newonw

RVC20260718AMD_Intel.7z

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cdd7938a9be24566faf936da6092488ff18fb36539fe661172a70978cc76fb04
-size 5575283376

RVC20260718Nvidia.7z

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:278cd7db9c9e86e45b506d70959297b0c56802d6d79d6d6481b2b6b0f925be86
-size 7799405386

RVC20260718Nvidia50x0.7z

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:d258bc0cbcce07136f05781f04aafb6f5e02c593f88c8fe8c62a4ab683751467
-size 7606183207

RVCRealtime-Win64VST.zip

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:8ccc089bab82c3f73b131800a0134e5da9cc08acea1ad8243a9c3f9391933893
-size 1144352

hubert_base/config.json

@@ -1,72 +0,0 @@
-{
-  "activation_dropout": 0.0,
-  "apply_spec_augment": true,
-  "architectures": [
-    "HubertModelWithFinalProj"
-  ],
-  "attention_dropout": 0.1,
-  "bos_token_id": 1,
-  "classifier_proj_size": 256,
-  "conv_bias": false,
-  "conv_dim": [
-    512,
-    512,
-    512,
-    512,
-    512,
-    512,
-    512
-  ],
-  "conv_kernel": [
-    10,
-    3,
-    3,
-    3,
-    3,
-    2,
-    2
-  ],
-  "conv_pos_batch_norm": false,
-  "conv_stride": [
-    5,
-    2,
-    2,
-    2,
-    2,
-    2,
-    2
-  ],
-  "ctc_loss_reduction": "sum",
-  "ctc_zero_infinity": false,
-  "do_stable_layer_norm": false,
-  "eos_token_id": 2,
-  "feat_extract_activation": "gelu",
-  "feat_extract_norm": "group",
-  "feat_proj_dropout": 0.1,
-  "feat_proj_layer_norm": true,
-  "final_dropout": 0.1,
-  "hidden_act": "gelu",
-  "hidden_dropout": 0.1,
-  "hidden_size": 768,
-  "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-05,
-  "layerdrop": 0.05,
-  "mask_feature_length": 10,
-  "mask_feature_min_masks": 0,
-  "mask_feature_prob": 0.0,
-  "mask_time_length": 10,
-  "mask_time_min_masks": 2,
-  "mask_time_prob": 0.8,
-  "model_type": "hubert",
-  "num_attention_heads": 12,
-  "num_conv_pos_embedding_groups": 16,
-  "num_conv_pos_embeddings": 128,
-  "num_feat_extract_layers": 7,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "torch_dtype": "float16",
-  "transformers_version": "4.49.0",
-  "use_weighted_layer_sum": false,
-  "vocab_size": 32
-}

hubert_base/preprocessor_config.json

@@ -1,9 +0,0 @@
-{
-  "do_normalize": false,
-  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
-  "feature_size": 1,
-  "padding_side": "right",
-  "padding_value": 0.0,
-  "return_attention_mask": false,
-  "sampling_rate": 16000
-}

hubert_base/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cc8c20f4b90a520757260197a3ff2505705a7adbd20ad9eeaa4e1a9b38442ef5
-size 189206711

pymss_weights/config_mel_band_roformer_karaoke.yaml

@@ -1,71 +0,0 @@
-audio:
-  chunk_size: 352800
-  dim_f: 1024
-  dim_t: 256
-  hop_length: 441
-  n_fft: 2048
-  num_channels: 2
-  sample_rate: 44100
-  min_mean_abs: 000
-
-model:
-  dim: 384
-  depth: 6
-  stereo: true
-  num_stems: 1
-  time_transformer_depth: 1
-  freq_transformer_depth: 1
-  num_bands: 60
-  dim_head: 64
-  heads: 8
-  attn_dropout: 0
-  ff_dropout: 0
-  flash_attn: True
-  dim_freqs_in: 1025
-  sample_rate: 44100  # needed for mel filter bank from librosa
-  stft_n_fft: 2048
-  stft_hop_length: 441
-  stft_win_length: 2048
-  stft_normalized: False
-  mask_estimator_depth: 2
-  multi_stft_resolution_loss_weight: 1.0
-  multi_stft_resolutions_window_sizes: !!python/tuple
-  - 4096
-  - 2048
-  - 1024
-  - 512
-  - 256
-  multi_stft_hop_size: 147
-  multi_stft_normalized: False
-
-training:
-  batch_size: 4
-  gradient_accumulation_steps: 1
-  grad_clip: 0
-  instruments:
-  - karaoke
-  - other
-  lr: 1.0e-05
-  patience: 2
-  reduce_factor: 0.95
-  target_instrument: karaoke
-  num_epochs: 1000
-  num_steps: 2000
-  augmentation: false # enable augmentations by audiomentations and pedalboard
-  augmentation_type: null
-  use_mp3_compress: false # Deprecated
-  augmentation_mix: false # Mix several stems of the same type with some probability
-  augmentation_loudness: false # randomly change loudness of each stem
-  augmentation_loudness_type: 1 # Type 1 or 2
-  augmentation_loudness_min: 0
-  augmentation_loudness_max: 0
-  q: 0.95
-  coarse_loss_clip: false
-  ema_momentum: 0.999
-  optimizer: adam
-  other_fix: false # it's needed for checking on multisong dataset if other is actually instrumental
-
-inference:
-  batch_size: 1
-  dim_t: 256
-  num_overlap: 4

pymss_weights/dereverb_mel_band_roformer_anvuew.yaml

@@ -1,76 +0,0 @@
-audio:
-  chunk_size: 352800
-  dim_f: 1024
-  dim_t: 256
-  hop_length: 441
-  n_fft: 2048
-  num_channels: 2
-  sample_rate: 44100
-  min_mean_abs: 0.000
-
-model:
-  dim: 384
-  depth: 6
-  stereo: true
-  num_stems: 1
-  time_transformer_depth: 1
-  freq_transformer_depth: 1
-  num_bands: 60
-  dim_head: 64
-  heads: 8
-  attn_dropout: 0
-  ff_dropout: 0
-  flash_attn: True
-  dim_freqs_in: 1025
-  sample_rate: 44100  # needed for mel filter bank from librosa
-  stft_n_fft: 2048
-  stft_hop_length: 441
-  stft_win_length: 2048
-  stft_normalized: False
-  mask_estimator_depth: 2
-  multi_stft_resolution_loss_weight: 1.0
-  multi_stft_resolutions_window_sizes: !!python/tuple
-  - 4096
-  - 2048
-  - 1024
-  - 512
-  - 256
-  multi_stft_hop_size: 147
-  multi_stft_normalized: False
-
-training:
-  batch_size: 3
-  gradient_accumulation_steps: 1
-  grad_clip: 0
-  instruments:
-  - noreverb
-  - reverb
-  lr: 5.0e-05
-  patience: 2
-  reduce_factor: 0.95
-  target_instrument: noreverb
-  num_epochs: 1000
-  num_steps: 4000
-  q: 0.95
-  coarse_loss_clip: false
-  ema_momentum: 0.999
-  optimizer: adamw
-  other_fix: true # it's needed for checking on multisong dataset if other is actually instrumental
-  use_amp: true # enable or disable usage of mixed precision (float16) - usually it must be true
-
-augmentations:
-  enable: true # enable or disable all augmentations (to fast disable if needed)
-  loudness: true # randomly change loudness of each stem on the range (loudness_min; loudness_max)
-  loudness_min: 0.1
-  loudness_max: 1.0
-  mixup: false # mix several stems of same type with some probability (only works for dataset types: 1, 2, 3)
-  mixup_probs: !!python/tuple # 2 additional stems of the same type (1st with prob 0.2, 2nd with prob 0.02)
-    - 0.2
-    - 0.02
-  mixup_loudness_min: 0.5
-  mixup_loudness_max: 1.5
-
-inference:
-  batch_size: 1
-  dim_t: 801
-  num_overlap: 2

pymss_weights/dereverb_mel_band_roformer_anvuew_sdr_19.1729.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4fcbfc9d419abfd1f07a24f920d83f80d51727ca3cde3e9d84c99398418d35f3
-size 456706759

pymss_weights/dereverb_mel_band_roformer_less_aggressive_anvuew_sdr_18.8050.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:9399701da33d179e328a436e882fe2c79ae2f118a3d49603dbc7210bfeb428ea
-size 456754215

pymss_weights/model_bs_roformer_ep_317_sdr_12.9755.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:4deed31719b7b92195530a9d0e86ea1c8d5c4aa9f0e2dd967c1f05419ebf96d5
-size 319821424

pymss_weights/model_bs_roformer_ep_317_sdr_12.9755.yaml

@@ -1,123 +0,0 @@
-audio:
-  chunk_size: 352800
-  dim_f: 1024
-  dim_t: 801
-  hop_length: 441
-  min_mean_abs: 0.0
-  n_fft: 2048
-  num_channels: 2
-  sample_rate: 44100
-inference:
-  batch_size: 4
-  dim_t: 801
-  num_overlap: 2
-model:
-  attn_dropout: 0.1
-  depth: 12
-  dim: 512
-  dim_freqs_in: 1025
-  dim_head: 64
-  ff_dropout: 0.1
-  flash_attn: true
-  freq_transformer_depth: 1
-  freqs_per_bands: !!python/tuple
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 2
-  - 4
-  - 4
-  - 4
-  - 4
-  - 4
-  - 4
-  - 4
-  - 4
-  - 4
-  - 4
-  - 4
-  - 4
-  - 12
-  - 12
-  - 12
-  - 12
-  - 12
-  - 12
-  - 12
-  - 12
-  - 24
-  - 24
-  - 24
-  - 24
-  - 24
-  - 24
-  - 24
-  - 24
-  - 48
-  - 48
-  - 48
-  - 48
-  - 48
-  - 48
-  - 48
-  - 48
-  - 128
-  - 129
-  heads: 8
-  linear_transformer_depth: 0
-  mask_estimator_depth: 2
-  multi_stft_hop_size: 147
-  multi_stft_normalized: false
-  multi_stft_resolution_loss_weight: 1.0
-  multi_stft_resolutions_window_sizes: !!python/tuple
-  - 4096
-  - 2048
-  - 1024
-  - 512
-  - 256
-  num_stems: 1
-  stereo: true
-  stft_hop_length: 441
-  stft_n_fft: 2048
-  stft_normalized: false
-  stft_win_length: 2048
-  time_transformer_depth: 1
-training:
-  batch_size: 2
-  coarse_loss_clip: true
-  ema_momentum: 0.999
-  grad_clip: 0
-  gradient_accumulation_steps: 1
-  instruments:
-  - vocals
-  - other
-  lr: 1.0e-05
-  num_epochs: 1000
-  num_steps: 1000
-  optimizer: adam
-  other_fix: true
-  patience: 2
-  q: 0.95
-  reduce_factor: 0.95
-  target_instrument: vocals
-  use_amp: true

pymss_weights/model_bs_roformer_ep_368_sdr_12.9628.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:97c9e1011924ff647d147b474638c161b80586fd5b9e83fab59cbbb70014bf62
-size 319821424

pymss_weights/model_bs_roformer_ep_368_sdr_12.9628.yaml

@@ -1,133 +0,0 @@
-audio:
-  chunk_size: 352800
-  dim_f: 1024
-  dim_t: 801 # don't work (use in model)
-  hop_length: 441 # don't work (use in model)
-  n_fft: 2048
-  num_channels: 2
-  sample_rate: 44100
-  min_mean_abs: 0.001
-
-model:
-  dim: 512
-  depth: 12
-  stereo: true
-  num_stems: 1
-  time_transformer_depth: 1
-  freq_transformer_depth: 1
-  freqs_per_bands: !!python/tuple
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 2
-    - 4
-    - 4
-    - 4
-    - 4
-    - 4
-    - 4
-    - 4
-    - 4
-    - 4
-    - 4
-    - 4
-    - 4
-    - 12
-    - 12
-    - 12
-    - 12
-    - 12
-    - 12
-    - 12
-    - 12
-    - 24
-    - 24
-    - 24
-    - 24
-    - 24
-    - 24
-    - 24
-    - 24
-    - 48
-    - 48
-    - 48
-    - 48
-    - 48
-    - 48
-    - 48
-    - 48
-    - 128
-    - 129
-  dim_head: 64
-  heads: 8
-  attn_dropout: 0.1
-  ff_dropout: 0.1
-  flash_attn: true
-  dim_freqs_in: 1025
-  stft_n_fft: 2048
-  stft_hop_length: 441
-  stft_win_length: 2048
-  stft_normalized: false
-  mask_estimator_depth: 2
-  multi_stft_resolution_loss_weight: 1.0
-  multi_stft_resolutions_window_sizes: !!python/tuple
-  - 4096
-  - 2048
-  - 1024
-  - 512
-  - 256
-  multi_stft_hop_size: 147
-  multi_stft_normalized: False
-
-training:
-  batch_size: 16
-  gradient_accumulation_steps: 1
-  grad_clip: 0
-  instruments:
-  - vocals
-  - instrumental
-  lr: 5.0e-05
-  patience: 2
-  reduce_factor: 0.95
-  target_instrument: vocals
-  num_epochs: 1000
-  num_steps: 1000
-  augmentation: false # enable augmentations by audiomentations and pedalboard
-  augmentation_type: simple1
-  use_mp3_compress: false # Deprecated
-  augmentation_mix: true # Mix several stems of the same type with some probability
-  augmentation_loudness: true # randomly change loudness of each stem
-  augmentation_loudness_type: 1 # Type 1 or 2
-  augmentation_loudness_min: 0.5
-  augmentation_loudness_max: 1.5
-  q: 0.95
-  coarse_loss_clip: true
-  ema_momentum: 0.999
-  optimizer: adam
-  other_fix: false # it's needed for checking on multisong dataset if other is actually instrumental
-  use_amp: true # enable or disable usage of mixed precision (float16) - usually it must be true
-
-inference:
-  batch_size: 1
-  dim_t: 901
-  num_overlap: 4

pymss_weights/model_mel_band_roformer_karaoke_aufr33_viperx_sdr_10.1956.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:6603c56e16e85f0eab78d471e43341b789ddc654230b9bcc81a25a8d1457a8c1
-size 456715871