A small audio model by Xiaomi, supporting auto-text, text-audio and audio-audio.
Specs
Params7B
LicenseMIT
Tags
modelsmodels/llms/multi-modalmodels/audio-generationartifacts/15
RAM score
—
Hugging Face Downloads
14.8K
last 30d
186.7K
all time
HF Likes
160
Relative Adoption Metric contextualizes downloads against the model's size bucket.
VAIL Fingerprint
005c:007b:00a0:0129:0168:02c6:0492:4d02
Explore other models with behavioral similarity to MiMo-Audio-7B-Instruct.
Related Models
