Profile Job Results
Jobs
jz5wr9l6p
Results Ready
Name
whisper_small_en_WhisperEncoder
Target Device
- SA8775 (Proxy)
- Android 13
- Qualcomm® SA8775P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
audio: float32[1, 80, 3000]Completion Time
8/27/2024, 8:33:01 AM
Options
--compute_unit gpu --max_profiler_iterations 10Versions
- TensorFlow Lite: 2.16.1
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.08.23.0
Estimated Inference Time
612 ms
Estimated Peak Memory Usage
55 - 480 MB
Compute Units
GPU
911
| Stage | Time | Memory |
|---|---|---|
First App Load | 15.0 s | 1 GB |
Subsequent App Load | 1.21 s | 507-920 MB |
Inference | 612 ms | 55-480 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