Profile Job Results
Jobs
jp8q62qop
Results Ready
Name
whisper_base_en_WhisperEncoder
Target Device
- Samsung Galaxy S23 (Family)
- Android 13
- Snapdragon® 8 Gen 2 | SM8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
audio
: float32[1, 80, 3000]Completion Time
11/26/2024, 9:56:06 AM
Options
--compute_unit gpu --max_profiler_iterations 10
Versions
- TensorFlow Lite: 2.17.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
200 ms
Estimated Peak Memory Usage
0 ‑ 81 MB
Compute Units
GPU
408
CPU
11
Stage | Time | Memory |
---|---|---|
First App Load | 4.13 s | 226‑227 MB |
Subsequent App Load | 300 ms | 158‑231 MB |
Inference | 200 ms | 0‑81 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