Profile Job Results
Jobs
j7gj8l3x5
Results Ready
Name
whisper_base_en_WhisperDecoder
Target Device
- XR2 Gen 2 (Proxy)
- Android 13
- Qualcomm® QCS8450
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
x: int32[1, 1]index: int32[1, 1]k_cache_cross: float32[6, 8, 64, 1500]v_cache_cross: float32[6, 8, 1500, 64]k_cache_self: float32[6, 8, 64, 224]v_cache_self: float32[6, 8, 224, 64]Completion Time
8/27/2024, 8:32:57 AM
Versions
- TensorFlow Lite: 2.16.1
- QNN TfLite Delegate: v2.25.0.240728104910_97711
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.08.23.0
Estimated Inference Time
26.8 ms
Estimated Peak Memory Usage
6 - 85 MB
Compute Units
NPU
983
| Stage | Time | Memory |
|---|---|---|
First App Load | 6.37 s | 990-998 MB |
Subsequent App Load | 337 ms | 146-226 MB |
Inference | 26.8 ms | 6-85 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