Skip to content

Real-time OCR, Real-time Translation Using Bilingual Corpus, Real-time Whisper-based Video Transcription, Post-processed Whisper-based Transcription, Domain-specific Retrieval Augmented Translation

License

Notifications You must be signed in to change notification settings

ylxmf2005/RealTimeSpecSubTrans

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Real-time Domain-specific Subtitles & Translation

Real-time OCR & Translation Using Bilingual Corpus

  • Above is the demo video with the original Chinese subtitles and the corresponding English subtitles below, matched from the game's unpacked data using the Chinese text.

  • The provided OCR options are Paddle OCR or Baidu OCR API. You can use your own OCR API in ocr_mode/ocr_api.

  • The unpacked data is from https://www.bilibili.com/read/cv23965717/.

  • The text_match algorithm uses ocr_text to truncate the text in the corpus and calculate their LCS Similarity.

Real-time Whisper-based Transcription & Translation Using Bilingual Corpus

Post-processed Whisper-based Transcription & Domain-specific Retrieval Augmented Translation

About

Real-time OCR, Real-time Translation Using Bilingual Corpus, Real-time Whisper-based Video Transcription, Post-processed Whisper-based Transcription, Domain-specific Retrieval Augmented Translation

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages