Profile Job Results
Jobs
j1p3oznlp
Results Ready
Name
whisper_small_en_WhisperEncoder
Target Device
- QCS8550 (Proxy)
- Android 12
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
audio: float32[1, 80, 3000]Completion Time
8/11/2024, 5:54:03 AM
Options
--max_profiler_iterations 10Versions
- QNN: v2.24.0.240626131148_96320
- QNN Backend API: 5.24.0
- QNN Core API: 2.17.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.08.01.0
Estimated Inference Time
1.28 s
Estimated Peak Memory Usage
1 - 2 MB
Compute Units
NPU
1329
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.46 s | 2-3 MB |
Subsequent App Load | 539 ms | 1-30 MB |
Inference | 1.28 s | 1-2 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