lucadellalib/dycast
Audio-to-Audio • Updated • 68 • 4
Luca Della Libera
lucadellalib
AI & ML interests
Speech processing, Audio tokenization, ASR, Continual learning, Reinforcement learning
Recent Activity
authored a paper 30 days ago
WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation upvoted a paper about 2 months ago
Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization updated a collection about 2 months ago
focalcodecOrganizations
lucadellalib/focalcodec_12_5hz
Audio-to-Audio • Updated • 586 • 2
lucadellalib/focalcodec_25hz
Audio-to-Audio • Updated • 195 • 1
lucadellalib/focalcodec_50hz
Audio-to-Audio • Updated • 1.46k • 1
lucadellalib/focalcodec_50hz_65k_causal
Audio-to-Audio • Updated • 12
lucadellalib/focalcodec_50hz_4k_causal
Audio-to-Audio • Updated • 214
lucadellalib/focalcodec_50hz_2k_causal
Audio-to-Audio • Updated • 1.04k
lucadellalib/discrete-wavlm-codec
Updated