# network architecture
# encoder related
encoder: conformer
encoder_conf:
    output_size: 256    # dimension of attention
    attention_heads: 4
    linear_units: 2048  # the number of units of position-wise feed forward
    num_blocks: 12      # the number of encoder blocks
    dropout_rate: 0.1
    positional_dropout_rate: 0.1
    attention_dropout_rate: 0.0
    input_layer: conv2d # encoder architecture type
    normalize_before: true
    pos_enc_layer_type: rel_pos
    selfattention_layer_type: rel_selfattn
    activation_type: swish
    macaron_style: true
    use_cnn_module: true
    cnn_module_kernel: 15

# decoder related
decoder: transformer
decoder_conf:
    attention_heads: 4
    linear_units: 2048
    num_blocks: 6
    dropout_rate: 0.1
    positional_dropout_rate: 0.1
    self_attention_dropout_rate: 0.0
    src_attention_dropout_rate: 0.0

# hybrid CTC/attention
model_conf:
    ctc_weight: 0.3
    lsm_weight: 0.1     # label smoothing option
    length_normalized_loss: false

# minibatch related
batch_type: length
batch_bins: 25000
num_workers: 16

# optimization related
accum_grad: 1
grad_clip: 5
max_epoch: 50
val_scheduler_criterion:
    - valid
    - acc
best_model_criterion:
-   - valid
    - acc
    - max
keep_nbest_models: 10

optim: adam
optim_conf:
   lr: 0.0005
scheduler: warmuplr
scheduler_conf:
   warmup_steps: 30000

specaug: specaug
specaug_conf:
    apply_time_warp: true
    time_warp_window: 5
    time_warp_mode: bicubic
    apply_freq_mask: true
    freq_mask_width_range:
    - 0
    - 30
    num_freq_mask: 2
    apply_time_mask: true
    time_mask_width_range:
    - 0
    - 40
    num_time_mask: 2

log_interval: 50
normalize: None