| 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: 0.000 | |
| 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 | |
| mlp_expansion_factor: 1 | |
| training: | |
| instruments: | |
| - vocals | |
| - other | |
| target_instrument: vocals | |
| use_amp: True | |
| inference: | |
| batch_size: 1 | |
| dim_t: 1101 | |
| num_overlap: 2 |