| # network architecture | |
| # encoder related | |
| encoder: conformer | |
| encoder_conf: | |
| output_size: 512 # dimension of attention | |
| attention_heads: 8 | |
| linear_units: 2048 # the number of units of position-wise feed forward | |
| num_blocks: 18 # the number of encoder blocks | |
| dropout_rate: 0.1 | |
| positional_dropout_rate: 0.0 | |
| attention_dropout_rate: 0.0 | |
| input_layer: conv2d6 # encoder input type, you can chose conv2d, conv2d6 and conv2d8 | |
| normalize_before: true | |
| cnn_module_kernel: 15 | |
| use_cnn_module: True | |
| activation_type: 'swish' | |
| macaron_style: True | |
| pos_enc_layer_type: 'rel_pos' | |
| selfattention_layer_type: 'abs_selfattn' | |
| nonorm: False | |
| cnn_prev: True | |
| cnn_after: False | |
| # decoder related | |
| decoder: transformer | |
| decoder_conf: | |
| attention_heads: 4 | |
| linear_units: 2048 | |
| num_blocks: 1 | |
| dropout_rate: 0.0 | |
| positional_dropout_rate: 0.0 | |
| self_attention_dropout_rate: 0.0 | |
| src_attention_dropout_rate: 0.0 | |
| # hybrid CTC/attention | |
| model_conf: | |
| ctc_weight: 1.0 | |
| lsm_weight: 0.1 # label smoothing option | |
| length_normalized_loss: false | |
| raw_wav: False | |
| data_save: True | |
| use_gc: True | |
| w2v_encoder: True | |
| pretrain: True | |
| random_pretrain: False | |
| wav2vec: True | |
| w2v_coef: 1.0 | |
| mpc_didi_ver: False | |
| wav2mpc: False | |
| wav2mpc_reduction: False | |
| mpc_mask_loss: False | |
| mpc_coef: 0.0 | |
| mask: True | |
| quantize_targets: True | |
| project_targets: True | |
| latent_vars: 320 | |
| w2v_reduct: True | |
| w2v_ext_loss: True | |
| w2v_loss_weights: [0.1,0] | |
| w2v_mask_prob: 0.65 | |
| mpc_prob: 0.5 | |
| remove_valbest: False | |
| model: | |
| method: 'npc' # Accepts npc/apc/vqapc | |
| paras: | |
| kernel_size: 15 # Receptive field size (R) = kernel_size + 2*(n_blocks) | |
| mask_size: 5 # Desired input mask size (M_in) as described in NPC paper | |
| n_blocks: 4 # Number of ConvBlocks stacked in NPC model | |
| hidden_size: 512 # Dimension of feature of all layers | |
| dropout: 0.1 # Dropout in ConvBlock | |
| residual: True # Residual connection in ConvBlock | |
| batch_norm: True # Apply BatchNorm in ConvBlock | |
| activate: 'relu' # Activation function of ConvBlock | |
| disable_cross_layer: False # Apply Masked ConvBlock at last layer only | |
| vq: | |
| codebook_size: [64,64,64,64] # Codebook size of each group in VQ-layer | |
| code_dim: [128,128,128,128] # Dim of each group summing up to hidden_size | |
| gumbel_temperature: 1.0 # Temperature of Gumbel Softmax in VQ-layer | |
| collate_conf: | |
| spec_aug: false | |
| # specaugmentation related | |
| spec_aug_conf: | |
| num_time_mask: 2 | |
| num_freq_mask: 2 | |
| max_time_mask: 50 | |
| max_freq_mask: 10 | |
| max_time_warp: 80 | |
| gauss_mask_for_time: False | |
| warp_for_time: False | |
| # dataset related | |
| dataset_conf: | |
| max_length: 4500 | |
| min_length: 80 | |
| max_frames_in_batch: 16000 | |
| batch_type: 'dynamic' # static or dynamic | |
| batch_size: 20 | |
| sort: true | |
| grad_clip: 10 | |
| accum_grad: 2 | |
| max_epoch: 180 | |
| log_interval: 100 | |
| optim: adam | |
| optim_conf: | |
| lr: 0.001 | |
| scheduler: warmuplr # pytorch v1.1.0+ required | |
| scheduler_conf: | |
| warmup_steps: 10000 | |