Yehor/vosk-uk

🚨🚨🚨 ATTENTION! 🚨🚨🚨

This repository contains VOSK models for Ukrainian and intend to be an archive.

We recommend to use modern models listed here: https://huggingface.co/Yehor/w2v-bert-uk-v2.1

---

Community

• Discord: https://bit.ly/discord-uds
• Speech Recognition: https://t.me/speech_recognition_uk
• Speech Synthesis: https://t.me/speech_synthesis_uk

See other Ukrainian models: https://github.com/egorsmkv/speech-recognition-uk

Models

• uk_v3_dynamic_nano.zip (73 mb)
• uk_v3_dynamic_small.zip (133 mb)
• uk_v3_dynamic.zip (345 mb)
• vosk_model_v1.zip (87 mb, an old model with less trained data)
• vosk_model_v2.zip (339 mb, demo code: https://github.com/egorsmkv/vosk-ukrainian-demo)
• vosk_model_v3.zip (343 mb)

See the Files section to download these models.

Cite this work

@misc {smoliakov_2025,
    author       = { {Smoliakov} },
    title        = { vosk-uk (Revision 1f56194) },
    year         = 2025,
    url          = { https://huggingface.co/Yehor/vosk-uk },
    doi          = { 10.57967/hf/4576 },
    publisher    = { Hugging Face }
}