Voxtral Transcribe 2: transcribes at the speed of sound

Comments

• Awajuk@piefed.social ⁨3⁩ ⁨weeks⁩ ago

  Nice but lacks polish support :(

  source

  • ExcessShiv@lemmy.dbzer0.com ⁨3⁩ ⁨weeks⁩ ago

    Like Nail polish?

    source

    • Awajuk@piefed.social ⁨3⁩ ⁨weeks⁩ ago

      like 🇵🇱 polish 😅 #poland

      source

      • -> View More Comments
• XLE@piefed.social ⁨3⁩ ⁨weeks⁩ ago

  How much does it cost to run a system that supports it, in 2026 hardware prices? 4B is not the biggest AI model number, but RAM and GPU prices are very daunting thanks to the company releasing this closed-source model

  source

  • Tetsuo@jlai.lu ⁨3⁩ ⁨weeks⁩ ago

    Closed source model? What do you mean?

    Isn’t this open weights?

    source

    • XLE@piefed.social ⁨3⁩ ⁨weeks⁩ ago

      “Open weights” just means you can download the blob they output from their sources. So… Closed source, unless they open it.

      Their terminology is just tricky marketing. It would be like calling a closed source program “open executable” or something…

      source

      • -> View More Comments
• muzzle@lemmy.zip ⁨3⁩ ⁨weeks⁩ ago

  I wonder if someone could use this to make an offline voice keyboard for android

  source

  • 0x0@infosec.pub ⁨3⁩ ⁨weeks⁩ ago

    keyboard.futo.org

    source

    • muzzle@lemmy.zip ⁨3⁩ ⁨weeks⁩ ago

      I prefer whisper futo never worked for me

      source

      • -> View More Comments