From 5a51708b7b020f2d439ffdc988eb19383b925844 Mon Sep 17 00:00:00 2001
From: Keith Ito <keeeto@gmail.com>
Date: Sat, 8 Jul 2017 13:15:43 -0400
Subject: [PATCH] Add a header for the sample output section

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

diff --git a/README.md b/README.md
index 2956489..f5e1797 100644
--- a/README.md
+++ b/README.md
@@ -13,6 +13,9 @@ Google [released](https://google.github.io/tacotron) some nice audio samples tha
 generated but didn't provide their source code or training data. This is an attempt to
 implement the model described in their paper.
 
+
+### Sample Output
+
 Output after training for 185K steps (~2 days):
 
   * [Audio Samples](https://keithito.github.io/audio-samples/)