Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
j5q6z6onp
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
11/26/2024, 9:47:12 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
710 ms
Estimated Peak Memory Usage
78 ‑ 445 MB
Compute Units
GPU
900
CPU
11
StageTimeMemory
First App Load
12.0 s1 GB
Subsequent App Load
788 ms747‑789 MB
Inference
710 ms78‑445 MB
TensorFlow LiteValue
number_of_threads4
GPUv2 DelegateValue
inference_preferenceTFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED
inference_priority1TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY
inference_priority2TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE
inference_priority3TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION
XNNPACK DelegateValue

Sign up to run this model on a hosted Qualcomm® device!

Run on device