Audio-to-Audio
Safetensors
torch

⚡ FocalCodec

A low-bitrate single-codebook 16 / 24 kHz speech codec based on focal modulation.

This repository contains the 50 Hz checkpoint trained on LibriTTS 960, as described in the preprints.


▶️ Quickstart

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


@ Citing

@article{dellalibera2025focalcodec,
    title   = {{FocalCodec}: Low-Bitrate Speech Coding via Focal Modulation Networks},
    author  = {Luca {Della Libera} and Francesco Paissan and Cem Subakan and Mirco Ravanelli},
    journal = {arXiv preprint arXiv:2502.04465},
    year    = {2025},
}

@article{dellalibera2025focalcodecstream,
    title   = {{FocalCodec-Stream}: Streaming Low-Bitrate Speech Coding via Causal Distillation},
    author  = {Luca {Della Libera} and Cem Subakan and Mirco Ravanelli},
    journal = {arXiv preprint arXiv:2509.16195},
    year    = {2025},
}

📧 Contact

luca.dellalib@gmail.com


Downloads last month
295
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for lucadellalib/focalcodec_50hz

Finetuned
(18)
this model

Dataset used to train lucadellalib/focalcodec_50hz

Collection including lucadellalib/focalcodec_50hz