Hugging Face's logo

OpenMOSS-Team
/
MOSS-Audio-4B-Thinking

Audio-Text-to-Text
Safetensors
English
Chinese
moss_audio
audio
speech
music
understanding
multimodal
reasoning
chain-of-thought
custom_code
Model card Files
xet
 Community
1
New discussion

Japanese/Korean Support && Recommend Models for Subtitle Transcription with Timestamps

2
#1 opened about 13 hours ago by
nemozxy123