#VOSK

16 hours ago

Speech input is one of the missing features in #Phosh's stevia. I had looked at several possible solutions but didn't want to pull in a ton more dependencies into stevia itself.

While looking for something completely different I stumbled onto #vosk-server which […]

[Original post on ruhr.social]

0 1 1 0

Nom__XD, 飲ん, 诺穆 (They/Them) 🐈‍⬛

@nom-xd.bsky.social

2 weeks ago

My #whisper plugin dev is stalled for now (blame the #AI CEOs). I'm looking into lighter alts for the CPU due to the RAM crisis—like #Vosk. On a positive note, #CUDA now runs on #Radeon via #ZLUDA, which means it might also work with a few tweaks. I just need to get my hands on a GPU for testing. 🐾

1 0 1 0

Maximilian Stefani

@mstefx.bsky.social

1 month ago

Minimalistisches Tech-Visual im Dark Mode. Eine zentrale UI-Karte visualisiert High-Speed-Spracherkennung: Links ein Mikrofon-Icon, gefolgt von einer Audio-Wellenform in Cyan und Magenta, die per Pfeil in das Wort „hoch“ übersetzt wird. Darunter die Kennzahl „< 100 ms“. Der dunkelgraue Hintergrund zeigt dezent angedeutete Server-Strukturen und „Worker“-Kästchen, die parallele Datenverarbeitung symbolisieren.

Built an ASR microservice that doesn’t overthink it: 1 word in, 1 word out.

Vosk (Offline) + FastAPI. Target: <100 ms.
Because if voice control lags, users hate it.

#Python #Vosk #FastAPI #ASR #Realtime

1 0 0 0

GLOBAL Visibility aéPiot - by aePiot.ro

@globalvisibility.bsky.social

2 months ago

aéPiot and the Future of Enterprise SaaS: Blueprint for Monetizing a 15.3M Organically-Acquired User Base. A Comprehensive Strategic Analysis of Freemium-to-Enterprise Transition. aéPiot and the Future of Enterprise SaaS: Blueprint for Monetizing a 15.3M Organically-Acquired User Base A Comprehensive Strategic Analy...

better-experience.blogspot.com/2026/01/aepi...

#MARTI #ROCA DE #TORRES
allgraph.ro/advanced-sea...
#JESSICA #VOSK
multi-search-tag-explorer.aepiot.ro/advanced-sea...
#MARK #VOS
multi-search-tag-explorer.allgraph.ro/advanced-sea...
headlines-world.com

0 0 0 0

Today In Nerd History

@todayinnerdhistory.bsky.social

5 months ago

The Star Trek Enterprise episode "Storm Front: Part 2" aired October 15, 2004.

For More Information
www.facebook.com/photo/?fbid=...

. #TodayInNerdHistory #October15 #StarTrek #StarTrekEnterprise #StormFrontPart2 #StormFront #Silik #Vosk #History #Aired #AirDate #News #OTD #FYP #Nerd .

0 0 0 0

Ronan

@ronan.mastodon.ronandev.ovh.ap.brid.gy

9 months ago

Vosk - Speaker identification model - hallucinations

vosk-model-spk-0.4 le modèle hallucine complétement, comme s'il ne prenait pas en compte le fichier audio en entrée.

0 0 0 0

Ronan

@ronan.mastodon.ronandev.ovh.ap.brid.gy

9 months ago

Original post on mastodon.ronandev.ovh

L'option "-t srt" de Vosk est intéressante pour générer des sous-titres.

Par contre, je n'ai pas encore réussi à utiliser le modèle vosk-model-spk-0.4 qui identifie les locuteurs. Le script Python vibe-codé en secondes est long à faire tourner et surtout il extrait du texte qui n'est pas dans […]

0 0 1 0