Add blog for OCR.

Author: winlinvip

i18n/en-us/docusaurus-plugin-content-blog/2024-05-20-OCR-Video-Streams.md

@@ -0,0 +1,105 @@
+---
+slug: ocr-video-streams
+title: Oryx - Leveraging OpenAI for OCR and Object Recognition in Video Streams
+authors: []
+tags: [ocr, ai, gpt, srs, oryx]
+custom_edit_url: null
+---
+
+# Leveraging OpenAI for OCR and Object Recognition in Video Streams using Oryx
+
+## Introduction
+
+In today's digital world, videos are everywhere. From social media clips to live broadcasts, we consume a 
+vast amount of video content daily. But have you ever wondered how we can make sense of all the information 
+in these videos? This is where AI comes in. With the help of artificial intelligence, we can now recognize 
+text, identify objects, and even describe scenes in video streams.
+
+<!--truncate-->
+
+One powerful tool that makes this process easy is Oryx. In this blog, we'll explore how Oryx can help you 
+perform OCR (Optical Character Recognition) on video streams, allowing you to extract valuable information 
+in real-time.
+
+## Step 1: Create Oryx by One Click
+
+Creating an Oryx is simple and can be done with just one click if you use Digital Ocean droplet.
+Please see [How to Setup a Video Streaming Service by 1-Click](./2022-04-09-Oryx-Tutorial.md) for detail.
+
+You can also use Docker to create an Oryx with a single command line:
+
+```bash
+docker run --restart always -d -it --name oryx -v $HOME/data:/data \
+  -p 80:2022 -p 443:2443 -p 1935:1935 -p 8000:8000/udp -p 10080:10080/udp \
+  ossrs/oryx:5
+```
+
+After creating the Oryx, you can access it through `http://your-server-ip/mgmt` via a browser.
+
+## Step 2: Publish a Live Stream to Oryx
+
+You can use OBS or FFmpeg to publish a live stream to Oryx. You can also set up HTTPS and publish via WebRTC.
+
+![](/img/blog-2024-05-20-01.png)
+
+Once the stream is published, you can preview it using an H5 player or VLC.
+Please see [How to Setup a Video Streaming Service by 1-Click](./2022-04-09-Oryx-Tutorial.md) for detail.
+
+## Step 3: Setup OpenAI Secret Key for OCR
+
+To use OCR, you must obtain a secret key from OpenAI. Please open the [API keys](https://platform.openai.com/api-keys)
+page in your browser and click the `Create new secret key` button. Once the key is created, copy it and set it in Oryx.
+Then, click the `Test OpenAI Service` button, as shown in the picture below.
+
+![](/img/blog-2024-05-20-02.png)
+
+If the test is successful, you can click the `Start OCR` button to start the OCR process.
+
+## Step 4: Setup AI Instructions for OCR
+
+Once you've configured your GPT AI assistant, you can update the bellow prompt at the setting webpage
+`Service Settings > AI Instructions > Instructions`.
+
+![](/img/blog-2024-05-20-03.png)
+
+To recognize text in video streams, you can use the following instructions:
+
+```text
+Recognize the text in the image. Output the identified text directly.
+```
+
+## Step 5: View OCR Results by Callback
+
+Once the OCR process is complete, you can view the results by setting up a callback URL in Oryx.
+
+![](/img/blog-2024-05-20-04.png)
+
+You can also view the last OCR result in the dashboard.
+
+![](/img/blog-2024-05-20-05.png)
+
+## Cloud Service
+
+At SRS, our goal is to establish a non-profit, open-source community dedicated to creating an all-in-one,
+out-of-the-box, open-source video solution for live streaming and WebRTC online services.
+
+Additionally, we offer a [Cloud](../cloud) service for those who prefer to use cloud service instead of building from
+scratch. Our cloud service features global network acceleration, enhanced congestion control algorithms,
+client SDKs for all platforms, and some free quota.
+
+To learn more about our cloud service, click [here](../cloud).
+
+## Conclusion
+
+In conclusion, using AI to recognize text and objects in video streams is a game-changer. It helps us quickly 
+and accurately extract valuable information from videos. Tools like Oryx make this process simple and efficient, 
+allowing you to publish live streams and get real-time OCR results with ease. Whether you're looking to identify 
+people, read text, or describe scenes, AI-powered OCR can transform how you interact with video content. By 
+leveraging these technologies, you can unlock new possibilities and insights from the videos you encounter 
+every day.
+
+## Contact
+
+Welcome for more discussion at [discord](https://discord.gg/bQUPDRqy79).
+
+![](https://ossrs.io/gif/v1/sls.gif?site=ossrs.io&path=/lts/blog-en/24-05-20-OCR-Video-Streams)

i18n/zh-cn/docusaurus-plugin-content-blog/2024-02-21-Dubbing-Translating.md

@@ -1,6 +1,6 @@
 ---
 slug: dubbing-translating
-title: Oryx - 视频多语言翻译和配音
+title: Oryx - 基于AI的视频多语言翻译和配音
 authors: []
 tags: [dubbing, translating, ai, gpt, voice, srs, oryx, multilingual]
 custom_edit_url: null

i18n/zh-cn/docusaurus-plugin-content-blog/2024-05-20-OCR-Video-Streams.md

@@ -0,0 +1,83 @@
+---
+slug: ocr-video-streams
+title: Oryx - 基于AI的视频流的OCR和对象识别
+authors: []
+tags: [ocr, ai, gpt, srs, oryx]
+custom_edit_url: null
+---
+
+# Leveraging OpenAI for OCR and Object Recognition in Video Streams using Oryx
+
+## Introduction
+
+在当今的数字世界中，视频无处不在。从社交媒体片段到直播，我们每天都在大量消费视频内容。但你是否想过我们如何理解这些视频中的所有信息？
+这就是人工智能的作用。有了人工智能的帮助，我们现在可以识别文字、识别物体，甚至描述视频流中的场景。
+
+<!--truncate-->
+
+一个强大的工具使这个过程变得简单，那就是Oryx。在这篇博客中，我们将探讨Oryx如何帮助你在视频流上执行OCR（光学字符识别），
+让你能够实时提取有价值的信息。
+
+## Step 1: Create Oryx by One Click
+
+创建 Oryx 很简单，只需点击一下，如果您使用 Digital Ocean droplet，就可以完成。
+请参阅[如何通过 1-Click 设置视频流服务](./2022-04-09-Oryx-Tutorial.md)了解详细信息。
+
+您还可以使用 Docker 通过单个命令行创建 Oryx：
+
+```bash
+docker run --restart always -d -it --name oryx -v $HOME/data:/data \
+  -p 80:2022 -p 443:2443 -p 1935:1935 -p 8000:8000/udp -p 10080:10080/udp \
+  registry.cn-hangzhou.aliyuncs.com/ossrs/oryx:5
+```
+
+创建 Oryx 后，您可以通过 `http://your-server-ip/mgmt` 访问它。
+
+## Step 2: Publish a Live Stream to Oryx
+
+您可以使用 OBS 或 FFmpeg 将直播流发布到 Oryx。您还可以设置 HTTPS 并通过 WebRTC 发布。
+
+![](/img/blog-2024-05-20-11.png)
+
+发布流后，您可以使用 H5 播放器或 VLC 预览它。
+请参阅[如何通过 1-Click 设置视频流服务](./2022-04-09-Oryx-Tutorial.md)了解详细信息。
+
+## Step 3: Setup OpenAI Secret Key for OCR
+
+要使用 Whisper ASR，您必须从 OpenAI 获取一个密钥。请在您的浏览器中打开 [API 密钥](https://platform.openai.com/api-keys)
+页面，然后点击 `创建新的密钥` 按钮。密钥创建后，复制它并在 Oryx 中设置。然后，如下图所示，点击 `测试OpenAI服务可用性`
+按钮。
+
+![](/img/blog-2024-05-20-12.png)
+
+如果测试成功，你可以点击 `开始OCR` 按钮来启动OCR过程。
+
+## Step 4: Setup AI Instructions for OCR
+
+配置好你的GPT AI助手后，你可以在设置网页上更新以下提示`服务设置 > AI模型配置 > 提示词`。
+
+![](/img/blog-2024-05-20-13.png)
+
+要在视频流中识别文本，你可以使用以下指令：
+
+```text
+Recognize the text in the image. Output the identified text directly.
+```
+
+## Step 5: View OCR Results by Callback
+
+一旦OCR过程完成，你可以通过在Oryx中设置回调URL来查看结果。
+
+![](/img/blog-2024-05-20-14.png)
+
+你也可以在仪表板中查看最新的OCR结果。
+
+![](/img/blog-2024-05-20-15.png)
+
+## Conclusion
+
+总之，使用AI识别视频流中的文本和物体是一个改变游戏规则的技术。它帮助我们快速准确地从视频中提取有价值的信息。
+像Oryx这样的工具使这个过程变得简单高效，让你能够轻松发布直播并获得实时OCR结果。无论你是想识别人、读取文本还是描述场景，
+AI驱动的OCR都可以改变你与视频内容的互动方式。通过利用这些技术，你可以从每天接触到的视频中解锁新的可能性和见解。
+
+![](https://ossrs.net/gif/v1/sls.gif?site=ossrs.net&path=/lts/blog-zh/24-05-20-OCR-Video-Streams)