) + logger.info("Response time %f s." % (time_end - time_start)) + return True + except Exception as e: + logger.error("Failed to speech recognition.") + logger.error(e) + return False + + @stats_wrapper + def __call__(self, + input: str, + server_ip: str="127.0.0.1", + port: int=8091, + sample_rate: int=16000, + lang: str="zh_cn", + audio_format: str="wav"): + """ + Python API to call an executor. + """ + logger.info("asr websocket client start") + handler = ASRWsAudioHandler(server_ip, port) + loop = asyncio.get_event_loop() + res = loop.run_until_complete(handler.run(input)) + logger.info("asr websocket client finished") + + return res['result'] + + @cli_client_register( name='paddlespeech_client.cls', description='visit cls service') class CLSClientExecutor(BaseExecutor): @@ -521,4 +592,4 @@ class TextClientExecutor(BaseExecutor): res = requests.post(url=url, data=json.dumps(request)) response_dict = res.json() punc_text = response_dict["result"]["punc_text"] - return punc_text \ No newline at end of file + return punc_text -- GitLab