Upload 27 files

.gitattributes

@@ -33,3 +33,8 @@ saved_model/**/* 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
+htdemucs_ft/04573f0d-f3cf25b2.th filter=lfs diff=lfs merge=lfs -text
+htdemucs_ft/92cfc3b6-ef3bcb9c.th filter=lfs diff=lfs merge=lfs -text
+htdemucs_ft/d12395a8-e57c48e6.th filter=lfs diff=lfs merge=lfs -text
+htdemucs_ft/f7e0c4bc-ba3fe64a.th filter=lfs diff=lfs merge=lfs -text
+htdemucs/955717e8-8726e21a.th filter=lfs diff=lfs merge=lfs -text

2_HP-UVR.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26d6400d2d2e90811ba2381828c8c3519196097375af524c3d0edd969acf5356
+size 126782699

4_HP-Vocal-UVR.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:295d1e1e3a52c17a040a4a6fe390214ad8ca0797f091b7c6d8db97d247a27271
+size 126792647

6_HP-Karaoke-UVR.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ce7eaaa9e56f09366b788aebf6d3a72aec8145692c56f1e090e4e7e2d7ce65f
+size 126782699

8_HP2-UVR.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e072299a87cf3fcdd36da6adc6d2837bed0c07a208775a7678c3d5deeea58f79
+size 550131079

Kim_Vocal_2.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce74ef3b6a6024ce44211a07be9cf8bc6d87728cc852a68ab34eb8e58cde9c8b
+size 66759214

MDX23C-8KFFT-InstVoc_HQ_2/MDX23C-8KFFT-InstVoc_HQ_2.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d960d8e40a458120412c1bd807e013d2dbca7b959cc9da2bbcb0eb203d1daea
+size 448093770

MDX23C-8KFFT-InstVoc_HQ_2/model_2_stem_full_band_8k.yaml

@@ -0,0 +1,43 @@
+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
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 8

MDX23C-De-Reverb-aufr33-jarredou/MDX23C-De-Reverb-aufr33-jarredou.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eae2471b707758d74db38ac1b1d5800e12f57c4e9d1ebbb2faf004b8e086e914
+size 448098867

MDX23C-De-Reverb-aufr33-jarredou/config_dereverb_mdx23c.yaml

@@ -0,0 +1,135 @@
+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
+  - No dry
+  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 # Number of processes to use during metadata reading for dataset. Can speed up metadata generation
+  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
+
+  all:
+    channel_shuffle: 0.5 # Set 0 or lower to disable
+    random_inverse: 0.05 # inverse track (better lower probability)
+    random_polarity: 0.5 # polarity change (multiply waveform to -1)
+
+    # pedalboard chorus block
+    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 block
+    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 block
+    pedalboard_pitch_shift: 0.01
+    pedalboard_pitch_shift_semitones_min: -7
+    pedalboard_pitch_shift_semitones_max: 7
+
+    # pedalboard resample block
+    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 block
+    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 block
+    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: 2
+  dim_t: 256
+  num_overlap: 4

Reverb_HQ_By_FoxJoy.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:233bb5c6aaa365e568659a0a81211746fa881f8f47f82d9e864fce1f7692db80
+size 66780123

UVR-De-Echo-Aggressive.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bd1d79d9c5d1b17d20f96f8a9f8aff1b55a83014f70712446bf420c0188e0a0
+size 127139365

UVR-DeEcho-DeReverb.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e644028ec82865dc0fe082bc6fea85a43f7c71cfe375caee2da2d154aa661ee7
+size 223650277

UVR-DeNoise.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5addf43ece5bddd18da9f575a02d7ffdb32342414e6ad7ac8d1dd7a04138a628
+size 127139365

UVR-MDX-NET-Inst_HQ_1.onnx

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

UVR-MDX-NET-Inst_HQ_5.onnx

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

UVR-MDX-NET-Inst_full_292.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:020f6b65fa219fb7c285e4f3fc2863bf22daf03c4c93e547b6d13d5f2757a7ec
+size 66759214

htdemucs/955717e8-8726e21a.th

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

htdemucs/htdemucs.yaml

@@ -0,0 +1 @@
+models: ['955717e8']

htdemucs_ft/04573f0d-f3cf25b2.th

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

htdemucs_ft/92cfc3b6-ef3bcb9c.th

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

htdemucs_ft/d12395a8-e57c48e6.th

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

htdemucs_ft/f7e0c4bc-ba3fe64a.th

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

htdemucs_ft/htdemucs_ft.yaml

@@ -0,0 +1,7 @@
+models: ['f7e0c4bc', 'd12395a8', '92cfc3b6', '04573f0d']
+weights: [
+  [1., 0., 0., 0.],
+  [0., 1., 0., 0.],
+  [0., 0., 1., 0.],
+  [0., 0., 0., 1.],
+]

mel_band_roformer_karaoke_aufr33_viperx_sdr_10/mel_band_roformer_karaoke_aufr33_viperx_sdr_10.1956.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1de20d459332fe8869aeb01327a31df0032262706e1365114e852dc271779813
+size 913096801

mel_band_roformer_karaoke_aufr33_viperx_sdr_10/mel_band_roformer_karaoke_aufr33_viperx_sdr_10.1956_config.yaml

@@ -0,0 +1,71 @@
+audio:
+  chunk_size: 352800
+  dim_f: 1024
+  dim_t: 801
+  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:
+  - Vocals
+  - Instrumental
+  lr: 1.0e-05
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: Vocals
+  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
+  use_amp: true # enable or disable usage of mixed precision (float16) - usually it must be true
+inference:
+  batch_size: 1
+  dim_t: 801
+  num_overlap: 4

model_bs_roformer_ep_317_sdr_12.9755/model_bs_roformer_ep_317_sdr_12.9755.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b84f37e8d444c8cb30c79d77f613a41c05868ff9c9ac6c7049c00aefae115aa
+size 639331213

model_bs_roformer_ep_317_sdr_12.9755/model_bs_roformer_ep_317_sdr_12.9755.yaml

@@ -0,0 +1,133 @@
+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: 801
+  num_overlap: 4