Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jg9lk008g
Results Ready
Name
whisper_base_en_WhisperDecoder
Target Device
  • SA8255 (Proxy)
  • Android 13
  • Qualcomm® SA8255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
x: int32[1, 1]
index: int32[1, 1]
k_cache_cross: float32[6, 8, 64, 1500]
v_cache_cross: float32[6, 8, 1500, 64]
k_cache_self: float32[6, 8, 64, 224]
v_cache_self: float32[6, 8, 224, 64]
Completion Time
11/26/2024, 10:01:01 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
38.5 ms
Estimated Peak Memory Usage
6 ‑ 44 MB
Compute Units
NPU
983
StageTimeMemory
First App Load
13.1 s1 GB
Subsequent App Load
12.8 s0‑1 GB
Inference
38.5 ms6‑44 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