Mmastodon TechnologySoftware first seen 8 h ago, last 8 h ago, peak #5
Whistle: tiny open-source speech-to-text model released
Original: Whistle: Speech to Text in 16.9 MB https://cactuscompute.com/blog/whistle # AI # OpenSource # SpeechToText
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.
Why now: A newly released, unusually small open-source transcription model is drawing attention in developer communities.
Evidence
- Whistle: Speech to Text in 16.9 MB https://cactuscompute.com/blog/whistle # AI # OpenSource # SpeechToText · lobsters@robot.villas · 4
API: https://socialmediatrends-api.osmike.com/v1/trends/1620999