Learn subtitles is a tool that allows you to prepare yourself before watching your favorite Movie/Series in its original language.

LearnSubtitles parses and lemmatizes the .str subtitle file (with srt and spaCy), then look at each word frequency using wordfreq. LearnSubtitles will divide these words in three categories: easy, intermediate and advanced.

Right now LearnSubtitles is only available for subtitles in German, English and Portuguese. However, feel free to implement your own language.

First make sure that you have installed all Dependencies, then you can look up for the words in your film base on their difficulty. You can also check how difficult is the film with the metric film_level (the higher, the easier).

import LearnSubtitles as ls

language = "de" # "pt" and "en" also available
my_sub = ls.LearnSubtitles("your/srt/file.srt", language)
print(my_sub.subtitle_path, my_sub.film_level)
print(*my_sub.easy_words, sep=", ")
print(*my_sub.intermediate_words, sep=", ")
print(*my_sub.advanced_words, sep=", ")

Easy words: lassen, paar, Woche, Junge, laufen, versuchen, Problem, schreiben, stehen, einfach, gehen, weiß, genau

Intermediate words: Aufstehen, Frühstück, Außenseiter, Alternativ, Ruhe, Lehrer, Kapitel, geschehen, Handy, reparieren, Plan, Backup, beheben, Software, Tür, Aufschrift, Betreten, verbieten, beginnen, Nachricht, langweilig, übertreiben, Klick, Beziehung, zerstören, wusste, öfter, Albtraum, jederzeit

Advanced words: Ungewöhnliches, einspielen, unbeobachtete, Spalt, mitzulesen, Frendschaften, bescheißen, Selbstdiagnose

Easy words: self, computer, people, leave, week, ago, happen, boy, give, phone, go, plan, try, problem, write, like, door, say, open, start, read, message, get, able, relationship, feel, know, far, exactly, want, time

Intermediate words: breakfast, diagnosis, outsider, alternatively, nerd, prefer, teacher, chapter, unusual, cell, fix, accord, import, backup, software, entry, crack, boring, click, destroy, friendship, nightmare

Advanced words: unobserved, overdo, crappy

Easy words: mão, pensar, esperar, deixar, dia, encontrar, voltar, mostrar, saber, vir, perder, pra, aprender, entender, amor, olhar, levar, código, som, pedir, mundo, gente, paz, viver, seguir, falar, mim, ir, ficar, manhã, nenhum, difícil, comigo, passar, viagem, longo, fazer, claro, tentar, Seja, sentir

Intermediate words: Menina, agir, mentir, confusão, direção, beber, catar, lata, olho, Desculpe, sincero, lógico, letra, rap, sólido, brigar, virar, der, meter, ensinar, curto, chorar, despedir, café, acordar, errar, ódio, rancor, precisar, independente, amar, negar, positivo, existir, cair, tratar, arrepender, envolver, querer, Noites, doer, justificar, sumir

Advanced words: champanhe, vidar, sórdido, Psicografado, súbito, bobeira, pirar, bandeiro, certar, horar, abalar, papar, inventariar, clichê

LearnSubtitles used spaCy, srt and wordfreq, so you need to install them. You can install it easily:

pip install -r requirements.txt

spaCy Models will be automatically downloaded if needed

• Make other languages available
• Download subtitles automatically
• Swipe GUI (like tinder), so the user can easily filter the words he doesn't know

• Execution time (spaCy model taking long time)
• Filter language (Words from other languages may also pop up)
• Improve NLP model for subtitles