egorsmkv/speech-recognition-uk
Ukrainian speech-to-text and text-to-speech models, datasets, and leaderboards hosted on Hugging Face.
Not currently ranked — collecting fresh signals.
star history
This repository aggregates links to models, datasets, and tools for Ukrainian speech recognition and synthesis. It provides implementations of transformer-based speech models including wav2vec2-bert, wav2vec2-XLS-R, HuBERT, Citrinet, ContextNet, and FastConformer. The project maintains leaderboards and demos on Hugging Face, serving as a central hub for the Ukrainian speech processing community.
Frequently asked
- What is egorsmkv/speech-recognition-uk?
- Ukrainian speech-to-text and text-to-speech models, datasets, and leaderboards hosted on Hugging Face.
- Is speech-recognition-uk open source?
- Yes — egorsmkv/speech-recognition-uk is an open-source project tracked on heatdrop.
- What language is speech-recognition-uk written in?
- egorsmkv/speech-recognition-uk is primarily written in Python.
- How popular is speech-recognition-uk?
- egorsmkv/speech-recognition-uk has 439 stars on GitHub.
- Where can I find speech-recognition-uk?
- egorsmkv/speech-recognition-uk is on GitHub at https://github.com/egorsmkv/speech-recognition-uk.