Profile Job Results
Jobs
jgon2d9dp
Results Ready
Name
whisper_base_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: float32[1, 80, 3000]Completion Time
6/28/2025, 8:58:39 AM
Options
--max_profiler_iterations 10Versions
- ONNX Runtime: 1.21.1
- QAIRT: v2.34.2.250528164111_119506
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.06.12.0
Estimated Inference Time
195 ms
Estimated Peak Memory Usage
1 ‑ 2 GB
Compute Units
NPU
434
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.91 min | 495‑502 MB |
Subsequent App Load | 1.93 min | 4,019‑67 MB |
Inference | 195 ms | 1‑2 GB |
| ONNX Runtime | Value |
|---|---|
| execution_mode | SEQUENTIAL |
| intra_op_num_threads | 0 |
| inter_op_num_threads | 0 |
| enable_memory_pattern | false |
| enable_cpu_memory_arena | false |
| graph_optimization_level | ENABLE_ALL |
| QNN Execution Provider | Value |
|---|---|
| htp_performance_mode | "burst" |
| htp_graph_finalization_optimization_mode | "3" |
| enable_htp_fp16_precision | "1" |
| capture_network_visualizations | false |
Sign up to run this model on a hosted Qualcomm® device!
Run on device