Features
Thai language speech recognition
Fine-tuned Whisper for Thai phonetics
Free Hugging Face Space demo
Open-source model weights download
No-code interface for audio upload
Supports common audio formats via browser
Short audio transcription (demo limit)
Community-contributed model on Hugging Face
Based on OpenAI Whisper architecture
Designed for Thai tonal accuracy
Transfer learning from multilingual Whisper
Suitable for ASR research and benchmarking
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
