cross-posted from: https://lemmy.ca/post/37011397

[email protected]

The popular open-source VLC video player was demonstrated on the floor of CES 2025 with automatic AI subtitling and translation, generated locally and offline in real time. Parent organization VideoLAN shared a video on Tuesday in which president Jean-Baptiste Kempf shows off the new feature, which uses open-source AI models to generate subtitles for videos in several languages.

    • @Eagle0110
      link
      English
      51 month ago

      Has there been any estimated minimal system requirements for this yet, since it runs locally?

      • @[email protected]
        link
        fedilink
        English
        11
        edit-2
        1 month ago

        It’s actually using whisper.cpp

        From the README:

        Memory usage Model Disk Mem tiny 75 MiB ~273 MB base 142 MiB ~388 MB small 466 MiB ~852 MB medium 1.5 GiB ~2.1 GB large 2.9 GiB ~3.9 GiB

        Those are the model sizes

        • @Eagle0110
          link
          English
          330 days ago

          Oh wow those pretty tiny memory requirements for a decent modern system! That’s actually very impressive! :D

          Many people can probably even run this on older media servers or even just a plain NAS! That’s awesome! :D

    • @[email protected]
      link
      fedilink
      English
      329 days ago

      Note that openai’s original whisper models are pretty slow; in my experience the distil-whisper project (via a tool like whisperx) is more than 10x faster.