Features
Ukrainian speech recognition models
Ukrainian text-to-speech models
Pre-trained models on Hugging Face Hub
Curated speech datasets for Ukrainian
Open-source repository on GitHub
Community support via Telegram and Discord
Hugging Face Spaces demos (StyleTTS2, RAD-TTS++)
Model collections for easy discovery
Non-profit, donation-funded (Monobank)
RAD-TTS++ multi-speaker TTS with HiFiGAN
StyleTTS2 high-quality voice synthesis
198B-A11B mixture-of-experts architecture
Vision-language understanding and generation
Fast inference for agent tool-use tasks
Multi-turn function calling support
Large context window for agent loops
Open-source model weights on HuggingFace
Strong multimodal reasoning and visual QA
High throughput per GPU with sparse activation
Customizable system prompts for agent behavior
Low-latency callback API design
Step-2 1.5B-step reasoning model on GitHub
