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

test logs

Browse Source
This commit is contained in:
Pascal
2026-05-31 02:39:03 +02:00
parent a62fde62e6
commit 29a7fa0f97
48 changed files with 1475 additions and 1463 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/tts-Vulkan0-Q4_K_M.log
+50 -49
View File
@@ -1,3 +1,4 @@
[Qwen] qwentts.cpp a62fde6 (2026-05-30)
ggml_cuda_init: found 1 CUDA devices (Total VRAM: 97247 MiB):
Device 0: NVIDIA RTX PRO 6000 Blackwell Workstation Edition, compute capability 12.0, VMM: yes, VRAM: 97247 MiB
load_backend: loaded CUDA backend from /mnt/workspace/qwentts.cpp/build/libggml-cuda.so
@@ -32,56 +33,56 @@ load_backend: loaded CPU backend from /mnt/workspace/qwentts.cpp/build/libggml-c
[Pipeline] Ready: hop 1920 samples @ 24000 Hz mono, 16 codebooks @ 12.5 Hz
[KVCache] Allocated: 28 layers, 8 KV heads, head_dim 128, max_seq_len 4096 -> 896 MB
[KVCache] Allocated: 5 layers, 8 KV heads, head_dim 128, max_seq_len 16 -> 0 MB
[Pipeline] Loaded: arch=1b7 variant=voice_design tokenizer=qwen3_tts_tokenizer_12hz codebooks=16 speaker_encoder=absent speakers=0
[Pipeline] Loaded: arch=1b7 variant=voice_design tokenizer=qwen3_tts_tokenizer_12hz codebooks=16 speaker_encoder=absent speakers=0 fa=on clamp_fp16=off
[BPE] Loaded from GGUF: 151676 vocab, 151291 merges, eos_id=151643
[BPE] Registered 5 arch special tokens (total specials=6)
[Prompt] Built: 38 ids, N_text=30, N_instruct=12, T_ctx=52, hidden=2048, lang=english (id=2050), speaker=none (id=-1) ref_spk_emb=no icl=no
[Debug] prompt-ids: [38] first4: 151644.000000 77091.000000 198.000000 80.000000
[Debug] talker-input-embed: [52, 2048] first4: 0.017779 -0.008618 0.002377 -0.014714
[Debug] talker-input-embed: [52, 2048] first4: 0.017777 -0.008612 0.002384 -0.014713
[Debug] trailing-text-hidden: [1, 2048] first4: -0.004540 0.007622 -0.004462 -0.000982
[Debug] tts-pad-embed: [2048] first4: -0.004540 0.007622 -0.004462 -0.000982
[Debug] talker-hidden-prefill-l0: [52, 2048] first4: -0.365522 -0.027829 -0.021236 -0.090642
[Debug] talker-hidden-prefill-l7: [52, 2048] first4: -11.040422 0.707821 5.835257 -2.337338
[Debug] talker-hidden-prefill-l14: [52, 2048] first4: -10.607057 0.632322 5.976467 -2.445058
[Debug] talker-hidden-prefill-l21: [52, 2048] first4: -9.635786 -0.167362 6.659793 -1.737383
[Debug] talker-hidden-prefill-l27: [52, 2048] first4: -13.698904 -29.517475 7.479723 30.061430
[Debug] talker-hidden-prefill-final: [52, 2048] first4: -0.651991 -1.466754 0.329333 1.304697
[Debug] talker-logits-prefill: [3072] first4: -6.046875 -8.476562 0.581055 -0.080627
[Debug] talker-hidden-prefill-l0: [52, 2048] first4: -0.365096 -0.027762 -0.021214 -0.090946
[Debug] talker-hidden-prefill-l7: [52, 2048] first4: -11.056854 0.711653 5.837515 -2.340098
[Debug] talker-hidden-prefill-l14: [52, 2048] first4: -10.623413 0.635837 5.978893 -2.448013
[Debug] talker-hidden-prefill-l21: [52, 2048] first4: -9.651576 -0.162840 6.661537 -1.739873
[Debug] talker-hidden-prefill-l27: [52, 2048] first4: -13.708377 -29.526840 7.488002 30.091181
[Debug] talker-hidden-prefill-final: [52, 2048] first4: -0.651999 -1.466224 0.329473 1.305102
[Debug] talker-logits-prefill: [3072] first4: -5.988281 -8.539062 0.579590 -0.133789
[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=1398 u=-1.0000000000 subseq=2
[Sample-CP] g=2 c=2030 u=-1.0000000000 subseq=3
[Sample-CP] g=3 c=6 u=-1.0000000000 subseq=4
[Sample-CP] g=4 c=2026 u=-1.0000000000 subseq=5
[Sample-CP] g=5 c=359 u=-1.0000000000 subseq=6
[Sample-CP] g=6 c=1643 u=-1.0000000000 subseq=7
[Sample-CP] g=7 c=1822 u=-1.0000000000 subseq=8
[Sample-CP] g=8 c=1360 u=-1.0000000000 subseq=9
[Sample-CP] g=9 c=743 u=-1.0000000000 subseq=10
[Sample-CP] g=10 c=437 u=-1.0000000000 subseq=11
[Sample-CP] g=11 c=1677 u=-1.0000000000 subseq=12
[Sample-CP] g=12 c=1484 u=-1.0000000000 subseq=13
[Sample-CP] g=13 c=1008 u=-1.0000000000 subseq=14
[Sample-CP] g=14 c=1409 u=-1.0000000000 subseq=15
[Sample-CP] g=5 c=1751 u=-1.0000000000 subseq=6
[Sample-CP] g=6 c=99 u=-1.0000000000 subseq=7
[Sample-CP] g=7 c=971 u=-1.0000000000 subseq=8
[Sample-CP] g=8 c=1221 u=-1.0000000000 subseq=9
[Sample-CP] g=9 c=288 u=-1.0000000000 subseq=10
[Sample-CP] g=10 c=248 u=-1.0000000000 subseq=11
[Sample-CP] g=11 c=706 u=-1.0000000000 subseq=12
[Sample-CP] g=12 c=1759 u=-1.0000000000 subseq=13
[Sample-CP] g=13 c=812 u=-1.0000000000 subseq=14
[Sample-CP] g=14 c=1435 u=-1.0000000000 subseq=15
[Debug] codes-step0: [16] first4: 1995.000000 1642.000000 1398.000000 2030.000000
[Debug] next-emb-step0: [2048] first4: 0.040523 -0.070059 0.015252 0.066806
[Debug] talker-hidden-step1: [2048] first4: 1.290672 -2.405036 4.064333 -2.934217
[Debug] next-emb-step0: [2048] first4: 0.052074 -0.063247 0.048163 0.061720
[Debug] talker-hidden-step1: [2048] first4: 1.124936 -1.231052 4.484270 -3.341861
[Sample] step=1 c0=215 u=-1.0000000000 subseq=16
[Sample-CP] g=0 c=85 u=-1.0000000000 subseq=17
[Sample-CP] g=0 c=1782 u=-1.0000000000 subseq=17
[Sample-CP] g=1 c=1398 u=-1.0000000000 subseq=18
[Sample-CP] g=2 c=282 u=-1.0000000000 subseq=19
[Sample-CP] g=3 c=371 u=-1.0000000000 subseq=20
[Sample-CP] g=4 c=74 u=-1.0000000000 subseq=21
[Sample-CP] g=5 c=1579 u=-1.0000000000 subseq=22
[Sample-CP] g=6 c=739 u=-1.0000000000 subseq=23
[Sample-CP] g=7 c=1694 u=-1.0000000000 subseq=24
[Sample-CP] g=8 c=1179 u=-1.0000000000 subseq=25
[Sample-CP] g=9 c=243 u=-1.0000000000 subseq=26
[Sample-CP] g=10 c=823 u=-1.0000000000 subseq=27
[Sample-CP] g=11 c=706 u=-1.0000000000 subseq=28
[Sample-CP] g=12 c=344 u=-1.0000000000 subseq=29
[Sample-CP] g=2 c=1336 u=-1.0000000000 subseq=19
[Sample-CP] g=3 c=1531 u=-1.0000000000 subseq=20
[Sample-CP] g=4 c=278 u=-1.0000000000 subseq=21
[Sample-CP] g=5 c=1155 u=-1.0000000000 subseq=22
[Sample-CP] g=6 c=405 u=-1.0000000000 subseq=23
[Sample-CP] g=7 c=1242 u=-1.0000000000 subseq=24
[Sample-CP] g=8 c=1124 u=-1.0000000000 subseq=25
[Sample-CP] g=9 c=324 u=-1.0000000000 subseq=26
[Sample-CP] g=10 c=1603 u=-1.0000000000 subseq=27
[Sample-CP] g=11 c=527 u=-1.0000000000 subseq=28
[Sample-CP] g=12 c=781 u=-1.0000000000 subseq=29
[Sample-CP] g=13 c=586 u=-1.0000000000 subseq=30
[Sample-CP] g=14 c=803 u=-1.0000000000 subseq=31
[Sample-CP] g=14 c=1435 u=-1.0000000000 subseq=31
[Pipeline] Generated 8 frames
[Pipeline] Generated 16 frames
[Pipeline] Generated 24 frames
@@ -92,7 +93,7 @@ load_backend: loaded CPU backend from /mnt/workspace/qwentts.cpp/build/libggml-c
[Pipeline] Generated 64 frames
[Pipeline] Generation done : 64 frames
[Debug] codes-full: [64, 16] first4: 1995.000000 1642.000000 1398.000000 2030.000000
[Debug] output-audio: [122880] first4: 0.000071 0.000095 0.000097 0.000094
[Debug] output-audio: [122880] first4: 0.000102 0.000140 0.000144 0.000138
[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...
@@ -105,21 +106,21 @@ load_backend: loaded CPU backend from /mnt/workspace/qwentts.cpp/build/libggml-c
[Python] Codes shape: (63, 16) (T_frames, num_code_groups)
[Python] Audio: 120960 samples 24000 Hz 5.04s -> python/tts/tts-python.wav
[Quant] Q4_K_M -> ../models/qwen-talker-1.7b-voicedesign-Q4_K_M.gguf + ../models/qwen-tokenizer-12hz-Q4_K_M.gguf
[GGML] Cmd: ../build/qwen-tts --model ../models/qwen-talker-1.7b-voicedesign-Q4_K_M.gguf --codec ../models/qwen-tokenizer-12hz-Q4_K_M.gguf --seed 42 --text qwentts.cpp is a minimal C++17 and GGML port of Qwen3-TTS for zero shot multilingual text to speech. --instruct male, young adult, moderate pitch --lang english --max-new 64 --dump cpp/tts -o cpp/tts/tts-cpp.wav --greedy
[GGML] Cmd: ../build/qwen-tts --model ../models/qwen-talker-1.7b-voicedesign-Q4_K_M.gguf --codec ../models/qwen-tokenizer-12hz-Q4_K_M.gguf --seed 42 --instruct male, young adult, moderate pitch --lang english --max-new 64 --dump cpp/tts -o cpp/tts/tts-cpp.wav --greedy
[GGML] Audio: 122880 samples 24000 Hz 5.12s -> cpp/tts/tts-cpp.wav
[Cossim] PromptIDs exact: 100.00% (38 values)
[Cossim] Embed cos: 0.999680 max: 1.3213e-02 mean: 9.5199e-04
[Cossim] Embed cos: 0.999680 max: 1.3244e-02 mean: 9.5245e-04
[Cossim] TrailingText cos: 0.999969 max: 2.4252e-03 mean: 2.2081e-04
[Cossim] TTSPadEmbed cos: 0.999969 max: 2.4252e-03 mean: 2.2081e-04
[Cossim] L0 cos: 0.999207 max: 7.6508e-01 mean: 6.5091e-03
[Cossim] L7 cos: 0.997484 max: 1.6003e+02 mean: 4.3654e-01
[Cossim] L14 cos: 0.997458 max: 1.6086e+02 mean: 5.4263e-01
[Cossim] L21 cos: 0.997065 max: 1.5880e+02 mean: 1.0092e+00
[Cossim] L27 cos: 0.988971 max: 5.3177e+02 mean: 4.5186e+00
[Cossim] Final cos: 0.935061 max: 2.8535e+01 mean: 5.0797e-01
[Cossim] Logits cos: 0.889198 max: 9.0670e+00 mean: 1.7116e+00
[Cossim] NextEmbStep0 cos: 0.832342 max: 1.4996e-01 mean: 3.1096e-02
[Cossim] TalkerHiddenStep1 cos: 0.695479 max: 1.1770e+01 mean: 1.7717e+00
[Cossim] CodesFull exact: 0.69% (1008 values)
[Cossim] Audio cos: -0.001740
[Cossim] WAV stft_cos: 0.091503 samples: 120960
[Cossim] L0 cos: 0.999207 max: 7.6313e-01 mean: 6.5139e-03
[Cossim] L7 cos: 0.997488 max: 1.4405e+02 mean: 4.3667e-01
[Cossim] L14 cos: 0.997462 max: 1.4487e+02 mean: 5.4271e-01
[Cossim] L21 cos: 0.997070 max: 1.4280e+02 mean: 1.0091e+00
[Cossim] L27 cos: 0.988935 max: 5.3251e+02 mean: 4.5243e+00
[Cossim] Final cos: 0.934961 max: 2.8912e+01 mean: 5.0838e-01
[Cossim] Logits cos: 0.892438 max: 8.9615e+00 mean: 1.6785e+00
[Cossim] NextEmbStep0 cos: 0.784060 max: 1.5974e-01 mean: 3.5553e-02
[Cossim] TalkerHiddenStep1 cos: 0.696972 max: 9.2397e+00 mean: 1.7850e+00
[Cossim] CodesFull exact: 0.30% (1008 values)
[Cossim] Audio cos: 0.000331
[Cossim] WAV stft_cos: 0.087055 samples: 120960