config_hop_96.json

{
    "output_path": "/mnt/netapp1/Proxecto_NOS/bsc/tts/training_outputs/0.14.3",
    "logger_uri": null,
    "run_name": "8kHz_vits_V2_lr_diff_1_5_m4_hop_96_ignore_teo_reduced_finetuning",
    "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": 1000,
    "save_step": 10000,
    "save_n_checkpoints": 6,
    "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": 550,
    "batch_size": 64,
    "eval_batch_size": 8,
    "grad_clip": [
        1000.0,
        1000.0
    ],
    "scheduler_after_epoch": false,
    "lr": 0.0007,
    "optimizer": "AdamW",
    "optimizer_params": {
        "betas": [
            0.8,
            0.99
        ],
        "eps": 1e-09,
        "weight_decay": 0.01
    },
    "lr_scheduler": "MultiStepLR",
    "lr_scheduler_params": {
        "gamma": 0.6,
        "milestones": [
            1000000
        ]
    },
    "use_grad_scaler": false,
    "allow_tf32": false,
    "cudnn_enable": true,
    "cudnn_deterministic": false,
    "cudnn_benchmark": false,
    "training_seed": 54321,
    "model": "vits",
    "num_loader_workers": 4,
    "num_eval_loader_workers": 4,
    "use_noise_augment": false,
    "audio": {
        "fft_size": 1024,
        "sample_rate": 8000,
        "win_length": 512,
        "hop_length": 96,
        "num_mels": 80,
        "mel_fmin": 60,
        "mel_fmax": null
    },
    "use_phonemes": true,
    "phonemizer": "espeak",
    "phoneme_language": "ca",
    "compute_input_seq_cache": false,
    "text_cleaner": "basic_cleaners",
    "enable_eos_bos_chars": false,
    "test_sentences_file": "",
    "phoneme_cache_path": "/mnt/netapp1/Proxecto_NOS/bsc/tts/training_outputs/0.14.3/phoneme_cache_festcat_google_10_01_2024",
    "characters": {
        "characters_class": "TTS.tts.models.vits.VitsCharacters",
        "vocab_dict": null,
        "pad": "_",
        "eos": "<EOS>",
        "bos": "<BOS>",
        "blank": null,
        "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz",
        "punctuations": ";:,.!?\u00a1\u00bf\u2014\u2026\"\u00ab\u00bb\u201c\u201d ",
        "phonemes": "\u0251\u0250\u0252\u00e6\u0253\u0299\u03b2\u0254\u0255\u00e7\u0257\u0256\u00f0\u02a4\u0259\u0258\u025a\u025b\u025c\u025d\u025e\u025f\u0284\u0261\u0260\u0262\u029b\u0266\u0267\u0127\u0265\u029c\u0268\u026a\u029d\u026d\u026c\u026b\u026e\u029f\u0271\u026f\u0270\u014b\u0273\u0272\u0274\u00f8\u0275\u0278\u03b8\u0153\u0276\u0298\u0279\u027a\u027e\u027b\u0280\u0281\u027d\u0282\u0283\u0288\u02a7\u0289\u028a\u028b\u2c71\u028c\u0263\u0264\u028d\u03c7\u028e\u028f\u0291\u0290\u0292\u0294\u02a1\u0295\u02a2\u01c0\u01c1\u01c2\u01c3\u02c8\u02cc\u02d0\u02d1\u02bc\u02b4\u02b0\u02b1\u02b2\u02b7\u02e0\u02e4\u02de\u2193\u2191\u2192\u2197\u2198'\u0329'\u1d7b",
        "is_unique": true,
        "is_sorted": true
    },
    "add_blank": true,
    "batch_group_size": 0,
    "loss_masking": null,
    "min_audio_len": 8000,
    "max_audio_len": 100000,
    "min_text_len": 3,
    "max_text_len": 175,
    "compute_f0": false,
    "compute_energy": false,
    "compute_linear_spec": true,
    "precompute_num_workers": 0,
    "start_by_longest": false,
    "shuffle": true,
    "drop_last": true,
    "datasets": [
        {
            "formatter": "vctk_old",
            "dataset_name": "vctk_old_mos_filter",
            "path": "/mnt/netapp1/Proxecto_NOS/bsc/speech_data/fest_google_vctk_denoised_8khz",
            "meta_file_train": "",
            "ignored_speakers": [
                "teo"
            ],
            "language": "ca",
            "phonemizer": "",
            "meta_file_val": "",
            "meta_file_attn_mask": ""
        }
    ],
    "test_sentences": [
        [
            "Per exemple, dels nostres bancs que inverteixen en armament de les nostres empreses.",
            "uri"
        ],
        [
            "Preguntin-se si aix\u00f2 era necessari.",
            "ona"
        ],
        [
            "La suposada ocultaci\u00f3 dels informes que advertien de risc s\u00edsmic.",
            "pau"
        ],
        [
            "\u00c9s de 633 milions d'euros quan es far\u00e0 la publicaci\u00f3 detallada.",
            "eva"
        ]
    ],
    "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": {
        "num_chars": 179,
        "out_channels": 513,
        "spec_segment_size": 64,
        "hidden_channels": 192,
        "hidden_channels_ffn_text_encoder": 768,
        "num_heads_text_encoder": 2,
        "num_layers_text_encoder": 6,
        "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": 2,
        "num_layers_posterior_encoder": 8,
        "kernel_size_flow": 5,
        "dilation_rate_flow": 1,
        "num_layers_flow": 4,
        "resblock_type_decoder": "2",
        "resblock_kernel_sizes_decoder": [
            3,
            5,
            7
        ],
        "resblock_dilation_sizes_decoder": [
            [
                1,
                2
            ],
            [
                2,
                6
            ],
            [
                3,
                12
            ]
        ],
        "upsample_rates_decoder": [
            8,
            4,
            3
        ],
        "upsample_initial_channel_decoder": 256,
        "upsample_kernel_sizes_decoder": [
            16,
            8,
            5
        ],
        "periods_multi_period_discriminator": [
            2,
            3,
            5,
            7,
            11
        ],
        "use_sdp": true,
        "noise_scale": 1.0,
        "inference_noise_scale": 0.667,
        "length_scale": 1.0,
        "noise_scale_dp": 1.0,
        "inference_noise_scale_dp": 1.0,
        "max_inference_len": null,
        "init_discriminator": true,
        "use_spectral_norm_disriminator": false,
        "use_speaker_embedding": true,
        "num_speakers": 241,
        "speakers_file": "speakers.pth",
        "d_vector_file": null,
        "speaker_embedding_channels": 256,
        "use_d_vector_file": false,
        "d_vector_dim": 0,
        "detach_dp_input": true,
        "use_language_embedding": false,
        "embedded_language_dim": 4,
        "num_languages": 0,
        "language_ids_file": null,
        "use_speaker_encoder_as_loss": false,
        "speaker_encoder_config_path": "",
        "speaker_encoder_model_path": "",
        "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": "MultiStepLR",
    "lr_scheduler_gen_params": {
        "gamma": 0.6,
        "milestones": [
            1000000
        ]
    },
    "lr_scheduler_disc": "MultiStepLR",
    "lr_scheduler_disc_params": {
        "gamma": 0.6,
        "milestones": [
            1000000
        ]
    },
    "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": null,
    "weighted_sampler_multipliers": null,
    "r": 1,
    "num_speakers": 0,
    "use_speaker_embedding": false,
    "speakers_file": "/mnt/netapp1/Proxecto_NOS/bsc/tts/training_outputs/0.14.3/8kHz_vits_V2_lr_diff_1_5_m4_hop_96_ignore_teo_reduced_finetuning-January-26-2024_04+43PM-0000000/speakers.pth",
    "speaker_embedding_channels": 256,
    "language_ids_file": null,
    "use_language_embedding": false,
    "use_d_vector_file": false,
    "d_vector_file": null,
    "d_vector_dim": 0
}