.

SCnet_models/SCNet-large_starrytong_fixed.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:65900dfa07d6b6e5d784c0f143920200a4bd281d6e78a806c549d0b912d5885e
-size 168852258

SCnet_models/config_musdb18_scnet.yaml

@@ -1,83 +0,0 @@
-audio:
-  chunk_size: 485100 # 44100 * 11
-  num_channels: 2
-  sample_rate: 44100
-  min_mean_abs: 0.000
-
-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: 5.0e-04
-  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 # 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: 0.5
-  loudness_max: 1.5
-  mixup: true # 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: 8
-  dim_t: 256
-  num_overlap: 4
-  normalize: true

SCnet_models/config_musdb18_scnet_large.yaml

@@ -1,88 +0,0 @@
-audio:
-  chunk_size: 485100 # 44100 * 11
-  num_channels: 2
-  sample_rate: 44100
-  min_mean_abs: 0.000
-
-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: 1.0e-04
-  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 # 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: 0.5
-  loudness_max: 1.5
-  mixup: true # 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
-  all:
-    channel_shuffle: 0.5 # Set 0 or lower to disable
-    random_inverse: 0.1 # inverse track (better lower probability)
-    random_polarity: 0.5 # polarity change (multiply waveform to -1)
-
-inference:
-  batch_size: 8
-  dim_t: 256
-  num_overlap: 4
-  normalize: false

SCnet_models/config_musdb18_scnet_large_starrytong.yaml

@@ -1,88 +0,0 @@
-audio:
-  chunk_size: 485100 # 44100 * 11
-  num_channels: 2
-  sample_rate: 44100
-  min_mean_abs: 0.000
-
-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: 1.0e-04
-  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 # 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: 0.5
-  loudness_max: 1.5
-  mixup: true # 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
-  all:
-    channel_shuffle: 0.5 # Set 0 or lower to disable
-    random_inverse: 0.1 # inverse track (better lower probability)
-    random_polarity: 0.5 # polarity change (multiply waveform to -1)
-
-inference:
-  batch_size: 8
-  dim_t: 256
-  num_overlap: 4
-  normalize: true

SCnet_models/config_musdb18_scnet_xl.yaml

@@ -1,207 +0,0 @@
-audio:
-  chunk_size: 485100 # 44100 * 11
-  num_channels: 2
-  sample_rate: 44100
-  min_mean_abs: 0.000
-
-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:
-    - 0.230
-    - 0.370
-    - 0.400
-  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: prodigy
-  optimizer: adam
-  lr: 1.0e-05
-  # lr: 1.0
-  normalize: false # perform normalization on input of model (use the same for inference!)
-  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
-
-
-augmentations:
-  enable: false # 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: 0.5
-  loudness_max: 1.5
-  mixup: true # 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
-
-  # apply mp3 compression to mixture only (emulate downloading mp3 from internet)
-  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 # Set 0 or lower to disable
-    random_inverse: 0.1 # inverse track (better lower probability)
-    random_polarity: 0.5 # polarity change (multiply waveform to -1)
-
-    mp3_compression: 0.01
-    mp3_compression_min_bitrate: 32
-    mp3_compression_max_bitrate: 320
-    mp3_compression_backend: "lameenc"
-
-    # pedalboard reverb block
-    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 block
-    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 block
-    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 block
-    pedalboard_distortion: 0.01
-    pedalboard_distortion_drive_db_min: 1.0
-    pedalboard_distortion_drive_db_max: 25.0
-
-    # pedalboard pitch shift block
-    pedalboard_pitch_shift: 0.01
-    pedalboard_pitch_shift_semitones_min: -7
-    pedalboard_pitch_shift_semitones_max: 7
-
-    # pedalboard resample block
-    pedalboard_resample: 0.01
-    pedalboard_resample_target_sample_rate_min: 4000
-    pedalboard_resample_target_sample_rate_max: 44100
-
-    # pedalboard bitcrash block
-    pedalboard_bitcrash: 0.01
-    pedalboard_bitcrash_bit_depth_min: 4
-    pedalboard_bitcrash_bit_depth_max: 16
-
-    # pedalboard mp3 compressor block
-    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: 4
-  dim_t: 256
-  num_overlap: 4
-  normalize: false

SCnet_models/model_scnet_ep_54_sdr_9.8051.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fd889cc1d97619ccac59280ecc859c190cd3cc1b1557fbe3a19b1610bb67e410
-size 216189106

SCnet_models/model_scnet_sdr_9.3244.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fe550315a76e8f4aed8475d7d5952137504a3b6c63b3adcef2443bfe73aac540
-size 168868194

SCnet_models/scnet_checkpoint_musdb18.ckpt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:1bc0d1abb20bfdf966dcd07637bafd03e4bc13653d09ef18bc9b3e342eafe2aa
-size 42434986