sound_tokenizer/config.json

{
    "model_type": "autoencoder_v2",
    "sampling_rate": 48000,
    "stereo": true,
    "use_wav_as_input": true,
    "normalize_volume": true,
    "hop_size": 1920,
    "input_channels": 1,
    "enc_type": "spec_convnext",
    "enc_dim": 192,
    "enc_intermediate_dim": 768,
    "enc_num_layers": 12,
    "enc_num_blocks": 2,
    "enc_n_fft": 64,
    "enc_hop_length": 16,
    "enc_latent_dim": 128,
    "enc_c_mults": [
        1,
        2,
        4
    ],
    "enc_strides": [
        4,
        5,
        6
    ],
    "enc_identity_init": false,
    "enc_use_snake": true,
    "dec_type": "oobleck",
    "dec_dim": 320,
    "dec_c_mults": [
        1,
        2,
        4,
        8,
        16
    ],
    "dec_strides": [
        2,
        4,
        5,
        6,
        8
    ],
    "dec_use_snake": true,
    "dec_final_tanh": false,
    "dec_out_channels": 2,
    "dec_anti_aliasing": false,
    "dec_use_nearest_upsample": false,
    "dec_use_tanh_at_final": false,
    "bottleneck_type": "vae",
    "bottleneck": {
        "type": "vae"
    },
    "activation": "snakebeta",
    "snake_logscale": true,
    "anti_aliasing": false,
    "use_cuda_kernel": false,
    "causal": false,
    "padding_mode": "zeros",
    "vocoder_input_dim": 64,
    "latent_mean": null,
    "latent_std": null
}