XiaomiMiMo / MiMo-Audio-Tokenizer

━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
MiMo Audio: Audio Language Models are Few-Shot Learners
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

Introduction

Existing audio language models typically rely on task-specific fine-tuning to accomplish particular audio tasks. In contrast, humans are able to generalize to new audio tasks with only a few examples or simple instructions. GPT-3 has shown that scaling next-token prediction pretraining enables strong generalization capabilities in text, and we believe this paradigm is equally applicable to the audio domain. By scaling MiMo-Audio's pretraining data to over one hundred million of hours, we observe the emergence of few-shot learning capabilities across a diverse set of audio tasks. We develop a systematic evaluation of these capabilities and find that MiMo-Audio-7B-Base achieves SOTA performance on both speech intelligence and audio understanding benchmarks among open-source models. Beyond standard metrics, MiMo-Audio-7B-Base generalizes to tasks absent from its training data, such as voice conversion, style transfer, and speech editing. MiMo-Audio-7B-Base also demonstrates powerful speech continuation capabilities, capable of generating highly realistic talk shows, recitations, livestreaming and debates. At the post-training stage, we curate a diverse instruction-tuning corpus and introduce thinking mechanisms into both audio understanding and generation. MiMo-Audio-7B-Instruct achieves open-source SOTA on audio understanding benchmarks, spoken dialogue benchmarks and instruct-TTS evaluations, approaching or surpassing closed-source models.

Architecture

MiMo-Audio-Tokenizer

MiMo-Audio-Tokenizer is a 1.2B-parameter Transformer operating at 25 Hz. It employs an eight-layer RVQ stack to generate 200 tokens per second. By jointly optimizing semantic and reconstruction objectives, we train MiMo-Audio-Tokenizer from scratch on a 10-million-hour corpus, achieving superior reconstruction quality and facilitating downstream language modeling.

MiMo-Audio couples a patch encoder, an LLM, and a patch decoder to improve modeling efficiency for high-rate sequences and bridge the length mismatch between speech and text. The patch encoder aggregates four consecutive time steps of RVQ tokens into a single patch, downsampling the sequence to a 6.25 Hz representation for the LLM. The patch decoder autoregressively generates the full 25 Hz RVQ token sequence via a delayed-generation scheme.

MiMo-Audio

Explore MiMo-Audio Now! 🚀🚀🚀

• 🎧 Try the Hugging Face demo: MiMo-Audio Demo
• 📰 Read the Official Blog: MiMo-Audio Blog
• 📄 Dive into the Technical Report: MiMo-Audio Technical Report

Model Download

Getting Started

Spin up the MiMo-Audio demo in minutes with the built-in Gradio app.

Installation

git clone https://github.com/XiaomiMiMo/MiMo-Audio.git
cd MiMo-Audio
pip install -e .

Run the demo

python run_mimo_audio.py

This launches a local Gradio interface where you can try MiMo-Audio interactively.

Enter the local paths for MiMo-Audio-Tokenizer and MiMo-Audio-7B-Instruct , then enjoy the full functionality of MiMo-Audio!

Inference Scripts

Base Model

We provide an example script to explore the in-context learning capabilities of MiMo-Audio-7B-Base .
See: inference_example_pretrain.py

Instruct Model

To try the instruction-tuned model MiMo-Audio-7B-Instruct , use the corresponding inference script.
See: inference_example_sft.py

Evaluation Toolkit

Full evaluation suite are available at 🌐 MiMo-Audio-Eval .

This toolkit is designed to evaluate MiMo-Audio and other recent audio LLMs as mentioned in the paper. It provides a flexible and extensible framework, supporting a wide range of datasets, tasks, and models.

Citation

@misc{coreteam2025mimoaudio,
      title={MiMo-Audio: Audio Language Models are Few-Shot Learners}, 
      author={LLM-Core-Team Xiaomi},
      year={2025},
      url={GitHub - XiaomiMiMo/MiMo-Audio}, 
}

Contact

Please contact us at [email protected] or open an issue if you have any questions.