Profile Job Results
Jobs
j5we8we35
Results Ready
Name
whisper_small_en_WhisperDecoder
Target Device
- Samsung Galaxy S24 (Family)
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
x: int32[1, 1]index: int32[1, 1]k_cache_cross: float32[12, 12, 64, 1500]v_cache_cross: float32[12, 12, 1500, 64]k_cache_self: float32[12, 12, 64, 224]v_cache_self: float32[12, 12, 224, 64]Completion Time
11/26/2024, 9:55:54 AM
Versions
- ONNX Runtime: 1.19.2
- QNN: v2.28.2.241116104011_103376
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
48.0 ms
Estimated Peak Memory Usage
0 ‑ 1 GB
Compute Units
NPU
2302
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.38 min | 4 GB |
Subsequent App Load | 759 ms | 1‑2 GB |
Inference | 48.0 ms | 0‑1 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" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device