Profile Job Results
Jobs
j1pvnwdmg
Results Ready
Name
whisper_small_en_WhisperEncoder
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
8/27/2024, 8:35:19 AM
Options
--compute_unit gpu --max_profiler_iterations 10Versions
- TensorFlow Lite: 2.16.1
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2024.08.23.0
Estimated Inference Time
482 ms
Estimated Peak Memory Usage
107 - 196 MB
Compute Units
GPU
911
| Stage | Time | Memory |
|---|---|---|
First App Load | 11.5 s | 1 GB |
Subsequent App Load | 631 ms | 670-800 MB |
Inference | 482 ms | 107-196 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device