Init configs

config.json

@@ -0,0 +1,255 @@
+{
+    "output_path": null,
+    "logger_uri": null,
+    "run_name": "",
+    "project_name": null,
+    "run_description": "",
+    "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": -1,
+    "run_eval": true,
+    "distributed_backend": "nccl",
+    "distributed_url": "tcp://localhost:54321",
+    "mixed_precision": true,
+    "epochs": 1000,
+    "batch_size": 32,
+    "eval_batch_size": 4,
+    "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": "",
+    "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": 8,
+    "use_noise_augment": false,
+    "audio": {
+        "fft_size": 1024,
+        "win_length": 1024,
+        "hop_length": 256,
+        "frame_shift_ms": null,
+        "frame_length_ms": null,
+        "stft_pad_mode": "reflect",
+        "sample_rate": 22050,
+        "resample": false,
+        "preemphasis": 0.0,
+        "ref_level_db": 20,
+        "do_sound_norm": false,
+        "log_func": "np.log",
+        "do_trim_silence": true,
+        "trim_db": 45,
+        "do_rms_norm": false,
+        "db_level": null,
+        "power": 1.5,
+        "griffin_lim_iters": 60,
+        "num_mels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "spec_gain": 1.0,
+        "do_amp_to_db_linear": false,
+        "do_amp_to_db_mel": true,
+        "pitch_fmax": 640.0,
+        "pitch_fmin": 0.0,
+        "signal_norm": true,
+        "min_level_db": -100,
+        "symmetric_norm": true,
+        "max_norm": 4.0,
+        "clip_norm": true,
+        "stats_path": null
+    },
+    "use_phonemes": false,
+    "phonemizer": null,
+    "phoneme_language": null,
+    "compute_input_seq_cache": true,
+    "text_cleaner": "multilingual_cleaners",
+    "enable_eos_bos_chars": false,
+    "test_sentences_file": "",
+    "phoneme_cache_path": null,
+    "characters": {
+        "characters_class": "TTS.tts.utils.text.characters.Graphemes",
+        "vocab_dict": null,
+        "pad": "<PAD>",
+        "eos": "<EOS>",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "characters": "abcdefghijklmnopqrstuvwxyz\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\u010d\u0161\u017e\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",
+        "punctuations": "!'(),-.:;? ",
+        "phonemes": null,
+        "is_unique": true,
+        "is_sorted": true
+    },
+    "add_blank": true,
+    "batch_group_size": 0,
+    "loss_masking": null,
+    "sort_by_audio_len": false,
+    "min_audio_len": 32768,
+    "max_audio_len": 132300,
+    "min_text_len": 1,
+    "max_text_len": Infinity,
+    "compute_f0": false,
+    "compute_linear_spec": true,
+    "precompute_num_workers": 12,
+    "start_by_longest": false,
+    "datasets": [
+        {
+            "name": "common_voice",
+            "path": "./datasets/sl_CV/",
+            "meta_file_train": "clean.tsv",
+            "ignored_speakers": null,
+            "language": "sl",
+            "meta_file_val": "",
+            "meta_file_attn_mask": ""
+        }
+    ],
+    "test_sentences": [
+        [
+            "Mavrica je svetlobni pojav v ozra\u010dju, ki ga vidimo v obliki loka spektralnih barv. Nastane zaradi loma, disperzije in odboja son\u010dnih \u017earkov v vodnih kapljicah v zraku.",
+            "MCV_0ea9252477debb73b13ca414dd3dabd2f7da821c8c5491473dad304837875cf9c2ab3788a8ef54b538de28c7aec89493b727b8e18622f220ec61208ff4e8888b",
+            null,
+            "sl"
+        ]
+    ],
+    "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,
+    "model_args": {
+        "num_chars": 132,
+        "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": 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": 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,
+            5,
+            7
+        ],
+        "resblock_dilation_sizes_decoder": [
+            [
+                1,
+                2
+            ],
+            [
+                2,
+                6
+            ],
+            [
+                3,
+                12
+            ]
+        ],
+        "upsample_rates_decoder": [
+            8,
+            8,
+            4
+        ],
+        "upsample_initial_channel_decoder": 256,
+        "upsample_kernel_sizes_decoder": [
+            16,
+            16,
+            8
+        ],
+        "use_sdp": true,
+        "noise_scale": 1.0,
+        "inference_noise_scale": 0.3,
+        "length_scale": 1,
+        "noise_scale_dp": 1.0,
+        "inference_noise_scale_dp": 0.3,
+        "max_inference_len": null,
+        "init_discriminator": false,
+        "use_spectral_norm_disriminator": false,
+        "use_speaker_embedding": true,
+        "num_speakers": 0,
+        "speakers_file": null,
+        "d_vector_file": null,
+        "speaker_embedding_channels": 256,
+        "use_d_vector_file": false,
+        "d_vector_dim": 0,
+        "detach_dp_input": true,
+        "use_language_embedding": true,
+        "embedded_language_dim": 4,
+        "num_languages": 1,
+        "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
+    },
+    "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,
+    "r": 1,
+    "num_speakers": 1,
+    "use_speaker_embedding": true,
+    "speakers_file": null,
+    "speaker_embedding_channels": 256,
+    "language_ids_file": null,
+    "use_language_embedding": true,
+    "use_d_vector_file": false,
+    "d_vector_file": null,
+    "d_vector_dim": 0
+}

language_ids.json

@@ -0,0 +1,3 @@
+{
+    "sl": 0
+}

speaker_ids.json

@@ -0,0 +1,4 @@
+{
+    "sl": 0,
+    "female": 0
+}