Model

.gitattributes

@@ -0,0 +1,2 @@
+cover.png filter=lfs diff=lfs merge=lfs -text
+model.pth filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,98 @@
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 20000,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 24,
+    "fp16_run": false,
+    "lr_decay": 0.999875,
+    "segment_size": 16384,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "fft_sizes": [768, 1366, 342],
+    "hop_sizes": [60, 120, 20], 
+    "win_lengths": [300, 600, 120],
+    "window": "hann_window"
+  },
+  "data": {
+    "use_mel_posterior_encoder": true,
+    "training_files": "../datasets/bluearchive_train.txt.cleaned",
+    "validation_files": "../datasets/bluearchive_val.txt.cleaned",
+    "text_cleaners": [
+      "japanese_cleaners2"
+    ],
+    "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": null,
+    "add_blank": false,
+    "n_speakers": 100,
+    "cleaned_text": true
+  },
+  "model": {
+    "use_mel_posterior_encoder": true,
+    "use_transformer_flows": true,
+    "transformer_flow_type": "pre_conv2",
+    "use_spk_conditioned_encoder": false,
+    "use_noise_scaled_mas": true,
+    "use_duration_discriminator": true,
+    "duration_discriminator_type": "dur_disc_2",
+    "ms_istft_vits": false,
+    "mb_istft_vits": true,
+    "istft_vits": false,
+    "subbands": 4,
+    "gen_istft_n_fft": 16,
+    "gen_istft_hop_size": 4,
+    "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": [4,4,2],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [16,16,8],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "use_sdp": false,
+    "gin_channels": 256
+  },
+  "speakers": ["JP_Airi", "JP_Akane", "JP_Akari", "JP_Ako", "JP_Aris", "JP_Arona", "JP_Aru", "JP_Asuna", "JP_Atsuko", "JP_Ayane", "JP_Azusa", "JP_Cherino", "JP_Chihiro", "JP_Chinatsu", "JP_Chise", "JP_Eimi", "JP_Erica", "JP_Fubuki", "JP_Fuuka", "JP_Hanae", "JP_Hanako", "JP_Hare", "JP_Haruka", "JP_Haruna", "JP_Hasumi", "JP_Hibiki", "JP_Hihumi", "JP_Himari", "JP_Hina", "JP_Hinata", "JP_Hiyori", "JP_Hoshino", "JP_Iori", "JP_Iroha", "JP_Izumi", "JP_Izuna", "JP_Juri", "JP_Kaede", "JP_Karin", "JP_Kayoko", "JP_Kazusa", "JP_Kirino", "JP_Koharu", "JP_Kokona", "JP_Kotama", "JP_Kotori", "JP_Main", "JP_Maki", "JP_Mari", "JP_Marina", "JP_Mashiro", "JP_Michiru", "JP_Midori", "JP_Miku", "JP_Mimori", "JP_Misaki", "JP_Miyako", "JP_Miyu", "JP_Moe", "JP_Momoi", "JP_Momoka", "JP_Mutsuki", "JP_NP0013", "JP_Natsu", "JP_Neru", "JP_Noa", "JP_Nodoka", "JP_Nonomi", "JP_Pina", "JP_Rin", "JP_Saki", "JP_Saori", "JP_Saya", "JP_Sena", "JP_Serika", "JP_Serina", "JP_Shigure", "JP_Shimiko", "JP_Shiroko", "JP_Shizuko", "JP_Shun", "JP_ShunBaby", "JP_Sora", "JP_Sumire", "JP_Suzumi", "JP_Tomoe", "JP_Tsubaki", "JP_Tsurugi", "JP_Ui", "JP_Utaha", "JP_Wakamo", "JP_Yoshimi", "JP_Yuuka", "JP_Yuzu", "JP_Zunko"]
+}

model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4174c49e4d393ce83b0b92ec70efc68c07539affba62e6ab5d1eb95f2717185a
+size 162174033