Hugging Face
Models
Datasets
Spaces
Community
Docs
Enterprise
Pricing
Log In
Sign Up
mispeech
/
midashenglm-7b-0804-bf16
like
0
Follow
Horizon Team, Xiaomi MiLM Plus
82
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-0804-bf16
/
fig
8.61 MB
2 contributors
History:
1 commit
zhoukz
Sync from mispeech/midashenglm-7b
e6e1644
unverified
3 months ago
Framework-1.png
Safe
3.23 MB
xet
Sync from mispeech/midashenglm-7b
3 months ago
acavcaps-1.png
Safe
1.85 MB
xet
Sync from mispeech/midashenglm-7b
3 months ago
batchsize_1_comparison_7b-1.png
Safe
350 kB
xet
Sync from mispeech/midashenglm-7b
3 months ago
capabilities_plot_7b-1.png
Safe
1.39 MB
xet
Sync from mispeech/midashenglm-7b
3 months ago
pretraining_sampling_rates-1.png
Safe
1.8 MB
xet
Sync from mispeech/midashenglm-7b
3 months ago