{
    "train": {
      "log_interval": 500,
      "eval_interval": 500,
      "seed": 1234,
      "epochs": 20000,
      "learning_rate": 1e-4,
      "betas": [0.8, 0.99],
      "eps": 1e-9,
      "batch_size": 64,
      "fp16_run": false,
      "lr_decay": 0.99875,
      "segment_size": 8192,
      "c_mel": 45,
      "c_kl": 1.0,
      "max_grad_norm_g": 2000.0,
      "max_grad_norm_d": 100.0,
      "max_grad_norm_dur_disc": 2.0,
      "grad_accum_steps": 8,
      "warmup_steps": 500,
      "reset_lr": true,
      "fft_sizes": [384, 683, 171],
      "hop_sizes": [30, 60, 10],
      "win_lengths": [150, 300, 60],
      "window": "hann_window"
    },
    "data": {
      "use_mel_posterior_encoder": true,
      "training_files":[
        "DUMMY1/train_filtered_manifest_ru.txt",
        "DUMMY1/manifests/alexander_vlasov.txt",
        "DUMMY1/manifests/kari.txt",
        "DUMMY1/manifests/nikolay.txt",
        "DUMMY1/manifests/victoria.txt",
        "DUMMY1/manifests/artem_lebedev.txt",
        "DUMMY1/manifests/larisa_actrisa.txt",
        "DUMMY1/manifests/rina.txt"
      ],
      "validation_files":"DUMMY1/val_filtered_manifest_ru.txt",
      "text_cleaners":[],
      "max_wav_value": 32768.0,
      "sampling_rate": 22050,
      "filter_length": 1024,
      "hop_length": 256,
      "win_length": 1024,
      "n_mel_channels": 80,
      "mel_fmin": 0.0,
      "mel_fmax": null,
      "add_blank": true,

      "n_speakers": 9,
      "n_tones": 4,
      "n_languages": 2,

      "cleaned_text": false
    },
    "model": {
      "gin_channels": 192,
      "n_speakers": 9,
      "n_tones": 4,
      "n_languages": 2,

      "monotonic_align": "sma_triton",
      "use_mel_posterior_encoder": true,
      "use_transformer_flows": true,
      "transformer_flow_type": "pre_conv2",
      "use_spk_conditioned_encoder": true,
      "use_noise_scaled_mas": true,
      "use_duration_discriminator": true,
      "duration_discriminator_type": "dur_disc_2",
      "ms_istft_vits": false,
      "mb_istft_vits": true,
      "istft_vits": false,
      "subbands": 4,
      "gen_istft_n_fft": 16,
      "gen_istft_hop_size": 4,
      "inter_channels": 192,
      "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": [4,4],
      "upsample_initial_channel": 512,
      "upsample_kernel_sizes": [16,16],
      "n_layers_q": 3,
      "use_spectral_norm": false,
      "use_sdp": false
    }
  }