💠 Model Weights | Anime-RVC

“Library tempat menyimpan Model RCV atau VITS anime dan Free download.

📑 Model Specifications

Property	Detail
Library Model	Anime-RVC (Retrieval-based Voice Conversion)
Space TTS	Plana-Archive
Lead Developer	Mutsumi Chan
Architecture	RVC v2 / RMVPE
Sample Rate	48kHz (Studio Grade)

📖 Description

A refined neural voice conversion model meticulously trained for the Library Anime TTS ecosystem. This model specializes in preserving tonal inflection and emotional nuances specific to Japanese anime character archetypes. Developed by Mutsumi Chan, the weights have been optimized for low-artifact synthesis and seamless integration into creative workflows.

🛠️ Key Features

🌠 Zero-Shot Conversion: Maintains character identity across diverse input pitches.
🌆 RMVPE Support: Utilizes robust pitch extraction for cleaner high-notes.
📦 Pre-trained Index: Includes a custom .index file to reduce robotic resonance.
🛡️ Privacy Centric: Optimized for local inference via RVC WebUI or CLI.

📥 Access & Integration

Download: Ambil file .pth dan .index dari Plana-Archive.
Deployment: Simpan file di direktori /assets/weights.

🍂 CATATAN : “Kalau terlalu sulit dimengerti, ambil saja atau contohkan dari Space mutsumi karena aku buat tidak Upload model hanya langsung download lewat app.py agar bisa keuploap semua model meskipun memakai CPU bassic dan Ram kecil namun tetap bisa jalan optimal.

Tapi untuk beberapa Space aku private modelnya karna khusus, namun di Scret huggingface Mutsumi memakai "HF_TOKEN" kakak tidak bisa mengambilnya sembarangan Demi keamanan yang Free modelnya tidak aku private kalau kurang paham minta aja Chatbot untuk membuat seperti menyamakan Space aku.

📜 Credits & Licensing

Author: Mutsumi Chan
Affiliation: Library Anime TTS Project
License: CreativeML Open RAIL-M

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support