model: funasr.cli.models.paraformer:Paraformer
model_conf:
  ctc_weight: 0.3
  lsm_weight: 0.1
  length_normalized_loss: false
  predictor_weight: 1.0
  sampling_ratio: 0.4
  use_1st_decoder_loss: true
frontend: wav_frontend
frontend_conf:
  fs: 16000
  window: hamming
  n_mels: 80
  frame_length: 25
  frame_shift: 10
  lfr_m: 1
  lfr_n: 1
train_conf:
  accum_grad: 1
  grad_clip: 5
  max_epoch: 150
  val_scheduler_criterion:
  - valid
  - acc
  best_model_criterion:
  - - valid
    - acc
    - max
  keep_nbest_models: 10
  log_interval: 50
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
predictor: cif_predictor
predictor_conf:
  idim: 256
  threshold: 1.0
  l_order: 1
  r_order: 1
  tail_threshold: 0.45
dataset_conf:
  data_names: speech,text
  data_types: sound,text
  shuffle: true
  shuffle_conf:
    shuffle_size: 2048
    sort_size: 500
  batch_conf:
    batch_type: example
    batch_size: 2
  num_workers: 8
normalize: null
model_pretrain: damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch
token_list: /Users/zhifu/.cache/modelscope/hub/damo/speech_paraformer-large_asr_nat-zh-cn-16k-common-vocab8404-pytorch/tokens.txt
train_data_set_list: /Users/zhifu/funasr_github/test_local/aishell2_dev_ios/asr_task_debug_len.jsonl
output_dir: /nfs/zhifu.gzf/ckpt/funasr2/exp2