From c93351f30b4b206dd749bfe0c037729bc2e534a0 Mon Sep 17 00:00:00 2001
From: trphoenix <spd260@126.com>
Date: 星期日, 21 九月 2025 17:38:47 +0800
Subject: [PATCH] 增加docker安装paddle-speech
---
Help/mkdocs.yml | 1
Help/docs/Usages/QA/语音合成与识别服务Docker-部署说明.md | 1008 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 1,009 insertions(+), 0 deletions(-)
diff --git "a/Help/docs/Usages/QA/\350\257\255\351\237\263\345\220\210\346\210\220\344\270\216\350\257\206\345\210\253\346\234\215\345\212\241Docker-\351\203\250\347\275\262\350\257\264\346\230\216.md" "b/Help/docs/Usages/QA/\350\257\255\351\237\263\345\220\210\346\210\220\344\270\216\350\257\206\345\210\253\346\234\215\345\212\241Docker-\351\203\250\347\275\262\350\257\264\346\230\216.md"
new file mode 100644
index 0000000..e30c74e
--- /dev/null
+++ "b/Help/docs/Usages/QA/\350\257\255\351\237\263\345\220\210\346\210\220\344\270\216\350\257\206\345\210\253\346\234\215\345\212\241Docker-\351\203\250\347\275\262\350\257\264\346\230\216.md"
@@ -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:
+
+
+
+
+### 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。
+
+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。
+
+
+## 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
+```
+
+
+
+### 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
+```
+
+
+### 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：
+
+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
+```
+
+
+
+### 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
+```
+
+
+
+
+
+### 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
+
+
+##### 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": ""
+}
+
+```
+
+
+***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"
+}
+```
+
+
+
+***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
+
+
+
+
+
+
+
+
+***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。
+
+
+
+***《完》***
\ No newline at end of file
diff --git a/Help/mkdocs.yml b/Help/mkdocs.yml
index 2b5a9a8..4de00c7 100644
--- a/Help/mkdocs.yml
+++ b/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
--
Gitblit v1.8.0