Siraj Raval
This episode of Fresh Machine Learning is about generating rap lyrics! Lyrical generation is possible using either Hidden Markov Models or deep learning. In this episode, I go through a few past examples of what’s been done before, then dive into our own example that we can code in Python. Welcome to the machine MC revolution!
The demo code for this video can be found here:
https://github.com/llSourcell/Rap_Lyric_Generator
I created a Slack channel for us, sign up here:
https://wizards.herokuapp.com/
Try it out live here:
I introduce three papers in this video
Unsupervised Rhyme Scheme Identification in Hip Hop Lyrics Using Hidden Markov Models:
http://link.springer.com/chapter/10.1007%2F978-3-642-39593-2_3
Modeling Hip Hop Challenge-Response Lyrics as Machine Translation:
http://www.illc.uva.nl/LaCo/CLS/papers/wu_hiphop_itg.pdf
DopeLearning: A Computational Approach to Rap Lyrics Generation:
http://arxiv.org/abs/1505.04771
More info about Hidden Markov Models:
https://www.youtube.com/watch?v=TPRoLreU9lA
https://www.quora.com/What-is-a-simple-explanation-of-the-Hidden-Markov-Model-algorithm
http://www.developerstation.org/2011/11/hidden-markov-models-for-dummies.html
I love you guys! Thanks for watching my videos, I do it for you. I left my awesome job at Twilio and I’m doing this full time now.
I recently created a Patreon page. If you like my videos, feel free to help support my effort here!:
https://www.patreon.com/user?ty=h&u=3191693
Much more to come so please subscribe, like, and comment.
Follow me:
Twitter: https://twitter.com/sirajraval
Facebook: https://www.facebook.com/sirajology Instagram: https://www.instagram.com/sirajraval/ Instagram: https://www.instagram.com/sirajraval/
Signup for my newsletter for exciting updates in the field of AI:
https://goo.gl/FZzJ5w
Source
Great videos. Love the short videos but I think you should consider making some longer in depth videos depending on what the viewers want to see. You're putting out great content so I'm sure you'll be rewarded richly over time
I felt like you speed up the video of you talking, if you can not say it in time then make the video itself longer, I don't mind spending a few extra mins (I had to do .50 speed to understand) (Love your videos)
You sir, deserve more views!
So it basically just try to predict the next word, right? What could I do to implement rhymes? Oh, thanks for being so awesome! Your channel is definitely helping me A LOT
I love your video so much!!
How did you find these 2 papers form Hong Kong and Finland ? I looked up at Google Scholars it is only cited for less than 10 times.
Also where you do normally go to look for machine learning papers?
Thank you so much!
I checked out the code from github, not really sure it works well with multiple training files, because the new counts would kind of overwrite the old transition probabilities. Also the code for the loops seemed very C-like and not very pythonic.
I've made some adjustments and created a pull request. Would be great for you review and merge it.
As a side note, inspired by the idea I started my own version of a Markov Model text generator. It uses ordered lists instead of dictionaries and numpy for faster computations, also makes some preprocessing on the text. Still a work in progress, but you can check it out on https://github.com/baldassarreFe/python-pankakes
Great job with the Learn Python for Data Science series, keep it going!!
Would be cool if the memes would be seletcted by a AI based on your spoken words :D.
awesome video! btw, at 2:10, did you mean cloudy to sunny?
Great video, although your voice is a little bit distorted at the end
I like how you try to reply to all the comments! Also new to Machine learning, But your videos motivate me to keep learning, Thanks a lot for this.
you are so cute, I want to catch you with my pokeball
why do you only have 30 k subs! Ur awsome. and also in the last python part u kinda went all robot voiced and stuff.
1:51 Guy predickted the weather.
You should really explore more of Lil Wayne's material…most of the artists you showed you liked (Tyler, Kanye, Kendrick) all worship wayne for a reason
Try to do that but with alternative rock
>protip you can't
ive copied and pasted love letters in a txt file, and trained the model with that data. forever alone
I SAW J.S.BACH!! YAY!!
srsly dude you spoke TOO fast!! xD
Ur Channel is AweSome, We need More Videos
Your videos aren't for beginners, are they?
I'm going to use your code to teach a computer how to make dank memes.
run at 0.75 speed! and thank me later..
I am scared of the future now
Part of me really feels like the project is a way wp to say the n-word ?
Basically boy coming period. AIs are not replacing anyone except rappers.
Can I use this model to generate answers to user asked questions?
THis is sooo cool and surprisingly its not even too complicated well to do at least understandings going to take a bit more messing around with
the demo code line 9:
for curr, succ in zip(words[1:], words[:-1]):
i think it should be like this:
for curr, succ in zip(words[:-1], words[1:]):
right?
I've been watching your channel, finding where to start. Help me ?
Is it even using Machine Learning to do RAP in your code? I guess it's just a plain random pick of words…
My
favourite
rhyme scheme
is ABCD
very cool! I learn a lot with your videos. Thank you!
can i develop a model with deep-learning to generate rap lyrics for Tunisia music ? arabic language
Do you fasten this video? Dude, it makes you sound like robot.
Hey Siraj! These lyrics don't make any sense. Is there any way to rework its grammar?
Can you help me work it?
Dat intro XD
2:15 im prety sure this is just a diagram of the uterus
i dont think there is any neural networks going on in the code….