mlx-community
/

MiMo-Audio-Tokenizer

@@ -1,202 +1,33 @@
 ---
-license: mit
-base_model: XiaomiMiMo/MiMo-Audio-Tokenizer
 tags:
 - mlx
-- speech
 - audio-tokenizer
-- automatic-speech-recognition
 ---
-<div align="center">
-  <picture>
-    <source srcset="https://github.com/XiaomiMiMo/MiMo-VL/raw/main/figures/Xiaomi_MiMo_darkmode.png?raw=true" media="(prefers-color-scheme: dark)">
-    <img src="https://github.com/XiaomiMiMo/MiMo-VL/raw/main/figures/Xiaomi_MiMo.png?raw=true" width="60%" alt="Xiaomi-MiMo" />
-  </picture>
-</div>
-<h3 align="center">
-  <b>
-    <span>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━</span>
-    <br/>
-    MiMo Audio: Audio Language Models are Few-Shot Learners
-    <br/>
-    <span>━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━</span>
-    <br/>
-  </b>
-</h3>
-<br/>
-<div align="center" style="line-height: 1;">
-  |
-  <a href="https://huggingface.co/collections/XiaomiMiMo/mimo-audio-68cc7202692c27dae881cce0" target="_blank">🤗 HuggingFace</a>
-  &nbsp;|
-  <a href="https://github.com/XiaomiMiMo/MiMo-Audio/blob/main/MiMo-Audio-Technical-Report.pdf" target="_blank">📄 Paper</a>
-  &nbsp;|
-  <a href="https://xiaomimimo.github.io/MiMo-Audio-Demo" target="_blank">📰 Blog</a>
-  &nbsp;|
-  <a href="https://huggingface.co/spaces/XiaomiMiMo/mimo_audio_chat" target="_blank">🔥 Online Demo</a>
-  &nbsp;|
-  <a href="https://github.com/XiaomiMiMo/MiMo-Audio-Eval" target="_blank">📊 MiMo-Audio-Eval</a>
-  &nbsp;|
-  <br/>
-</div>
-<br/>
-## MLX Conversion
-This repository is the MLX export used by `mlx-community/MiMo-V2.5-ASR-MLX`.
-- Default precision is `fp32`.
-- This export keeps the encoder and RVQ path used by MiMo ASR.
-- Decoder and vocoder weights are omitted here because they are not used in the ASR pipeline.
-- The published MLX weights are therefore an ASR-focused inference subset, not a byte-for-byte mirror of the full official tokenizer release.
-## MLX Usage
-Current MLX usage is documented in:
-- [ailuntx/MiMo-V2.5-ASR-MLX](https://github.com/ailuntx/MiMo-V2.5-ASR-MLX)
-- [ailuntx/MiMo-Audio-Tokenizer-MLX](https://github.com/ailuntx/MiMo-Audio-Tokenizer-MLX)
-Install the current MLX path:
-```bash
-pip install git+https://github.com/ailuntx/mlx-audio@feat/mimo-v25-asr
-```
-Download the tokenizer:
-```bash
-hf download mlx-community/MiMo-Audio-Tokenizer --local-dir ./models/MiMo-Audio-Tokenizer
-```
-This tokenizer is consumed automatically by:
-- [mlx-community/MiMo-V2.5-ASR-MLX](https://huggingface.co/mlx-community/MiMo-V2.5-ASR-MLX)
-If you are following the standalone GitHub path, clone the MiMo ASR fork and use its helper script:
 ```bash
 git clone https://github.com/ailuntx/MiMo-V2.5-ASR-MLX.git
 cd MiMo-V2.5-ASR-MLX
-python run_mimo_asr_mlx.py \
-    --model ./models/MiMo-V2.5-ASR-MLX \
-    --audio path/to/audio.wav
-```
-Notes:
-- `mlx-community/MiMo-V2.5-ASR-MLX` resolves this tokenizer through `mlx_manifest.json`.
-- This repo is not meant to be the primary user entrypoint; use the MiMo ASR repo above for end-to-end transcription.
-## 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.
-<p align="center">
-  <img width="95%" src="https://github.com/XiaomiMiMo/MiMo-Audio/blob/main/assets/Results.png?raw=true">
-</p>
-## 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.
-For clarity: the official Xiaomi release above describes the full tokenizer stack. This MLX repository publishes the encoder/RVQ subset used by `MiMo-V2.5-ASR`, which is why the Hugging Face file summary for this repo is about `0.64B` parameters instead of the full `1.2B`.
-<p align="center">
-  <img width="95%" src="https://github.com/XiaomiMiMo/MiMo-Audio/blob/main/assets/tokenizer.png?raw=true">
-</p>
-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
-<p align="center">
-  <img width="95%" src="https://github.com/XiaomiMiMo/MiMo-Audio/blob/main/assets/architecture.png?raw=true">
-</p>
-## Explore MiMo-Audio Now! 🚀🚀🚀
-- 🎧 **Try the Hugging Face demo:** [MiMo-Audio Demo](https://huggingface.co/spaces/XiaomiMiMo/mimo_audio_chat)
-- 📰 **Read the Official Blog:** [MiMo-Audio Blog](https://xiaomimimo.github.io/MiMo-Audio-Demo)
-- 📄 **Dive into the Technical Report:** [MiMo-Audio Technical Report](https://github.com/XiaomiMiMo/MiMo-Audio/blob/main/MiMo-Audio-Technical-Report.pdf)
-## Model Download
-| Models   | 🤗 Hugging Face |
-|-------|-------|
-| MiMo-Audio-Tokenizer | [XiaomiMiMo/MiMo-Audio-Tokenizer](https://huggingface.co/XiaomiMiMo/MiMo-Audio-Tokenizer) |
-| MiMo-Audio-7B-Base | [XiaomiMiMo/MiMo-Audio-7B-Base](https://huggingface.co/XiaomiMiMo/MiMo-Audio-7B-Base) |
-| MiMo-Audio-7B-Instruct | [XiaomiMiMo/MiMo-Audio-7B-Instruct](https://huggingface.co/XiaomiMiMo/MiMo-Audio-7B-Instruct) |
-## Getting Started
-Spin up the MiMo-Audio demo in minutes with the built-in Gradio app.
-### Installation
-```sh
-git clone https://github.com/XiaomiMiMo/MiMo-Audio.git
-cd MiMo-Audio
-pip install -e .
-```
-### Run the demo
-```sh
-python run_mimo_audio.py
-```
-This launches a local Gradio interface where you can try MiMo-Audio interactively.
-<p align="center">
-  <img width="95%" src="https://github.com/XiaomiMiMo/MiMo-Audio/blob/main/assets/demo_ui.jpg?raw=true">
-</p>
-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`](https://github.com/XiaomiMiMo/MiMo-Audio/blob/main/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`](https://github.com/XiaomiMiMo/MiMo-Audio/blob/main/inference_example_sft.py)
-## Evaluation Toolkit
-Full evaluation suite are available at 🌐[MiMo-Audio-Eval](https://github.com/XiaomiMiMo/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.
-## Validation
-This MLX export was validated locally with `mlx-audio-swift` and `MiMo-V2.5-ASR-MLX`.
-- Smoke samples: `intention.wav`, `conversational_a.wav`, `noisy_audio.wav`
-- Release precision: `fp32`
-- Lower-precision internal experiments were kept out of the Hub release to avoid frontend drift and naming ambiguity
-## Citation
-```bibtex
-@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 [mimo@xiaomi.com](mailto:mimo@xiaomi.com) or open an issue if you have any questions.

 ---
+license: apache-2.0
+library_name: mlx
+base_model:
+- XiaomiMiMo/MiMo-V2.5-ASR
 tags:
 - mlx
+- apple-silicon
 - audio-tokenizer
+- mimo
 ---
+Part of the [MiMo V2.5 ASR MLX](https://huggingface.co/collections/mlx-community/mimo-v25-asr-6a02cb99466d6a36475a4d70) collection.
+# MiMo Audio Tokenizer (MLX)
+Audio tokenizer assets for the community MLX conversion of [XiaomiMiMo/MiMo-V2.5-ASR](https://github.com/XiaomiMiMo/MiMo-V2.5-ASR).
+## Quick Start
 ```bash
 git clone https://github.com/ailuntx/MiMo-V2.5-ASR-MLX.git
 cd MiMo-V2.5-ASR-MLX
+pip install git+https://github.com/ailuntx/mlx-audio.git
+hf download mlx-community/MiMo-Audio-Tokenizer --local-dir ./models/MiMo-Audio-Tokenizer
+hf download mlx-community/MiMo-V2.5-ASR-MLX --local-dir ./models/MiMo-V2.5-ASR-MLX
+python run_mimo_asr_mlx.py --model ./models/MiMo-V2.5-ASR-MLX --audio path/to/audio.wav
 ```
+## Notes
+This repository is a required companion asset for the MiMo ASR MLX model repositories. Keep it next to the model checkpoint or pass its path through the runtime configuration.