# This is an example that demonstrates how to configure a model file.
# You can modify the configuration according to your own requirements.

# to print the register_table:
# from funasr.register import tables
# tables.print()

# network architecture
model: LLMASR
model_conf:
    lsm_weight: 0.1     # label smoothing option
    length_normalized_loss: true

# encoder
encoder: WhisperWarp
encoder_conf:
    hub: funasr
    init_param_path: "/nfs/maziyang.mzy/models/Whisper-large-v2"
    freeze: true

llm: Vicuna
llm_conf:
  hub: hf
  init_param_path: "/nfs/maziyang.mzy/models/vicuna-7b-v1.5"
  freeze: true

adaptor: Linear
adaptor_conf:
  downsample_rate: 5
  llm_dim: 4096
  encoder_dim: 512

# frontend related
frontend: WhisperFrontend
frontend_conf:
    fs: 16000
    whisper_model: large
    do_pad_trim: true


specaug: SpecAugLFR
specaug_conf:
    apply_time_warp: false
    time_warp_window: 5
    time_warp_mode: bicubic
    apply_freq_mask: true
    freq_mask_width_range:
    - 0
    - 30
    lfr_rate: 6
    num_freq_mask: 1
    apply_time_mask: true
    time_mask_width_range:
    - 0
    - 12
    num_time_mask: 1

train_conf:
  accum_grad: 1
  grad_clip: 5
  max_epoch: 150
  keep_nbest_models: 10
  log_interval: 10

optim: adamw
optim_conf:
   lr: 0.0001
   weight_decay: 0.000001
scheduler: warmuplr
scheduler_conf:
   warmup_steps: 1500

dataset: AudioLLMDataset
dataset_conf:
    index_ds: IndexDSJsonl
    batch_sampler: BatchSampler
    batch_type: example # example or length
    batch_size: 8 # if batch_type is example, batch_size is the numbers of samples; if length, batch_size is source_token_len+target_token_len;
    max_token_length: 2048 # filter samples if source_token_len+target_token_len > max_token_length,
    buffer_size: 500
    shuffle: True
    num_workers: 4
    preprocessor_text: TextPreprocessRemovePunctuation

tokenizer: HuggingfaceTokenizer
tokenizer_conf:
  unk_symbol: <unk>
  init_param_path: "/nfs/maziyang.mzy/models/vicuna-7b-v1.5"