From 6ca034829f0294b6df77d946121c7d211d74de56 Mon Sep 17 00:00:00 2001
From: adigoryl <31667817+adigoryl@users.noreply.github.com>
Date: Wed, 20 Nov 2019 15:25:39 +0000
Subject: [PATCH] Update README.md

---
 README.md | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 75f3455..3f636d8 100644
--- a/README.md
+++ b/README.md
@@ -2,4 +2,5 @@
 
 This work utilises a pre-trained GPT2-small model from Transformer library. The pre-trained model was fine-tuned using a lyrics dataset that comprises of 15.5K unique songs that are accompanied by metadata, that is, the genre, artist, year, album and song name. By using an appropiate training input construction and feeding strategy the GPT2 outputs can be constrained with the aformentioned lyrics' features, in order to produce mashup song. For example, once could constrain the lyrics to look like from the "Queen" band, however, in a "Country" genre style. The model can be used as a tool for creative lyrics composition inspiration.
 
-Open an interactive demo of the model in Google Colab: https://colab.research.google.com/drive/1Gl5zGR8vQM6q7fV0XAPvWg5sX1ZNgDOs 
+Open an interactive demo of the model in Google Colab (requires a google account): https://colab.research.google.com/drive/1Gl5zGR8vQM6q7fV0XAPvWg5sX1ZNgDOs 
+