A little of backstory about this project: my co-founder and I are big fans of Anki, which is an awesome flashcard software and a really effective tool for language learning.
However, it's hard to find quality decks online. There are some apps with good flashcards, but they tend to be expensive. You certainly can make your own, but that's really time consuming. That's why we decided to build Deckmill, a repository of high quality, but affordable flashcards.
For those are interested in the tech, this is how we did it:
1. Used a mix of ML + hand curation to select 3000 sentences from tatoeba.org (a massive dataset)
2. Then machine translation to translate the sentences
3. Then we had native speakers review the translations
4. Wavenet to generate audio
5. genanki to put together the cards
Fluent speaker of Spanish as second language. The audio here is terrible for learning the language, "Mi hermano es medico" is pronounced as though two Venezuelans are talking at a dinner party. It needs to be slower and more distinctly enunciated for a learner.
Hi spoonjim! In our experience it's important to train your ears to listen to native speakers as early as possible in the learning process. However, you are correct that listening to slow speaking is also very pedagogical -- this is exactly why we provide a 0.5x speed version of the audio, alongside the 1x (native-like) version.
Yes, I tried the 0.5x version, but it's not the way that a Spanish teacher talks. A good Spanish teacher emphasizes the parts of the sounds that are different from English, and doesn't slow down even close to 0.5x -- it's more like 10%, but a much clearer 10%.
In this example, a Spanish teacher would have put more of a pause between "Mi" and "hermano", not such a weird elongation of the "o" in "hermano", and less emphasis on the "es" (even a native conversation would not have that kind of stress on the "es").
Hi ngokevin! The Anki community is fantastic and there are some great decks out there. However, we found that the quality, format and even difficulty tend to vary wildly across decks. For example, many decks have low quality audio or don't include it at all; others have poor sentence selection, etc
Wow, great project! I'm going to keep an eye on this and will talk with my partner about signing up.
I love how your example cards are sentences and not just individual terms. Super engaging.
As a word of feedback, I might suggest adding the names of the languages that you currently support underneath each of the language flags as it makes it more instantly-recognizable (and therefore likely lower friction).
This is an awesome concept and I really like it!
Sorry for the self-plug on someone else's thread, but if you're learning a language with a partner, I've been building an app to help couples learn each other's languages (https://learncoupling.com) if you're interested.
I'll risk being misunderstood and/or downvoted to note that "coupling" is a synonym for "sex". It's not quite "learnintercourse" but it's close. Apologies if this comes across as condescending or prurient or juvenile; just looking to help in case the association wasn't clear and you might gain by moving to a different domain.
Thanks for the input! I think I did see that before but as an American English speaker, I didn't feel the connotation that strongly. I'll genuinely keep that in mind and think about that. I wonder others here feel the same. I hear it more often for gears, physics, programming, or synonym for pairs or couple. Maybe it connotes to mating more in biology contexts or maybe British English?
Why these particular words/sentences? Is this based on frequency? Something else?
I was trying to learn Spanish based off of frequency dictionaries at one point, but many didn’t provide conjugations of the verbs which made it questionable to learn.
I was even contemplating creating something myself that would take the top 5000 words and make complete sentences out of them... using conjugations of course.
Indeed, using frequency alone will lead to a suboptimal set of sentences. Our approach was to choose sentences that increase smoothly in complexity, where we estimate complexity through a combination of criteria: frequency of vocab, tenses, number of clauses, etc.
I wasn’t sure how many sentences were included but bought anyway (you might want to add this to the FAQ unless somehow I missed it elsewhere). Seems to be about 2000 sentences per deck. Learning Spanish so this gives me access to 6000 sentences.
Perhaps you could mention on your page, what do you expect to be the native language of the learner. After seeing the examples, I've realized that this is nothing for me since I am native German speaker.
Hi funcDropShadow, that's a good point. We really want to expand to other language pairs (e.g. German-Spanish). In fact we are also not native English speakers :)
When "touring" the flashcards, I would love to see a "skill level" prompt then receive 5-10 cards as part of a smooth onboarding flow.
Also I would rather see flashcard examples tailored for each language, as the simple English sentence "my brother is a doctor" doesn't necessarily represent a "beginner" flashcard for every language.
The fact that this is a $10 one-off fee is very attractive to me. There are so many subscriptions in the language learning world, it’s incredibly refreshing to see a product using a different model.
Also, you can use them with Anki. Perfect. I’m probably going to purchase. Hopefully they live up to expectations.
Hi James, thank you for your comment. It's great to hear you say that because it is exactly what we had in mind when we started the project -- we were also pretty tired of the subscription model in language learning apps :)
Neither the "See our decks" nor "Why Deckmill?" buttons do anything on my desktop setup. After inspecting, it seems they scroll but my screen is tall enough that there is no scroll behavior (or scrollbar).
I expected they'd take me to a more detailed version of what's on the homepage.
Seeing "Jump start you language learning." when I click on a deck doesn't engender confidence in the product quality even if the website is held to a different standard than the decks themselves.
I wish language learning platforms would include more than the same handful languages. There may not be as many people who want to learn them, but there are also almost no resources online for some.
I actually created the same exact product years ago. I hope it goes well for you! I wasn't a very good entrepreneur at the time and never did make it work.
Hey Trias!
Yes, our flashcards run on top of Anki, so they can be used completely offline - that was of our main intentions when making this product, as many apps require internet access.
A little of backstory about this project: my co-founder and I are big fans of Anki, which is an awesome flashcard software and a really effective tool for language learning.
However, it's hard to find quality decks online. There are some apps with good flashcards, but they tend to be expensive. You certainly can make your own, but that's really time consuming. That's why we decided to build Deckmill, a repository of high quality, but affordable flashcards.
For those are interested in the tech, this is how we did it: 1. Used a mix of ML + hand curation to select 3000 sentences from tatoeba.org (a massive dataset) 2. Then machine translation to translate the sentences 3. Then we had native speakers review the translations 4. Wavenet to generate audio 5. genanki to put together the cards