Profile Job Results
Jobs
j57ykywv5
Results Ready
Name
whisper_tiny_en_WhisperDecoder
Target Device
- XR2 Gen 2 (Proxy)
- Android 13
- Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
x: int32[1, 1]index: int32[1, 1]k_cache_cross: float32[4, 6, 64, 1500]v_cache_cross: float32[4, 6, 1500, 64]k_cache_self: float32[4, 6, 64, 224]v_cache_self: float32[4, 6, 224, 64]Completion Time
11/26/2024, 9:42:16 AM
Versions
- QNN: v2.28.2.241116104011_103376
- QNN Backend API: 5.28.0
- QNN Core API: 2.21.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
2.92 ms
Estimated Peak Memory Usage
9 ‑ 51 MB
Compute Units
NPU
447
| Stage | Time | Memory |
|---|---|---|
First App Load | 2.46 s | 458‑466 MB |
Subsequent App Load | 2.31 s | 195‑439 MB |
Inference | 2.92 ms | 9‑51 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.precision | FLOAT16 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device