-
Download model from this URL: https://drive.google.com/file/d/1MdlN3JWUe8bpCR9A0irEr-Icc1WiPgZs/view?usp=sharing (you can also check out newer versions here: https://github.com/egorsmkv/speech-recognition-uk)
-
Unpack the archive into
data/modelfolder -
Save some WAV files in the
samplesfolder -
Install dependencies using pipenv and enter into the shell
pipenv install pipenv shell -
Run the recognizer
python recognize.py