| audio: | |
| chunk_size: 1764000 # samplerate * segment | |
| min_mean_abs: 0.000 | |
| hop_length: 1024 | |
| training: | |
| batch_size: 8 | |
| gradient_accumulation_steps: 1 | |
| grad_clip: 0 | |
| segment: 40 | |
| shift: 1 | |
| samplerate: 44100 | |
| channels: 2 | |
| normalize: true | |
| instruments: ['kick', 'snare', 'cymbals', 'toms'] | |
| target_instrument: null | |
| num_epochs: 1000 | |
| num_steps: 1000 | |
| optimizer: adam | |
| lr: 9.0e-05 | |
| patience: 2 | |
| reduce_factor: 0.95 | |
| q: 0.95 | |
| coarse_loss_clip: true | |
| ema_momentum: 0.999 | |
| other_fix: false # it's needed for checking on multisong dataset if other is actually instrumental | |
| use_amp: false # 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 | |
| inference: | |
| num_overlap: 4 | |
| batch_size: 8 | |
| model: hdemucs | |
| hdemucs: # see demucs/hdemucs.py for a detailed description | |
| channels: 48 | |
| channels_time: null | |
| growth: 2 | |
| nfft: 4096 | |
| wiener_iters: 0 | |
| end_iters: 0 | |
| wiener_residual: False | |
| cac: True | |
| depth: 6 | |
| rewrite: True | |
| hybrid: True | |
| hybrid_old: False | |
| multi_freqs: [] | |
| multi_freqs_depth: 3 | |
| freq_emb: 0.2 | |
| emb_scale: 10 | |
| emb_smooth: True | |
| kernel_size: 8 | |
| stride: 4 | |
| time_stride: 2 | |
| context: 1 | |
| context_enc: 0 | |
| norm_starts: 4 | |
| norm_groups: 4 | |
| dconv_mode: 1 | |
| dconv_depth: 2 | |
| dconv_comp: 4 | |
| dconv_attn: 4 | |
| dconv_lstm: 4 | |
| dconv_init: 0.001 | |
| rescale: 0.1 | |