############################################
#          Network Architecture           #
############################################
freeze_hubert: False
normalize_wav: True
output_norm: True
init_type: kaiming_uniform # !Warning: need to convergence
enc:
  input_shape: 1024
  dnn_blocks: 2
  dnn_neurons: 1024
  activation: True
ctc:
  enc_n_units: 1024
  blank_id: 0
  dropout_rate: 0.0
hubert_params_path: "exp/hubert/hubert-large-lv60.pdparams"


task_cfg:
  label_rate: 50.0
  sample_rate: 16000
  normalize: True
  enable_padding: False
  max_keep_size: None
  max_sample_size: 250000
  min_sample_size: 32000
  single_target: False
  random_crop: True
  pad_audio: False

model_cfg:
  dropout_input: 0.0
  final_dropout: 0.0
  dropout: 0.0
  attention_dropout: 0.0
  activation_dropout: 0.1
  apply_mask: True
  mask_length: 10
  mask_prob: 0.5
  mask_selection: static
  mask_other: 0.0
  no_mask_overlap: False
  mask_channel_length: 64
  mask_channel_prob: 0.25
  mask_channel_selection: static
  mask_channel_other: 0.0
  no_mask_channel_overlap: False
  feature_grad_mult: 0.0
  layerdrop: 0.1
  normalize: True
  fp16: True
  label_rate: 50
  extractor_mode: layer_norm
  encoder_layers: 24
  encoder_embed_dim: 1024
  encoder_ffn_embed_dim: 4096
  encoder_attention_heads: 16
  activation_fn: gelu
  encoder_layerdrop: 0.1
  dropout_features: 0.0
  final_dim: 768
  untie_final_proj: True
  layer_norm_first: True
  conv_feature_layers: "[(512,10,5)] + [(512,3,2)] * 4 + [(512,2,2)] * 2"
  conv_bias: False
  logit_temp: 0.1
  target_glu: False
  mask_min_space: 1
  mask_channel_min_space: 1
  conv_pos: 128
  conv_pos_groups: 16
  latent_temp: [2.0, 0.5, 0.999995]
  skip_masked: False
  skip_nomask: True

###########################################
#                   Data                  #
###########################################
train_manifest: data/manifest.train-clean-100
dev_manifest: data/manifest.dev
test_manifest: data/manifest.test-clean

###########################################
#              Dataloader                 #
###########################################
vocab_filepath: data/lang_char/vocab.txt 
unit_type: char
mean_std_filepath: ""
preprocess_config: conf/preprocess.yaml
sortagrad: -1 # Feed samples from shortest to longest ; -1: enabled for all epochs 0: disabled other: enabled for other epochs 
batch_size: 4  # Different batch_size may cause large differences in results
maxlen_in: 1500  # 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: 0
subsampling_factor: 1
num_encs: 1
dist_sampler: True
shortest_first: True
return_lens_rate: True
  
############################################
#             Data Augmentation            #
############################################
audio_augment:  # for raw audio 
  sample_rate: 16000
  speeds: [95, 100, 105]

###########################################
#                 Training                #
###########################################
n_epoch: 3
accum_grad: 8
global_grad_clip: 5.0
model_optim: adadelta
model_optim_conf:
  lr: 1.0
  epsilon: 1.0e-6
  rho: 0.95
model_scheduler: constantlr    
model_scheduler_conf:
  warmup_steps: 25000
  lr_decay: 1.0
hubert_optim: adadelta
hubert_optim_conf:
  lr: 0.95
  epsilon: 1.0e-6
  rho: 0.95
hubert_scheduler: constantlr    
hubert_scheduler_conf:
  warmup_steps: 25000
  lr_decay: 1.0
log_interval: 1
checkpoint:
  kbest_n: 50
  latest_n: 5