Profile Job Results
Jobs
jg9y96dv5
Results Ready
Name
whisper_small_en_WhisperEncoderInf
Target Device
- SA7255P ADP
- Android 14
- Qualcomm® SA7255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
audio: float32[1, 80, 3000]Completion Time
8/2/2025, 2:03:31 PM
Options
--compute_unit gpu --max_profiler_iterations 10Versions
- TensorFlow Lite: 2.17.0
- Android: 14 (UQ1A.240205.002)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00012-STD.PROD-5
- AI Hub: aihub-2025.07.25.0
Estimated Inference Time
3.23 s
Estimated Peak Memory Usage
109 ‑ 142 MB
Compute Units
GPU
900
CPU
11
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.03 min | 970‑980 MB |
Subsequent App Load | 1.02 min | 1 GB |
Inference | 3.23 s | 109‑142 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| GPUv2 Delegate | Value |
|---|---|
| inference_preference | TFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED |
| inference_priority1 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY |
| inference_priority2 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE |
| inference_priority3 | TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device