Delete config.json

config.json

@@ -1,243 +0,0 @@
-{
-    "logger_uri": null,
-    "project_name": "VCTK_European_English_Females",
-    "run_description": "Voices trained using VCTK dataset\n        ",
-    "print_step": 50,
-    "plot_step": 100,
-    "model_param_stats": false,
-    "wandb_entity": null,
-    "dashboard_logger": "tensorboard",
-    "save_on_interrupt": true,
-    "log_model_step": 1000,
-    "save_step": 5000,
-    "save_n_checkpoints": 2,
-    "save_checkpoints": true,
-    "save_all_best": false,
-    "save_best_after": 10000,
-    "target_loss": "loss_1",
-    "print_eval": false,
-    "test_delay_epochs": 0,
-    "run_eval": true,
-    "run_eval_steps": null,
-    "distributed_backend": "nccl",
-    "distributed_url": "tcp://localhost:54321",
-    "mixed_precision": true,
-    "epochs": 1000,
-    "batch_size": 16,
-    "eval_batch_size": 16,
-    "grad_clip": [
-        1000.0,
-        1000.0
-    ],
-    "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": null,
-    "lr_scheduler_params": {},
-    "use_grad_scaler": false,
-    "cudnn_enable": true,
-    "cudnn_deterministic": false,
-    "cudnn_benchmark": false,
-    "training_seed": 54321,
-    "model": "vits",
-    "num_loader_workers": 8,
-    "num_eval_loader_workers": 0,
-    "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,
-    "phoneme_language": "en",
-    "compute_input_seq_cache": true,
-    "text_cleaner": "multilingual_cleaners",
-    "enable_eos_bos_chars": false,
-    "test_sentences_file": "",
-    "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": "iy\u0268\u0289\u026fu\u026a\u028f\u028ae\u00f8\u0258\u0259\u0275\u0264o\u025b\u0153\u025c\u025e\u028c\u0254\u00e6\u0250a\u0276\u0251\u0252\u1d7b\u0298\u0253\u01c0\u0257\u01c3\u0284\u01c2\u0260\u01c1\u029bpbtd\u0288\u0256c\u025fk\u0261q\u0262\u0294\u0274\u014b\u0272\u0273n\u0271m\u0299r\u0280\u2c71\u027e\u027d\u0278\u03b2fv\u03b8\u00f0sz\u0283\u0292\u0282\u0290\u00e7\u029dx\u0263\u03c7\u0281\u0127\u0295h\u0266\u026c\u026e\u028b\u0279\u027bj\u0270l\u026d\u028e\u029f\u02c8\u02cc\u02d0\u02d1\u028dw\u0265\u029c\u02a2\u02a1\u0255\u0291\u027a\u0267\u025a\u02de\u026b'\u0303' ",
-        "is_unique": true,
-        "is_sorted": true
-    },
-    "add_blank": true,
-    "batch_group_size": 48,
-    "loss_masking": null,
-    "min_audio_len": 1,
-    "max_audio_len": 160000,
-    "min_text_len": 1,
-    "max_text_len": Infinity,
-    "compute_f0": false,
-    "compute_energy": false,
-    "compute_linear_spec": true,
-    "precompute_num_workers": 12,
-    "start_by_longest": true,
-    "shuffle": false,
-    "drop_last": false,
-    "datasets": [
-        {
-            "formatter": "vctk",
-            "language": "en"
-        }
-    ],
-    "eval_split_max_size": 256,
-    "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": 284,
-        "out_channels": 513,
-        "spec_segment_size": 32,
-        "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": 0.667,
-        "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": false,
-        "num_speakers": 24,
-        "speakers_file": "supplemental/speakers.pth",
-        "d_vector_file": [
-            "supplemental/speakers.json",
-            "supplemental/dataset-speakers.pth"
-        ],
-        "speaker_embedding_channels": 256,
-        "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": "supplemental/language_ids.json",
-        "use_speaker_encoder_as_loss": true,
-        "speaker_encoder_config_path": "supplemental/config_se.json",
-        "speaker_encoder_model_path": "supplemental/model_se.pth.tar",
-        "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": 24,
-    "use_speaker_embedding": false,
-    "speaker_embedding_channels": 256,
-    "language_ids_file": "supplemental/language_ids.json",
-    "use_language_embedding": true,
-    "use_d_vector_file": true,
-    "d_vector_file": [
-        "supplemental/speakers.json",
-        "supplemental/dataset-speakers.pth"
-    ],
-    "d_vector_dim": 512
-}