Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jg9lklvwg
Results Ready
Name
whisper_tiny_en_WhisperDecoder
Target Device
  • SA8650 (Proxy)
  • Android 13
  • Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
x: int32[1, 1]
index: int32[1, 1]
k_cache_cross: float32[4, 6, 64, 1500]
v_cache_cross: float32[4, 6, 1500, 64]
k_cache_self: float32[4, 6, 64, 224]
v_cache_self: float32[4, 6, 224, 64]
Completion Time
11/26/2024, 9:39:47 AM
Versions
  • TensorFlow Lite: 2.17.0
  • QNN TfLite Delegate: v2.28.2.241116104011_103376
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2024.11.22.0
Estimated Inference Time
4.00 ms
Estimated Peak Memory Usage
3 ‑ 50 MB
Compute Units
NPU
557
StageTimeMemory
First App Load
7.52 s606‑607 MB
Subsequent App Load
7.44 s456‑765 MB
Inference
4.00 ms3‑50 MB
TensorFlow LiteValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.useConvHmxtrue

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

Run on device