Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
mispeech
/
midashenglm-7b
like
46
Follow
Horizon Team, Xiaomi MiLM Plus
57
Audio-Text-to-Text
Safetensors
5 languages
midashenglm
multimodal
audio-language-model
audio
custom_code
arxiv:
2508.03983
License:
apache-2.0
Model card
Files
Files and versions
xet
Community
1
main
midashenglm-7b
/
fig
Ctrl+K
Ctrl+K
2 contributors
History:
1 commit
jimbozhang
Upload figures
7c3ae10
verified
12 days ago
Framework-1.png
Safe
3.23 MB
xet
Upload figures
12 days ago
acavcaps-1.png
Safe
1.85 MB
xet
Upload figures
12 days ago
batchsize_1_comparison_7b-1.png
Safe
350 kB
xet
Upload figures
12 days ago
capabilities_plot_7b-1.png
Safe
1.39 MB
xet
Upload figures
12 days ago
pretraining_sampling_rates-1.png
Safe
1.8 MB
xet
Upload figures
12 days ago