Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
MehdiLeZ 
posted an update Mar 7
Post
Dear music lovers 🕺,

MusicLang Space is now live: musiclang/README


MusicLang is a controllable model for music generation:

> 🦙 Discover the LLAMA2 architecture, trained from scratch for symbolic music generation, ensuring exceptional quality;
> 👨‍🎨 Unleash your creativity by extending an existing music, or create new ones from scratch;
> 🤖 Integrate MusicLang into your applications, with an inference optimized for CPUs written in C, other integrations and optimizations coming soon.

In the space, you’ll find :

1️⃣ MusicLang foundation model: our fondation model for creating and generating original midi soundtracks musiclang/musiclang-v2;

2️⃣ MusicLang predict: our AI prediction api of the MusicLang package https://github.com/musiclang/musiclang_predict?tab=readme-ov-file;

3️⃣ MusicLang Language:a new language for tonal music. This language allows composers to load, write, transform and predict symbolic music in a simple, condensed and high level manner https://github.com/MusicLang/musiclang;

4️⃣ MusicLang Demo Space: musiclang/musiclang-predict

5️⃣ Our Colab: https://colab.research.google.com/drive/1MA2mek826c05BjbWk2nRkVv2rW7kIU_S?usp=sharing

Help us share the future of music composition! Spread the word, show your support by adding a star or contribute to our project. ⭐️✨

Music Sounds Definitely Better with You 🎶 🖤

cc @floriangardin @MehdiLeZ @reach-vb

Thanks a lot,

The MusicLang team ❤️
reach-vb

Love itt! Thanks for open sourcing this! What’s next? :)

·
MehdiLeZ

Thanks @reach-vb ! Next for us :

  • Adding control over the instruments used in each bar and their properties (note density, pitch range, average velocity);
  • Some performances improvements over the inference C script;
  • A faster distilled model for real-time generation that can be embedded in plugins or mobile applications;
  • Some specialized smaller models depending on our users' needs;
  • & more, so stay tuned! ❤️
deleted
This comment has been hidden
t1u1
•
edited Mar 8

Interesting approach 👍

It would be nice to see a collaboration between your project and ChatMusician ( https://huggingface.co./m-a-p/ChatMusician )

asigalov61

Yes, I like your project too! Congrats!

And thank you for following me :)

I just wanted to give you a bit of feedback on your MIDI encoder...

I tried your musiclang_predict colab and it seems that it does not encode the MIDI properly. For example, a piano performance MIDI plays rough and the timings seem off. I am assuming this is due to the fact that you process the MIDI into a standard (or yours) music notation which is not usually suitable for complex piano performances.

So I wanted to suggest to review your approach to MIDI encoding. For example, you can add an option to bypass standard music notation encoding and use a tokenizer instead.

I can elaborate more and provide examples if you want.

Otherwise, I really liked your project and I will review it in more detail shortly :)

Thank you.

Alex

·
MehdiLeZ

Hi @asigalov61

Thanks for your feedback! Any help or contribution of course welcomed, so don't hesitate to elaborate further :-) Happy to discuss this.

All the best,

Mehdi

In this post