In this article, I’ll walk you through my experience to code a model that will learn some Ed Sheeran songs and try to create some first sentences for a song.
Writing a song is one of the hardest tasks ever. In this article, I’ll walk you through my experience to code a model that will learn some Ed Sheeran songs and try to create some first sentences for a song. I’m well aware here that it should be better to make a model that creates audio and not just a poem because the work of Ed Sheeran is mainly catchy rhythms that stick in our minds. However, I didn’t want to create Shakespeare’s text. I wanted something more modern. It should be awesome to create song lyrics with its audio band but let’s focus here to create lyrics first, one step at a time!
Let’s dive in!
For the basics concepts of my code please take a look at my article NLP in Tensorflow: Sentiment analysis
So first of all, let’s import the libraries and the source file of some Ed Sheeran’s songs. I took the two last albums to start our training. You can find it on my Github here.
After tokenization, sequencing, and padding we’re ready to predict. Generating a text is predicting for each next word which word from our corpus would it be. An almost simple multi-class prediction isn’t it?! Yeah almost!
Teaching machines to understand human context can be a daunting task. With the current evolving landscape, Natural Language Processing (NLP) has turned out to be an extraordinary breakthrough with its advancements in semantic and linguistic knowledge.NLP is vastly leveraged by businesses to build customised chatbots and voice assistants using its optical character and speed recognition
In this article we will write an algorithm that classifies movie reviews: positive or negative, we will train it on an already labeled comment dataset. Tensorflow has included databases ready to be playing with.
Quick reminder that there is now only 1 week left in our Early Bird Pricing for the Chatbot Conference and Workshops. These tickets can save you as much as $400!
Every week we bring to you the best AI research papers, articles and videos that we have found interesting, cool or simply weird that week. Have fun!
A step-by-step tutorial on developing LSTM, GRU and Bi-Directional LSTM models to predict water consumption. In this post, I develop three sequential models; LSTM, GRU and Bidirectional LSTM, to predict water consumption under the impact of climate change.