Add application file

app.py

@@ -81,12 +81,7 @@ 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"
-    }
+    others = {}
     voices = []
     tts_voice_list = asyncio.get_event_loop().run_until_complete(edge_tts.list_voices())
     for r in tts_voice_list:
@@ -129,16 +124,4 @@ if __name__ == '__main__':
                             vc_output2 = gr.Audio(label="Output Audio")
                 vc_submit.click(vc_fn, [vc_input, vc_transform, auto_f0, tts_text, tts_voice, tts_mode], [vc_output1, vc_output2], api_name=f"{name.lower().strip()}")
                 tts_mode.change(change_to_tts_mode, [tts_mode], [vc_input, tts_text, tts_voice, auto_f0])
-            for category, link in others.items():
-                with gr.TabItem(category):
-                    gr.Markdown(
-                        f'''
-                        <center>
-                          <h2>Click to Go</h2>
-                          <a href="{link}">
-                            <img src="https://huggingface.co/datasets/huggingface/badges/raw/main/open-in-hf-spaces-xl-dark.svg"
-                          </a>
-                        </center>
-                        '''
-                    )
         app.queue(concurrency_count=1, api_open=args.api).launch(share=args.share)

models/kobo/config.json

@@ -0,0 +1,93 @@
+{
+  "train": {
+    "log_interval": 100,
+    "eval_interval": 800,
+    "seed": 1234,
+    "epochs": 10000,
+    "learning_rate": 0.0001,
+    "betas": [
+      0.8,
+      0.99
+    ],
+    "eps": 1e-09,
+    "batch_size": 1,
+    "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
+  },
+  "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": {
+    "kobo": 0
+  }
+}

models/kobo/kobo.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e0c00e8497ee213cdb2cb802236209bae5dabb489685d51ea02d93aa62f5c9f
+size 542789469