Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
j5q68jmop
Results Ready
Name
whisper_base_en_WhisperEncoder
Target Device
  • XR2 Gen 2 (Proxy)
  • Android 13
  • Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
audio: float32[1, 80, 3000]
Completion Time
1/21/2025, 9:55:52 AM
Options
--compute_unit gpu --max_profiler_iterations 10
Versions
  • TensorFlow Lite: 2.17.0
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2025.01.04.0
Estimated Inference Time
275 ms
Estimated Peak Memory Usage
38 ‑ 85 MB
Compute Units
GPU
408
CPU
11
StageTimeMemory
First App Load
7.47 s229‑238 MB
Subsequent App Load
6.54 s271‑330 MB
Inference
275 ms38‑85 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