Mark Filion
April 03, 2024
Reading time:
WhisperFusion, and its fully open source text-to-speech models, has been nominated for Embedded Award 2024, in the artificial intelligence category!
Honouring outstanding innovations in the field of embedded system technologies, the annual Embedded Award ceremony will be taking place next week at Embedded World 2024 in Nuremberg. Collabora is absolutely thrilled to see WhisperFusion nominated for this esteemed award.
Developed entirely in the open, WhisperFusion uses both WhisperLive and WhisperSpeech to create a real-time AI chatbot communication system, addressing the unnatural delay in current bot interactions for seamless conversation.
WhisperFusion's diverse applications span entertainment, commercial, and educational contexts. Collabora will be showcasing the award-nominated WhisperFusion as part of an advanced AI Front Counter/Drive-Thru sales agent demonstration. Powered by WhisperLive, WhisperSpeech, Phi-2, torch.compile, and AMD, the demo will be available throughout the week at Collabora's booth (Hall 4, booth #404).
In addition to our booth and demonstrations, Marcus Edel, Collabora's Machine Learning lead, will be taking part in the Embedded Vision & Edge AI track at the Embedded World Conference, with a talk exploring how language learning models utilize GPU capabilities on embedded devices.
02/06/2025
Next week Collabora will be covering a lot of ground, attending 3 separate events in 3 different time zones: ISC High Performance, Augmented…
29/05/2025
After cleaning up and expanding Whisper-Hindi to 3,000 hours, we now have explicit timestamp prediction, faster I/O, and fine-tuned models…
27/05/2025
The latest Linux kernel brings expanded hardware support for MediaTek and Rockchip, enhanced graphics drivers, and more. Collabora played…
Comments (0)
Add a Comment