ABBNDZ/ATTS1HG1

ATTS1HG1: High-Performance llama.cpp Implementation of XTTS-v2

ATTS1HG1 v1.1 is a high-speed, native C++ implementation of the Coqui XTTS-v2 model, utilizing the llama.cpp library. It features a custom integrated HiFiGAN vocoder optimized for Vulkan and CPU inference.

<div align="center">

</div>

🚀 Key Features

• —Blazing Fast: Generates audio in < 0.5s on consumer GPUs (RTX 3090) and ~1.0s on CPU.
• —Vulkan Support: Fully optimized HiFiGAN vocoder running on Vulkan (compatible with NVIDIA, AMD, Intel iGPUs).
• —Lightweight: Native C++ application utilizing the llama.cpp, no heavy Python dependencies.
• —Multi-Language: Supports 17 languages.
• —Voice : Supports 58 speaker (similar to XTTS).

🌍 Supported Languages

The model supports the following 17 languages:

⚡ Performance

Benchmarks based on standard text generation ("Bonjour le monde") using the C++ client:

Note: The Vulkan backend is significantly faster for the HiFiGAN part of the pipeline compared to CUDA due to optimized command buffers and reduced kernel launch overhead for small convolutions.

🔧 Key Technical Upgrades

• —Split Model Architecture (GPT2 + HiFiGAN):

• —The text-to-latent model (GPT2) and the vocoder (HiFiGAN) are now separate GGUF files.

• —Allows users to load HiFiGAN via Vulkan for lower latency while keeping GPT2 optimized for CUDA.

• —Result: Up to 3x faster audio generation on RTX series.

• —Advanced Text Preprocessing:

• —Automatic Language Detection (New!):

ATTS now features a robust LanguageDetector class that analyzes input text. Uses Script Range (Unicode blocks), Dictionary (common words), and N-Grams (suffixes/patterns). Supports 17 languages with confidence scoring and fallback logic. In "Auto Mode" (LangDirIndex == 0), the system automatically selects the language for synthesis.

• —MeCab Integration: Native Japanese tokenization and segmentation for natural prosody.

• —Romanization: Automatic romanization for Chinese (Pinyin), Japanese (Romaji), and Korean (Revised Romanization).

• —Num2Words: Converts numbers (e.g., "123") into words ("one hundred twenty-three") across all 17

🛠️ Usage

This repository contains the converted .zip and .gguf weights required by the ATTS1HG1 software.

Zero-Configuration Deployment:

1. 1.Download the Pre-compiled GUI Applications (.zip) and the model files from this repository.

1. 1.No C++ compilation, no Python dependencies, no pip install.

1. 1.Just unzip and run attsguiapp_v1.1.exe.

1. 1.Load the model in the GUI or CLI and select Vulkan for best performance.

🧠 Model Files (GGUF via llama.cpp)

• —atts1hg1q6k.gguf (Legacy: Combined GPT2+HiFiGAN)

• —ATTS1q6k.gguf (New: GPT2 Only)

• —hifigan1_FP16.gguf (New: HiFiGAN Only)

🔊 Sample Audio Files

Test the quality with these pre-generated samples covering various speakers and languages.

📜 License

This project uses the weights from Coqui XTTS-v2, which is licensed under the Coqui Public Model License (CPML).

Credits: Based on the excellent work by Coqui.ai and the GGML library by ggerganov.