Reported by Bai Jiao from Aofeisi Quantum Bit | WeChat Official Account QbitAI
A Bilibili UP master has created a translator that claims to be able to handle any raw video, even games.
This translator is based on OCR technology, which means you just need to take a screenshot on the interface, and even subtitles from games and new anime can be translated.
Moreover, as the screen changes, it can automatically translate in real-time.
It can also handle raw manga.
No need to worry while playing Japanese nurturing games~
Netizens have commented: “Awesome, I can uninstall VNR (a translation software for raw videos).”
Currently, this software is available for free download on GitHub, with the link provided at the end of the article.
How to Use
This OCR translator utilizes Baidu AI’s text recognition to translate foreign text from images.
After downloading, it looks like this.
Before use, you need to configure a series of parameters by clicking the second settings button on the left.
The first page is the API settings interface, where you need to register your own API key to use the translator.
The topmost OCR API must be registered. Click the button to register OCR, and a registration tutorial will pop up.
Just follow the registration tutorial, and after filling in the key and secret, remember to save the settings! It is also recommended to register the API code below.
The next page is the translator settings, where you can choose your preferred translation source from 12 options.
Public translation and web translation can be used directly, while private translation requires registration of an API key as set on the previous page.
Also, you can set the source language for translation (currently only supporting English, Japanese, and Korean), and set the automatic translation time.
Next is the translation style, where you can choose color, font size, font style, etc.
There are also other settings.
Its basic operations are:
-
Capture the coordinates of the screen area that needs translation through screenshots.
-
Take a screenshot using the coordinates (can be automatic) and send it to Baidu AI’s text recognition interface;
-
After obtaining the recognized text, send it to translation interfaces such as Baidu, Tencent, and Caiyun;
-
Feedback the results to the GUI interface.
What you need to do is just take a screenshot and then translate.
There is also a small feature.
The red-highlighted “Music” button, when clicked, can play the original text.
This software is currently open-source on GitHub, so interested friends can go download it~
But I’ll take the lead and test it out first.
Testing It Out
According to the tutorial provided on GitHub, after downloading, it looks like this.
Since I have already tested raw Japanese videos and games earlier, let’s test the translation of a PDF version.
Before that, I chose public Youdao, web Tencent, and private Baidu. The color settings are as follows:
The translation language is set to English, and shortcut keys are set so that A is for screenshot and S is for translation.
Taking a machine learning paper titled Review of Text Style Transfer Based on Deep Learning as an example in PDF format.
Let’s try the title.
First, capture the title area.
Pressing the S key brings up the translation interface.
The order is original text, private Baidu, web Tencent, and public Youdao.
Next, let’s try the first three lines of the paper’s Introduction.
The translation is as follows:
(If it is not clear, you can adjust the position and transparency accordingly)
In addition to translation, you can also compare the translation levels of several translation services~
By the way, which translation service do you think is the best? Or do you have better translation software?
Feel free to leave a comment in the section below, seeking recommendations!
Links
https://github.com/PantsuDango/Dango-Translator
Bilibili demonstration video:
https://www.bilibili.com/video/BV1gp4y1Q7Ts?from=search&seid=2515920591076249883
— End —
Special Offer | One-Stop Audio and Video Solutions
Quantum Bit QbitAI · Author on Toutiao
Tracking new developments in AI technology and products
If you like it, please click “Looking”!