CPU Tasks
LoadModel       600.5 milliseconds
RunComplete     14.9475 seconds
Run     14.8676 seconds
Callbacks       8.0039 milliseconds, 37 calls, 216.322 microseconds average
Spectrogram     193.196 milliseconds, 42 calls, 4.59991 milliseconds average
Sample  52.0611 milliseconds, 511 calls, 101.881 microseconds average
Encode  5.97889 seconds, 10 calls, 597.889 milliseconds average
Decode  8.8778 seconds, 10 calls, 887.78 milliseconds average
DecodeStep      8.82556 seconds, 511 calls, 17.2712 milliseconds average
    GPU Tasks
LoadModel       457.133 milliseconds
Run     14.7971 seconds
Encode  6.01034 seconds, 10 calls, 601.034 milliseconds average
EncodeLayer     5.11447 seconds, 240 calls, 21.3103 milliseconds average
Decode  8.78676 seconds, 10 calls, 878.676 milliseconds average
DecodeStep      8.78674 seconds, 511 calls, 17.1952 milliseconds average
DecodeLayer     8.10499 seconds, 12264 calls, 660.876 microseconds average
    Compute Shaders
mulMatTiled     6.3857 seconds, 5290 calls, 1.20713 milliseconds average
mulMatByRowTiled        4.79001 seconds, 144789 calls, 33.0827 microseconds average
normFixed       417.279 milliseconds, 37793 calls, 11.0412 microseconds average
fmaRepeat1      399.385 milliseconds, 37793 calls, 10.5677 microseconds average
softMaxFixed    382.654 milliseconds, 12504 calls, 30.6025 microseconds average
addRepeatEx     378.135 milliseconds, 37272 calls, 10.1453 microseconds average
copyConvert     319.573 milliseconds, 25488 calls, 12.5382 microseconds average
copyTranspose   258.327 milliseconds, 25008 calls, 10.3298 microseconds average
softMaxLong     244.787 milliseconds, 511 calls, 479.035 microseconds average
addRepeatScale  223.995 milliseconds, 24528 calls, 9.13223 microseconds average
addRepeatGelu   181.428 milliseconds, 12524 calls, 14.4864 microseconds average
softMax 150.065 milliseconds, 12264 calls, 12.2362 microseconds average
scaleInPlace    147.891 milliseconds, 12504 calls, 11.8275 microseconds average
addRepeat       145.362 milliseconds, 12984 calls, 11.1955 microseconds average
convolutionMain2Fixed   124.04 milliseconds, 10 calls, 12.404 milliseconds average
diagMaskInf     78.8542 milliseconds, 12264 calls, 6.42973 microseconds average
convolutionMain 66.8723 milliseconds, 10 calls, 6.68723 milliseconds average
convolutionPrep1        15.4358 milliseconds, 20 calls, 771.79 microseconds average
convolutionPrep2        3.8144 milliseconds, 20 calls, 190.72 microseconds average
addRows 3.5214 milliseconds, 511 calls, 6.89119 microseconds average
add     929.8 microseconds, 10 calls, 92.98 microseconds average
    Memory Usage
Model   877.966 KB RAM, 1.42785 GB VRAM
Context 91.0716 MB RAM, 785.219 MB VRAM
Total   91.929 MB RAM, 2.19467 GB VRAM