k2-fsa

AI & ML interests

FSA/FST algorithms, differentiable, with PyTorch compatibility. Automatic speech recognition

Recent Activity

yfyeung  authored a paper about 21 hours ago

MMAE: A Massive Multitask Audio Editing Benchmark

yfyeung  authored a paper 5 days ago

UAT: Unified Audio-Text Diffusion for Audio Generation, Editing, and Captioning

csukuangfj  updated a Space 6 days ago

k2-fsa/automatic-speech-recognition

View all activity

Team members 17