Initial model commit

D_16000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1956fea85004e0db5ad70df7de475384a6a826c073e62cfb08c1a5d57c71b22e
+size 561098249

G_16000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a211c75b834704e2e7ff26d7cf59da7b054659c92634546e6a674fca2ced80b
+size 449949678

config.json

@@ -0,0 +1,89 @@
+
+{
+    "model_dir": "/content/drive/MyDrive/models/vits_multi",
+    "train": {
+        "log_interval": 2000,
+        "eval_interval": 2000,
+        "seed": 1234,
+        "epochs": 10,
+        "learning_rate": 0.0002,
+        "betas": [
+            0.8,
+            0.99
+        ],
+        "eps": 1e-09,
+        "batch_size": 10,
+        "fp16_run": true,
+        "lr_decay": 0.999875,
+        "segment_size": 8192,
+        "init_lr_ratio": 1,
+        "warmup_epochs": 0,
+        "c_mel": 45,
+        "c_kl": 1.0
+    },
+    "data": {
+        "training_files": "single_train.csv",
+        "validation_files": "single_val_n_test.csv",
+        "text_cleaners": [
+            "transliteration_cleaners"
+        ],
+        "max_wav_value": 32768.0,
+        "sampling_rate": 22500,
+        "filter_length": 1024,
+        "hop_length": 256,
+        "win_length": 1024,
+        "n_mel_channels": 80,
+        "mel_fmin": 0.0,
+        "mel_fmax": null,
+        "add_blank": true,
+        "n_speakers": 0,
+        "cleaned_text": true
+    },
+    "model": {
+        "inter_channels": 192,
+        "hidden_channels": 192,
+        "filter_channels": 768,
+        "n_heads": 2,
+        "n_layers": 6,
+        "kernel_size": 3,
+        "p_dropout": 0.1,
+        "resblock": "1",
+        "resblock_kernel_sizes": [
+            3,
+            7,
+            11
+        ],
+        "resblock_dilation_sizes": [
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ],
+            [
+                1,
+                3,
+                5
+            ]
+        ],
+        "upsample_rates": [
+            8,
+            8,
+            2,
+            2
+        ],
+        "upsample_initial_channel": 512,
+        "upsample_kernel_sizes": [
+            16,
+            16,
+            4,
+            4
+        ],
+        "n_layers_q": 3,
+        "use_spectral_norm": false
+    }
+}

vocab.txt

@@ -0,0 +1,39 @@
+z
+e
+d
+f
+p
+c
+4
+j
+s
+g
+r
+-
+n
+w
+a
+b
+k
+y
+_
+t
+o
+ŋ
+ 
+'
+l
+h
+v
+i
+u
+m
+–
+3
+1
+0
+2
+x
+q
+5
+6