Steps:
- Place this script inside your librispeech dataset folder.
- This should the directory structure of the dataset folder:
libri_dataset
|-libri_annotator.py
|-txt
|- sample1.txt
|- sample2.txt
| <!-- PATCH TO ENABLE KATEX & HIGHLIGHT.JS FOR THINKIFIC QUIZ SECTIONS --> | |
| <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/[email protected]/dist/katex.min.css" integrity="sha384-t5CR+zwDAROtph0PXGte6ia8heboACF9R5l/DiY+WZ3P2lxNgvJkQk5n7GPvLMYw" crossorigin="anonymous"> | |
| <script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/katex.min.js" integrity="sha384-FaFLTlohFghEIZkw6VGwmf9ISTubWAVYW8tG8+w2LAIftJEULZABrF9PPFv+tVkH" crossorigin="anonymous"></script> | |
| <script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/contrib/auto-render.min.js" integrity="sha384-bHBqxz8fokvgoJ/sc17HODNxa42TlaEhB+w8ZJXTc2nZf1VgEaFZeZvT4Mznfz0v" crossorigin="anonymous"></script> | |
| <link rel="stylesheet" href="//cdnjs.cloudflare.com/ajax/libs/highlight.js/10.7.2/styles/dracula.min.css"> | |
| <script src="//cdnjs.cloudflare.com/ajax/libs/highlight.js/10.7.2/highlight.min.js"></script> | |
| <script> |
| /* For my usage with the "Custom JavaScript for Websites 2" extension, | |
| to jump across trial-based paywalls of certain websites like nautil.us or medium.com */ | |
| // Delete all cookies (Src: https://stackoverflow.com/a/33366171 ) | |
| (function () { | |
| var cookies = document.cookie.split("; "); | |
| for (var c = 0; c < cookies.length; c++) { | |
| var d = window.location.hostname.split("."); | |
| while (d.length > 0) { | |
| var cookieBase = encodeURIComponent(cookies[c].split(";")[0].split("=")[0]) + '=; expires=Thu, 01-Jan-1970 00:00:01 GMT; domain=' + d.join('.') + ' ;path='; |
Steps:
libri_dataset
|-libri_annotator.py
|-txt
|- sample1.txt
|- sample2.txt
| import sys | |
| from subprocess import Popen, PIPE, STDOUT | |
| def run_command(command): | |
| out = Popen(command.split(), shell=True, stdout=PIPE, stderr=STDOUT) | |
| stdout, stderr = out.communicate() | |
| return stdout.decode("utf-8").strip() | |
| def remove_package_adb(pkg_name, disable=True): | |
| out = run_command('adb uninstall %s' % pkg_name) |
| import json | |
| import requests | |
| import sys | |
| from tabulate import tabulate | |
| USAGE = 'python %s <search_query> <num_pages>' % sys.argv[0] | |
| POST_URL = 'https://data.mypustak.com//search/get/SearchBooksCollection/%s/%d' | |
| payload = {"query_by": "title,author,publication,isbn", "stock_filter_by":["N"], "bookType_filter_by":[0]} | |
| def get_book_list(response): |
| # Basically I was trying to find out the size of MBERT model's data for Indian languages | |
| # Date based on: https://github.com/google-research/bert/blob/f18bd94b8fee9bda3c293e0932d100add35b780c/multilingual.md | |
| import requests | |
| from bs4 import BeautifulSoup | |
| from time import sleep | |
| ARCHIVE_API = 'http://web.archive.org/cdx/search/cdx?url=%s&output=json' | |
| WIKIDUMP_URL = 'https://dumps.wikimedia.org/%swiki/%s' | |
| ARCHIVE_URL = 'http://web.archive.org/web/%s/%s' |
Created for my stupid-ass friend Anudeep KS.
Inspiration: https://www.instagram.com/p/B_dlpBTgGIG/
pip install pyautogui| @echo off | |
| :: OpenSSH Private Key File | |
| set KEY_PATH=C:\\Users\\GokulNC\\Desktop\\Keys\\GCP_VM\\id_rsa | |
| set USERNAME=GokulNC_GCP | |
| set REMOTE_DIR=/ | |
| set /p IP=Enter the IP: | |
| set /p DriveLetter=Enter the mount drive letter: |