SinsuSquid/Kasane-Teto-UTAU-RVC-v2

Kasane Teto (重音テト) — Studio Master RVC v2 Model (40kHz) 🥖

🐙 Code & Training Pipeline: Full dataset preparation and training scripts are available on GitHub at SinsuSquid/KasaneTeto_RVC.

An artisan, booth-clean Retrieval-based Voice Conversion (RVC v2) model for Kasane Teto (重音テト), trained on an enterprise NVIDIA A100-SXM4-40GB GPU using the official 2024 uncompressed anechoic studio UTAU voicebank from kasaneteto.jp.

---

🌟 Why This Model?

Most existing Kasane Teto RVC models on the internet suffer from:

• Background music (BGM) bleed and phase cancellation from automated vocal rippers (UVR5).
• Artificial room reverb baked directly into the neural vocoder.
• Glitchy pitch tracking (harvest / pm octave drops).

This model fixes that entirely:

• Zero Reverb / Zero BGM: Sourced directly from 400 clean anechoic booth recordings (TETO-OUset240323.zip).
• State-of-the-art Pitch Tracking: Extracted via RMVPE (Robust Model for Vocal Pitch Estimation).
• Phonetic Timbre: Clustered via ContentVec and indexed with a dedicated 129 MB FAISS .index file.
• Trained on NVIDIA A100 SXM4: 200 epochs, 3,600 gradient updates, lowest Mel-spectral generator loss 36.014.

---

📦 Files in this Repository

File	Size	Description
KasaneTeto.pth	53 MB	HiFi-GAN 40kHz Generator PyTorch model weights
KasaneTeto.index	129 MB	FAISS feature retrieval index
KasaneTeto.onnx	106 MB	Standalone ONNX runtime model (Zero-PyTorch CPU/Edge)
KasaneTeto_RVC_v2.zip	168 MB	One-click bundle for Applio / RVC WebUI
output_teto_kimi.wav	197 KB	Audio sample ("Kimi wa jitsu ni baka da na")

---

🚀 How to Use

Option A: Applio / RVC WebUI (1-Click Install)

1. Copy the download link of KasaneTeto_RVC_v2.zip.
2. In Applio or RVC WebUI, navigate to the Download tab.
3. Paste the URL and click Download Model.

Option B: Manual Placement

• Place KasaneTeto.pth into your logs/ or weights/ folder.
• Place KasaneTeto.index into your logs/KasaneTeto/ folder.

Recommended Inference Settings

• f0 Method: rmvpe
• Index Rate: 0.75 (higher = more distinctive Teto UTAU timbre)
• Protect Consonants: 0.33
• Pitch Shift: 0 (or +12 when converting male vocals to female range)

---

📜 Credits & Licensing

• Original Character & Voice Provider: Twindrill (ツインドリル) & Oyamano Mayo (小山乃舞世).
• Official Twindrill Portal: kasaneteto.jp
• License: Free for non-commercial fan creations with attribution, adhering strictly to the official Twindrill Voice License Guidelines.
• Pipeline & Training: Trained by SinsuSquid on NVIDIA A100 GPUs.