Upload folder using huggingface_hub

bs_roformer/bs_karaoke_3stem_giantailab.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:364964794b0c82c843c53099d80b6ecfee852cf2bf42f098515276c779623bb6
+size 1295074954

bs_roformer/bs_karaoke_3stem_giantailab_config.yaml

@@ -0,0 +1,189 @@
+conditional: true
+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: 0.000
+
+model:
+  dim: 512
+  depth: 12
+  stereo: true
+  num_stems: 3
+  time_transformer_depth: 1
+  freq_transformer_depth: 1
+  linear_transformer_depth: 0
+  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: 1
+  gradient_accumulation_steps: 1
+  grad_clip: 0
+  instruments: 
+    - vocals
+    - backing_vocal
+    - instrumental
+  gan_model: 
+    - music 
+    - music 
+    - none
+  mix_instruments:
+    - vocals
+    - backing_vocal
+    - instrumental
+  diffusion_model:
+    - dit
+    - none
+    - none
+  lr: 1.0e-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 # 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: false # mix several stems of same type with some probability (only works for dataset types: 1, 2, 3)
+  mixup_probs: !!python/tuple # 2 additional stems of the same type (1st with prob 0.2, 2nd with prob 0.02)
+    - 0.2
+    - 0.02
+  mixup_loudness_min: 0.5
+  mixup_loudness_max: 1.5
+
+  # 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)
+
+inference:
+  batch_size: 4
+  dim_t: 801
+  num_overlap: 2
+
+
+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"