Profile Job Results
Jobs
jgj2v3r85
Results Ready
Name
whisper_large_v3_turbo_HfWhisperEncoder
Target Device
- SA7255P ADP
- Android 14
- Qualcomm® SA7255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_features: float16[1, 128, 3000]Completion Time
6/28/2025, 8:51:51 AM
Options
--max_profiler_iterations 10Versions
- QAIRT: v2.34.2.250528164111_119506-auto
- QNN Backend API: 5.34.0
- QNN Core API: 2.25.0
- Android: 14 (UQ1A.240205.002)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00012-STD.PROD-5
- AI Hub: aihub-2025.06.12.0
Estimated Inference Time
2.63 s
Estimated Peak Memory Usage
1 ‑ 10 MB
Compute Units
NPU
5026
| Stage | Time | Memory |
|---|---|---|
First App Load | 13.7 s | 27‑34 MB |
Subsequent App Load | 8.56 s | 26‑34 MB |
Inference | 2.63 s | 1‑10 MB |
| QNN | Value |
|---|---|
| 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