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/base-Vulkan0-Q8_0.log
+53 -53
View File
@@ -43,47 +43,47 @@ load_backend: loaded CPU backend from /mnt/workspace/qwentts.cpp/build/libggml-c
[Debug] trailing-text-hidden: [1, 2048] first4: -0.005270 0.008716 -0.004355 0.001036
[Debug] tts-pad-embed: [2048] first4: -0.005270 0.008716 -0.004355 0.001036
[Debug] talker-hidden-prefill-l0: [40, 2048] first4: -0.461420 -0.072044 0.014792 -0.037443
[Debug] talker-hidden-prefill-l7: [40, 2048] first4: -2.199468 0.166968 0.200645 1.604671
[Debug] talker-hidden-prefill-l14: [40, 2048] first4: -1.975133 0.353360 0.306994 1.579719
[Debug] talker-hidden-prefill-l21: [40, 2048] first4: -1.461743 0.289562 0.665961 0.999581
[Debug] talker-hidden-prefill-l27: [40, 2048] first4: 6.705354 -34.567703 -7.414961 28.435642
[Debug] talker-hidden-prefill-final: [40, 2048] first4: 0.228340 -1.229235 -0.234628 0.882638
[Debug] talker-logits-prefill: [3072] first4: -4.078125 -6.410156 -1.056641 -3.250000
[Debug] talker-hidden-prefill-l7: [40, 2048] first4: -2.199481 0.165310 0.198761 1.609799
[Debug] talker-hidden-prefill-l14: [40, 2048] first4: -1.975275 0.352142 0.305376 1.584287
[Debug] talker-hidden-prefill-l21: [40, 2048] first4: -1.463363 0.287608 0.663962 1.005549
[Debug] talker-hidden-prefill-l27: [40, 2048] first4: 6.687571 -34.492264 -7.387871 28.361349
[Debug] talker-hidden-prefill-final: [40, 2048] first4: 0.227624 -1.225957 -0.233658 0.879905
[Debug] talker-logits-prefill: [3072] first4: -4.097656 -6.390625 -1.061523 -3.240234
[Sample] step=0 c0=1995 u=-1.0000000000 subseq=0
[Sample-CP] g=0 c=1159 u=-1.0000000000 subseq=1
[Sample-CP] g=1 c=887 u=-1.0000000000 subseq=2
[Sample-CP] g=2 c=1853 u=-1.0000000000 subseq=3
[Sample-CP] g=3 c=369 u=-1.0000000000 subseq=4
[Sample-CP] g=4 c=645 u=-1.0000000000 subseq=5
[Sample-CP] g=5 c=889 u=-1.0000000000 subseq=6
[Sample-CP] g=6 c=1274 u=-1.0000000000 subseq=7
[Sample-CP] g=7 c=338 u=-1.0000000000 subseq=8
[Sample-CP] g=8 c=373 u=-1.0000000000 subseq=9
[Sample-CP] g=9 c=1795 u=-1.0000000000 subseq=10
[Sample-CP] g=10 c=651 u=-1.0000000000 subseq=11
[Sample-CP] g=11 c=1572 u=-1.0000000000 subseq=12
[Sample-CP] g=12 c=1160 u=-1.0000000000 subseq=13
[Sample-CP] g=13 c=1079 u=-1.0000000000 subseq=14
[Sample-CP] g=14 c=780 u=-1.0000000000 subseq=15
[Debug] codes-step0: [16] first4: 1995.000000 1159.000000 887.000000 1853.000000
[Debug] next-emb-step0: [2048] first4: -0.011231 -0.048261 -0.014040 0.004942
[Debug] talker-hidden-step1: [2048] first4: -1.172883 -4.615955 1.940985 -1.469731
[Sample] step=1 c0=1028 u=-1.0000000000 subseq=16
[Sample-CP] g=0 c=1763 u=-1.0000000000 subseq=17
[Sample-CP] g=1 c=1203 u=-1.0000000000 subseq=18
[Sample-CP] g=2 c=1114 u=-1.0000000000 subseq=19
[Sample-CP] g=3 c=1041 u=-1.0000000000 subseq=20
[Sample-CP] g=4 c=1461 u=-1.0000000000 subseq=21
[Sample-CP] g=5 c=267 u=-1.0000000000 subseq=22
[Sample-CP] g=6 c=1595 u=-1.0000000000 subseq=23
[Sample-CP] g=7 c=1445 u=-1.0000000000 subseq=24
[Sample-CP] g=8 c=87 u=-1.0000000000 subseq=25
[Sample-CP] g=9 c=1146 u=-1.0000000000 subseq=26
[Sample-CP] g=10 c=478 u=-1.0000000000 subseq=27
[Sample-CP] g=11 c=474 u=-1.0000000000 subseq=28
[Sample-CP] g=12 c=1654 u=-1.0000000000 subseq=29
[Sample-CP] g=13 c=14 u=-1.0000000000 subseq=30
[Sample-CP] g=14 c=777 u=-1.0000000000 subseq=31
[Sample-CP] g=1 c=355 u=-1.0000000000 subseq=2
[Sample-CP] g=2 c=22 u=-1.0000000000 subseq=3
[Sample-CP] g=3 c=1174 u=-1.0000000000 subseq=4
[Sample-CP] g=4 c=1093 u=-1.0000000000 subseq=5
[Sample-CP] g=5 c=625 u=-1.0000000000 subseq=6
[Sample-CP] g=6 c=1814 u=-1.0000000000 subseq=7
[Sample-CP] g=7 c=1058 u=-1.0000000000 subseq=8
[Sample-CP] g=8 c=905 u=-1.0000000000 subseq=9
[Sample-CP] g=9 c=1846 u=-1.0000000000 subseq=10
[Sample-CP] g=10 c=1247 u=-1.0000000000 subseq=11
[Sample-CP] g=11 c=1677 u=-1.0000000000 subseq=12
[Sample-CP] g=12 c=889 u=-1.0000000000 subseq=13
[Sample-CP] g=13 c=812 u=-1.0000000000 subseq=14
[Sample-CP] g=14 c=901 u=-1.0000000000 subseq=15
[Debug] codes-step0: [16] first4: 1995.000000 1159.000000 355.000000 22.000000
[Debug] next-emb-step0: [2048] first4: -0.042839 -0.033702 -0.000574 0.188203
[Debug] talker-hidden-step1: [2048] first4: 1.651582 -2.566358 6.810423 0.678816
[Sample] step=1 c0=215 u=-1.0000000000 subseq=16
[Sample-CP] g=0 c=1722 u=-1.0000000000 subseq=17
[Sample-CP] g=1 c=355 u=-1.0000000000 subseq=18
[Sample-CP] g=2 c=310 u=-1.0000000000 subseq=19
[Sample-CP] g=3 c=1174 u=-1.0000000000 subseq=20
[Sample-CP] g=4 c=1093 u=-1.0000000000 subseq=21
[Sample-CP] g=5 c=625 u=-1.0000000000 subseq=22
[Sample-CP] g=6 c=1814 u=-1.0000000000 subseq=23
[Sample-CP] g=7 c=930 u=-1.0000000000 subseq=24
[Sample-CP] g=8 c=1144 u=-1.0000000000 subseq=25
[Sample-CP] g=9 c=679 u=-1.0000000000 subseq=26
[Sample-CP] g=10 c=1247 u=-1.0000000000 subseq=27
[Sample-CP] g=11 c=896 u=-1.0000000000 subseq=28
[Sample-CP] g=12 c=889 u=-1.0000000000 subseq=29
[Sample-CP] g=13 c=812 u=-1.0000000000 subseq=30
[Sample-CP] g=14 c=803 u=-1.0000000000 subseq=31
[Pipeline] Generated 8 frames
[Pipeline] Generated 16 frames
[Pipeline] Generated 24 frames
@@ -93,8 +93,8 @@ 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 1159.000000 887.000000 1853.000000
[Debug] output-audio: [122880] first4: -0.000002 -0.000010 -0.000003 -0.000009
[Debug] codes-full: [64, 16] first4: 1995.000000 1159.000000 355.000000 22.000000
[Debug] output-audio: [122880] first4: 0.000015 0.000017 0.000015 0.000017
[WAV] Wrote cpp/base/base-cpp.wav: 122880 samples, 24000 Hz, mono S16
[Pipeline] Wrote 122880 samples (5.12 s) -> cpp/base/base-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: 0.999987 max: 2.2577e-03 mean: 1.8282e-04
[Cossim] TrailingText cos: 0.999999 max: 2.1233e-04 mean: 4.3863e-05
[Cossim] TTSPadEmbed cos: 0.999999 max: 2.1233e-04 mean: 4.3863e-05
[Cossim] L0 cos: 0.999991 max: 9.1096e-02 mean: 6.4066e-04
[Cossim] L7 cos: 0.999986 max: 2.1562e+01 mean: 4.2083e-02
[Cossim] L14 cos: 0.999986 max: 2.1610e+01 mean: 4.8769e-02
[Cossim] L21 cos: 0.999985 max: 2.1766e+01 mean: 7.8347e-02
[Cossim] L27 cos: 0.999957 max: 5.4678e+01 mean: 3.4737e-01
[Cossim] Final cos: 0.999642 max: 4.1274e+00 mean: 2.2081e-02
[Cossim] Logits cos: 0.999946 max: 2.0047e-01 mean: 3.0143e-02
[Cossim] NextEmbStep0 cos: 0.426517 max: 5.3731e-01 mean: 5.7581e-02
[Cossim] TalkerHiddenStep1 cos: 0.292946 max: 2.1366e+01 mean: 2.2204e+00
[Cossim] CodesFull exact: 0.20% (1008 values)
[Cossim] Audio cos: 0.077502
[Cossim] WAV stft_cos: 0.115858 samples: 120960
[Cossim] L0 cos: 0.999992 max: 9.1096e-02 mean: 6.4077e-04
[Cossim] L7 cos: 0.999986 max: 2.1572e+01 mean: 4.2006e-02
[Cossim] L14 cos: 0.999986 max: 2.1626e+01 mean: 4.8583e-02
[Cossim] L21 cos: 0.999985 max: 2.1762e+01 mean: 7.8263e-02
[Cossim] L27 cos: 0.999955 max: 5.8713e+01 mean: 3.4944e-01
[Cossim] Final cos: 0.999624 max: 4.1470e+00 mean: 2.2311e-02
[Cossim] Logits cos: 0.999949 max: 1.8228e-01 mean: 2.9513e-02
[Cossim] NextEmbStep0 cos: 0.999992 max: 1.1117e-03 mean: 2.2935e-04
[Cossim] TalkerHiddenStep1 cos: 0.999821 max: 1.7147e-01 mean: 3.5799e-02
[Cossim] CodesFull exact: 99.90% (1008 values)
[Cossim] Audio cos: 0.981612
[Cossim] WAV stft_cos: 0.989094 samples: 120960