增加docker安装paddle-speech

trphoenix

2025-09-21 c93351f30b4b206dd749bfe0c037729bc2e534a0

增加docker安装paddle-speech

 Help/docs/Usages/QA/语音合成与识别服务Docker-部署说明.md

New file
@@ -0,0 +1,1008 @@
# 语音合成与识别服务Docker-部署说明

## 一、简介
语音合成与识别服务（以下简称“服务”）提供高质量的文本转语音（TTS）和语音转文本（ASR）功能。为了方便用户快速部署和使用该服务，我们提供了基于Docker的部署方案。本文档将详细介绍如何使用Docker部署该服务。
本文提供的语音合成与识别服务，是基于paddlespeech开发的TTS和ASR服务(纯CPU服务)，用户可以通过Docker快速部署并使用该服务。
## 二、环境准备
在开始部署之前，请确保您的环境满足以下要求：
1. 已安装Docker和Docker Compose。
2. 具备一定的Linux命令行操作基础。
3. 确保您的服务器具备足够的计算资源（CPU、内存、GPU等）。
## 三、获取Docker镜像
我们提供了预构建的Docker镜像，地址位于七牛云，地址为：

```
https://datacdn.data-it.tech/HomeAssistant/dokerimages/paddlespeech1.1/paddlespeech.tar
```


## 四、在线部署步骤

### 执行一键安装脚本

```
curl -fsSL   https://datacdn.data-it.tech/HomeAssistant/dokerimages/paddlespeech1.1/install-paddlespeech.sh | sudo bash
```
#### 如下图所示:
![](https://qncdn.tairongkj.com/docs/images/20250921094451.png)
![](https://qncdn.tairongkj.com/docs/images/20250921095852.png)


### 首次运行

使用TTS或asr服务，首次运行会自动下载模型文件，模型文件较大,***下载过程约需10分钟***，请耐心等待。
#### 如下所示
我们可以如用下命令实时查看运行日志:

```
docker logs -f paddlespeech
```
TTS模型首次使用时侍自动从网络下载约2G的模型文件，下载完成后会自动启动服务。后续再次使用时，不会重复下载模型文件。
![](https://qncdn.tairongkj.com/docs/images/20250921093139.png)
Asr模型首次使用时侍自动从网络下载约1G的模型文件，下载完成后会自动启动服务。后续再次使用时，不会重复下载模型文件。
![](https://qncdn.tairongkj.com/docs/images/20250921093510.png)

##　五、离线部署步骤
### 离线部署的相关文件下载地址

1. Docker镜像文件: [下载地址](https://datacdn.data-it.tech/HomeAssistant/dokerimages/paddlespeech1.1/paddlespeech.tar)
2. 数据卷文件: 以下文件要下载并复制到目标机器临时认置的目录,与install-paddlespeech-localh.sh所在目录同级的子目录data目录下
    - [home_dtuser_opt_paddlespeech_data_logs.tar.gz](https://datacdn.data-it.tech/HomeAssistant/dokerimages/paddlespeech1.1/data/home_dtuser_opt_paddlespeech_data_logs.tar.gz)
    - [home_dtuser_opt_paddlespeech_data_nltk_data.tar.gz](https://datacdn.data-it.tech/HomeAssistant/dokerimages/paddlespeech1.1/data/home_dtuser_opt_paddlespeech_data_nltk_data.tar.gz)
    - [home_dtuser_opt_paddlespeech_data_output.tar.gz](https://datacdn.data-it.tech/HomeAssistant/dokerimages/paddlespeech1.1/data/home_dtuser_opt_paddlespeech_data_output.tar.gz)
    - [home_dtuser_opt_paddlespeech_data_paddlenlp_models.tar.gz](https://datacdn.data-it.tech/HomeAssistant/dokerimages/paddlespeech1.1/data/home_dtuser_opt_paddlespeech_data_paddlenlp_models.tar.gz)
    - [home_dtuser_opt_paddlespeech_data_paddlespeech_models.tar.gz](https://datacdn.data-it.tech/HomeAssistant/dokerimages/paddlespeech1.1/data/home_dtuser_opt_paddlespeech_data_paddlespeech_models.tar.gz)
3. 离线安装脚本: [下载地址](https://datacdn.data-it.tech/HomeAssistant/dokerimages/paddlespeech1.1/install-paddlespeech-localh.sh)
4. 测试演示使用网页: [下载地址](https://datacdn.data-it.tech/HomeAssistant/dokerimages/paddlespeech1.1/tts_demo.zip)

***离线安装包分两部份，一部份是容器镜像，一部份是数据卷文件，安装启动容器前先替换对据卷绑定的目录，这样容器启动后无须下载模型，可以在无互联网的情况下直接使用***

### 1. 下载Docker镜像与数据卷文件
如下示例，我们将文件放到用户目录的down下,请保持相应的目录结构，如下所示：

```bash
tst@tst-VMware-Virtual-Platform:~/down$ pwd
/home/tst/down
tst@tst-VMware-Virtual-Platform:~/down$ ls
data  install-paddlespeech-localh.sh
tst@tst-VMware-Virtual-Platform:~/down$ tree
.
├── data
│   ├── home_dtuser_opt_paddlespeech_data_logs.tar.gz
│   ├── home_dtuser_opt_paddlespeech_data_nltk_data.tar.gz
│   ├── home_dtuser_opt_paddlespeech_data_output.tar.gz
│   ├── home_dtuser_opt_paddlespeech_data_paddlenlp_models.tar.gz
│   └── home_dtuser_opt_paddlespeech_data_paddlespeech_models.tar.gz
└── install-paddlespeech-localh.sh

2 directories, 6 files
```
 
![](https://qncdn.tairongkj.com/docs/images/20250921171328.png)

### 2. 给运行脚本添加执行权限

```bash
chmod +x install-paddlespeech-localh.sh
```
### 3. 执行安装脚本

```bash
sudo ./install-paddlespeech-localh.sh
```
按装脚本将会先解压文件，并加载docker镜像，然后启动容器，启动完成后，可以使用docker ps命令查看运行状态，如下所示：

```bash
tst@tst-VMware-Virtual-Platform:~/down$ sudo ./install-paddlespeech-localh.sh
[INFO] 开始 PaddleSpeech 离线安装...
[SUCCESS] 磁盘空间检查通过（55GB）
[INFO] 检测网络连接...
[SUCCESS] 网络连接正常
[INFO] 创建目录结构...
[SUCCESS] 目录结构创建完成
[INFO] 解压数据卷...
[INFO] 正在解压: /home/tst/down/data/home_dtuser_opt_paddlespeech_data_logs.tar.gz 到 /dt_opt/paddlespeech/data/logs
./
[INFO] 正在解压: /home/tst/down/data/home_dtuser_opt_paddlespeech_data_nltk_data.tar.gz 到 /dt_opt/paddlespeech/data/nltk_data
./
./taggers/
./taggers/averaged_perceptron_tagger/
./taggers/averaged_perceptron_tagger/averaged_perceptron_tagger.pickle
./taggers/averaged_perceptron_tagger.zip
./corpora/
./corpora/cmudict/
./corpora/cmudict/cmudict
./corpora/cmudict/README
./corpora/cmudict.zip
[INFO] 正在解压: /home/tst/down/data/home_dtuser_opt_paddlespeech_data_output.tar.gz 到 /dt_opt/paddlespeech/data/output
./
./2753d658-b228-4ae6-94fc-3404a41f4526.wav
./9f24d71e-9f29-4d60-aa13-677fd19bba46.wav
./38ea94c6-e19b-4e41-8cca-454d8e374a15.wav
./d44aa891-c36b-473f-aef3-44484f0cd74b.wav
./c5ef53d3-502b-4f81-9fdd-583836ba7096.wav
./3931cd47-e022-4385-b588-4a61e64e5eed.wav
./1d213380-eee6-43ba-88db-99ba9b5609df.wav
./c85f65de-a4c1-43aa-a251-52ce4e9df271.wav
./7cd5fc65-665b-444c-9c9f-41f1ce8036f8.wav
./f74dbda7-1cf8-4056-bd30-523b74af8b0e.wav
[INFO] 正在解压: /home/tst/down/data/home_dtuser_opt_paddlespeech_data_paddlenlp_models.tar.gz 到 /dt_opt/paddlespeech/data/paddlenlp_models
./
./packages/
./models/
./models/bert-base-chinese/
./models/bert-base-chinese/bert-base-chinese-vocab.txt
./models/bert-base-chinese/tokenizer_config.json
./models/bert-base-chinese/vocab.txt
./models/bert-base-chinese/special_tokens_map.json
./models/embeddings/
./models/.locks/
./models/.locks/bert-base-chinese/
./datasets/
[INFO] 正在解压: /home/tst/down/data/home_dtuser_opt_paddlespeech_data_paddlespeech_models.tar.gz 到 /dt_opt/paddlespeech/data/paddlespeech_models
./
./conf/
./conf/cache.yaml
./models/
./models/G2PWModel_1.1/
./models/G2PWModel_1.1/config.py
./models/G2PWModel_1.1/MONOPHONIC_CHARS.txt
./models/G2PWModel_1.1/__pycache__/
./models/G2PWModel_1.1/__pycache__/config.cpython-39.pyc
./models/G2PWModel_1.1/__pycache__/config.cpython-310.pyc
./models/G2PWModel_1.1/record.log
./models/G2PWModel_1.1/bopomofo_to_pinyin_wo_tune_dict.json
./models/G2PWModel_1.1/POLYPHONIC_CHARS.txt
./models/G2PWModel_1.1/char_bopomofo_dict.json
./models/G2PWModel_1.1/g2pW.onnx
./models/G2PWModel_1.1/version
./models/G2PWModel_1.1.zip
./models/conformer_wenetspeech-zh-16k/
./models/conformer_wenetspeech-zh-16k/1.0/
./models/conformer_wenetspeech-zh-16k/1.0/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar/
./models/conformer_wenetspeech-zh-16k/1.0/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar/conf/
./models/conformer_wenetspeech-zh-16k/1.0/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar/conf/preprocess.yaml
./models/conformer_wenetspeech-zh-16k/1.0/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar/conf/tuning/
./models/conformer_wenetspeech-zh-16k/1.0/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar/conf/tuning/decode.yaml
./models/conformer_wenetspeech-zh-16k/1.0/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar/conf/conformer.yaml
./models/conformer_wenetspeech-zh-16k/1.0/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar/conf/conformer_infer.yaml
./models/conformer_wenetspeech-zh-16k/1.0/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar/data/
./models/conformer_wenetspeech-zh-16k/1.0/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar/data/lang_char/
./models/conformer_wenetspeech-zh-16k/1.0/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar/data/lang_char/vocab.txt
./models/conformer_wenetspeech-zh-16k/1.0/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar/data/mean_std.json
./models/conformer_wenetspeech-zh-16k/1.0/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar/model.yaml
./models/conformer_wenetspeech-zh-16k/1.0/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar/exp/
./models/conformer_wenetspeech-zh-16k/1.0/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar/exp/conformer/
./models/conformer_wenetspeech-zh-16k/1.0/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar/exp/conformer/checkpoints/
./models/conformer_wenetspeech-zh-16k/1.0/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar/exp/conformer/checkpoints/wenetspeech.pdparams
./models/conformer_wenetspeech-zh-16k/1.0/asr1_conformer_wenetspeech_ckpt_0.1.1.model.tar.gz
./models/fastspeech2_csmsc-zh/
./models/fastspeech2_csmsc-zh/1.0/
./models/fastspeech2_csmsc-zh/1.0/fastspeech2_nosil_baker_ckpt_0.4.zip
./models/fastspeech2_csmsc-zh/1.0/fastspeech2_nosil_baker_ckpt_0.4/
./models/fastspeech2_csmsc-zh/1.0/fastspeech2_nosil_baker_ckpt_0.4/snapshot_iter_76000.pdz
./models/fastspeech2_csmsc-zh/1.0/fastspeech2_nosil_baker_ckpt_0.4/phone_id_map.txt
./models/fastspeech2_csmsc-zh/1.0/fastspeech2_nosil_baker_ckpt_0.4/default.yaml
./models/fastspeech2_csmsc-zh/1.0/fastspeech2_nosil_baker_ckpt_0.4/speech_stats.npy
./models/fastspeech2_csmsc-zh/1.0/fastspeech2_nosil_baker_ckpt_0.4/pitch_stats.npy
./models/fastspeech2_csmsc-zh/1.0/fastspeech2_nosil_baker_ckpt_0.4/energy_stats.npy
./models/hifigan_csmsc-zh/
./models/hifigan_csmsc-zh/1.0/
./models/hifigan_csmsc-zh/1.0/hifigan_csmsc_ckpt_0.1.1.zip
./models/hifigan_csmsc-zh/1.0/hifigan_csmsc_ckpt_0.1.1/
./models/hifigan_csmsc-zh/1.0/hifigan_csmsc_ckpt_0.1.1/default.yaml
./models/hifigan_csmsc-zh/1.0/hifigan_csmsc_ckpt_0.1.1/snapshot_iter_2500000.pdz
./models/hifigan_csmsc-zh/1.0/hifigan_csmsc_ckpt_0.1.1/feats_stats.npy
./datasets/
[SUCCESS] 数据卷解压完成
[INFO] 解压镜像包...
[SUCCESS] 镜像包已移动到 /dt_opt/paddlespeech/images
[INFO] 加载Docker镜像...
daf557c4f08e: Loading layer [==================================================>]  81.04MB/81.04MB
d593918d433d: Loading layer [==================================================>]  4.123MB/4.123MB
7c4cff21e743: Loading layer [==================================================>]  41.36MB/41.36MB
25f6bb353e99: Loading layer [==================================================>]   5.12kB/5.12kB
bc3a46414f17: Loading layer [==================================================>]  1.536kB/1.536kB
8fc7185920f1: Loading layer [==================================================>]  3.584kB/3.584kB
bac2a7f893df: Loading layer [==================================================>]    847MB/847MB
092bab498a3d: Loading layer [==================================================>]  13.31MB/13.31MB
19db93cce63e: Loading layer [==================================================>]   2.56kB/2.56kB
2fc7499dded4: Loading layer [==================================================>]  3.042GB/3.042GB
7da6b60d7eb7: Loading layer [==================================================>]   2.53MB/2.53MB
057242764992: Loading layer [==================================================>]  8.704kB/8.704kB
9a996f3d539d: Loading layer [==================================================>]  3.072kB/3.072kB
4cdf0570391d: Loading layer [==================================================>]  104.2MB/104.2MB
Loaded image: dt_iot/paddlespeech:latest
[SUCCESS] 镜像加载成功
[INFO] 生成docker-compose.yaml...
[SUCCESS] docker-compose.yaml创建完成
[INFO] 启动容器...
[+] Running 2/2
 ✔ Network dtnet           Created                                                                                                                                  0.5s 
 ✔ Container paddlespeech  Started                                                                                                                                  4.6s 
[SUCCESS] 容器启动成功
[SUCCESS] PaddleSpeech 离线安装完成！

```

### 4. 查看容器运行状态
```bash
docker ps
```
### 5. 实时查看容器日志

```bash
docker logs -f paddlespeech
```
![](https://qncdn.tairongkj.com/docs/images/20250921171624.png)

### 6. 管理容器
进入容器器的部署目录：
/dt_opt/paddlespeech

```bash 

docker ps up -d  # 启动容器
docker ps down # 停止容器
docker ps restart # 重启容器
docker ps logs -f paddlespeech # 实时查看日志
docker ps exec -it paddlespeech /bin/bash # 进入容器
docker ps rm -f paddlespeech # 删除容器
docker rmi dt_iot/paddlespeech:latest # 删除镜像
docker volume rm paddlespeech_data # 删除数据卷
docker network rm dtnet # 删除网络
docker system prune -a # 清理无用的镜像、容器、数据卷、网络等

```
以上是常用命令，使用时根据需要灵活使用。

### 7. 调整端口

找到文件

```
/dt_opt/paddlespeech/docker-compose.yaml

```
修改对应的端口号，如下所示：
![](https://qncdn.tairongkj.com/docs/images/20250921172307.png)
更改第一个端口为需要的端口号即可，如下所示:


```bash
docker-compse down
sudo nano ./docker-compose.yaml
# 修改对应的端口号，第6行
    #  - "8001:8001"
# 保存退出，重启容器即可生效
docker-compose up -d

```


## 六、使用说明
为了方便的演示如何调用这个api，我们提供了一个测试网页,[下载地址](https://datacdn.data-it.tech/HomeAssistant/dokerimages/paddlespeech1.1/tts_demo.zip)为:

```
https://datacdn.data-it.tech/HomeAssistant/dokerimages/paddlespeech1.1/tts_demo.zip
```
![](https://qncdn.tairongkj.com/docs/images/20250921170242.png)


### 1. 语音合成（TTS）服务

##### curl示例 
```curl
curl --request POST \
  --url http://ikuai.m-iot.tech:58150/tts \
  --header 'content-type: application/x-www-form-urlencoded' \
  --data 'text=请张三到一室做检查' \
  --data lang=zh \
  --data spk_id=0
```
#### HTTTP API说明

```HTTP
POST /tts HTTP/1.1
Content-Type: application/x-www-form-urlencoded
Host: ikuai.m-iot.tech:58150
Content-Length: 103

text=%E8%AF%B7%E5%BC%A0%E4%B8%89%E5%88%B0%E4%B8%80%E5%AE%A4%E5%81%9A%E6%A3%80%E6%9F%A5&lang=zh&spk_id=0
```

##### Java 示例

```java
//asynchttp
AsyncHttpClient client = new DefaultAsyncHttpClient();
client.prepare("POST", "http://ikuai.m-iot.tech:58150/tts")
  .setHeader("content-type", "application/x-www-form-urlencoded")
  .setBody("text=%E8%AF%B7%E5%BC%A0%E4%B8%89%E5%88%B0%E4%B8%80%E5%AE%A4%E5%81%9A%E6%A3%80%E6%9F%A5&lang=zh&spk_id=0")
  .execute()
  .toCompletableFuture()
  .thenAccept(System.out::println)
  .join();

client.close();
//nethttp
HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("http://ikuai.m-iot.tech:58150/tts"))
    .header("content-type", "application/x-www-form-urlencoded")
    .method("POST", HttpRequest.BodyPublishers.ofString("text=%E8%AF%B7%E5%BC%A0%E4%B8%89%E5%88%B0%E4%B8%80%E5%AE%A4%E5%81%9A%E6%A3%80%E6%9F%A5&lang=zh&spk_id=0"))
    .build();
HttpResponse<String> response = HttpClient.newHttpClient().send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());
//okhttp
OkHttpClient client = new OkHttpClient();

MediaType mediaType = MediaType.parse("application/x-www-form-urlencoded");
RequestBody body = RequestBody.create(mediaType, "text=%E8%AF%B7%E5%BC%A0%E4%B8%89%E5%88%B0%E4%B8%80%E5%AE%A4%E5%81%9A%E6%A3%80%E6%9F%A5&lang=zh&spk_id=0");
Request request = new Request.Builder()
  .url("http://ikuai.m-iot.tech:58150/tts")
  .post(body)
  .addHeader("content-type", "application/x-www-form-urlencoded")
  .build();

Response response = client.newCall(request).execute();
//unirest
HttpResponse<String> response = Unirest.post("http://ikuai.m-iot.tech:58150/tts")
  .header("content-type", "application/x-www-form-urlencoded")
  .body("text=%E8%AF%B7%E5%BC%A0%E4%B8%89%E5%88%B0%E4%B8%80%E5%AE%A4%E5%81%9A%E6%A3%80%E6%9F%A5&lang=zh&spk_id=0")
  .asString();
```

#### javaScript 示例

```javascript
//Xhr
const data = 'text=%E8%AF%B7%E5%BC%A0%E4%B8%89%E5%88%B0%E4%B8%80%E5%AE%A4%E5%81%9A%E6%A3%80%E6%9F%A5&lang=zh&spk_id=0';

const xhr = new XMLHttpRequest();
xhr.withCredentials = true;

xhr.addEventListener('readystatechange', function () {
  if (this.readyState === this.DONE) {
    console.log(this.responseText);
  }
});

xhr.open('POST', 'http://ikuai.m-iot.tech:58150/tts');
xhr.setRequestHeader('content-type', 'application/x-www-form-urlencoded');

xhr.send(data);

//Axios
import axios from 'axios';

const encodedParams = new URLSearchParams();
encodedParams.set('text', '请张三到一室做检查');
encodedParams.set('lang', 'zh');
encodedParams.set('spk_id', '0');

const options = {
  method: 'POST',
  url: 'http://ikuai.m-iot.tech:58150/tts',
  headers: {'content-type': 'application/x-www-form-urlencoded'},
  data: encodedParams,
};

try {
  const { data } = await axios.request(options);
  console.log(data);
} catch (error) {
  console.error(error);
}
//Fetch
const url = 'http://ikuai.m-iot.tech:58150/tts';
const options = {
  method: 'POST',
  headers: {'content-type': 'application/x-www-form-urlencoded'},
  body: new URLSearchParams({text: '请张三到一室做检查', lang: 'zh', spk_id: '0'})
};

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
//JQuery
const settings = {
  async: true,
  crossDomain: true,
  url: 'http://ikuai.m-iot.tech:58150/tts',
  method: 'POST',
  headers: {
    'content-type': 'application/x-www-form-urlencoded'
  },
  data: {
    text: '请张三到一室做检查',
    lang: 'zh',
    spk_id: '0'
  }
};

$.ajax(settings).done(function (response) {
  console.log(response);
});

```
##### C# 示例

```csharp
//httpclient
using System.Net.Http.Headers;
var client = new HttpClient();
var request = new HttpRequestMessage
{
    Method = HttpMethod.Post,
    RequestUri = new Uri("http://ikuai.m-iot.tech:58150/tts"),
    Content = new FormUrlEncodedContent(new Dictionary<string, string>
    {
        { "text", "请张三到一室做检查" },
        { "lang", "zh" },
        { "spk_id", "0" },
    }),
};
using (var response = await client.SendAsync(request))
{
    response.EnsureSuccessStatusCode();
    var body = await response.Content.ReadAsStringAsync();
    Console.WriteLine(body);
}
//restsharp
var client = new RestClient("http://ikuai.m-iot.tech:58150/tts");
var request = new RestRequest("", Method.Post);
request.AddHeader("content-type", "application/x-www-form-urlencoded");
request.AddParameter("application/x-www-form-urlencoded", "text=%E8%AF%B7%E5%BC%A0%E4%B8%89%E5%88%B0%E4%B8%80%E5%AE%A4%E5%81%9A%E6%A3%80%E6%9F%A5&lang=zh&spk_id=0", ParameterType.RequestBody);
var response = client.Execute(request);


```

#### go 示例

```go
package main

import (
    "fmt"
    "strings"
    "net/http"
    "io"
)

func main() {

    url := "http://ikuai.m-iot.tech:58150/tts"

    payload := strings.NewReader("text=%E8%AF%B7%E5%BC%A0%E4%B8%89%E5%88%B0%E4%B8%80%E5%AE%A4%E5%81%9A%E6%A3%80%E6%9F%A5&lang=zh&spk_id=0")

    req, _ := http.NewRequest("POST", url, payload)

    req.Header.Add("content-type", "application/x-www-form-urlencoded")

    res, _ := http.DefaultClient.Do(req)

    defer res.Body.Close()
    body, _ := io.ReadAll(res.Body)

    fmt.Println(res)
    fmt.Println(string(body))

}

```

##### 返回结果

```
Preparing request to http://ikuai.m-iot.tech:58150/tts
Current time is 2025-09-21T07:49:17.236Z
POST http://ikuai.m-iot.tech:58150/tts
Accept: application/json, text/plain, */*
Content-Type: application/x-www-form-urlencoded
User-Agent: bruno-runtime/2.3.0
text=%E8%AF%B7%E5%BC%A0%E4%B8%89%E5%88%B0%E4%B8%80%E5%AE%A4%E5%81%9A%E6%A3%80%E6%9F%A5&lang=zh&spk_id=0
SSL validation: enabled
HTTP/1.1 200 OK
date: Sun, 21 Sep 2025 07:49:18 GMT
server: uvicorn
content-type: audio/wav
content-disposition: attachment; filename="7b41c15b-e0a4-4ba5-aeb1-ceff058c90e6.wav"
content-length: 89444
last-modified: Sun, 21 Sep 2025 07:49:20 GMT
etag: d85eaa2cadf7182ac9b54763e6a97e2c
request-duration: 2224
Request completed in 2224 ms
```
![](https://qncdn.tairongkj.com/docs/images/20250921160616.png)
![](https://qncdn.tairongkj.com/docs/images/20250921160647.png)
![](https://qncdn.tairongkj.com/docs/images/20250921160716.png)
![](https://qncdn.tairongkj.com/docs/images/20250921160755.png)

### 2. 语音识别（ASR）服务
#### 上传文件调用示例
##### curl示例
```curl
curl --request POST \
  --url http://ikuai.m-iot.tech:58150/asr \
  --header 'content-type: multipart/form-data' \
  --form 'file=@C:\Users\trphoenix\Documents\录音\录音 (6).m4a' \
  --form lang=zh \
  --form format=wav \
  --form sample_rate=16000
```
直接上传文件，文件格式支持wav、m4a、mp3等常见音频格式，服务端会自动转换为wav格式进行识别。
```curl
curl --request POST \
  --url http://ikuai.m-iot.tech:58150/asr \
  --header 'content-type: multipart/form-data' \
  --form 'file=@C:\Users\trphoenix\Documents\录音\录音 (6).m4a' \
  --form lang=zh
```
传入参数可以只有file与lang这两个参数，其它参数，可以忽略，如下图所示
![](https://qncdn.tairongkj.com/docs/images/20250921162309.png)

##### HTTP 示例说明

```HTTP
POST /asr HTTP/1.1
Content-Type: multipart/form-data; boundary=---011000010111000001101001
Host: ikuai.m-iot.tech:58150
Content-Length: 239

-----011000010111000001101001
Content-Disposition: form-data; name="file"

C:\Users\trphoenix\Documents\录音\录音 (6).m4a
-----011000010111000001101001
Content-Disposition: form-data; name="lang"

zh
-----011000010111000001101001--

```

#####　java 示例

```java
// asynchttp
AsyncHttpClient client = new DefaultAsyncHttpClient();
client.prepare("POST", "http://ikuai.m-iot.tech:58150/asr")
  .setHeader("content-type", "multipart/form-data; boundary=---011000010111000001101001")
  .setBody("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\nC:\\Users\\trphoenix\\Documents\\录音\\录音 (6).m4a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nzh\r\n-----011000010111000001101001--\r\n\r\n")
  .execute()
  .toCompletableFuture()
  .thenAccept(System.out::println)
  .join();

client.close();
// nethttp

HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("http://ikuai.m-iot.tech:58150/asr"))
    .header("content-type", "multipart/form-data; boundary=---011000010111000001101001")
    .method("POST", HttpRequest.BodyPublishers.ofString("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\nC:\\Users\\trphoenix\\Documents\\录音\\录音 (6).m4a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nzh\r\n-----011000010111000001101001--\r\n\r\n"))
    .build();
HttpResponse<String> response = HttpClient.newHttpClient().send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());
// okhttp
OkHttpClient client = new OkHttpClient();

MediaType mediaType = MediaType.parse("multipart/form-data; boundary=---011000010111000001101001");
RequestBody body = RequestBody.create(mediaType, "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\nC:\\Users\\trphoenix\\Documents\\录音\\录音 (6).m4a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nzh\r\n-----011000010111000001101001--\r\n\r\n");
Request request = new Request.Builder()
  .url("http://ikuai.m-iot.tech:58150/asr")
  .post(body)
  .addHeader("content-type", "multipart/form-data; boundary=---011000010111000001101001")
  .build();

Response response = client.newCall(request).execute();
// unirest
HttpResponse<String> response = Unirest.post("http://ikuai.m-iot.tech:58150/asr")
  .header("content-type", "multipart/form-data; boundary=---011000010111000001101001")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\nC:\\Users\\trphoenix\\Documents\\录音\\录音 (6).m4a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nzh\r\n-----011000010111000001101001--\r\n\r\n")
  .asString();
```

##### javascript 示例

```javascript
//xhr
const data = new FormData();
data.append('file', 'C:\Users\trphoenix\Documents\录音\录音 (6).m4a');
data.append('lang', 'zh');

const xhr = new XMLHttpRequest();
xhr.withCredentials = true;

xhr.addEventListener('readystatechange', function () {
  if (this.readyState === this.DONE) {
    console.log(this.responseText);
  }
});

xhr.open('POST', 'http://ikuai.m-iot.tech:58150/asr');

xhr.send(data);
// Axios
import axios from 'axios';

const form = new FormData();
form.append('file', 'C:\Users\trphoenix\Documents\录音\录音 (6).m4a');
form.append('lang', 'zh');

const options = {
  method: 'POST',
  url: 'http://ikuai.m-iot.tech:58150/asr',
  headers: {'content-type': 'multipart/form-data; boundary=---011000010111000001101001'},
  data: '[form]'
};

try {
  const { data } = await axios.request(options);
  console.log(data);
} catch (error) {
  console.error(error);
}
// fetch
const url = 'http://ikuai.m-iot.tech:58150/asr';
const form = new FormData();
form.append('file', 'C:\Users\trphoenix\Documents\录音\录音 (6).m4a');
form.append('lang', 'zh');

const options = {method: 'POST'};

options.body = form;

try {
  const response = await fetch(url, options);
  const data = await response.json();
  console.log(data);
} catch (error) {
  console.error(error);
}
//jquery
const form = new FormData();
form.append('file', 'C:\Users\trphoenix\Documents\录音\录音 (6).m4a');
form.append('lang', 'zh');

const settings = {
  async: true,
  crossDomain: true,
  url: 'http://ikuai.m-iot.tech:58150/asr',
  method: 'POST',
  headers: {},
  processData: false,
  contentType: false,
  mimeType: 'multipart/form-data',
  data: form
};

$.ajax(settings).done(function (response) {
  console.log(response);
});


```

##### C# 示例

```csharp
//httpclient
using System.Net.Http.Headers;
var client = new HttpClient();
var request = new HttpRequestMessage
{
    Method = HttpMethod.Post,
    RequestUri = new Uri("http://ikuai.m-iot.tech:58150/asr"),
    Content = new MultipartFormDataContent
    {
        new StringContent(["C:\\Users\\trphoenix\\Documents\\录音\\录音 (6).m4a"])
        {
            Headers =
            {
                ContentDisposition = new ContentDispositionHeaderValue("form-data")
                {
                    Name = "file",
                    FileName = "C:\Users\trphoenix\Documents\录音\录音 (6).m4a",
                }
            }
        },
        new StringContent("zh")
        {
            Headers =
            {
                ContentDisposition = new ContentDispositionHeaderValue("form-data")
                {
                    Name = "lang",
                }
            }
        },
    },
};
using (var response = await client.SendAsync(request))
{
    response.EnsureSuccessStatusCode();
    var body = await response.Content.ReadAsStringAsync();
    Console.WriteLine(body);
}
//Restsharp 
var client = new RestClient("http://ikuai.m-iot.tech:58150/asr");
var request = new RestRequest("", Method.Post);
request.AddHeader("content-type", "multipart/form-data; boundary=---011000010111000001101001");
request.AddParameter("multipart/form-data; boundary=---011000010111000001101001", "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\nC:\\Users\\trphoenix\\Documents\\录音\\录音 (6).m4a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nzh\r\n-----011000010111000001101001--\r\n\r\n", ParameterType.RequestBody);
var response = client.Execute(request); 

```

##### go 示例

```go
package main

import (
    "fmt"
    "strings"
    "net/http"
    "io"
)

func main() {

    url := "http://ikuai.m-iot.tech:58150/asr"

    payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\nC:\\Users\\trphoenix\\Documents\\录音\\录音 (6).m4a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nzh\r\n-----011000010111000001101001--\r\n\r\n")

    req, _ := http.NewRequest("POST", url, payload)

    req.Header.Add("content-type", "multipart/form-data; boundary=---011000010111000001101001")

    res, _ := http.DefaultClient.Do(req)

    defer res.Body.Close()
    body, _ := io.ReadAll(res.Body)

    fmt.Println(res)
    fmt.Println(string(body))

}

```

##### java 示例

```java
// asynchttp
AsyncHttpClient client = new DefaultAsyncHttpClient();
client.prepare("POST", "http://ikuai.m-iot.tech:58150/asr")
  .setHeader("content-type", "multipart/form-data; boundary=---011000010111000001101001")
  .setBody("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\nC:\\Users\\trphoenix\\Documents\\录音\\录音 (6).m4a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nzh\r\n-----011000010111000001101001--\r\n\r\n")
  .execute()
  .toCompletableFuture()
  .thenAccept(System.out::println)
  .join();

client.close();

// nethttp
HttpRequest request = HttpRequest.newBuilder()
    .uri(URI.create("http://ikuai.m-iot.tech:58150/asr"))
    .header("content-type", "multipart/form-data; boundary=---011000010111000001101001")
    .method("POST", HttpRequest.BodyPublishers.ofString("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\nC:\\Users\\trphoenix\\Documents\\录音\\录音 (6).m4a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nzh\r\n-----011000010111000001101001--\r\n\r\n"))
    .build();
HttpResponse<String> response = HttpClient.newHttpClient().send(request, HttpResponse.BodyHandlers.ofString());
System.out.println(response.body());
// okhttp
OkHttpClient client = new OkHttpClient();

MediaType mediaType = MediaType.parse("multipart/form-data; boundary=---011000010111000001101001");
RequestBody body = RequestBody.create(mediaType, "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\nC:\\Users\\trphoenix\\Documents\\录音\\录音 (6).m4a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nzh\r\n-----011000010111000001101001--\r\n\r\n");
Request request = new Request.Builder()
  .url("http://ikuai.m-iot.tech:58150/asr")
  .post(body)
  .addHeader("content-type", "multipart/form-data; boundary=---011000010111000001101001")
  .build();

Response response = client.newCall(request).execute();

// unirest
HttpResponse<String> response = Unirest.post("http://ikuai.m-iot.tech:58150/asr")
  .header("content-type", "multipart/form-data; boundary=---011000010111000001101001")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"\r\n\r\nC:\\Users\\trphoenix\\Documents\\录音\\录音 (6).m4a\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\nzh\r\n-----011000010111000001101001--\r\n\r\n")
  .asString();

```
##### 返回结果

```json
{
  "result": "喂语音测试语音测试录音测试录音测试",
  "file_size": 185334,
  "wav_info": {
    "n_channels": 1,
    "sample_width": 2,
    "framerate": 16000,
    "n_frames": 115029,
    "duration": 7.1893125
  },
  "ffmpeg_log": ""
}

```
![](https://qncdn.tairongkj.com/docs/images/20250921164758.png)

***body*** 

```json
{
  "_overheadLength": 252,
  "_valueLength": 2,
  "_valuesToMeasure": [
    {
      "fd": null,
      "path": "C:\\Users\\trphoenix\\Documents\\录音\\录音 (6).m4a",
      "flags": "r",
      "mode": 438,
      "end": null,
      "bytesRead": 0,
      "_events": {},
      "_readableState": {
        "highWaterMark": 65536,
        "buffer": [],
        "bufferIndex": 0,
        "length": 0,
        "pipes": [],
        "awaitDrainWriters": null
      },
      "_eventsCount": 3
    }
  ],
  "writable": false,
  "readable": true,
  "dataSize": 0,
  "maxDataSize": 2097152,
  "pauseStreams": true,
  "_released": false,
  "_streams": [
    "----------------------------147555471668548578107544\r\nContent-Disposition: form-data; name=\"file\"; filename=\"录音 (6).m4a\"\r\nContent-Type: wav\r\n\r\n",
    {
      "source": "[Circular]",
      "dataSize": 0,
      "maxDataSize": null,
      "pauseStream": true,
      "_maxDataSizeExceeded": false,
      "_released": false,
      "_bufferedEvents": [
        {
          "0": "pause"
        }
      ],
      "_events": {},
      "_eventsCount": 1
    },
    null,
    "----------------------------147555471668548578107544\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\n",
    "zh",
    null
  ],
  "_currentStream": null,
  "_insideLoop": false,
  "_pendingNext": false,
  "_boundary": "--------------------------147555471668548578107544"
}
```
![](https://qncdn.tairongkj.com/docs/images/20250921164909.png)
![](https://qncdn.tairongkj.com/docs/images/20250921164934.png)

***Network Logs ***
```
Preparing request to http://ikuai.m-iot.tech:58150/asr
Current time is 2025-09-21T08:22:20.590Z
POST http://ikuai.m-iot.tech:58150/asr
Accept: application/json, text/plain, */*
Content-Type: multipart/form-data; boundary=--------------------------147555471668548578107544
User-Agent: bruno-runtime/2.3.0
{
  "_overheadLength": 252,
  "_valueLength": 2,
  "_valuesToMeasure": [
    {
      "fd": null,
      "path": "C:\\Users\\trphoenix\\Documents\\录音\\录音 (6).m4a",
      "flags": "r",
      "mode": 438,
      "end": null,
      "bytesRead": 0,
      "_events": {},
      "_readableState": {
        "highWaterMark": 65536,
        "buffer": [],
        "bufferIndex": 0,
        "length": 0,
        "pipes": [],
        "awaitDrainWriters": null
      },
      "_eventsCount": 3
    }
  ],
  "writable": false,
  "readable": true,
  "dataSize": 0,
  "maxDataSize": 2097152,
  "pauseStreams": true,
  "_released": false,
  "_streams": [
    "----------------------------147555471668548578107544\r\nContent-Disposition: form-data; name=\"file\"; filename=\"录音 (6).m4a\"\r\nContent-Type: wav\r\n\r\n",
    {
      "source": {
        "fd": null,
        "path": "C:\\Users\\trphoenix\\Documents\\录音\\录音 (6).m4a",
        "flags": "r",
        "mode": 438,
        "end": null,
        "bytesRead": 0,
        "_events": {},
        "_readableState": {
          "highWaterMark": 65536,
          "buffer": [],
          "bufferIndex": 0,
          "length": 0,
          "pipes": [],
          "awaitDrainWriters": null
        },
        "_eventsCount": 3
      },
      "dataSize": 0,
      "maxDataSize": null,
      "pauseStream": true,
      "_maxDataSizeExceeded": false,
      "_released": false,
      "_bufferedEvents": [
        {
          "0": "pause"
        }
      ],
      "_events": {},
      "_eventsCount": 1
    },
    null,
    "----------------------------147555471668548578107544\r\nContent-Disposition: form-data; name=\"lang\"\r\n\r\n",
    "zh",
    null
  ],
  "_currentStream": null,
  "_insideLoop": false,
  "_pendingNext": false,
  "_boundary": "--------------------------147555471668548578107544"
}
SSL validation: enabled
HTTP/1.1 200 OK
date: Sun, 21 Sep 2025 08:22:21 GMT
server: uvicorn
content-length: 201
content-type: application/json
request-duration: 6989
Request completed in 6989 ms
```

#### 浏览器录音识别示例

![](https://qncdn.tairongkj.com/docs/images/20250921165339.png)
![](https://qncdn.tairongkj.com/docs/images/20250921165403.png)
![](https://qncdn.tairongkj.com/docs/images/20250921165449.png)
![](https://qncdn.tairongkj.com/docs/images/20250921165607.png)
![](https://qncdn.tairongkj.com/docs/images/20250921165632.png)
![](https://qncdn.tairongkj.com/docs/images/20250921165652.png)

***说明***

paddlespeech中用的一个库有可能是单线程的，所以在高并发场景下，可能会出现响应变慢的情况，这个时候，可以考虑增加实例来解决这个问题。
实际使用时,如果想提高并发能力，可以尝试更改环境变量中的PYTHONUNBUFFFERED=4,或更高一个适合的数字，来提高并发能力。
![](https://qncdn.tairongkj.com/docs/images/20250921172804.png)


***《完》***

 Help/mkdocs.yml

@@ -34,6 +34,7 @@
        - 基于Docker的方式安装HomeAssistant :  Usages\QA\基于Docker的方式安装HomeAssistant.md

        - 如何快速部署frpc服务 : Usages\QA\如何快速部署frpc服务.md

        - windows不能访问HA的共享配置目录的解决办法 : Usages\QA\windows不能访问HA的共享配置目录的解决办法.md

        - 语音合成与识别服务Docker-部署说明 : Usages\QA\语音合成与识别服务Docker-部署说明.md

  - 其它教程:

      - Node-red相关:

        - 安装node-red记录: node-reds\安装node-red记录.md