Set female config

config.json

@@ -45,7 +45,7 @@
     "use_grad_scaler": false,
     "cudnn_enable": true,
     "cudnn_deterministic": false,
-    "cudnn_benchmark": true,
+    "cudnn_benchmark": false,
     "training_seed": 54321,
     "model": "vits",
     "num_loader_workers": 8,
@@ -58,7 +58,7 @@
         "frame_shift_ms": null,
         "frame_length_ms": null,
         "stft_pad_mode": "reflect",
-        "sample_rate": 16000,
+        "sample_rate": 22050,
         "resample": false,
         "preemphasis": 0.0,
         "ref_level_db": 20,
@@ -78,7 +78,7 @@
         "do_amp_to_db_mel": true,
         "pitch_fmax": 640.0,
         "pitch_fmin": 0.0,
-        "signal_norm": false,
+        "signal_norm": true,
         "min_level_db": -100,
         "symmetric_norm": true,
         "max_norm": 4.0,
@@ -100,7 +100,7 @@
         "eos": "<EOS>",
         "bos": "<BOS>",
         "blank": "<BLNK>",
-        "characters": "a\u0105bc\u0107de\u0119fghijkl\u0142mn\u0144o\u00f3pqrs\u015btuvwxyz\u017a\u017c",
+        "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\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,
@@ -120,12 +120,10 @@
     "start_by_longest": false,
     "datasets": [
         {
-            "name": "mailabs",
-            "path": "./logs/pl_PL",
-            "meta_file_train": "",
-            "ignored_speakers": [
-                "piotr_nater"
-            ],
+            "name": "common_voice",
+            "path": "./datasets/pl_CV/",
+            "meta_file_train": "clean.tsv",
+            "ignored_speakers": null,
             "language": "pl",
             "meta_file_val": "",
             "meta_file_attn_mask": ""
@@ -134,7 +132,7 @@
     "test_sentences": [
         [
             "T\u0119cza, zjawisko optyczne i meteorologiczne, wyst\u0119puj\u0105ce w postaci charakterystycznego wielobarwnego \u0142uku.",
-            "nina_brown",
+            "MCV_72a8725537f15ecfbd2aca0c342ee4ac0367ad23595ccd3d7efadb015af1af5e0614adb92ad6bf009711df662453a870c31467ca0ec71005a00aa82dc5e02a40",
             null,
             "pl"
         ]
@@ -146,7 +144,7 @@
     "use_language_weighted_sampler": true,
     "language_weighted_sampler_alpha": 1.0,
     "model_args": {
-        "num_chars": 50,
+        "num_chars": 129,
         "out_channels": 513,
         "spec_segment_size": 32,
         "hidden_channels": 192,
@@ -165,38 +163,33 @@
         "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,

speaker_ids.json

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