eupolicy.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
This Mastodon server is a friendly and respectful discussion space for people working in areas related to EU policy. When you request to create an account, please tell us something about you.

Server stats:

216
active users

#speechtotext

0 posts0 participants0 posts today
Debby<p><span class="h-card" translate="no"><a href="https://mastodon.social/@thelinuxEXP" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>thelinuxEXP</span></a></span> I really like Speech Note! It's a fantastic tool for quick and local voice transcription in multiple languages, created by <span class="h-card" translate="no"><a href="https://mastodon.social/@mkiol" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>mkiol</span></a></span> </p><p>It's incredibly handy for capturing thoughts on the go, conducting interviews, or making voice memos without worrying about language barriers. The app uses strictly locally running LLMs, and its ease of use makes it a standout choice for anyone needing offline transcription services.</p><p>I primarily use <a href="https://hear-me.social/tags/WhisperAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>WhisperAI</span></a> for transcription and Piper for voice, but many other models are available as well. </p><p>It is available as flatpak and <a href="https://github.com/mkiol/dsnote" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">github.com/mkiol/dsnote</span><span class="invisible"></span></a> </p><p><a href="https://hear-me.social/tags/TTS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TTS</span></a> <a href="https://hear-me.social/tags/transcription" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>transcription</span></a> <a href="https://hear-me.social/tags/TextToSpeech" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TextToSpeech</span></a> <a href="https://hear-me.social/tags/translator" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>translator</span></a> translation <a href="https://hear-me.social/tags/offline" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>offline</span></a> <a href="https://hear-me.social/tags/machinetranslation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>machinetranslation</span></a> <a href="https://hear-me.social/tags/sailfishos" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>sailfishos</span></a> <a href="https://hear-me.social/tags/SpeechSynthesis" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpeechSynthesis</span></a> <a href="https://hear-me.social/tags/SpeechRecognition" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpeechRecognition</span></a> <a href="https://hear-me.social/tags/speechtotext" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>speechtotext</span></a> <a href="https://hear-me.social/tags/nmt" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>nmt</span></a> <a href="https://hear-me.social/tags/linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>linux</span></a>-desktop <a href="https://hear-me.social/tags/stt" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>stt</span></a> <a href="https://hear-me.social/tags/asr" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>asr</span></a> <a href="https://hear-me.social/tags/flatpak" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>flatpak</span></a>-applications <a href="https://hear-me.social/tags/SpeechNote" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpeechNote</span></a></p>
Benjamin Carr, Ph.D. 👨🏻‍💻🧬<p><a href="https://hachyderm.io/tags/Mozilla" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Mozilla</span></a> Formally Discontinues Its <a href="https://hachyderm.io/tags/DeepSpeech" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>DeepSpeech</span></a> Project<br><a href="https://hachyderm.io/tags/MozillaDeepSpeech" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>MozillaDeepSpeech</span></a> was a <a href="https://hachyderm.io/tags/speechtotext" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>speechtotext</span></a> engine with great performance for real-time communication even when running on <a href="https://hachyderm.io/tags/RaspberryPi" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>RaspberryPi</span></a> and other low-power systems.<br>Mozilla discontinuing DeepSpeech sadly doesn't as surprise. Last tagged release was 0.9.3 back in December 2020 and there hadn't been any Git activity since 2021.<br>Even in 2020 DeepSpeech was considered at risk of ceasing development following Mozilla layoffs.<br><a href="https://www.phoronix.com/news/Mozilla-DeepSpeech-Discontinued" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="ellipsis">phoronix.com/news/Mozilla-Deep</span><span class="invisible">Speech-Discontinued</span></a></p>
doboprobodyne<p><a href="https://mathstodon.xyz/tags/Whisper" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Whisper</span></a> <a href="https://mathstodon.xyz/tags/WebGPU" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>WebGPU</span></a> by <a href="https://mathstodon.xyz/tags/Huggingface" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Huggingface</span></a> sounds very exciting!</p><p>Does this mean an <a href="https://mathstodon.xyz/tags/activitypub" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>activitypub</span></a> server could delegate translation-into-user's-language of all the posts to the user's device?</p><p>I'm too thick to have been able to find any system-requirements information for just the text-translation feature... Is this <a href="https://mathstodon.xyz/tags/translation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>translation</span></a> feature likely to fly on mobile devices too?</p><p>Am I getting too excited too soon?</p><p><a href="https://dev.to/proflead/real-time-audio-to-text-in-your-browser-whisper-webgpu-tutorial-j6d" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">dev.to/proflead/real-time-audi</span><span class="invisible">o-to-text-in-your-browser-whisper-webgpu-tutorial-j6d</span></a></p><p><a href="https://github.com/keatonkraiger/Whisper-Transcribe-and-Translate-Tutorial" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/keatonkraiger/Whisp</span><span class="invisible">er-Transcribe-and-Translate-Tutorial</span></a></p><p><a href="https://mathstodon.xyz/tags/language" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>language</span></a> <a href="https://mathstodon.xyz/tags/linguistics" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>linguistics</span></a> <a href="https://mathstodon.xyz/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://mathstodon.xyz/tags/STT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>STT</span></a> <a href="https://mathstodon.xyz/tags/SpeechToText" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpeechToText</span></a> <a href="https://mathstodon.xyz/tags/piefed" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>piefed</span></a> <a href="https://mathstodon.xyz/tags/mastodon" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>mastodon</span></a> <a href="https://mathstodon.xyz/tags/edgeComputing" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>edgeComputing</span></a></p>
unfa🇺🇦<p>If you're using an android phone you need this:</p><p><a href="https://keyboard.futo.org/" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">keyboard.futo.org/</span><span class="invisible"></span></a><br> <a href="https://www.youtube.com/watch?v=cFP5bp3JvaU" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://www.</span><span class="">youtube.com/watch?v=cFP5bp3JvaU</span><span class="invisible"></span></a></p><p>I have been on the lookout for a sensible Gboard replacement that wasn't making my (voice) typing experience painful, and so far only FUTO Keyboard managed to provide that.</p><p>It has really good offline voice typing as well, which is something I use a lot.</p><p>I can not recommend this enough!</p><p><a href="https://mastodon.social/tags/FUTO" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>FUTO</span></a> <a href="https://mastodon.social/tags/Android" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Android</span></a> <a href="https://mastodon.social/tags/Privacy" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Privacy</span></a> <a href="https://mastodon.social/tags/SpeechToText" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpeechToText</span></a> <a href="https://mastodon.social/tags/VoiceTyping" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VoiceTyping</span></a> <a href="https://mastodon.social/tags/Swype" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Swype</span></a> <a href="https://mastodon.social/tags/Gboard" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Gboard</span></a> <a href="https://mastodon.social/tags/Heliboard" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Heliboard</span></a> <a href="https://mastodon.social/tags/Florisboard" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Florisboard</span></a></p>
Open Titus :opensource: :tux:<p>🗣️🐧 Trascrizione Vocale Su GNU-Linux</p><p>Ecco la nuovissima funzionalità speech to text di ibus che verrà introdotta nella nuova Fedora 42. <br>Intanto proviamo insieme la Beta in Fedora 41.<br>Buona Visione.</p><p><a href="https://youtu.be/lxPgQft1e0s" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="">youtu.be/lxPgQft1e0s</span><span class="invisible"></span></a></p><p><a href="https://mastodon.uno/tags/unolinux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>unolinux</span></a> <a href="https://mastodon.uno/tags/opensourceitalia" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>opensourceitalia</span></a> <a href="https://mastodon.uno/tags/fedora" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>fedora</span></a> <a href="https://mastodon.uno/tags/ibus" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ibus</span></a> <a href="https://mastodon.uno/tags/speechtotext" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>speechtotext</span></a></p>
Leonid<p>Kennt ihr eine gute kostenlose Speech-to-Text Lösung, um den Inhalt einer Sprachnotiz zu extrahieren?</p><p><a href="https://norden.social/tags/speechtotext" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>speechtotext</span></a> <a href="https://norden.social/tags/ai" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>ai</span></a></p>
Joseph Nuthalapati :fbx:<p>Does anybody know of a better <a href="https://social.masto.host/tags/speechToText" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>speechToText</span></a> alternative to this? </p><p>This feels like a terrible hack that keeps breaking. I decided to look for alternatives after I saw them using /dev/shm to store ML models.</p><p>QuantiusBenignus/BlahST<br><a href="https://github.com/QuantiusBenignus/BlahST" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/QuantiusBenignus/Bl</span><span class="invisible">ahST</span></a></p><p>SpeechNote (aka dsnote) does not qualify since it doesn't integrate with the clipboard.</p><p><a href="https://social.masto.host/tags/STT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>STT</span></a> <a href="https://social.masto.host/tags/WhisperCPP" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>WhisperCPP</span></a></p>
nilocram<p><a href="https://framapiaf.org/tags/Framasoft" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Framasoft</span></a> ha da poco annunciato l'apertura di <a href="https://framapiaf.org/tags/Framamia" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Framamia</span></a>, un sito per condividere le conoscenze sulle <a href="https://framapiaf.org/tags/IntelligenzeArtificiali" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>IntelligenzeArtificiali</span></a>, porsi dei problemi, fare ricerche. Un primo risultato: <a href="https://framapiaf.org/tags/Lokas" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Lokas</span></a> il prototipo di una app <a href="https://framapiaf.org/tags/SpeechToText" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpeechToText</span></a> per mobile. La traduzione italiana dell'articolo è qui: <a href="https://poliverso.org/display/0477a01e-4467-65b8-84cf-c33499214437" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">poliverso.org/display/0477a01e</span><span class="invisible">-4467-65b8-84cf-c33499214437</span></a> E ancora una volta: merci <span class="h-card" translate="no"><a href="https://framapiaf.org/@Framasoft" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>Framasoft</span></a></span> :frama: <a href="https://framapiaf.org/tags/IA" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>IA</span></a> <a href="https://framapiaf.org/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AI</span></a> <a href="https://framapiaf.org/tags/BeniComuni" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>BeniComuni</span></a> <span class="h-card" translate="no"><a href="https://a.gup.pe/u/scuola" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>scuola@a.gup.pe</span></a></span> <span class="h-card" translate="no"><a href="https://poliverso.org/profile/scuola" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>scuola@poliverso.org</span></a></span> <span class="h-card" translate="no"><a href="https://framapiaf.org/@maupao" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>maupao</span></a></span> <span class="h-card" translate="no"><a href="https://mastodon.uno/@filippodb" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>filippodb</span></a></span> <span class="h-card" translate="no"><a href="https://poliversity.it/@macfranc" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>macfranc</span></a></span> <span class="h-card" translate="no"><a href="https://livellosegreto.it/@alephoto85" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>alephoto85</span></a></span> <br> <span class="h-card" translate="no"><a href="https://mastodon.uno/@quinta" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>quinta</span></a></span> <span class="h-card" translate="no"><a href="https://social.ilnostropianetaselvaggio.it/@dado" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>dado</span></a></span> <span class="h-card" translate="no"><a href="https://poliversity.it/@skariko" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>skariko</span></a></span> <span class="h-card" translate="no"><a href="https://mastodon.social/@iamarf" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>iamarf</span></a></span> <span class="h-card" translate="no"><a href="https://poliversity.it/@mcp" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>mcp</span></a></span> <span class="h-card" translate="no"><a href="https://mastodon.uno/@Puntopanto" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>Puntopanto</span></a></span> <span class="h-card" translate="no"><a href="https://mastodon.uno/@FlaviaMarzano" class="u-url mention" rel="nofollow noopener" target="_blank">@<span>FlaviaMarzano</span></a></span></p>
SleepyCatten<p>Hey folks :FediverseSymbol: </p><p>We've actually done an unwritten, off-the-cusp trans voice Friday recording today :TransHeart: </p><p>We've not listened back to it, because voice dysphoria, but we've added full alt text.</p><p>In case you're wondering how we've done that without listening back to it, we've once against used an amazing tool called <a href="https://www.nikse.dk/subtitleedit" rel="nofollow noopener" target="_blank">Subtitle Edit</a>, which has audio to text functionality via the <a href="https://github.com/Purfview/whisper-standalone-win" rel="nofollow noopener" target="_blank">Whisper</a> speech recognition engine.</p><p>We used the large-v3 model, which is about 3.1 GB, but gives incredibly accurate transcription.</p><p>In case anyone can't access the alt text, we've added the full transcript below too.</p><p><a href="https://cultofshiv.wtf/tags/TransVoiceFriday" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TransVoiceFriday</span></a> <a href="https://cultofshiv.wtf/tags/TransVoice" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TransVoice</span></a> <a href="https://cultofshiv.wtf/tags/voice" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>voice</span></a> <a href="https://cultofshiv.wtf/tags/VoiceFeminisation" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VoiceFeminisation</span></a> <a href="https://cultofshiv.wtf/tags/VoiceFeminization" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VoiceFeminization</span></a> <a href="https://cultofshiv.wtf/tags/VoiceTraining" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VoiceTraining</span></a> <a href="https://cultofshiv.wtf/tags/trans" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>trans</span></a> <a href="https://cultofshiv.wtf/tags/transgender" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>transgender</span></a> <a href="https://cultofshiv.wtf/tags/TransFem" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>TransFem</span></a> <a href="https://cultofshiv.wtf/tags/VoiceDysphoria" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>VoiceDysphoria</span></a> <a href="https://cultofshiv.wtf/tags/SubtitleEdit" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SubtitleEdit</span></a> <a href="https://cultofshiv.wtf/tags/PurfviewWhisper" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>PurfviewWhisper</span></a> <a href="https://cultofshiv.wtf/tags/AudioToText" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>AudioToText</span></a> <a href="https://cultofshiv.wtf/tags/SpeechToText" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpeechToText</span></a> <a href="https://cultofshiv.wtf/tags/SpeechRecognition" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpeechRecognition</span></a> </p><blockquote><p>Hey folks, I know that we haven't done a voice note in forever, and that's been for a multitude of reasons, some of which are related to mental health, some of which are related to work, stress, anxiety, depression, etc, things like that, which comes under mental health anyway, yeah, partly due to poor time management, yay for being AuDHD! But not gonna lie, some of it does come down to underlying voice dysphoria, because this is the best we've managed to get since December 2021. And just for anyone who hasn't heard roughly what we sounded like beforehand, we haven't exactly moved our voice up a lot. I mean, the base level would just be down here. So I can move my voice back up here easily now, and this is the comfortable, this is the default voice. But, um... It's not where I want it to be, it's not in the female range, and I can't easily push the pitch up higher without it sounding wrong. But yeah, there's been a lot of stuff going on recently, um, a lot of bad stuff for everyone, don't want to talk about all of that. But, um, let's just focus on supporting each other, helping each other, um, being kind to ourselves and others right now, and being compassionate and empathetic. That's all I've really got to say. I'm trying to do the same thing with ourselves, but yeah, it's hard sometimes. Anyway, ta-ta for now.</p></blockquote>
Joseph Nuthalapati :fbx:<p>This is a pretty good speech-to-text solution for the Linux desktop.</p><p><a href="https://github.com/QuantiusBenignus/BlahST" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/QuantiusBenignus/Bl</span><span class="invisible">ahST</span></a></p><p>i am using this with the Mozilla/llamafile model for WhisperCPP. </p><p>Its integration with the Debian GNOME desktop is user-friendly. There is a microphone icon displayed in the taskbar when the speech-to-text is active. You can paste using middle click once the the dictation is done, i.e. when the microphone disappears.</p><p>(This toot was dictated and then edited.)</p><p><a href="https://social.masto.host/tags/accessibility" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>accessibility</span></a> <a href="https://social.masto.host/tags/speechToText" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>speechToText</span></a></p>
Thorsten Rochelmeyer<p>Gibt es aktuell eine gut funktionierende und anwendungsfreundliche Möglichkeit, Text direkt in ein <a href="https://climatejustice.social/tags/Libreoffice" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Libreoffice</span></a>-Dokument zu <a href="https://climatejustice.social/tags/diktieren" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>diktieren</span></a>? <br>Lokale Lösungen! Keinesfalls Cloud. </p><p>Ich kenne den Weg, eine Audio-Datei mit <a href="https://climatejustice.social/tags/Whisper" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Whisper</span></a> zu transkribieren. Das ist super, nutzt mir aber aktuell gerade recht wenig. Ich bräuchte was, wo der Prozess schon während des Sprechens läuft ...so wie bei Dragon und ähnlichen "Diktiersystemen", die es mal gab (und von denen ich nicht weiß, ob sie noch existieren). </p><p><a href="https://climatejustice.social/tags/Linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Linux</span></a> <a href="https://climatejustice.social/tags/STT" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>STT</span></a> <a href="https://climatejustice.social/tags/SpeechToText" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpeechToText</span></a> <a href="https://climatejustice.social/tags/SpeechRecognition" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpeechRecognition</span></a></p>
alxd of the Story Seed Library<p><a href="https://writing.exchange/tags/opensource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>opensource</span></a> <a href="https://writing.exchange/tags/tools" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>tools</span></a> question: do you know any good <a href="https://writing.exchange/tags/offline" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>offline</span></a> <a href="https://writing.exchange/tags/speechToText" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>speechToText</span></a> <a href="https://writing.exchange/tags/transcription" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>transcription</span></a> tool?</p>
Fabien Nicolet 🏳️‍🌈🏴<p>Question technique :<br>Si je veux transcrire automatiquement des messages audio reçus sur whattsapp ios (oui, je sais), est-ce qu'il existe une solution open source qui ne nécessite pas de compiler une app ios ou au moins en local pour faire ça, ou est-ce que je suis obligé de passer par des sites plus ou moins fiables et transparents ?</p><p>(l'option qui semble être sortie sur le dernier ios n'est pas envisageable)</p><p><a href="https://tooting.ch/tags/openSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>openSource</span></a> <a href="https://tooting.ch/tags/speechToText" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>speechToText</span></a> <a href="https://tooting.ch/tags/iOS" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>iOS</span></a> <a href="https://tooting.ch/tags/privacy" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>privacy</span></a></p>
Sharon Machlis<p>The {minutemaker} <a href="https://masto.machlis.com/tags/rstats" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>rstats</span></a> 📦 “allows transcribing audio recordings using different speech-to-text APIs and then summarizing the transcripts using remote or local Large Language Models.</p><p>“The package at the moment uses the Whisper API from either OpenAI or Azure or a local model on top of <a href="https://github.com/Softcatala/whisper-ctranslate2" rel="nofollow noopener" translate="no" target="_blank"><span class="invisible">https://</span><span class="ellipsis">github.com/Softcatala/whisper-</span><span class="invisible">ctranslate2</span></a> (to be installed separately) for the speech transcription.” By Angelo D'Ambrosio</p><p>I haven’t tried this yet but it looks interesting.</p><p><a href="https://masto.machlis.com/tags/LLMs" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>LLMs</span></a> <a href="https://masto.machlis.com/tags/SpeechToText" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>SpeechToText</span></a> <a href="https://masto.machlis.com/tags/GenAI" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>GenAI</span></a></p>
Monika Barget<p>Dear <a href="https://akademienl.social/tags/research" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>research</span></a> community, does anyone have recommendations for <a href="https://akademienl.social/tags/speechtotext" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>speechtotext</span></a> apps on Windows, Android &amp; Linux? I know that anthropologists etc. use this for interview transcriptions. I would need something for taking down my own notes, lecture concepts etc. The built-in speech-recognition in WORD is too slow and misunderstands me all the time, whereas I have no issues talking to Google or ChatGPT. Recording notes first and then feeding them into a tool would also work. <a href="https://akademienl.social/tags/OpenSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>OpenSource</span></a> is welcome.</p>
Oblomov<p>Are there any decent <a href="https://sociale.network/tags/speechToText" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>speechToText</span></a> options for <a href="https://sociale.network/tags/Linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#<span>Linux</span></a>? Last time I checked the situation seemed pretty dire.</p>