Upload config.json with huggingface_hub

config.json

@@ -1,5 +1,5 @@
 {
-    "output_path": "/kaggle/working/train_output/kagg",
+    "output_path": "/kaggle/working/train_output",
     "logger_uri": null,
     "run_name": "vits_fa_female",
     "project_name": null,
@@ -98,54 +98,53 @@
     "drop_last": false,
     "datasets": [
         {
-            "formatter": "mozilla",
-            "dataset_name": "",
-            "path": "/kaggle/input/persian-tts-dataset",
+            "formatter": "mozilla_with_speaker",
+            "dataset_name": "multi_persian",
+            "path": "/kaggle/input",
             "meta_file_train": "metadata.csv",
             "ignored_speakers": null,
-            "language": "",
-            "phonemizer": "",
-            "meta_file_val": "",
-            "meta_file_attn_mask": ""
-        },
-        {
-            "formatter": "mozilla",
-            "dataset_name": "",
-            "path": "/kaggle/input/persian-tts-dataset-famale",
-            "meta_file_train": "metadata.csv",
-            "ignored_speakers": null,
-            "language": "",
-            "phonemizer": "",
-            "meta_file_val": "",
-            "meta_file_attn_mask": ""
-        },
-        {
-            "formatter": "mozilla",
-            "dataset_name": "",
-            "path": "/kaggle/input/persian-tts-dataset-male",
-            "meta_file_train": "metadata.csv",
-            "ignored_speakers": null,
-            "language": "",
-            "phonemizer": "",
+            "language": "fa",
+            "phonemizer": "espeak",
             "meta_file_val": "",
             "meta_file_attn_mask": ""
         }
     ],
     "test_sentences": [
         [
-            "\u0633\u0644\u0637\u0627\u0646 \u0645\u062d\u0645\u0648\u062f \u062f\u0631 \u0632\u0645\u0633\u062a\u0627\u0646\u06cc \u0633\u062e\u062a \u0628\u0647 \u0637\u0644\u062e\u06a9 \u06af\u0641\u062a \u06a9\u0647: \u0628\u0627 \u0627\u06cc\u0646 \u062c\u0627\u0645\u0647 \u06cc \u06cc\u06a9 \u0644\u0627 \u062f\u0631 \u0627\u06cc\u0646 \u0633\u0631\u0645\u0627 \u0686\u0647 \u0645\u06cc \u06a9\u0646\u06cc "
+            "\u0633\u0644\u0637\u0627\u0646 \u0645\u062d\u0645\u0648\u062f \u062f\u0631 \u0632\u0645\u0633\u062a\u0627\u0646\u06cc \u0633\u062e\u062a \u0628\u0647 \u0637\u0644\u062e\u06a9 \u06af\u0641\u062a \u06a9\u0647",
+            "dilara",
+            null,
+            "fa"
+        ],
+        [
+            " \u0628\u0627 \u0627\u06cc\u0646 \u062c\u0627\u0645\u0647 \u06cc \u06cc\u06a9 \u0644\u0627 \u062f\u0631 \u0627\u06cc\u0646 \u0633\u0631\u0645\u0627 \u0686\u0647 \u0645\u06cc \u06a9\u0646\u06cc ",
+            "farid",
+            null,
+            "fa"
         ],
         [
-            "\u0645\u0631\u062f\u06cc \u0646\u0632\u062f \u0628\u0642\u0627\u0644\u06cc \u0622\u0645\u062f \u0648 \u06af\u0641\u062a \u067e\u06cc\u0627\u0632 \u0647\u0645 \u062f\u0647 \u062a\u0627 \u062f\u0647\u0627\u0646 \u0628\u062f\u0627\u0646 \u062e\u0648 \u0634\u0628\u0648\u06cc \u0633\u0627\u0632\u0645."
+            "\u0645\u0631\u062f\u06cc \u0646\u0632\u062f \u0628\u0642\u0627\u0644\u06cc \u0622\u0645\u062f \u0648 \u06af\u0641\u062a \u067e\u06cc\u0627\u0632 \u0647\u0645 \u062f\u0647 \u062a\u0627 \u062f\u0647\u0627\u0646 \u0628\u062f\u0627\u0646 \u062e\u0648 \u0634\u0628\u0648\u06cc \u0633\u0627\u0632\u0645.",
+            "farid",
+            null,
+            "fa"
         ],
         [
-            "\u0627\u0632 \u0645\u0627\u0644 \u062e\u0648\u062f \u067e\u0627\u0631\u0647 \u0627\u06cc \u06af\u0648\u0634\u062a \u0628\u0633\u062a\u0627\u0646 \u0648 \u0632\u06cc\u0631\u0647 \u0628\u0627\u06cc\u06cc \u0645\u0639\u0637\u0651\u0631 \u0628\u0633\u0627\u0632"
+            "\u0627\u0632 \u0645\u0627\u0644 \u062e\u0648\u062f \u067e\u0627\u0631\u0647 \u0627\u06cc \u06af\u0648\u0634\u062a \u0628\u0633\u062a\u0627\u0646 \u0648 \u0632\u06cc\u0631\u0647 \u0628\u0627\u06cc\u06cc \u0645\u0639\u0637\u0651\u0631 \u0628\u0633\u0627\u0632",
+            "dilara",
+            null,
+            "fa"
         ],
         [
-            "\u06cc\u06a9 \u0628\u0627\u0631 \u0647\u0645 \u0627\u0632 \u062c\u0647\u0646\u0645 \u0628\u06af\u0648\u06cc\u06cc\u062f."
+            "\u06cc\u06a9 \u0628\u0627\u0631 \u0647\u0645 \u0627\u0632 \u062c\u0647\u0646\u0645 \u0628\u06af\u0648\u06cc\u06cc\u062f.",
+            "changiz",
+            null,
+            "fa"
         ],
         [
-            "\u06cc\u06a9\u06cc \u0627\u0633\u0628\u06cc \u0628\u0647 \u0639\u0627\u0631\u06cc\u062a \u062e\u0648\u0627\u0633\u062a"
+            "\u06cc\u06a9\u06cc \u0627\u0633\u0628\u06cc \u0628\u0647 \u0639\u0627\u0631\u06cc\u062a \u062e\u0648\u0627\u0633\u062a",
+            "changiz",
+            null,
+            "fa"
         ]
     ],
     "eval_split_max_size": null,
@@ -163,7 +162,7 @@
         "hidden_channels": 192,
         "hidden_channels_ffn_text_encoder": 768,
         "num_heads_text_encoder": 2,
-        "num_layers_text_encoder": 6,
+        "num_layers_text_encoder": 10,
         "kernel_size_text_encoder": 3,
         "dropout_p_text_encoder": 0.1,
         "dropout_p_duration_predictor": 0.5,
@@ -227,19 +226,21 @@
         "use_spectral_norm_disriminator": false,
         "use_speaker_embedding": false,
         "num_speakers": 0,
-        "speakers_file": "train_output/kagg/speakers.pth",
-        "d_vector_file": null,
+        "speakers_file": "train_output/vits_fa_female-March-18-2023_08+54PM-0000000/speakers.pth",
+        "d_vector_file": [
+            "/kaggle/working/speakers.pth"
+        ],
         "speaker_embedding_channels": 256,
-        "use_d_vector_file": false,
-        "d_vector_dim": 0,
+        "use_d_vector_file": true,
+        "d_vector_dim": 512,
         "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": "",
+        "speaker_encoder_config_path": "https://github.com/coqui-ai/TTS/releases/download/speaker_encoder_model/config_se.json",
+        "speaker_encoder_model_path": "https://github.com/coqui-ai/TTS/releases/download/speaker_encoder_model/model_se.pth.tar",
         "condition_dp_on_speaker": true,
         "freeze_encoder": false,
         "freeze_DP": false,
@@ -269,19 +270,23 @@
     "feat_loss_alpha": 1.0,
     "mel_loss_alpha": 45.0,
     "dur_loss_alpha": 1.0,
-    "speaker_encoder_loss_alpha": 1.0,
+    "speaker_encoder_loss_alpha": 9.0,
     "return_wav": true,
-    "use_weighted_sampler": false,
-    "weighted_sampler_attrs": {},
+    "use_weighted_sampler": true,
+    "weighted_sampler_attrs": {
+        "speaker_name": 1.0
+    },
     "weighted_sampler_multipliers": {},
     "r": 1,
-    "num_speakers": 3,
+    "num_speakers": 0,
     "use_speaker_embedding": false,
-    "speakers_file": "train_output/kagg/speakers.pth",
+    "speakers_file": "train_output/vits_fa_female-March-18-2023_08+54PM-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
+    "use_d_vector_file": true,
+    "d_vector_file": [
+        "/kaggle/working/speakers.pth"
+    ],
+    "d_vector_dim": 512
 }