Add the models

README.md

@@ -1,5 +1,5 @@
 ---
-title: Sovits Models
+title: Sovits Vtubers
 emoji: 🎙️
 colorFrom: gray
 colorTo: pink
@@ -8,4 +8,5 @@ sdk_version: 3.18.0
 app_file: app.py
 pinned: false
 license: mit
+duplicated_from: sayashi/sovits-models
 ---

app.py

@@ -31,7 +31,7 @@ gr.Audio.postprocess = audio_postprocess
 def create_vc_fn(model, sid):
     def vc_fn(input_audio, vc_transform, auto_f0, tts_text, tts_voice, tts_mode):
         if tts_mode:
-            if len(tts_text) > 100 and limitation:
+            if len(tts_text) > 600 and limitation:
                 return "Text is too long", None
             if tts_text is None or tts_voice is None:
                 return "You need to enter text and select a voice", None
@@ -48,8 +48,8 @@ def create_vc_fn(model, sid):
             return "You need to upload an audio", None
         sampling_rate, audio = input_audio
         duration = audio.shape[0] / sampling_rate
-        if duration > 20 and limitation:
-            return "Please upload an audio file that is less than 20 seconds. If you need to generate a longer audio file, please use Colab.", None
+        if duration > 60 and limitation:
+            return "Please upload an audio file that is less than 60 seconds. If you need to generate a longer audio file, please use Colab.", None
         audio = (audio / np.iinfo(audio.dtype).max).astype(np.float32)
         if len(audio.shape) > 1:
             audio = librosa.to_mono(audio.transpose(1, 0))
@@ -79,10 +79,9 @@ if __name__ == '__main__':
     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"
+        "100% Orange Juice": "https://huggingface.co/spaces/mthsk/sovits-100orangejuice",
+        "Dota 2": "https://huggingface.co/spaces/mthsk/sovits-models",
+        "Miscellanous": "https://huggingface.co/spaces/mthsk/sovits-models-misc"
     }
     voices = []
     tts_voice_list = asyncio.get_event_loop().run_until_complete(edge_tts.list_voices())
@@ -97,10 +96,7 @@ if __name__ == '__main__':
         gr.Markdown(
             "# <center> Sovits Models\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)"
+            "[![Original Repo](https://badgen.net/badge/icon/github?icon=github&label=Original%20Repo)](https://github.com/svc-develop-team/so-vits-svc)\n\n"
 
         )
         with gr.Tabs():
@@ -114,11 +110,11 @@ if __name__ == '__main__':
                         )
                     with gr.Row():
                         with gr.Column():
-                            vc_input = gr.Audio(label="Input audio"+' (less than 20 seconds)' if limitation else '')
+                            vc_input = gr.Audio(label="Input audio"+' (less than 60 seconds)' if limitation else '')
                             vc_transform = gr.Number(label="vc_transform", value=0)
                             auto_f0 = gr.Checkbox(label="auto_f0", value=False)
                             tts_mode = gr.Checkbox(label="tts (use edge-tts as input)", value=False)
-                            tts_text = gr.Textbox(visible=False, label="TTS text (100 words limitation)" if limitation else "TTS text")
+                            tts_text = gr.Textbox(visible=False, label="TTS text (600 words limitation)" if limitation else "TTS text")
                             tts_voice = gr.Dropdown(choices=voices, visible=False)
                             vc_submit = gr.Button("Generate", variant="primary")
                         with gr.Column():

models/amelia/amelia.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ec661a99ab27cc4a3365ab6397f276b89e45d6bde0209eeb8b6a5b9a471e99f
+size 542781471

models/amelia/config.json

@@ -0,0 +1,93 @@
+{
+  "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": 16,
+    "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": {
+    "amelia": 0
+  }
+}

models/haachama/config.json

@@ -0,0 +1,93 @@
+{
+  "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": 16,
+    "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": {
+    "haachama": 0
+  }
+}

models/haachama/haachama.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:546e1c390ab3691de855d23e37c9c648f64d662a4c4fef2689f4aaa3f82bf983
+size 542781471

models/kson/config.json

@@ -0,0 +1,93 @@
+{
+  "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": 16,
+    "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": {
+    "kson": 0
+  }
+}

models/kson/kson.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff00adc23136d5acb1b31466ed813c0bdc55c90366e52637927d059f7ab14bd2
+size 542781471