Profile Job Results
Jobs
jp3vx6elg
Results Ready
Name
whisper_tiny_en_WhisperEncoderInf
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
audio: float16[1, 80, 3000]Completion Time
5/6/2025, 7:57:17 AM
Options
--max_profiler_iterations 10Versions
- QAIRT: v2.32.6.250402152434_116405
- QNN Backend API: 5.32.0
- QNN Core API: 2.24.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.05.02.0
Estimated Inference Time
56.8 ms
Estimated Peak Memory Usage
1 ‑ 243 MB
Compute Units
NPU
311
| Stage | Time | Memory |
|---|---|---|
First App Load | 23.9 s | 664‑672 MB |
Subsequent App Load | 25.2 s | 1 GB |
Inference | 56.8 ms | 1‑243 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.optimizations[0].type | FINALIZE_OPTIMIZATION_FLAG |
| default_graph_options.htp_options.optimizations[0].value | 3.0 |
| default_graph_options.htp_options.precision | FLOAT16 |
| default_graph_options.htp_options.vtcm_size | 0 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device