The aim of this repository is to collect information and datasets for speech recognition in Ukrainian.
Get in touch with us in our Telegram group: https://t.me/speech_recognition_uk
- Silero: https://github.com/snakers4/silero-models (demo code: https://github.com/egorsmkv/ua-silero-demo, also there is a demo as a Telegram bot: https://t.me/ukr_stt_bot)
- VOSK v2: https://drive.google.com/file/d/1MdlN3JWUe8bpCR9A0irEr-Icc1WiPgZs/view?usp=sharing (demo code: https://github.com/egorsmkv/vosk-ukrainian-demo)
- VOSK v1: https://drive.google.com/file/d/1nzpXRd4Gtdi0YVxCFYzqtKKtw_tPZQfK/view?usp=sharing (an old model with less trained data)
- DeepSpeech using transfer learning from English model: https://github.com/robinhad/voice-recognition-ua
- Mega: https://mega.nz/folder/T34DQSCL#Q1O8vcrX_8Qnp27Ge56_4A (use MEGAcmd to download, downloading in a browser has speed limitations)
- Torrent file: https://git.io/Jtq5E (72.4 GB)
- Mozilla Common Voice has the Ukrainian model: https://commonvoice.mozilla.org/uk/datasets
- M-AILABS Ukrainian Corpus Ukrainian: http://www.caito.de/data/Training/stt_tts/uk_UK.tgz
- VoxForge Repository: http://www.repository.voxforge1.org/downloads/uk/Trunk/