MioCodec 25Hz 44.1kHz v2
简介
核心亮点
- 支持 44.1kHz 高保真音频重建
- 低采样率表征,大幅降低数据带宽
- MIT 协议开源,商业部署灵活便捷
- 适用于语音压缩与实时音频传输
使用方法
# 安装 Hugging Face transformers
pip install transformers torch
# 使用 transformers 加载模型
from transformers import AutoModel, AutoTokenizer
model = AutoModel.from_pretrained("Aratako/MioCodec-25Hz-44.1kHz-v2")
tokenizer = AutoTokenizer.from_pretrained("Aratako/MioCodec-25Hz-44.1kHz-v2")
Hugging Face 下载
我们推荐使用命令行或者 Hugging Face Hub SDK 来进行模型的下载。
操作指引:在下载前,请先通过如下命令安装 huggingface_hub:
pip install -U huggingface_hub
命令行下载
下载完整模型库
huggingface-cli download Aratako/MioCodec-25Hz-44.1kHz-v2
下载单个文件到指定本地文件夹(以下载 config.json 到当前路径下 ./dir 目录为例)
huggingface-cli download Aratako/MioCodec-25Hz-44.1kHz-v2 config.json --local-dir ./dir
SDK 下载
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('Aratako/MioCodec-25Hz-44.1kHz-v2')
Git 下载
请确保 lfs 已经被正确安装
git lfs install
git clone https://huggingface.co/Aratako/MioCodec-25Hz-44.1kHz-v2
如果您希望跳过 lfs 大文件下载,可以使用如下命令
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/Aratako/MioCodec-25Hz-44.1kHz-v2
模型文件托管在 Hugging Face Hub,使用 HF CLI / SDK / Git 直接下载,不经过本站。
PyTorch / Transformers 使用
安装 Transformers
pip install -U transformers torch
模型加载和推理
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained('Aratako/MioCodec-25Hz-44.1kHz-v2')
tokenizer = AutoTokenizer.from_pretrained('Aratako/MioCodec-25Hz-44.1kHz-v2')
模型下载
我们推荐使用命令行或者 ModelScope SDK 来进行模型的下载。
操作指引:在下载前,请先通过如下命令安装 ModelScope:
pip install modelscope
命令行下载
下载完整模型库
modelscope download --model Aratako/MioCodec-25Hz-44.1kHz-v2
下载单个文件到指定本地文件夹(以下载 README.md 到当前路径下 dir 目录为例)
modelscope download --model Aratako/MioCodec-25Hz-44.1kHz-v2 README.md --local_dir ./dir
SDK 下载
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('Aratako/MioCodec-25Hz-44.1kHz-v2')
Git 下载
请确保 lfs 已经被正确安装
git lfs install
git clone https://www.modelscope.cn/Aratako/MioCodec-25Hz-44.1kHz-v2.git
如果您希望跳过 lfs 大文件下载,可以使用如下命令
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/Aratako/MioCodec-25Hz-44.1kHz-v2.git
ModelScope 模型页直接下载模型文件;无需将模型文件放在本站服务器。
Notebook 快速开发
下载并安装 ModelScope library
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html
模型加载和推理
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks
p = pipeline('text-generation', 'Aratako/MioCodec-25Hz-44.1kHz-v2')
完整文档
---
license: mit
language:
- en
- ja
- nl
- fr
- de
- it
- pl
- pt
- es
- ko
- zh
tags:
- speech
- audio
- tokenizer
datasets:
- sarulab-speech/mls_sidon
- mythicinfinity/Libriheavy-HQ
- nvidia/hifitts-2
pipeline_tag: audio-to-audio
base_model:
- Aratako/MioCodec-25Hz-24kHz
---
MioCodec-25Hz-44.1kHz-v2: Lightweight Neural Audio Codec for Efficient Spoken Language Modeling

MioCodec-25Hz-44.1kHz-v2 is an upsampled, high-fidelity version of the MioCodec-25Hz-24kHz model.
By integrating an UpsamplerBlock inspired by Inworld TTS-1 into the decoder, this model reconstructs 44.1 kHz audio from the standard 25 Hz token stream.
🌟 What's New in v2
This model is a fine-tuned version of MioCodec-25Hz-24kHz with the following architectural enhancements:
- 44.1 kHz Output: Achieves higher audio fidelity compared to the base 24 kHz model.
- UpsamplerBlock + SnakeBeta: We adopted the UpsamplerBlock architecture from Inworld TTS-1 and enhanced it by integrating SnakeBeta activations. This combination allows the decoder to effectively predict and generate high-frequency components, enabling clear 44.1 kHz reconstruction from the lower-resolution input.
- Token Compatibility: During fine-tuning, the content branch was frozen. This means the discrete tokens generated by this model are identical to those from
MioCodec-25Hz-24kHz. You can take any TTS model trained on the 24kHz tokens and simply swap the codec to this v2 model during inference to instantly upgrade the audio quality to 44.1 kHz.
📊 Model Comparison
| Model | Token Rate | Vocab Size | Bit Rate | Sample Rate | SSL Encoder | Vocoder | Parameters | Highlights |
| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :--- |
| MioCodec-25Hz-44.1kHz-v2 | 25 Hz | 12,800 | 341 bps | 44.1 kHz | WavLM-base+ | - (iSTFTHead) | 133M | Fast inference, good quality |
| MioCodec-25Hz-24kHz | 25 Hz | 12,800 | 341 bps | 24 kHz | WavLM-base+ | - (iSTFTHead) | 132M | Lightweight, fast inference |
| MioCodec-25Hz-44.1kHz | 25 Hz | 12,800 | 341 bps | 44.1 kHz | WavLM-base+ | MioVocoder (Jointly Tuned) | 118M (w/o vocoder) | High-quality, high sample rate |
| kanade-25hz | 25 Hz | 12,800 | 341 bps | 24 kHz | WavLM-base+ | Vocos 24kHz | 118M (w/o vocoder) | Original 25Hz model |
| kanade-12.5hz | 12.5 Hz | 12,800 | 171 bps | 24 kHz | WavLM-base+ | Vocos 24kHz | 120M (w/o vocoder) | Original 12.5Hz model |
🚀 Quick Start
Installation
# Install via pip
pip install git+https://github.com/Aratako/MioCodec
Or using uv
uv add git+https://github.com/Aratako/MioCodecBasic Inference
Basic usage for encoding and decoding audio:
from miocodec import MioCodecModel, load_audio
import soundfile as sf
1. Load model
model = MioCodecModel.from_pretrained("Aratako/MioCodec-25Hz-44.1kHz-v2").eval().cuda()
2. Load audio
waveform = load_audio("input.wav", sample_rate=model.config.sample_rate).cuda()
3. Encode Audio
features = model.encode(waveform)
4. Decode to Waveform (directly, no vocoder needed)
resynth = model.decode(
content_token_indices=features.content_token_indices,
global_embedding=features.global_embedding,
)
5. Save
sf.write("output.wav", resynth.cpu().numpy(), model.config.sample_rate)Voice Conversion (Zero-shot)
MioCodec allows you to swap speaker identities by combining the content tokens of a source with the global embedding of a reference.
source = load_audio("source_content.wav", sample_rate=model.config.sample_rate).cuda()
reference = load_audio("target_speaker.wav", sample_rate=model.config.sample_rate).cuda()
Perform conversion
vc_wave = model.voice_conversion(source, reference)
sf.write("converted.wav", vc_wave.cpu().numpy(), model.config.sample_rate)📜 Acknowledgements
- Codec Architecture: Based on the brilliant work of kanade-tokenizer.
- Decoder Design: Inspired by XCodec2 and Inworld TTS-1.
🖊️ Citation
@misc{miocodec-25hz-44.1khz-v2,
author = {Chihiro Arata},
title = {MioCodec: High-Fidelity Neural Audio Codec for Efficient Spoken Language Modeling},
year = {2026},
publisher = {Hugging Face},
journal = {Hugging Face repository},
howpublished = {\url{https://huggingface.co/Aratako/MioCodec-25Hz-44.1kHz-v2}}
}