Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jgn6o68k5
Results Ready
Name
whisper_small_en_WhisperDecoder
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
x: int32[1, 1]
index: int32[1, 1]
k_cache_cross: float32[12, 12, 64, 1500]
v_cache_cross: float32[12, 12, 1500, 64]
k_cache_self: float32[12, 12, 64, 224]
v_cache_self: float32[12, 12, 224, 64]
Completion Time
11/26/2024, 9:47:57 AM
Versions
  • TensorFlow Lite: 2.17.0
  • QNN TfLite Delegate: v2.28.2.241116104011_103376
  • Android: 14 (UP1A.231005.007)
  • AI Hub: aihub-2024.11.22.0
Estimated Inference Time
28.7 ms
Estimated Peak Memory Usage
16 ‑ 101 MB
Compute Units
NPU
2573
StageTimeMemory
First App Load
23.0 s3 GB
Subsequent App Load
23.1 s4 GB
Inference
28.7 ms16‑101 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