From 965b388c221b86323e4667f2f958bea604930448 Mon Sep 17 00:00:00 2001 From: lym0302 Date: Thu, 24 Mar 2022 19:27:32 +0800 Subject: [PATCH 1/4] update readme, test=doc --- README.md | 31 +++++++++++++++++++++++++++++++ README_cn.md | 28 ++++++++++++++++++++++++++++ 2 files changed, 59 insertions(+) diff --git a/README.md b/README.md index ceef15af6..f1570b4a0 100644 --- a/README.md +++ b/README.md @@ -7,6 +7,7 @@

Quick Start + | Quick Start Server | Documents | Models List @@ -242,6 +243,36 @@ For more command lines, please see: [demos](https://github.com/PaddlePaddle/Padd If you want to try more functions like training and tuning, please have a look at [Speech-to-Text Quick Start](./docs/source/asr/quick_start.md) and [Text-to-Speech Quick Start](./docs/source/tts/quick_start.md). + + +## Quick Start Server + +Developers can have a try of our speech server with [PaddleSpeech Server Command Line](./paddlespeech/server/README.md). + +**Start server** +```shell +paddlespeech_server start --config_file ./paddlespeech/server/conf/application.yaml +``` + +**Access Speech Recognition Services** +```shell +paddlespeech_client asr --server_ip 127.0.0.1 --port 8090 --input input_16k.wav +``` + +**Access Text to Speech Services** +```shell +paddlespeech_client tts --server_ip 127.0.0.1 --port 8090 --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav +``` + +**Access Audio Classification Services** +```shell +paddlespeech_client cls --server_ip 127.0.0.1 --port 8090 --input input.wav +``` + + +For more information about server command lines, please see: [speech server demos](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/demos/speech_server) + + ## Model List PaddleSpeech supports a series of most popular models. They are summarized in [released models](./docs/source/released_model.md) and attached with available pretrained models. diff --git a/README_cn.md b/README_cn.md index 8ea91e98d..70f6b2d95 100644 --- a/README_cn.md +++ b/README_cn.md @@ -6,6 +6,7 @@

快速开始 + | 快速使用服务 | 教程文档 | 模型列表 @@ -236,6 +237,33 @@ paddlespeech asr --input ./zh.wav | paddlespeech text --task punc 更多命令行命令请参考 [demos](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/demos) > Note: 如果需要训练或者微调，请查看[语音识别](./docs/source/asr/quick_start.md)， [语音合成](./docs/source/tts/quick_start.md)。 + +## 快速使用服务 +安装完成后，开发者可以通过命令行快速使用服务。 + +**启动服务** +```shell +paddlespeech_server start --config_file ./paddlespeech/server/conf/application.yaml +``` + +**访问语音识别服务** +```shell +paddlespeech_client asr --server_ip 127.0.0.1 --port 8090 --input input_16k.wav +``` + +**访问语音合成服务** +```shell +paddlespeech_client tts --server_ip 127.0.0.1 --port 8090 --input "您好，欢迎使用百度飞桨语音合成服务。" --output output.wav +``` + +**访问音频分类服务** +```shell +paddlespeech_client cls --server_ip 127.0.0.1 --port 8090 --input input.wav +``` + +更多服务相关的命令行使用信息，请参考 [demos](https://github.com/PaddlePaddle/PaddleSpeech/tree/develop/demos/speech_server) + + ## 模型列表 PaddleSpeech 支持很多主流的模型，并提供了预训练模型，详情请见[模型列表](./docs/source/released_model.md)。 From 829f1e332eaa9d788df112d333749e83bf184f5e Mon Sep 17 00:00:00 2001 From: lym0302 Date: Thu, 24 Mar 2022 19:39:35 +0800 Subject: [PATCH 2/4] update readme, test=doc --- paddlespeech/server/README.md | 8 ++++++-- paddlespeech/server/README_cn.md | 7 ++++++- 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/paddlespeech/server/README.md b/paddlespeech/server/README.md index 4ce9605d6..819fe440d 100644 --- a/paddlespeech/server/README.md +++ b/paddlespeech/server/README.md @@ -10,7 +10,7 @@ paddlespeech_server help ``` ### Start the server - First set the service-related configuration parameters, similar to `./conf/application.yaml`, + First set the service-related configuration parameters, similar to `./conf/application.yaml`. Set `engine_list`, which represents the speech tasks included in the service to be started Then start the service: ```bash paddlespeech_server start --config_file ./conf/application.yaml @@ -23,7 +23,7 @@ ``` ### Access speech recognition services ``` - paddlespeech_client asr --server_ip 127.0.0.1 --port 8090 --input ./tests/16_audio.wav + paddlespeech_client asr --server_ip 127.0.0.1 --port 8090 --input input_16k.wav ``` ### Access text to speech services @@ -31,3 +31,7 @@ paddlespeech_client tts --server_ip 127.0.0.1 --port 8090 --input "你好，欢迎使用百度飞桨深度学习框架！" --output output.wav ``` + ### Access audio classification services + ```bash + paddlespeech_client cls --server_ip 127.0.0.1 --port 8090 --input input.wav + ``` diff --git a/paddlespeech/server/README_cn.md b/paddlespeech/server/README_cn.md index 2dfd9474b..c0a4a7336 100644 --- a/paddlespeech/server/README_cn.md +++ b/paddlespeech/server/README_cn.md @@ -10,7 +10,7 @@ paddlespeech_server help ``` ### 启动服务 - 首先设置服务相关配置文件，类似于 `./conf/application.yaml`，同时设置服务配置中的语音任务模型相关配置，类似于 `./conf/tts/tts.yaml`。 + 首先设置服务相关配置文件，类似于 `./conf/application.yaml`，设置 `engine_list`，该值表示即将启动的服务中包含的语音任务。 然后启动服务： ```bash paddlespeech_server start --config_file ./conf/application.yaml @@ -30,3 +30,8 @@ ```bash paddlespeech_client tts --server_ip 127.0.0.1 --port 8090 --input "你好，欢迎使用百度飞桨深度学习框架！" --output output.wav ``` + + ### 访问音频分类服务 + ```bash + paddlespeech_client cls --server_ip 127.0.0.1 --port 8090 --input input.wav + ``` From 754ecabac493e34f4fe42ec24c1d73af44c16f47 Mon Sep 17 00:00:00 2001 From: lym0302 Date: Thu, 24 Mar 2022 20:01:31 +0800 Subject: [PATCH 3/4] update readme, test=doc --- demos/speech_server/README.md | 4 ++-- demos/speech_server/README_cn.md | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/demos/speech_server/README.md b/demos/speech_server/README.md index 10489e713..66bf11caa 100644 --- a/demos/speech_server/README.md +++ b/demos/speech_server/README.md @@ -15,8 +15,8 @@ You can choose one way from meduim and hard to install paddlespeech. ### 2. Prepare config File The configuration file can be found in `conf/application.yaml` . -Among them, `engine_list` indicates the speech engine that will be included in the service to be started, in the format of _. -At present, the speech tasks integrated by the service include: asr (speech recognition) and tts (speech synthesis). +Among them, `engine_list` indicates the speech engine that will be included in the service to be started, in the format of speech task_engine type. +At present, the speech tasks integrated by the service include: asr (speech recognition), tts (text to sppech) and cls (audio classification). Currently the engine type supports two forms: python and inference (Paddle Inference) diff --git a/demos/speech_server/README_cn.md b/demos/speech_server/README_cn.md index 2bd8af6c9..687b51f10 100644 --- a/demos/speech_server/README_cn.md +++ b/demos/speech_server/README_cn.md @@ -17,7 +17,7 @@ ### 2. 准备配置文件 配置文件可参见 `conf/application.yaml` 。 其中，`engine_list`表示即将启动的服务将会包含的语音引擎，格式为 <语音任务>_<引擎类型>。 -目前服务集成的语音任务有： asr(语音识别)、tts(语音合成)。 +目前服务集成的语音任务有： asr(语音识别)、tts(语音合成)以及cls(音频分类)。 目前引擎类型支持两种形式：python 及 inference (Paddle Inference) From ec8c870f85e06ea5cc3625125d9df94795ec99ae Mon Sep 17 00:00:00 2001 From: lym0302 Date: Thu, 24 Mar 2022 20:03:38 +0800 Subject: [PATCH 4/4] update readme, test=doc --- demos/speech_server/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/demos/speech_server/README.md b/demos/speech_server/README.md index 66bf11caa..0323d3983 100644 --- a/demos/speech_server/README.md +++ b/demos/speech_server/README.md @@ -15,7 +15,7 @@ You can choose one way from meduim and hard to install paddlespeech. ### 2. Prepare config File The configuration file can be found in `conf/application.yaml` . -Among them, `engine_list` indicates the speech engine that will be included in the service to be started, in the format of speech task_engine type. +Among them, `engine_list` indicates the speech engine that will be included in the service to be started, in the format of `_`. At present, the speech tasks integrated by the service include: asr (speech recognition), tts (text to sppech) and cls (audio classification). Currently the engine type supports two forms: python and inference (Paddle Inference)