Skip to main content

#Audiutor

This project has been developed for the Computer Programming course at the University of Bolzano, Ed Faculty. It allows you to automatically transcribe and summarize a Youtube video in English using Watson IBM speech to text API.

Youtube is full of interesting lectures and educational videos, but not everyone has time to watch them. This little program was developed with one goal in mind -- reduce time and allow students and working people to retrieve the information contained in such educational videos, faster. At the moment, the program is available for English videos only and it works with larger files as well.

Before running this program you will need to create your own Watson Speech to text API key and URL, it will literally take 2 minutes of your time. You can do so by (last update June 2021):

  1. Registering for free here: https://cloud.ibm.com/registration

  2. Creating your Watson Speech to text API key and URL. Just hit the CREATE button (in the right-hand corner below) on this page: https://cloud.ibm.com/catalog/services/speech-to-text'

Call the function:

  • audiutor() to run the program
  • transcript_wordcloud() to create a wordcloud
  • kws_extraction() to extract keywords

In order for the program to function correctly, please do not change the filenames.

Used dependencies:

from pytube import YouTube import os import moviepy.editor as mp from ibm_watson import SpeechToTextV1 from ibm_watson.websocket import RecognizeCallback, AudioSource from ibm_cloud_sdk_core.authenticators import IAMAuthenticator import subprocess import nltk from nltk.corpus import stopwords from nltk.tokenize import word_tokenize nltk.download('stopwords') nltk.download('punkt') from wordcloud import WordCloud from string import punctuation import re import string from wordcloud import WordCloud import matplotlib.pyplot as plt from gensim.summarization import summarize from random import randrange from time import sleep import pprint import spacy import textacy.ke from textacy import * from docx import Document import sys

Metadata

Release files for Audiutor-PatBe 0.0.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for Audiutor-PatBe 0.0.5
File Size Uploaded Provenance Actions
Audiutor-PatBe-0.0.5.tar.gz 3.0 kB Without provenance Details for Audiutor-PatBe-0.0.5.tar.gz

Built distribution (wheel)

Table of built distributions (wheels) for Audiutor-PatBe 0.0.5
File Interpreter ABI Platform Actions
Audiutor_PatBe-0.0.5-py3-none-any.whl Python 3 none any Details for Audiutor_PatBe-0.0.5-py3-none-any.whl

Total release size: 6.2 kB

Release files / Audiutor-PatBe-0.0.5.tar.gz

Download URL Audiutor-PatBe-0.0.5.tar.gz
Size 3.0 kB
Tags Source
SHA-256 checksum
How to use checksums
80a9a251ba7dc3309f832bbeaf9887b6ea72a4181bda9bc902d3597334dc1902
BLAKE2b-256 checksum
How to use checksums
22bd81c797ad46cf0610cfba516fc597446e169dd2a526ae581ba47c508aba01
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/3.4.1 importlib_metadata/4.0.1 pkginfo/1.7.0 requests/2.23.0 requests-toolbelt/0.9.1 tqdm/4.41.1 CPython/3.7.10

Release files / Audiutor_PatBe-0.0.5-py3-none-any.whl

Download URL Audiutor_PatBe-0.0.5-py3-none-any.whl
Size 3.2 kB
Tags Python 3
SHA-256 checksum
How to use checksums
d681742cb557aebb9363ea3911f7df8058ca1a7d449777ea1c8d9ac94aaa1fb9
BLAKE2b-256 checksum
How to use checksums
51873ac9360ba7aee880ebe63d75fa22006652967346c4223aa3f223433cd003
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/3.4.1 importlib_metadata/4.0.1 pkginfo/1.7.0 requests/2.23.0 requests-toolbelt/0.9.1 tqdm/4.41.1 CPython/3.7.10

Security for Audiutor-PatBe 0.0.5

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page