Spaces:
Running
on
Zero
Running
on
Zero
| audio: | |
| chunk_size: 485100 | |
| 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 | |
| lora: | |
| r: 8 | |
| lora_alpha: 16 # alpha / rank > 1 | |
| lora_dropout: 0.05 | |
| merge_weights: False | |
| fan_in_fan_out: False | |
| enable_lora: [True, False, True] # This for QKV | |
| # enable_lora: [True] # For non-Roformers architectures | |
| model: | |
| dim: 384 | |
| depth: 8 | |
| stereo: true | |
| num_stems: 4 | |
| 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 | |
| mlp_expansion_factor: 2 | |
| use_torch_checkpoint: False # it allows to greatly reduce GPU memory consumption during training (not fully tested) | |
| skip_connection: False # Enable skip connection between transformer blocks - can solve problem with gradients and probably faster training | |
| training: | |
| batch_size: 1 | |
| gradient_accumulation_steps: 1 | |
| grad_clip: 0 | |
| instruments: ['drums', 'bass', 'other', 'vocals'] | |
| patience: 3 | |
| reduce_factor: 0.95 | |
| target_instrument: null | |
| 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: prodigy | |
| optimizer: adam | |
| # lr: 1.0 | |
| lr: 1.0e-5 | |
| 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) | |
| 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: 0.1 | |
| time_stretch_min_rate: 0.8 | |
| time_stretch_max_rate: 1.25 | |
| inference: | |
| batch_size: 2 | |
| dim_t: 1101 | |
| num_overlap: 2 |