Add Elaine's model

app.py

@@ -78,12 +78,6 @@ if __name__ == '__main__':
     args = parser.parse_args()
     hubert_model = utils.get_hubert_model().to(args.device)
     models = []
-    others = {
-        "rudolf": "https://huggingface.co/spaces/sayashi/sovits-rudolf",
-        "teio": "https://huggingface.co/spaces/sayashi/sovits-teio",
-        "goldship": "https://huggingface.co/spaces/sayashi/sovits-goldship",
-        "tannhauser": "https://huggingface.co/spaces/sayashi/sovits-tannhauser"
-    }
     voices = []
     tts_voice_list = asyncio.get_event_loop().run_until_complete(edge_tts.list_voices())
     for r in tts_voice_list:
@@ -95,12 +89,8 @@ if __name__ == '__main__':
         models.append((name, cover, create_vc_fn(model, name)))
     with gr.Blocks() as app:
         gr.Markdown(
-            "# <center> Sovits Models\n"
+            "# <center> KoMETA AI Demo\n"
             "## <center> The input audio should be clean and pure voice without background music.\n"
-            "![visitor badge](https://visitor-badge.glitch.me/badge?page_id=sayashi.Sovits-Umamusume)\n\n"
-            "[![image](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1wfsBbMzmtLflOJeqc5ZnJiLY7L239hJW?usp=share_link)\n\n"
-            "[![Duplicate this Space](https://huggingface.co/datasets/huggingface/badges/raw/main/duplicate-this-space-sm-dark.svg)](https://huggingface.co/spaces/sayashi/sovits-models?duplicate=true)\n\n"
-            "[![Original Repo](https://badgen.net/badge/icon/github?icon=github&label=Original%20Repo)](https://github.com/svc-develop-team/so-vits-svc)"
 
         )
         with gr.Tabs():

models/{alice → elaine}/config.json

@@ -1,93 +1,98 @@
-{
-  "train": {
-    "log_interval": 200,
-    "eval_interval": 800,
-    "seed": 1234,
-    "epochs": 10000,
-    "learning_rate": 0.0001,
-    "betas": [
-      0.8,
-      0.99
-    ],
-    "eps": 1e-09,
-    "batch_size": 32,
-    "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": 99
-  },
-  "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": 256,
-    "ssl_dim": 256,
-    "n_speakers": 200
-  },
-  "spk": {
-    "alice": 0
-  }
+{
+  "train": {
+    "log_interval": 200,
+    "eval_interval": 8000,
+    "seed": 70235,
+    "epochs": 500,
+    "learning_rate": 0.0002,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 8,
+    "fp16_run": false,
+    "bf16_run": true,
+    "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,
+    "num_workers": 4,
+    "log_version": 0,
+    "ckpt_name_by_step": false,
+    "accumulate_grad_batches": 1
+  },
+  "data": {
+    "training_files": "filelists/44k/train.txt",
+    "validation_files": "filelists/44k/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": 256,
+    "ssl_dim": 256,
+    "n_speakers": 200
+  },
+  "spk": {
+    "mommylaine": 0
+  }
 }

models/{alice/alice.pth → elaine/elaine.pth}

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d1bef76e26beeadcae5f716cc0b60abb2aac4aae1316cac709cc439726cf533
-size 180883747
+oid sha256:656c2ea75e261d37496e75e93598a019e09a1bbf70d9d6f9de8f1550ff5a7c3e
+size 542789469