Profile Job Results
Jobs
jgzjv1m6p
Results Ready
Name
whisper_medium_en_WhisperEncoderInf
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
audio: float32[1, 80, 3000]Completion Time
8/2/2025, 2:02:02 PM
Options
--compute_unit gpu --max_profiler_iterations 10Versions
- TensorFlow Lite: 2.17.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.07.25.0
Estimated Inference Time
1.71 s
Estimated Peak Memory Usage
172 ‑ 416 MB
Compute Units
GPU
1980
CPU
11
| Stage | Time | Memory |
|---|---|---|
First App Load | 22.0 s | 3 GB |
Subsequent App Load | 25.2 s | 3 GB |
Inference | 1.71 s | 172‑416 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