Automatic music generation #510
Conversation
|
Hello there! 👋 Welcome to the project! 💖 Feel free to get in touch with me through social media handles. Hope to see you there!😄 |
There was a problem hiding this comment.
Changes to be done:
Project file name should be titled as "music_generation.ipynb
There should be only 1 .ipynb file where you load the dataset, read the dataset, detect outliers, data visualizations, train the data, test the data and using multiple algorithms. This is not sufficient. Use multiple models.
In README.md, add the project description of what this project is, in accuracies you should list out all the models used alog with the accuracy yu had got and then elaborative conclusion. Needs more details. Check on with the README template.
Also there should be a "requirements.txt" file where we list out all the libraries used in this project
Also in the "Dataset" folder, there should be other README.md file where you list out all the attributes used in your project file along with link of dataset.
Kindly do the needful changes. @pranjall29
|
Kindly do the changes. @pranjall29 |
|
Are you doing changes or not? Last date to merge PR's is tomorrow. Else I would have to remove off the label. @pranjall29 |
|
No response and time is up. So label is removed. You can do the changes and submit the work. But won't be counted under LGMSOC program. But still holding PR for this long is not right. I shall wait for 2 more days before I closing this PR. If you want this contribution to be valuable, then complete the PR in given time. @pranjall29 |
Related Issue
Issue Music Generation Analysis #472
LGM-SOC'21 Participant
DevIncept Participant
Contributor
Closes: #472
Describe the add-ons or changes you've made
Give a clear description of what have you added or modifications made
This project proposes the use of 2 models, Wavenet and LSTM to generate automatic music. WaveNet takes the chunk of a raw audio wave as an input. Raw audio wave refers to the representation of a wave in the time series domain. Given the sequence of the amplitude values, WaveNet tries to predict the successive amplitude value. Another approach for automatic music generation is based on the Long Short Term Memory (LSTM) model. The preparation of input and output sequences is similar to WaveNet. At each timestep, an amplitude value is fed into the Long Short Term Memory cell – it then computes the hidden vector and passes it on to the next timesteps.
Dataset: https://www.kaggle.com/anubhavjin/midi-data-containing-melodies
Type of change
What sort of change have you made:
How Has This Been Tested?
Describe how it has been tested
Describe how have you verified the changes made
Checklist:
Screenshots (Only for Front End and UI/UX Designers)