model:
  name: E2TTS_Base
  tokenizer: pinyin
  tokenizer_path: null
  backbone: UNetT
  arch:
    dim: 1024
    depth: 24
    heads: 16
    ff_mult: 4
    text_mask_padding: False
    pe_attn_head: 1
  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