config.yaml

model:
  class_path: miocodec.model.MioCodecModel
  init_args:
    config:
      # SSL Feature settings
      local_ssl_layers: [6, 9]
      global_ssl_layers: [1, 2]
      normalize_ssl_features: true

      # Down/up-sampling settings
      downsample_factor: 2
      use_conv_downsample: true

      # Audio settings
      sample_rate: 24000
      n_fft: 1920
      hop_length: 480

      # Wave decoder settings
      use_wave_decoder: true
      wave_upsample_factor: 2
      wave_interpolation_mode: linear
      wave_decoder_dim: 512
      wave_resnet_num_blocks: 2
      wave_resnet_kernel_size: 3
      wave_resnet_num_groups: 32
      wave_resnet_dropout: 0.1
      istft_padding: same

    ssl_feature_extractor:
      class_path: miocodec.module.ssl_extractor.SSLFeatureExtractor
      init_args:
        model_name: wavlm_base_plus
        output_layer: 9
        sample_rate: 24000

    local_encoder:
      class_path: miocodec.module.transformer.Transformer
      init_args:
        dim: 768
        n_layers: 6
        n_heads: 12
        window_size: 125
        use_rope: true
        rope_theta: 10000.0
        max_seq_len: 512
        use_flash_attention: true

    local_quantizer:
      class_path: miocodec.module.fsq.FiniteScalarQuantizer
      init_args:
        input_dim: 768
        output_dim: 768
        levels: [8, 8, 8, 5, 5]  # 12800

    feature_decoder: null

    global_encoder:
      class_path: miocodec.module.global_encoder.GlobalEncoder
      init_args:
        input_channels: 768
        output_channels: 128
        num_layers: 4
        dim: 384
        intermediate_dim: 1152

    # Mel decoder not used
    mel_prenet: null
    mel_decoder: null
    mel_postnet: null

    # Wave decoder components
    wave_prenet:
      class_path: miocodec.module.transformer.Transformer
      init_args:
        dim: 768
        output_dim: 512
        n_layers: 6
        n_heads: 12
        window_size: 65
        use_rope: true
        rope_theta: 10000.0
        max_seq_len: 512
        use_flash_attention: true

    wave_decoder:
      class_path: miocodec.module.transformer.Transformer
      init_args:
        dim: 512
        n_layers: 8
        n_heads: 8
        window_size: 65
        use_rope: true
        rope_theta: 10000.0
        max_seq_len: 512
        adanorm_condition_dim: 128
        use_adaln_zero: true
        use_flash_attention: true