Qualcomm® AI HubAI Hub
Qualcomm® AI Hub Models
Whisper-Base-En

Profile Job Results

Jobs
jp3n63xz5
Results Ready
Name
whisper_base_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
3/11/2025, 1:09:45 PM
Options
--max_profiler_iterations 10
Versions
  • QAIRT: v2.32.0.250228225014_116386
  • QNN Backend API: 5.32.0
  • QNN Core API: 2.24.0
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2025.03.06.0
Estimated Inference Time
250 ms
Estimated Peak Memory Usage
1 ‑ 3 MB
Compute Units
NPU
529
StageTimeMemory
First App Load
685 ms2‑3 MB
Subsequent App Load
602 ms1‑2 MB
Inference
250 ms1‑3 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