MiMo-Audio
MiMo-Audio: Audio Language Models are Few-Shot Learners
File Explorer
Download Latest Version (.zip)- architecture.png
- demo_ui.jpg
- Results.png
- tokenizer.png
- 0013_000139.wav
- 0013_000200.wav
- 0013_000559.wav
- 0013_000769.wav
- 0013_000963.wav
- 0013_001142.wav
- 0019_000139.wav
- 0019_000559.wav
- 0019_000769.wav
- 0019_000963.wav
- 0019_001142.wav
- prompt_speech_en_m.wav
- prompt_speech_en_w.wav
- prompt_speech_zh_m.wav
- prompt_speech_zh_w.wav
- spoken_dialogue_assistant_turn_1.wav
- δ»ε€©ε€©ζ°ε¦δ½.mp3
- εδΊ¬.mp3
- mimo_audio.py
- modeling_mimo_audio.py
- process_speechdata.py
- templates.py
- __init__.py
- configuration_audio_tokenizer.py
- modeling_audio_tokenizer.py
- modeling_rope_utils.py
- quantization.py
- .gitignore
- inference_example_pretrain.py
- inference_example_sft.py
- LICENSE
- MiMo-Audio-Technical-Report.pdf
- README.md
- requirements.txt
- run_mimo_audio.py
# Installation Guide
git clone https://github.com/XiaomiMiMo/MiMo-Audio
Downloads the entire project code from GitHub to your computer.
cd MiMo-Audio
Moves into the project folder you just downloaded.
2. Official Install Script
Easy Recommended- Python 3 Python is required to use pip.
pip install huggingface-hub
Installs the package published on PyPI directly β no need to clone the source.
pip install flash-attn==2.7.4.post1
Installs the package published on PyPI directly β no need to clone the source.
Pulled directly from this repo's README.
3. Python
Easypip install huggingface-hub
Installs the package published on PyPI directly β no need to clone the source.
pip install -r requirements.txt
Installs the Python libraries listed in requirements.txt (or similar).
pip install flash-attn==2.7.4.post1
Installs the package published on PyPI directly β no need to clone the source.
> pip install /path/to/flash_attn-2.7.4.post1+cu12torch2.6cxx11abiFALSE-cp312-cp312-linux_x86_64.whl
Installs the Python libraries listed in requirements.txt (or similar).
Pulled directly from this repo's README.
