audiotokenizer/speechtokenizer_hubert_avg_config.json

{
    "resblock": "1",
    "num_gpus": 3,
    "batch_size": 60,
    "learning_rate": 0.0001,
    "adam_b1": 0.5,
    "adam_b2": 0.9,
    "lr_decay": 0.98,
    "seed": 1234,
    "lambda_distill": 0.15,

    "n_filters": 64,
    "strides": [8,5,4,2],
    "dimension": 1024,
    "semantic_dimension": 768,
    "bidirectional": true,
    "dilation_base": 2,
    "residual_kernel_size": 3,
    "n_residual_layers": 1,
    "lstm_layers": 2,
    "activation": "ELU",


    "segment_size": 48000,
    "num_mels": 80,
    "num_freq": 1025,
    "n_fft": 1024,
    "hop_size": 240,
    "win_size": 1024,

    "sampling_rate": 16000,
    "sample_rate": 16000,

    "codebook_size": 1024,
    "n_q": 8,

    "fmin": 0,
    "fmax": 8000,
    "fmax_for_loss": null,

    "num_workers": 12,

    "dist_config": {
        "dist_backend": "nccl",
        "dist_url": "tcp://localhost:54322",
        "world_size": 1
    }
}