gpt:
  layers: 8
  model_dim: 512
  heads: 8
  max_text_tokens: 120
  max_mel_tokens: 250
  stop_mel_token: 8193
  start_text_token: 8192
  start_mel_token: 8192
  num_mel_codes: 8194
  num_text_tokens: 6681
vocoder:
  name: bigvgan_v2_22khz_80band_256x
  checkpoint: null
  use_fp16: true
  use_deepspeed: false
s2mel:
  checkpoint: models/s2mel.onnx
  preprocess:
    sr: 22050
    n_fft: 1024
    hop_length: 256
    win_length: 1024
    n_mels: 80
    fmin: 0.0
    fmax: 8000.0
dataset:
  bpe_model: models/bpe.model
  vocab_size: 6681
emotions:
  num_dims: 8
  num:
  - 5
  - 6
  - 8
  - 6
  - 5
  - 4
  - 7
  - 6
  matrix_path: models/emotion_matrix.safetensors
inference:
  device: cpu
  use_fp16: false
  batch_size: 1
  top_k: 50
  top_p: 0.95
  temperature: 1.0
  repetition_penalty: 1.0
  length_penalty: 1.0
model_dir: models