Announcement

Collapse
No announcement yet.

Mozilla Developing Whisperfile For Local Audio-To-Text Translation

Collapse
X
 
  • Filter
  • Time
  • Show
Clear All
new posts

  • Mozilla Developing Whisperfile For Local Audio-To-Text Translation

    Phoronix: Mozilla Developing Whisperfile For Local Audio-To-Text Translation

    The Mozilla Ocho group leads "innovation and experiments" at Mozilla. Following all of their work on Llamafile for easily distributing large language models as a single file that can be easily executed across different hardware/software, their newest effort is Whisperfile for easy audio-to-text translations...

    Phoronix, Linux Hardware Reviews, Linux hardware benchmarks, Linux server benchmarks, Linux benchmarking, Desktop Linux, Linux performance, Open Source graphics, Linux How To, Ubuntu benchmarks, Ubuntu hardware, Phoronix Test Suite

  • #2
    Now the only thing I'd need is proper text to audio.

    Comment


    • #3
      simple Speech to text has been around for ages now using whisper, I don't see what's special about this, seems like yet another waste of resources.

      Comment


      • #4
        Originally posted by Quackdoc View Post
        simple Speech to text has been around for ages now using whisper, I don't see what's special about this, seems like yet another waste of resources.
        It's about a standardized file format where the trained models are stored in, not about whisper the logic.

        Comment


        • #5
          Originally posted by oleid View Post
          Now the only thing I'd need is proper text to audio.
          Have you tried Piper yet?

          Comment


          • #6
            It's by Justine. In Justine we trust!

            Comment


            • #7
              Originally posted by TheJackiNonster View Post

              Have you tried Piper yet?
              No, I haven't. My native language sounds kind of strange, but English sounds good to me.

              I'm currently eying this one, but it would appear that not much happened during the last few months:

              Comment


              • #8
                Originally posted by reba View Post
                It's about a standardized file format where the trained models are stored in, not about whisper the logic.
                I see, Im not fully convinced since I found converting models not too difficult, but I suppose it's an improvement in any case.

                Comment


                • #9
                  Originally posted by Quackdoc View Post
                  simple Speech to text has been around for ages now using whisper, I don't see what's special about this, seems like yet another waste of resources.
                  you're saying you've had better commoditized speech to text models before whisper?

                  Comment


                  • #10
                    Originally posted by raystriker View Post

                    you're saying you've had better commoditized speech to text models before whisper?
                    no? I'm saying whisper has been extremely easy for a while now. I'm using it on my phone, as well as on my pcs.

                    Comment

                    Working...
                    X