tts_model/config.json

{
    "output_path": "../checkpoints/VITS-multilingual/VITS_fixes/new/new-SE/use_noise_aument_false/xlarge-ZS-PT-VCTK/pt-en+LibriTTS-fr/speaker_encoder_as_loss_9_alpha/mixed-p-false-bug-SDP-fixed/",
    "logger_uri": null,
    "run_name": "vits_tts-portuguese",
    "project_name": null,
    "run_description": "",
    "print_step": 25,
    "plot_step": 100,
    "model_param_stats": false,
    "wandb_entity": null,
    "dashboard_logger": "tensorboard",
    "save_on_interrupt": true,
    "log_model_step": 10000,
    "save_step": 10000,
    "save_n_checkpoints": 5,
    "save_checkpoints": true,
    "save_all_best": false,
    "save_best_after": 10000,
    "target_loss": null,
    "print_eval": true,
    "test_delay_epochs": -1,
    "run_eval": true,
    "run_eval_steps": null,
    "distributed_backend": "nccl",
    "distributed_url": "tcp://localhost:54321",
    "mixed_precision": false,
    "precision": "fp16",
    "epochs": 1000,
    "batch_size": 52,
    "eval_batch_size": 52,
    "grad_clip": [
        5.0,
        5.0
    ],
    "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": "",
    "lr_scheduler_params": null,
    "use_grad_scaler": false,
    "allow_tf32": false,
    "cudnn_enable": true,
    "cudnn_deterministic": false,
    "cudnn_benchmark": true,
    "training_seed": 54321,
    "model": "vits",
    "num_loader_workers": 4,
    "num_eval_loader_workers": 4,
    "use_noise_augment": false,
    "audio": {
        "fft_size": 1024,
        "sample_rate": 16000,
        "win_length": 1024,
        "hop_length": 256,
        "num_mels": 80,
        "mel_fmin": 0,
        "mel_fmax": null
    },
    "use_phonemes": false,
    "phonemizer": null,
    "phoneme_language": "pt-br",
    "compute_input_seq_cache": false,
    "text_cleaner": "multilingual_cleaners",
    "enable_eos_bos_chars": false,
    "test_sentences_file": "",
    "phoneme_cache_path": null,
    "characters": {
        "characters_class": "TTS.tts.models.vits.VitsCharacters",
        "vocab_dict": null,
        "pad": "_",
        "eos": "&",
        "bos": "*",
        "blank": null,
        "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz\u00af\u00b7\u00df\u00e0\u00e1\u00e2\u00e3\u00e4\u00e6\u00e7\u00e8\u00e9\u00ea\u00eb\u00ec\u00ed\u00ee\u00ef\u00f1\u00f2\u00f3\u00f4\u00f5\u00f6\u00f9\u00fa\u00fb\u00fc\u00ff\u0101\u0105\u0107\u0113\u0119\u011b\u012b\u0131\u0142\u0144\u014d\u0151\u0153\u015b\u016b\u0171\u017a\u017c\u01ce\u01d0\u01d2\u01d4\u0430\u0431\u0432\u0433\u0434\u0435\u0436\u0437\u0438\u0439\u043a\u043b\u043c\u043d\u043e\u043f\u0440\u0441\u0442\u0443\u0444\u0445\u0446\u0447\u0448\u0449\u044a\u044b\u044c\u044d\u044e\u044f\u0451\u0454\u0456\u0457\u0491\u2013!'(),-.:;? ",
        "punctuations": "!'(),-.:;? ",
        "phonemes": "",
        "is_unique": true,
        "is_sorted": true
    },
    "add_blank": true,
    "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": "../../datasets/VCTK-Corpus-removed-silence_16Khz/",
            "meta_file_train": null,
            "ignored_speakers": null,
            "language": "en",
            "phonemizer": "",
            "meta_file_val": null,
            "meta_file_attn_mask": ""
        },
        {
            "formatter": "",
            "dataset_name": "",
            "path": "../../datasets/LibriTTS/LibriTTS/dataset-preprocessed-clean-100-and-360/dataset-22k/",
            "meta_file_train": "metadata_all.csv",
            "ignored_speakers": null,
            "language": "en",
            "phonemizer": "",
            "meta_file_val": "dev-clean_500.csv",
            "meta_file_attn_mask": ""
        },
        {
            "formatter": "",
            "dataset_name": "",
            "path": "../../datasets/TTS-Portuguese-Corpus_16khz/",
            "meta_file_train": "train_TTS-Portuguese_Corpus_metadata.csv",
            "ignored_speakers": null,
            "language": "pt-br",
            "phonemizer": "",
            "meta_file_val": "eval_TTS-Portuguese_Corpus_metadata.csv",
            "meta_file_attn_mask": ""
        },
        {
            "formatter": "",
            "dataset_name": "",
            "path": "../../datasets/M-AILABS/fr_FR",
            "meta_file_train": "",
            "ignored_speakers": null,
            "language": "fr-fr",
            "phonemizer": "",
            "meta_file_val": null,
            "meta_file_attn_mask": null
        }
    ],
    "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.",
            "VCTK_p225",
            null,
            "en"
        ],
        [
            "It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
            "ED",
            null,
            "en"
        ],
        [
            "It took me quite a long time to develop a voice, and now that I have it I'm not going to be silent.",
            "bernard",
            null,
            "en"
        ],
        [
            "This cake is great. It's so delicious and moist.",
            "VCTK_p234",
            null,
            "en"
        ],
        [
            "This cake is great. It's so delicious and moist.",
            "ED",
            null,
            "en"
        ],
        [
            "This cake is great. It's so delicious and moist.",
            "ezwa",
            null,
            "en"
        ],
        [
            "Hoje \u00e9 fundamental encontrar a raz\u00e3o da exist\u00eancia humana.",
            "ED",
            null,
            "pt-br"
        ],
        [
            "Hoje \u00e9 fundamental encontrar a raz\u00e3o da exist\u00eancia humana.",
            "VCTK_p238",
            null,
            "pt-br"
        ],
        [
            "Hoje \u00e9 fundamental encontrar a raz\u00e3o da exist\u00eancia humana.",
            "gilles_g_le_blanc",
            null,
            "pt-br"
        ],
        [
            "Em muitas cidades a popula\u00e7\u00e3o est\u00e1 diminuindo.",
            "ED",
            null,
            "pt-br"
        ],
        [
            "Em muitas cidades a popula\u00e7\u00e3o est\u00e1 diminuindo.",
            "VCTK_p245",
            null,
            "pt-br"
        ],
        [
            "Em muitas cidades a popula\u00e7\u00e3o est\u00e1 diminuindo.",
            "nadine_eckert_boulet",
            null,
            "pt-br"
        ],
        [
            "Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
            "VCTK_p245",
            null,
            "fr-fr"
        ],
        [
            "Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
            "ED",
            null,
            "fr-fr"
        ],
        [
            "Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
            "ezwa",
            null,
            "fr-fr"
        ],
        [
            "Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
            "bernard",
            null,
            "fr-fr"
        ],
        [
            "Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
            "gilles_g_le_blanc",
            null,
            "fr-fr"
        ],
        [
            "Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
            "nadine_eckert_boulet",
            null,
            "fr-fr"
        ],
        [
            "Il m'a fallu beaucoup de temps pour d\u00e9velopper une voix, et maintenant que je l'ai, je ne vais pas me taire.",
            "zeckou",
            null,
            "fr-fr"
        ]
    ],
    "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": true,
    "language_weighted_sampler_alpha": 1.0,
    "use_length_weighted_sampler": false,
    "length_weighted_sampler_alpha": 1.0,
    "model_args": {
        "num_chars": 165,
        "out_channels": 513,
        "spec_segment_size": 62,
        "hidden_channels": 192,
        "hidden_channels_ffn_text_encoder": 768,
        "num_heads_text_encoder": 2,
        "num_layers_text_encoder": 10,
        "kernel_size_text_encoder": 3,
        "dropout_p_text_encoder": 0.1,
        "dropout_p_duration_predictor": 0.5,
        "kernel_size_posterior_encoder": 5,
        "dilation_rate_posterior_encoder": 1,
        "num_layers_posterior_encoder": 16,
        "kernel_size_flow": 5,
        "dilation_rate_flow": 1,
        "num_layers_flow": 4,
        "resblock_type_decoder": "2",
        "resblock_kernel_sizes_decoder": [
            3,
            7,
            11
        ],
        "resblock_dilation_sizes_decoder": [
            [
                1,
                3,
                5
            ],
            [
                1,
                3,
                5
            ],
            [
                1,
                3,
                5
            ]
        ],
        "upsample_rates_decoder": [
            8,
            8,
            2,
            2
        ],
        "upsample_initial_channel_decoder": 512,
        "upsample_kernel_sizes_decoder": [
            16,
            16,
            4,
            4
        ],
        "periods_multi_period_discriminator": [
            2,
            3,
            5,
            7,
            11
        ],
        "use_sdp": true,
        "noise_scale": 1.0,
        "inference_noise_scale": 0.3,
        "length_scale": 1.5,
        "noise_scale_dp": 0.6,
        "inference_noise_scale_dp": 0.3,
        "max_inference_len": null,
        "init_discriminator": true,
        "use_spectral_norm_disriminator": false,
        "use_speaker_embedding": false,
        "num_speakers": 1244,
        "speakers_file": null,
        "d_vector_file": [
            "tts_model/speakers.json"
        ],
        "speaker_embedding_channels": 512,
        "use_d_vector_file": true,
        "d_vector_dim": 512,
        "detach_dp_input": true,
        "use_language_embedding": true,
        "embedded_language_dim": 4,
        "num_languages": 3,
        "language_ids_file": null,
        "use_speaker_encoder_as_loss": true,
        "speaker_encoder_config_path": "tts_model/config_se.json",
        "speaker_encoder_model_path": "tts_model/model_se.pth",
        "condition_dp_on_speaker": true,
        "freeze_encoder": false,
        "freeze_DP": false,
        "freeze_PE": false,
        "freeze_flow_decoder": false,
        "freeze_waveform_decoder": false,
        "encoder_sample_rate": null,
        "interpolate_z": true,
        "reinit_DP": false,
        "reinit_text_encoder": false
    },
    "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": 9.0,
    "return_wav": true,
    "use_weighted_sampler": false,
    "weighted_sampler_attrs": {},
    "weighted_sampler_multipliers": {},
    "r": 1,
    "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": true,
    "d_vector_file": [
        "tts_model/speakers.json"
    ],
    "d_vector_dim": 512
}