Add files using upload-large-folder tool

bandit/bandit_plus_config.yaml

@@ -0,0 +1,70 @@
+name: MultiMaskMultiSourceBandSplitRNN
+audio:
+  chunk_size: 264600
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.001
+model:
+  in_channel: 1
+  stems:
+    - speech
+    - music
+    - effects
+  band_specs: musical
+  n_bands: 64
+  fs: 44100
+  require_no_overlap: false
+  require_no_gap: true
+  normalize_channel_independently: false
+  treat_channel_as_feature: true
+  n_sqm_modules: 8
+  emb_dim: 128
+  rnn_dim: 256
+  bidirectional: true
+  rnn_type: GRU
+  mlp_dim: 512
+  hidden_activation: Tanh
+  hidden_activation_kwargs: null
+  complex_mask: true
+  n_fft: 2048
+  win_length: 2048
+  hop_length: 512
+  window_fn: hann_window
+  wkwargs: null
+  power: null
+  center: true
+  normalized: true
+  pad_mode: constant
+  onesided: true
+training:
+  batch_size: 4
+  gradient_accumulation_steps: 4
+  grad_clip: 0
+  instruments:
+    - speech
+    - music
+    - effects
+  lr: 9.0e-05
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 1000
+  num_steps: 1000
+  augmentation: false
+  augmentation_type: simple1
+  use_mp3_compress: false
+  augmentation_mix: true
+  augmentation_loudness: true
+  augmentation_loudness_type: 1
+  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: true
+  use_amp: true
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2

bandit_v2/bandit_v2_multi_config.yaml

@@ -0,0 +1,75 @@
+cls: Bandit
+audio:
+  chunk_size: 384000
+  num_channels: 2
+  sample_rate: 48000
+  min_mean_abs: 0.0
+kwargs:
+  in_channels: 1
+  stems:
+    - speech
+    - music
+    - sfx
+  band_type: musical
+  n_bands: 64
+  normalize_channel_independently: false
+  treat_channel_as_feature: true
+  n_sqm_modules: 8
+  emb_dim: 128
+  rnn_dim: 256
+  bidirectional: true
+  rnn_type: GRU
+  mlp_dim: 512
+  hidden_activation: Tanh
+  hidden_activation_kwargs: null
+  complex_mask: true
+  use_freq_weights: true
+  n_fft: 2048
+  win_length: 2048
+  hop_length: 512
+  window_fn: hann_window
+  wkwargs: null
+  power: null
+  center: true
+  normalized: true
+  pad_mode: reflect
+  onesided: true
+training:
+  batch_size: 4
+  gradient_accumulation_steps: 4
+  grad_clip: 0
+  instruments:
+    - speech
+    - music
+    - sfx
+  lr: 9.0e-05
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 1000
+  num_steps: 1000
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: adam
+  other_fix: true
+  use_amp: true
+augmentations:
+  enable: true
+  loudness: true
+  loudness_min: 0.5
+  loudness_max: 1.5
+  mixup: true
+  mixup_probs: !!python/tuple
+    - 0.2
+    - 0.02
+  mixup_loudness_min: 0.5
+  mixup_loudness_max: 1.5
+  all:
+    channel_shuffle: 0.5
+    random_inverse: 0.1
+    random_polarity: 0.5
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2

htdemucs/demucs3_mmi.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1941ce654b11df4132b9f4eae408556b4c83fad6fe26b4bc0dbcb36b975befb3
+size 167407275

htdemucs/demucs4_4stem.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8726e21a993978c7ba086d3872e7608d7d5bfca646ca4aca459ffda844faa8b4
+size 84141911

htdemucs/demucs4_6stem.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34c22ccb381c6f9fdbf324f04e1e2fe21aaaf293f5ded163a162697ff9a02ddd
+size 54996327

htdemucs/demucs4_choirsep.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd18ca3a8345c02b9656a0852193ddcbb1796188884e1b7119ce5758250bbcd
+size 109841648

htdemucs/demucs4_ft_bass.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e57c48e6b0e38af4f7118d7bd08c49f0a0c0edf7d09143bdd902ea0d237303e6
+size 84141271

htdemucs/demucs4_ft_drums.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba3fe64ae8ef66ac9a4857222ce48efbdc5eb3ad375cb79dd13debee5aaa4066
+size 84141271

htdemucs/demucs4_ft_other.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef3bcb9c8b40d14ae5d51b6db2587339cc12c6b77c0be151ce6d69002e087bf2
+size 84141271

htdemucs/demucs4_ft_vocals.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3cf25b222c4eed7cd49dd8b2c9597d50c18bd154090f7b919cfa5f93cf22c49
+size 84141271

htdemucs/demucs4_mvsep_vocals.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ea6e9495685045e6b4e66174131be5d19808bb0d6d1a1ba717d238f9380e8d0
+size 168124336

htdemucs/demucs_mid_side_wesleyr36.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9970dca36a15c0d0cf3338d24592aa35469697dc3be4b07e9056f5d54b82185
+size 168122809

mdx23c/mdx23c_4stem_zfturbo_config.yaml

@@ -0,0 +1,54 @@
+audio:
+  chunk_size: 261120
+  dim_f: 4096
+  dim_t: 256
+  hop_length: 1024
+  n_fft: 8192
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.001
+model:
+  act: gelu
+  bottleneck_factor: 4
+  growth: 128
+  norm: InstanceNorm
+  num_blocks_per_scale: 2
+  num_channels: 128
+  num_scales: 5
+  num_subbands: 4
+  scale:
+    - 2
+    - 2
+training:
+  batch_size: 6
+  gradient_accumulation_steps: 6
+  grad_clip: 0
+  instruments:
+    - vocals
+    - bass
+    - drums
+    - other
+  lr: 5.0e-05
+  patience: 3
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 1000
+  num_steps: 1000
+  augmentation: false
+  augmentation_type: simple1
+  use_mp3_compress: false
+  augmentation_mix: true
+  augmentation_loudness: true
+  augmentation_loudness_type: 2
+  augmentation_loudness_min: 0.8
+  augmentation_loudness_max: 1.2
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: adam
+  other_fix: false
+  use_amp: true
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2

mdx23c/mdx23c_d1581_config.yaml

@@ -0,0 +1,37 @@
+audio:
+  chunk_size: 260096
+  dim_f: 4096
+  dim_t: 256
+  hop_length: 2048
+  n_fft: 12288
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.001
+model:
+  act: gelu
+  bottleneck_factor: 4
+  growth: 64
+  norm: InstanceNorm
+  num_blocks_per_scale: 2
+  num_channels: 128
+  num_scales: 5
+  num_subbands: 4
+  scale:
+    - 2
+    - 2
+  name: epoch_10.ckpt
+training:
+  batch_size: 16
+  grad_clip: 0
+  instruments:
+    - Vocals
+    - Instrumental
+  lr: 5.0e-05
+  target_instrument: null
+  num_epochs: 100
+  num_steps: 1000
+  use_amp: true
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2

mdx23c/mdx23c_dereverb_aufr33_jarredou_config.yaml

@@ -0,0 +1,114 @@
+audio:
+  chunk_size: 261120
+  dim_f: 4096
+  dim_t: 256
+  hop_length: 1024
+  n_fft: 8192
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.001
+model:
+  act: gelu
+  bottleneck_factor: 4
+  growth: 128
+  norm: InstanceNorm
+  num_blocks_per_scale: 2
+  num_channels: 128
+  num_scales: 5
+  num_subbands: 4
+  scale:
+    - 2
+    - 2
+training:
+  batch_size: 2
+  gradient_accumulation_steps: 1
+  grad_clip: 0
+  instruments:
+    - dry
+    - other
+  lr: 1.0e-06
+  patience: 4
+  reduce_factor: 0.93
+  target_instrument: null
+  num_epochs: 40
+  num_steps: 1000
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: adamw
+  read_metadata_procs: 8
+  other_fix: false
+  use_amp: true
+augmentations:
+  enable: false
+  loudness: true
+  loudness_min: 0.5
+  loudness_max: 1.5
+  mixup: true
+  mixup_probs: !!python/tuple
+    - 0.2
+    - 0.02
+  mixup_loudness_min: 0.5
+  mixup_loudness_max: 1.5
+  all:
+    channel_shuffle: 0.5
+    random_inverse: 0.05
+    random_polarity: 0.5
+    pedalboard_chorus: 0.001
+    pedalboard_chorus_rate_hz_min: 1.0
+    pedalboard_chorus_rate_hz_max: 7.0
+    pedalboard_chorus_depth_min: 0.25
+    pedalboard_chorus_depth_max: 0.95
+    pedalboard_chorus_centre_delay_ms_min: 3
+    pedalboard_chorus_centre_delay_ms_max: 10
+    pedalboard_chorus_feedback_min: 0.0
+    pedalboard_chorus_feedback_max: 0.01
+    pedalboard_chorus_mix_min: 0.1
+    pedalboard_chorus_mix_max: 0.9
+    pedalboard_phazer: 0.001
+    pedalboard_phazer_rate_hz_min: 1.0
+    pedalboard_phazer_rate_hz_max: 10.0
+    pedalboard_phazer_depth_min: 0.25
+    pedalboard_phazer_depth_max: 0.95
+    pedalboard_phazer_centre_frequency_hz_min: 200
+    pedalboard_phazer_centre_frequency_hz_max: 12000
+    pedalboard_phazer_feedback_min: 0.0
+    pedalboard_phazer_feedback_max: 0.5
+    pedalboard_phazer_mix_min: 0.1
+    pedalboard_phazer_mix_max: 0.9
+    pedalboard_pitch_shift: 0.01
+    pedalboard_pitch_shift_semitones_min: -7
+    pedalboard_pitch_shift_semitones_max: 7
+    pedalboard_resample: 0.001
+    pedalboard_resample_target_sample_rate_min: 4000
+    pedalboard_resample_target_sample_rate_max: 44100
+    mp3_compression_min_bitrate: 32
+    mp3_compression_max_bitrate: 320
+    mp3_compression_backend: lameenc
+  dry:
+    pedalboard_distortion: 0.001
+    pedalboard_distortion_drive_db_min: 1.0
+    pedalboard_distortion_drive_db_max: 25.0
+    tanh_distortion: 0.05
+    tanh_distortion_min: 0.1
+    tanh_distortion_max: 0.7
+    pedalboard_bitcrash: 0.005
+    pedalboard_bitcrash_bit_depth_min: 4
+    pedalboard_bitcrash_bit_depth_max: 16
+    seven_band_parametric_eq: 0.24
+    seven_band_parametric_eq_min_gain_db: -9
+    seven_band_parametric_eq_max_gain_db: 9
+    gaussian_noise: 0.005
+    gaussian_noise_min_amplitude: 0.001
+    gaussian_noise_max_amplitude: 0.01
+    time_stretch: 0.01
+    time_stretch_min_rate: 0.8
+    time_stretch_max_rate: 1.25
+  other:
+    seven_band_parametric_eq: 0.24
+    seven_band_parametric_eq_min_gain_db: -9
+    seven_band_parametric_eq_max_gain_db: 9
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2

mdx23c/mdx23c_drumsep_6stem_aufr33_jarredou_config.yaml

@@ -0,0 +1,80 @@
+audio:
+  chunk_size: 130560
+  dim_f: 1024
+  dim_t: 256
+  hop_length: 512
+  n_fft: 2048
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.001
+model:
+  act: gelu
+  bottleneck_factor: 4
+  growth: 128
+  norm: InstanceNorm
+  num_blocks_per_scale: 2
+  num_channels: 128
+  num_scales: 5
+  num_subbands: 4
+  scale:
+    - 2
+    - 2
+training:
+  batch_size: 12
+  gradient_accumulation_steps: 1
+  grad_clip: 0
+  instruments:
+    - kick
+    - snare
+    - toms
+    - hh
+    - ride
+    - crash
+  lr: 9.0e-05
+  patience: 30
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 1000
+  num_steps: 1268
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: adam
+  other_fix: false
+  use_amp: true
+augmentations:
+  enable: true
+  loudness: true
+  loudness_min: 0.5
+  loudness_max: 1.5
+  mixup: true
+  mixup_probs: !!python/tuple
+    - 0.2
+    - 0.02
+  mixup_loudness_min: 0.5
+  mixup_loudness_max: 1.5
+  mp3_compression_on_mixture: 0.0
+  mp3_compression_on_mixture_bitrate_min: 32
+  mp3_compression_on_mixture_bitrate_max: 320
+  mp3_compression_on_mixture_backend: lameenc
+  all:
+    channel_shuffle: 0.5
+    random_inverse: 0.01
+    random_polarity: 0.5
+    mp3_compression: 0.0
+    mp3_compression_min_bitrate: 32
+    mp3_compression_max_bitrate: 320
+    mp3_compression_backend: lameenc
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -3
+    pitch_shift_max_semitones: 3
+    seven_band_parametric_eq: 0.5
+    seven_band_parametric_eq_min_gain_db: -6
+    seven_band_parametric_eq_max_gain_db: 6
+    tanh_distortion: 0.2
+    tanh_distortion_min: 0.1
+    tanh_distortion_max: 0.5
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2

mdx23c/mdx23c_instvoc_hq1_config.yaml

@@ -0,0 +1,44 @@
+audio:
+  chunk_size: 261120
+  dim_f: 4096
+  dim_t: 256
+  hop_length: 1024
+  n_fft: 8192
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.001
+model:
+  act: gelu
+  bottleneck_factor: 4
+  growth: 128
+  norm: InstanceNorm
+  num_blocks_per_scale: 2
+  num_channels: 128
+  num_scales: 5
+  num_subbands: 4
+  scale:
+    - 2
+    - 2
+training:
+  batch_size: 6
+  grad_clip: 0
+  instruments:
+    - Vocals
+    - Instrumental
+  lr: 1.0e-05
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 1000
+  num_steps: 1000
+  augmentation: 1
+  augmentation_type: simple1
+  augmentation_mix: true
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  use_amp: true
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2

mdx23c/mdx23c_instvoc_hq2_config.yaml

@@ -0,0 +1,44 @@
+audio:
+  chunk_size: 261120
+  dim_f: 4096
+  dim_t: 256
+  hop_length: 1024
+  n_fft: 8192
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.001
+model:
+  act: gelu
+  bottleneck_factor: 4
+  growth: 128
+  norm: InstanceNorm
+  num_blocks_per_scale: 2
+  num_channels: 128
+  num_scales: 5
+  num_subbands: 4
+  scale:
+    - 2
+    - 2
+training:
+  batch_size: 6
+  grad_clip: 0
+  instruments:
+    - Vocals
+    - Instrumental
+  lr: 1.0e-05
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 1000
+  num_steps: 1000
+  augmentation: 1
+  augmentation_type: simple1
+  augmentation_mix: true
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  use_amp: true
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2

mdx23c/mdx23c_instvoc_zfturbo_config.yaml

@@ -0,0 +1,88 @@
+audio:
+  chunk_size: 261120
+  dim_f: 4096
+  dim_t: 256
+  hop_length: 1024
+  n_fft: 8192
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.001
+model:
+  act: gelu
+  bottleneck_factor: 4
+  growth: 128
+  norm: InstanceNorm
+  num_blocks_per_scale: 2
+  num_channels: 128
+  num_scales: 5
+  num_subbands: 4
+  scale:
+    - 2
+    - 2
+training:
+  batch_size: 6
+  gradient_accumulation_steps: 1
+  grad_clip: 0
+  instruments:
+    - vocals
+    - other
+  lr: 9.0e-05
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 1000
+  num_steps: 1000
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: adam
+  read_metadata_procs: 8
+  other_fix: true
+  use_amp: true
+augmentations:
+  enable: true
+  loudness: true
+  loudness_min: 0.5
+  loudness_max: 1.5
+  mixup: true
+  mixup_probs: !!python/tuple
+    - 0.2
+    - 0.02
+  mixup_loudness_min: 0.5
+  mixup_loudness_max: 1.5
+  mp3_compression_on_mixture: 0.01
+  mp3_compression_on_mixture_bitrate_min: 32
+  mp3_compression_on_mixture_bitrate_max: 320
+  mp3_compression_on_mixture_backend: lameenc
+  all:
+    channel_shuffle: 0.5
+    random_inverse: 0.1
+    random_polarity: 0.5
+    mp3_compression: 0.01
+    mp3_compression_min_bitrate: 32
+    mp3_compression_max_bitrate: 320
+    mp3_compression_backend: lameenc
+  vocals:
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -5
+    pitch_shift_max_semitones: 5
+    seven_band_parametric_eq: 0.25
+    seven_band_parametric_eq_min_gain_db: -9
+    seven_band_parametric_eq_max_gain_db: 9
+    tanh_distortion: 0.1
+    tanh_distortion_min: 0.1
+    tanh_distortion_max: 0.7
+  other:
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -4
+    pitch_shift_max_semitones: 4
+    gaussian_noise: 0.1
+    gaussian_noise_min_amplitude: 0.001
+    gaussian_noise_max_amplitude: 0.015
+    time_stretch: 0.01
+    time_stretch_min_rate: 0.8
+    time_stretch_max_rate: 1.25
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2

mdx23c/mdx23c_mid_side_wesleyr36_config.yaml

@@ -0,0 +1,82 @@
+audio:
+  chunk_size: 130560
+  dim_f: 1024
+  dim_t: 256
+  hop_length: 512
+  n_fft: 2048
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.001
+model:
+  act: gelu
+  bottleneck_factor: 4
+  growth: 128
+  norm: InstanceNorm
+  num_blocks_per_scale: 2
+  num_channels: 128
+  num_scales: 5
+  num_subbands: 4
+  scale:
+    - 2
+    - 2
+training:
+  batch_size: 2
+  gradient_accumulation_steps: 3
+  grad_clip: 0
+  instruments:
+    - similarity
+    - difference
+  lr: 1.0
+  patience: 15
+  reduce_factor: 0.95
+  target_instrument: similarity
+  num_epochs: 1000
+  num_steps: 2235
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: prodigy
+  other_fix: false
+  use_amp: true
+augmentations:
+  enable: true
+  loudness: true
+  loudness_min: 0.5
+  loudness_max: 1.5
+  all:
+    channel_shuffle: 0.5
+    random_inverse: 0.01
+    random_polarity: 0.5
+    mp3_compression: 0.0
+    mp3_compression_min_bitrate: 32
+    mp3_compression_max_bitrate: 320
+    mp3_compression_backend: lameenc
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -3
+    pitch_shift_max_semitones: 3
+    seven_band_parametric_eq: 0.5
+    seven_band_parametric_eq_min_gain_db: -6
+    seven_band_parametric_eq_max_gain_db: 6
+    tanh_distortion: 0.2
+    tanh_distortion_min: 0.1
+    tanh_distortion_max: 0.5
+similarity:
+  gaussian_noise: 0.1
+  gaussian_noise_min_amplitude: 0.001
+  gaussian_noise_max_amplitude: 0.015
+difference:
+  pedalboard_reverb: 0.01
+  pedalboard_reverb_room_size_min: 0.1
+  pedalboard_reverb_room_size_max: 0.9
+  pedalboard_reverb_damping_min: 0.1
+  pedalboard_reverb_damping_max: 0.9
+  pedalboard_reverb_wet_level_min: 0.1
+  pedalboard_reverb_wet_level_max: 0.5
+  pedalboard_reverb_dry_level_min: 0.5
+  pedalboard_reverb_dry_level_max: 0.9
+  pedalboard_reverb_width_min: 0.3
+  pedalboard_reverb_width_max: 1.0
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2

mdx23c/mdx23c_orch_verosment_config.yaml

@@ -0,0 +1,93 @@
+audio:
+  chunk_size: 261120
+  dim_f: 4096
+  dim_t: 256
+  hop_length: 1024
+  n_fft: 8192
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.001
+model:
+  act: gelu
+  bottleneck_factor: 4
+  growth: 128
+  norm: InstanceNorm
+  num_blocks_per_scale: 2
+  num_channels: 128
+  num_scales: 5
+  num_subbands: 4
+  scale:
+    - 2
+    - 2
+training:
+  batch_size: 1
+  gradient_accumulation_steps: 3
+  grad_clip: 0
+  instruments:
+    - inst
+    - orch
+  lr: 9.0e-05
+  patience: 6
+  reduce_factor: 0.95
+  target_instrument: orch
+  num_epochs: 1000
+  num_steps: 750
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: adam
+  other_fix: true
+  use_amp: true
+augmentations:
+  enable: true
+  loudness: true
+  loudness_min: 0.5
+  loudness_max: 1.5
+  mixup: true
+  mixup_probs:
+    - 0.4
+    - 0.02
+  mixup_loudness_min: 0.5
+  mixup_loudness_max: 1.5
+  mp3_compression_on_mixture: 0.01
+  mp3_compression_on_mixture_bitrate_min: 32
+  mp3_compression_on_mixture_bitrate_max: 320
+  mp3_compression_on_mixture_backend: lameenc
+  all:
+    channel_shuffle: 0.5
+    random_inverse: 0.1
+    random_polarity: 0.5
+    mp3_compression: 0.01
+    mp3_compression_min_bitrate: 32
+    mp3_compression_max_bitrate: 320
+    mp3_compression_backend: lameenc
+  orch:
+    pitch_shift: 0.25
+    pitch_shift_min_semitones: -5
+    pitch_shift_max_semitones: 5
+    seven_band_parametric_eq: 1
+    seven_band_parametric_eq_min_gain_db: -6
+    seven_band_parametric_eq_max_gain_db: 6
+    tanh_distortion: 0.5
+    tanh_distortion_min: 0.05
+    tanh_distortion_max: 0.6
+  inst:
+    pitch_shift: 0.25
+    pitch_shift_min_semitones: -5
+    pitch_shift_max_semitones: 5
+    gaussian_noise: 0.1
+    gaussian_noise_min_amplitude: 0.001
+    gaussian_noise_max_amplitude: 0.015
+    time_stretch: 0.01
+    time_stretch_min_rate: 0.8
+    time_stretch_max_rate: 1.25
+    seven_band_parametric_eq: 1
+    seven_band_parametric_eq_min_gain_db: -6
+    seven_band_parametric_eq_max_gain_db: 6
+    tanh_distortion: 0.5
+    tanh_distortion_min: 0.05
+    tanh_distortion_max: 0.6
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2

mdxnet/mdx_inst_hq1.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38a045c4ded87e3bf97b609ec5be7910e8a7cecec455f507227ab12b5e29f7f9
+size 66759214

mdxnet/mdx_inst_hq5.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:811cb24095d865763752310848b7ec86aeede0626cb05749ab35350e46897000
+size 59074342

mdxnet/mdx_kim_inst.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86b1940e7122fbdd2beadc65507cbff6c352d79012a8a7e60d56db98532af5f7
+size 66759214

mdxnet/mdx_kuielab_a_drums.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40f586b7091934dd6f5563f0cba8f14bad57ce88440da1098bf388ea716c2901
+size 29703204

mdxnet/mdx_kuielab_a_other.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b67a1dcb5f232153528c59960b4c7bf8dc736b8114de360af0e719633f53358
+size 29703204

mdxnet/mdx_kuielab_a_vocals.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daba83c2ee1afee9139766ad64c9b6808d6b6f092fff04bed3338be50baac721
+size 29703204

mdxnet/mdx_main_390.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:286c4f0847ca837e2c3f4c4058f756d5f150cbf080506aa6f33a2847aba92e8c
+size 66759214

mdxnet/mdx_main_406.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f158816a44eef1f0ba0f48b813cbfcf460ed1c70a754af3609ade44aaf7d1b23
+size 66759214

scnet/scnet_4stem_zfturbo_config.yaml

@@ -0,0 +1,82 @@
+audio:
+  chunk_size: 485100
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.0
+model:
+  sources:
+    - drums
+    - bass
+    - other
+    - vocals
+  audio_channels: 2
+  dims:
+    - 4
+    - 64
+    - 128
+    - 256
+  nfft: 4096
+  hop_size: 1024
+  win_size: 4096
+  normalized: true
+  band_SR:
+    - 0.225
+    - 0.372
+    - 0.403
+  band_stride:
+    - 1
+    - 4
+    - 16
+  band_kernel:
+    - 3
+    - 4
+    - 16
+  conv_depths:
+    - 3
+    - 2
+    - 1
+  compress: 4
+  conv_kernel: 3
+  num_dplayer: 6
+  expand: 1
+training:
+  batch_size: 6
+  gradient_accumulation_steps: 1
+  grad_clip: 0
+  instruments:
+    - drums
+    - bass
+    - other
+    - vocals
+  lr: 1.0
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 1000
+  num_steps: 1000
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: prodigy
+  other_fix: false
+  use_amp: true
+augmentations:
+  enable: true
+  loudness: true
+  loudness_min: 0.5
+  loudness_max: 1.5
+  mixup: true
+  mixup_probs: !!python/tuple
+    - 0.2
+    - 0.02
+  mixup_loudness_min: 0.5
+  mixup_loudness_max: 1.5
+  all:
+    channel_shuffle: 0.5
+    random_inverse: 0.1
+    random_polarity: 0.5
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2
+  normalize: true

scnet/scnet_choirsep_exp_config.yaml

@@ -0,0 +1,101 @@
+audio:
+  chunk_size: 131072
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.0
+model:
+  sources:
+    - alto
+    - bass
+    - soprano
+    - tenor
+  audio_channels: 2
+  dims:
+    - 4
+    - 32
+    - 64
+    - 128
+  nfft: 4096
+  hop_size: 1024
+  win_size: 4096
+  normalized: true
+  band_SR:
+    - 0.175
+    - 0.392
+    - 0.433
+  band_stride:
+    - 1
+    - 4
+    - 16
+  band_kernel:
+    - 3
+    - 4
+    - 16
+  conv_depths:
+    - 3
+    - 2
+    - 1
+  compress: 4
+  conv_kernel: 3
+  num_dplayer: 6
+  expand: 1
+training:
+  batch_size: 9
+  gradient_accumulation_steps: 1
+  grad_clip: 0
+  instruments:
+    - alto
+    - bass
+    - soprano
+    - tenor
+  lr: 0.0005
+  patience: 6
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 1000
+  num_steps: 1000
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: adamw8bit
+  other_fix: false
+  use_amp: true
+loss_multistft:
+  fft_sizes:
+    - 1024
+    - 2048
+    - 4096
+  hop_sizes:
+    - 512
+    - 1024
+    - 2048
+  win_lengths:
+    - 1024
+    - 2048
+    - 4096
+  window: hann_window
+  scale: mel
+  n_bins: 128
+  sample_rate: 44100
+  perceptual_weighting: true
+  w_sc: 1.0
+  w_log_mag: 1.0
+  w_lin_mag: 0.0
+  w_phs: 0.0
+  mag_distance: L1
+augmentations:
+  enable: false
+  loudness: true
+  loudness_min: 0.5
+  loudness_max: 1.5
+  mixup: false
+  mixup_probs: !!python/tuple
+    - 0.2
+    - 0.02
+  mixup_loudness_min: 0.5
+  mixup_loudness_max: 1.5
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2
+  normalize: false

scnet/scnet_huge_4stem_aname_config.yaml

@@ -0,0 +1,67 @@
+audio:
+  chunk_size: 661500
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.0
+model:
+  sources:
+    - drums
+    - bass
+    - other
+    - vocals
+  audio_channels: 2
+  dims:
+    - 4
+    - 64
+    - 128
+    - 256
+  nfft: 4096
+  hop_size: 1024
+  win_size: 4096
+  normalized: true
+  band_SR:
+    - 0.23
+    - 0.37
+    - 0.4
+  band_stride:
+    - 1
+    - 4
+    - 4
+  band_kernel:
+    - 3
+    - 4
+    - 4
+  conv_depths:
+    - 3
+    - 3
+    - 3
+  compress: 4
+  conv_kernel: 3
+  num_dplayer: 10
+  expand: 1
+training:
+  batch_size: 1
+  gradient_accumulation_steps: 1
+  grad_clip: 0
+  instruments:
+    - drums
+    - bass
+    - other
+    - vocals
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 1000
+  num_steps: 1000
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: adam
+  lr: 1.0
+  normalize: false
+  other_fix: false
+  use_amp: true
+inference:
+  batch_size: 1
+  dim_t: 1101
+  num_overlap: 2

scnet/scnet_jazz_4stem_jorisvaneyghen_config.yaml

@@ -0,0 +1,82 @@
+audio:
+  chunk_size: 485100
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.0
+model:
+  sources:
+    - drums
+    - bass
+    - piano
+    - other
+  audio_channels: 2
+  dims:
+    - 4
+    - 64
+    - 128
+    - 256
+  nfft: 4096
+  hop_size: 1024
+  win_size: 4096
+  normalized: true
+  band_SR:
+    - 0.225
+    - 0.372
+    - 0.403
+  band_stride:
+    - 1
+    - 4
+    - 16
+  band_kernel:
+    - 3
+    - 4
+    - 16
+  conv_depths:
+    - 3
+    - 2
+    - 1
+  compress: 4
+  conv_kernel: 3
+  num_dplayer: 6
+  expand: 1
+training:
+  batch_size: 1
+  gradient_accumulation_steps: 3
+  grad_clip: 0
+  instruments:
+    - drums
+    - bass
+    - piano
+    - other
+  lr: 5.0e-05
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 1000
+  num_steps: 500
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: adam
+  other_fix: false
+  use_amp: true
+augmentations:
+  enable: true
+  loudness: true
+  loudness_min: 0.5
+  loudness_max: 1.5
+  mixup: true
+  mixup_probs: !!python/tuple
+    - 0.2
+    - 0.02
+  mixup_loudness_min: 0.5
+  mixup_loudness_max: 1.5
+  all:
+    channel_shuffle: 0.5
+    random_inverse: 0.1
+    random_polarity: 0.5
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2
+  normalize: false

scnet/scnet_xl_4stem_starrytong_config.yaml

@@ -0,0 +1,179 @@
+audio:
+  chunk_size: 485100
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.0
+model:
+  sources:
+    - drums
+    - bass
+    - other
+    - vocals
+  audio_channels: 2
+  dims:
+    - 4
+    - 64
+    - 128
+    - 256
+  nfft: 4096
+  hop_size: 1024
+  win_size: 4096
+  normalized: true
+  band_SR:
+    - 0.23
+    - 0.37
+    - 0.4
+  band_stride:
+    - 1
+    - 4
+    - 16
+  band_kernel:
+    - 3
+    - 4
+    - 16
+  conv_depths:
+    - 3
+    - 2
+    - 1
+  compress: 4
+  conv_kernel: 3
+  num_dplayer: 8
+  expand: 1
+training:
+  batch_size: 4
+  gradient_accumulation_steps: 1
+  grad_clip: 0
+  instruments:
+    - drums
+    - bass
+    - other
+    - vocals
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 1000
+  num_steps: 1000
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: adam
+  lr: 1.0e-05
+  normalize: false
+  other_fix: false
+  use_amp: true
+augmentations:
+  enable: false
+  loudness: true
+  loudness_min: 0.5
+  loudness_max: 1.5
+  mixup: true
+  mixup_probs: !!python/tuple
+    - 0.2
+    - 0.02
+  mixup_loudness_min: 0.5
+  mixup_loudness_max: 1.5
+  mp3_compression_on_mixture: 0.01
+  mp3_compression_on_mixture_bitrate_min: 32
+  mp3_compression_on_mixture_bitrate_max: 320
+  mp3_compression_on_mixture_backend: lameenc
+  all:
+    channel_shuffle: 0.5
+    random_inverse: 0.1
+    random_polarity: 0.5
+    mp3_compression: 0.01
+    mp3_compression_min_bitrate: 32
+    mp3_compression_max_bitrate: 320
+    mp3_compression_backend: lameenc
+    pedalboard_reverb: 0.01
+    pedalboard_reverb_room_size_min: 0.1
+    pedalboard_reverb_room_size_max: 0.9
+    pedalboard_reverb_damping_min: 0.1
+    pedalboard_reverb_damping_max: 0.9
+    pedalboard_reverb_wet_level_min: 0.1
+    pedalboard_reverb_wet_level_max: 0.9
+    pedalboard_reverb_dry_level_min: 0.1
+    pedalboard_reverb_dry_level_max: 0.9
+    pedalboard_reverb_width_min: 0.9
+    pedalboard_reverb_width_max: 1.0
+    pedalboard_chorus: 0.01
+    pedalboard_chorus_rate_hz_min: 1.0
+    pedalboard_chorus_rate_hz_max: 7.0
+    pedalboard_chorus_depth_min: 0.25
+    pedalboard_chorus_depth_max: 0.95
+    pedalboard_chorus_centre_delay_ms_min: 3
+    pedalboard_chorus_centre_delay_ms_max: 10
+    pedalboard_chorus_feedback_min: 0.0
+    pedalboard_chorus_feedback_max: 0.5
+    pedalboard_chorus_mix_min: 0.1
+    pedalboard_chorus_mix_max: 0.9
+    pedalboard_phazer: 0.01
+    pedalboard_phazer_rate_hz_min: 1.0
+    pedalboard_phazer_rate_hz_max: 10.0
+    pedalboard_phazer_depth_min: 0.25
+    pedalboard_phazer_depth_max: 0.95
+    pedalboard_phazer_centre_frequency_hz_min: 200
+    pedalboard_phazer_centre_frequency_hz_max: 12000
+    pedalboard_phazer_feedback_min: 0.0
+    pedalboard_phazer_feedback_max: 0.5
+    pedalboard_phazer_mix_min: 0.1
+    pedalboard_phazer_mix_max: 0.9
+    pedalboard_distortion: 0.01
+    pedalboard_distortion_drive_db_min: 1.0
+    pedalboard_distortion_drive_db_max: 25.0
+    pedalboard_pitch_shift: 0.01
+    pedalboard_pitch_shift_semitones_min: -7
+    pedalboard_pitch_shift_semitones_max: 7
+    pedalboard_resample: 0.01
+    pedalboard_resample_target_sample_rate_min: 4000
+    pedalboard_resample_target_sample_rate_max: 44100
+    pedalboard_bitcrash: 0.01
+    pedalboard_bitcrash_bit_depth_min: 4
+    pedalboard_bitcrash_bit_depth_max: 16
+    pedalboard_mp3_compressor: 0.01
+    pedalboard_mp3_compressor_pedalboard_mp3_compressor_min: 0
+    pedalboard_mp3_compressor_pedalboard_mp3_compressor_max: 9.999
+  vocals:
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -5
+    pitch_shift_max_semitones: 5
+    seven_band_parametric_eq: 0.25
+    seven_band_parametric_eq_min_gain_db: -9
+    seven_band_parametric_eq_max_gain_db: 9
+    tanh_distortion: 0.1
+    tanh_distortion_min: 0.1
+    tanh_distortion_max: 0.7
+  bass:
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -2
+    pitch_shift_max_semitones: 2
+    seven_band_parametric_eq: 0.25
+    seven_band_parametric_eq_min_gain_db: -3
+    seven_band_parametric_eq_max_gain_db: 6
+    tanh_distortion: 0.2
+    tanh_distortion_min: 0.1
+    tanh_distortion_max: 0.5
+  drums:
+    pitch_shift: 0.33
+    pitch_shift_min_semitones: -5
+    pitch_shift_max_semitones: 5
+    seven_band_parametric_eq: 0.25
+    seven_band_parametric_eq_min_gain_db: -9
+    seven_band_parametric_eq_max_gain_db: 9
+    tanh_distortion: 0.33
+    tanh_distortion_min: 0.1
+    tanh_distortion_max: 0.6
+  other:
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -4
+    pitch_shift_max_semitones: 4
+    gaussian_noise: 0.1
+    gaussian_noise_min_amplitude: 0.001
+    gaussian_noise_max_amplitude: 0.015
+    time_stretch: 0.01
+    time_stretch_min_rate: 0.8
+    time_stretch_max_rate: 1.25
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2
+  normalize: false

scnet/scnet_xl_4stem_zftrubo_config.yaml

@@ -0,0 +1,78 @@
+audio:
+  chunk_size: 485100
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.0
+model:
+  sources:
+    - drums
+    - bass
+    - other
+    - vocals
+  audio_channels: 2
+  dims:
+    - 4
+    - 32
+    - 64
+    - 128
+  nfft: 4096
+  hop_size: 1024
+  win_size: 4096
+  normalized: true
+  band_SR:
+    - 0.175
+    - 0.392
+    - 0.433
+  band_stride:
+    - 1
+    - 4
+    - 16
+  band_kernel:
+    - 3
+    - 4
+    - 16
+  conv_depths:
+    - 3
+    - 2
+    - 1
+  compress: 4
+  conv_kernel: 3
+  num_dplayer: 6
+  expand: 1
+training:
+  batch_size: 10
+  gradient_accumulation_steps: 1
+  grad_clip: 0
+  instruments:
+    - drums
+    - bass
+    - other
+    - vocals
+  lr: 0.0005
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 1000
+  num_steps: 1000
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: adam
+  other_fix: false
+  use_amp: true
+augmentations:
+  enable: true
+  loudness: true
+  loudness_min: 0.5
+  loudness_max: 1.5
+  mixup: true
+  mixup_probs: !!python/tuple
+    - 0.2
+    - 0.02
+  mixup_loudness_min: 0.5
+  mixup_loudness_max: 1.5
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2
+  normalize: true

scnet/scnet_xl_ihf_4stem_zfturbo_config.yaml

@@ -0,0 +1,180 @@
+audio:
+  chunk_size: 485100
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.0
+model:
+  sources:
+    - drums
+    - bass
+    - other
+    - vocals
+  audio_channels: 2
+  dims:
+    - 4
+    - 64
+    - 128
+    - 256
+  nfft: 4096
+  hop_size: 1024
+  win_size: 4096
+  normalized: true
+  band_SR:
+    - 0.23
+    - 0.37
+    - 0.4
+  band_stride:
+    - 1
+    - 4
+    - 4
+  band_kernel:
+    - 3
+    - 4
+    - 4
+  conv_depths:
+    - 3
+    - 3
+    - 3
+  compress: 4
+  conv_kernel: 3
+  num_dplayer: 8
+  expand: 1
+training:
+  batch_size: 3
+  gradient_accumulation_steps: 1
+  grad_clip: 0
+  instruments:
+    - drums
+    - bass
+    - other
+    - vocals
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 1000
+  num_steps: 1000
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: adam
+  lr: 5.0e-05
+  normalize: false
+  other_fix: false
+  use_amp: true
+augmentations:
+  enable: true
+  loudness: true
+  loudness_min: 0.5
+  loudness_max: 1.5
+  mixup: true
+  mixup_probs: !!python/tuple
+    - 0.2
+    - 0.02
+    - 0.002
+  mixup_loudness_min: 0.5
+  mixup_loudness_max: 1.5
+  mp3_compression_on_mixture: 0.01
+  mp3_compression_on_mixture_bitrate_min: 32
+  mp3_compression_on_mixture_bitrate_max: 320
+  mp3_compression_on_mixture_backend: lameenc
+  all:
+    channel_shuffle: 0.5
+    random_inverse: 0.1
+    random_polarity: 0.5
+    mp3_compression: 0.01
+    mp3_compression_min_bitrate: 32
+    mp3_compression_max_bitrate: 320
+    mp3_compression_backend: lameenc
+    pedalboard_reverb: 0.01
+    pedalboard_reverb_room_size_min: 0.1
+    pedalboard_reverb_room_size_max: 0.9
+    pedalboard_reverb_damping_min: 0.1
+    pedalboard_reverb_damping_max: 0.9
+    pedalboard_reverb_wet_level_min: 0.1
+    pedalboard_reverb_wet_level_max: 0.9
+    pedalboard_reverb_dry_level_min: 0.1
+    pedalboard_reverb_dry_level_max: 0.9
+    pedalboard_reverb_width_min: 0.9
+    pedalboard_reverb_width_max: 1.0
+    pedalboard_chorus: 0.01
+    pedalboard_chorus_rate_hz_min: 1.0
+    pedalboard_chorus_rate_hz_max: 7.0
+    pedalboard_chorus_depth_min: 0.25
+    pedalboard_chorus_depth_max: 0.95
+    pedalboard_chorus_centre_delay_ms_min: 3
+    pedalboard_chorus_centre_delay_ms_max: 10
+    pedalboard_chorus_feedback_min: 0.0
+    pedalboard_chorus_feedback_max: 0.5
+    pedalboard_chorus_mix_min: 0.1
+    pedalboard_chorus_mix_max: 0.9
+    pedalboard_phazer: 0.01
+    pedalboard_phazer_rate_hz_min: 1.0
+    pedalboard_phazer_rate_hz_max: 10.0
+    pedalboard_phazer_depth_min: 0.25
+    pedalboard_phazer_depth_max: 0.95
+    pedalboard_phazer_centre_frequency_hz_min: 200
+    pedalboard_phazer_centre_frequency_hz_max: 12000
+    pedalboard_phazer_feedback_min: 0.0
+    pedalboard_phazer_feedback_max: 0.5
+    pedalboard_phazer_mix_min: 0.1
+    pedalboard_phazer_mix_max: 0.9
+    pedalboard_distortion: 0.01
+    pedalboard_distortion_drive_db_min: 1.0
+    pedalboard_distortion_drive_db_max: 25.0
+    pedalboard_pitch_shift: 0.01
+    pedalboard_pitch_shift_semitones_min: -7
+    pedalboard_pitch_shift_semitones_max: 7
+    pedalboard_resample: 0.01
+    pedalboard_resample_target_sample_rate_min: 4000
+    pedalboard_resample_target_sample_rate_max: 44100
+    pedalboard_bitcrash: 0.01
+    pedalboard_bitcrash_bit_depth_min: 4
+    pedalboard_bitcrash_bit_depth_max: 16
+    pedalboard_mp3_compressor: 0.01
+    pedalboard_mp3_compressor_pedalboard_mp3_compressor_min: 0
+    pedalboard_mp3_compressor_pedalboard_mp3_compressor_max: 9.999
+  vocals:
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -5
+    pitch_shift_max_semitones: 5
+    seven_band_parametric_eq: 0.25
+    seven_band_parametric_eq_min_gain_db: -9
+    seven_band_parametric_eq_max_gain_db: 9
+    tanh_distortion: 0.1
+    tanh_distortion_min: 0.1
+    tanh_distortion_max: 0.7
+  bass:
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -2
+    pitch_shift_max_semitones: 2
+    seven_band_parametric_eq: 0.25
+    seven_band_parametric_eq_min_gain_db: -3
+    seven_band_parametric_eq_max_gain_db: 6
+    tanh_distortion: 0.2
+    tanh_distortion_min: 0.1
+    tanh_distortion_max: 0.5
+  drums:
+    pitch_shift: 0.33
+    pitch_shift_min_semitones: -5
+    pitch_shift_max_semitones: 5
+    seven_band_parametric_eq: 0.25
+    seven_band_parametric_eq_min_gain_db: -9
+    seven_band_parametric_eq_max_gain_db: 9
+    tanh_distortion: 0.33
+    tanh_distortion_min: 0.1
+    tanh_distortion_max: 0.6
+  other:
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -4
+    pitch_shift_max_semitones: 4
+    gaussian_noise: 0.1
+    gaussian_noise_min_amplitude: 0.001
+    gaussian_noise_max_amplitude: 0.015
+    time_stretch: 0.01
+    time_stretch_min_rate: 0.8
+    time_stretch_max_rate: 1.25
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2
+  normalize: false

scnet/scnet_xl_jazz_4stem_jorisvaneyghen_config.yaml

@@ -0,0 +1,83 @@
+audio:
+  chunk_size: 485100
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.0
+model:
+  sources:
+    - drums
+    - bass
+    - piano
+    - other
+  audio_channels: 2
+  dims:
+    - 4
+    - 64
+    - 128
+    - 256
+  nfft: 4096
+  hop_size: 1024
+  win_size: 4096
+  normalized: true
+  band_SR:
+    - 0.23
+    - 0.37
+    - 0.4
+  band_stride:
+    - 1
+    - 4
+    - 16
+  band_kernel:
+    - 3
+    - 4
+    - 16
+  conv_depths:
+    - 3
+    - 2
+    - 1
+  compress: 4
+  conv_kernel: 3
+  num_dplayer: 8
+  expand: 1
+training:
+  batch_size: 1
+  gradient_accumulation_steps: 4
+  grad_clip: 0
+  instruments:
+    - drums
+    - bass
+    - piano
+    - other
+  lr: 0.0001
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 250
+  num_steps: 1000
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: adam
+  normalize: false
+  other_fix: false
+  use_amp: true
+augmentations:
+  enable: true
+  loudness: true
+  loudness_min: 0.5
+  loudness_max: 1.5
+  mixup: true
+  mixup_probs: !!python/tuple
+    - 0.2
+    - 0.02
+  mixup_loudness_min: 0.5
+  mixup_loudness_max: 1.5
+  all:
+    stereo_to_mono: 0.1
+    channel_shuffle: 0.5
+    random_polarity: 0.5
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2
+  normalize: false

scnet_masked/scnet_masked_small_4stem_zftrubo_config.yaml

@@ -0,0 +1,159 @@
+audio:
+  chunk_size: 485100
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.0
+model:
+  sources:
+    - drums
+    - bass
+    - other
+    - vocals
+  audio_channels: 2
+  dims:
+    - 4
+    - 32
+    - 64
+    - 128
+  nfft: 4096
+  hop_size: 1024
+  win_size: 4096
+  normalized: true
+  band_SR:
+    - 0.175
+    - 0.392
+    - 0.433
+  band_stride:
+    - 1
+    - 4
+    - 16
+  band_kernel:
+    - 3
+    - 4
+    - 16
+  conv_depths:
+    - 3
+    - 2
+    - 1
+  compress: 4
+  conv_kernel: 3
+  num_dplayer: 6
+  expand: 1
+training:
+  batch_size: 10
+  gradient_accumulation_steps: 1
+  grad_clip: 0
+  instruments:
+    - drums
+    - bass
+    - other
+    - vocals
+  lr: 0.0005
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 1000
+  num_steps: 1000
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: adam
+  normalize: false
+  other_fix: false
+  use_amp: true
+augmentations:
+  enable: true
+  loudness: true
+  loudness_min: 0.5
+  loudness_max: 1.5
+  mixup: true
+  mixup_probs: !!python/tuple
+    - 0.2
+    - 0.02
+  mixup_loudness_min: 0.5
+  mixup_loudness_max: 1.5
+  mp3_compression_on_mixture: 0.01
+  mp3_compression_on_mixture_bitrate_min: 32
+  mp3_compression_on_mixture_bitrate_max: 320
+  mp3_compression_on_mixture_backend: lameenc
+  all:
+    channel_shuffle: 0.5
+    random_inverse: 0.1
+    random_polarity: 0.5
+    mp3_compression: 0.01
+    mp3_compression_min_bitrate: 32
+    mp3_compression_max_bitrate: 320
+    mp3_compression_backend: lameenc
+    pedalboard_reverb: 0.01
+    pedalboard_reverb_room_size_min: 0.1
+    pedalboard_reverb_room_size_max: 0.9
+    pedalboard_reverb_damping_min: 0.1
+    pedalboard_reverb_damping_max: 0.9
+    pedalboard_reverb_wet_level_min: 0.1
+    pedalboard_reverb_wet_level_max: 0.9
+    pedalboard_reverb_dry_level_min: 0.1
+    pedalboard_reverb_dry_level_max: 0.9
+    pedalboard_reverb_width_min: 0.9
+    pedalboard_reverb_width_max: 1.0
+    pedalboard_chorus: 0.01
+    pedalboard_chorus_rate_hz_min: 1.0
+    pedalboard_chorus_rate_hz_max: 7.0
+    pedalboard_chorus_depth_min: 0.25
+    pedalboard_chorus_depth_max: 0.95
+    pedalboard_chorus_centre_delay_ms_min: 3
+    pedalboard_chorus_centre_delay_ms_max: 10
+    pedalboard_chorus_feedback_min: 0.0
+    pedalboard_chorus_feedback_max: 0.5
+    pedalboard_chorus_mix_min: 0.1
+    pedalboard_chorus_mix_max: 0.9
+    pedalboard_phazer: 0.01
+    pedalboard_phazer_rate_hz_min: 1.0
+    pedalboard_phazer_rate_hz_max: 10.0
+    pedalboard_phazer_depth_min: 0.25
+    pedalboard_phazer_depth_max: 0.95
+    pedalboard_phazer_centre_frequency_hz_min: 200
+    pedalboard_phazer_centre_frequency_hz_max: 12000
+    pedalboard_phazer_feedback_min: 0.0
+    pedalboard_phazer_feedback_max: 0.5
+    pedalboard_phazer_mix_min: 0.1
+    pedalboard_phazer_mix_max: 0.9
+    pedalboard_distortion: 0.01
+    pedalboard_distortion_drive_db_min: 1.0
+    pedalboard_distortion_drive_db_max: 25.0
+    pedalboard_pitch_shift: 0.01
+    pedalboard_pitch_shift_semitones_min: -7
+    pedalboard_pitch_shift_semitones_max: 7
+    pedalboard_resample: 0.01
+    pedalboard_resample_target_sample_rate_min: 4000
+    pedalboard_resample_target_sample_rate_max: 44100
+    pedalboard_bitcrash: 0.01
+    pedalboard_bitcrash_bit_depth_min: 4
+    pedalboard_bitcrash_bit_depth_max: 16
+    pedalboard_mp3_compressor: 0.01
+    pedalboard_mp3_compressor_pedalboard_mp3_compressor_min: 0
+    pedalboard_mp3_compressor_pedalboard_mp3_compressor_max: 9.999
+  vocals:
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -5
+    pitch_shift_max_semitones: 5
+    seven_band_parametric_eq: 0.1
+    seven_band_parametric_eq_min_gain_db: -9
+    seven_band_parametric_eq_max_gain_db: 9
+    tanh_distortion: 0.1
+    tanh_distortion_min: 0.1
+    tanh_distortion_max: 0.7
+  other:
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -4
+    pitch_shift_max_semitones: 4
+    gaussian_noise: 0.1
+    gaussian_noise_min_amplitude: 0.001
+    gaussian_noise_max_amplitude: 0.015
+    time_stretch: 0.01
+    time_stretch_min_rate: 0.8
+    time_stretch_max_rate: 1.25
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2
+  normalize: false

scnet_masked/scnet_masked_xl_ihf_4stem_zftrubo_config.yaml

@@ -0,0 +1,180 @@
+audio:
+  chunk_size: 485100
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.0
+model:
+  sources:
+    - drums
+    - bass
+    - other
+    - vocals
+  audio_channels: 2
+  dims:
+    - 4
+    - 64
+    - 128
+    - 256
+  nfft: 4096
+  hop_size: 1024
+  win_size: 4096
+  normalized: true
+  band_SR:
+    - 0.23
+    - 0.37
+    - 0.4
+  band_stride:
+    - 1
+    - 4
+    - 4
+  band_kernel:
+    - 3
+    - 4
+    - 4
+  conv_depths:
+    - 3
+    - 3
+    - 3
+  compress: 4
+  conv_kernel: 3
+  num_dplayer: 8
+  expand: 1
+training:
+  batch_size: 2
+  gradient_accumulation_steps: 1
+  grad_clip: 0
+  instruments:
+    - drums
+    - bass
+    - other
+    - vocals
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 1000
+  num_steps: 1000
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: adam
+  lr: 5.0e-05
+  normalize: false
+  other_fix: false
+  use_amp: true
+augmentations:
+  enable: true
+  loudness: true
+  loudness_min: 0.5
+  loudness_max: 1.5
+  mixup: true
+  mixup_probs: !!python/tuple
+    - 0.2
+    - 0.02
+    - 0.002
+  mixup_loudness_min: 0.5
+  mixup_loudness_max: 1.5
+  mp3_compression_on_mixture: 0.01
+  mp3_compression_on_mixture_bitrate_min: 32
+  mp3_compression_on_mixture_bitrate_max: 320
+  mp3_compression_on_mixture_backend: lameenc
+  all:
+    channel_shuffle: 0.5
+    random_inverse: 0.1
+    random_polarity: 0.5
+    mp3_compression: 0.01
+    mp3_compression_min_bitrate: 32
+    mp3_compression_max_bitrate: 320
+    mp3_compression_backend: lameenc
+    pedalboard_reverb: 0.01
+    pedalboard_reverb_room_size_min: 0.1
+    pedalboard_reverb_room_size_max: 0.9
+    pedalboard_reverb_damping_min: 0.1
+    pedalboard_reverb_damping_max: 0.9
+    pedalboard_reverb_wet_level_min: 0.1
+    pedalboard_reverb_wet_level_max: 0.9
+    pedalboard_reverb_dry_level_min: 0.1
+    pedalboard_reverb_dry_level_max: 0.9
+    pedalboard_reverb_width_min: 0.9
+    pedalboard_reverb_width_max: 1.0
+    pedalboard_chorus: 0.01
+    pedalboard_chorus_rate_hz_min: 1.0
+    pedalboard_chorus_rate_hz_max: 7.0
+    pedalboard_chorus_depth_min: 0.25
+    pedalboard_chorus_depth_max: 0.95
+    pedalboard_chorus_centre_delay_ms_min: 3
+    pedalboard_chorus_centre_delay_ms_max: 10
+    pedalboard_chorus_feedback_min: 0.0
+    pedalboard_chorus_feedback_max: 0.5
+    pedalboard_chorus_mix_min: 0.1
+    pedalboard_chorus_mix_max: 0.9
+    pedalboard_phazer: 0.01
+    pedalboard_phazer_rate_hz_min: 1.0
+    pedalboard_phazer_rate_hz_max: 10.0
+    pedalboard_phazer_depth_min: 0.25
+    pedalboard_phazer_depth_max: 0.95
+    pedalboard_phazer_centre_frequency_hz_min: 200
+    pedalboard_phazer_centre_frequency_hz_max: 12000
+    pedalboard_phazer_feedback_min: 0.0
+    pedalboard_phazer_feedback_max: 0.5
+    pedalboard_phazer_mix_min: 0.1
+    pedalboard_phazer_mix_max: 0.9
+    pedalboard_distortion: 0.01
+    pedalboard_distortion_drive_db_min: 1.0
+    pedalboard_distortion_drive_db_max: 25.0
+    pedalboard_pitch_shift: 0.01
+    pedalboard_pitch_shift_semitones_min: -7
+    pedalboard_pitch_shift_semitones_max: 7
+    pedalboard_resample: 0.01
+    pedalboard_resample_target_sample_rate_min: 4000
+    pedalboard_resample_target_sample_rate_max: 44100
+    pedalboard_bitcrash: 0.01
+    pedalboard_bitcrash_bit_depth_min: 4
+    pedalboard_bitcrash_bit_depth_max: 16
+    pedalboard_mp3_compressor: 0.01
+    pedalboard_mp3_compressor_pedalboard_mp3_compressor_min: 0
+    pedalboard_mp3_compressor_pedalboard_mp3_compressor_max: 9.999
+  vocals:
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -5
+    pitch_shift_max_semitones: 5
+    seven_band_parametric_eq: 0.1
+    seven_band_parametric_eq_min_gain_db: -9
+    seven_band_parametric_eq_max_gain_db: 9
+    tanh_distortion: 0.1
+    tanh_distortion_min: 0.1
+    tanh_distortion_max: 0.7
+  bass:
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -2
+    pitch_shift_max_semitones: 2
+    seven_band_parametric_eq: 0.1
+    seven_band_parametric_eq_min_gain_db: -3
+    seven_band_parametric_eq_max_gain_db: 6
+    tanh_distortion: 0.1
+    tanh_distortion_min: 0.1
+    tanh_distortion_max: 0.5
+  drums:
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -5
+    pitch_shift_max_semitones: 5
+    seven_band_parametric_eq: 0.1
+    seven_band_parametric_eq_min_gain_db: -9
+    seven_band_parametric_eq_max_gain_db: 9
+    tanh_distortion: 0.1
+    tanh_distortion_min: 0.1
+    tanh_distortion_max: 0.6
+  other:
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -4
+    pitch_shift_max_semitones: 4
+    gaussian_noise: 0.1
+    gaussian_noise_min_amplitude: 0.001
+    gaussian_noise_max_amplitude: 0.015
+    time_stretch: 0.01
+    time_stretch_min_rate: 0.8
+    time_stretch_max_rate: 1.25
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2
+  normalize: false

scnet_tran/scnet_tran_4stem_zftrubo_config.yaml

@@ -0,0 +1,167 @@
+audio:
+  chunk_size: 485100
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.0
+model:
+  sources:
+    - drums
+    - bass
+    - other
+    - vocals
+  audio_channels: 2
+  dims:
+    - 4
+    - 32
+    - 64
+    - 128
+  nfft: 4096
+  hop_size: 1024
+  win_size: 4096
+  normalized: true
+  band_SR:
+    - 0.175
+    - 0.392
+    - 0.433
+  band_stride:
+    - 1
+    - 4
+    - 16
+  band_kernel:
+    - 3
+    - 4
+    - 16
+  conv_depths:
+    - 3
+    - 2
+    - 1
+  compress: 4
+  conv_kernel: 3
+  num_dplayer: 6
+  expand: 1
+  tran_rotary_embedding_dim: 64
+  tran_depth: 1
+  tran_heads: 8
+  tran_dim_head: 64
+  tran_attn_dropout: 0.0
+  tran_ff_dropout: 0.0
+  tran_flash_attn: false
+training:
+  batch_size: 5
+  gradient_accumulation_steps: 1
+  grad_clip: 0
+  instruments:
+    - drums
+    - bass
+    - other
+    - vocals
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: null
+  num_epochs: 1000
+  num_steps: 1000
+  q: 0.95
+  coarse_loss_clip: true
+  ema_momentum: 0.999
+  optimizer: adam
+  lr: 5.0e-05
+  normalize: false
+  other_fix: false
+  use_amp: true
+augmentations:
+  enable: true
+  loudness: true
+  loudness_min: 0.5
+  loudness_max: 1.5
+  mixup: true
+  mixup_probs: !!python/tuple
+    - 0.2
+    - 0.02
+    - 0.002
+  mixup_loudness_min: 0.5
+  mixup_loudness_max: 1.5
+  mp3_compression_on_mixture: 0.01
+  mp3_compression_on_mixture_bitrate_min: 32
+  mp3_compression_on_mixture_bitrate_max: 320
+  mp3_compression_on_mixture_backend: lameenc
+  all:
+    channel_shuffle: 0.5
+    random_inverse: 0.01
+    random_polarity: 0.5
+  vocals:
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -5
+    pitch_shift_max_semitones: 5
+    seven_band_parametric_eq: 0.1
+    seven_band_parametric_eq_min_gain_db: -9
+    seven_band_parametric_eq_max_gain_db: 9
+    tanh_distortion: 0.1
+    tanh_distortion_min: 0.1
+    tanh_distortion_max: 0.7
+    time_stretch: 0.01
+    time_stretch_min_rate: 0.8
+    time_stretch_max_rate: 1.25
+  bass:
+    pitch_shift: 0.01
+    pitch_shift_min_semitones: -2
+    pitch_shift_max_semitones: 2
+    seven_band_parametric_eq: 0.01
+    seven_band_parametric_eq_min_gain_db: -3
+    seven_band_parametric_eq_max_gain_db: 6
+    tanh_distortion: 0.01
+    tanh_distortion_min: 0.1
+    tanh_distortion_max: 0.5
+    time_stretch: 0.1
+    time_stretch_min_rate: 0.9
+    time_stretch_max_rate: 1.1
+  drums:
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -5
+    pitch_shift_max_semitones: 5
+    seven_band_parametric_eq: 0.1
+    seven_band_parametric_eq_min_gain_db: -9
+    seven_band_parametric_eq_max_gain_db: 9
+    tanh_distortion: 0.1
+    tanh_distortion_min: 0.1
+    tanh_distortion_max: 0.6
+    time_stretch: 0.01
+    time_stretch_min_rate: 0.8
+    time_stretch_max_rate: 1.25
+  other:
+    pitch_shift: 0.1
+    pitch_shift_min_semitones: -4
+    pitch_shift_max_semitones: 4
+    gaussian_noise: 0.1
+    gaussian_noise_min_amplitude: 0.001
+    gaussian_noise_max_amplitude: 0.015
+    time_stretch: 0.01
+    time_stretch_min_rate: 0.8
+    time_stretch_max_rate: 1.25
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2
+  normalize: false
+loss_multistft:
+  fft_sizes:
+    - 1024
+    - 2048
+    - 4096
+  hop_sizes:
+    - 147
+    - 256
+    - 512
+  win_lengths:
+    - 1024
+    - 2048
+    - 4096
+  window: hann_window
+  scale: mel
+  n_bins: 128
+  sample_rate: 44100
+  perceptual_weighting: true
+  w_sc: 1.0
+  w_log_mag: 1.0
+  w_lin_mag: 0.0
+  w_phs: 0.0
+  mag_distance: L1

vr/10_sp-uvr-2b-32000-1_config.yaml

@@ -0,0 +1,49 @@
+model:
+  model_params:
+    bins: 768
+    unstable_bins: 7
+    reduction_bins: 705
+    band:
+      1:
+        sr: 6000
+        hl: 66
+        n_fft: 512
+        crop_start: 0
+        crop_stop: 240
+        lpf_start: 60
+        lpf_stop: 118
+        res_type: sinc_fastest
+      2:
+        sr: 32000
+        hl: 352
+        n_fft: 1024
+        crop_start: 22
+        crop_stop: 505
+        hpf_start: 44
+        hpf_stop: 23
+        res_type: sinc_medium
+    sr: 32000
+    pre_filter_start: 710
+    pre_filter_stop: 731
+    mid_side: false
+    mid_side_b: false
+    mid_side_b2: false
+    stereo_w: false
+    stereo_n: false
+    reverse: false
+  nout: null
+  nout_lstm: null
+training:
+  target_instrument: null
+  instruments:
+    - Instrumental
+    - Vocals
+  use_amp: true
+inference:
+  batch_size: 1
+  aggression: 5
+  high_end_process: false
+  post_process_threshold: 0.2
+  window_size: 512
+audio:
+  sample_rate: 44100

vr/11_sp-uvr-2b-32000-2_config.yaml

@@ -0,0 +1,49 @@
+model:
+  model_params:
+    bins: 768
+    unstable_bins: 7
+    reduction_bins: 705
+    band:
+      1:
+        sr: 6000
+        hl: 66
+        n_fft: 512
+        crop_start: 0
+        crop_stop: 240
+        lpf_start: 60
+        lpf_stop: 118
+        res_type: sinc_fastest
+      2:
+        sr: 32000
+        hl: 352
+        n_fft: 1024
+        crop_start: 22
+        crop_stop: 505
+        hpf_start: 44
+        hpf_stop: 23
+        res_type: sinc_medium
+    sr: 32000
+    pre_filter_start: 710
+    pre_filter_stop: 731
+    mid_side: false
+    mid_side_b: false
+    mid_side_b2: false
+    stereo_w: false
+    stereo_n: false
+    reverse: false
+  nout: null
+  nout_lstm: null
+training:
+  target_instrument: null
+  instruments:
+    - Instrumental
+    - Vocals
+  use_amp: true
+inference:
+  batch_size: 1
+  aggression: 5
+  high_end_process: false
+  post_process_threshold: 0.2
+  window_size: 512
+audio:
+  sample_rate: 44100

vr/12_sp-uvr-3b-44100_config.yaml

@@ -0,0 +1,60 @@
+model:
+  model_params:
+    bins: 768
+    unstable_bins: 5
+    reduction_bins: 733
+    band:
+      1:
+        sr: 11025
+        hl: 128
+        n_fft: 768
+        crop_start: 0
+        crop_stop: 278
+        lpf_start: 28
+        lpf_stop: 140
+        res_type: polyphase
+      2:
+        sr: 22050
+        hl: 256
+        n_fft: 768
+        crop_start: 14
+        crop_stop: 322
+        hpf_start: 70
+        hpf_stop: 14
+        lpf_start: 283
+        lpf_stop: 314
+        res_type: polyphase
+      3:
+        sr: 44100
+        hl: 512
+        n_fft: 768
+        crop_start: 131
+        crop_stop: 313
+        hpf_start: 154
+        hpf_stop: 141
+        res_type: sinc_medium
+    sr: 44100
+    pre_filter_start: 757
+    pre_filter_stop: 768
+    mid_side: false
+    mid_side_b: false
+    mid_side_b2: false
+    stereo_w: false
+    stereo_n: false
+    reverse: false
+  nout: null
+  nout_lstm: null
+training:
+  target_instrument: null
+  instruments:
+    - Instrumental
+    - Vocals
+  use_amp: true
+inference:
+  batch_size: 1
+  aggression: 5
+  high_end_process: false
+  post_process_threshold: 0.2
+  window_size: 512
+audio:
+  sample_rate: 44100

vr/13_sp-uvr-4b-44100-1_config.yaml

@@ -0,0 +1,71 @@
+model:
+  model_params:
+    bins: 768
+    unstable_bins: 7
+    reduction_bins: 668
+    band:
+      1:
+        sr: 11025
+        hl: 128
+        n_fft: 1024
+        crop_start: 0
+        crop_stop: 186
+        lpf_start: 37
+        lpf_stop: 73
+        res_type: polyphase
+      2:
+        sr: 11025
+        hl: 128
+        n_fft: 512
+        crop_start: 4
+        crop_stop: 185
+        hpf_start: 36
+        hpf_stop: 18
+        lpf_start: 93
+        lpf_stop: 185
+        res_type: polyphase
+      3:
+        sr: 22050
+        hl: 256
+        n_fft: 512
+        crop_start: 46
+        crop_stop: 186
+        hpf_start: 93
+        hpf_stop: 46
+        lpf_start: 164
+        lpf_stop: 186
+        res_type: polyphase
+      4:
+        sr: 44100
+        hl: 512
+        n_fft: 768
+        crop_start: 121
+        crop_stop: 382
+        hpf_start: 138
+        hpf_stop: 123
+        res_type: sinc_medium
+    sr: 44100
+    pre_filter_start: 740
+    pre_filter_stop: 768
+    mid_side: false
+    mid_side_b: false
+    mid_side_b2: false
+    stereo_w: false
+    stereo_n: false
+    reverse: false
+  nout: null
+  nout_lstm: null
+training:
+  target_instrument: null
+  instruments:
+    - Instrumental
+    - Vocals
+  use_amp: true
+inference:
+  batch_size: 1
+  aggression: 5
+  high_end_process: false
+  post_process_threshold: 0.2
+  window_size: 512
+audio:
+  sample_rate: 44100

vr/14_sp-uvr-4b-44100-2_config.yaml

@@ -0,0 +1,71 @@
+model:
+  model_params:
+    bins: 768
+    unstable_bins: 7
+    reduction_bins: 668
+    band:
+      1:
+        sr: 11025
+        hl: 128
+        n_fft: 1024
+        crop_start: 0
+        crop_stop: 186
+        lpf_start: 37
+        lpf_stop: 73
+        res_type: polyphase
+      2:
+        sr: 11025
+        hl: 128
+        n_fft: 512
+        crop_start: 4
+        crop_stop: 185
+        hpf_start: 36
+        hpf_stop: 18
+        lpf_start: 93
+        lpf_stop: 185
+        res_type: polyphase
+      3:
+        sr: 22050
+        hl: 256
+        n_fft: 512
+        crop_start: 46
+        crop_stop: 186
+        hpf_start: 93
+        hpf_stop: 46
+        lpf_start: 164
+        lpf_stop: 186
+        res_type: polyphase
+      4:
+        sr: 44100
+        hl: 512
+        n_fft: 768
+        crop_start: 121
+        crop_stop: 382
+        hpf_start: 138
+        hpf_stop: 123
+        res_type: sinc_medium
+    sr: 44100
+    pre_filter_start: 740
+    pre_filter_stop: 768
+    mid_side: false
+    mid_side_b: false
+    mid_side_b2: false
+    stereo_w: false
+    stereo_n: false
+    reverse: false
+  nout: null
+  nout_lstm: null
+training:
+  target_instrument: null
+  instruments:
+    - Instrumental
+    - Vocals
+  use_amp: true
+inference:
+  batch_size: 1
+  aggression: 5
+  high_end_process: false
+  post_process_threshold: 0.2
+  window_size: 512
+audio:
+  sample_rate: 44100

vr/15_sp-uvr-mid-44100-1_config.yaml

@@ -0,0 +1,60 @@
+model:
+  model_params:
+    mid_side: true
+    bins: 768
+    unstable_bins: 5
+    reduction_bins: 733
+    band:
+      1:
+        sr: 11025
+        hl: 128
+        n_fft: 768
+        crop_start: 0
+        crop_stop: 278
+        lpf_start: 28
+        lpf_stop: 140
+        res_type: polyphase
+      2:
+        sr: 22050
+        hl: 256
+        n_fft: 768
+        crop_start: 14
+        crop_stop: 322
+        hpf_start: 70
+        hpf_stop: 14
+        lpf_start: 283
+        lpf_stop: 314
+        res_type: polyphase
+      3:
+        sr: 44100
+        hl: 512
+        n_fft: 768
+        crop_start: 131
+        crop_stop: 313
+        hpf_start: 154
+        hpf_stop: 141
+        res_type: sinc_medium
+    sr: 44100
+    pre_filter_start: 757
+    pre_filter_stop: 768
+    mid_side_b: false
+    mid_side_b2: false
+    stereo_w: false
+    stereo_n: false
+    reverse: false
+  nout: null
+  nout_lstm: null
+training:
+  target_instrument: null
+  instruments:
+    - Instrumental
+    - Vocals
+  use_amp: true
+inference:
+  batch_size: 1
+  aggression: 5
+  high_end_process: false
+  post_process_threshold: 0.2
+  window_size: 512
+audio:
+  sample_rate: 44100

vr/16_sp-uvr-mid-44100-2_config.yaml

@@ -0,0 +1,60 @@
+model:
+  model_params:
+    mid_side: true
+    bins: 768
+    unstable_bins: 5
+    reduction_bins: 733
+    band:
+      1:
+        sr: 11025
+        hl: 128
+        n_fft: 768
+        crop_start: 0
+        crop_stop: 278
+        lpf_start: 28
+        lpf_stop: 140
+        res_type: polyphase
+      2:
+        sr: 22050
+        hl: 256
+        n_fft: 768
+        crop_start: 14
+        crop_stop: 322
+        hpf_start: 70
+        hpf_stop: 14
+        lpf_start: 283
+        lpf_stop: 314
+        res_type: polyphase
+      3:
+        sr: 44100
+        hl: 512
+        n_fft: 768
+        crop_start: 131
+        crop_stop: 313
+        hpf_start: 154
+        hpf_stop: 141
+        res_type: sinc_medium
+    sr: 44100
+    pre_filter_start: 757
+    pre_filter_stop: 768
+    mid_side_b: false
+    mid_side_b2: false
+    stereo_w: false
+    stereo_n: false
+    reverse: false
+  nout: null
+  nout_lstm: null
+training:
+  target_instrument: null
+  instruments:
+    - Instrumental
+    - Vocals
+  use_amp: true
+inference:
+  batch_size: 1
+  aggression: 5
+  high_end_process: false
+  post_process_threshold: 0.2
+  window_size: 512
+audio:
+  sample_rate: 44100

vr/17_hp-wind_inst-uvr_config.yaml

@@ -0,0 +1,71 @@
+model:
+  model_params:
+    bins: 672
+    unstable_bins: 8
+    reduction_bins: 530
+    band:
+      1:
+        sr: 7350
+        hl: 80
+        n_fft: 640
+        crop_start: 0
+        crop_stop: 85
+        lpf_start: 25
+        lpf_stop: 53
+        res_type: polyphase
+      2:
+        sr: 7350
+        hl: 80
+        n_fft: 320
+        crop_start: 4
+        crop_stop: 87
+        hpf_start: 25
+        hpf_stop: 12
+        lpf_start: 31
+        lpf_stop: 62
+        res_type: polyphase
+      3:
+        sr: 14700
+        hl: 160
+        n_fft: 512
+        crop_start: 17
+        crop_stop: 216
+        hpf_start: 48
+        hpf_stop: 24
+        lpf_start: 139
+        lpf_stop: 210
+        res_type: polyphase
+      4:
+        sr: 44100
+        hl: 480
+        n_fft: 960
+        crop_start: 78
+        crop_stop: 383
+        hpf_start: 130
+        hpf_stop: 86
+        res_type: kaiser_fast
+    sr: 44100
+    pre_filter_start: 668
+    pre_filter_stop: 672
+    mid_side: false
+    mid_side_b: false
+    mid_side_b2: false
+    stereo_w: false
+    stereo_n: false
+    reverse: false
+  nout: null
+  nout_lstm: null
+training:
+  target_instrument: null
+  instruments:
+    - No Woodwinds
+    - Woodwinds
+  use_amp: true
+inference:
+  batch_size: 1
+  aggression: 5
+  high_end_process: false
+  post_process_threshold: 0.2
+  window_size: 512
+audio:
+  sample_rate: 44100

vr/1_hp-uvr_config.yaml

@@ -0,0 +1,71 @@
+model:
+  model_params:
+    bins: 768
+    unstable_bins: 7
+    reduction_bins: 668
+    band:
+      1:
+        sr: 11025
+        hl: 128
+        n_fft: 1024
+        crop_start: 0
+        crop_stop: 186
+        lpf_start: 37
+        lpf_stop: 73
+        res_type: polyphase
+      2:
+        sr: 11025
+        hl: 128
+        n_fft: 512
+        crop_start: 4
+        crop_stop: 185
+        hpf_start: 36
+        hpf_stop: 18
+        lpf_start: 93
+        lpf_stop: 185
+        res_type: polyphase
+      3:
+        sr: 22050
+        hl: 256
+        n_fft: 512
+        crop_start: 46
+        crop_stop: 186
+        hpf_start: 93
+        hpf_stop: 46
+        lpf_start: 164
+        lpf_stop: 186
+        res_type: polyphase
+      4:
+        sr: 44100
+        hl: 512
+        n_fft: 768
+        crop_start: 121
+        crop_stop: 382
+        hpf_start: 138
+        hpf_stop: 123
+        res_type: sinc_medium
+    sr: 44100
+    pre_filter_start: 740
+    pre_filter_stop: 768
+    mid_side: false
+    mid_side_b: false
+    mid_side_b2: false
+    stereo_w: false
+    stereo_n: false
+    reverse: false
+  nout: null
+  nout_lstm: null
+training:
+  target_instrument: null
+  instruments:
+    - Instrumental
+    - Vocals
+  use_amp: true
+inference:
+  batch_size: 1
+  aggression: 5
+  high_end_process: false
+  post_process_threshold: 0.2
+  window_size: 512
+audio:
+  sample_rate: 44100

vr/2_hp-uvr_config.yaml

@@ -0,0 +1,71 @@
+model:
+  model_params:
+    bins: 672
+    unstable_bins: 8
+    reduction_bins: 637
+    band:
+      1:
+        sr: 7350
+        hl: 80
+        n_fft: 640
+        crop_start: 0
+        crop_stop: 85
+        lpf_start: 25
+        lpf_stop: 53
+        res_type: polyphase
+      2:
+        sr: 7350
+        hl: 80
+        n_fft: 320
+        crop_start: 4
+        crop_stop: 87
+        hpf_start: 25
+        hpf_stop: 12
+        lpf_start: 31
+        lpf_stop: 62
+        res_type: polyphase
+      3:
+        sr: 14700
+        hl: 160
+        n_fft: 512
+        crop_start: 17
+        crop_stop: 216
+        hpf_start: 48
+        hpf_stop: 24
+        lpf_start: 139
+        lpf_stop: 210
+        res_type: polyphase
+      4:
+        sr: 44100
+        hl: 480
+        n_fft: 960
+        crop_start: 78
+        crop_stop: 383
+        hpf_start: 130
+        hpf_stop: 86
+        res_type: kaiser_fast
+    sr: 44100
+    pre_filter_start: 668
+    pre_filter_stop: 672
+    mid_side: false
+    mid_side_b: false
+    mid_side_b2: false
+    stereo_w: false
+    stereo_n: false
+    reverse: false
+  nout: null
+  nout_lstm: null
+training:
+  target_instrument: null
+  instruments:
+    - Instrumental
+    - Vocals
+  use_amp: true
+inference:
+  batch_size: 1
+  aggression: 5
+  high_end_process: false
+  post_process_threshold: 0.2
+  window_size: 512
+audio:
+  sample_rate: 44100