[Quant] Q8_0 -> ../models/omnivoice-base-Q8_0.gguf + ../models/omnivoice-tokenizer-Q8_0.gguf
[Input] Prompt: 102 chars: omnivoice.cpp is a minimal C++17 and GGML port of OmniVoice ...
[Input] Instruct: male, young adult, moderate pitch
[Input] Language: French
[Input] Seed: 42

Loading weights:   0%|          | 0/313 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 313/313 [00:00<00:00, 31582.40it/s]

Loading weights:   0%|          | 0/527 [00:00<?, ?it/s]
Loading weights: 100%|██████████| 527/527 [00:00<00:00, 28844.32it/s]
[CLI] Seed: 42
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/omnivoice.cpp/build/libggml-cuda.so
ggml_vulkan: Found 1 Vulkan devices:
ggml_vulkan: 0 = NVIDIA RTX PRO 6000 Blackwell Workstation Edition (NVIDIA) | uma: 0 | fp16: 1 | bf16: 0 | warp size: 32 | shared memory: 49152 | int dot: 1 | matrix cores: NV_coopmat2
load_backend: loaded Vulkan backend from /mnt/workspace/omnivoice.cpp/build/libggml-vulkan.so
load_backend: loaded CPU backend from /mnt/workspace/omnivoice.cpp/build/libggml-cpu-zen4.so
[Load] LM backend: CUDA0 (CPU threads: 16)
[GGUF] ../models/omnivoice-base-Q8_0.gguf: 312 tensors, data at offset 5339136
[LM-Load] Loaded: 28L H=1024 FFN=3072 Nh=16 Nkv=8 D=128 theta=1000000 eps=1e-06 | audio: K=8 V=1025 mask_id=1024
[Qwen3] Attn: Q+K+V fused
[Qwen3] MLP: gate+up fused
[WeightCtx] Loaded 312 tensors, 620.9 MB into backend
[Load] Flash attention disabled
[BPE] Loaded from GGUF: 151676 vocab, 151387 merges, eos_id=151643
[BPE] Registered 7 OmniVoice special tokens (total specials=8)
[GGUF] ../models/omnivoice-tokenizer-Q8_0.gguf: 486 tensors, data at offset 43680
[WeightCtx] Loaded 52 tensors, 11.1 MB into backend
[DAC] Loaded: 5 blocks, upsample 960x (8*5*4*2*3), 24 kHz mono out, weights 38.7 MB
[DAC-Enc] Loaded: 5 blocks, downsample 960x (8*5*4*2*3), 24 kHz mono in, weights 98.0 MB
[Sem-Enc] Loaded: 2 blocks, hidden=768, no temporal downsample, weights 28.1 MB
[HuBERT-Feat] Loaded: 7 conv layers, cumul stride 320, weights 8.0 MB
[HuBERT-Proj] Loaded: LN(512) + Linear(512 -> 768), weights 0.4 MB
[HuBERT-EncInit] Loaded: pos_conv k=128 g=16 + LN(768), weights 9.0 MB
[HuBERT-Stack] Loaded: 12 layers, hidden=768 heads=12 ffn=3072, weights 86.5 MB
[PipelineCodec] Loaded codec: sr=24000 hop=960 backend=CUDA0
[TTS-Long] Single-shot path: T=163 frames (6.52s), threshold=750 frames
[Prompt] Built: B'=2 K=8 S=205 N1=12 N2=30 Sref=0 Stgt=163 c_len=205 u_len=163 denoise=0
[Debug] prompt-cond-ids: [205] first4: 151670.000000 1626.000000 151671.000000 151672.000000
[Debug] prompt-uncond-ids: [205] first4: 1024.000000 1024.000000 1024.000000 1024.000000
[TTS] Prompt: B'=2 K=8 S=205 c_len=205 u_len=163
[MaskGIT] Start: T=163 K=8 S=205 num_step=32 guidance=2.00 t_shift=0.100 layer_pen=5.00 cls_t=0.00 pos_t=5.00
[Debug] lm-hidden-step0-cond-embed: [205, 1024] first4: -0.032649 -0.045788 -0.006769 0.006769
[Debug] lm-hidden-step0-cond-l0: [205, 1024] first4: 0.141092 0.028385 -0.173764 -3.204908
[Debug] lm-hidden-step0-cond-l1: [205, 1024] first4: 0.486492 0.130315 -0.127969 -4.270612
[Debug] lm-hidden-step0-cond-l2: [205, 1024] first4: 0.451498 0.355822 -0.097643 -4.201322
[Debug] lm-hidden-step0-cond-l3: [205, 1024] first4: 0.350925 0.435515 0.104707 -3.924219
[Debug] lm-hidden-step0-cond-l4: [205, 1024] first4: 0.080748 0.630445 0.158736 -3.914514
[Debug] lm-hidden-step0-cond-l5: [205, 1024] first4: 0.247336 0.615743 0.115521 -3.742074
[Debug] lm-hidden-step0-cond-l6: [205, 1024] first4: 0.508840 0.508420 -0.042312 -3.387783
[Debug] lm-hidden-step0-cond-l13: [205, 1024] first4: 1.235033 1.372217 0.329518 -4.885667
[Debug] lm-hidden-step0-cond-l14: [205, 1024] first4: 1.162764 1.816814 0.293495 -4.500912
[Debug] lm-hidden-step0-cond-l15: [205, 1024] first4: 0.752557 2.439555 0.451490 -4.830612
[Debug] lm-hidden-step0-cond-l16: [205, 1024] first4: 0.531708 3.262591 0.644435 -3.912714
[Debug] lm-hidden-step0-cond-l17: [205, 1024] first4: -0.320051 4.586965 -0.514368 -2.349482
[Debug] lm-hidden-step0-cond-l18: [205, 1024] first4: 0.133298 5.321824 -1.941605 -1.026288
[Debug] lm-hidden-step0-cond-l19: [205, 1024] first4: 0.616354 4.981306 0.394881 -1.078204
[Debug] lm-hidden-step0-cond-l20: [205, 1024] first4: 0.204271 12.178906 -4.512753 0.120572
[Debug] lm-hidden-step0-cond-l1-norm1: [205, 1024] first4: 0.018586 0.005402 0.018377 0.166925
[Debug] lm-hidden-step0-cond-l1-attn: [205, 1024] first4: 0.230562 -0.063147 0.417904 -0.603062
[Debug] lm-hidden-step0-cond-l1-norm2: [205, 1024] first4: 0.184092 -0.024238 -0.157244 -4.954337
[Debug] lm-hidden-step0-cond-l1-mlp: [205, 1024] first4: 0.114838 0.165078 -0.372109 -0.462642
[Debug] lm-hidden-step0-cond: [205, 1024] first4: 0.337307 7.768000 42.797329 0.159504
[Debug] lm-hidden-step0-uncond-embed: [205, 1024] first4: 0.005380 0.004855 0.010246 0.009150
[Debug] lm-hidden-step0-uncond-l0: [205, 1024] first4: -0.051625 0.059900 0.243252 -2.710808
[Debug] lm-hidden-step0-uncond-l1: [205, 1024] first4: -0.274705 0.406423 0.244897 -3.155345
[Debug] lm-hidden-step0-uncond-l2: [205, 1024] first4: -0.414259 0.747018 0.240752 -3.523101
[Debug] lm-hidden-step0-uncond-l3: [205, 1024] first4: -0.092766 0.854092 0.113439 -3.482504
[Debug] lm-hidden-step0-uncond-l4: [205, 1024] first4: -0.234864 0.601983 -0.040992 -3.579212
[Debug] lm-hidden-step0-uncond-l5: [205, 1024] first4: -0.206304 1.169172 0.035129 -4.019620
[Debug] lm-hidden-step0-uncond-l6: [205, 1024] first4: -0.308291 0.832311 0.014568 -4.748949
[Debug] lm-hidden-step0-uncond-l13: [205, 1024] first4: 2.473259 1.439130 -0.037022 -12.997085
[Debug] lm-hidden-step0-uncond-l14: [205, 1024] first4: 2.644835 2.262453 -0.108625 -15.102911
[Debug] lm-hidden-step0-uncond-l15: [205, 1024] first4: 3.585491 3.298950 0.413927 -19.134167
[Debug] lm-hidden-step0-uncond-l16: [205, 1024] first4: 4.340610 1.866031 -0.719878 -15.702097
[Debug] lm-hidden-step0-uncond-l17: [205, 1024] first4: 4.185430 3.241367 -1.738344 -13.227559
[Debug] lm-hidden-step0-uncond-l18: [205, 1024] first4: 3.022331 3.679394 3.502697 -11.665640
[Debug] lm-hidden-step0-uncond-l19: [205, 1024] first4: 3.380286 7.706031 9.605055 -7.291924
[Debug] lm-hidden-step0-uncond-l20: [205, 1024] first4: 6.247076 16.711468 1.511102 -5.295573
[Debug] lm-hidden-step0-uncond-l1-norm1: [205, 1024] first4: -0.007154 0.011991 -0.027060 0.148516
[Debug] lm-hidden-step0-uncond-l1-attn: [205, 1024] first4: -0.239398 0.405594 0.344235 -0.053435
[Debug] lm-hidden-step0-uncond-l1-norm2: [205, 1024] first4: -0.156492 0.352342 -0.410773 -3.904237
[Debug] lm-hidden-step0-uncond-l1-mlp: [205, 1024] first4: 0.016318 -0.059071 -0.342591 -0.391102
[Debug] lm-hidden-step0-uncond: [205, 1024] first4: 0.837195 47.099628 129.019913 0.552044
[Debug] lm-logits-step0-cond: [8, 163, 1025] first4: 17.097706 12.082623 17.530075 17.390030
[Debug] lm-logits-step0-uncond: [8, 163, 1025] first4: 16.830109 11.095350 15.792145 16.459023
[Debug] mg-pred-tokens-step0: [8, 163] first4: 511.000000 644.000000 956.000000 1013.000000
[Debug] mg-scores-step0: [8, 163] first4: -2.017292 -2.205665 -2.563331 -2.068046
[Debug] mg-log-probs-step0: [8, 163, 1025] first4: -9.680384 -13.256117 -6.307348 -8.061239
[MaskGIT-Step] 1/32 demask=5 remaining=1299
[MaskGIT-Step] 2/32 demask=5 remaining=1294
[MaskGIT-Step] 3/32 demask=5 remaining=1289
[MaskGIT-Step] 4/32 demask=6 remaining=1283
[MaskGIT-Step] 5/32 demask=6 remaining=1277
[MaskGIT-Step] 6/32 demask=6 remaining=1271
[MaskGIT-Step] 7/32 demask=7 remaining=1264
[MaskGIT-Step] 8/32 demask=7 remaining=1257
[MaskGIT-Step] 9/32 demask=8 remaining=1249
[MaskGIT-Step] 10/32 demask=8 remaining=1241
[MaskGIT-Step] 11/32 demask=9 remaining=1232
[MaskGIT-Step] 12/32 demask=9 remaining=1223
[MaskGIT-Step] 13/32 demask=10 remaining=1213
[MaskGIT-Step] 14/32 demask=11 remaining=1202
[MaskGIT-Step] 15/32 demask=12 remaining=1190
[MaskGIT-Step] 16/32 demask=13 remaining=1177
[MaskGIT-Step] 17/32 demask=15 remaining=1162
[MaskGIT-Step] 18/32 demask=16 remaining=1146
[MaskGIT-Step] 19/32 demask=18 remaining=1128
[MaskGIT-Step] 20/32 demask=21 remaining=1107
[MaskGIT-Step] 21/32 demask=23 remaining=1084
[MaskGIT-Step] 22/32 demask=27 remaining=1057
[MaskGIT-Step] 23/32 demask=31 remaining=1026
[MaskGIT-Step] 24/32 demask=36 remaining=990
[MaskGIT-Step] 25/32 demask=43 remaining=947
[MaskGIT-Step] 26/32 demask=52 remaining=895
[MaskGIT-Step] 27/32 demask=64 remaining=831
[MaskGIT-Step] 28/32 demask=80 remaining=751
[MaskGIT-Step] 29/32 demask=105 remaining=646
[MaskGIT-Step] 30/32 demask=142 remaining=504
[MaskGIT-Step] 31/32 demask=204 remaining=300
[MaskGIT-Step] 32/32 demask=300 remaining=0
[MaskGIT] Total LM forward: 322.93 ms across 32 steps (avg 10.09 ms/step)
[Debug] mg-tokens: [8, 163] first4: 947.000000 465.000000 885.000000 524.000000
[TTS] Decode: K=8 T=163 expected_samples=156480
[Debug] output-audio: [156480] first4: -0.000604 -0.003757 -0.004956 -0.004674
[TTS-Long] Post-proc: 156480 -> 161280 samples (6.72s at 24000 Hz, ref_rms=-1.0000)
[WAV] Wrote cpp/tts-cpp.wav: 161280 samples, 24000 Hz, mono F32
[OmniVoice-TTS] TTS: wrote cpp/tts-cpp.wav (161280 samples @ 24000 Hz, 6.72 s)
[Python] Audio: 161280 samples 6.72s -> python/tts-python.wav
[GGML] Cmd: ../build/omnivoice-tts --model ../models/omnivoice-base-Q8_0.gguf --codec ../models/omnivoice-tokenizer-Q8_0.gguf --seed 42 --instruct male, young adult, moderate pitch --lang French --format wav32 --dump cpp --no-fa -o cpp/tts-cpp.wav
[GGML] Audio: 161280 samples 24000 Hz 6.72s -> cpp/tts-cpp.wav
[Cossim] PromptIDs cond exact: 100.00% uncond exact: 100.00%
[Cossim] Embed cond cos: 0.999982 max: 4.3700e-03 mean: 4.3656e-04 uncond cos: 0.999983 max: 3.2318e-03 mean: 4.2568e-04
[Cossim] L0 cond cos: 0.999992 max: 5.3192e-02 mean: 2.5048e-03 uncond cos: 0.999985 max: 4.1177e-02 mean: 3.5060e-03
[Cossim] L6 cond cos: 0.999985 max: 1.9293e-01 mean: 5.3796e-03 uncond cos: 0.999964 max: 2.2104e-01 mean: 9.2558e-03
[Cossim] L13 cond cos: 0.999985 max: 7.6294e-01 mean: 1.2233e-02 uncond cos: 0.999979 max: 5.1918e-01 mean: 1.3900e-02
[Cossim] L20 cond cos: 0.999984 max: 1.3434e+01 mean: 7.9942e-02 uncond cos: 0.999985 max: 1.7849e+00 mean: 5.1549e-02
[Cossim] Final cond cos: 0.999998 max: 2.3239e+00 mean: 5.5314e-03 uncond cos: 0.999999 max: 5.2432e-01 mean: 5.7846e-03
[Cossim] Logits cond cos: 0.999998 max: 1.4072e+00 mean: 1.2423e-01 uncond cos: 0.999998 max: 9.7286e-01 mean: 1.4521e-01
[Cossim] Step0Tokens exact: 47.16% diffs: 689
[Cossim] Step0Scores cos: 0.995320 max_abs_diff: 2.208165 mean_abs_diff: 0.286031
[Cossim] Step0LogProbs cos: 0.999006 max_abs_diff: 3.559841 mean_abs_diff: 0.315928
[Cossim] Tokens: 0.755005 exact: 1.92%
[Cossim] Audio: 0.009296
[Cossim] WAV stft_cos: 0.421529 samples: 161280