-
pip3 install -r requirements.txt -
Download a Vosk Model and unpack.
-
Define Folder in
MODEL_PATH = "small" -
python3 transcribe.py -
cd web && python3 -m http.server 8080 -
Go To http://localhost:8080 in your browser and see subtitles
-
...
-
profit
Transcribes everything the microphone hears
-
Font: OpenDyslexic
-
Used Voice Model: vosk-model-small-de-0.15 from https://alphacephei.com/vosk/models