Profile Job Results
Jobs
jpr2vxov5
Results Ready
Name
whisper_small_en_WhisperDecoderInf
Target Device
- SA8255 (Proxy)
- Android 13
- Qualcomm® SA8255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
x
: int32[1, 1]index
: int32[1, 1]k_cache_cross
: float32[12, 12, 64, 1500]v_cache_cross
: float32[12, 12, 1500, 64]k_cache_self
: float32[12, 12, 64, 224]v_cache_self
: float32[12, 12, 224, 64]Completion Time
6/28/2025, 7:58:03 AM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.34.2.250528164111_119506
- QNN TfLite Delegate: v2.34.2.250528164111_119506
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.06.12.0
Estimated Inference Time
51.0 ms
Estimated Peak Memory Usage
10 ‑ 42 MB
Compute Units
NPU
2573
Stage | Time | Memory |
---|---|---|
First App Load | 16.2 s | 2 GB |
Subsequent App Load | 14.3 s | 2 GB |
Inference | 51.0 ms | 10‑42 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