Upload 4 files

BaseModelv2/D_202000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe2b785bb6b09b18cf2a60eb91cd65d0c91e70f1180aebdc74ca02a7b4146ae2
+size 561098185

BaseModelv2/G_202000.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:455eb3adadae39b00f3d2fc522a00d47d1c8a6bcc9fe3a97ec945449738b2dea
+size 548687645

BaseModelv2/README.txt

@@ -0,0 +1,3 @@
+An attempt at creating a second "base" model.
+Used voice clips from Applebloom, Applejack, Cadance, Celestia, Fluttershy, Luna, Pinkie Pie, Rainbow Dash, Rarity, Scootaloo, Starlight Glimmer, Sweetie Belle, Trixie, and Twilight Sparkle.
+Total duration of audio in dataset is ~29 hours.

BaseModelv2/config.json

@@ -0,0 +1,107 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 50000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 18,
+    "fp16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 10240,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "use_sr": true,
+    "max_speclen": 512,
+    "port": "8001",
+    "keep_ckpts": 3
+  },
+  "data": {
+    "training_files": "filelists/train.txt",
+    "validation_files": "filelists/val.txt",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": 22050,
+    "contentvec_final_proj": false
+  },
+  "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,
+      2
+    ],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [
+      16,
+      16,
+      4,
+      4,
+      4
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "ssl_dim": 768,
+    "n_speakers": 200
+  },
+  "spk": {
+    "Applebloom": 0,
+    "Applejack": 1,
+    "Cadance": 2,
+    "Celestia": 3,
+    "Fluttershy": 4,
+    "Luna": 5,
+    "Pinkie": 6,
+    "RainbowDash": 7,
+    "Rarity": 8,
+    "Scootaloo": 9,
+    "Starlight": 10,
+    "SweetieBelle": 11,
+    "Trixie": 12,
+    "Twilight Sparkle": 13
+  }
+}