Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
j5w3733mp
Results Ready
Name
whisper_base_en_HfWhisperDecoder
Target Device
  • SA8775P ADP
  • Android 14
  • Qualcomm® SA8775P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_ids: int32[1, 1]
attention_mask: float32[1, 1, 1, 200]
k_cache_self_0_in: float32[8, 1, 64, 199]
v_cache_self_0_in: float32[8, 1, 199, 64]
k_cache_self_1_in: float32[8, 1, 64, 199]
v_cache_self_1_in: float32[8, 1, 199, 64]
k_cache_self_2_in: float32[8, 1, 64, 199]
v_cache_self_2_in: float32[8, 1, 199, 64]
k_cache_self_3_in: float32[8, 1, 64, 199]
v_cache_self_3_in: float32[8, 1, 199, 64]
k_cache_self_4_in: float32[8, 1, 64, 199]
v_cache_self_4_in: float32[8, 1, 199, 64]
k_cache_self_5_in: float32[8, 1, 64, 199]
v_cache_self_5_in: float32[8, 1, 199, 64]
k_cache_cross_0: float32[8, 1, 64, 1500]
v_cache_cross_0: float32[8, 1, 1500, 64]
k_cache_cross_1: float32[8, 1, 64, 1500]
v_cache_cross_1: float32[8, 1, 1500, 64]
k_cache_cross_2: float32[8, 1, 64, 1500]
v_cache_cross_2: float32[8, 1, 1500, 64]
k_cache_cross_3: float32[8, 1, 64, 1500]
v_cache_cross_3: float32[8, 1, 1500, 64]
k_cache_cross_4: float32[8, 1, 64, 1500]
v_cache_cross_4: float32[8, 1, 1500, 64]
k_cache_cross_5: float32[8, 1, 64, 1500]
v_cache_cross_5: float32[8, 1, 1500, 64]
position_ids: int32[1]
Completion Time
8/23/2025, 8:17:35 PM
Options
--qairt_version latest
Versions
  • TensorFlow Lite: 2.17.0
  • QAIRT: v2.37.0.250724175447_124859-auto
  • QNN TfLite Delegate: v2.37.0.250724175447_124859-auto
  • Android: 14 (UQ1A.240205.002)
  • Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00011-STD.PROD-1.89321.2
  • AI Hub: aihub-2025.08.21.0
Estimated Inference Time
7.00 ms
Estimated Peak Memory Usage
5 ‑ 154 MB
Compute Units
NPU
1144
StageTimeMemory
First App Load
11.2 s831‑840 MB
Subsequent App Load
11.2 s1 GB
Inference
7.00 ms5‑154 MB
TensorFlow LiteValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.precisionkHtpFp16
htp_options.useConvHmxtrue
htp_options.device_id1

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

Run on device