initial release
This commit is contained in:
@@ -0,0 +1,143 @@
|
||||
[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, 26564.49it/s]
|
||||
|
||||
Loading weights: 0%| | 0/527 [00:00<?, ?it/s]
|
||||
Loading weights: 100%|██████████| 527/527 [00:00<00:00, 28382.10it/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: CPU (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=CPU
|
||||
[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: 0.141127 0.028480 -0.173933 -3.205186
|
||||
[Debug] lm-hidden-step0-cond-l1: [205, 1024] first4: 0.485743 0.131329 -0.129260 -4.268756
|
||||
[Debug] lm-hidden-step0-cond-l2: [205, 1024] first4: 0.451186 0.356976 -0.099721 -4.199864
|
||||
[Debug] lm-hidden-step0-cond-l3: [205, 1024] first4: 0.354036 0.435237 0.103277 -3.923582
|
||||
[Debug] lm-hidden-step0-cond-l4: [205, 1024] first4: 0.084226 0.631740 0.157809 -3.915523
|
||||
[Debug] lm-hidden-step0-cond-l5: [205, 1024] first4: 0.247957 0.617610 0.119682 -3.741882
|
||||
[Debug] lm-hidden-step0-cond-l6: [205, 1024] first4: 0.507512 0.507268 -0.037517 -3.389683
|
||||
[Debug] lm-hidden-step0-cond-l13: [205, 1024] first4: 1.237017 1.364527 0.329351 -4.886948
|
||||
[Debug] lm-hidden-step0-cond-l14: [205, 1024] first4: 1.166781 1.806478 0.296166 -4.500538
|
||||
[Debug] lm-hidden-step0-cond-l15: [205, 1024] first4: 0.752382 2.428083 0.457693 -4.833712
|
||||
[Debug] lm-hidden-step0-cond-l16: [205, 1024] first4: 0.524039 3.249174 0.648307 -3.916344
|
||||
[Debug] lm-hidden-step0-cond-l17: [205, 1024] first4: -0.335010 4.584835 -0.483551 -2.361471
|
||||
[Debug] lm-hidden-step0-cond-l18: [205, 1024] first4: 0.112950 5.315489 -1.897550 -1.030699
|
||||
[Debug] lm-hidden-step0-cond-l19: [205, 1024] first4: 0.608981 4.998482 0.428165 -1.095730
|
||||
[Debug] lm-hidden-step0-cond-l20: [205, 1024] first4: 0.208701 12.202758 -4.538644 0.093163
|
||||
[Debug] lm-hidden-step0-cond-l1-norm1: [205, 1024] first4: 0.018590 0.005420 0.018393 0.166927
|
||||
[Debug] lm-hidden-step0-cond-l1-attn: [205, 1024] first4: 0.230060 -0.063016 0.417126 -0.602279
|
||||
[Debug] lm-hidden-step0-cond-l1-norm2: [205, 1024] first4: 0.183862 -0.024080 -0.156636 -4.953710
|
||||
[Debug] lm-hidden-step0-cond-l1-mlp: [205, 1024] first4: 0.114556 0.165865 -0.372453 -0.461290
|
||||
[Debug] lm-hidden-step0-cond: [205, 1024] first4: 0.336127 7.767795 42.782616 0.160128
|
||||
[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: -0.051981 0.059643 0.242803 -2.710410
|
||||
[Debug] lm-hidden-step0-uncond-l1: [205, 1024] first4: -0.276543 0.405631 0.246121 -3.154772
|
||||
[Debug] lm-hidden-step0-uncond-l2: [205, 1024] first4: -0.415722 0.744238 0.244081 -3.524319
|
||||
[Debug] lm-hidden-step0-uncond-l3: [205, 1024] first4: -0.095866 0.851245 0.116631 -3.484274
|
||||
[Debug] lm-hidden-step0-uncond-l4: [205, 1024] first4: -0.236836 0.599254 -0.037242 -3.580574
|
||||
[Debug] lm-hidden-step0-uncond-l5: [205, 1024] first4: -0.207356 1.166708 0.037786 -4.020639
|
||||
[Debug] lm-hidden-step0-uncond-l6: [205, 1024] first4: -0.311079 0.830015 0.012306 -4.746327
|
||||
[Debug] lm-hidden-step0-uncond-l13: [205, 1024] first4: 2.458821 1.433856 -0.039787 -13.004999
|
||||
[Debug] lm-hidden-step0-uncond-l14: [205, 1024] first4: 2.617807 2.256731 -0.101241 -15.098066
|
||||
[Debug] lm-hidden-step0-uncond-l15: [205, 1024] first4: 3.535855 3.295662 0.426010 -19.088314
|
||||
[Debug] lm-hidden-step0-uncond-l16: [205, 1024] first4: 4.292028 1.864804 -0.729806 -15.659145
|
||||
[Debug] lm-hidden-step0-uncond-l17: [205, 1024] first4: 4.145811 3.217169 -1.741059 -13.167794
|
||||
[Debug] lm-hidden-step0-uncond-l18: [205, 1024] first4: 2.999762 3.649144 3.490895 -11.620733
|
||||
[Debug] lm-hidden-step0-uncond-l19: [205, 1024] first4: 3.380697 7.641136 9.605453 -7.238606
|
||||
[Debug] lm-hidden-step0-uncond-l20: [205, 1024] first4: 6.218327 16.649353 1.514950 -5.209467
|
||||
[Debug] lm-hidden-step0-uncond-l1-norm1: [205, 1024] first4: -0.007204 0.011941 -0.027014 0.148511
|
||||
[Debug] lm-hidden-step0-uncond-l1-attn: [205, 1024] first4: -0.240019 0.405991 0.344779 -0.053408
|
||||
[Debug] lm-hidden-step0-uncond-l1-norm2: [205, 1024] first4: -0.157031 0.352479 -0.410875 -3.903977
|
||||
[Debug] lm-hidden-step0-uncond-l1-mlp: [205, 1024] first4: 0.015458 -0.060003 -0.341461 -0.390954
|
||||
[Debug] lm-hidden-step0-uncond: [205, 1024] first4: 0.836763 47.126915 128.953995 0.549016
|
||||
[Debug] lm-logits-step0-cond: [8, 163, 1025] first4: 17.067307 12.047602 17.459633 17.405617
|
||||
[Debug] lm-logits-step0-uncond: [8, 163, 1025] first4: 16.817457 11.126129 15.793516 16.454260
|
||||
[Debug] mg-pred-tokens-step0: [8, 163] first4: 492.000000 644.000000 956.000000 1013.000000
|
||||
[Debug] mg-scores-step0: [8, 163] first4: -2.077560 -2.165167 -2.593139 -2.143889
|
||||
[Debug] mg-log-probs-step0: [8, 163, 1025] first4: -9.845706 -13.522164 -6.620845 -8.104381
|
||||
[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: 13542.93 ms across 32 steps (avg 423.22 ms/step)
|
||||
[Debug] mg-tokens: [8, 163] first4: 164.000000 992.000000 807.000000 885.000000
|
||||
[TTS] Decode: K=8 T=163 expected_samples=156480
|
||||
[Debug] output-audio: [156480] first4: -0.000056 -0.000399 -0.000358 -0.000285
|
||||
[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: 5.1172e-02 mean: 2.5036e-03 uncond cos: 0.999985 max: 3.8886e-02 mean: 3.5071e-03
|
||||
[Cossim] L6 cond cos: 0.999984 max: 2.2097e-01 mean: 5.5048e-03 uncond cos: 0.999964 max: 1.4544e-01 mean: 9.2647e-03
|
||||
[Cossim] L13 cond cos: 0.999985 max: 6.6708e-01 mean: 1.1900e-02 uncond cos: 0.999978 max: 7.4876e-01 mean: 1.4051e-02
|
||||
[Cossim] L20 cond cos: 0.999989 max: 9.7499e+00 mean: 6.8194e-02 uncond cos: 0.999985 max: 1.4187e+00 mean: 5.2343e-02
|
||||
[Cossim] Final cond cos: 0.999998 max: 3.8532e+00 mean: 5.4428e-03 uncond cos: 0.999999 max: 4.7534e-01 mean: 5.7941e-03
|
||||
[Cossim] Logits cond cos: 0.999998 max: 1.2323e+00 mean: 1.2287e-01 uncond cos: 0.999998 max: 9.7068e-01 mean: 1.4425e-01
|
||||
[Cossim] Step0Tokens exact: 46.47% diffs: 698
|
||||
[Cossim] Step0Scores cos: 0.995428 max_abs_diff: 2.216954 mean_abs_diff: 0.279892
|
||||
Reference in New Issue
Block a user