fix conflict

.gitattributes

@@ -32,3 +32,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text

jp/config.json

@@ -0,0 +1,57 @@
+{
+    "train": {
+      "log_interval": 200,
+      "eval_interval": 3000,
+      "seed": 1234,
+      "epochs": 10000,
+      "learning_rate": 2e-4,
+      "betas": [0.8, 0.99],
+      "eps": 1e-9,
+      "batch_size": 32,
+      "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":"filelists/tr_19.cleaned",
+      "validation_files":"filelists/val_19.cleaned",
+      "text_cleaners":["japanese_cleaners2"],
+      "max_wav_value": 32768.0,
+      "sampling_rate": 22050,
+      "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": 56,
+      "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,
+      "gin_channels": 256
+    },
+    "speakers": ["nen","meg","tou","tsu","miu","azu","rio","eri","kano","かぐや","弥栄","虹夢","あてな","幌子","yoshino","nena","mulasama","mako","小春","芦花"],
+    "symbols": ["_", ",", ".", "!", "?", "-", "~", "\u2026", "A", "E", "I", "N", "O", "Q", "U", "a", "b", "d", "e", "f", "g", "h", "i", "j", "k", "m", "n", "o", "p", "r", "s", "t", "u", "v", "w", "y", "z", "\u0283", "\u02a7", "\u02a6", "\u2193", "\u2191", " "]
+  }
+  

jp/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f030344bed72b127073c3dad4f07858ae06b2fa13367f7e47a96b4e37bf8c0e
+size 121135968

jp_cn/config.json

@@ -0,0 +1,35 @@
+{
+  "train": {
+    "segment_size": 8192
+  },
+  "data": {
+    "text_cleaners":["zh_ja_mixture_cleaners"],
+    "max_wav_value": 32768.0,
+    "sampling_rate": 22050,
+    "filter_length": 1024,
+    "hop_length": 256,
+    "win_length": 1024,
+    "add_blank": true,
+    "n_speakers": 5
+  },
+  "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,
+    "gin_channels": 256
+  },
+  "speakers": ["\u7dbe\u5730\u5be7\u3005", "\u5728\u539f\u4e03\u6d77", "\u5c0f\u8338", "\u5510\u4e50\u541f"],
+  "symbols": ["_", ",", ".", "!", "?", "-", "~", "\u2026", "A", "E", "I", "N", "O", "Q", "U", "a", "b", "d", "e", "f", "g", "h", "i", "j", "k", "l", "m", "n", "o", "p", "r", "s", "t", "u", "v", "w", "y", "z", "\u0283", "\u02a7", "\u02a6", "\u026f", "\u0279", "\u0259", "\u0265", "\u207c", "\u02b0", "`", "\u2192", "\u2193", "\u2191", " "]
+}

jp_cn/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac210365de160dd5db134f9333525e4ff38426a6a24fcb73e24375b09bef15e
+size 121090654

open_jtalk_dic_utf_8-1.11.zip

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfae558c6693804aab0a45f97d9ef2d072656e61a282dc6ad4d9c7d37b4e458e
+size 24023512