This paper demonstrates the application of hierarchical convolutional neural networks using self-Attention mechanisms for the task of generating recipes given a set of ingredients the recipe should contain. We compare this model, RECIPEGM, to an LSTM baseline and RecipeGPT using several metrics and show that our model is able to outperform even RecipeGPT in some cases. Furthermore, this work discusses suitable evaluation techniques for recipe generation and highlights weak points of some current in use metrics.