training/configs/hindi_female.yaml

# Hindi Female VITS Training Configuration
# Dataset: OpenSLR Hindi + IndicTTS Hindi Female subset

model:
  name: vits
  hidden_channels: 192
  filter_channels: 768
  n_heads: 2
  n_layers: 6
  kernel_size: 3
  p_dropout: 0.1
  resblock: "1"
  resblock_kernel_sizes: [3, 7, 11]
  resblock_dilation_sizes: [[1, 3, 5], [1, 3, 5], [1, 3, 5]]
  upsample_rates: [8, 8, 2, 2]
  upsample_initial_channel: 512
  upsample_kernel_sizes: [16, 16, 4, 4]
  n_speakers: 1
  gin_channels: 256

audio:
  sample_rate: 22050
  filter_length: 1024
  hop_length: 256
  win_length: 1024
  n_mel_channels: 80
  mel_fmin: 0.0
  mel_fmax: null
  max_wav_value: 32768.0

data:
  training_files: data/hindi_female/metadata_train.csv
  validation_files: data/hindi_female/metadata_val.csv
  text_cleaners: [hindi_cleaners]
  segment_size: 8192
  add_blank: true

training:
  learning_rate: 2e-4
  betas: [0.8, 0.99]
  eps: 1e-9
  batch_size: 32
  fp16: true
  epochs: 1000
  warmup_epochs: 50
  checkpoint_interval: 10000
  eval_interval: 1000
  seed: 42

  # Loss weights
  c_mel: 45
  c_kl: 1.0

language:
  code: hi
  name: Hindi

speaker:
  id: hindi_female_001
  gender: female