• @[email protected]
    link
    fedilink
    English
    10
    edit-2
    11 hours ago

    They are, however, able to inaccurately summarize it in GLaDOS’s voice, which is a strong point in their favor.

    • JackGreenEarth
      link
      fedilink
      English
      311 hours ago

      Surely you’d need TTS for that one, too? Which one do you use, is it open weights?

      • @brucethemoose
        link
        English
        1
        edit-2
        11 hours ago

        Zonos just came out, seems sick:

        https://huggingface.co/Zyphra

        There are also some “native” tts LLMs like GLM 9B, which “capture” more information in the output than pure text input.

          • @brucethemoose
            link
            English
            17 hours ago

            Whoops, yeah, should have linked the blog.

            I didn’t want to link the individual models because I’m not sure hybrid or pure transformers is better?

            • @ag10n
              link
              English
              116 minutes ago

              Looks pretty interesting, thanks for sharing it