Profile Job Results

Jobs
jz5wyl26g
Results Ready
Name
whisper_small_en_WhisperEncoder
Target Device
  • SA8255 (Proxy)
  • Android 13
  • Qualcomm® SA8255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
audio: float32[1, 80, 3000]
Completion Time
8/11/2024, 6:08:05 AM
Options
--max_profiler_iterations 10
Versions
  • 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
1.29 s
Estimated Peak Memory Usage
1 - 2 MB
Compute Units
NPU
1329
StageTimeMemory
First App Load
1.16 s32-33 MB
Subsequent App Load
602 ms1-30 MB
Inference
1.29 s1-2 MB
QNNValue
context_options.htp_options.performance_modeBURST
default_graph_options.htp_options.precisionFLOAT16

Sign up to run this model on a hosted Qualcomm® device!

Run on device