diff --git a/README.md b/README.md
index 792575e..57452b4 100644
--- a/README.md
+++ b/README.md
@@ -30,6 +30,12 @@ The final architecture is shown in the following figure.
 1. [librosa](https://github.com/librosa/librosa) >= 0.4.3
 1. [tqdm] (https://github.com/tqdm/tqdm) >= 4.10.0
 
+To install the required python packages ( except TensorFlow ), run
+
+```
+pip install -r requirements.txt
+```
+
 ## Dataset
 
 We used only 36,395 sentences in the VCTK corpus with a length of more than 5 seconds to prevent CTC loss errors. VCTK corpus can be downloaded from [http://homepages.inf.ed.ac.uk/jyamagis/release/VCTK-Corpus.tar.gz](http://homepages.inf.ed.ac.uk/jyamagis/release/VCTK-Corpus.tar.gz). After downloading, extract the 'VCTK-Corpus.tar.gz' file to the 'asset/data/' directory.
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..293c7aa
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,4 @@
+sugartensor>=0.0.1.9
+pandas>=0.19.1
+librosa>=0.4.3
+tqdm>=4.10.0
\ No newline at end of file