Extract text from a YouTube video in a single command, using OpenAi's Whisper speech recognition model
Project description
YT2TEXT
Extract text from a YouTube video in a single command, using OpenAi's Whisper speech recognition model. It doesn't use disk, performs everything in memory.
INSTALL: pip install yt2text
USAGE:
You'll only interact with the get_text function. It takes a YouTube URL as an argument and returns the text as a string.
import yt2text result= yt2text.get_text(YOUTUBE_URL)
OPTIONAL ARGUMENTS: model Set Whisper model (tiny,base,small,medium or large). Check here for details: https://github.com/openai/whisper#available-models-and-languages Defaults to "base" which should be good enough for most cases. The first time you use a model, it will be downloaded first.
verbose Set True to print each step of the process. Defaults to False, it only prints if there is an error.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.