model:
  name: F5TTS_Base
  tokenizer: pinyin
  tokenizer_path: null
  backbone: DiT
  arch:
    dim: 1024
    depth: 22
    heads: 16
    ff_mult: 2
    text_dim: 512
    text_mask_padding: False
    conv_layers: 4
    pe_attn_head: 1
    attn_backend: torch
    attn_mask_enabled: False
    checkpoint_activations: False
  mel_spec:
    target_sample_rate: 24000
    n_mel_channels: 100
    hop_length: 256
    win_length: 1024
    n_fft: 1024
    mel_spec_type: vocos
  vocoder:
    is_local: False
    local_path: null