Simple Python audio transcriber using OpenAI's Whisper speech recognition model
- Install required packages with pip
pip install -r requirements.txt
- Run a program with Python3
python3 transcriber.py -u, --url <URL>
-
In case you get an error message like this FileNotFoundError: [Errno 2] No such file or directory: 'ffmpeg' , ensure that you have ffmpeg installed.
Reference: kkroening/ffmpeg-python#251
In linux env:
sudo apt install ffmpeg
-
If you want to see a progress bar while transcription is done, then ...
Visit openai/whisper#850 for a reference