| 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 |
| stft_n_fft: 2048 |
| stft_hop_length: 441 |
| stft_win_length: 2048 |
| stft_normalized: False |
| mask_estimator_depth: 3 |
| 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: |
| instruments: |
| - vocals |
| - other |
| target_instrument: vocals |
| use_amp: True |
|
|
| inference: |
| batch_size: 1 |
| dim_t: 1101 |
| num_overlap: 2 |
