MagiCodec 16k 50hz
MagiCodec is a single-layer, streaming codec model that delivers state-of-the-art audio quality and highly model-able discrete tokens.
Fonte do modelo
- Tipo
- Other
- Tamanho do arquivo
- 800 MB
- Versão
- vRevision 36b011f
- Atualizado
- 22 de set. de 2026
- Downloads
- 72
- Fonte
- Hugging Face
Trecho da fonte
MagiCodec is a single-layer, streaming codec model that delivers state-of-the-art audio quality and highly model-able discrete tokens.
Fontes
1 fonte
Fontes
1 fonteVerificado 5 de set.
Artefatos de modelo
1 artefato
Artefatos de modelo
1 artefatoTrechos de fonte
2 trechos
Trechos de fonte
2 trechos--- language: - en license: mit pipeline_tag: audio-to-audio tags: - pytorch --- # MagiCodec: Simple Masked Gaussian-Injected Audio Codec for High-Fidelity Reconstruction & Generation [](https://github.com/Ereboas/MagiCodec) [](https://arxiv.org/abs/2506.00385) [](https://ereboas.github.io/MagiCodec/) [](https://huggingface.co/Ereboas/MagiCodec_16k_50hz) MagiCodec is a **single-layer**, **streaming** codec model that delivers state-of-the-art audio quality *and* highly model-able discrete tokens. This is the code for the MagiCodec neural audio codec presented in the paper [MagiCodec: Simple **Ma**sked **G**aussian-**I**njected Audio **Codec** for High-Fidelity Reconstruction and Generation](https://arxiv.org/pdf/2506.00385) [[abs](https://arxiv.org/abs/2506.00385)]. ## ✨ Key Features - **Single‑layer streaming design** – lightweight causal Transformer that drops straight into audio‑native LLMs with minimal latency. - **Low bit‑rate & compute‑efficient** – <= 850 bps and <= 40 ms look‑ahead keep bandwidth and FLOPs tiny for on‑device use. - **Rich acoustic *and* semantic information** – captures fine‑grained detail plus high‑level semantics, achieving top scores in both waveform reconstruction and downstream tasks. ## 🎧 Samples To get a quick sense of our codec’s performance, please check out the [Sample Page](). **Comprehensive benchmarks covering a variety of baselines are available on this page.** ## 🛠️ Installation Our released code is based on a specific version ([2.3.6](https://github.com/Dao-AILab/flash-attention/releases/tag/v2.3.6)) of [FlashAttention](https://github.com/Dao-AILab/flash-attention/tree/92dd5703ecdb99aa4a4aee9817f28557907403a2). Please note that different (including newer or older) versions of flash-attention may introduce changes to the C/Python interfaces called by our custom ops. Compatibility issues may arise if you use a different version of flash-attention. We recommend creating a fresh conda environment for installation. ### Env Setup ```bash conda create -n MagiCodec python=3.9 -y conda activate MagiCodec ``` ### Basic R...
Source context: 72 downloads · 1 likes · Pipeline audio-to-audio · Repo Ereboas/MagiCodec_16k_50hz
