umuiq's Stars
openvpi/DiffSinger
An advanced singing voice synthesis system with high fidelity, expressiveness, controllability and flexibility based on DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism
asigalov61/Giant-Music-Transformer
[SOTA] [92% acc] 786M-8k-44L-32H multi-instrumental music transformer with true full MIDI instruments range, efficient encoding, octo-velocity and outro tokens
apple/ml-llarp
zhaojw1998/AccoMontage-3
Code and demo for paper: Zhao et al., AccoMontage-3: Full-Band Accompaniment Arrangement via Sequential Style Transfer and Multi-Track Function Prior.
asigalov61/Allegro-X-Music-Transformer
Very fast and efficient large multi-instrumental music transformer with 8k sequence length, dynamic MIDI notes encoding, full MIDI instruments range, chords counters and outro tokens
asigalov61/Experimental-Music-Transformer
Experimental music transformer to explore new techniques and ideas
asigalov61/POP-Melody-Transformer
Fantastic and very fast performance POP music melody arrangement/extraction transformer
asigalov61/Tiny-Music-Transformer
Miniature multi-instrumental music transformer with super-efficient encoding
VladPetk/Piano-music-transformer-MIDI-
A transformer model for generating solo piano compositions. Generetes quantized output suitable for working in DAWs.
asigalov61/Algorithmic-Accompaniment-Generator
Algorithmic accompaniment generator
guan-yuan/seq2seq-with-attentation-batch-pytorch
It's the baseline model (seq2seq with attention mechanism) for the natural language generation
asigalov61/Full-MIDI-Music-Transformer
Ultra-fast, full-featured, full MIDI specification music transformer with events and time counters tokens
blance714/EVT-CN-Translation
The Estill Voice Model: Theory and Translation 中文翻译