Simple Python audio transcriber using OpenAI's Whisper speech recognition model
-
Python version needs to be below 3.11
-
Install required packages with pip
pip install -r requirements.txt
- Run a program with Python3
python3 transcriber.py -u, --url <URL>
-
pytube requires pip installation
-
ffmpeg needs to be pip installed if not already present
-
in "LOCAL_PATH_TO/pytube/cipher.py", Change this line: 411: transform_plan_raw = find_object_from_startpoint(raw_code, match.span()[1] - 1) to this: 152: transform_plan_raw = js