Profile Job Results

    Jobs
    jmg9jd2w5
    Results Ready
    Name
    whisper_tiny_en_WhisperDecoder
    Target Device
    Samsung Galaxy S24+ (14)
    Creator
    ai-hub-support@qti.qualcomm.com
    Target Model
    Input Specs
    x: int32[1, 1]
    index: int32[1, 1]
    mask: int32[1, 224, 384]
    b0_cross_attn_k: float32[1, 1500, 384]
    b0_cross_attn_v: float32[1, 1500, 384]
    b1_cross_attn_k: float32[1, 1500, 384]
    b1_cross_attn_v: float32[1, 1500, 384]
    b2_cross_attn_k: float32[1, 1500, 384]
    b2_cross_attn_v: float32[1, 1500, 384]
    b3_cross_attn_k: float32[1, 1500, 384]
    b3_cross_attn_v: float32[1, 1500, 384]
    b0_self_attn_k: float32[1, 224, 384]
    b0_self_attn_v: float32[1, 224, 384]
    b1_self_attn_k: float32[1, 224, 384]
    b1_self_attn_v: float32[1, 224, 384]
    b2_self_attn_k: float32[1, 224, 384]
    b2_self_attn_v: float32[1, 224, 384]
    b3_self_attn_k: float32[1, 224, 384]
    b3_self_attn_v: float32[1, 224, 384]
    Completion Time
    4/14/2024, 8:09:54 AM
    Estimated Inference Time
    5.48 ms
    Estimated Peak Memory Usage
    3 - 221 MB
    Compute Units
    NPU
    303
    CPU
    2
    StageTimeMemory
    First App Load
    1.75 s629-637 MB
    Subsequent App Load
    188 ms94-321 MB
    Inference
    5.48 ms3-221 MB

    Sign up to run this model on a hosted Qualcomm® device!

    Run on device