Profile Job Results
Jobs
jp0zynr95
Results Ready
Name
whisper_tiny_en_WhisperEncoder
Target Device
- Samsung Galaxy S24 (Family)
- 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
1/21/2025, 9:36:19 AM
Options
--compute_unit gpu --max_profiler_iterations 10
Versions
- TensorFlow Lite: 2.17.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.01.04.0
Estimated Inference Time
82.1 ms
Estimated Peak Memory Usage
20 ‑ 61 MB
Compute Units
GPU
260
CPU
11
Stage | Time | Memory |
---|---|---|
First App Load | 2.26 s | 127‑134 MB |
Subsequent App Load | 2.28 s | 117‑166 MB |
Inference | 82.1 ms | 20‑61 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