MiMo-V2.5-ASR is a state-of-the-art end-to-end automatic speech recognition (ASR) model developed by the Xiaomi MiMo team. It is built to deliver accurate and robust transcription across Mandarin Chinese and English, multiple Chinese dialects, code-switched speech, song lyrics, knowledge-intensive content, noisy acoustic environments, and multi-speaker conversations. MiMo-V2.5-ASR achieves state-of-the-art results on a wide range of public benchmarks.
Automatic speech recognition systems are expected to faithfully transcribe speech signals that originate from diverse languages, dialects, accents, and domains, and that are captured under a wide variety of acoustic conditions. While conventional end-to-end models perform well on in-domain data, they still fall short of real-world requirements in challenging scenarios such as dialect mixing, code-switching, knowledge-intensive content, noisy environments, and multi-speaker conversations. Therefore, we present MiMo-V2.5-ASR, an end-to-end speech recognition model developed by the Xiaomi MiMo team. Through large-scale mid-training, high-quality supervised fine-tuning, and a novel reinforcement-learning algorithm, MiMo-V2.5-ASR achieves systematic improvements along the following dimensions:
- 🗣️ Chinese Dialects: Native support for Wu, Cantonese, Hokkien, Sichuanese, and more.
- 🔀 Code-Switch: Seamless Chinese–English code-switching transcription with no language tags required.
- 🎵 Song Recognition: High-precision lyrics transcription for Chinese and English songs, even with mixed accompaniment and vocals.
- 🔊 Noisy Environments: Robust recognition under heavy noise, far-field capture, and other adverse acoustic conditions.
- 👥 Multi-Speaker: Accurate transcription of overlapping, multi-party conversations such as meetings.
- 🇬🇧 Complex English Scenarios: Leading performance on the Open ASR Leaderboard for challenging English benchmarks such as AMI.
- 📚 Knowledge-Intensive Recognition: Precise recognition of classical poetry, technical terminology, personal names, place names, and other knowledge-dense material.
- 📝 Native Punctuation: Punctuation generated natively from prosody and semantics, delivering ready-to-use transcripts with no post-processing needed.
MiMo-V2.5-ASR has been evaluated across a broad set of benchmarks spanning standard Mandarin and English, Chinese dialects, lyric recognition, and internal business scenarios. The chart below summarizes the average performance of MiMo-V2.5-ASR across these scenarios.
For per-benchmark numbers and specific qualitative cases, please refer to our blog.
| Models | 🤗 Hugging Face |
|---|---|
| MiMo-Audio-Tokenizer | XiaomiMiMo/MiMo-Audio-Tokenizer |
| MiMo-V2.5-ASR | XiaomiMiMo/MiMo-V2.5-ASR |
| MiMo-Audio-Tokenizer (MLX) | mlx-community/MiMo-Audio-Tokenizer |
| MiMo-V2.5-ASR (MLX) | mlx-community/MiMo-V2.5-ASR-MLX |
pip install huggingface-hub
hf download XiaomiMiMo/MiMo-Audio-Tokenizer --local-dir ./models/MiMo-Audio-Tokenizer
hf download XiaomiMiMo/MiMo-V2.5-ASR --local-dir ./models/MiMo-V2.5-ASRThis repo also tracks an MLX path for Apple Silicon. The current integration uses ailuntx/mlx-audio main, which includes MiMo support:
pip install -r requirements-mlx.txtDownload the MLX checkpoints:
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-MLXRun a transcription:
python run_mimo_asr_mlx.py \
--model ./models/MiMo-V2.5-ASR-MLX \
--audio path/to/audio.wavPython API:
from mlx_audio.stt import load
model = load("./models/MiMo-V2.5-ASR-MLX")
result = model.generate("path/to/audio.wav", language="en")
print(result.text)Notes:
mlx-community/MiMo-V2.5-ASR-MLXresolvesmlx-community/MiMo-Audio-Tokenizerthroughmlx_manifest.json.- If you keep both directories locally, you can also pass
--audio-tokenizer-dir ./models/MiMo-Audio-Tokenizer. - This path will be updated to the upstream
mlx-audiorelease once MiMo support is merged there.
Spin up the MiMo-V2.5-ASR demo in minutes with the built-in Gradio app.
- Python 3.12
- CUDA >= 12.0
git clone https://github.com/XiaomiMiMo/MiMo-V2.5-ASR.git
cd MiMo-V2.5-ASR-MLX
pip install -r requirements.txt
pip install flash-attn==2.7.4.post1Note
If the compilation of flash-attn takes too long, you can download the precompiled wheel and install it manually:
pip install /path/to/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp312-cp312-linux_x86_64.whlpython run_mimo_asr.py
This launches a local Gradio interface for MiMo-V2.5-ASR. You can:
- Upload an audio file or record directly from your microphone.
- Optionally specify a language tag (Chinese / English / Auto) to bias the model for a specific language, or leave it to Auto for automatic language detection (recommended for code-switched speech).
- The demo calls the
asr_sft()interface under the hood.
To load the model and tokenizer automatically at startup, pass their paths on the command line:
python run_mimo_asr.py \
--model-path ./models/MiMo-V2.5-ASR \
--tokenizer-path ./models/MiMo-Audio-TokenizerOtherwise, enter the local paths for MiMo-Audio-Tokenizer and MiMo-V2.5-ASR in the Model Configuration tab, then start transcribing!
Basic usage with the asr_sft interface:
from src.mimo_audio.mimo_audio import MimoAudio
model = MimoAudio(
model_path="./models/MiMo-V2.5-ASR",
tokenizer_path="./models/MiMo-Audio-Tokenizer",
)
# Automatic language detection (recommended for code-switching)
text = model.asr_sft("path/to/audio.wav")
print(text)
# With explicit language tag
text_zh = model.asr_sft("path/to/audio.wav", audio_tag="<chinese>")
text_en = model.asr_sft("path/to/audio.wav", audio_tag="<english>")@misc{coreteam2026mimov25asr,
title={MiMo-V2.5-ASR: Robust Speech Recognition Across Languages, Dialects, and Complex Acoustic Scenarios},
author={LLM-Core-Team Xiaomi},
year={2026},
url={https://github.com/XiaomiMiMo/MiMo-V2.5-ASR},
}Please contact us at mimo@xiaomi.com or open an issue if you have any questions.