Momentum
A 16.9 MB Speech Model for Devices: Cactus Whistle Draws 16K Downloads
16K+ HF downloads Community reports 2 sources
C
Cactus Whistle
News Oct 12, 2026
Cactus Compute's on-device speech model packages seven-language transcription, word timestamps and audio embeddings in a creator-described 16.9 MB file.
2 sources attached
What happened lately
Cactus Whistle timeline
Cactus Compute pitches Whistle as a compact speech-to-text model for phones, wearables and other devices. Its English model card describes a single 16.9 MB model file supporting seven languages, word timestamps and audio embeddings without a GPU. Those capabilities and size are the creator’s descriptions, not independent measurements by AITrending.
The Hugging Face repository was created September 30. It appeared in a trend snapshot checked October 12, when the platform listed 16,434 cumulative downloads and 349 likes. Those counters indicate attention to the project but do not establish when each download occurred or how many distinct people used it.