Meet open source local: insanely-fast-whisper: Incredibly fast Whisper-large-v3.
Transcribe 300 minutes (5 hours) of audio in less than 98 seconds - with OpenAI's Whisper Large v3.
I am using it now.
You have no excuse to not build your own AI. https://t.co/PMjmXQC096
The @MODI_CCAM showcased at #IPIC Athens last week with a great impact.
@FernandoLiesa explained the project's objectives, and @Dr_PO took part in the "Electric and Autonomous only make sense when going full Physical Internet" plenary session.
Einride goes live in Norway in a partnership with Postnord; together we will reduce 2,100 tonnes of CO2 emissions across three years. Read more about this exciting deployment. https://t.co/eoJAfriQa0
Einride Mesh 2023 surpassed all expectations thanks to our amazing team. A special thanks to all the insightful attendees and esteemed Mesh speakers whose enlightening discussions made this event a success. Join us next year in 2024. https://t.co/xjEa3RngQ9
Elektrifiering, digitalisering och AI kan revolutionera framtidens vägtransporter. Lyssna på nytt avsnitt av podden Innovation med Per Olof Arnäs @Dr_PO@einrideofficial och Sofia Wieselfors, Vinnova. Finns där poddar finns.
@jordibruin Love this! Are you also considering automatic speaker identification? Like:
* Identify Speaker 1, 2, 3 etc.
* I then name them
* JSON export with speaker names
@jordibruin I think I have voted. In the App Store app the vote count does not increase when I click. Is diarization part of the Whisper model or do you need another model for that?