diff --git a/README.md b/README.md
index c3b7cdc..3ca0de2 100644
--- a/README.md
+++ b/README.md
@@ -1,6 +1,6 @@
 #  Music Separation Enhancement With Generative Modeling
 
-[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/interactiveaudiolab/MSG/blob/main/MSG.ipynb)`
+[![Open in Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/interactiveaudiolab/MSG/blob/main/MSG.ipynb)
 
 This is the official implementation of the Make it Sound Good (MSG) model from our 2022 ISMIR paper "Music Separation Enhancement with Generative Modeling" [\[paper\]](https://arxiv.org/pdf/2208.12387.pdf)[ \[website\]](https://interactiveaudiolab.github.io/project/msg.html) 
 
@@ -14,23 +14,16 @@ We introduce Make it Sound Good (MSG), a post-processor that enhances the output
 - [Citation](#Citation)
 
 ## Setup
-1. We train our model using salient source samples from the training data. To get the salient source samples, our training loop uses [nussl's](https://github.com/nussl/nussl/tree/salient_mixsrc2/nussl) SalientExcerptMixSourceFolder class from the salient_mixsrc2 branch. The specific branch of the repo can be downloaded using the steps below:
+1. Download our repo from github.
+```bash
+git clone https://github.com/interactiveaudiolab/MSG.git
 ```
-$ git clone https://github.com/nussl/nussl.git
-$ cd nussl
-$ git checkout salient_mixsrc2
-$ pip install -e .
+2. Change to the MSG repo folder and install the requirements.
+```bash
+cd MSG
+pip install -r requirements.txt
 ```
-2. Download our repo from github.
-```
-$ git clone https://github.com/interactiveaudiolab/MSG.git
-```
-3. Change to the MSG repo folder and download the requirements.txt.
-```
-$ cd MSG
-$ pip install -r requirements.txt
-```
-4. If you would like to use our [pretrained checkpoints on huggingface download](https://huggingface.co/boazcogan/MSG_pretrained_checkpoints/tree/main) the model.
+3. If you would like to use our [pretrained checkpoints on huggingface download](https://huggingface.co/boazcogan/MSG_pretrained_checkpoints/tree/main) the model.
 
 ## Training
 
diff --git a/requirements.txt b/requirements.txt
index 28dd785..e2aa772 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -12,3 +12,4 @@ SoundFile
 librosa==0.8.1
 torch
 wandb
+git+https://github.com/nussl/nussl.git@salient_mixsrc2
\ No newline at end of file