enne2/qwentts.cpp
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

tests logs

Browse Source
This commit is contained in:
Pascal
2026-05-11 16:27:12 +02:00
parent 32560ea597
commit eefb13043e
48 changed files with 3185 additions and 1119 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/tts-Vulkan0-Q8_0.log
+53 -53
View File
@@ -41,47 +41,47 @@ load_backend: loaded CPU backend from /mnt/workspace/qwentts.cpp/build/libggml-c
[Debug] trailing-text-hidden: [1, 2048] first4: -0.004554 0.007647 -0.004656 -0.000707
[Debug] tts-pad-embed: [2048] first4: -0.004554 0.007647 -0.004656 -0.000707
[Debug] talker-hidden-prefill-l0: [52, 2048] first4: -0.379852 -0.054862 -0.041081 -0.052085
[Debug] talker-hidden-prefill-l7: [52, 2048] first4: -1.402517 0.407066 1.510208 0.573808
[Debug] talker-hidden-prefill-l14: [52, 2048] first4: -1.175941 0.612193 1.632609 0.488113
[Debug] talker-hidden-prefill-l21: [52, 2048] first4: -0.785830 0.492748 1.932347 0.109454
[Debug] talker-hidden-prefill-l27: [52, 2048] first4: -7.070812 -29.670967 -2.154939 31.796692
[Debug] talker-hidden-prefill-final: [52, 2048] first4: -0.319355 -1.399132 -0.090039 1.309577
[Debug] talker-logits-prefill: [3072] first4: -2.992188 -10.062500 -1.494141 -3.066406
[Debug] talker-hidden-prefill-l7: [52, 2048] first4: -1.402396 0.408609 1.507983 0.574799
[Debug] talker-hidden-prefill-l14: [52, 2048] first4: -1.175818 0.613162 1.630474 0.489529
[Debug] talker-hidden-prefill-l21: [52, 2048] first4: -0.786077 0.493968 1.929888 0.109035
[Debug] talker-hidden-prefill-l27: [52, 2048] first4: -7.063078 -29.640556 -2.152674 31.781174
[Debug] talker-hidden-prefill-final: [52, 2048] first4: -0.318960 -1.397496 -0.089932 1.308749
[Debug] talker-logits-prefill: [3072] first4: -2.982422 -10.085938 -1.507812 -3.093750
[Sample] step=0 c0=1995 u=-1.0000000000 subseq=0
[Sample-CP] g=0 c=1642 u=-1.0000000000 subseq=1
[Sample-CP] g=1 c=1602 u=-1.0000000000 subseq=2
[Sample-CP] g=2 c=1088 u=-1.0000000000 subseq=3
[Sample-CP] g=3 c=1000 u=-1.0000000000 subseq=4
[Sample-CP] g=4 c=1521 u=-1.0000000000 subseq=5
[Sample-CP] g=5 c=1767 u=-1.0000000000 subseq=6
[Sample-CP] g=6 c=1023 u=-1.0000000000 subseq=7
[Sample-CP] g=7 c=635 u=-1.0000000000 subseq=8
[Sample-CP] g=8 c=398 u=-1.0000000000 subseq=9
[Sample-CP] g=9 c=1820 u=-1.0000000000 subseq=10
[Sample-CP] g=10 c=612 u=-1.0000000000 subseq=11
[Sample-CP] g=11 c=157 u=-1.0000000000 subseq=12
[Sample-CP] g=12 c=1794 u=-1.0000000000 subseq=13
[Sample-CP] g=13 c=1399 u=-1.0000000000 subseq=14
[Sample-CP] g=14 c=1772 u=-1.0000000000 subseq=15
[Debug] codes-step0: [16] first4: 1995.000000 1642.000000 1602.000000 1088.000000
[Debug] next-emb-step0: [2048] first4: 0.056649 -0.053523 0.010754 -0.035536
[Debug] talker-hidden-step1: [2048] first4: -1.753798 -3.439198 -0.773368 -0.761658
[Sample] step=1 c0=505 u=-1.0000000000 subseq=16
[Sample-CP] g=0 c=1752 u=-1.0000000000 subseq=17
[Sample-CP] g=1 c=878 u=-1.0000000000 subseq=18
[Sample-CP] g=2 c=1112 u=-1.0000000000 subseq=19
[Sample-CP] g=3 c=791 u=-1.0000000000 subseq=20
[Sample-CP] g=4 c=1572 u=-1.0000000000 subseq=21
[Sample-CP] g=5 c=267 u=-1.0000000000 subseq=22
[Sample-CP] g=6 c=1731 u=-1.0000000000 subseq=23
[Sample-CP] g=7 c=279 u=-1.0000000000 subseq=24
[Sample-CP] g=8 c=1039 u=-1.0000000000 subseq=25
[Sample-CP] g=9 c=346 u=-1.0000000000 subseq=26
[Sample-CP] g=10 c=395 u=-1.0000000000 subseq=27
[Sample-CP] g=11 c=1033 u=-1.0000000000 subseq=28
[Sample-CP] g=12 c=1918 u=-1.0000000000 subseq=29
[Sample-CP] g=13 c=1805 u=-1.0000000000 subseq=30
[Sample-CP] g=14 c=193 u=-1.0000000000 subseq=31
[Sample-CP] g=1 c=1398 u=-1.0000000000 subseq=2
[Sample-CP] g=2 c=1703 u=-1.0000000000 subseq=3
[Sample-CP] g=3 c=1047 u=-1.0000000000 subseq=4
[Sample-CP] g=4 c=37 u=-1.0000000000 subseq=5
[Sample-CP] g=5 c=1759 u=-1.0000000000 subseq=6
[Sample-CP] g=6 c=1163 u=-1.0000000000 subseq=7
[Sample-CP] g=7 c=564 u=-1.0000000000 subseq=8
[Sample-CP] g=8 c=1 u=-1.0000000000 subseq=9
[Sample-CP] g=9 c=743 u=-1.0000000000 subseq=10
[Sample-CP] g=10 c=796 u=-1.0000000000 subseq=11
[Sample-CP] g=11 c=783 u=-1.0000000000 subseq=12
[Sample-CP] g=12 c=1999 u=-1.0000000000 subseq=13
[Sample-CP] g=13 c=82 u=-1.0000000000 subseq=14
[Sample-CP] g=14 c=803 u=-1.0000000000 subseq=15
[Debug] codes-step0: [16] first4: 1995.000000 1642.000000 1398.000000 1703.000000
[Debug] next-emb-step0: [2048] first4: 0.004793 -0.029425 0.017809 0.080303
[Debug] talker-hidden-step1: [2048] first4: 0.538580 -0.664507 7.114338 -3.862589
[Sample] step=1 c0=2042 u=-1.0000000000 subseq=16
[Sample-CP] g=0 c=1230 u=-1.0000000000 subseq=17
[Sample-CP] g=1 c=141 u=-1.0000000000 subseq=18
[Sample-CP] g=2 c=1879 u=-1.0000000000 subseq=19
[Sample-CP] g=3 c=371 u=-1.0000000000 subseq=20
[Sample-CP] g=4 c=628 u=-1.0000000000 subseq=21
[Sample-CP] g=5 c=1799 u=-1.0000000000 subseq=22
[Sample-CP] g=6 c=187 u=-1.0000000000 subseq=23
[Sample-CP] g=7 c=645 u=-1.0000000000 subseq=24
[Sample-CP] g=8 c=834 u=-1.0000000000 subseq=25
[Sample-CP] g=9 c=908 u=-1.0000000000 subseq=26
[Sample-CP] g=10 c=132 u=-1.0000000000 subseq=27
[Sample-CP] g=11 c=942 u=-1.0000000000 subseq=28
[Sample-CP] g=12 c=1522 u=-1.0000000000 subseq=29
[Sample-CP] g=13 c=317 u=-1.0000000000 subseq=30
[Sample-CP] g=14 c=623 u=-1.0000000000 subseq=31
[Pipeline] Generated 8 frames
[Pipeline] Generated 16 frames
[Pipeline] Generated 24 frames
@@ -91,8 +91,8 @@ load_backend: loaded CPU backend from /mnt/workspace/qwentts.cpp/build/libggml-c
[Pipeline] Generated 56 frames
[Pipeline] Generated 64 frames
[Pipeline] Generation done : 64 frames
[Debug] codes-full: [64, 16] first4: 1995.000000 1642.000000 1602.000000 1088.000000
[Debug] output-audio: [122880] first4: 0.000018 0.000022 0.000014 0.000015
[Debug] codes-full: [64, 16] first4: 1995.000000 1642.000000 1398.000000 1703.000000
[Debug] output-audio: [122880] first4: 0.000047 0.000055 0.000042 0.000045
[WAV] Wrote cpp/tts/tts-cpp.wav: 122880 samples, 24000 Hz, mono S16
[Pipeline] Wrote 122880 samples (5.12 s) -> cpp/tts/tts-cpp.wav
[Input] Prompt: 100 chars: qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS fo...
@@ -111,15 +111,15 @@ load_backend: loaded CPU backend from /mnt/workspace/qwentts.cpp/build/libggml-c
[Cossim] Embed cos: 0.999989 max: 2.2227e-03 mean: 1.6673e-04
[Cossim] TrailingText cos: 0.999999 max: 1.8711e-04 mean: 4.2146e-05
[Cossim] TTSPadEmbed cos: 0.999999 max: 1.8711e-04 mean: 4.2146e-05
[Cossim] L0 cos: 0.999992 max: 4.5462e-02 mean: 6.5980e-04
[Cossim] L7 cos: 0.999986 max: 2.6321e+01 mean: 3.2151e-02
[Cossim] L14 cos: 0.999986 max: 2.6197e+01 mean: 4.0514e-02
[Cossim] L21 cos: 0.999983 max: 2.6375e+01 mean: 7.7104e-02
[Cossim] L27 cos: 0.999945 max: 6.2261e+01 mean: 3.3700e-01
[Cossim] Final cos: 0.999666 max: 1.4233e+00 mean: 3.7771e-02
[Cossim] Logits cos: 0.999756 max: 3.9106e-01 mean: 6.4052e-02
[Cossim] NextEmbStep0 cos: 0.565000 max: 2.6307e-01 mean: 4.8794e-02
[Cossim] TalkerHiddenStep1 cos: 0.277044 max: 2.2239e+01 mean: 2.5255e+00
[Cossim] CodesFull exact: 0.20% (1008 values)
[Cossim] Audio cos: 0.006878
[Cossim] WAV stft_cos: 0.064563 samples: 120960
[Cossim] L0 cos: 0.999992 max: 4.9368e-02 mean: 6.5849e-04
[Cossim] L7 cos: 0.999986 max: 1.8340e+01 mean: 3.2028e-02
[Cossim] L14 cos: 0.999986 max: 1.8247e+01 mean: 4.0458e-02
[Cossim] L21 cos: 0.999983 max: 1.8454e+01 mean: 7.6089e-02
[Cossim] L27 cos: 0.999947 max: 6.4114e+01 mean: 3.3413e-01
[Cossim] Final cos: 0.999670 max: 1.4440e+00 mean: 3.7552e-02
[Cossim] Logits cos: 0.999767 max: 4.0209e-01 mean: 6.3427e-02
[Cossim] NextEmbStep0 cos: 0.999990 max: 1.0252e-03 mean: 2.4056e-04
[Cossim] TalkerHiddenStep1 cos: 0.999732 max: 2.9859e-01 mean: 5.0384e-02
[Cossim] CodesFull exact: 8.23% (1008 values)
[Cossim] Audio cos: 0.217182
[Cossim] WAV stft_cos: 0.489313 samples: 120960