encoder: chunk_conformer
encoder_conf:
      activation_type: swish
      positional_dropout_rate: 0.5
      time_reduction_factor: 2
      unified_model_training: true
      default_chunk_size: 16
      jitter_range: 4
      left_chunk_size: 1
      embed_vgg_like: false
      subsampling_factor: 4
      linear_units: 2048
      output_size: 512
      attention_heads: 8
      dropout_rate: 0.5
      positional_dropout_rate: 0.5
      attention_dropout_rate: 0.5
      cnn_module_kernel: 15
      num_blocks: 12    

# decoder related
rnnt_decoder: rnnt
rnnt_decoder_conf:
    embed_size: 512
    hidden_size: 512
    embed_dropout_rate: 0.5
    dropout_rate: 0.5
joint_network_conf:
    joint_space_size: 512

# frontend related
frontend: wav_frontend
frontend_conf:
    fs: 16000
    window: hamming
    n_mels: 80
    frame_length: 25
    frame_shift: 10
    lfr_m: 1
    lfr_n: 1


# Auxiliary CTC
model: rnnt_unified
model_conf:
    auxiliary_ctc_weight: 0.0

# minibatch related
use_amp: true

# optimization related
accum_grad: 1
grad_clip: 5
max_epoch: 120
val_scheduler_criterion:
    - valid
    - loss
best_model_criterion:
-   - valid
    - cer_transducer_chunk
    - min
keep_nbest_models: 10

optim: adam
optim_conf:
   lr: 0.001
scheduler: warmuplr
scheduler_conf:
   warmup_steps: 25000

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
    - 40
    num_freq_mask: 2
    apply_time_mask: true
    time_mask_width_range:
    - 0
    - 50
    num_time_mask: 5

dataset_conf:
    data_names: speech,text
    data_types: sound,text
    shuffle: True
    shuffle_conf:
        shuffle_size: 2048
        sort_size: 500
    batch_conf:
        batch_type: token
        batch_size: 16000
    num_workers: 8

log_interval: 50