126 lines
8.2 KiB
Plaintext
126 lines
8.2 KiB
Plaintext
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
|
|
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/qwentts.cpp/build/libggml-vulkan.so
|
|
load_backend: loaded CPU backend from /mnt/workspace/qwentts.cpp/build/libggml-cpu-zen4.so
|
|
[Load] Talker backend: Vulkan0 (CPU threads: 16)
|
|
[GGUF] ../models/qwen-talker-1.7b-base-Q4_K_M.gguf: 480 tensors, data at offset 5954496
|
|
[WeightCtx] Loaded 316 tensors, 1012.7 MB into backend
|
|
[Talker] Loaded: 28 layers, hidden 2048, heads 16/8, head_dim 128, FFN 6144, RoPE theta 1000000, mrope sections [24,20,20] interleaved=0
|
|
[WeightCtx] Loaded 88 tensors, 109.5 MB into backend
|
|
[CodePredictor] Loaded: 5 layers, hidden 1024, heads 16/8, head_dim 128, FFN 3072, RoPE theta 1000000, 15 acoustic codebooks (vocab 2048 each), mtp_proj linear
|
|
[WeightCtx] Loaded 76 tensors, 34.9 MB into backend
|
|
[SpeakerEncoder] Loaded: enc_dim=2048 sr=24000 mel_dim=128 hidden=512 mfa=1536 asp_attn=128 se=128 scale=8
|
|
[GGUF] ../models/qwen-tokenizer-12hz-Q4_K_M.gguf: 398 tensors, data at offset 29760
|
|
[WeightCtx] Loaded 18 tensors, 33.0 MB into backend
|
|
[Quantizer] Loaded: 16 codebooks (1 semantic + 15 acoustic), 2048 entries x 256 dim, hidden 512
|
|
[WeightCtx] Loaded 93 tensors, 16.4 MB into backend
|
|
[Transformer] Loaded: 8 layers, hidden 512, heads 16/16, head_dim 64, FFN 1024, RoPE theta 10000, sliding window 72
|
|
[WeightCtx] Loaded 22 tensors, 25.1 MB into backend
|
|
[Upsample] Loaded: 2 blocks (2x ratio per block), channels 1024, dwconv kernel 7
|
|
[WeightCtx] Loaded 118 tensors, 142.9 MB into backend
|
|
[DAC] Loaded: 4 blocks (strides 8/5/4/3), 24 kHz mono out, weights 142.9 MB
|
|
[WeightCtx] Loaded 2 tensors, 3.0 MB into backend
|
|
[WeightCtx] Loaded 28 tensors, 24.1 MB into backend
|
|
[SEANet] Loaded: 4 stages (ratios 4/5/6/8), 64 -> 512 channels, weights 24.1 MB
|
|
[WeightCtx] Loaded 96 tensors, 13.6 MB into backend
|
|
[EncTransformer] Loaded: 8 layers, hidden 512, heads 8/8, head_dim 64, FFN 2048, RoPE theta 10000
|
|
[WeightCtx] Loaded 1 tensors, 2.0 MB into backend
|
|
[EncDownsample] Loaded: k=4 stride=2, 512 -> 512 channels, weights 2.0 MB
|
|
[WeightCtx] Loaded 20 tensors, 34.0 MB into backend
|
|
[EncQuantizer] Loaded: 16 codebooks (1 semantic + 15 acoustic), 2048 entries x 256 dim, hidden 512, weights 34.0 MB
|
|
[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=base tokenizer=qwen3_tts_tokenizer_12hz codebooks=16 speaker_encoder=loaded speakers=0
|
|
[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=0, T_ctx=40, 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: [40, 2048] first4: 0.022105 -0.009079 0.008285 -0.019901
|
|
[Debug] trailing-text-hidden: [1, 2048] first4: -0.005388 0.008927 -0.004415 0.000679
|
|
[Debug] tts-pad-embed: [2048] first4: -0.005388 0.008927 -0.004415 0.000679
|
|
[Debug] talker-hidden-prefill-l0: [40, 2048] first4: -0.440114 -0.067513 0.007682 0.014812
|
|
[Debug] talker-hidden-prefill-l7: [40, 2048] first4: -8.839585 0.783318 0.508945 0.097937
|
|
[Debug] talker-hidden-prefill-l14: [40, 2048] first4: -8.774442 1.117288 0.612085 0.163537
|
|
[Debug] talker-hidden-prefill-l21: [40, 2048] first4: -8.658731 1.690545 1.112828 -0.787406
|
|
[Debug] talker-hidden-prefill-l27: [40, 2048] first4: 4.962493 -31.760586 -6.788569 21.825624
|
|
[Debug] talker-hidden-prefill-final: [40, 2048] first4: 0.167658 -1.120514 -0.213115 0.672126
|
|
[Debug] talker-logits-prefill: [3072] first4: -6.832031 -4.953125 0.424805 -1.972656
|
|
[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=1294 u=-1.0000000000 subseq=4
|
|
[Sample-CP] g=4 c=778 u=-1.0000000000 subseq=5
|
|
[Sample-CP] g=5 c=1206 u=-1.0000000000 subseq=6
|
|
[Sample-CP] g=6 c=308 u=-1.0000000000 subseq=7
|
|
[Sample-CP] g=7 c=1117 u=-1.0000000000 subseq=8
|
|
[Sample-CP] g=8 c=1439 u=-1.0000000000 subseq=9
|
|
[Sample-CP] g=9 c=359 u=-1.0000000000 subseq=10
|
|
[Sample-CP] g=10 c=55 u=-1.0000000000 subseq=11
|
|
[Sample-CP] g=11 c=453 u=-1.0000000000 subseq=12
|
|
[Sample-CP] g=12 c=989 u=-1.0000000000 subseq=13
|
|
[Sample-CP] g=13 c=403 u=-1.0000000000 subseq=14
|
|
[Sample-CP] g=14 c=363 u=-1.0000000000 subseq=15
|
|
[Debug] codes-step0: [16] first4: 1995.000000 1159.000000 887.000000 1853.000000
|
|
[Debug] next-emb-step0: [2048] first4: 0.016646 -0.005029 -0.033803 -0.002747
|
|
[Debug] talker-hidden-step1: [2048] first4: -0.929883 -3.736696 0.872852 -1.414843
|
|
[Sample] step=1 c0=1014 u=-1.0000000000 subseq=16
|
|
[Sample-CP] g=0 c=780 u=-1.0000000000 subseq=17
|
|
[Sample-CP] g=1 c=1203 u=-1.0000000000 subseq=18
|
|
[Sample-CP] g=2 c=1315 u=-1.0000000000 subseq=19
|
|
[Sample-CP] g=3 c=77 u=-1.0000000000 subseq=20
|
|
[Sample-CP] g=4 c=111 u=-1.0000000000 subseq=21
|
|
[Sample-CP] g=5 c=267 u=-1.0000000000 subseq=22
|
|
[Sample-CP] g=6 c=592 u=-1.0000000000 subseq=23
|
|
[Sample-CP] g=7 c=1932 u=-1.0000000000 subseq=24
|
|
[Sample-CP] g=8 c=813 u=-1.0000000000 subseq=25
|
|
[Sample-CP] g=9 c=1506 u=-1.0000000000 subseq=26
|
|
[Sample-CP] g=10 c=547 u=-1.0000000000 subseq=27
|
|
[Sample-CP] g=11 c=2001 u=-1.0000000000 subseq=28
|
|
[Sample-CP] g=12 c=111 u=-1.0000000000 subseq=29
|
|
[Sample-CP] g=13 c=1942 u=-1.0000000000 subseq=30
|
|
[Sample-CP] g=14 c=1285 u=-1.0000000000 subseq=31
|
|
[Pipeline] Generated 8 frames
|
|
[Pipeline] Generated 16 frames
|
|
[Pipeline] Generated 24 frames
|
|
[Pipeline] Generated 32 frames
|
|
[Pipeline] Generated 40 frames
|
|
[Pipeline] Generated 48 frames
|
|
[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: 0.000014 0.000013 0.000006 0.000011
|
|
[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...
|
|
[Input] Lang: english Seed: 42 MaxNewTokens: 64
|
|
[Input] Mode: greedy
|
|
[Python] Device: cuda
|
|
[Python] InputIds shape: (1, 38)
|
|
[Python] Codes shape: (63, 16) (T_frames, num_code_groups)
|
|
[Python] Audio: 120960 samples 24000 Hz 5.04s -> python/base/base-python.wav
|
|
[Quant] Q4_K_M -> ../models/qwen-talker-1.7b-base-Q4_K_M.gguf + ../models/qwen-tokenizer-12hz-Q4_K_M.gguf
|
|
[GGML] Cmd: ../build/qwen-tts --model ../models/qwen-talker-1.7b-base-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. --lang english --max-new 64 --dump cpp/base -o cpp/base/base-cpp.wav --greedy
|
|
[GGML] Audio: 122880 samples 24000 Hz 5.12s -> cpp/base/base-cpp.wav
|
|
[Cossim] PromptIDs exact: 100.00% (38 values)
|
|
[Cossim] Embed cos: 0.999695 max: 1.0566e-02 mean: 9.6975e-04
|
|
[Cossim] TrailingText cos: 0.999969 max: 1.4858e-03 mean: 2.2947e-04
|
|
[Cossim] TTSPadEmbed cos: 0.999969 max: 1.4858e-03 mean: 2.2947e-04
|
|
[Cossim] L0 cos: 0.999279 max: 7.9302e-01 mean: 6.4647e-03
|
|
[Cossim] L7 cos: 0.997448 max: 4.1743e+01 mean: 5.8622e-01
|
|
[Cossim] L14 cos: 0.997441 max: 4.3301e+01 mean: 6.7443e-01
|
|
[Cossim] L21 cos: 0.997231 max: 4.2807e+01 mean: 1.0945e+00
|
|
[Cossim] L27 cos: 0.982530 max: 1.7326e+03 mean: 5.0100e+00
|
|
[Cossim] Final cos: 0.946231 max: 2.4114e+01 mean: 2.9488e-01
|
|
[Cossim] Logits cos: 0.976299 max: 3.4270e+00 mean: 7.1229e-01
|
|
[Cossim] NextEmbStep0 cos: 0.439674 max: 4.9057e-01 mean: 5.7374e-02
|
|
[Cossim] TalkerHiddenStep1 cos: 0.265089 max: 2.4202e+01 mean: 2.2974e+00
|
|
[Cossim] CodesFull exact: 0.20% (1008 values)
|
|
[Cossim] Audio cos: 0.274084
|
|
[Cossim] WAV stft_cos: 0.412402 samples: 120960
|