Duplicate from Shashashasha/so-vits-fork-vika

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Voice Cloning
+emoji: 😻
+colorFrom: blue
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.27.0
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: Shashashasha/so-vits-fork-vika
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,120 @@
+import json
+from pathlib import Path
+
+import gradio as gr
+import librosa
+import numpy as np
+import torch
+from huggingface_hub import hf_hub_download, list_repo_files
+from so_vits_svc_fork.hparams import HParams
+from so_vits_svc_fork.inference.core import Svc
+
+##########################################################
+# REPLACE THESE VALUES TO CHANGE THE MODEL REPO/CKPT NAME
+##########################################################
+repo_id = "Shashashasha/vika"
+ckpt_name = None  # None will pick latest
+##########################################################
+
+# Figure out the latest generator by taking highest value one.
+# Ex. if the repo has: G_0.pth, G_100.pth, G_200.pth, we'd use G_200.pth
+if ckpt_name is None:
+    latest_id = sorted(
+        [
+            int(Path(x).stem.split("_")[1])
+            for x in list_repo_files(repo_id)
+            if x.startswith("G_") and x.endswith(".pth")
+        ]
+    )[-1]
+    ckpt_name = f"G_{latest_id}.pth"
+
+generator_path = hf_hub_download(repo_id, ckpt_name)
+config_path = hf_hub_download(repo_id, "config.json")
+hparams = HParams(**json.loads(Path(config_path).read_text()))
+speakers = list(hparams.spk.keys())
+device = "cuda" if torch.cuda.is_available() else "cpu"
+model = Svc(net_g_path=generator_path, config_path=config_path, device=device, cluster_model_path=None)
+
+
+def predict(
+    speaker,
+    audio,
+    transpose: int = 0,
+    auto_predict_f0: bool = False,
+    cluster_infer_ratio: float = 0,
+    noise_scale: float = 0.4,
+    f0_method: str = "crepe",
+    db_thresh: int = -40,
+    pad_seconds: float = 0.5,
+    chunk_seconds: float = 0.5,
+    absolute_thresh: bool = False,
+):
+    audio, _ = librosa.load(audio, sr=model.target_sample)
+    audio = model.infer_silence(
+        audio.astype(np.float32),
+        speaker=speaker,
+        transpose=transpose,
+        auto_predict_f0=auto_predict_f0,
+        cluster_infer_ratio=cluster_infer_ratio,
+        noise_scale=noise_scale,
+        f0_method=f0_method,
+        db_thresh=db_thresh,
+        pad_seconds=pad_seconds,
+        chunk_seconds=chunk_seconds,
+        absolute_thresh=absolute_thresh,
+    )
+    return model.target_sample, audio
+
+
+description=f"""
+This app uses models trained with so-vits-svc-fork to clone your voice. Model currently being used is https://hf.co/{repo_id}.
+
+To change the model being served, duplicate the space and update the `repo_id` in `app.py`.
+""".strip()
+
+article="""
+<p style='text-align: center'>
+    <a href='https://github.com/voicepaw/so-vits-svc-fork' target='_blank'>Github Repo</a>
+</p>
+""".strip()
+
+interface_mic = gr.Interface(
+    predict,
+    inputs=[
+        gr.Dropdown(speakers, value=speakers[0], label="Target Speaker"),
+        gr.Audio(type="filepath", source="microphone", label="Source Audio"),
+        gr.Slider(-12, 12, value=0, step=1, label="Transpose (Semitones)"),
+        gr.Checkbox(False, label="Auto Predict F0"),
+        gr.Slider(0.0, 1.0, value=0.0, step=0.1, label='cluster infer ratio'),
+        gr.Slider(0.0, 1.0, value=0.4, step=0.1, label="noise scale"),
+        gr.Dropdown(choices=["crepe", "crepe-tiny", "parselmouth", "dio", "harvest"], value='crepe', label="f0 method"),
+    ],
+    outputs="audio",
+    title="Voice Cloning",
+    description=description,
+    article=article,
+)
+interface_file = gr.Interface(
+    predict,
+    inputs=[
+        gr.Dropdown(speakers, value=speakers[0], label="Target Speaker"),
+        gr.Audio(type="filepath", source="upload", label="Source Audio"),
+        gr.Slider(-12, 12, value=0, step=1, label="Transpose (Semitones)"),
+        gr.Checkbox(False, label="Auto Predict F0"),
+        gr.Slider(0.0, 1.0, value=0.0, step=0.1, label='cluster infer ratio'),
+        gr.Slider(0.0, 1.0, value=0.4, step=0.1, label="noise scale"),
+        gr.Dropdown(choices=["crepe", "crepe-tiny", "parselmouth", "dio", "harvest"], value='crepe', label="f0 method"),
+    ],
+    outputs="audio",
+    title="Voice Cloning",
+    description=description,
+    article=article,
+)
+interface = gr.TabbedInterface(
+    [interface_mic, interface_file],
+    ["Clone From Mic", "Clone From File"],
+)
+
+
+if __name__ == '__main__':
+    interface.launch()

requirements.txt

@@ -0,0 +1,3 @@
+so_vits_svc_fork
+huggingface_hub
+gradio