Sample audio clips, with performance stats

11 files changed, 373 insertions, 0 deletions

diff --git a/SampleClips/Readme.txt b/SampleClips/Readme.txt
new file mode 100644
index 0000000..69432f4
--- /dev/null
+++ b/SampleClips/Readme.txt
@@ -0,0 +1,17 @@
+This folder contains 2 sample speech audio clips, `jfk.wav` and `columbia.wma`
+
+jfk.wav is from whisper.cpp repository.
+
+columbia.wma is from Wikipedia: https://upload.wikimedia.org/wikipedia/commons/1/1f/George_W_Bush_Columbia_FINAL.ogg
+I had to re-encoded the audio from Ogg Vorbis into Windows Media Audio, because Media Foundation is unable to decode Vorbis.
+
+The rest of the text files in this folder are the outputs of the in-app performance profiler, when the app was transcribing these two audio clips on two different computers.
+
+The files names containing `1080ti` are from my desktop, which has nVidia GeForce 1080Ti GPU.
+
+The files names containing `vega7` are from my laptop, the GPU is integrated into AMD Ryzen 5 5600U processor.
+The laptop model is HP ProBook 445 G8. While running the tests, the laptop was on battery power.
+
+The files names with `medium` in the middle were made with `ggml-medium.bin` Whisper model.
+
+The files with `large` were made with `ggml-large.bin` model.
\ No newline at end of file
diff --git a/SampleClips/columbia-large-1080ti.txt b/SampleClips/columbia-large-1080ti.txt
new file mode 100644
index 0000000..a15ff4e
--- /dev/null
+++ b/SampleClips/columbia-large-1080ti.txt
@@ -0,0 +1,43 @@
+    CPU Tasks
+LoadModel       6.69478 seconds
+RunComplete     33.7046 seconds
+Run     33.637 seconds
+Callbacks       12.7347 milliseconds, 44 calls, 289.425 microseconds average
+Spectrogram     679.962 milliseconds, 41 calls, 16.5844 milliseconds average
+Sample  64.9643 milliseconds, 527 calls, 123.272 microseconds average
+Encode  13.5814 seconds, 9 calls, 1.50905 seconds average
+Decode  20.0426 seconds, 9 calls, 2.22696 seconds average
+DecodeStep      19.9774 seconds, 527 calls, 37.9077 milliseconds average
+    GPU Tasks
+LoadModel       6.50695 seconds
+Run     33.4847 seconds
+Encode  13.6283 seconds, 9 calls, 1.51426 seconds average
+EncodeLayer     11.6754 seconds, 288 calls, 40.5397 milliseconds average
+Decode  19.8563 seconds, 9 calls, 2.20626 seconds average
+DecodeStep      19.8559 seconds, 527 calls, 37.6773 milliseconds average
+DecodeLayer     18.5337 seconds, 16864 calls, 1.09901 milliseconds average
+    Compute Shaders
+mulMatTiled     14.6726 seconds, 6345 calls, 2.31247 milliseconds average
+mulMatByRowTiled        11.8939 seconds, 199430 calls, 59.6393 microseconds average
+norm    1.3396 seconds, 51704 calls, 25.909 microseconds average
+softMax 858.923 milliseconds, 17391 calls, 49.3889 microseconds average
+addRepeat       792.962 milliseconds, 68896 calls, 11.5096 microseconds average
+fmaRepeat1      567.753 milliseconds, 51704 calls, 10.9808 microseconds average
+copyConvert     541.081 milliseconds, 34880 calls, 15.5126 microseconds average
+softMaxFixed    523.378 milliseconds, 17152 calls, 30.5141 microseconds average
+copyTranspose   422.677 milliseconds, 34304 calls, 12.3215 microseconds average
+addRepeatScale  329.963 milliseconds, 33728 calls, 9.78305 microseconds average
+addInPlace      306.328 milliseconds, 34304 calls, 8.92981 microseconds average
+addRepeatGelu   290.074 milliseconds, 17170 calls, 16.8942 microseconds average
+scaleInPlace    237.756 milliseconds, 17152 calls, 13.8617 microseconds average
+add     196.816 milliseconds, 16873 calls, 11.6645 microseconds average
+convolutionMain2Fixed   187.457 milliseconds, 9 calls, 20.8285 milliseconds average
+diagMaskInf     103.247 milliseconds, 16864 calls, 6.12231 microseconds average
+convolutionMain 75.5589 milliseconds, 9 calls, 8.39543 milliseconds average
+convolutionPrep1        21.4927 milliseconds, 18 calls, 1.19404 milliseconds average
+addRows 9.2908 milliseconds, 527 calls, 17.6296 microseconds average
+convolutionPrep2        5.0944 milliseconds, 18 calls, 283.022 microseconds average
+    Memory Usage
+Model   892.591 KB RAM, 2.8815 GB VRAM
+Context 92.2616 MB RAM, 1.20719 GB VRAM
+Total   93.1333 MB RAM, 4.08869 GB VRAM
diff --git a/SampleClips/columbia-large-vega7.txt b/SampleClips/columbia-large-vega7.txt
new file mode 100644
index 0000000..836654e
--- /dev/null
+++ b/SampleClips/columbia-large-vega7.txt
@@ -0,0 +1,46 @@
+    CPU Tasks
+LoadModel       3.44286 seconds
+RunComplete     174.677 seconds
+Run     174.601 seconds
+Callbacks       22.604 milliseconds, 44 calls, 513.727 microseconds average
+Spectrogram     1.65973 seconds, 41 calls, 40.4812 milliseconds average
+Sample  148.233 milliseconds, 527 calls, 281.276 microseconds average
+Encode  110.192 seconds, 9 calls, 12.2436 seconds average
+Decode  64.3834 seconds, 9 calls, 7.15371 seconds average
+DecodeStep      64.2344 seconds, 527 calls, 121.887 milliseconds average
+    GPU Tasks
+LoadModel       2.20374 seconds
+Run     173.895 seconds
+Encode  111.531 seconds, 9 calls, 12.3923 seconds average
+EncodeLayer     96.2295 seconds, 288 calls, 334.13 milliseconds average
+Decode  62.3642 seconds, 9 calls, 6.92936 seconds average
+DecodeStep      62.3636 seconds, 527 calls, 118.337 milliseconds average
+DecodeLayer     58.6225 seconds, 16864 calls, 3.47619 milliseconds average
+    Compute Shaders
+mulMatTiledEx   89.3411 seconds, 2880 calls, 31.0212 milliseconds average
+mulMatTiled     25.4265 seconds, 3465 calls, 7.33809 milliseconds average
+mulMatByRowTiled        22.2805 seconds, 166278 calls, 133.995 microseconds average
+mulMatByRowTiledEx      13.8414 seconds, 33152 calls, 417.514 microseconds average
+softMaxFixed    3.90482 seconds, 17152 calls, 227.66 microseconds average
+addRepeatGelu   2.52778 seconds, 17170 calls, 147.221 microseconds average
+norm    2.10933 seconds, 51704 calls, 40.7962 microseconds average
+convolutionMain2Fixed   2.06899 seconds, 9 calls, 229.888 milliseconds average
+matReshapePanels        1.99444 seconds, 1737 calls, 1.14821 milliseconds average
+addRepeat       1.84752 seconds, 68896 calls, 26.816 microseconds average
+fmaRepeat1      1.28479 seconds, 51704 calls, 24.849 microseconds average
+copyConvert     1.23617 seconds, 34880 calls, 35.4406 microseconds average
+softMax 1.11773 seconds, 17391 calls, 64.2704 microseconds average
+scaleInPlace    848.371 milliseconds, 17152 calls, 49.4619 microseconds average
+copyTranspose   796.781 milliseconds, 34304 calls, 23.227 microseconds average
+addInPlace      733.523 milliseconds, 34304 calls, 21.383 microseconds average
+addRepeatScale  727.214 milliseconds, 33728 calls, 21.5611 microseconds average
+convolutionMain 535.149 milliseconds, 9 calls, 59.461 milliseconds average
+add     525.766 milliseconds, 16873 calls, 31.1602 microseconds average
+diagMaskInf     361.151 milliseconds, 16864 calls, 21.4155 microseconds average
+convolutionPrep1        58.0177 milliseconds, 18 calls, 3.22321 milliseconds average
+convolutionPrep2        30.1294 milliseconds, 18 calls, 1.67386 milliseconds average
+addRows 1.8544 milliseconds, 527 calls, 3.51879 microseconds average
+    Memory Usage
+Model   892.591 KB RAM, 2.8815 GB VRAM
+Context 92.2617 MB RAM, 1.27432 GB VRAM
+Total   93.1334 MB RAM, 4.15582 GB VRAM
diff --git a/SampleClips/columbia-medium-1080ti.txt b/SampleClips/columbia-medium-1080ti.txt
new file mode 100644
index 0000000..4a6402a
--- /dev/null
+++ b/SampleClips/columbia-medium-1080ti.txt
@@ -0,0 +1,43 @@
+    CPU Tasks
+LoadModel       766.119 milliseconds
+RunComplete     19.7043 seconds
+Run     19.5957 seconds
+Callbacks       9.6164 milliseconds, 37 calls, 259.903 microseconds average
+Spectrogram     720.672 milliseconds, 42 calls, 17.1589 milliseconds average
+Sample  64.2796 milliseconds, 511 calls, 125.792 microseconds average
+Encode  7.79098 seconds, 10 calls, 779.098 milliseconds average
+Decode  11.7948 seconds, 10 calls, 1.17948 seconds average
+DecodeStep      11.7302 seconds, 511 calls, 22.9555 milliseconds average
+    GPU Tasks
+LoadModel       611.184 milliseconds
+Run     19.4034 seconds
+Encode  7.70488 seconds, 10 calls, 770.488 milliseconds average
+EncodeLayer     6.5897 seconds, 240 calls, 27.4571 milliseconds average
+Decode  11.6985 seconds, 10 calls, 1.16985 seconds average
+DecodeStep      11.6985 seconds, 511 calls, 22.8933 milliseconds average
+DecodeLayer     10.6646 seconds, 12264 calls, 869.587 microseconds average
+    Compute Shaders
+mulMatTiled     8.16985 seconds, 5290 calls, 1.5444 milliseconds average
+mulMatByRowTiled        6.60967 seconds, 144789 calls, 45.6503 microseconds average
+softMax 797.261 milliseconds, 12775 calls, 62.4079 microseconds average
+addRepeat       571.485 milliseconds, 50256 calls, 11.3715 microseconds average
+fmaRepeat1      416.121 milliseconds, 37793 calls, 11.0105 microseconds average
+normFixed       411.604 milliseconds, 37793 calls, 10.891 microseconds average
+softMaxFixed    383.004 milliseconds, 12504 calls, 30.6305 microseconds average
+copyConvert     373.59 milliseconds, 25488 calls, 14.6575 microseconds average
+copyTranspose   337.831 milliseconds, 25008 calls, 13.5089 microseconds average
+addRepeatScale  227.901 milliseconds, 24528 calls, 9.29146 microseconds average
+addInPlace      226.48 milliseconds, 25008 calls, 9.05631 microseconds average
+addRepeatGelu   215.091 milliseconds, 12524 calls, 17.1743 microseconds average
+scaleInPlace    164.065 milliseconds, 12504 calls, 13.121 microseconds average
+add     139.896 milliseconds, 12274 calls, 11.3978 microseconds average
+convolutionMain2Fixed   129.329 milliseconds, 10 calls, 12.9329 milliseconds average
+diagMaskInf     75.8229 milliseconds, 12264 calls, 6.18256 microseconds average
+convolutionMain 70.7461 milliseconds, 10 calls, 7.07461 milliseconds average
+convolutionPrep1        16.0788 milliseconds, 20 calls, 803.94 microseconds average
+convolutionPrep2        5.4456 milliseconds, 20 calls, 272.28 microseconds average
+addRows 4.1574 milliseconds, 511 calls, 8.13581 microseconds average
+    Memory Usage
+Model   877.966 KB RAM, 1.42785 GB VRAM
+Context 91.0719 MB RAM, 841.634 MB VRAM
+Total   91.9293 MB RAM, 2.24976 GB VRAM
diff --git a/SampleClips/columbia-medium-vega7.txt b/SampleClips/columbia-medium-vega7.txt
new file mode 100644
index 0000000..06b3ad3
--- /dev/null
+++ b/SampleClips/columbia-medium-vega7.txt
@@ -0,0 +1,46 @@
+    CPU Tasks
+LoadModel       1.63669 seconds
+RunComplete     97.4095 seconds
+Run     97.3338 seconds
+Callbacks       18.5655 milliseconds, 37 calls, 501.77 microseconds average
+Spectrogram     1.4999 seconds, 42 calls, 35.7119 milliseconds average
+Sample  135.736 milliseconds, 511 calls, 265.628 microseconds average
+Encode  61.2992 seconds, 10 calls, 6.12992 seconds average
+Decode  36.0131 seconds, 10 calls, 3.60131 seconds average
+DecodeStep      35.8768 seconds, 511 calls, 70.2089 milliseconds average
+    GPU Tasks
+LoadModel       875.606 milliseconds
+Run     96.9497 seconds
+Encode  62.3057 seconds, 10 calls, 6.23057 seconds average
+EncodeLayer     53.632 seconds, 240 calls, 223.467 milliseconds average
+Decode  34.644 seconds, 10 calls, 3.4644 seconds average
+DecodeStep      34.6434 seconds, 511 calls, 67.7954 milliseconds average
+DecodeLayer     31.2704 seconds, 12264 calls, 2.54977 milliseconds average
+    Compute Shaders
+mulMatTiledEx   46.2214 seconds, 2400 calls, 19.2589 milliseconds average
+mulMatTiled     17.3476 seconds, 2890 calls, 6.00262 milliseconds average
+mulMatByRowTiled        13.9489 seconds, 120741 calls, 115.527 microseconds average
+mulMatByRowTiledEx      5.45206 seconds, 24048 calls, 226.716 microseconds average
+softMaxFixed    2.49323 seconds, 12504 calls, 199.395 microseconds average
+convolutionMain2Fixed   1.51065 seconds, 10 calls, 151.065 milliseconds average
+matReshapePanels        1.26582 seconds, 1450 calls, 872.982 microseconds average
+addRepeat       1.21062 seconds, 50256 calls, 24.0891 microseconds average
+softMax 986.762 milliseconds, 12775 calls, 77.2417 microseconds average
+addRepeatGelu   937.447 milliseconds, 12524 calls, 74.852 microseconds average
+copyConvert     787.692 milliseconds, 25488 calls, 30.9044 microseconds average
+fmaRepeat1      769.494 milliseconds, 37793 calls, 20.3608 microseconds average
+normFixed       741.028 milliseconds, 37793 calls, 19.6076 microseconds average
+addRepeatScale  600.233 milliseconds, 24528 calls, 24.4714 microseconds average
+addInPlace      548.734 milliseconds, 25008 calls, 21.9423 microseconds average
+scaleInPlace    489.186 milliseconds, 12504 calls, 39.1224 microseconds average
+convolutionMain 469.994 milliseconds, 10 calls, 46.9994 milliseconds average
+copyTranspose   452.957 milliseconds, 25008 calls, 18.1125 microseconds average
+add     296.072 milliseconds, 12274 calls, 24.1219 microseconds average
+diagMaskInf     194.708 milliseconds, 12264 calls, 15.8764 microseconds average
+convolutionPrep2        43.5675 milliseconds, 20 calls, 2.17837 milliseconds average
+convolutionPrep1        40.4517 milliseconds, 20 calls, 2.02258 milliseconds average
+addRows 1.6846 milliseconds, 511 calls, 3.29667 microseconds average
+    Memory Usage
+Model   877.966 KB RAM, 1.42785 GB VRAM
+Context 91.0721 MB RAM, 893.634 MB VRAM
+Total   91.9295 MB RAM, 2.30054 GB VRAM
diff --git a/SampleClips/columbia.wma b/SampleClips/columbia.wma
new file mode 100644
index 0000000..7196199
--- /dev/null
+++ b/SampleClips/columbia.wma
diff --git a/SampleClips/jfk-large-1080ti.txt b/SampleClips/jfk-large-1080ti.txt
new file mode 100644
index 0000000..6b963cb
--- /dev/null
+++ b/SampleClips/jfk-large-1080ti.txt
@@ -0,0 +1,43 @@
+    CPU Tasks
+LoadModel       1.31643 seconds
+RunComplete     2.62992 seconds
+Run     2.55991 seconds
+Callbacks       268.8 microseconds, 4 calls, 67.2 microseconds average
+Spectrogram     41.7164 milliseconds, 3 calls, 13.9055 milliseconds average
+Sample  3.7334 milliseconds, 27 calls, 138.274 microseconds average
+Encode  1.59685 seconds
+Decode  962.766 milliseconds
+DecodeStep      959.004 milliseconds, 27 calls, 35.5187 milliseconds average
+    GPU Tasks
+LoadModel       1.16929 seconds
+Run     2.50813 seconds
+Encode  1.54197 seconds
+EncodeLayer     1.31304 seconds, 32 calls, 41.0324 milliseconds average
+Decode  966.163 milliseconds
+DecodeStep      966.159 milliseconds, 27 calls, 35.7837 milliseconds average
+DecodeLayer     902.348 milliseconds, 864 calls, 1.04438 milliseconds average
+    Compute Shaders
+mulMatTiled     1.48565 seconds, 705 calls, 2.10731 milliseconds average
+mulMatByRowTiled        597.295 milliseconds, 10010 calls, 59.6698 microseconds average
+norm    73.0336 milliseconds, 2684 calls, 27.2107 microseconds average
+addRepeat       53.7049 milliseconds, 3616 calls, 14.852 microseconds average
+softMaxFixed    42.5443 milliseconds, 896 calls, 47.4825 microseconds average
+softMax 42.278 milliseconds, 891 calls, 47.4501 microseconds average
+fmaRepeat1      32.9186 milliseconds, 2684 calls, 12.2648 microseconds average
+copyConvert     30.5182 milliseconds, 1856 calls, 16.443 microseconds average
+copyTranspose   23.707 milliseconds, 1792 calls, 13.2294 microseconds average
+convolutionMain2Fixed   20.2435 milliseconds
+addInPlace      20.0419 milliseconds, 1792 calls, 11.1841 microseconds average
+addRepeatGelu   19.4727 milliseconds, 898 calls, 21.6845 microseconds average
+addRepeatScale  17.2226 milliseconds, 1728 calls, 9.96678 microseconds average
+scaleInPlace    15.5358 milliseconds, 896 calls, 17.3391 microseconds average
+add     11.4178 milliseconds, 865 calls, 13.1998 microseconds average
+convolutionMain 8.7583 milliseconds
+diagMaskInf     5.3196 milliseconds, 864 calls, 6.15694 microseconds average
+convolutionPrep1        2.3276 milliseconds, 2 calls, 1.1638 milliseconds average
+convolutionPrep2        572.4 microseconds, 2 calls, 286.2 microseconds average
+addRows 207.9 microseconds, 27 calls, 7.7 microseconds average
+    Memory Usage
+Model   892.591 KB RAM, 2.8815 GB VRAM
+Context 1.98413 MB RAM, 1.07361 GB VRAM
+Total   2.8558 MB RAM, 3.95511 GB VRAM
diff --git a/SampleClips/jfk-large-vega7.txt b/SampleClips/jfk-large-vega7.txt
new file mode 100644
index 0000000..712c626
--- /dev/null
+++ b/SampleClips/jfk-large-vega7.txt
@@ -0,0 +1,46 @@
+    CPU Tasks
+LoadModel       2.48295 seconds
+RunComplete     19.41 seconds
+Run     19.325 seconds
+Callbacks       938.5 microseconds, 4 calls, 234.625 microseconds average
+Spectrogram     101.776 milliseconds, 3 calls, 33.9253 milliseconds average
+Sample  7.4609 milliseconds, 27 calls, 276.33 microseconds average
+Encode  16.6219 seconds
+Decode  2.7018 seconds
+DecodeStep      2.69429 seconds, 27 calls, 99.7886 milliseconds average
+    GPU Tasks
+LoadModel       1.59925 seconds
+Run     19.1489 seconds
+Encode  16.6535 seconds
+EncodeLayer     14.7506 seconds, 32 calls, 460.957 milliseconds average
+Decode  2.4954 seconds
+DecodeStep      2.49537 seconds, 27 calls, 92.4212 milliseconds average
+DecodeLayer     2.33892 seconds, 864 calls, 2.70708 milliseconds average
+    Compute Shaders
+mulMatTiledEx   10.8399 seconds, 320 calls, 33.8745 milliseconds average
+mulMatTiled     2.40696 seconds, 385 calls, 6.25184 milliseconds average
+norm    1.1565 seconds, 2684 calls, 430.885 microseconds average
+addRepeatGelu   1.1138 seconds, 898 calls, 1.24031 milliseconds average
+mulMatByRowTiled        1.08614 seconds, 8346 calls, 130.14 microseconds average
+mulMatByRowTiledEx      692.772 milliseconds, 1664 calls, 416.329 microseconds average
+softMaxFixed    416.688 milliseconds, 896 calls, 465.053 microseconds average
+convolutionMain2Fixed   415.361 milliseconds
+matReshapePanels        179.52 milliseconds, 193 calls, 930.155 microseconds average
+addRepeat       171.572 milliseconds, 3616 calls, 47.4479 microseconds average
+convolutionMain 126.679 milliseconds
+copyConvert     95.046 milliseconds, 1856 calls, 51.2101 microseconds average
+fmaRepeat1      74.6558 milliseconds, 2684 calls, 27.8151 microseconds average
+copyTranspose   73.589 milliseconds, 1792 calls, 41.0653 microseconds average
+addInPlace      67.0819 milliseconds, 1792 calls, 37.4341 microseconds average
+scaleInPlace    66.1625 milliseconds, 896 calls, 73.8421 microseconds average
+softMax 65.629 milliseconds, 891 calls, 73.6577 microseconds average
+addRepeatScale  29.3899 milliseconds, 1728 calls, 17.008 microseconds average
+add     25.2651 milliseconds, 865 calls, 29.2082 microseconds average
+convolutionPrep1        13.325 milliseconds, 2 calls, 6.6625 milliseconds average
+diagMaskInf     11.2047 milliseconds, 864 calls, 12.9684 microseconds average
+convolutionPrep2        5.9717 milliseconds, 2 calls, 2.98585 milliseconds average
+addRows 93.7 microseconds, 27 calls, 3.47037 microseconds average
+    Memory Usage
+Model   892.591 KB RAM, 2.8815 GB VRAM
+Context 1.98427 MB RAM, 1.13175 GB VRAM
+Total   2.85594 MB RAM, 4.01325 GB VRAM
diff --git a/SampleClips/jfk-medium-1080ti.txt b/SampleClips/jfk-medium-1080ti.txt
new file mode 100644
index 0000000..f76376d
--- /dev/null
+++ b/SampleClips/jfk-medium-1080ti.txt
@@ -0,0 +1,43 @@
+    CPU Tasks
+LoadModel       751.527 milliseconds
+RunComplete     1.46731 seconds
+Run     1.39689 seconds
+Callbacks       319.7 microseconds, 4 calls, 79.925 microseconds average
+Spectrogram     40.711 milliseconds, 3 calls, 13.5703 milliseconds average
+Sample  3.6208 milliseconds, 28 calls, 129.314 microseconds average
+Encode  803.503 milliseconds
+Decode  593.049 milliseconds
+DecodeStep      589.41 milliseconds, 28 calls, 21.0504 milliseconds average
+    GPU Tasks
+LoadModel       597.603 milliseconds
+Run     1.34198 seconds
+Encode  754.654 milliseconds
+EncodeLayer     645.794 milliseconds, 24 calls, 26.9081 milliseconds average
+Decode  587.324 milliseconds
+DecodeStep      587.321 milliseconds, 28 calls, 20.9758 milliseconds average
+DecodeLayer     543.185 milliseconds, 672 calls, 808.311 microseconds average
+    Compute Shaders
+mulMatTiled     723.882 milliseconds, 529 calls, 1.3684 milliseconds average
+mulMatByRowTiled        346.71 milliseconds, 7803 calls, 44.4329 microseconds average
+softMax 39.6096 milliseconds, 700 calls, 56.5851 microseconds average
+addRepeat       31.2462 milliseconds, 2808 calls, 11.1276 microseconds average
+softMaxFixed    27.2224 milliseconds, 696 calls, 39.1126 microseconds average
+normFixed       24.8054 milliseconds, 2093 calls, 11.8516 microseconds average
+fmaRepeat1      24.7513 milliseconds, 2093 calls, 11.8258 microseconds average
+copyConvert     19.778 milliseconds, 1440 calls, 13.7347 microseconds average
+copyTranspose   18.6921 milliseconds, 1392 calls, 13.4282 microseconds average
+addRepeatScale  13.4873 milliseconds, 1344 calls, 10.0352 microseconds average
+addInPlace      13.0325 milliseconds, 1392 calls, 9.36243 microseconds average
+convolutionMain2Fixed   12.33 milliseconds
+addRepeatGelu   12.1985 milliseconds, 698 calls, 17.4764 microseconds average
+scaleInPlace    10.3726 milliseconds, 696 calls, 14.9032 microseconds average
+add     8.0935 milliseconds, 673 calls, 12.026 microseconds average
+convolutionMain 6.6079 milliseconds
+diagMaskInf     3.9483 milliseconds, 672 calls, 5.87545 microseconds average
+convolutionPrep1        1.5073 milliseconds, 2 calls, 753.65 microseconds average
+convolutionPrep2        540.7 microseconds, 2 calls, 270.35 microseconds average
+addRows 204.8 microseconds, 28 calls, 7.31429 microseconds average
+    Memory Usage
+Model   877.966 KB RAM, 1.42785 GB VRAM
+Context 1.98347 MB RAM, 723.729 MB VRAM
+Total   2.84085 MB RAM, 2.13462 GB VRAM
diff --git a/SampleClips/jfk-medium-vega7.txt b/SampleClips/jfk-medium-vega7.txt
new file mode 100644
index 0000000..0be45d3
--- /dev/null
+++ b/SampleClips/jfk-medium-vega7.txt
@@ -0,0 +1,46 @@
+    CPU Tasks
+LoadModel       1.44983 seconds
+RunComplete     9.9723 seconds
+Run     9.8953 seconds
+Callbacks       876.5 microseconds, 4 calls, 219.125 microseconds average
+Spectrogram     100.602 milliseconds, 3 calls, 33.5339 milliseconds average
+Sample  8.2281 milliseconds, 28 calls, 293.861 microseconds average
+Encode  8.28685 seconds
+Decode  1.60728 seconds
+DecodeStep      1.599 seconds, 28 calls, 57.1073 milliseconds average
+    GPU Tasks
+LoadModel       751.497 milliseconds
+Run     9.73531 seconds
+Encode  8.28303 seconds
+EncodeLayer     7.19651 seconds, 24 calls, 299.855 milliseconds average
+Decode  1.45228 seconds
+DecodeStep      1.45225 seconds, 28 calls, 51.866 milliseconds average
+DecodeLayer     1.31372 seconds, 672 calls, 1.95494 milliseconds average
+    Compute Shaders
+mulMatTiledEx   5.73474 seconds, 240 calls, 23.8947 milliseconds average
+mulMatTiled     1.59442 seconds, 289 calls, 5.51703 milliseconds average
+mulMatByRowTiled        708.039 milliseconds, 6507 calls, 108.812 microseconds average
+mulMatByRowTiledEx      292.797 milliseconds, 1296 calls, 225.923 microseconds average
+convolutionMain2Fixed   267.762 milliseconds
+softMaxFixed    252.702 milliseconds, 696 calls, 363.078 microseconds average
+addRepeat       122.774 milliseconds, 2808 calls, 43.7229 microseconds average
+matReshapePanels        116.085 milliseconds, 145 calls, 800.583 microseconds average
+convolutionMain 100.111 milliseconds
+addRepeatGelu   78.6895 milliseconds, 698 calls, 112.736 microseconds average
+normFixed       64.6521 milliseconds, 2093 calls, 30.8897 microseconds average
+scaleInPlace    64.0629 milliseconds, 696 calls, 92.0444 microseconds average
+copyConvert     62.7305 milliseconds, 1440 calls, 43.5628 microseconds average
+softMax 50.9006 milliseconds, 700 calls, 72.7151 microseconds average
+fmaRepeat1      49.6347 milliseconds, 2093 calls, 23.7146 microseconds average
+copyTranspose   44.2248 milliseconds, 1392 calls, 31.7707 microseconds average
+addInPlace      44.1766 milliseconds, 1392 calls, 31.7361 microseconds average
+addRepeatScale  31.3737 milliseconds, 1344 calls, 23.3435 microseconds average
+add     19.0564 milliseconds, 673 calls, 28.3156 microseconds average
+convolutionPrep1        8.494 milliseconds, 2 calls, 4.247 milliseconds average
+diagMaskInf     6.9839 milliseconds, 672 calls, 10.3927 microseconds average
+convolutionPrep2        6.0876 milliseconds, 2 calls, 3.0438 milliseconds average
+addRows 72 microseconds, 28 calls, 2.57143 microseconds average
+    Memory Usage
+Model   877.966 KB RAM, 1.42785 GB VRAM
+Context 1.9836 MB RAM, 771.354 MB VRAM
+Total   2.84099 MB RAM, 2.18113 GB VRAM
diff --git a/SampleClips/jfk.wav b/SampleClips/jfk.wav
new file mode 100644
index 0000000..3184d37
--- /dev/null
+++ b/SampleClips/jfk.wav