Profile Job Results
Jobs
j5q6z6j4p
Results Ready
Name
whisper_tiny_en_WhisperDecoder
Target Device
- Samsung Galaxy S23 (Family)
- Android 13
- Snapdragon® 8 Gen 2 | SM8550
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
11/26/2024, 9:36:29 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
3.99 ms
Estimated Peak Memory Usage
3 ‑ 50 MB
Compute Units
NPU
557
| Stage | Time | Memory |
|---|---|---|
First App Load | 7.45 s | 606‑607 MB |
Subsequent App Load | 7.51 s | 460‑757 MB |
Inference | 3.99 ms | 3‑50 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device