| seed: 1234 | |
| # Data | |
| f0_path: '' | |
| p_train: 0.95 | |
| min_frames: null | |
| batch_size: 128 | |
| features: f0_interp,vuv | |
| out_features: norm_f0_interp,vuv | |
| segment_size: null | |
| segment_multi: 16 | |
| num_workers: 4 | |
| vuv_scale: 2 | |
| speaker_stats: '' | |
| recon_loss_fn: l1_loss | |
| # Optimization | |
| learning_rate: 0.0002 | |
| adam_b1: 0.8 | |
| adam_b2: 0.99 | |
| lr_decay: 0.999 | |
| lambda_commit: 0.02 | |
| # VQ params | |
| vq_params: | |
| l_bins: 64 | |
| emb_width: 128 | |
| mu: 0.99 | |
| levels: 1 | |
| # Encoder params | |
| encoder_params: | |
| input_emb_width: 2 | |
| output_emb_width: 128 | |
| levels: 1 | |
| downs_t: | |
| - 4 | |
| strides_t: | |
| - 2 | |
| width: 32 | |
| depth: 4 | |
| m_conv: 1.0 | |
| dilation_growth_rate: 3 | |
| # Decoder params | |
| decoder_params: | |
| input_emb_width: 2 | |
| output_emb_width: 128 | |
| levels: 1 | |
| downs_t: | |
| - 4 | |
| strides_t: | |
| - 2 | |
| width: 32 | |
| depth: 4 | |
| m_conv: 1.0 | |
| dilation_growth_rate: 3 | |