MelodyFlow - a facebook Collection

facebook 's Collections

perception-encoder-audio-visual

Physics of Language Models: Part 4.2

Perception Encoder

Seamless Communication

Robust Wav2Vec 2.0

Fairseq S^2 TTS

MusicGen Stereo

FAIR's LayerSkip Llama models

MelodyFlow

updated Mar 2

MelodyFlow: High Fidelity Text-Guided Music Generation and Editing via Single-Stage Flow Matching