|
Download README.md from SinsuSquid/Kasane-Teto-UTAU-RVC-v2: direct link, hf CLI and curl.
- Browser
- Download file 3.12 kB
-
https://huggingface.co/SinsuSquid/Kasane-Teto-UTAU-RVC-v2/resolve/main/README.md
- Command line
-
hf download hf://SinsuSquid/Kasane-Teto-UTAU-RVC-v2/README.md
-
curl -L -o README.md https://huggingface.co/SinsuSquid/Kasane-Teto-UTAU-RVC-v2/resolve/main/README.md
3.12 kB
| language: | |
| - ja | |
| - ko | |
| - en | |
| license: other | |
| tags: | |
| - rvc | |
| - rvc-v2 | |
| - voice-conversion | |
| - kasane-teto | |
| - utau | |
| - vocaloid | |
| - applio | |
| # Kasane Teto (ιι³γγ) β Studio Master RVC v2 Model (40kHz) π₯ | |
| > π **Code & Training Pipeline**: Full dataset preparation and training scripts are available on GitHub at [**SinsuSquid/KasaneTeto_RVC**](https://github.com/SinsuSquid/KasaneTeto_RVC). | |
| An artisan, booth-clean **Retrieval-based Voice Conversion (RVC v2)** model for **Kasane Teto (ιι³γγ)**, trained on an enterprise **NVIDIA A100-SXM4-40GB GPU** using the official 2024 uncompressed anechoic studio UTAU voicebank from [kasaneteto.jp](https://kasaneteto.jp/). | |
| --- | |
| ## π 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**. | |
| --- | |
| ## π¦ 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"*) | | |
| --- | |
| ## π 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) | |
| --- | |
| ## π Credits & Licensing | |
| - **Original Character & Voice Provider**: Twindrill (γγ€γ³γγͺγ«) & Oyamano Mayo (ε°ε±±δΉθδΈ). | |
| - **Official Twindrill Portal**: [kasaneteto.jp](https://kasaneteto.jp/) | |
| - **License**: Free for non-commercial fan creations with attribution, adhering strictly to the official [Twindrill Voice License Guidelines](https://kasaneteto.jp/guideline/voice.html). | |
| - **Pipeline & Training**: Trained by [SinsuSquid](https://github.com/SinsuSquid/KasaneTeto_RVC) on NVIDIA A100 GPUs. | |