lucadellalib/dycast
Audio-to-Audio • Updated • 56 • 4
Luca Della Libera
lucadellalib
AI & ML interests
Speech processing, Audio tokenization, ASR, Continual learning, Reinforcement learning
Recent Activity
authored a paper about 1 month ago
WavSLM: Single-Stream Speech Language Modeling via WavLM Distillation upvoted a paper 2 months ago
Beyond Fixed Frames: Dynamic Character-Aligned Speech Tokenization updated a collection 2 months ago
focalcodecOrganizations
lucadellalib/focalcodec_12_5hz
Audio-to-Audio • Updated • 2.06k • 2
lucadellalib/focalcodec_25hz
Audio-to-Audio • Updated • 214 • 1
lucadellalib/focalcodec_50hz
Audio-to-Audio • Updated • 1.45k • 2
lucadellalib/focalcodec_50hz_65k_causal
Audio-to-Audio • Updated • 26
lucadellalib/focalcodec_50hz_4k_causal
Audio-to-Audio • Updated • 163
lucadellalib/focalcodec_50hz_2k_causal
Audio-to-Audio • Updated • 772
lucadellalib/discrete-wavlm-codec
Updated