OEby OpenAI-Edge
Whisper-Edge-Tiny
8%Edge fork of Whisper-Tiny with NPU-friendly attention rewriting. INT4 variant runs on the Pi alone.
Embedded ASRMITINT8INT4asrenglishtiny
412K downloads 25K deploymentsUpdated Mar 18, 2028
Headline:220ms · Raspberry Pi 5 + Hailo HAT · INT8
HIL simulation runs
End-to-end runs of Whisper-Edge-Tiny in scenario rigs that match real customer conditions. Each tile is an actual playable HIL session — sustained throughput, in-sim accuracy, intervention counts, the whole trace.
48 FPS94.1% acc
Open
Logistics · Apron
Airport baggage · Whisper-Edge-Tiny
Whisper-Edge-Tiny×HHailo-8
37 min runMar 18, 2028
24 FPS88.6% acc
Open
Robotics · AMR
Warehouse amr · Whisper-Edge-Tiny
Whisper-Edge-Tiny×QQualcomm QCS6490
70 min runMar 18, 2028
18 FPS90.4% acc
Open
Industrial · Inspection
Factory inspection · Whisper-Edge-Tiny
Whisper-Edge-Tiny×QQualcomm QCS8550
61 min runMar 18, 2028
58 FPS92.8% acc
Open
AV · Urban
Av urban · Whisper-Edge-Tiny
Whisper-Edge-Tiny×QSnapdragon 8 Gen 3 NPU
32 min runMar 18, 2028
Pro tier opens up scenario authoring
Pro and Team customers can configure custom HIL scenarios — chain CARLA towns, drop in your own actor policies, and pin the exact downstream consumers your fleet runs. Enterprise extends this to dedicated rigs in the lab and on-prem replication.