Text-to-Music Generation

This is the Github Repository for the project "Text-to-Music Generation".

• To have some intuition about how this works, check this huggingface space: https://huggingface.co/spaces/Mubert/Text-to-Music
• Currently, we are in a stage where we should check related work and communicate ideas. Later, once we have some creative ideas, we can make plans and start implementation.
• This is an open-source project, so you're welcome to come up with ideas at any time or directly contribute to the GitHub repository.

You're welcome to join our discord server to share your thoughts and report feedbacks!

Roadmap

• check related work
• make a plan/timeline
• start implementation

Quick Start

Recommended Python Version: 3.7

1. installation:

   pip install text2music
   

2. experimental example:

   import text2music as t2m
   t2m.experimental.mubert_generate(
     prompt = 'I am quite happy today',
     duration = 10,
     output_path = 'test.mp3'
   )

Contribution

The easiest way to contribute is to check our task list and see what you could help. Then, you can simply open a pull request to contribute the codes :)

• if you are new to GitHub pull request, check this document

Or, if you have any novel ideas about text-to-music generation, feel free to discuss in the discord server

We appreciate your contribution!

Active Line of Work

1. we are collecting real user prompts for later dataset building. If you would like to share your ideas, fill this google form and submit. We really appreciate your help and will add you to the "wall of love" later:)

Check our task list for more details