Updated configs

config.json

@@ -1,28 +1,56 @@
 {
-    "model": "vits",
+    "output_path": null,
+    "logger_uri": null,
     "run_name": "",
+    "project_name": null,
     "run_description": "",
-    "epochs": 10000,
-    "batch_size": null,
-    "eval_batch_size": null,
-    "mixed_precision": false,
-    "scheduler_after_epoch": true,
-    "run_eval": true,
-    "test_delay_epochs": 0,
-    "print_eval": false,
     "print_step": 25,
-    "tb_plot_step": 100,
-    "tb_model_param_stats": false,
+    "plot_step": 100,
+    "model_param_stats": false,
+    "wandb_entity": null,
+    "dashboard_logger": "tensorboard",
+    "log_model_step": null,
     "save_step": 10000,
-    "checkpoint": true,
-    "keep_all_best": false,
-    "keep_after": 10000,
-    "num_loader_workers": null,
-    "num_eval_loader_workers": 0,
-    "use_noise_augment": false,
-    "output_path": null,
+    "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,
@@ -35,17 +63,21 @@
         "preemphasis": 0.0,
         "ref_level_db": 20,
         "do_sound_norm": false,
-        "log_func": "np.log10",
+        "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": 20,
-        "do_amp_to_db_linear": true,
+        "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,
@@ -54,62 +86,65 @@
         "stats_path": null
     },
     "use_phonemes": true,
+    "phonemizer": "espeak",
     "phoneme_language": "en",
-    "compute_input_seq_cache": false,
+    "compute_input_seq_cache": true,
     "text_cleaner": "phoneme_cleaners",
-    "phonemizer": "espeak",
     "enable_eos_bos_chars": false,
     "test_sentences_file": "",
-    "phoneme_cache_path": null,
-    "characters":{
-	"characters_class": "TTS.tts.models.vits.VitsCharacters",
-        "pad": "_",
-        "eos": "",
-        "bos": "",
-        "characters": "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz",
-        "punctuations":";:,.!?¡¿—…\"«»“” ",
-        "phonemes":"ɑɐɒæɓʙβɔɕçɗɖðʤəɘɚɛɜɝɞɟʄɡɠɢʛɦɧħɥʜɨɪʝɭɬɫɮʟɱɯɰŋɳɲɴøɵɸθœɶʘɹɺɾɻʀʁɽʂʃʈʧʉʊʋⱱʌɣɤʍχʎʏʑʐʒʔʡʕʢǀǁǂǃˈˌːˑʼʴʰʱʲʷˠˤ˞↓↑→↗↘'̩'ᵻ"
+    "phoneme_cache_path": "./logs/phoneme_cache",
+    "characters": {
+        "characters_class": "TTS.tts.utils.text.characters.IPAPhonemes",
+        "vocab_dict": null,
+        "pad": "<PAD>",
+        "eos": "<EOS>",
+        "bos": "<BOS>",
+        "blank": "<BLNK>",
+        "characters": "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\u02b2\u025a\u02de\u026b",
+        "punctuations": "!'(),-.:;? ",
+        "phonemes": null,
+        "is_unique": false,
+        "is_sorted": true
     },
+    "add_blank": true,
     "batch_group_size": 0,
     "loss_masking": null,
-    "min_seq_len": 13,
-    "max_seq_len": 200,
+    "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,
-    "add_blank": true,
+    "precompute_num_workers": 12,
+    "start_by_longest": false,
     "datasets": [
         {
-            "name": "",
-            "path": "",
-            "meta_file_train": "",
-            "ununsed_speakers": null,
+            "name": "ljspeech",
+            "path": "./datasets/ljspeech/",
+            "meta_file_train": "metadata.csv",
+            "ignored_speakers": null,
+            "language": "en",
             "meta_file_val": "",
             "meta_file_attn_mask": ""
         }
     ],
-    "optimizer": "AdamW",
-    "optimizer_params": {
-        "betas": [
-            0.8,
-            0.99
-        ],
-        "eps": 1e-09,
-        "weight_decay": 0.01
-    },
-    "lr_scheduler": "",
-    "lr_scheduler_params": {},
     "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."
+        [
+            "A rainbow is a meteorological phenomenon that is caused by reflection, refraction and dispersion of light.",
+            "ljspeech",
+            null,
+            "en"
+        ]
     ],
-    "use_speaker_embedding": false,
-    "use_d_vector_file": false,
-    "d_vector_dim": 0,
+    "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": 179,
+        "num_chars": 131,
         "out_channels": 513,
         "spec_segment_size": 32,
         "hidden_channels": 192,
@@ -118,69 +153,75 @@
         "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": "1",
+        "resblock_type_decoder": "2",
         "resblock_kernel_sizes_decoder": [
             3,
-            7,
-            11
+            5,
+            7
         ],
         "resblock_dilation_sizes_decoder": [
             [
                 1,
-                3,
-                5
+                2
             ],
             [
-                1,
-                3,
-                5
+                2,
+                6
             ],
             [
-                1,
                 3,
-                5
+                12
             ]
         ],
         "upsample_rates_decoder": [
             8,
             8,
-            2,
-            2
+            4
         ],
-        "upsample_initial_channel_decoder": 512,
+        "upsample_initial_channel_decoder": 256,
         "upsample_kernel_sizes_decoder": [
             16,
             16,
-            4,
-            4
+            8
         ],
         "use_sdp": true,
         "noise_scale": 1.0,
-        "inference_noise_scale": 0.667,
+        "inference_noise_scale": 0.3,
         "length_scale": 1,
         "noise_scale_dp": 1.0,
-        "inference_noise_scale_dp": 0.8,
+        "inference_noise_scale_dp": 0.3,
         "max_inference_len": null,
         "init_discriminator": false,
         "use_spectral_norm_disriminator": false,
-        "use_speaker_embedding": false,
+        "use_speaker_embedding": true,
         "num_speakers": 0,
-        "speakers_file": null,
+        "speakers_file": "./logs/run-June-03-2022_10+09PM-f3efb56/speakers.json",
+        "d_vector_file": null,
         "speaker_embedding_channels": 256,
         "use_d_vector_file": false,
         "d_vector_dim": 0,
-        "detach_dp_input": true
+        "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
     },
-    "grad_clip": [
-        5,
-        5
-    ],
     "lr_gen": 0.0002,
     "lr_disc": 0.0002,
     "lr_scheduler_gen": "ExponentialLR",
@@ -198,6 +239,17 @@
     "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
+    "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 @@
+{
+    "en": 0
+}

speaker_ids.json

@@ -0,0 +1,4 @@
+{
+    "en": 0,
+    "ljspeech": 0
+}