Jump to content
Chinese-Forums

How are you guys OCR-ing our text nowadays?


Recommended Posts

Posted

I used to use videosubfinder and subs2srs and stuff to get anki cards out of hard coded subtitles. 

just wondering with all this ai stuff and tech improving, now that i am back to studying chinese if there are new ways or better ways or updated ways to make srt files out of hard coded subs

  • Good question! 1
Posted

望言OCR  is an efficient and accurate subtitle extraction tool that can quickly extract hard‑coded subtitles from videos. see the official site:https://static.subocr.cn/


you can do both Automatic Analysis and Manual Setup for place the frame on designated position of sub and go.


also you can choose to use third‑party OCR services by enter the corresponding API key and secret key. 
currently supports the following third‑party OCR interfaces: 百度 OCR, 百度高精 OCR, 腾讯云OCR, 腾讯高精OCR, 阿里云OCR.


you can download from community(free) version from github and professional version from baidu webdisc.
https://github.com/nhjydywd/SubtitleOCR
https://www.bilibili.com/video/BV1Xgq6BtEuo/

Posted

To answer the question in the title...

Quote

How are you guys OCR-ing our text nowadays?

 

If I'm using OCR, it'll be via ChatGPT, Yandex, or Pleco's OCR (which came as part of a dictionary bundle I bought many years ago).  But honestly, at my level, it's very seldom needed.

 

As for...

Quote

if there are new ways or better ways or updated ways to make srt files out of hard coded subs

 

I've tried "hard coded subs to soft coded subs" software, and it requires too much computer processing, so I don't use it.  (Also, I can read the hard-coded subs, and for the exceptions, I just guess the pinyin using phonetic components or handwrite them into Pleco.)

 

If I actually want to make subtitle files, I upload the audio file (downloaded with youtube-dl -x) to https://jianwai.youdao.com/ and it auto-generates subtitles in Chinese.  But if I just want a transcript of what's said... I just put my iPhone in "voice input" mode, put it near a speaker, and play the audio aloud, and the iPhone automatically transcribes what is said.

  • Helpful 1
Posted

thanks for the suggestions both of you!

 

edit:

sad face.

 

停服公告
亲爱用户您好,因公司业务战略调整网易见外于2025年12月18日 12:00停止服务
详细请查看 关于网易见外产品停服及数据处理的公告

Join the conversation

You can post now and select your username and password later. If you have an account, sign in now to post with your account.
Note: Your post will require moderator approval before it will be visible.

Guest
Unfortunately, your content contains terms that we do not allow. Please edit your content to remove the highlighted words below.
Click here to reply. Select text to quote.

×   Pasted as rich text.   Paste as plain text instead

  Only 75 emoji are allowed.

×   Your link has been automatically embedded.   Display as a link instead

×   Your previous content has been restored.   Clear editor

×   You cannot paste images directly. Upload or insert images from URL.

×
×
  • Create New...