Cactus Compute

Whistle is a new speech-to-text model that fits in just 16.9 MB, making transcription practical on-device even on low-resource hardware. Announced in a blog post by Cactus Compute, it has drawn attention for how small it is compared with typical speech models. Readers are discussing its accuracy, language coverage, and what tiny on-device models mean for privacy-friendly transcription.

Developers are highlighting Whistle, an open-source speech-to-text model that fits in just 16.9 MB, detailed in a post by Cactus Compute. The model's small footprint makes it practical for running transcription locally on constrained devices. Tech communities are sharing the link and discussing its potential for on-device AI.