Profile Job Results
Jobs
jnp1on225
Results Ready
Name
whisper_small_en_WhisperEncoder
Target Device
- QCS8550 (Proxy)
- Android 12
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
audio: float32[1, 80, 3000]Completion Time
8/11/2024, 5:39:50 AM
Options
--compute_unit gpu --max_profiler_iterations 10Versions
- TensorFlow Lite: 2.16.1
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2024.08.01.0
Estimated Inference Time
610 ms
Estimated Peak Memory Usage
0 - 432 MB
Compute Units
GPU
911
| Stage | Time | Memory |
|---|---|---|
First App Load | 13.4 s | 999-1,000 MB |
Subsequent App Load | 1.12 s | 802-961 MB |
Inference | 610 ms | 0-432 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