diff --git a/.github/workflows/publish-to-pypi.yml b/.github/workflows/publish-to-pypi.yml
index 4d49723..1171e3c 100644
--- a/.github/workflows/publish-to-pypi.yml
+++ b/.github/workflows/publish-to-pypi.yml
@@ -18,7 +18,7 @@ jobs:
     - name: Install dependencies
       run: |
         pip install --upgrade pip
-        pip install setuptools wheel twine
+        pip install setuptools wheel twine build
         if [ -f requirements.txt ]; then pip install -r requirements.txt; fi
 
     - name: Build and publish
diff --git a/.gitignore b/.gitignore
index 59a2da0..52d35d5 100644
--- a/.gitignore
+++ b/.gitignore
@@ -10,4 +10,5 @@ output
 cache*
 lib
 .hypothesis
-pycocoevalcap/tokenizer/tmp*
\ No newline at end of file
+pycocoevalcap/tokenizer/tmp*
+.DS_Store
\ No newline at end of file
diff --git a/README.md b/README.md
index 048cc54..0172cea 100644
--- a/README.md
+++ b/README.md
@@ -18,5 +18,4 @@ score = get_aces_score(candidates, references, average=True)
 ```
 
 ## Evaluation
-All the code that is used to evaluate different models for the research paper can be found in the `evaluation` folder. Particularly,
-the model evaluation can be found in `evaluation/eval.py`, and information about the FENSE experiment can be found in `evaluation/fense_experiment/main.py`. 
+All the code that is used to evaluate different models for the research paper can be found in the `evaluation` folder on the [github](https://github.com/GlJS/ACES). Particularly, the model evaluation can be found in `evaluation/eval.py`, and information about the FENSE experiment can be found in `evaluation/fense_experiment/main.py`. 
diff --git a/evaluation/eval.py b/evaluation/eval.py
index ccbe473..7c7d17b 100644
--- a/evaluation/eval.py
+++ b/evaluation/eval.py
@@ -12,7 +12,7 @@
 import string
 
 from bert_score import score
-from src.aces.aces import ACES, get_aces_score
+from src.aces import ACES, get_aces_score
 from evaluation.eval_metrics import evaluate_metrics_from_lists
 from transformers import pipeline
 from fense.evaluator import Evaluator
diff --git a/evaluation/fense_experiment/experiment/main.py b/evaluation/fense_experiment/experiment/main.py
index c8e0f08..4cafcc1 100644
--- a/evaluation/fense_experiment/experiment/main.py
+++ b/evaluation/fense_experiment/experiment/main.py
@@ -2,7 +2,7 @@
 os.environ["CUDA_VISIBLE_DEVICES"] = "2,1"
 import sys
 sys.path.insert(0, os.getcwd()) 
-from src.aces.aces import get_aces_score, ACES
+from src.aces import get_aces_score, ACES
 import json
 import numpy as np
 import pandas as pd
diff --git a/pyproject.toml b/pyproject.toml
index e91f351..9c80be9 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -9,8 +9,4 @@ description = "ACES metric for evaluating automated audio captioning models base
 readme = "README.md"
 authors = [{name = "Gijs Wijngaard", email = "hi@gijs.me"}]
 license = {file = "LICENSE"}
-requires-python = ">=3.9"
-
-[tool.setuptools]
-include-package-data = true
-packages = ["aces"]
\ No newline at end of file
+requires-python = ">=3.9"
\ No newline at end of file
diff --git a/__init__.py b/src/aces/__init__.py
similarity index 100%
rename from __init__.py
rename to src/aces/__init__.py
diff --git a/test_aces.py b/test_aces.py
index e9a5b51..05695a5 100644
--- a/test_aces.py
+++ b/test_aces.py
@@ -3,7 +3,7 @@
 import torch
 os.environ["CUDA_VISIBLE_DEVICES"] = "0,1,2"
 
-from src.aces.aces import get_aces_score, ACES
+from src.aces import get_aces_score, ACES
 from transformers import pipeline
 import time
 from evaluation.fense_experiment.experiment.sweep import get_aces_score as get_aces_score_old