dasemu/Transcriptarr
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

Browse Source
This commit is contained in:
McCloudS
2024-02-11 15:05:01 -07:00
committed by GitHub
parent 765a8d04f9
commit 5fa87307b5
1 changed files with 1 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
README.md
View File

@@ -161,16 +161,12 @@ There is now only a single image being maintained, the image has everything nece
# What are the limitations/problems? # What are the limitations/problems?
* If Plex adds multiple shows (like a season pack), it may fail to process subtitles. * If Plex adds multiple shows (like a season pack), it may fail to process subtitles.
* Long pauses/silence behave strangely. It will likely show the previous or next words during long gaps of silence. (**This is appears mostly fixed now using stable-ts!**)
* I made it and know nothing about formal deployment for python coding. * I made it and know nothing about formal deployment for python coding.
* It's using trained AI models to transcribe, so it WILL mess up * It's using trained AI models to transcribe, so it WILL mess up
# What's next? # What's next?
I'm hoping someone that is much more skilled than I, to use this as a pushing off point to make this better. In a perfect world, this would integrate with Plex, Sonarr, Radarr, or Bazarr. Bazarr tracks failed subtitle downloads, I originally wanted to utilize its API, but decided on my current solution for simplicity. Fix documentation and make it prettier!
Optimizations I can think of off hand:
* Add an ability via a web-ui or something to generate subtitles for particular media files/folders. (**No GUI planned, but TRANSCRIBE_FOLDERS can do this**)
# Audio Languages Supported (via OpenAI) # Audio Languages Supported (via OpenAI)
@@ -178,8 +174,6 @@ Afrikaans, Arabic, Armenian, Azerbaijani, Belarusian, Bosnian, Bulgarian, Catala
# Additional reading: # Additional reading:
* https://github.com/ggerganov/whisper.cpp/issues/89 (Benchmarks)
* https://github.com/openai/whisper/discussions/454 (Whisper CPU implementation)
* https://github.com/openai/whisper (Original OpenAI project) * https://github.com/openai/whisper (Original OpenAI project)
* https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes (2 letter subtitle codes) * https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes (2 letter subtitle codes)