Audio-to-Audio
Safetensors
torch

πŸ—œοΈ ZipCodec

A 6.25 Hz, 0.80 kbit/s streaming neural audio codec based on WavLM.


▢️ Quickstart

See the readme at: https://github.com/lucadellalib/zipcodec


@ Citing

@article{dellalibera2026zipcodec,
    title   = {{ZipCodec}: Ultra-Low-Frame-Rate Streaming Speech Coding},
    author  = {Luca {Della Libera} and Cem Subakan and Mirco Ravanelli},
    journal = {arXiv preprint arXiv:2609.11642},
    year    = {2026},
}

πŸ“§ Contact

luca.dellalib@gmail.com


Downloads last month
169
Safetensors
Model size
0.8B params
Tensor type
F32
Β·
Inference Providers NEW
This model isn't deployed by any Inference Provider. πŸ™‹ Ask for provider support

Model tree for lucadellalib/zipcodec

Finetuned
(39)
this model

Papers for lucadellalib/zipcodec