config_dit_mel_seed_uvit_whisper_small_wavenet.yml

log_dir: "./runs"
save_freq: 1
log_interval: 10
save_interval: 1000
device: "cuda"
epochs: 1000 # number of epochs for first stage training (pre-training)
batch_size: 2
batch_length: 100 # maximum duration of audio in a batch (in seconds)
max_len: 80 # maximum number of frames
pretrained_model: ""
pretrained_encoder: "./temp_ckpt.pth"
load_only_params: False # set to true if do not want to load epoch numbers and optimizer parameters

preprocess_params:
  sr: 22050
  spect_params:
    n_fft: 1024
    win_length: 1024
    hop_length: 256
    n_mels: 80
    fmin: 0
    fmax: "None"

model_params:
  dit_type: "DiT" # uDiT or DiT
  reg_loss_type: "l1" # l1 or l2

  speech_tokenizer:
    type: 'whisper'
    whisper_name: "openai/whisper-small"
    path: "speech_tokenizer_v1.onnx"

  cosyvoice:
    path: "../CosyVoice/pretrained_models/CosyVoice-300M"

  style_encoder:
    dim: 192
    campplus_path: "campplus_cn_common.bin"

  DAC:
    encoder_dim: 64
    encoder_rates: [2, 5, 5, 6]
    decoder_dim: 1536
    decoder_rates: [ 6, 5, 5, 2 ]
    sr: 24000

  length_regulator:
    channels: 512
    is_discrete: false
    in_channels: 768
    content_codebook_size: 2048
    sampling_ratios: [1, 1, 1, 1]
    vector_quantize: false
    n_codebooks: 1
    quantizer_dropout: 0.0
    f0_condition: false
    n_f0_bins: 512

  DiT:
    hidden_dim: 512
    num_heads: 8
    depth: 13
    class_dropout_prob: 0.1
    block_size: 8192
    in_channels: 80
    style_condition: true
    final_layer_type: 'wavenet'
    target: 'mel' # mel or codec
    content_dim: 512
    content_codebook_size: 1024
    content_type: 'discrete'
    f0_condition: false
    n_f0_bins: 512
    content_codebooks: 1
    is_causal: false
    long_skip_connection: true
    zero_prompt_speech_token: false # for prompt component, do not input corresponding speech token
    time_as_token: false
    style_as_token: false
    uvit_skip_connection: true
    add_resblock_in_transformer: false

  wavenet:
    hidden_dim: 512
    num_layers: 8
    kernel_size: 5
    dilation_rate: 1
    p_dropout: 0.2
    style_condition: true

loss_params:
  base_lr: 0.0001
  lambda_mel: 45
  lambda_kl: 1.0