Profile Job Results
Jobs
jp20olyrg
Results Ready
Name
whisper_tiny_en_WhisperDecoderInf
Target Device
- SA7255P ADP
- Android 14
- Qualcomm® SA7255P
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
5/20/2025, 9:26:48 AM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.6.250402152434_116405-auto
- QNN TfLite Delegate: v2.32.6.250402152434_116405-auto
- Android: 14 (UQ1A.240205.002)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00012-STD.PROD-5
- AI Hub: aihub-2025.05.14.0
Estimated Inference Time
6.88 ms
Estimated Peak Memory Usage
3 ‑ 70 MB
Compute Units
NPU
557
| Stage | Time | Memory |
|---|---|---|
First App Load | 9.86 s | 384‑393 MB |
Subsequent App Load | 9.95 s | 392‑521 MB |
Inference | 6.88 ms | 3‑70 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.precision | kHtpFp16 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device