Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jogkdnoop
Results Ready
Name
whisper_tiny_en_WhisperDecoder
Target Device
QCS8550 (Proxy) (12)
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
6/23/2024, 7:32:34 AM
Estimated Inference Time
3.88 ms
Estimated Peak Memory Usage
3 - 5 MB
Compute Units
NPU
557
StageTimeMemory
Compilation
0 ms0 MB
First App Load
2.42 s581-582 MB
Subsequent App Load
259 ms94-176 MB
Inference
3.88 ms3-5 MB

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

Run on device