Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,26 @@
+---
+license: mit
+tags:
+  - audio
+  - voice
+  - onnx
+  - wavlm
+---
+
+# pbTrueVoiceLeveler ONNX models
+
+ONNX models for **pbTrueVoiceLeveler** (idempotent voice leveling).
+
+| file | content |
+|---|---|
+| `wavlm_base_plus.onnx` | WavLM Base+ 12-layer feature extractor. input `audio[B,N]` (16k, RMS-normalized) -> `layers[B,T,12,768]` |
+| `tension.onnx` | TensionNet: clip features -> target LUFS/dynrange + bounded 16-band residual |
+| `compressor.onnx` | CompressorNet: clip features -> (strength, thr_off) |
+| `trim.onnx` | TrimNet: frame features -> keep logit [B,T] |
+| `contour.onnx` | LoudnessContourNet: frame features -> relative loudness [B,T] |
+| `stats.json` | standardization stats + band centers (pre/post-processing) |
+
+All fp32, opset 17, dynamic batch/time axes. Numerically equivalent to the PyTorch originals
+(max abs diff < 1e-4 for nets, < 1e-3 for WavLM).
+
+WavLM Base+ original weights: Microsoft WavLM (MIT). This is an ONNX export for inference use.

compressor.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c47e8775dbe83f33c64b169e4245cd9563d14c360773e9dc4100cef1651e6e
+size 4128

contour.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc48b20f256fd5feeba983088d0fa1f7c810ed7f95699dc507f5612ad2326d22
+size 323527

stats.json

@@ -0,0 +1,201 @@
+{
+  "hand_mean": [
+    0.8247005939483643,
+    1.0876652002334595,
+    1.3980737924575806,
+    0.003092983039095998,
+    0.016998110339045525,
+    0.5430187582969666,
+    0.36897987127304077,
+    0.04390266165137291,
+    0.021645288914442062,
+    0.005342323333024979,
+    -10.406497955322266,
+    6.043864727020264,
+    0.7134523391723633,
+    0.5468224883079529,
+    18.207645416259766,
+    17.32281494140625
+  ],
+  "hand_std": [
+    0.43672510981559753,
+    0.6927884817123413,
+    1.577569842338562,
+    0.0030944424215704203,
+    0.034547824412584305,
+    0.22783923149108887,
+    0.23976890742778778,
+    0.05253620445728302,
+    0.04673965275287628,
+    0.01221376657485962,
+    2.648101329803467,
+    2.599325656890869,
+    0.36470016837120056,
+    0.10297990590333939,
+    2.1968021392822266,
+    2.201693296432495
+  ],
+  "tgt_mean": [
+    -28.275049209594727,
+    15.87100887298584,
+    16.849992752075195,
+    1.1245465278625488,
+    1.8059496879577637,
+    1.5384730100631714,
+    2.1794867515563965,
+    1.0911192893981934,
+    0.1668255478143692,
+    -0.3728558123111725,
+    -0.5393341183662415,
+    -0.4481179118156433,
+    -0.626317024230957,
+    -0.5533212423324585,
+    -1.257381796836853,
+    -1.4533828496932983,
+    -1.2536845207214355,
+    -1.0984221696853638,
+    -0.2648342549800873
+  ],
+  "tgt_std": [
+    2.976301908493042,
+    1.8337033987045288,
+    2.3204894065856934,
+    2.503650665283203,
+    2.658596992492676,
+    2.2184300422668457,
+    3.0965473651885986,
+    2.2954437732696533,
+    1.703050971031189,
+    1.7998127937316895,
+    2.5607945919036865,
+    2.648752450942993,
+    1.7743725776672363,
+    1.8354082107543945,
+    2.1120643615722656,
+    2.8958237171173096,
+    3.065124273300171,
+    2.741800546646118,
+    1.4787986278533936
+  ],
+  "contour_mean": 0.0,
+  "contour_std": 1.7811644077301025,
+  "band_centers": [
+    31.5,
+    50.0,
+    80.0,
+    125.0,
+    200.0,
+    315.0,
+    500.0,
+    800.0,
+    1250.0,
+    2000.0,
+    3150.0,
+    5000.0,
+    6300.0,
+    8000.0,
+    11000.0,
+    16000.0
+  ],
+  "meta": {
+    "artifact_layout_version": 5,
+    "model_name": "voiceleveler",
+    "source_pt_sha256": "d828bc0286dc846400ea85b2f45d560e91fc16454fcc8999c47e08db94014174",
+    "source_pt_size_bytes": 997894,
+    "generated_at_utc": "2026-09-16T05:14:46Z",
+    "onnx_sha256": {
+      "tension.onnx": "f97dc24954f7d2bb08d35654883010071ae1714a3fae80e3a9c2091f46d2e4b0",
+      "compressor.onnx": "d6c47e8775dbe83f33c64b169e4245cd9563d14c360773e9dc4100cef1651e6e",
+      "trim.onnx": "14225047b122debd331f93ab827fb275b7f127dd76a800282b6b4d1d89779222",
+      "contour.onnx": "cc48b20f256fd5feeba983088d0fa1f7c810ed7f95699dc507f5612ad2326d22"
+    },
+    "shared_wavlm_sha256": "64ce575658c0d50b8e9ce23390f9b2db731977ac8c3c8ace34ad7cce0e7ce0ea",
+    "shared_wavlm_provenance": "verified_training",
+    "n_handcraft_clip": 16,
+    "n_handcraft_frame": 10,
+    "wavlm_layers": 12,
+    "wavlm_dim": 768,
+    "n_targets": 19,
+    "n_bands": 16,
+    "opset": 17,
+    "tension_schema": "lufs_crest_dyn_residual_env_v4",
+    "spectral_mode": "residual",
+    "dynamics_projection": true,
+    "contour_runtime_projection": false,
+    "contour_conditioning": "wavlm_handcraft_peak_v2",
+    "compressor_schema": "soft_knee_downward_v2",
+    "dynamics_contour_schema": "residual_gain_v2",
+    "trim_schema": "soft_boundary_v2",
+    "clip_feature_schema": "hand16_relpitch_iqr_diffmad_v2",
+    "tension_arch_schema": "mlp_state_wav_bounded_v3",
+    "compressor_conditioning_schema": "tension_shape_hand_zerofloor_v2",
+    "tension_state_indices": [
+      0,
+      1,
+      2,
+      3,
+      4,
+      5,
+      6,
+      7,
+      8,
+      9,
+      10,
+      11,
+      12,
+      13,
+      14,
+      15
+    ],
+    "compressor_hand_indices": [
+      13,
+      14,
+      15
+    ],
+    "tension_state_shrink": 1.0,
+    "tension_state_ridge_lambda": 0.0,
+    "compressor_zero_floor": 0.05,
+    "frame_feature_schema": "frame10_peak_v2"
+  },
+  "training": {
+    "training_schema": 5,
+    "tension_schema": "lufs_crest_dyn_residual_env_v4",
+    "frame_feature_schema": "frame10_peak_v2",
+    "spectral_mode": "residual",
+    "dynamics_projection": true,
+    "contour_runtime_projection": false,
+    "contour_conditioning": "wavlm_handcraft_peak_v2",
+    "compressor_schema": "soft_knee_downward_v2",
+    "dynamics_contour_schema": "residual_gain_v2",
+    "trim_schema": "soft_boundary_v2",
+    "clip_feature_schema": "hand16_relpitch_iqr_diffmad_v2",
+    "tension_arch_schema": "mlp_state_wav_bounded_v3",
+    "tension_state_shrink": 1.0,
+    "tension_state_ridge_lambda": 0.0,
+    "compressor_conditioning_schema": "tension_shape_hand_zerofloor_v2",
+    "tension_state_indices": [
+      0,
+      1,
+      2,
+      3,
+      4,
+      5,
+      6,
+      7,
+      8,
+      9,
+      10,
+      11,
+      12,
+      13,
+      14,
+      15
+    ],
+    "compressor_hand_indices": [
+      13,
+      14,
+      15
+    ],
+    "compressor_zero_floor": 0.05
+  }
+}

tension.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f97dc24954f7d2bb08d35654883010071ae1714a3fae80e3a9c2091f46d2e4b0
+size 106692

trim.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14225047b122debd331f93ab827fb275b7f127dd76a800282b6b4d1d89779222
+size 483481

wavlm_base_plus.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64ce575658c0d50b8e9ce23390f9b2db731977ac8c3c8ace34ad7cce0e7ce0ea
+size 377837042