upload AIs

app.py

@@ -95,7 +95,7 @@ if __name__ == '__main__':
         models.append((name, cover, create_fn(model, name)))
     with gr.Blocks() as app:
         gr.Markdown(
-            "# <center> 罪恶都市角色语音生成，即将上线...\n"
+            "# <center> 罪恶都市角色语音生成\n"
             "## <center> 模型作者：B站[Cyber蝈蝈总](https://space.bilibili.com/37706580)\n"
             "#### <center> 圣安地列斯人物AI语音请移步[GTASA](https://huggingface.co/spaces/GroveStreet/GTA_SOVITS)，使用此资源创作的作品请标明出处\n"
         )

models/cortez/config_cortez.json

@@ -0,0 +1,99 @@
+{
+  "train": {
+    "log_interval": 500,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 6,
+    "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,
+    "all_in_mem": true,
+    "vol_aug": true
+  },
+  "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
+  },
+  "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": 768,
+    "ssl_dim": 768,
+    "n_speakers": 1,
+    "vocoder_name": "nsf-hifigan",
+    "speech_encoder": "vec768l12",
+    "speaker_embedding": false,
+    "vol_embedding": true
+  },
+  "spk": {
+    "cortez": 0
+  }
+}

models/cortez/cortez.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06ea485bf5048c475e519e98e468853422054528c663d80880185f9a5cd99b1b
+size 209238367

models/diaz/config_diaz.json

@@ -0,0 +1,99 @@
+{
+  "train": {
+    "log_interval": 500,
+    "eval_interval": 1000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 6,
+    "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,
+    "all_in_mem": true,
+    "vol_aug": true
+  },
+  "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
+  },
+  "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": 768,
+    "ssl_dim": 768,
+    "n_speakers": 1,
+    "vocoder_name": "nsf-hifigan",
+    "speech_encoder": "vec768l12",
+    "speaker_embedding": false,
+    "vol_embedding": true
+  },
+  "spk": {
+    "diaz": 0
+  }
+}

models/diaz/diaz.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3316c9b3dff6425a0f94c09eeef32b31d63fdde42e4aa59a176aec3cd6a3ad0a
+size 209238367

models/lance/config_lance.json

@@ -0,0 +1,99 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 2000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 6,
+    "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,
+    "all_in_mem": true,
+    "vol_aug": true
+  },
+  "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
+  },
+  "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": 768,
+    "ssl_dim": 768,
+    "n_speakers": 1,
+    "vocoder_name": "nsf-hifigan",
+    "speech_encoder": "vec768l12",
+    "speaker_embedding": false,
+    "vol_embedding": true
+  },
+  "spk": {
+    "lance": 0
+  }
+}

models/lance/lance.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:19e29f0aa87cfc04e4ab7b4ed883dec1ef3a41eeafaded4d3aace89c974c4fed
+size 209238367

models/paul/config_paul.json

@@ -0,0 +1,99 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 5000,
+    "seed": 1234,
+    "epochs": 100000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 6,
+    "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": 10,
+    "all_in_mem": true,
+    "vol_aug": true
+  },
+  "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
+  },
+  "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": 768,
+    "ssl_dim": 768,
+    "n_speakers": 1,
+    "vocoder_name": "nsf-hifigan",
+    "speech_encoder": "vec768l12",
+    "speaker_embedding": false,
+    "vol_embedding": true
+  },
+  "spk": {
+    "paul": 0
+  }
+}

models/paul/paul.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24bc08162e4e894e49fe848a3376be2b112a57e44ed962c9395f0a57bc9f5b8f
+size 209238367

models/rose/config_rose.json

@@ -0,0 +1,99 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 5000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 6,
+    "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": 10,
+    "all_in_mem": true,
+    "vol_aug": true
+  },
+  "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
+  },
+  "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": 768,
+    "ssl_dim": 768,
+    "n_speakers": 1,
+    "vocoder_name": "nsf-hifigan",
+    "speech_encoder": "vec768l12",
+    "speaker_embedding": false,
+    "vol_embedding": true
+  },
+  "spk": {
+    "rose": 0
+  }
+}

models/rose/rose.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a86a9c17eca6a14e2f53b909e6d5bbefd2e78a5ffb820311a38c9a30c1b8d2fd
+size 209238367

models/sonny/config_sonny.json

@@ -0,0 +1,99 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 2000,
+    "seed": 1234,
+    "epochs": 100000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 6,
+    "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,
+    "all_in_mem": false,
+    "vol_aug": true
+  },
+  "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
+  },
+  "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": 768,
+    "ssl_dim": 768,
+    "n_speakers": 1,
+    "vocoder_name": "nsf-hifigan",
+    "speech_encoder": "vec768l12",
+    "speaker_embedding": false,
+    "vol_embedding": true
+  },
+  "spk": {
+    "sonny": 0
+  }
+}

models/sonny/sonny.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4651a28618c39577e05f182ec0e73857bc73e87c2e996d07fa4933de58e5ed43
+size 209238367

models/victor/config_victor.json

@@ -0,0 +1,99 @@
+{
+  "train": {
+    "log_interval": 1000,
+    "eval_interval": 5000,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 6,
+    "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,
+    "all_in_mem": false,
+    "vol_aug": true
+  },
+  "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
+  },
+  "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": 768,
+    "ssl_dim": 768,
+    "n_speakers": 1,
+    "vocoder_name": "nsf-hifigan",
+    "speech_encoder": "vec768l12",
+    "speaker_embedding": false,
+    "vol_embedding": true
+  },
+  "spk": {
+    "victor": 0
+  }
+}

models/victor/victor.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa9b889cb35922b51c1bc5bc5ddad936da29b416a43306cb4d2624222c77e73c
+size 209238367