Downloads · 30 days
2.1K
72% of all-time downloads
MamreTTS
notmax123/MamreTTS
MamreTTS is a text-to-speech model from notmax123. Use it when you need text read aloud. The card lists the license as cc-by-nc-4.0.
All-time downloads
2.9K
Public
Repo size
8.1 GB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors3.9 GB · 100%
At a glance
- Task
- Text-to-Speech
- License
- cc-by-nc-4.0
- Access
- Public
- Created
- Feb 27, 2026
- Updated
- Feb 28, 2026
- SHA
- cb4d22c4
Base models
Model card
From the Hugging Face model README
🎙️ MamreVoice: State-of-the-Art Hebrew TTS
MamreVoice is a high-performance, end-to-end Text-to-Speech (TTS) and Voice Conversion system specifically optimized for the Hebrew language. Built on the innovative DiffMamba architecture, it delivers expressive, clear, and lifelike synthetic speech.
✨ Features
- Expressive Hebrew Synthesis: Specialized optimization for Hebrew prosody, rhythm, and naturalness.
- Voice Conversion: High-quality voice cloning and identity preservation.
- Phonetics-Aware: Seamless integration with Phonikud for accurate Hebrew diacritization (Niqqud) and vowelization.
- Efficiency: Designed for low computational overhead, enabling real-time performance on modern Nvidia GPU hardware.
🛠️ Technical Overview
Architecture
MamreVoice utilizes DiffMamba, which addresses the computational heavy-lifting of traditional diffusion models by using Mamba blocks. This allows for long-context handling and faster inference without sacrificing audio quality.
Components
- Text Processing: Advanced normalization and diacritization via Phonikud.
- BackBone Model: DiffMamba-based Backbone
- Rest Of The Model: is based on Zonos
- Task
- Text-to-Speech
- License
- cc-by-nc-4.0
- Languages
- he
- Created
- Feb 27, 2026
- Updated
- Feb 28, 2026