Upload folder using huggingface_hub

mdx23c/mdx23c_sfx_jasper.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:527f0a98e106fc4e2ad939a8c09d4f59966aa13272c31a530b36598f81c0edd3
+size 1344401799

mdx23c/mdx23c_sfx_jasper_config.yaml

@@ -0,0 +1,52 @@
+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:
+    - foreground
+    - background
+  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

mel_band_roformer/mbr_bgm_jasper.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49248d3e106e95f351b4a51942b87c00b6c3d3f6c0da11f6cf4d86b2d8ba55f9
+size 2739398173

mel_band_roformer/mbr_bgm_jasper_config.yaml

@@ -0,0 +1,69 @@
+audio:
+  chunk_size: 352800
+  dim_f: 1024
+  dim_t: 256
+  hop_length: 441
+  n_fft: 2048
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.0
+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
+  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: 2
+  gradient_accumulation_steps: 1
+  grad_clip: 0
+  instruments:
+    - vocals
+    - other
+  lr: 1.0e-05
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: vocals
+  num_epochs: 1000
+  num_steps: 1000
+  augmentation: false
+  augmentation_type: null
+  use_mp3_compress: false
+  augmentation_mix: false
+  augmentation_loudness: false
+  augmentation_loudness_type: 1
+  augmentation_loudness_min: 0
+  augmentation_loudness_max: 0
+  q: 0.95
+  coarse_loss_clip: false
+  ema_momentum: 0.999
+  optimizer: adam
+  other_fix: true
+  use_amp: true
+inference:
+  batch_size: 1
+  dim_t: 256
+  num_overlap: 2

mel_band_roformer/mbr_scratch_aname.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e89b915fb0d4b1f23a9ebed8f499ada3c212256fa6f449e1b2c16412eeb3c38e
+size 725806842

mel_band_roformer/mbr_scratch_aname_config.yaml

@@ -0,0 +1,69 @@
+audio:
+  chunk_size: 485100
+  dim_f: 1024
+  dim_t: 1101
+  hop_length: 441
+  n_fft: 2048
+  num_channels: 2
+  sample_rate: 44100
+  min_mean_abs: 0.0
+model:
+  dim: 320
+  depth: 12
+  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
+  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: 1
+  gradient_accumulation_steps: 1
+  grad_clip: 0.0
+  instruments:
+    - vocals
+    - other
+  lr: 1.0
+  patience: 2
+  reduce_factor: 0.95
+  target_instrument: vocals
+  num_epochs: 1000
+  num_steps: 1000
+  augmentation: true
+  augmentation_type: null
+  use_mp3_compress: false
+  augmentation_mix: true
+  augmentation_loudness: true
+  augmentation_loudness_type: 1
+  augmentation_loudness_min: 0
+  augmentation_loudness_max: 0
+  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: 1101
+  num_overlap: 2

scnet/scnet_huge_4stem1.2_aname.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807f470b13fe073414832f47184a4a59c944ced0713aec7d5f078bf3193e5e1d
+size 395599229

scnet/scnet_huge_4stem1.2_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_huge_4stem_bleedless_aname.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c4a00f4dd9517402d41bfc7e95f544c5f65c805e5106bbd21263a683d649d28
+size 395602493

scnet/scnet_huge_4stem_bleedless_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_huge_4stem_fullness_aname.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c618b00274e3a2f4f279157bb967427ba51eb5d3622d1c8bbecc201e2784bb04
+size 395597693

scnet/scnet_huge_4stem_fullness_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_huge_4stem_str_fullness_aname.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bb7b5ed236314107e7aaf95d59153a479276f8a3640c26a334113efeee2b9d6
+size 395598013

scnet/scnet_huge_4stem_str_fullness_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