Msanii: High Fidelity Music Synthesis on a Shoestring Budget

Model combines the expressiveness of mel spectrograms, the generative capabilities of diffusion models, and the vocoding capabilities of neural vocoders.

Новая модель на основе диффузии для эффективного синтеза длинной музыки высокого качества.

pip install -q git+https://github.com/Kinyugo/msanii.git

🖥 Github: https://github.com/kinyugo/msanii

⭐️ Demo: https://kinyugo.github.io/msanii-demo/

⭐️ Colab: https://colab.research.google.com/github/Kinyugo/msanii/blob/main/notebooks/msanii_demo.ipynb

✅️ Paper: https://arxiv.org/abs/2301.06468

🤗Hugging face: https://huggingface.co/spaces/kinyugo/msanii

👉 @bigdata_1