############################################
#           Network Architecture           #
############################################
cmvn_file: 
cmvn_file_type: "json"
# 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   # sublayer output dropout
    positional_dropout_rate: 0.1
    attention_dropout_rate: 0.0
    input_layer: conv2d # encoder input type, you can chose conv2d, conv2d6 and conv2d8
    normalize_before: True
    cnn_module_kernel: 15
    use_cnn_module: True
    activation_type: 'swish'
    pos_enc_layer_type: 'rpoe_pos' # abs_pos, rel_pos, rope_pos
    selfattention_layer_type: 'rel_selfattn' # unused
    causal: true
    use_dynamic_chunk: true
    cnn_module_norm: 'layer_norm' # using nn.LayerNorm makes model converge faster
    use_dynamic_left_chunk: false
# decoder related
decoder: transformer # transformer, bitransformer
decoder_conf:
    attention_heads: 4
    linear_units: 2048
    num_blocks: 6
    r_num_blocks: 3    # only for bitransformer
    dropout_rate: 0.1  # sublayer output dropout
    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
    reverse_weight: 0.3 # only for bitransformer
    length_normalized_loss: false
    init_type: 'kaiming_uniform' # !Warning: need to convergence

###########################################
#                   Data                  #
###########################################

train_manifest: data/manifest.train
dev_manifest: data/manifest.dev
test_manifest: data/manifest.test


###########################################
#              Dataloader                 #
###########################################

vocab_filepath: data/lang_char/vocab.txt 
spm_model_prefix: ''
unit_type: 'char'
preprocess_config: conf/preprocess.yaml
feat_dim: 80
stride_ms: 10.0
window_ms: 25.0
sortagrad: 0 # Feed samples from shortest to longest ; -1: enabled for all epochs, 0: disabled, other: enabled for 'other' epochs 
batch_size: 32
maxlen_in: 512  # if input length  > maxlen-in, batchsize is automatically reduced
maxlen_out: 150  # if output length > maxlen-out, batchsize is automatically reduced
minibatches: 0 # for debug
batch_count: auto
batch_bins: 0
batch_frames_in: 0
batch_frames_out: 0
batch_frames_inout: 0
num_workers: 2
subsampling_factor: 1
num_encs: 1

###########################################
#                 Training                #
###########################################
n_epoch: 240 
accum_grad: 1
global_grad_clip: 5.0
dist_sampler: True
optim: adam
optim_conf:
  lr: 0.001
  weight_decay: 1.0e-6
scheduler: warmuplr
scheduler_conf:
  warmup_steps: 25000
  lr_decay: 1.0
log_interval: 100
checkpoint:
  kbest_n: 50
  latest_n: 5