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
Files
Weights, configs, and per-vendor compiled exports. Files marked LFS are stored on the Fo’c’sle CDN and served regional.
| Name | Size | Updated | |
|---|---|---|---|
| README.md | 8.4 KB | 2028-03-18 | |
| config.json | 2.1 KB | 2028-03-18 | |
| tokenizer.json | 1.8 MB | 2028-03-18 | |
| model.safetensorsLFS | 46.0 MB | 2028-03-18 | |
| whisper-edge-tiny.onnxLFS | 41.0 MB | 2028-03-18 | |
| whisper-edge-tiny_int8.tfliteLFS | 39 MB | 2028-03-18 | |
| whisper-edge-tiny.hailo8.hefLFS | 35 MB | 2028-03-18 | |
| whisper-edge-tiny.mlmodelcLFS | 43 MB | 2028-03-18 | |
| examples/ | — | 2028-03-18 | |
| benchmarks/ | — | 2028-03-18 | |
| LICENSE | 11.4 KB | 2028-03-18 |