Profile Job Results
Jobs
jp1y4eo7p
Results Ready
Name
whisper_small_v2_HfWhisperDecoder
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_ids: int32[1, 1]attention_mask: float32[1, 1, 1, 200]k_cache_self_0_in: float32[12, 1, 64, 199]v_cache_self_0_in: float32[12, 1, 199, 64]k_cache_self_1_in: float32[12, 1, 64, 199]v_cache_self_1_in: float32[12, 1, 199, 64]k_cache_self_2_in: float32[12, 1, 64, 199]v_cache_self_2_in: float32[12, 1, 199, 64]k_cache_self_3_in: float32[12, 1, 64, 199]v_cache_self_3_in: float32[12, 1, 199, 64]k_cache_self_4_in: float32[12, 1, 64, 199]v_cache_self_4_in: float32[12, 1, 199, 64]k_cache_self_5_in: float32[12, 1, 64, 199]v_cache_self_5_in: float32[12, 1, 199, 64]k_cache_self_6_in: float32[12, 1, 64, 199]v_cache_self_6_in: float32[12, 1, 199, 64]k_cache_self_7_in: float32[12, 1, 64, 199]v_cache_self_7_in: float32[12, 1, 199, 64]k_cache_self_8_in: float32[12, 1, 64, 199]v_cache_self_8_in: float32[12, 1, 199, 64]k_cache_self_9_in: float32[12, 1, 64, 199]v_cache_self_9_in: float32[12, 1, 199, 64]k_cache_self_10_in: float32[12, 1, 64, 199]v_cache_self_10_in: float32[12, 1, 199, 64]k_cache_self_11_in: float32[12, 1, 64, 199]v_cache_self_11_in: float32[12, 1, 199, 64]k_cache_cross_0: float32[12, 1, 64, 1500]v_cache_cross_0: float32[12, 1, 1500, 64]k_cache_cross_1: float32[12, 1, 64, 1500]v_cache_cross_1: float32[12, 1, 1500, 64]k_cache_cross_2: float32[12, 1, 64, 1500]v_cache_cross_2: float32[12, 1, 1500, 64]k_cache_cross_3: float32[12, 1, 64, 1500]v_cache_cross_3: float32[12, 1, 1500, 64]k_cache_cross_4: float32[12, 1, 64, 1500]v_cache_cross_4: float32[12, 1, 1500, 64]k_cache_cross_5: float32[12, 1, 64, 1500]v_cache_cross_5: float32[12, 1, 1500, 64]k_cache_cross_6: float32[12, 1, 64, 1500]v_cache_cross_6: float32[12, 1, 1500, 64]k_cache_cross_7: float32[12, 1, 64, 1500]v_cache_cross_7: float32[12, 1, 1500, 64]k_cache_cross_8: float32[12, 1, 64, 1500]v_cache_cross_8: float32[12, 1, 1500, 64]k_cache_cross_9: float32[12, 1, 64, 1500]v_cache_cross_9: float32[12, 1, 1500, 64]k_cache_cross_10: float32[12, 1, 64, 1500]v_cache_cross_10: float32[12, 1, 1500, 64]k_cache_cross_11: float32[12, 1, 64, 1500]v_cache_cross_11: float32[12, 1, 1500, 64]position_ids: int32[1]Completion Time
4/8/2025, 8:52:38 AM
Versions
- TensorFlow Lite: 2.17.0
- QAIRT: v2.32.0.250228225014_116386
- QNN TfLite Delegate: v2.32.0.250228225014_116386
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.03.24.0
Estimated Inference Time
23.9 ms
Estimated Peak Memory Usage
14 ‑ 32 MB
Compute Units
NPU
3136
| Stage | Time | Memory |
|---|---|---|
First App Load | 22.2 s | 2 GB |
Subsequent App Load | 21.8 s | 2 GB |
Inference | 23.9 ms | 14‑32 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