Downloads · 30 days
342
8% of all-time downloads
focalcodec_25hz
lucadellalib/focalcodec_25hz
focalcodec_25hz is a audio-to-audio model from lucadellalib. Use it for the audio-to-audio task on the model card, and read the license before you ship it in a product. It is set up for pytorch. The card lists the license as apache-2.0.
A low-bitrate single-codebook 16 / 24 kHz speech codec based on focal modulation.
All-time downloads
4.3K
Public
Parameters
144M
577 MB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors577 MB · 100%
Parameter types
How the weights are stored.
F32144M · 100%
Base models
Datasets
Model card
From the Hugging Face model README
⚡ FocalCodec
A low-bitrate single-codebook 16 / 24 kHz speech codec based on focal modulation.
This repository contains the 25 Hz checkpoint trained on LibriTTS 960, as described in the preprints.
-
📜 Preprints:
-
🌐 Project Page: https://lucadellalib.github.io/focalcodec-web/
▶️ 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
- Task
- Audio-to-Audio
- Library
- pytorch
- License
- apache-2.0
- Created
- Feb 11, 2025
- Updated
- Sep 22, 2025