tts_models/voice_conversion_models--multilingual--vctk--freevc24/config.json

{
    "output_path": "output",
    "logger_uri": null,
    "run_name": "run",
    "project_name": null,
    "run_description": "\ud83d\udc38Coqui trainer run.",
    "print_step": 25,
    "plot_step": 100,
    "model_param_stats": false,
    "wandb_entity": null,
    "dashboard_logger": "tensorboard",
    "log_model_step": null,
    "save_step": 10000,
    "save_n_checkpoints": 5,
    "save_checkpoints": true,
    "save_all_best": false,
    "save_best_after": 10000,
    "target_loss": null,
    "print_eval": false,
    "test_delay_epochs": 0,
    "run_eval": true,
    "run_eval_steps": null,
    "distributed_backend": "nccl",
    "distributed_url": "tcp://localhost:54321",
    "mixed_precision": false,
    "epochs": 1000,
    "batch_size": 32,
    "eval_batch_size": 16,
    "grad_clip": [
        1000,
        1000
    ],
    "scheduler_after_epoch": true,
    "lr": 0.001,
    "optimizer": "AdamW",
    "optimizer_params": {
        "betas": [
            0.8,
            0.99
        ],
        "eps": 1e-09,
        "weight_decay": 0.01
    },
    "lr_scheduler": null,
    "lr_scheduler_params": {},
    "use_grad_scaler": false,
    "cudnn_enable": true,
    "cudnn_deterministic": false,
    "cudnn_benchmark": false,
    "training_seed": 54321,
    "model": "freevc",
    "num_loader_workers": 0,
    "num_eval_loader_workers": 0,
    "use_noise_augment": false,
    "audio": {
        "max_wav_value": 32768.0,
        "input_sample_rate": 16000,
        "output_sample_rate": 24000,
        "filter_length": 1280,
        "hop_length": 320,
        "win_length": 1280,
        "n_mel_channels": 80,
        "mel_fmin": 0.0,
        "mel_fmax": null
    },
    "batch_group_size": 0,
    "loss_masking": null,
    "min_audio_len": 1,
    "max_audio_len": Infinity,
    "min_text_len": 1,
    "max_text_len": Infinity,
    "compute_f0": false,
    "compute_energy": false,
    "compute_linear_spec": true,
    "precompute_num_workers": 0,
    "start_by_longest": false,
    "shuffle": false,
    "drop_last": false,
    "datasets": [
        {
            "formatter": "",
            "dataset_name": "",
            "path": "",
            "meta_file_train": "",
            "ignored_speakers": null,
            "language": "",
            "phonemizer": "",
            "meta_file_val": "",
            "meta_file_attn_mask": ""
        }
    ],
    "test_sentences": [
        [
            "It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent."
        ],
        [
            "Be a voice, not an echo."
        ],
        [
            "I'm sorry Dave. I'm afraid I can't do that."
        ],
        [
            "This cake is great. It's so delicious and moist."
        ],
        [
            "Prior to November 22, 1963."
        ]
    ],
    "eval_split_max_size": null,
    "eval_split_size": 0.01,
    "use_speaker_weighted_sampler": false,
    "speaker_weighted_sampler_alpha": 1.0,
    "use_language_weighted_sampler": false,
    "language_weighted_sampler_alpha": 1.0,
    "use_length_weighted_sampler": false,
    "length_weighted_sampler_alpha": 1.0,
    "model_args": {
        "spec_channels": 641,
        "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": [
            10,
            6,
            4,
            2
        ],
        "upsample_initial_channel": 512,
        "upsample_kernel_sizes": [
            16,
            16,
            4,
            4
        ],
        "n_layers_q": 3,
        "use_spectral_norm": false,
        "gin_channels": 256,
        "ssl_dim": 1024,
        "use_spk": true,
        "num_spks": 0,
        "segment_size": 8960
    },
    "lr_gen": 0.0002,
    "lr_disc": 0.0002,
    "lr_scheduler_gen": "ExponentialLR",
    "lr_scheduler_gen_params": {
        "gamma": 0.999875,
        "last_epoch": -1
    },
    "lr_scheduler_disc": "ExponentialLR",
    "lr_scheduler_disc_params": {
        "gamma": 0.999875,
        "last_epoch": -1
    },
    "kl_loss_alpha": 1.0,
    "disc_loss_alpha": 1.0,
    "gen_loss_alpha": 1.0,
    "feat_loss_alpha": 1.0,
    "mel_loss_alpha": 45.0,
    "dur_loss_alpha": 1.0,
    "speaker_encoder_loss_alpha": 1.0,
    "return_wav": true,
    "use_weighted_sampler": false,
    "weighted_sampler_attrs": {},
    "weighted_sampler_multipliers": {},
    "r": 1,
    "add_blank": true,
    "num_speakers": 0,
    "use_speaker_embedding": false,
    "speakers_file": null,
    "speaker_embedding_channels": 256,
    "language_ids_file": null,
    "use_language_embedding": false,
    "use_d_vector_file": false,
    "d_vector_file": null,
    "d_vector_dim": null
}