Added sources

README.md

@@ -27,13 +27,16 @@ By the use of the aforementioned autoencoder, it allows the user to encode piano
 - **Model type:** Variational autoencoder
 - **License:** MIT
 
-### Model Sources [optional]
+### Sources
 
 <!-- Provide the basic links for the model. -->
 
-- **Repository:** [More Information Needed]
-- **Paper [optional]:** [More Information Needed]
-- **Demo [optional]:** [More Information Needed]
+- **Code:** Some of the code of this repository includes modifications (not the entire code, due to the differences in the architecture) from the following sites:
+1. [Tensorflow tutorial where pretty-midi is used](https://www.tensorflow.org/tutorials/audio/music_generation)
+2. [VAE explanation and code](https://towardsdatascience.com/vae-with-tensorflow-6-ways-9c689cb76829)
+3. [Microsoft article on the KL training schedule which was applied in this model](https://www.microsoft.com/en-us/research/blog/less-pain-more-gain-a-simple-method-for-vae-training-with-less-of-that-kl-vanishing-agony/)
+
+There might be acknowledgments missing. If you find some other resemblance to a site's code, please notify me and I will make sure of including it.
 
 ## Uses 
 <!-- MENTION COLAB HERE -->
@@ -45,7 +48,7 @@ By the use of the aforementioned autoencoder, it allows the user to encode piano
 
 <!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
 
-If you prefered directly using or testing the model without the need to install it, you can use the following colab notebook and follow its instructions. Moreover, this serves as an example of use.
+If you preferred directly using or testing the model without the need to install it, you can use the following colab notebook and follow its instructions. Moreover, this serves as an example of use.
 [colab link]
 
 [More Information Needed]
@@ -98,7 +101,7 @@ The first one will clone the repository. Then, fluidsynth, a real-time MIDI synt
 
 ## Training Details
 
-Pivaenist was trained on the [MAESTRO v2.0.0 dataset](https://magenta.tensorflow.org/datasets/maestro){:target="_blank"}, which contains 1282 midi files [check it in colab]. Their preprocessing involves splitting each note in pitch, duration and step, which compose a column of a 3xN matrix (which we call song map), where N is the number of notes and a row represents sequentially the different pitches, durations and steps. The VAE's objective is to reconstruct these matrices, making it then possible to generate random maps by sampling from the distribution, and then convert them to a MIDI file.
+Pivaenist was trained on the [MAESTRO v2.0.0 dataset](https://magenta.tensorflow.org/datasets/maestro), which contains 1282 midi files [check it in colab]. Their preprocessing involves splitting each note in pitch, duration and step, which compose a column of a 3xN matrix (which we call song map), where N is the number of notes and a row represents sequentially the different pitches, durations and steps. The VAE's objective is to reconstruct these matrices, making it then possible to generate random maps by sampling from the distribution, and then convert them to a MIDI file.
 
 ### Training Data