[HN Gopher] Whisper-WebUI
       ___________________________________________________________________
        
       Whisper-WebUI
        
       Author : ivank
       Score  : 22 points
       Date   : 2024-08-21 08:01 UTC (2 days ago)
        
 (HTM) web link (github.com)
 (TXT) w3m dump (github.com)
        
       | yjftsjthsd-h wrote:
       | This says it can generate subtitle files, which is something I've
       | wanted from whisper for a while. But does anyone know of a way to
       | do that with just a cli tool that I can run locally? Like,
       | ideally, just `whisper-make-subtitles ./*.mp4` to loop over every
       | .mp4 in a directory and create matching subtitle files.
        
         | jjwiseman wrote:
         | The whisper command at https://github.com/openai/whisper can
         | generate .srt and .vtt subtitle files using --output_format.
        
         | wccrawford wrote:
         | I've used https://github.com/tomchang25/whisper-auto-transcribe
         | to generate subtitles and then translate them to English and it
         | worked fairly well. It's not professional-level, but it was
         | good enough to understand what they were saying and enjoy
         | foreign TV.
        
       | jamesblonde wrote:
       | This was a lab assignment I gave my students at KTH in Nov 2022O
       | https://github.com/ID2223KTH/id2223kth.github.io/blob/master...
       | 
       | See some of their example solutions here (along with their
       | projects in 2022):
       | https://id2223kth.github.io/assignments/project/ServerlessML...
       | 
       | One of the student labs was gamified language learning - say the
       | image in the language you are learning, and Whisper tells you
       | whether you said it in an understandable way.
       | 
       | This Gradio implementation is a more polished version of their
       | early efforts.
        
       | vlugorilla wrote:
       | Also check out https://whishper.net
        
       ___________________________________________________________________
       (page generated 2024-08-23 23:00 UTC)