144 lines
11 KiB
Plaintext
144 lines
11 KiB
Plaintext
[Quant] F32 -> ../models/omnivoice-base-F32.gguf + ../models/omnivoice-tokenizer-F32.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, 31951.35it/s]
|
|
|
|
Loading weights: 0%| | 0/527 [00:00<?, ?it/s]
|
|
Loading weights: 100%|██████████| 527/527 [00:00<00:00, 31959.26it/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-F32.gguf: 312 tensors, data at offset 5339040
|
|
[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, 2336.8 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-F32.gguf: 486 tensors, data at offset 44160
|
|
[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 1.5 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 324.5 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: -0.032496 -0.045770 -0.006827 0.006779
|
|
[Debug] lm-hidden-step0-cond-l0: [205, 1024] first4: 0.143429 0.028058 -0.176004 -3.210877
|
|
[Debug] lm-hidden-step0-cond-l1: [205, 1024] first4: 0.495611 0.133859 -0.131644 -4.269015
|
|
[Debug] lm-hidden-step0-cond-l2: [205, 1024] first4: 0.458203 0.357299 -0.100272 -4.198600
|
|
[Debug] lm-hidden-step0-cond-l3: [205, 1024] first4: 0.357937 0.436961 0.106377 -3.917122
|
|
[Debug] lm-hidden-step0-cond-l4: [205, 1024] first4: 0.088977 0.634135 0.160155 -3.906283
|
|
[Debug] lm-hidden-step0-cond-l5: [205, 1024] first4: 0.255354 0.620559 0.113358 -3.732861
|
|
[Debug] lm-hidden-step0-cond-l6: [205, 1024] first4: 0.518232 0.512233 -0.046988 -3.379119
|
|
[Debug] lm-hidden-step0-cond-l13: [205, 1024] first4: 1.239480 1.377719 0.334330 -4.866330
|
|
[Debug] lm-hidden-step0-cond-l14: [205, 1024] first4: 1.163611 1.817584 0.306644 -4.481832
|
|
[Debug] lm-hidden-step0-cond-l15: [205, 1024] first4: 0.760563 2.433619 0.459761 -4.811815
|
|
[Debug] lm-hidden-step0-cond-l16: [205, 1024] first4: 0.543520 3.254392 0.652481 -3.903667
|
|
[Debug] lm-hidden-step0-cond-l17: [205, 1024] first4: -0.318273 4.585968 -0.490006 -2.352975
|
|
[Debug] lm-hidden-step0-cond-l18: [205, 1024] first4: 0.116620 5.299300 -1.922667 -1.066189
|
|
[Debug] lm-hidden-step0-cond-l19: [205, 1024] first4: 0.575392 4.952140 0.378127 -1.110631
|
|
[Debug] lm-hidden-step0-cond-l20: [205, 1024] first4: 0.189642 12.136806 -4.513153 0.095100
|
|
[Debug] lm-hidden-step0-cond-l1-norm1: [205, 1024] first4: 0.018902 0.005342 0.018621 0.167302
|
|
[Debug] lm-hidden-step0-cond-l1-attn: [205, 1024] first4: 0.227721 -0.063162 0.416183 -0.599596
|
|
[Debug] lm-hidden-step0-cond-l1-norm2: [205, 1024] first4: 0.183972 -0.024493 -0.154803 -4.961101
|
|
[Debug] lm-hidden-step0-cond-l1-mlp: [205, 1024] first4: 0.124462 0.168964 -0.371823 -0.458541
|
|
[Debug] lm-hidden-step0-cond: [205, 1024] first4: 0.337540 7.761668 42.813408 0.161507
|
|
[Debug] lm-hidden-step0-uncond-embed: [205, 1024] first4: 0.005183 0.004625 0.009925 0.009213
|
|
[Debug] lm-hidden-step0-uncond-l0: [205, 1024] first4: -0.055614 0.061210 0.241398 -2.712474
|
|
[Debug] lm-hidden-step0-uncond-l1: [205, 1024] first4: -0.278304 0.415421 0.243089 -3.153144
|
|
[Debug] lm-hidden-step0-uncond-l2: [205, 1024] first4: -0.421454 0.747654 0.239361 -3.513885
|
|
[Debug] lm-hidden-step0-uncond-l3: [205, 1024] first4: -0.101611 0.854395 0.111338 -3.486203
|
|
[Debug] lm-hidden-step0-uncond-l4: [205, 1024] first4: -0.249011 0.603088 -0.036039 -3.584491
|
|
[Debug] lm-hidden-step0-uncond-l5: [205, 1024] first4: -0.216003 1.170896 0.038527 -4.025774
|
|
[Debug] lm-hidden-step0-uncond-l6: [205, 1024] first4: -0.314576 0.831446 0.012469 -4.754603
|
|
[Debug] lm-hidden-step0-uncond-l13: [205, 1024] first4: 2.455498 1.447640 -0.039729 -12.965415
|
|
[Debug] lm-hidden-step0-uncond-l14: [205, 1024] first4: 2.610186 2.270953 -0.097502 -15.046100
|
|
[Debug] lm-hidden-step0-uncond-l15: [205, 1024] first4: 3.542682 3.306396 0.433103 -19.015217
|
|
[Debug] lm-hidden-step0-uncond-l16: [205, 1024] first4: 4.347703 1.863318 -0.667007 -15.599176
|
|
[Debug] lm-hidden-step0-uncond-l17: [205, 1024] first4: 4.205956 3.181918 -1.625845 -13.151051
|
|
[Debug] lm-hidden-step0-uncond-l18: [205, 1024] first4: 3.064053 3.621870 3.550607 -11.619642
|
|
[Debug] lm-hidden-step0-uncond-l19: [205, 1024] first4: 3.456345 7.613440 9.715604 -7.268495
|
|
[Debug] lm-hidden-step0-uncond-l20: [205, 1024] first4: 6.245480 16.691681 1.669448 -5.199030
|
|
[Debug] lm-hidden-step0-uncond-l1-norm1: [205, 1024] first4: -0.007703 0.012248 -0.026843 0.148544
|
|
[Debug] lm-hidden-step0-uncond-l1-attn: [205, 1024] first4: -0.238602 0.407195 0.342191 -0.051809
|
|
[Debug] lm-hidden-step0-uncond-l1-norm2: [205, 1024] first4: -0.158114 0.354332 -0.407803 -3.901946
|
|
[Debug] lm-hidden-step0-uncond-l1-mlp: [205, 1024] first4: 0.015913 -0.052983 -0.340500 -0.388862
|
|
[Debug] lm-hidden-step0-uncond: [205, 1024] first4: 0.837443 47.190083 128.835205 0.552667
|
|
[Debug] lm-logits-step0-cond: [8, 163, 1025] first4: 17.020012 11.748607 17.811529 17.076855
|
|
[Debug] lm-logits-step0-uncond: [8, 163, 1025] first4: 16.651178 10.937085 16.705170 16.514231
|
|
[Debug] mg-pred-tokens-step0: [8, 163] first4: 976.000000 644.000000 599.000000 679.000000
|
|
[Debug] mg-scores-step0: [8, 163] first4: -1.943948 -1.842691 -2.858332 -2.091614
|
|
[Debug] mg-log-probs-step0: [8, 163, 1025] first4: -9.550063 -13.936092 -7.283494 -9.105639
|
|
[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: 646.50 ms across 32 steps (avg 20.20 ms/step)
|
|
[Debug] mg-tokens: [8, 163] first4: 947.000000 453.000000 524.000000 878.000000
|
|
[TTS] Decode: K=8 T=163 expected_samples=156480
|
|
[Debug] output-audio: [156480] first4: 0.001864 0.000758 0.001075 0.001731
|
|
[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-F32.gguf --codec ../models/omnivoice-tokenizer-F32.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: 1.000000 max: 2.3842e-07 mean: 2.3634e-09 uncond cos: 1.000000 max: 2.3842e-07 mean: 2.3634e-09
|
|
[Cossim] L0 cond cos: 1.000000 max: 7.6294e-06 mean: 7.2469e-08 uncond cos: 1.000000 max: 7.6294e-06 mean: 8.7633e-08
|
|
[Cossim] L6 cond cos: 1.000000 max: 4.5776e-05 mean: 5.9211e-07 uncond cos: 1.000000 max: 2.0981e-05 mean: 3.4285e-07
|
|
[Cossim] L13 cond cos: 1.000000 max: 1.4496e-04 mean: 1.8604e-06 uncond cos: 1.000000 max: 3.0518e-05 mean: 6.4515e-07
|
|
[Cossim] L20 cond cos: 1.000000 max: 7.3242e-04 mean: 7.8134e-06 uncond cos: 1.000000 max: 1.8311e-04 mean: 2.3730e-06
|
|
[Cossim] Final cond cos: 1.000000 max: 3.6621e-04 mean: 3.9112e-07 uncond cos: 1.000000 max: 7.6294e-05 mean: 2.9361e-07
|
|
[Cossim] Logits cond cos: 1.000000 max: 3.5095e-04 mean: 3.4896e-05 uncond cos: 1.000000 max: 3.6621e-04 mean: 3.4818e-05
|
|
[Cossim] Step0Tokens exact: 99.85% diffs: 2
|
|
[Cossim] Step0Scores cos: 1.000000 max_abs_diff: 0.000826 mean_abs_diff: 0.000130
|
|
[Cossim] Step0LogProbs cos: 1.000000 max_abs_diff: 0.001174 mean_abs_diff: 0.000126
|
|
[Cossim] Tokens: 1.000000 exact: 100.00%
|
|
[Cossim] Audio: 0.999992
|
|
[Cossim] WAV stft_cos: 0.999998 samples: 161280
|