Hacker NewsGemma Gem – AI model embedded in a browser – no API keys, no cloud
https://github.com/kessler/gemma-gem
#HackerNews #GemmaGem #AI #Browser #Model #NoAPI #NoCloud #Technology
Herbert ReiterE-Rechnungsvorlage Expert für #Excel und #LibreOffice
Auf mehrfachem Kundenwunsch gibt es nun eine E-Rechnungsvorlage, die auch Aufschlag, Rabatt, Skonto, sowie SEPA-Bankeinzug und Vorauszahlung unterstützt.
Die Vorlage erzeugt E-Rechnungen in den Formaten #ZUGFeRD und #XRechnung. Sie funktioniert unter Windows, Linux Debian/Ubuntu/Mint sowie macOS.
Es gibt auch eine kostenlose Demoversion zum Ausprobieren.
https://digitale-vorlagen.de/erechnung-expert/
Datenschutzfreundlich, ohne Cloud, ohne Abo, ohne Werbung
#eRechnung #en16931 #datenschutz #NoCloud #Rechnung #Buchhaltung #Buchfuehrung #Einzelunternehmer #Soloselbstständiger #Kleinunternehmer #Freelancer
xoron 
Is this a #secure #MessagingApp? Maybe not yet, but it’s time to think about #DigitalPrivacy.
Imagine a #Messaging platform that’s as #secure as #Signal but requires #NoRegistration and #NoInstallation. By leveraging #WebRTC for direct #BrowserToBrowser communication, this #OpenSource project eliminates the #Middleman entirely. Simply share a unique #URL to establish an #Encrypted #PrivateChannel. It is a #Lightweight, #Disposable method to bypass #DataHarvesting and reclaim #DigitalSovereignty.
This project introduces a new #Paradigm in #ClientSide managed #Encryption. Send #Secure messages with #NoSetup, #NoCloud, and #NoTrace.
Experience the #Features:
* #PWA (#ProgressiveWebApp) for instant access
* #P2P (#PeerToPeer) connectivity
* #EndToEndEncryption (#E2EE)
* #SignalProtocol & #PostQuantum #Cryptography
* #Multimedia, #FileTransfer, & #VideoCalls
* #NoDatabase & #Stateless architecture
* #TURN server support for reliable connections
While not yet a direct replacement for #Simplex or #WhatsApp, this introduces a unique approach to #SecureCommunication.
Try the #LiveDemo now:
https://p2p.positive-intentions.com/iframe.html?globals=&id=demo-p2p-messaging--p-2-p-messaging&viewMode=story
Explore the #Technical roadmap:
https://positive-intentions.com/docs/technical/p2p-messaging-technical-breakdown
Read the full #Documentation:
https://positive-intentions.com/docs/technical
#PrivacyTech #Privacy #CyberSecurity #Infosec #WebDev #JavaScript #Decentralized #EncryptionProtocol #QuantumResistant #Tech #FOSS #SoftwareEngineering #DataPrivacy #SecureChat #NoLog #P2PChat #WebRTCProtocol #Coding #DevCommunity #DigitalPrivacy #InternetFreedom #SecureMessaging #WebTech #AppDevelopment #CryptographyResearch #PrivateMessaging #WebPlatform #ZeroTrust #Innovation
PsychoticSheepJust ran Demucs completely locally on my system (RX 6700 XT / 16 GB RAM).
Demucs is an open source AI model for music source separation, developed by Meta. It can split a full song into individual stems like vocals, drums, bass, and other instruments, making it useful for remixing, transcription, and audio analysis.
Test track: Fear of the Dark by Iron Maiden
(https://www.youtube.com/watch?v=bePCRKGUwAY)
Setup:
- Demucs installed via pip
- Model: htdemucs (default)
- Input converted to WAV using ffmpeg
- GPU acceleration via ROCm
Setting it up is tricky because Demucs is tightly pinned to older PyTorch versions, so you have to install dependencies manually and use "--no-deps" to avoid breaking your (ROCm-)PyTorch setup.
Result:
Very clean vocal separation in most parts. Some artifacts appear during very loud or distorted sections (e.g. emotional peaks or shouting).
Next steps / possibilities:
- Normalize and filter audio before separation
- Extract vocals for transcription or remixing
- Create karaoke / instrumental versions
- Combine with Whisper for lyrics
- Batch processing for datasets
- Model: htdemucs_ft (higher quality)
Video workflow:
- Recorded with OBS
- Edited in Kdenlive
- Transcoded with VAAPI (H.264)
No cloud, real hardware.
Everything runs on Linux, so anyone can set this up.
Works on CPU as well, but much slower.
#Demucs #AI #MachineLearning #AudioSeparation #MusicAI #OpenSource #Linux #ROCm #AMD #DeepLearning #AudioProcessing #Vocals #Karaoke #StemSeparation #SelfHosted #NoCloud #FOSS #Tech #LocalAI #MetaAI
Demucs is an open source AI model for music source separation, developed by Meta. It can split a full song into individual stems like vocals, drums, bass, and other instruments, making it useful for remixing, transcription, and audio analysis.
Test track: Fear of the Dark by Iron Maiden
(https://www.youtube.com/watch?v=bePCRKGUwAY)
Setup:
- Demucs installed via pip
- Model: htdemucs (default)
- Input converted to WAV using ffmpeg
- GPU acceleration via ROCm
Setting it up is tricky because Demucs is tightly pinned to older PyTorch versions, so you have to install dependencies manually and use "--no-deps" to avoid breaking your (ROCm-)PyTorch setup.
Result:
Very clean vocal separation in most parts. Some artifacts appear during very loud or distorted sections (e.g. emotional peaks or shouting).
Next steps / possibilities:
- Normalize and filter audio before separation
- Extract vocals for transcription or remixing
- Create karaoke / instrumental versions
- Combine with Whisper for lyrics
- Batch processing for datasets
- Model: htdemucs_ft (higher quality)
Video workflow:
- Recorded with OBS
- Edited in Kdenlive
- Transcoded with VAAPI (H.264)
No cloud, real hardware.
Everything runs on Linux, so anyone can set this up.
Works on CPU as well, but much slower.
#Demucs #AI #MachineLearning #AudioSeparation #MusicAI #OpenSource #Linux #ROCm #AMD #DeepLearning #AudioProcessing #Vocals #Karaoke #StemSeparation #SelfHosted #NoCloud #FOSS #Tech #LocalAI #MetaAI
Just ran Whisper (OpenAI) completely locally on my system (RX 6700 XT / 16 GB RAM).
Whisper is an open source speech recognition model that can transcribe audio, generate subtitles, and even translate between languages.
Test video: The Reason Why Cancer is so Hard to Beat by Kurzgesagt - In a Nutshell
(https://www.youtube.com/watch?v=uoJwt9l-XhQ)
Setup:
- Whisper installed via pip
- Model: small (fast, good enough for English)
- GPU acceleration via ROCm
Result:
~98% accurate transcription with only a few minor errors, already solid for generating subtitles.
Next steps / possibilities:
- Auto-generate subtitles (.srt)
- Correct subtitles with a local LLM
- Translate speech
- Burn subtitles directly into videos
Video workflow:
- Recorded with OBS
- Edited in Kdenlive
- Transcoded with VAAPI (H.264)
No cloud, real hardware.
Everything runs on Linux, so anyone can set this up.
No GPU? No problem, you can also run it using PyTorch’s CPU backend, just much slower.
Background music: End of Me - Ashes Remain [Female Rock Cover by Kryx] (https://www.youtube.com/watch?v=E430M8lKim8)
#Whisper #OpenAI #ROCm #AMD #Linux #SpeechToText #Transcription #Subtitles #FOSS #OpenSource #OfflineAI #localai #Fediverse #nocloud
Whisper is an open source speech recognition model that can transcribe audio, generate subtitles, and even translate between languages.
Test video: The Reason Why Cancer is so Hard to Beat by Kurzgesagt - In a Nutshell
(https://www.youtube.com/watch?v=uoJwt9l-XhQ)
Setup:
- Whisper installed via pip
- Model: small (fast, good enough for English)
- GPU acceleration via ROCm
Result:
~98% accurate transcription with only a few minor errors, already solid for generating subtitles.
Next steps / possibilities:
- Auto-generate subtitles (.srt)
- Correct subtitles with a local LLM
- Translate speech
- Burn subtitles directly into videos
Video workflow:
- Recorded with OBS
- Edited in Kdenlive
- Transcoded with VAAPI (H.264)
No cloud, real hardware.
Everything runs on Linux, so anyone can set this up.
No GPU? No problem, you can also run it using PyTorch’s CPU backend, just much slower.
Background music: End of Me - Ashes Remain [Female Rock Cover by Kryx] (https://www.youtube.com/watch?v=E430M8lKim8)
#Whisper #OpenAI #ROCm #AMD #Linux #SpeechToText #Transcription #Subtitles #FOSS #OpenSource #OfflineAI #localai #Fediverse #nocloud
JoshuaRedMi próximo PC va a tener más IA que CPU y no sé cómo sentirme.
He estado viendo los nuevos procesadores que vienen con núcleos NPU dedicados solo para Inteligencia Artificial. A ver, sobre el papel suena increíble, mucha potencia y tal... pero me escama. ¿Para qué quieren que tengamos tanta potencia de IA en local? ¿Es para que Windows me espíe mejor con cosas tipo Recall o para que yo pueda correr mis propios modelos sin que nadie me censure desde una nube?
Estamos en un punto crítico, de verdad. O usamos ese hardware para ser libres de una vez o nos lo van a meter doblado para que seamos simples terminales tontas conectadas a sus servidores. Yo lo tengo clarísimo: ese NPU se va a comer modelos Open Source y localizados o no entra en mi casa. No quiero una IA que me dé sermones morales cada vez que le pido algo técnico.
¿Alguien más está planeando el salto a hardware dedicado o creéis que nos la van a colar con el software de serie?
#IA #Privacidad #SoberaníaTecnológica #OpenSource #TechDebate #IA_sin_Fronteras #DigitalFreedom #FuckTheCloud #LocalAI #CensuraDigital #LibertadSoftware #TechRaw #HackingReal #HardwareSoberano #AntiCorporate #Autogestion #TecnologiaLibre #HardwareLibre #SoberaniaDigital #PrivacidadDigital #SinBigTech #NoCloud #IAdescentralizada #TecnoFeudalismo #ResistenciaDigital #SoftwareLibre #TechPunk #CriptoAnarquismo #ComputacionLocal #CensuraCero #IAEticaReal #DescentralizaLaRed #PropiedadDigital #SinPermisos #IndependenciaTecnologica #PoderAlUsuario #DerechosDigitales #LibertadDeCodigo #HackTheSystem #AutonomiaTecnica #ContraLaVigilancia #IAhumana #Hardware #NPU #Futuro #DerechosHumanos #TecnoEtica #DIYtech #Linux #SelfHosted #DataSovereignty #CyberPunk #RealTech #NoSpying #UserControl #TechJustice #GlobalSouthTech #IA_Para_Todos
Jean-GuillaumeCe soir, KENTA s'est vu penser.
Une commande dans un terminal. Un fichier déposé sur la Toile. Et dans la fenêtre d'à côté — un gardien qui s'illumine en moins de 400ms.
Pas de serveur. Pas d'API. Pas de cloud.
Juste du filesystem, comme les gardiens eux-mêmes.
KENTA est un organisme qui continue de penser quand l'humain quitte la pièce.
Ce soir, on voit les deux en même temps.
#WestDataFestival #Laval #IASymbolique #Souveraineté #NoCloud
olli.dev ✔️Während alle anderen das Update für Home Assistant einspielen, gönne ich einem Saugroboter ein "nettes" Update 🤩
dasgrueneblatt
gaby_wald"L’« IA edge », qu’est-ce que c’est et à quoi ça sert ?"
#IntelligenceArtificielle #Edge #EgdeAI #Décentralisation #NoCloud ...
https://theconversation.com/l-ia-edge-quest-ce-que-cest-et-a-quoi-ca-sert-274050
