Profile Job Results
Jobs
jp140r37p
Results Ready
Name
whisper_small_en_WhisperEncoder
Target Device
- SA8650 (Proxy)
- Android 13
- Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
audio
: float32[1, 80, 3000]Completion Time
1/21/2025, 9:45:47 AM
Options
--compute_unit gpu --max_profiler_iterations 10
Versions
- TensorFlow Lite: 2.17.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.01.04.0
Estimated Inference Time
684 ms
Estimated Peak Memory Usage
18 ‑ 157 MB
Compute Units
GPU
900
CPU
11
Stage | Time | Memory |
---|---|---|
First App Load | 13.0 s | 1 GB |
Subsequent App Load | 12.1 s | 1 GB |
Inference | 684 ms | 18‑157 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