Profile Job Results

    Jobs
    jygzoqqk5
    Results Ready
    Name
    whisper_base_en_WhisperDecoder
    Target Device
    QCS8550 (Proxy) (12)
    Creator
    ai-hub-support@qti.qualcomm.com
    Target Model
    Input Specs
    x: int32[1, 1]
    index: int32[1, 1]
    mask: int32[1, 224, 512]
    b0_cross_attn_k: float32[1, 1500, 512]
    b0_cross_attn_v: float32[1, 1500, 512]
    b1_cross_attn_k: float32[1, 1500, 512]
    b1_cross_attn_v: float32[1, 1500, 512]
    b2_cross_attn_k: float32[1, 1500, 512]
    b2_cross_attn_v: float32[1, 1500, 512]
    b3_cross_attn_k: float32[1, 1500, 512]
    b3_cross_attn_v: float32[1, 1500, 512]
    b4_cross_attn_k: float32[1, 1500, 512]
    b4_cross_attn_v: float32[1, 1500, 512]
    b5_cross_attn_k: float32[1, 1500, 512]
    b5_cross_attn_v: float32[1, 1500, 512]
    b0_self_attn_k: float32[1, 224, 512]
    b0_self_attn_v: float32[1, 224, 512]
    b1_self_attn_k: float32[1, 224, 512]
    b1_self_attn_v: float32[1, 224, 512]
    b2_self_attn_k: float32[1, 224, 512]
    b2_self_attn_v: float32[1, 224, 512]
    b3_self_attn_k: float32[1, 224, 512]
    b3_self_attn_v: float32[1, 224, 512]
    b4_self_attn_k: float32[1, 224, 512]
    b4_self_attn_v: float32[1, 224, 512]
    b5_self_attn_k: float32[1, 224, 512]
    b5_self_attn_v: float32[1, 224, 512]
    Completion Time
    4/16/2024, 7:46:11 PM
    Estimated Inference Time
    13.9 ms
    Estimated Peak Memory Usage
    5 - 8 MB
    Compute Units
    NPU
    447
    CPU
    2
    StageTimeMemory
    First App Load
    3.26 s1 GB
    Subsequent App Load
    295 ms148-149 MB
    Inference
    13.9 ms5-8 MB

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

    Run on device