Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jgl2vwoep
Results Ready
Name
whisper_small_en_WhisperEncoderInf
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
audio: float32[1, 80, 3000]
Completion Time
6/28/2025, 7:58:05 AM
Options
--compute_unit gpu --max_profiler_iterations 10
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 14 (UP1A.231005.007)
  • AI Hub: aihub-2025.06.12.0
Estimated Inference Time
675 ms
Estimated Peak Memory Usage
45 ‑ 119 MB
Compute Units
GPU
900
CPU
11
StageTimeMemory
First App Load
12.2 s1 GB
Subsequent App Load
11.9 s935‑937 MB
Inference
675 ms45‑119 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