audio_tokenizer/config.json

{
  "max_audio_seconds": 300,
  "stride_size": 2,
  "avg_pooler": 2,
  "d_model": 1024,
  "scale_embedding": false,
  "kernel_size": 3,
  "activation_function": "gelu",
  "encoder_layers": 24,
  "encoder_skip_layer_id": 3,
  "encoder_attention_heads": 16,
  "encoder_ffn_dim": 4096,
  "encoder_causal": true,
  "encoder_attn_window_size": [
    128,
    0
  ],
  "decoder_layers": 24,
  "decoder_attention_heads": 16,
  "decoder_ffn_dim": 4096,
  "decoder_kernel_size": 3,
  "decoder_stride_size": 2,
  "decoder_causal": true,
  "decoder_attn_window_size": [
    128,
    0
  ],
  "nfft": 960,
  "n_mels": 128,
  "sampling_rate": 24000,
  "hop_length": 240,
  "window_size": 960,
  "vocoder_padding": "same",
  "fmin": 0,
  "fmax": null,
  "num_quantizers": 20,
  "codebook_size": [
    1024,
    1024,
    256,
    128,
    128,
    128,
    128,
    128,
    128,
    128,
    128,
    128,
    128,
    128,
    128,
    128,
    128,
    128,
    128,
    128
  ],
  "threshold_ema_dead_code": 2,
  "position_embedding_type": "rope",
  "rope_theta": 10000,
  "rope_type": "default",
  "ln_type": "LayerNorm",
  "use_istft_only": true,
  "hybrid_attention": true,
  "hybrid_block_size": 8,
  "swa_per_block": 2
}