weights_path: hf://kaanhgunay/pocket-tts-tr/model.safetensors@v0.1-base
weights_path_without_voice_cloning: null
default_temperature: 0.3
flow_lm:
  insert_bos_before_voice: true
  dtype: float32
  flow:
    depth: 6
    dim: 512
  transformer:
    d_model: 1024
    hidden_scale: 4
    max_period: 10000
    num_heads: 16
    num_layers: 24
  lookup_table:
    dim: 1024
    n_bins: 4000
    tokenizer: sentencepiece
    tokenizer_path: hf://kaanhgunay/pocket-tts-tr/tokenizer.model@v0.1-base
mimi:
  dtype: float32
  sample_rate: 24000
  inner_dim: 32
  outer_dim: 512
  channels: 1
  frame_rate: 12.5
  seanet:
    dimension: 512
    channels: 1
    n_filters: 64
    n_residual_layers: 1
    ratios:
    - 6
    - 5
    - 4
    kernel_size: 7
    residual_kernel_size: 3
    last_kernel_size: 3
    dilation_base: 2
    pad_mode: constant
    compress: 2
  transformer:
    d_model: 512
    num_heads: 8
    num_layers: 2
    layer_scale: 0.01
    context: 250
    dim_feedforward: 2048
    input_dimension: 512
    output_dimensions:
    - 512
  quantizer:
    dimension: 32
    output_dimension: 512