conf/titanet-finetune.yaml

name: &name "TitaNet-Finetune"
sample_rate: &sample_rate 16000

init_from_pretrained_model:
  speaker_tasks:
    name: 'titanet_large'
    include: ["preprocessor","encoder"]
    exclude: ["decoder.final"] # Add specific layer names here to exlude or just ["decoder"] if to exclude all of decoder pretrained weights

model:
  train_ds:
    manifest_filepath: ???
    sample_rate: 16000
    labels: null
    batch_size: 64
    shuffle: True
    is_tarred: False
    tarred_audio_filepaths: null
    tarred_shard_strategy: "scatter"
    augmentor:
      speed:
        prob: 0.3
        sr: *sample_rate
        resample_type: 'kaiser_fast'
        min_speed_rate: 0.95
        max_speed_rate: 1.05

  validation_ds:
    manifest_filepath: ???
    sample_rate: 16000
    labels: null
    batch_size: 128
    shuffle: False

  test_ds:
    manifest_filepath: ???
    sample_rate: 16000
    labels: null
    batch_size: 1
    shuffle: False
    embedding_dir: './embeddings'

  model_defaults:
    filters: 1024
    repeat: 3
    dropout: 0.1
    separable: true
    se: true
    se_context_size: -1
    kernel_size_factor: 1.0
    
  preprocessor:
    _target_: nemo.collections.asr.modules.AudioToMelSpectrogramPreprocessor
    normalize: "per_feature"
    window_size: 0.025
    sample_rate: *sample_rate
    window_stride: 0.01
    window: "hann"
    features: &n_mels 80
    n_fft: 512
    frame_splicing: 1
    dither: 0.00001

  encoder:
    _target_: nemo.collections.asr.modules.ConvASREncoder
    feat_in: *n_mels
    activation: relu
    conv_mask: true

    jasper:
      -   filters: ${model.model_defaults.filters}
          repeat: 1
          kernel: [3]
          stride: [1]
          dilation: [1]
          dropout: 0.0
          residual: false
          separable: ${model.model_defaults.separable}
          se: ${model.model_defaults.se}
          se_context_size: ${model.model_defaults.se_context_size}

      -   filters: ${model.model_defaults.filters}
          repeat:  ${model.model_defaults.repeat}
          kernel: [7]
          stride: [1]
          dilation: [1]
          dropout: ${model.model_defaults.dropout}
          residual: true
          separable: ${model.model_defaults.separable}
          se: ${model.model_defaults.se}
          se_context_size: ${model.model_defaults.se_context_size}

      -   filters: ${model.model_defaults.filters}
          repeat: ${model.model_defaults.repeat}
          kernel: [11]
          stride: [1]
          dilation: [1]
          dropout: ${model.model_defaults.dropout}
          residual: true
          separable: ${model.model_defaults.separable}
          se: ${model.model_defaults.se}
          se_context_size: ${model.model_defaults.se_context_size}

      -   filters: ${model.model_defaults.filters}
          repeat: ${model.model_defaults.repeat}
          kernel: [15]
          stride: [1]
          dilation: [1]
          dropout: ${model.model_defaults.dropout}
          residual: true
          separable: ${model.model_defaults.separable}
          se: ${model.model_defaults.se}
          se_context_size: ${model.model_defaults.se_context_size}

      -   filters: &enc_feat_out 3072
          repeat: 1
          kernel: [1]
          stride: [1]
          dilation: [1]
          dropout: 0.0
          residual: false
          separable: ${model.model_defaults.separable}
          se: ${model.model_defaults.se}
          se_context_size: ${model.model_defaults.se_context_size}

  decoder:
    _target_: nemo.collections.asr.modules.SpeakerDecoder
    feat_in: *enc_feat_out
    num_classes: ???
    pool_mode: 'attention'
    emb_sizes: 192

  loss:
    _target_: nemo.collections.asr.losses.angularloss.AngularSoftmaxLoss # you could also use cross-entrophy loss
    scale: 30
    margin: 0.2

  optim_param_groups:
    encoder:
      lr: .001

  optim:
    name: adamw
    lr: .0001 #(original titanet-large was trained with 0.08 lr)
    weight_decay: 0.0002

    # scheduler setup
    sched:
      name: CosineAnnealing
      warmup_ratio: 0.1
      min_lr: 0.0

trainer:
  devices: 1 # number of gpus (original titanet-large was trained on 4 nodes with 8 gpus each)
  max_epochs: 10
  max_steps: -1 # computed at runtime if not set
  num_nodes: 1
  accelerator: gpu
  strategy: ddp
  deterministic: True
  enable_checkpointing: False
  logger: False
  log_every_n_steps: 1  # Interval of logging.
  val_check_interval: 1.0  # Set to 0.25 to check 4 times per epoch, or an int for number of iterations
  gradient_clip_val: 1.0

exp_manager:
  exp_dir: null
  name: *name
  create_tensorboard_logger: True
  create_checkpoint_callback: True