msb-public
/
PaddleSpeech
mirror of https://github.com/PaddlePaddle/PaddleSpeech
1
0
Code Issues Projects Releases Wiki Activity

[server] update readme (#1851)

Browse Source 
* update readme, test=doc

* update readme, test=doc

* update readme, test=doc
pull/1856/head
liangym 3 years ago committed by GitHub
parent 6f7c3d6c85
commit e87495f045
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
7 changed files with 45 additions and 32 deletions
Show Stats Download Patch File Download Diff File

11
demos/speech_server/README.md
Unescape View File

@ -10,7 +10,7 @@ This demo is an implementation of starting the voice service and accessing the s
### 1. Installation ### 1. Installation
see [installation](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md). see [installation](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md).
It is recommended to use **paddlepaddle 2.2.1** or above. It is recommended to use **paddlepaddle 2.2.2** or above.
You can choose one way from meduim and hard to install paddlespeech. You can choose one way from meduim and hard to install paddlespeech.
### 2. Prepare config File ### 2. Prepare config File
@ -18,6 +18,7 @@ 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 `<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). 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) Currently the engine type supports two forms: python and inference (Paddle Inference)
**Note:** If the service can be started normally in the container, but the client access IP is unreachable, you can try to replace the `host` address in the configuration file with the local IP address.
The input of ASR client demo should be a WAV file(`.wav`), and the sample rate must be the same as the model. The input of ASR client demo should be a WAV file(`.wav`), and the sample rate must be the same as the model.
@ -51,8 +52,8 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee
[2022-02-23 11:17:32] [INFO] [on.py:26] Waiting for application startup. [2022-02-23 11:17:32] [INFO] [on.py:26] Waiting for application startup.
INFO: Application startup complete. INFO: Application startup complete.
[2022-02-23 11:17:32] [INFO] [on.py:38] Application startup complete. [2022-02-23 11:17:32] [INFO] [on.py:38] Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit) INFO: Uvicorn running on http://127.0.0.1:8090 (Press CTRL+C to quit)
[2022-02-23 11:17:32] [INFO] [server.py:204] Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit) [2022-02-23 11:17:32] [INFO] [server.py:204] Uvicorn running on http://127.0.0.1:8090 (Press CTRL+C to quit)
``` ```
@ -74,8 +75,8 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee
[2022-02-23 14:57:56] [INFO] [on.py:26] Waiting for application startup. [2022-02-23 14:57:56] [INFO] [on.py:26] Waiting for application startup.
INFO: Application startup complete. INFO: Application startup complete.
[2022-02-23 14:57:56] [INFO] [on.py:38] Application startup complete. [2022-02-23 14:57:56] [INFO] [on.py:38] Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit) INFO: Uvicorn running on http://127.0.0.1:8090 (Press CTRL+C to quit)
[2022-02-23 14:57:56] [INFO] [server.py:204] Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit) [2022-02-23 14:57:56] [INFO] [server.py:204] Uvicorn running on http://127.0.0.1:8090 (Press CTRL+C to quit)
``` ```

19
demos/speech_server/README_cn.md
Unescape View File

@ -1,17 +1,17 @@
([简体中文](./README_cn.md)|English) (简体中文|[English](./README.md))
# 语音服务 # 语音服务
## 介绍 ## 介绍
这个demo是一个启动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。 这个demo是一个启动离线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。
## 使用方法 ## 使用方法
### 1. 安装 ### 1. 安装
请看 [安装文档](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md). 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。 推荐使用 **paddlepaddle 2.2.2** 或以上版本。
你可以从 medium，hard 三中方式中选择一种方式安装 PaddleSpeech。 你可以从 medium，hard 两种方式中选择一种方式安装 PaddleSpeech。
### 2. 准备配置文件 ### 2. 准备配置文件
@ -19,9 +19,10 @@
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>。 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)以及cls(音频分类)。 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) 目前引擎类型支持两种形式：python 及 inference (Paddle Inference)
**注意：** 如果在容器里可正常启动服务，但客户端访问 ip 不可达，可尝试将配置文件中 `host` 地址换成本地 ip 地址。
这个 ASR client 的输入应该是一个 WAV 文件（`.wav`），并且采样率必须与模型的采样率相同。 ASR client 的输入是一个 WAV 文件（`.wav`），并且采样率必须与模型的采样率相同。
可以下载此 ASR client的示例音频： 可以下载此 ASR client的示例音频：
```bash ```bash
@ -52,8 +53,8 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee
[2022-02-23 11:17:32] [INFO] [on.py:26] Waiting for application startup. [2022-02-23 11:17:32] [INFO] [on.py:26] Waiting for application startup.
INFO: Application startup complete. INFO: Application startup complete.
[2022-02-23 11:17:32] [INFO] [on.py:38] Application startup complete. [2022-02-23 11:17:32] [INFO] [on.py:38] Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit) INFO: Uvicorn running on http://127.0.0.1:8090 (Press CTRL+C to quit)
[2022-02-23 11:17:32] [INFO] [server.py:204] Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit) [2022-02-23 11:17:32] [INFO] [server.py:204] Uvicorn running on http://127.0.0.1:8090 (Press CTRL+C to quit)
``` ```
@ -75,8 +76,8 @@ wget -c https://paddlespeech.bj.bcebos.com/PaddleAudio/zh.wav https://paddlespee
[2022-02-23 14:57:56] [INFO] [on.py:26] Waiting for application startup. [2022-02-23 14:57:56] [INFO] [on.py:26] Waiting for application startup.
INFO: Application startup complete. INFO: Application startup complete.
[2022-02-23 14:57:56] [INFO] [on.py:38] Application startup complete. [2022-02-23 14:57:56] [INFO] [on.py:38] Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit) INFO: Uvicorn running on http://127.0.0.1:8090 (Press CTRL+C to quit)
[2022-02-23 14:57:56] [INFO] [server.py:204] Uvicorn running on http://0.0.0.0:8090 (Press CTRL+C to quit) [2022-02-23 14:57:56] [INFO] [server.py:204] Uvicorn running on http://127.0.0.1:8090 (Press CTRL+C to quit)
``` ```

6
demos/speech_server/conf/application.yaml
Unescape View File

@ -1,4 +1,4 @@
# This is the parameter configuration file for PaddleSpeech Serving. # This is the parameter configuration file for PaddleSpeech Offline Serving.
################################################################################# #################################################################################
# SERVER SETTING # # SERVER SETTING #
@ -7,8 +7,8 @@ host: 127.0.0.1
port: 8090 port: 8090
# The task format in the engin_list is: <speech task>_<engine type> # The task format in the engin_list is: <speech task>_<engine type>
# task choices = ['asr_python', 'asr_inference', 'tts_python', 'tts_inference'] # task choices = ['asr_python', 'asr_inference', 'tts_python', 'tts_inference', 'cls_python', 'cls_inference']
protocol: 'http'
engine_list: ['asr_python', 'tts_python', 'cls_python'] engine_list: ['asr_python', 'tts_python', 'cls_python']

6
demos/streaming_tts_server/README.md
Unescape View File

@ -10,7 +10,7 @@ This demo is an implementation of starting the streaming speech synthesis servic
### 1. Installation ### 1. Installation
see [installation](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md). see [installation](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md).
It is recommended to use **paddlepaddle 2.2.1** or above. It is recommended to use **paddlepaddle 2.2.2** or above.
You can choose one way from meduim and hard to install paddlespeech. You can choose one way from meduim and hard to install paddlespeech.
@ -29,6 +29,8 @@ The configuration file can be found in `conf/tts_online_application.yaml`.
- When the voc model is mb_melgan, when voc_pad=14, the synthetic audio for streaming inference is consistent with the non-streaming synthetic audio; the minimum voc_pad can be set to 7, and the synthetic audio has no abnormal hearing. If the voc_pad is less than 7, the synthetic audio sounds abnormal. - When the voc model is mb_melgan, when voc_pad=14, the synthetic audio for streaming inference is consistent with the non-streaming synthetic audio; the minimum voc_pad can be set to 7, and the synthetic audio has no abnormal hearing. If the voc_pad is less than 7, the synthetic audio sounds abnormal.
- When the voc model is hifigan, when voc_pad=20, the streaming inference synthetic audio is consistent with the non-streaming synthetic audio; when voc_pad=14, the synthetic audio has no abnormal hearing. - When the voc model is hifigan, when voc_pad=20, the streaming inference synthetic audio is consistent with the non-streaming synthetic audio; when voc_pad=14, the synthetic audio has no abnormal hearing.
- Inference speed: mb_melgan > hifigan; Audio quality: mb_melgan < hifigan - Inference speed: mb_melgan > hifigan; Audio quality: mb_melgan < hifigan
- **Note:** If the service can be started normally in the container, but the client access IP is unreachable, you can try to replace the `host` address in the configuration file with the local IP address.
### 3. Streaming speech synthesis server and client using http protocol ### 3. Streaming speech synthesis server and client using http protocol
@ -120,6 +122,7 @@ The configuration file can be found in `conf/tts_online_application.yaml`.
- `sample_rate`: Sampling rate, choices: [0, 8000, 16000], the default is the same as the model. Default: 0 - `sample_rate`: Sampling rate, choices: [0, 8000, 16000], the default is the same as the model. Default: 0
- `output`: Output wave filepath. Default: None, which means not to save the audio to the local. - `output`: Output wave filepath. Default: None, which means not to save the audio to the local.
- `play`: Whether to play audio, play while synthesizing, default value: False, which means not playing. **Playing audio needs to rely on the pyaudio library**. - `play`: Whether to play audio, play while synthesizing, default value: False, which means not playing. **Playing audio needs to rely on the pyaudio library**.
- `spk_id, speed, volume, sample_rate` do not take effect in streaming speech synthesis service temporarily.
Output: Output:
```bash ```bash
@ -254,6 +257,7 @@ The configuration file can be found in `conf/tts_online_application.yaml`.
- `sample_rate`: Sampling rate, choices: [0, 8000, 16000], the default is the same as the model. Default: 0 - `sample_rate`: Sampling rate, choices: [0, 8000, 16000], the default is the same as the model. Default: 0
- `output`: Output wave filepath. Default: None, which means not to save the audio to the local. - `output`: Output wave filepath. Default: None, which means not to save the audio to the local.
- `play`: Whether to play audio, play while synthesizing, default value: False, which means not playing. **Playing audio needs to rely on the pyaudio library**. - `play`: Whether to play audio, play while synthesizing, default value: False, which means not playing. **Playing audio needs to rely on the pyaudio library**.
- `spk_id, speed, volume, sample_rate` do not take effect in streaming speech synthesis service temporarily.
Output: Output:

30
demos/streaming_tts_server/README_cn.md
Unescape View File

@ -10,25 +10,27 @@
### 1. 安装 ### 1. 安装
请看 [安装文档](https://github.com/PaddlePaddle/PaddleSpeech/blob/develop/docs/source/install.md). 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。 推荐使用 **paddlepaddle 2.2.2** 或以上版本。
你可以从 medium，hard 两种方式中选择一种方式安装 PaddleSpeech。 你可以从 medium，hard 两种方式中选择一种方式安装 PaddleSpeech。
### 2. 准备配置文件 ### 2. 准备配置文件
配置文件可参见 `conf/tts_online_application.yaml` 。 配置文件可参见 `conf/tts_online_application.yaml` 。
- `protocol`表示该流式TTS服务使用的网络协议，目前支持 **http 和 websocket** 两种。 - `protocol` 表示该流式 TTS 服务使用的网络协议，目前支持 **http 和 websocket** 两种。
- `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>。 - `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>。
- 该demo主要介绍流式语音合成服务，因此语音任务应设置为tts。 - 该 demo 主要介绍流式语音合成服务，因此语音任务应设置为 tts。
- 目前引擎类型支持两种形式：**online** 表示使用python进行动态图推理的引擎；**online-onnx** 表示使用onnxruntime进行推理的引擎。其中，online-onnx的推理速度更快。 - 目前引擎类型支持两种形式：**online** 表示使用python进行动态图推理的引擎；**online-onnx** 表示使用 onnxruntime 进行推理的引擎。其中，online-onnx 的推理速度更快。
- 流式TTS引擎的AM模型支持：**fastspeech2 以及fastspeech2_cnndecoder**; Voc 模型支持：**hifigan, mb_melgan** - 流式 TTS 引擎的 AM 模型支持：**fastspeech2 以及fastspeech2_cnndecoder**; Voc 模型支持：**hifigan, mb_melgan**
- 流式am推理中，每次会对一个chunk的数据进行推理以达到流式的效果。其中`am_block`表示chunk中的有效帧数，`am_pad` 表示一个chunk中am_block前后各加的帧数。am_pad的存在用于消除流式推理产生的误差，避免由流式推理对合成音频质量的影响。 - 流式 am 推理中，每次会对一个 chunk 的数据进行推理以达到流式的效果。其中 `am_block` 表示 chunk 中的有效帧数，`am_pad` 表示一个 chunk 中 am_block 前后各加的帧数。am_pad 的存在用于消除流式推理产生的误差，避免由流式推理对合成音频质量的影响。
- fastspeech2不支持流式am推理，因此am_pad与am_block对它无效 - fastspeech2 不支持流式 am 推理，因此 am_pad 与 m_block 对它无效
- fastspeech2_cnndecoder 支持流式推理，当am_pad=12时，流式推理合成音频与非流式合成音频一致 - fastspeech2_cnndecoder 支持流式推理，当 am_pad=12 时，流式推理合成音频与非流式合成音频一致
- 流式voc推理中，每次会对一个chunk的数据进行推理以达到流式的效果。其中`voc_block`表示chunk中的有效帧数，`voc_pad` 表示一个chunk中voc_block前后各加的帧数。voc_pad的存在用于消除流式推理产生的误差，避免由流式推理对合成音频质量的影响。 - 流式 voc 推理中，每次会对一个 chunk 的数据进行推理以达到流式的效果。其中 `voc_block` 表示chunk中的有效帧数，`voc_pad` 表示一个 chunk 中 voc_block 前后各加的帧数。voc_pad 的存在用于消除流式推理产生的误差，避免由流式推理对合成音频质量的影响。
- hifigan, mb_melgan 均支持流式voc 推理 - hifigan, mb_melgan 均支持流式 voc 推理
- 当voc模型为mb_melgan，当voc_pad=14时，流式推理合成音频与非流式合成音频一致；voc_pad最小可以设置为7，合成音频听感上没有异常，若voc_pad小于7，合成音频听感上存在异常。 - 当 voc 模型为 mb_melgan，当 voc_pad=14 时，流式推理合成音频与非流式合成音频一致；voc_pad 最小可以设置为7，合成音频听感上没有异常，若 voc_pad 小于7，合成音频听感上存在异常。
- 当voc模型为hifigan，当voc_pad=20时，流式推理合成音频与非流式合成音频一致；当voc_pad=14时，合成音频听感上没有异常。 - 当 voc 模型为 hifigan，当 voc_pad=20 时，流式推理合成音频与非流式合成音频一致；当 voc_pad=14 时，合成音频听感上没有异常。
- 推理速度：mb_melgan > hifigan; 音频质量：mb_melgan < hifigan - 推理速度：mb_melgan > hifigan; 音频质量：mb_melgan < hifigan
- **注意：** 如果在容器里可正常启动服务，但客户端访问 ip 不可达，可尝试将配置文件中 `host` 地址换成本地 ip 地址。
### 3. 使用http协议的流式语音合成服务端及客户端使用方法 ### 3. 使用http协议的流式语音合成服务端及客户端使用方法
#### 3.1 服务端使用方法 #### 3.1 服务端使用方法
@ -119,6 +121,7 @@
- `sample_rate`: 采样率，可选 [0, 8000, 16000]，默认值：0，表示与模型采样率相同 - `sample_rate`: 采样率，可选 [0, 8000, 16000]，默认值：0，表示与模型采样率相同
- `output`: 输出音频的路径， 默认值：None，表示不保存音频到本地。 - `output`: 输出音频的路径， 默认值：None，表示不保存音频到本地。
- `play`: 是否播放音频，边合成边播放， 默认值：False，表示不播放。**播放音频需要依赖pyaudio库**。 - `play`: 是否播放音频，边合成边播放， 默认值：False，表示不播放。**播放音频需要依赖pyaudio库**。
- `spk_id, speed, volume, sample_rate` 在流式语音合成服务中暂时不生效。
输出: 输出:
@ -254,6 +257,7 @@
- `sample_rate`: 采样率，可选 [0, 8000, 16000]，默认值：0，表示与模型采样率相同 - `sample_rate`: 采样率，可选 [0, 8000, 16000]，默认值：0，表示与模型采样率相同
- `output`: 输出音频的路径， 默认值：None，表示不保存音频到本地。 - `output`: 输出音频的路径， 默认值：None，表示不保存音频到本地。
- `play`: 是否播放音频，边合成边播放， 默认值：False，表示不播放。**播放音频需要依赖pyaudio库**。 - `play`: 是否播放音频，边合成边播放， 默认值：False，表示不播放。**播放音频需要依赖pyaudio库**。
- `spk_id, speed, volume, sample_rate` 在流式语音合成服务中暂时不生效。
输出: 输出:

4
paddlespeech/server/README.md
Unescape View File

@ -10,7 +10,9 @@
paddlespeech_server help paddlespeech_server help
``` ```
### Start the server ### Start the server
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 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.
**Note:** If the service can be started normally in the container, but the client access IP is unreachable, you can try to replace the `host` address in the configuration file with the local IP address.
Then start the service: Then start the service:
```bash ```bash
paddlespeech_server start --config_file ./conf/application.yaml paddlespeech_server start --config_file ./conf/application.yaml

1
paddlespeech/server/README_cn.md
Unescape View File

@ -11,6 +11,7 @@
``` ```
### 启动服务 ### 启动服务
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。 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。
**注意：** 如果在容器里可正常启动服务，但客户端访问 ip 不可达，可尝试将配置文件中 `host` 地址换成本地 ip 地址。
然后启动服务： 然后启动服务：
```bash ```bash
paddlespeech_server start --config_file ./conf/application.yaml paddlespeech_server start --config_file ./conf/application.yaml

Write Preview
Loading…
Cancel
Save