Mastodon Skip to content
  • Home
  • Aktuell
  • Tags
  • Über dieses Forum
Einklappen
Grafik mit zwei überlappenden Sprechblasen, eine grün und eine lila.
Abspeckgeflüster – Forum für Menschen mit Gewicht(ung)

Kostenlos. Werbefrei. Menschlich. Dein Abnehmforum.

  1. Home
  2. Uncategorized
  3. We've built our own text-to-speech system with an initial English language model we trained ourselves with fully open source data.

We've built our own text-to-speech system with an initial English language model we trained ourselves with fully open source data.

Geplant Angeheftet Gesperrt Verschoben Uncategorized
42 Beiträge 28 Kommentatoren 0 Aufrufe
  • Älteste zuerst
  • Neuste zuerst
  • Meiste Stimmen
Antworten
  • In einem neuen Thema antworten
Anmelden zum Antworten
Dieses Thema wurde gelöscht. Nur Nutzer mit entsprechenden Rechten können es sehen.
  • grapheneos@grapheneos.socialG grapheneos@grapheneos.social

    We're going to build our own speech-to-text implementation to go along with this too. We're starting with an English model for both but we can add other languages which have high quality training data available. English and Mandarin have by far the most training data available.

    malmen@masto.ptM This user is from outside of this forum
    malmen@masto.ptM This user is from outside of this forum
    malmen@masto.pt
    schrieb zuletzt editiert von
    #31

    @GrapheneOS will this enable speach commands on android auto?

    1 Antwort Letzte Antwort
    0
    • grapheneos@grapheneos.socialG grapheneos@grapheneos.social

      We're going to build our own speech-to-text implementation to go along with this too. We're starting with an English model for both but we can add other languages which have high quality training data available. English and Mandarin have by far the most training data available.

      T This user is from outside of this forum
      T This user is from outside of this forum
      topcaser@mastodontech.de
      schrieb zuletzt editiert von
      #32

      @GrapheneOS please, please add German to that list

      1 Antwort Letzte Antwort
      0
      • grapheneos@grapheneos.socialG grapheneos@grapheneos.social

        We've built our own text-to-speech system with an initial English language model we trained ourselves with fully open source data. It will be added to our App Store soon and then included in GrapheneOS as a default enabled TTS backend once some more improvements are made to it.

        emberfox@bark.lgbtE This user is from outside of this forum
        emberfox@bark.lgbtE This user is from outside of this forum
        emberfox@bark.lgbt
        schrieb zuletzt editiert von
        #33

        @GrapheneOS I am very excited to not have to use an external tool to do this anymore.

        1 Antwort Letzte Antwort
        0
        • grapheneos@grapheneos.socialG grapheneos@grapheneos.social

          Our full time developer working on this already built their own Transcribro app for on-device speech-to-text available in the Accrescent app store. For GrapheneOS itself, we want actual open source implementations of these features rather than OpenAI's phony open source though.

          lunareclipse@snug.moeL This user is from outside of this forum
          lunareclipse@snug.moeL This user is from outside of this forum
          lunareclipse@snug.moe
          schrieb zuletzt editiert von
          #34

          @GrapheneOS highly interested in seeing high quality open source TTS/STT, great work!

          1 Antwort Letzte Antwort
          0
          • grapheneos@grapheneos.socialG grapheneos@grapheneos.social

            We've built our own text-to-speech system with an initial English language model we trained ourselves with fully open source data. It will be added to our App Store soon and then included in GrapheneOS as a default enabled TTS backend once some more improvements are made to it.

            catsalad@infosec.exchangeC This user is from outside of this forum
            catsalad@infosec.exchangeC This user is from outside of this forum
            catsalad@infosec.exchange
            schrieb zuletzt editiert von
            #35

            @GrapheneOS How good is this model at meowing?

            float13@masto.hackers.townF 1 Antwort Letzte Antwort
            0
            • catsalad@infosec.exchangeC catsalad@infosec.exchange

              @GrapheneOS How good is this model at meowing?

              float13@masto.hackers.townF This user is from outside of this forum
              float13@masto.hackers.townF This user is from outside of this forum
              float13@masto.hackers.town
              schrieb zuletzt editiert von
              #36

              @catsalad @GrapheneOS

              catsalad@infosec.exchangeC 1 Antwort Letzte Antwort
              0
              • float13@masto.hackers.townF float13@masto.hackers.town

                @catsalad @GrapheneOS

                catsalad@infosec.exchangeC This user is from outside of this forum
                catsalad@infosec.exchangeC This user is from outside of this forum
                catsalad@infosec.exchange
                schrieb zuletzt editiert von
                #37

                @float13 @GrapheneOS

                1 Antwort Letzte Antwort
                0
                • grapheneos@grapheneos.socialG grapheneos@grapheneos.social

                  Our full time developer working on this already built their own Transcribro app for on-device speech-to-text available in the Accrescent app store. For GrapheneOS itself, we want actual open source implementations of these features rather than OpenAI's phony open source though.

                  D This user is from outside of this forum
                  D This user is from outside of this forum
                  detietsch@mastodon.social
                  schrieb zuletzt editiert von
                  #38

                  @GrapheneOS wow ! this is great ! Good Work GOS-Team 👍

                  1 Antwort Letzte Antwort
                  0
                  • grapheneos@grapheneos.socialG grapheneos@grapheneos.social

                    We're going to build our own speech-to-text implementation to go along with this too. We're starting with an English model for both but we can add other languages which have high quality training data available. English and Mandarin have by far the most training data available.

                    tmakarios@theres.lifeT This user is from outside of this forum
                    tmakarios@theres.lifeT This user is from outside of this forum
                    tmakarios@theres.life
                    schrieb zuletzt editiert von
                    #39

                    @GrapheneOS
                    This is great news! I'll be interested to find out how well your English speech-to-text model copes with non-rhotic accents. (Think of a posh British "received pronunciation" accent, or anyone from southeast England, or Australia or New Zealand.) Currently, if I want something like Dicio to understand me, I have to put on an American accent, which my wife says is "creepy".

                    1 Antwort Letzte Antwort
                    0
                    • grapheneos@grapheneos.socialG grapheneos@grapheneos.social

                      We've built our own text-to-speech system with an initial English language model we trained ourselves with fully open source data. It will be added to our App Store soon and then included in GrapheneOS as a default enabled TTS backend once some more improvements are made to it.

                      D This user is from outside of this forum
                      D This user is from outside of this forum
                      dei@is.nota.live
                      schrieb zuletzt editiert von
                      #40

                      @GrapheneOS Perfect timing! Since december 2025 google text to speach is not working anymore without Exploit protection compatibility mode.

                      1 Antwort Letzte Antwort
                      0
                      • grapheneos@grapheneos.socialG grapheneos@grapheneos.social

                        We've built our own text-to-speech system with an initial English language model we trained ourselves with fully open source data. It will be added to our App Store soon and then included in GrapheneOS as a default enabled TTS backend once some more improvements are made to it.

                        bartavi@mastodon.nlB This user is from outside of this forum
                        bartavi@mastodon.nlB This user is from outside of this forum
                        bartavi@mastodon.nl
                        schrieb zuletzt editiert von
                        #41

                        @GrapheneOS made my day! Each time I think GrapheneOS is already amazing, you make it even better! Thanks a lot for your dedication!

                        1 Antwort Letzte Antwort
                        0
                        • grapheneos@grapheneos.socialG grapheneos@grapheneos.social

                          We've built our own text-to-speech system with an initial English language model we trained ourselves with fully open source data. It will be added to our App Store soon and then included in GrapheneOS as a default enabled TTS backend once some more improvements are made to it.

                          G This user is from outside of this forum
                          G This user is from outside of this forum
                          grantjoseph@mastodon.social
                          schrieb zuletzt editiert von
                          #42

                          @GrapheneOS Fantastic work as always! Any news on the replacement keyboard plans I've seen mentioned from time to time?

                          1 Antwort Letzte Antwort
                          0
                          • svenja@mstdn.gamesS svenja@mstdn.games shared this topic
                          Antworten
                          • In einem neuen Thema antworten
                          Anmelden zum Antworten
                          • Älteste zuerst
                          • Neuste zuerst
                          • Meiste Stimmen



                          Copyright (c) 2025 abSpecktrum (@abspecklog@fedimonster.de)

                          Erstellt mit Schlaflosigkeit, Kaffee, Brokkoli & ♥

                          Impressum | Datenschutzerklärung | Nutzungsbedingungen

                          • Anmelden

                          • Du hast noch kein Konto? Registrieren

                          • Anmelden oder registrieren, um zu suchen
                          • Erster Beitrag
                            Letzter Beitrag
                          0
                          • Home
                          • Aktuell
                          • Tags
                          • Über dieses Forum