abdljasser2

Joined 4 years ago

Karma

157

Submissions

32

Member since

Feb 24

View on Hacker News

Recent submissions

Comment · 10 months ago

code here: https://github.com/erl-j/neurosymbolic-music-generation

Show HN: Neurosymbolic music generation with Claude Opus 4.5 youtube.com

3 abdljasser2 10 months ago 1 comments

Comment · 1 year ago

My plan is to become a people person / ideas guy.

Comment · 1 year ago

Comment · 1 year ago

Thank you! I can also recommend this work which had a similar idea:

https://instrumentgen.netlify.app/

Show HN: I made an AI soundfont generator huggingface.co

2 abdljasser2 1 year ago 3 comments

Comment · 1 year ago

Good question. In my experience combining generic descriptors is what works best. This is probably due to the text captions used during training mostly consist of generic instrument names, genre names and adjectives.

Show HN: Downloadable AI Musical Instruments huggingface.co

10 abdljasser2 1 year ago 2 comments

Comment · 2 years ago

https://erl-j.github.io/textsynth/

Sortof ML, Evolutionary algorithm w/ fitness determined by a ML model.

Show HN: Loop Savant: Cute AI MIDI Loops in the Browser erl-j.github.io

1 abdljasser2 3 years ago 0 comments

Show HN: Textsynth: Evolve synthesizer sounds from text prompts github.com

7 abdljasser2 3 years ago 1 comments

Comment · 4 years ago

[4] https://forum.juce.com/t/ddsp-tone-transfer-vst-possibility/...

Comment · 4 years ago

[4] https://forum.juce.com/t/ddsp-tone-transfer-vst-possibility/...

Comment · 4 years ago

Hello! I think this will be possible!