Aller au contenu
ModelPrésentéExterne
Télécharger

Focalcodec 50hz 4k Causal

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

TypeOtherModèle de basemicrosoft/wavlm-largeVersionRevision f60218eBClasse

Source du modèle

Type
Other
Taille du fichier
950 MB
Modèle de base
microsoft/wavlm-large
Version
vRevision f60218e
Mis à jour
22 sept. 2026
Téléchargements
2,1 k
Source
Hugging Face

Extrait de la source

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

Sources

1 source
Hugging FacePrincipalVersion f60218e9628b214f2fa39f9c3d0b7c91090159f2
huggingface.co/lucadellalib/focalcodec_50hz_4k_causal/tree/f60218e9628b214f2fa39f9c3d0b7c91090159f2

Vérifié 5 sept.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · 950 MB · SHA-256 5bda5565d496…6808 · Hugging Face

Download file

Extraits de sources

2 extraits

--- license: apache-2.0 library_name: torch base_model: - microsoft/wavlm-large pipeline_tag: audio-to-audio --- # ⚡ FocalCodec A low-bitrate single-codebook 16 / 24 kHz speech codec based on [focal modulation](https://arxiv.org/abs/2203.11926). This repository contains the **50 Hz causal checkpoint with a codebook size of 4096** trained on **Libri-Light**, as described in the preprints. - 📜 **Preprints**: - [FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks](https://arxiv.org/abs/2502.04465) - [FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation](https://arxiv.org/abs/2509.16195) - 🌐 **Project Page**: https://lucadellalib.github.io/focalcodec-web/ - 💾 **GitHub**: https://github.com/lucadellalib/focalcodec <img src="focalcodec-stream.png" width="700"> --------------------------------------------------------------------------------------------------------- ## ▶️ 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 [[email protected]](mailto:[email protected]) ---------------------------------------------------------------------------------------------------------

Source context: 2069 downloads · 1 likes · Pipeline audio-to-audio · Library torch · Repo lucadellalib/focalcodec_50hz_4k_causal