Upload 4 files

Data/dingzhen/config.json

@@ -0,0 +1,108 @@
+{
+  "train": {
+    "log_interval": 50,
+    "eval_interval": 50,
+    "seed": 42,
+    "epochs": 1000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 12,
+    "bf16_run": false,
+    "lr_decay": 0.99995,
+    "segment_size": 16384,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0,
+    "c_commit": 100,
+    "skip_optimizer": true,
+    "freeze_ZH_bert": false,
+    "freeze_JP_bert": false,
+    "freeze_EN_bert": false,
+    "freeze_emo": false
+  },
+  "data": {
+    "training_files": "Data/dingzhen/filelists/train.list",
+    "validation_files": "Data/dingzhen/filelists/val.list",
+    "max_wav_value": 32768.0,
+    "sampling_rate": 44100,
+    "filter_length": 2048,
+    "hop_length": 512,
+    "win_length": 2048,
+    "n_mel_channels": 128,
+    "mel_fmin": 0.0,
+    "mel_fmax": null,
+    "add_blank": true,
+    "n_speakers": 1,
+    "cleaned_text": true,
+    "spk2id": {
+      "dingzhen": 0
+    }
+  },
+  "model": {
+    "use_spk_conditioned_encoder": true,
+    "use_noise_scaled_mas": true,
+    "use_mel_posterior_encoder": false,
+    "use_duration_discriminator": true,
+    "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,
+      8,
+      2,
+      2
+    ],
+    "n_layers_q": 3,
+    "use_spectral_norm": false,
+    "gin_channels": 512,
+    "slm": {
+      "model": "./slm/wavlm-base-plus",
+      "sr": 16000,
+      "hidden": 768,
+      "nlayers": 13,
+      "initial_channel": 64
+    }
+  },
+  "version": "2.3"
+}

Data/dingzhen/models/G_2650.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:540afcc29da68230b57c885fb00dd0dcd897b97f0796fab486ced3ede7fbfef7
+size 728370270

app.py

@@ -392,9 +392,9 @@ if __name__ == "__main__":
         with gr.Row():
             with gr.Column():
                 gr.Markdown(value="""
-               【AI星瞳2.3】在线语音合成（Bert-Vits2 2.3中日英）\n
+               【AI丁真2.0】在线语音合成（Bert-Vits2 2.3中日英）\n
                 作者：Xz乔希 https://space.bilibili.com/5859321\n
-                声音归属：星瞳_Official https://space.bilibili.com/401315430\n
+                声音归属：理塘丁真 https://space.bilibili.com/1463028352\n
                 【AI合集】https://www.modelscope.cn/studios/xzjosh/Bert-VITS2\n
                 Bert-VITS2项目：https://github.com/Stardust-minus/Bert-VITS2\n
                 使用本模型请严格遵守法律法规！\n

config.yml

@@ -4,7 +4,7 @@
 # 拟提供通用路径配置，统一存放数据，避免数据放得很乱
 # 每个数据集与其对应的模型存放至统一路径下，后续所有的路径配置均为相对于datasetPath的路径
 # 不填或者填空则路径为相对于项目根目录的路径
-dataset_path: "Data/XingTong"
+dataset_path: "Data/dingzhen"
 
 # 模型镜像源，默认huggingface，使用openi镜像源需指定openi_token
 mirror: ""
@@ -26,7 +26,7 @@ resample:
 # 注意， “:” 后需要加空格
 preprocess_text:
   # 原始文本文件路径，文本格式应为{wav_path}|{speaker_name}|{language}|{text}。
-  transcription_path: "filelists/Azusa.list"
+  transcription_path: "filelists/.list"
   # 数据清洗后文本路径，可以不填。不填则将在原始文本目录生成
   cleaned_path: ""
   # 训练集路径
@@ -102,7 +102,7 @@ webui:
   # 推理设备
   device: "cpu"
   # 模型路径
-  model: "models/G_11600.pth"
+  model: "models/G_2650.pth"
   # 配置文件路径
   config_path: "config.json"
   # 端口号