Upload 4 files

.gitignore

@@ -0,0 +1,4 @@
+__pycache__/
+*.pyc
+rvc/
+.env

README.md

@@ -0,0 +1,55 @@
+---
+title: RVC Voice Conversion CPU
+emoji: 🎙️
+colorFrom: blue
+colorTo: purple
+sdk: gradio
+app_file: app.py
+app_port: 7860
+pinned: false
+---
+
+# RVC Voice Conversion — Hugging Face CPU Basic
+
+CPU-only deployment of the official RVC WebUI.
+
+## What this Space does
+
+- Upload an input voice/song
+- Select an RVC `.pth` voice model
+- Optional `.index` retrieval index
+- Convert voice with RVC
+- Supports CPU inference
+
+## Important
+
+This Space is intended for **inference**, not RVC model training.
+
+You still need an RVC voice model (`.pth`). You can upload/select your own model through the RVC interface.
+
+The first startup downloads the RVC inference assets. This can take several minutes.
+
+## CPU performance
+
+CPU Basic can run RVC, but it is considerably slower than GPU inference. For long songs, expect substantial processing time.
+
+For best CPU performance:
+
+- Use RMVPE only when needed.
+- Keep audio reasonably short while testing.
+- Avoid running several conversions simultaneously.
+- Use a smaller/shorter input when troubleshooting.
+
+## Deployment
+
+1. Create a new Hugging Face Space.
+2. Choose **Gradio**.
+3. Choose **CPU Basic**.
+4. Upload `app.py`, `requirements.txt`, and this `README.md`.
+5. Wait for the Space to build.
+6. Open the Space after it becomes `Running`.
+
+## Official project
+
+RVC-Project / Retrieval-based-Voice-Conversion-WebUI:
+https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI

app.py

@@ -0,0 +1,48 @@
+import os
+import sys
+import subprocess
+from pathlib import Path
+
+# Hugging Face Spaces / CPU-only settings
+os.environ["CUDA_VISIBLE_DEVICES"] = ""
+os.environ["GRADIO_SERVER_NAME"] = "0.0.0.0"
+os.environ["GRADIO_SERVER_PORT"] = "7860"
+os.environ["HF_HUB_DISABLE_TELEMETRY"] = "1"
+
+ROOT = Path(__file__).resolve().parent
+RVC_DIR = ROOT / "rvc"
+
+def run(cmd, cwd=None):
+    print(">>>", " ".join(map(str, cmd)), flush=True)
+    subprocess.check_call(cmd, cwd=cwd)
+
+# Clone the official RVC WebUI at build/start time so the Space stays small.
+if not (RVC_DIR / "infer-web.py").exists():
+    run([
+        "git", "clone", "--depth", "1",
+        "https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git",
+        str(RVC_DIR)
+    ])
+
+# Make RVC's Python modules importable.
+sys.path.insert(0, str(RVC_DIR))
+os.chdir(RVC_DIR)
+
+# Download the inference-only pretrained assets once.
+# RVC's official repository documents hubert_base.pt and rmvpe.pt as required
+# inference assets.
+hubert = RVC_DIR / "assets" / "hubert" / "hubert_base.pt"
+rmvpe = RVC_DIR / "assets" / "rmvpe" / "rmvpe.pt"
+
+if not hubert.exists() or not rmvpe.exists():
+    downloader = RVC_DIR / "tools" / "download_models.py"
+    if downloader.exists():
+        run([sys.executable, str(downloader)], cwd=RVC_DIR)
+
+# Start the official RVC WebUI on the Space's expected port.
+run([
+    sys.executable,
+    "infer-web.py",
+    "--pycmd", sys.executable,
+    "--port", "7860",
+], cwd=RVC_DIR)

requirements.txt

@@ -0,0 +1,51 @@
+# RVC official CPU stack for Python 3.12
+--extra-index-url https://download.pytorch.org/whl/cpu
+
+torch==2.4.1+cpu
+torchaudio==2.4.1+cpu
+torchvision==0.19.1+cpu
+
+setuptools>=75.0,<81
+wheel>=0.45,<1
+packaging>=24.0
+
+av>=15.1.0,<16
+einops>=0.8.0,<1
+faiss-cpu>=1.13.0,<2
+ffmpeg-python>=0.2.0,<1
+FreeSimpleGUI>=5.1.0,<5.2
+librosa>=0.10.2,<0.11
+local-attention>=1.11.0,<2
+hyper-connections>=0.1.8,<0.4.3
+matplotlib>=3.8.2,<4
+networkx>=3.2.0,<4
+numpy>=1.26.4,<2
+onnxruntime>=1.24.4,<2
+coloredlogs>=15.0,<16
+opencv-python-headless>=4.10.0,<5
+praat-parselmouth>=0.4.5,<1
+PyYAML>=6.0
+scikit-learn>=1.6.0,<2
+scipy>=1.13.1,<2
+sounddevice>=0.5.0,<1
+soundfile>=0.13.0,<1
+tensorboard>=2.19.0
+torchfcpe>=0.0.4,<0.1
+tqdm>=4.67.0,<5
+transformers>=4.49.0,<4.50
+
+# RVC imports fairseq directly.
+fairseq @ git+https://github.com/One-sixth/fairseq.git
+
+gradio>=3.14.0,<3.15
+altair>=4.2.0,<5
+anyio>=3.6.2,<4
+fastapi>=0.88.0,<0.100
+httpx>=0.23.0,<0.24
+markdown-it-py>=2.2.0,<3
+mdit-py-plugins>=0.3.3,<0.4
+pydantic>=1.10.13,<2
+pyparsing>=3.0.9,<3.1
+starlette>=0.22.0,<0.28
+websockets>=10.4,<11
+python-dotenv>=1.0,<2